chore: bump version to 1.7.12

- Added blackbox provider to APIKEY_PROVIDERS in providers.ts
- Added blackbox pricing entries in pricing.ts
- Added blackbox to ProviderId typedef in types.ts
- Added blackbox models endpoint config in models/route.ts

.agents/workflows/deploy-vps.md

@@ -0,0 +1,55 @@
+---
+description: Deploy the latest OmniRoute code to the Akamai VPS (69.164.221.35) via npm
+---
+
+# Deploy to VPS Workflow
+
+Deploy OmniRoute to the production VPS using Node.js + PM2 (no Docker).
+
+**VPS:** `69.164.221.35` (Akamai, Ubuntu 24.04, 1GB RAM + 2.5GB swap)
+**App path:** `/opt/omniroute-app`
+**Process manager:** PM2 (`omniroute`)
+**Port:** `20128`
+
+## Steps
+
+### 1. Push to GitHub
+
+Ensure all changes are committed and pushed:
+
+```bash
+git push origin main
+```
+
+### 2. SSH into VPS, pull latest code, rebuild, and restart
+
+// turbo-all
+
+```bash
+ssh root@69.164.221.35 "
+  cd /opt/omniroute-app &&
+  git fetch origin &&
+  git reset --hard origin/main &&
+  export NODE_OPTIONS='--max-old-space-size=1536' &&
+  npm install --no-audit --no-fund &&
+  npm run build &&
+  pm2 restart omniroute &&
+  pm2 save &&
+  echo '✅ Deploy complete!'
+"
+```
+
+### 3. Verify the deployment
+
+```bash
+ssh root@69.164.221.35 "pm2 list && curl -s -o /dev/null -w 'HTTP %{http_code}' http://localhost:20128/"
+```
+
+Expected: PM2 shows `online`, HTTP returns `307` (redirect to login).
+
+## Notes
+
+- The VPS has only 1GB RAM. `NODE_OPTIONS='--max-old-space-size=1536'` uses swap for the build.
+- PM2 is configured with `pm2 startup` to auto-restart on reboot.
+- The `.env` file is at `/opt/omniroute-app/.env` (copied from the old Docker setup at `/opt/omniroute/.env`).
+- Nginx proxies `omniroute.online` → `localhost:20128`.

.agents/workflows/generate-release.md

@@ -0,0 +1,78 @@
+---
+description: Create a new release, bump version up to 1.x.10 threshold, update changelog, and manage Pull Requests
+---
+
+# Generate Release Workflow
+
+Bump version, finalize CHANGELOG, commit, tag, push, publish to npm, and create GitHub release.
+
+## Steps
+
+### 1. Determine new version
+
+Check current version in `package.json` and increment the patch number:
+
+```bash
+grep '"version"' package.json
+```
+
+Version format: `1.x.y` — increment `y` for patch, `x` for minor (threshold: y=10 triggers x+1).
+
+### 2. Finalize CHANGELOG.md
+
+Replace `[Unreleased]` header with the new version and date:
+
+```markdown
+## [1.x.y] — YYYY-MM-DD
+```
+
+### 3. Bump version in package.json
+
+```bash
+sed -i 's/"version": "OLD"/"version": "NEW"/' package.json
+```
+
+### 4. Stage, commit, and tag
+
+// turbo-all
+
+```bash
+git add -A
+git commit -m "feat(release): vX.Y.Z — summary of changes"
+git tag -a vX.Y.Z -m "Release vX.Y.Z — summary"
+```
+
+### 5. Push to GitHub
+
+```bash
+git push origin main
+git push origin vX.Y.Z
+```
+
+### 6. Publish to npm
+
+```bash
+npm publish
+```
+
+Wait for completion (prepublishOnly runs `npm run build:cli` automatically).
+
+### 7. Create GitHub release
+
+```bash
+gh release create vX.Y.Z --title "Release vX.Y.Z" --notes-file /tmp/release_notes.md
+```
+
+### 8. Deploy to VPS (if requested)
+
+See `/deploy-vps` workflow for Akamai VPS or use npm for local VPS:
+
+```bash
+ssh root@<VPS_IP> "npm install -g omniroute@X.Y.Z && pm2 restart omniroute"
+```
+
+## Notes
+
+- Always run `/update-docs` BEFORE this workflow (ensures CHANGELOG and README are current)
+- The `prepublishOnly` script runs `npm run build:cli` automatically during `npm publish`
+- After npm publish, verify with `npm info omniroute version`

.agents/workflows/issue-triage.md

@@ -0,0 +1,50 @@
+---
+description: How to respond to GitHub issues with insufficient information
+---
+
+# Issue Triage Workflow
+
+Respond to GitHub issues that need more information before they can be investigated.
+
+## Steps
+
+### 1. Identify issues needing triage
+
+```bash
+gh issue list --state open --limit 20
+```
+
+### 2. Evaluate each issue
+
+Check if the issue has:
+
+- Clear reproduction steps
+- Environment details (OS, Node.js version, OmniRoute version)
+- Error logs/screenshots
+- Expected vs actual behavior
+
+### 3. Respond with triage template
+
+For issues missing information:
+
+```markdown
+Thank you for reporting this issue! To help us investigate, please provide:
+
+1. **OmniRoute version**: (`omniroute --version`)
+2. **Node.js version**: (`node --version`)
+3. **Operating system**: (e.g., Ubuntu 24.04, macOS 15, Windows 11)
+4. **Installation method**: (npm, Docker, source)
+5. **Steps to reproduce**: (exact commands/actions that trigger the issue)
+6. **Error logs**: (paste relevant logs from the console)
+7. **Expected behavior**: (what should happen)
+
+This will help us debug and resolve your issue faster. 🙏
+```
+
+### 4. Label the issue
+
+Add appropriate labels: `needs-info`, `bug`, `enhancement`, `question`, etc.
+
+```bash
+gh issue edit <NUMBER> --add-label "needs-info"
+```

.agents/workflows/resolve-issues.md

@@ -1,12 +1,12 @@
 ---
-description: Fetch all open GitHub issues, analyze bugs, resolve what's possible, triage the rest, then commit and release
+description: Fetch all open GitHub issues, analyze bugs, resolve what's possible, triage the rest, wait for user validation, then commit and release
 ---
 
 # /resolve-issues — Automated Issue Resolution Workflow
 
 ## Overview
 
-This workflow fetches all open issues from the project's GitHub repository, classifies them, analyzes bugs, resolves what can be fixed, triages issues with insufficient information, and generates a release with all fixes.
+This workflow fetches all open issues from the project's GitHub repository, classifies them, analyzes bugs, resolves what can be fixed, and triages issues with insufficient information. **It does NOT merge or release automatically** — it creates a PR and waits for user validation before merging.
 
 ## Steps
 
@@ -60,41 +60,61 @@ Call the `/issue-triage` workflow (located at `~/.gemini/antigravity/global_work
 
 Proceed with resolution:
 
-1. **Research** — Search the codebase for files related to the issue
-2. **Root Cause** — Identify the root cause by reading the relevant source files
-3. **Implement Fix** — Apply the fix following existing code patterns and conventions
-4. **Test** — Build the project and run tests to verify the fix
-5. **Commit** — Commit with message format: `fix: <description> (#<issue_number>)`
+1. **Create a fix branch** — `git checkout -b fix/issue-<NUMBER>-<short-description>`
+2. **Research** — Search the codebase for files related to the issue
+3. **Root Cause** — Identify the root cause by reading the relevant source files
+4. **Implement Fix** — Apply the fix following existing code patterns and conventions
+5. **Test** — Build the project and run tests to verify the fix
+6. **Commit** — Commit with message format: `fix: <description> (#<issue_number>)`
 
-### 5. Commit All Fixes
+### 5. Generate Report & Wait for Validation
 
-After processing all issues:
+Present a summary report to the user via `notify_user` with `BlockedOnUser: true`:
 
-- Ensure all fixes are committed with proper issue references
-- Each fix should be its own commit for clean git history
+| Issue | Title | Status        | Action                        |
+| ----- | ----- | ------------- | ----------------------------- |
+| #N    | Title | ✅ Ready      | Files changed (not committed) |
+| #N    | Title | ❓ Needs Info | Triage comment posted         |
+| #N    | Title | ⏭️ Skipped    | Feature request / not a bug   |
 
-### 6. Close Resolved Issues
+> **⚠️ IMPORTANT**: Do NOT commit, close issues, or generate releases at this step.
+> Wait for the user to review the changes and respond with **OK** before proceeding.
 
-For each successfully fixed issue:
-// turbo
+- If the user says **OK** or approves → Proceed to step 6
+- If the user requests changes → Apply the requested adjustments first, then present the report again
+- If the user rejects → Revert the changes and stop
 
-- Close with a comment: `gh issue close <NUMBER> --repo <owner>/<repo> --comment "Fixed in <commit_hash>. The fix will be included in the next release."`
+### 6. Commit & Push Fix Branch (only after user approval)
 
-### 7. Generate Report
+After the user validates:
 
-Present a summary report to the user via `notify_user`:
+- Commit each fix individually with message format: `fix: <description> (#<issue_number>)`
+- Push the fix branch: `git push origin fix/issue-<NUMBER>-<short-description>`
+- Create a PR: `gh pr create --title "fix: <description> (#<issue_number>)" --body "<details>" --base main`
 
-| Issue | Title | Status        | Action                      |
-| ----- | ----- | ------------- | --------------------------- |
-| #N    | Title | ✅ Fixed      | Commit hash                 |
-| #N    | Title | ❓ Needs Info | Triage comment posted       |
-| #N    | Title | ⏭️ Skipped    | Feature request / not a bug |
+### 7. 🛑 WAIT — Notify User & Await PR Verification
 
-### 8. Update Docs & Release
+**This is a mandatory stop point.** Use `notify_user` with `BlockedOnUser: true`:
 
-If any fixes were committed:
+- Inform the user that the PR was created and is **awaiting their verification**
+- Include the PR number, URL, and a summary of what was changed
+- **DO NOT merge, close issues, generate releases, or deploy until the user confirms**
 
-1. Run the `/update-docs` workflow (at `~/.gemini/antigravity/global_workflows/update-docs.md`) to update CHANGELOG and README
-2. Run the `/generate-release` workflow (at `.agents/workflows/generate-release.md`) to bump version, tag, and publish
+Wait for the user to respond:
+
+- **User confirms** → Proceed to step 8
+- **User requests changes** → Apply changes, push to the same branch, notify again
+- **User rejects** → Close the PR and stop
+
+### 8. Merge, Close Issues & Release (only after user confirms PR)
+
+After the user confirms the PR:
+
+1. **Merge** the PR: `gh pr merge <NUMBER> --merge --repo <owner>/<repo>` or via local merge
+2. **Close** resolved issues with a comment: `gh issue close <NUMBER> --repo <owner>/<repo> --comment "Fixed in <commit_hash>. The fix will be included in the next release."`
+3. **Switch to main**: `git checkout main && git pull`
+4. Run the `/update-docs` workflow (at `~/.gemini/antigravity/global_workflows/update-docs.md`) to update CHANGELOG and README
+5. Run the `/generate-release` workflow (at `.agents/workflows/generate-release.md`) to bump version, tag, and publish
+6. Deploy to local VPS: `ssh root@192.168.0.15 "npm install -g omniroute@<VERSION> && pm2 restart omniroute"`
 
 If NO fixes were committed, skip this step and just present the report.

.agents/workflows/review-prs.md

@@ -6,7 +6,7 @@ description: Analyze open Pull Requests from the project's GitHub repository, ge
 
 ## Overview
 
-This workflow fetches all open PRs from the project's GitHub repository, performs a critical analysis of each one, generates a detailed report, and waits for user approval before proceeding with implementation.
+This workflow fetches all open PRs from the project's GitHub repository, performs a critical analysis of each one, generates a detailed report, and waits for user approval before proceeding with implementation. **All improvements are committed on top of the PR branch** and the user must verify before merge.
 
 ## Steps
 
@@ -60,6 +60,21 @@ This workflow fetches all open PRs from the project's GitHub repository, perform
 - Are edge cases covered?
 - Would existing tests break?
 
+#### 3f. Cross-Layer (Global) Analysis
+
+Perform a **global impact assessment** to verify whether the PR changes are complete across all layers of the application:
+
+- **Backend → Frontend check**: If the PR adds or modifies backend-only resources (new endpoints, services, data models), evaluate whether corresponding frontend changes are missing:
+  - Does a new endpoint require a new screen/page in the dashboard?
+  - Should there be a new action button, menu item, or navigation link?
+  - Are there new data fields that should be displayed or editable in the UI?
+  - Does a new feature need a toggle, configuration panel, or status indicator?
+- **Frontend → Backend check**: If the PR adds frontend elements, verify the backend support exists:
+  - Are the required API endpoints implemented?
+  - Is the data model sufficient for the new UI components?
+- **Cross-cutting concerns**: Check shared layers (types, DTOs, validation schemas, routes, middleware) for completeness
+- **Document gaps** — If missing layers are detected, list them as **IMPORTANT** issues in the report with concrete suggestions for what should be added
+
 ### 4. Generate Report — Create a markdown report for each PR including:
 
 - **PR Summary** — What it does, files affected, commit count
@@ -79,18 +94,52 @@ This workflow fetches all open PRs from the project's GitHub repository, perform
 
 ### 6. Implementation (if approved)
 
-- Checkout the PR branch or apply changes locally
+- Checkout the PR branch: `gh pr checkout <NUMBER>`
 - Implement any required fixes identified in the analysis
+- If the Cross-Layer Analysis (3f) identified missing frontend/backend counterparts, implement them
+- **Commit improvements on top of the PR branch** with descriptive commit messages
 - Run the project's test suite to verify nothing breaks
   // turbo
 - Run: `npm test` or equivalent test command
 - Build the project to verify compilation
   // turbo
 - Run: `npm run build` or equivalent build command
-- If all checks pass, prepare the merge
+- Push the updated branch: `git push origin <branch-name>`
 
-### 7. Post-Merge (if applicable)
+### 7. 🛑 WAIT — Notify User & Await PR Verification
 
-- Update CHANGELOG.md with the new feature
-- Consider version bump if warranted
-- Follow the `/generate-release` workflow if a release is needed
+**This is a mandatory stop point.** Use `notify_user` with `BlockedOnUser: true`:
+
+- Inform the user that the PR has been **improved and pushed**, and is **awaiting their verification**
+- Include:
+  - PR number and URL
+  - Summary of improvements/fixes applied
+  - Build/test status
+  - List of files changed
+- **DO NOT merge, generate releases, or deploy until the user confirms**
+
+Wait for the user to respond:
+
+- **User confirms** → Proceed to step 8
+- **User requests more changes** → Apply changes, push to the same branch, notify again
+- **User rejects** → Leave a review comment and stop
+
+### 8. Thank the Contributor
+
+- Post a **thank-you comment** on the PR via the GitHub API
+- The message should:
+  - Thank the author by name/username for their contribution
+  - Briefly mention what the PR accomplishes and any improvements applied
+  - Be friendly, professional, and encouraging
+- Example: _"Thanks @author for this great contribution! 🎉 The [feature/fix] is now merged and will be part of the next release. We appreciate your effort!"_
+
+### 9. Merge & Release (only after user confirms PR)
+
+After the user confirms the PR:
+
+1. **Merge** the PR into main (local merge with `--no-ff` or via `gh pr merge`)
+2. **Push** to main: `git push origin main`
+3. **Clean up** the feature branch: `git branch -d <branch-name>`
+4. **Update CHANGELOG.md** with the new feature/fix
+5. Run the `/generate-release` workflow (at `.agents/workflows/generate-release.md`) to bump version, tag, and publish
+6. Deploy to local VPS: `ssh root@192.168.0.15 "npm install -g omniroute@<VERSION> && pm2 restart omniroute"`

.agents/workflows/update-docs.md

@@ -0,0 +1,105 @@
+---
+description: How to automatically summarize recent changes and update README and CHANGELOG
+---
+
+# Update Documentation Workflow
+
+Update CHANGELOG.md, README.md, docs/ files, and all multi-language translations whenever features are added or changed.
+
+## Steps
+
+### 1. Summarize recent changes
+
+Review git log and identify new features, fixes, or changes since the last release tag:
+
+```bash
+git log $(git describe --tags --abbrev=0)..HEAD --oneline
+```
+
+### 2. Update English CHANGELOG.md
+
+Add an `[Unreleased]` section (or version header if releasing) with:
+
+- `### ✨ New Features` — each feature as a bullet point
+- `### 🐛 Bug Fixes` — if applicable
+- `### 🧪 Tests` — test count changes
+- `### 📁 New Files` — table of new files with purpose
+
+### 3. Update English README.md
+
+Update the feature tables in these sections:
+
+- **🧠 Routing & Intelligence** — for routing/model features
+- **🛡️ Resilience & Security** — for security/resilience features
+- **📊 Observability & Analytics** — for monitoring features
+- **☁️ Deploy & Sync** — for deployment features
+
+### 4. Update docs/ files
+
+- `docs/FEATURES.md` — update the Settings section description
+- `docs/API_REFERENCE.md` — add new API routes if any
+- `docs/ARCHITECTURE.md` — update architecture if structural changes
+
+### 5. 🌐 Sync Multi-Language Documentation (CRITICAL)
+
+// turbo-all
+
+**This step MUST be run after every README or docs update.**
+
+The project has **30 language versions** of documentation:
+
+**README files (root directory):**
+
+```
+README.md (English - source of truth)
+README.pt-BR.md README.pt.md README.es.md README.fr.md README.it.md
+README.de.md README.nl.md README.sv.md README.no.md README.da.md README.fi.md
+README.ru.md README.uk-UA.md README.bg.md README.sk.md README.pl.md README.ro.md README.hu.md
+README.ar.md README.he.md README.th.md README.in.md README.id.md README.ms.md README.vi.md
+README.ja.md README.ko.md README.zh-CN.md README.phi.md
+```
+
+**docs/i18n/ directories (29 languages):**
+
+```
+docs/i18n/{ar,bg,da,de,es,fi,fr,he,hu,id,in,it,ja,ko,ms,nl,no,phi,pl,pt,pt-BR,ro,ru,sk,sv,th,uk-UA,vi,zh-CN}/
+Each contains: API_REFERENCE.md, ARCHITECTURE.md, CODEBASE_DOCUMENTATION.md, FEATURES.md, TROUBLESHOOTING.md, USER_GUIDE.md
+```
+
+**Sync approach for feature table updates:**
+
+a. Identify which feature table rows were added to English README.md
+b. For each translated README, find the corresponding anchor lines:
+
+- **Routing section:** Find the `💬` (System Prompt) table row — the line before it is always the last routing feature. Insert new routing features before System Prompt.
+- **Resilience section:** Find the `📊` Rate Limits table row (the one in lines 590-600, NOT the quota tracking one in lines 560-570). Insert new resilience features after it.
+  c. The new feature entries can stay in English for technical features, matching the pattern used in the existing translations.
+  d. Use `sed` or similar tool to batch-insert across all 29 translated READMEs.
+
+**Verification:**
+
+```bash
+# Verify all READMEs have the new features
+grep -l "NEW_FEATURE_NAME" README.*.md | wc -l
+# Should return 30 (all language versions)
+```
+
+**FEATURES.md sync:**
+
+```bash
+# Update Settings description in all docs/i18n/*/FEATURES.md
+for dir in docs/i18n/*/; do
+  # Update the Settings section description to mention new features
+  # Check FEATURES.md in each directory
+done
+```
+
+### 6. Verify documentation changes
+
+```bash
+# Check all modified files
+git status --short
+
+# Verify no broken markdown
+# Optional: run markdownlint if available
+```

.env.example

@@ -130,6 +130,22 @@ GEMINI_CLI_OAUTH_CLIENT_SECRET=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
 # IFLOW_OAUTH_CLIENT_ID=
 IFLOW_OAUTH_CLIENT_SECRET=4Z3YjXycVsQvyGF1etiNlIBB4RsqSDtW
 
+# ─────────────────────────────────────────────────────────────────────────────
+# Provider User-Agent Overrides (optional — customize per-provider UA headers)
+# ─────────────────────────────────────────────────────────────────────────────
+# Format: {PROVIDER_ID}_USER_AGENT=custom-value
+# When set, overrides the default User-Agent header sent to that provider.
+# Useful when providers update versions or block old user-agents.
+CLAUDE_USER_AGENT=claude-cli/1.0.83 (external, cli)
+CODEX_USER_AGENT=codex-cli/0.92.0 (Windows 10.0.26100; x64)
+GITHUB_USER_AGENT=GitHubCopilotChat/0.26.7
+ANTIGRAVITY_USER_AGENT=antigravity/1.104.0 darwin/arm64
+KIRO_USER_AGENT=AWS-SDK-JS/3.0.0 kiro-ide/1.0.0
+IFLOW_USER_AGENT=iFlow-Cli
+QWEN_USER_AGENT=google-api-nodejs-client/9.15.1
+CURSOR_USER_AGENT=connect-es/1.6.1
+GEMINI_CLI_USER_AGENT=google-api-nodejs-client/9.15.1
+
 # API Key Providers (Phase 1 + Phase 4)
 # Add via Dashboard → Providers → Add API Key, or set here
 # DEEPSEEK_API_KEY=

.github/workflows/electron-release.yml

@@ -3,11 +3,11 @@ name: Build Electron Desktop App
 on:
   push:
     tags:
-      - 'v*'
+      - "v*"
   workflow_dispatch:
     inputs:
       version:
-        description: 'Release version (e.g., v1.6.8)'
+        description: "Release version (e.g., v1.6.8)"
         required: true
         type: string
 
@@ -89,6 +89,8 @@ jobs:
         run: npm ci
 
       - name: Build Next.js standalone
+        env:
+          JWT_SECRET: ci-build-secret-with-sufficient-length-for-validation
         run: npm run build
 
       - name: Install Electron dependencies
@@ -100,6 +102,7 @@ jobs:
         run: npm run build:${{ matrix.target }}
 
       - name: Collect installers
+        shell: bash
         run: |
           mkdir -p release-assets
           cd electron/dist-electron
@@ -139,11 +142,11 @@ jobs:
           # Create source code archives (excluding dev dependencies and build artifacts)
           export TARBALL="OmniRoute-${{ needs.validate.outputs.version }}.source.tar.gz"
           export ZIPBALL="OmniRoute-${{ needs.validate.outputs.version }}.source.zip"
-          
+
           # Use git archive for clean source export
           git archive --format=tar.gz --prefix=OmniRoute-${{ needs.validate.outputs.version }}/ HEAD -o "release-assets/$TARBALL"
           git archive --format=zip --prefix=OmniRoute-${{ needs.validate.outputs.version }}/ HEAD -o "release-assets/$ZIPBALL"
-          
+
           echo "✓ Created source archives:"
           ls -lh "release-assets/$TARBALL" "release-assets/$ZIPBALL"
 

CHANGELOG.md

@@ -7,6 +7,185 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 
 ---
 
+## [1.7.11] — 2026-03-02
+
+### ✨ Features
+
+- **Blackbox AI Provider** — Added blackbox.ai as a new OpenAI-compatible provider with 6 default models (GPT-4o, Gemini 2.5 Flash, Claude Sonnet 4, DeepSeek V3, Blackbox AI, Blackbox AI Pro) and provider logo. Fixes #175
+
+### 🐛 Bug Fixes
+
+- **Antigravity 404 Error** — Added warning logs when `generateProjectId()` generates a fallback project ID because `credentials.projectId` is null. The executor now prefers the translator-set `body.project` before generating a new fallback, eliminating duplicate warnings and ID mismatch. Fixes #176. Includes improvements from PRs #184 and #185
+
+## [1.7.10] — 2026-03-02
+
+### 🐛 Bug Fixes
+
+- **Streaming Tool Calls (Responses→ChatCompletions)** — Fixed two issues in the `openaiResponsesToOpenAIResponse` translator that broke tool call execution in agentic clients (OpenCode, Claude Code, Cursor, etc.): (1) Argument delta chunks now include `tool_calls[].id` and `type: "function"` so clients can associate argument fragments correctly. (2) `finish_reason` is now `"tool_calls"` instead of hardcoded `"stop"` when tool calls occurred. Fixes #180
+
+## [1.7.9] — 2026-03-02
+
+### 🐛 Bug Fixes
+
+- **Electron CI Build** — Added `JWT_SECRET` environment variable to the Electron release workflow `Build Next.js standalone` step, fixing build failures in GitHub Actions. PR #178 by @benzntech
+
+### 📝 Documentation
+
+- **README** — Updated OpenClaw link from `cline/cline` to `openclaw/openclaw` to reflect the project rename. PR #179 by @MAINER4IK
+
+## [1.7.8] — 2026-03-02
+
+### ✨ New Features
+
+- **Theme Color Customization** — Users can now select from 7 preset accent colors (Coral, Blue, Red, Green, Violet, Orange, Cyan) or define a custom color via color picker/hex input. The chosen color dynamically updates `--color-primary` and `--color-primary-hover` CSS variables across the entire UI. PR #174 by @mainer4ik
+
+### 🌐 Multi-Language Sync
+
+- **Theme & Media i18n** — Added `themeCoral`, `themeBlue`, `themeRed`, `themeGreen`, `themeViolet`, `themeOrange`, `themeCyan`, `themeAccent`, `themeAccentDesc`, `themeCustom`, `themeCreate`, and media section translations across all **30 language locales**
+
+### 🔧 Code Quality (Review Improvements)
+
+- Exported `COLOR_THEMES` constant from `themeStore.ts` for DRY reuse
+- Added hex color validation with visual feedback (red border + disabled apply button)
+- Synced local state via Zustand `subscribe` pattern for cross-tab consistency
+- Removed dead `/themes` route from Header.tsx
+- Added CSS `color-mix()` fallback for older browsers
+
+## [1.7.7] — 2026-03-02
+
+### 🐛 Bug Fixes
+
+- **Gemini Tool Schema Sanitization** — The standard Gemini provider now sanitizes OpenAI tool schemas before forwarding to Gemini API, removing unsupported JSON Schema keywords (`additionalProperties`, `$schema`, `const`, `default`, `not`, etc.). Previously, sanitization only ran in the CLI executor path, causing Gemini to reject tool calls when schemas contained unsupported constraints. Also applied sanitization to `response_format.json_schema`. Fixes #173
+
+## [1.7.6] — 2026-03-02
+
+### 🐛 Bug Fixes
+
+- **Cloud Proxy `undefined/v1` Fix** — When the `NEXT_PUBLIC_CLOUD_URL` environment variable is not set (common in Docker deployments), the endpoint page now correctly falls back instead of showing `undefined/v1`. The cloud sync API now returns `cloudUrl` in its response so the frontend can use it dynamically. Fixes #171
+
+### ✨ New Features
+
+- **Cloud Worker `/v1/models` Endpoint** — The Cloud Worker now supports the `/v1/models` endpoint for both URL formats (`/v1/models` and `/{machineId}/v1/models`), returning all available models synced from the local OmniRoute instance
+
+### 🔧 Infrastructure
+
+- **Cloudflare Workers Compatibility** — Fixed `setInterval` in global scope issue in `accountFallback.ts` that blocked Cloud Worker deployment. Lazy initialization pattern ensures compatibility with Cloudflare Workers runtime restrictions
+
+## [1.7.5] — 2026-03-02
+
+### 🐛 Bug Fixes
+
+- **OAuth Re-Auth Duplicate Fix** — Re-authenticating an expired OAuth connection now updates the existing connection instead of creating a duplicate entry. When re-auth is triggered, the system matches by `provider` + `email` + `authType` and refreshes tokens in-place. Fixes #170
+
+## [1.7.4] — 2026-03-01
+
+### ✨ New Features
+
+- **OpenCode CLI Integration** — Added full integration guide for [OpenCode](https://opencode.ai) AI CLI tool using `@ai-sdk/openai-compatible` adapter with custom `opencode.json` config. Resolves #169
+- **Endpoint Page Restructured** — Reorganized the Endpoint dashboard page into 3 grouped categories (Core APIs, Media & Multi-Modal, Utility & Management) with visual dividers. Added 2 new endpoint sections: **Responses API** (`/v1/responses`) and **List Models** (`/v1/models`)
+- **Model Aliases & Background Degradation i18n** — Added 14 translated settings keys and 7 translated endpoint keys across all **30 language locales**. Fixed missing translations showing raw keys like `settings.modelAliasesTitle` in the UI
+
+### 🌐 Multi-Language Sync
+
+- **30 README translations synced** — All 28 translated READMEs updated with v1.7.3 feature entries (Model Aliases, Background Degradation, Rate Limit Persistence, Token Refresh Resilience)
+- **6 docs/i18n FEATURES.md updated** — Settings description expanded in da, it, nl, phi, pl, sv
+
+### 📁 New Files
+
+| File                                    | Purpose                                                     |
+| --------------------------------------- | ----------------------------------------------------------- |
+| `.agents/workflows/update-docs.md`      | Documentation update workflow with multi-language sync step |
+| `.agents/workflows/generate-release.md` | Release generation workflow (version bump, npm, GitHub)     |
+| `.agents/workflows/issue-triage.md`     | Issue triage workflow for issues with insufficient info     |
+
+## [1.7.3] — 2026-03-01
+
+### ✨ New Features
+
+- **Model Deprecation Auto-Forward** — New `modelDeprecation.ts` service with 10+ built-in aliases for legacy Gemini, Claude, and OpenAI models. Deprecated model IDs (e.g., `gemini-pro`, `claude-2`) are automatically forwarded to their current replacements. Custom aliases configurable via new Settings → Routing → Model Aliases UI tab with full CRUD API (`/api/settings/model-aliases`)
+- **Background Task Smart Degradation** — New `backgroundTaskDetector.ts` service detects background/utility requests (title generation, summarization, etc.) via 19 system prompt patterns and `X-Request-Priority` header, and automatically reroutes them to cheaper models. Configurable degradation map and detection patterns via new Settings → Routing → Background Degradation UI tab. Disabled by default (opt-in)
+- **Rate Limit Persistence** — Learned rate limits from API response headers are now persisted to SQLite with 60-second debouncing and restored on startup (24h staleness filter). Rate limits survive server restarts instead of being lost in memory
+- **thinkingLevel String Conversion** — `applyThinkingBudget()` now handles string-based `thinkingLevel` inputs (`"high"`, `"medium"`, `"low"`, `"none"`) by converting them to numeric token budgets. Supports `thinkingLevel`, `thinking_level`, and Gemini's `generationConfig.thinkingConfig.thinkingLevel` fields
+- **Claude -thinking Model Auto-Injection** — Models ending with `-thinking` suffix (e.g., `claude-opus-4-6-thinking`) automatically get thinking parameters injected to prevent API errors. `hasThinkingCapableModel()` updated to recognize these suffixes
+- **Gemini 3.0/3.1 Model Registry** — Updated provider registry to explicitly distinguish Gemini 3.1 (Pro, Flash) from 3.0 Preview variants across `gemini`, `gemini-cli`, and `antigravity` providers with clear naming conventions
+- **Token Refresh Circuit Breaker** — Per-provider circuit breaker in `refreshWithRetry()`: 5 consecutive failures trigger a 30-minute cooldown to prevent infinite retry loops. Added 30-second timeout wrapper per refresh attempt. Exported `isProviderBlocked()` and `getCircuitBreakerStatus()` for diagnostics
+
+### 🧪 Tests
+
+- **40+ new unit tests** across 3 files: `model-deprecation.test.mjs` (14 tests), `background-task-detector.test.mjs` (14 tests), extended `thinking-budget.test.mjs` (+13 tests). Total suite: **561 tests, 0 failures**
+
+### 📁 New Files
+
+| File                                                                   | Purpose                                                               |
+| ---------------------------------------------------------------------- | --------------------------------------------------------------------- |
+| `open-sse/services/modelDeprecation.ts`                                | Model deprecation alias resolver with built-in + custom aliases       |
+| `open-sse/services/backgroundTaskDetector.ts`                          | Background task detection with pattern matching and model degradation |
+| `src/app/api/settings/model-aliases/route.ts`                          | CRUD API for model alias management                                   |
+| `src/app/api/settings/background-degradation/route.ts`                 | API for background degradation config                                 |
+| `src/app/(dashboard)/settings/components/ModelAliasesTab.tsx`          | Settings UI for model alias management                                |
+| `src/app/(dashboard)/settings/components/BackgroundDegradationTab.tsx` | Settings UI for background degradation                                |
+| `tests/unit/model-deprecation.test.mjs`                                | 14 unit tests for model deprecation                                   |
+| `tests/unit/background-task-detector.test.mjs`                         | 14 unit tests for background task detection                           |
+
+---
+
+## [1.7.2] — 2026-03-01
+
+### ✨ New Features
+
+- **Multi-Modal Provider Support** — Added 6 TTS providers (ElevenLabs, Nvidia NIM, HuggingFace, Coqui, Tortoise, Qwen3), 3 STT providers, 2 image providers (SD WebUI, ComfyUI), and two new modalities: `/v1/videos/generations` (Text-to-Video) and `/v1/music/generations` (Text-to-Music). Shared abstractions via `registryUtils.ts` and `comfyuiClient.ts` ([PR #167](https://github.com/diegosouzapw/OmniRoute/pull/167) by @ken2190)
+- **Media Playground Page** — New dashboard page at `/dashboard/media` with tabbed interface (Image/Video/Music), model selector, prompt input, and JSON result viewer
+- **Unit Tests for Registry Utils** — 24 tests covering `parseModelFromRegistry`, `getAllModelsFromRegistry`, `buildAuthHeaders`, and integration with video/music registries
+- **WFGY 16-Problem RAG Failure Map** — Added troubleshooting reference for RAG/LLM failure taxonomy in `docs/TROUBLESHOOTING.md` ([PR #164](https://github.com/diegosouzapw/OmniRoute/pull/164) by @onestardao)
+
+### 🐛 Fixed
+
+- **Gemini Imported Models Return 404** — Strip `models/` prefix from Gemini model IDs during import to prevent doubled paths ([#163](https://github.com/diegosouzapw/OmniRoute/issues/163))
+- **Pino File Transport Fails in Next.js Production** — Log actual error + add sync `pino.destination()` fallback ([#165](https://github.com/diegosouzapw/OmniRoute/issues/165))
+- **Windows Electron CI Build** — Added `shell: bash` to Collect installers step for Windows runners ([PR #168](https://github.com/diegosouzapw/OmniRoute/pull/168) by @benzntech)
+- **TypeScript Safety** — Replaced `Record<string, any>` with `Record<string, unknown>` in `registryUtils.ts`
+
+---
+
+## [1.7.1] — 2026-02-28
+
+### 🐛 Fixed
+
+- **Dashboard Layout Breakage** — Tailwind CSS v4 auto-detection failed to scan Next.js route group directories with parentheses (e.g. `(dashboard)`), causing all responsive grid utilities (`sm:grid-cols-*`, `md:grid-cols-*`, `lg:grid-cols-*`, `xl:grid-cols-*`) to be purged from production CSS. Cards displayed in a single column instead of multi-column grids. Fixed by adding explicit `@source` directives in `globals.css`
+
+---
+
+## [1.7.0] — 2026-02-28
+
+### ✨ New Features
+
+- **16 Pain Points Documentation** — New collapsible section "🎯 What OmniRoute Solves — 16 Real Pain Points" added to the main README and all 29 language-specific READMEs. Each pain point uses `<details>/<summary>` tags for clean, expandable content
+- **Configurable User-Agent per Provider** — User-Agent strings for OAuth providers (Claude, Codex, GitHub, Antigravity, Kiro, iFlow, Qwen, Cursor, Gemini CLI) are now configurable via environment variables. Format: `{PROVIDER_ID}_USER_AGENT=custom-value` ([#155](https://github.com/diegosouzapw/OmniRoute/issues/155))
+
+### 🐛 Fixed
+
+- **Hardcoded `$HOME` Path in Standalone/Bun Builds** — 5 files (`backupService.ts`, `mitm/manager.ts`, `mitm/server.ts`, `mitm/cert/generate.ts`, `codex-profiles/route.ts`) were bypassing the centralized `dataPaths.ts` and using `os.homedir()` directly. This caused paths to bake the build machine's `$HOME` into standalone/bun builds, producing `EACCES: permission denied` errors on other machines. All files now use `resolveDataDir()` from `dataPaths.ts`, respecting `DATA_DIR` env var and XDG conventions ([#156](https://github.com/diegosouzapw/OmniRoute/issues/156))
+
+### 📝 Documentation
+
+- **`.env` and `.env.example` Synced** — Added 9 User-Agent env vars with latest known default values to both environment files
+- **30 README Translations Updated** — All language READMEs now include the 16 Pain Points section
+
+---
+
+## [1.6.9] — 2026-02-28
+
+### 🐛 Fixed
+
+- **Proxy Port Preservation** — `new URL()` silently strips default ports (80/443); proxy connections now extract the port from the raw URL string before parsing, preventing connection timeouts ([PR #161](https://github.com/diegosouzapw/OmniRoute/pull/161))
+- **Proxy Credential Encoding** — URL-encode special characters in proxy username/password; decode during legacy migration ([PR #161](https://github.com/diegosouzapw/OmniRoute/pull/161))
+- **HTTPS Proxy Default Port** — Changed from 8080 to 443 in frontend and migration logic ([PR #161](https://github.com/diegosouzapw/OmniRoute/pull/161))
+- **Proxy Dispatcher Cache** — Invalidate cached dispatchers when proxy config is updated or deleted ([PR #161](https://github.com/diegosouzapw/OmniRoute/pull/161))
+- **Proxy Logger SQLite Type** — Cast `proxyPort` to `Number` for INTEGER column ([PR #161](https://github.com/diegosouzapw/OmniRoute/pull/161))
+- **CopilotToolCard URL** — Use `baseUrl` prop directly instead of redundant `window.location.origin`; filter to chat models only (`!m.type && !m.parent`) ([PR #160](https://github.com/diegosouzapw/OmniRoute/pull/160))
+
+---
+
 ## [1.6.8] — 2026-02-28
 
 ### 🔧 Improved

Dockerfile

@@ -2,6 +2,7 @@ FROM node:22-bookworm-slim AS builder
 WORKDIR /app
 
 COPY package*.json ./
+COPY scripts/postinstall.mjs ./scripts/postinstall.mjs
 RUN if [ -f package-lock.json ]; then npm ci --no-audit --no-fund; else npm install --no-audit --no-fund; fi
 
 COPY . ./

README.ar.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ بداية سريعة
 
 **1. التثبيت عالميًا:**
@@ -310,6 +567,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **نماذج مخصصة**                | أضف أي معرف نموذج إلى أي مزود                                                                  |
 | 🌐 **جهاز توجيه Wildcard**        | قم بتوجيه أنماط `provider/*` إلى أي مزود ديناميكيًا                                            |
 | 🧠 **ميزانية التفكير**            | أوضاع العبور والتلقائي والمخصص والتكيفي لنماذج الاستدلال                                       |
+| 🔀 **Model Aliases**              | Auto-forward deprecated model IDs to current replacements (built-in + custom)                  |
+| ⚡ **Background Degradation**     | Auto-route background tasks (titles, summaries) to cheaper models                              |
 | 💬 **الحقن الفوري للنظام**        | يتم تطبيق موجه النظام العالمي على كافة الطلبات                                                 |
 | 📄 **Responses API**              | دعم واجهة برمجة تطبيقات استجابات OpenAI الكاملة (`/v1/responses`) لـ Codex                     |
 
@@ -335,6 +594,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **انتحال بصمة الإصبع TLS**                 | تجاوز اكتشاف الروبوتات المستندة إلى TLS عبر wreq-js                                         |
 | 🌐 **تصفية IP**                               | القائمة المسموح بها/القائمة المحظورة للتحكم في الوصول إلى واجهة برمجة التطبيقات             |
 | 📊 **حدود المعدل القابلة للتحرير**            | عدد الدورات في الدقيقة القابل للتكوين والفجوة الدنيا والحد الأقصى المتزامن على مستوى النظام |
+| 💾 **Rate Limit Persistence**                 | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness                |
+| 🔄 **Token Refresh Resilience**               | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                      |
 | 🛡 **حماية نقطة نهاية واجهة برمجة التطبيقات** | بوابة المصادقة + حظر الموفر لنقطة النهاية `/models`                                         |
 | 🔒 **رؤية الوكيل**                            | شارات مرمزة بالألوان: 🟢 عالمية، 🟡 مزود، 🔵 لكل اتصال مع عرض IP                            |
 | 🌐 ** تكوين الوكيل ذو 3 مستويات **            | قم بتكوين الوكلاء على المستوى العالمي أو لكل مزود أو لكل اتصال                              |

README.bg.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Бърз старт
 
 **1. Инсталирайте глобално:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Персонализирани модели**                   | Добавете всеки модел ID към който и да е доставчик                                                                           |
 | 🌐 **Wildcard Router**                          | Насочвайте `provider/*` шаблони към всеки доставчик динамично                                                                |
 | 🧠 **Мислен бюджет**                            | Преминаване, автоматичен, персонализиран и адаптивен режим за модели на разсъждение                                          |
+| 🔀 **Model Aliases**                            | Auto-forward deprecated model IDs to current replacements (built-in + custom)                                                |
+| ⚡ **Background Degradation**                   | Auto-route background tasks (titles, summaries) to cheaper models                                                            |
 | 💬 **Системно бързо инжектиране**               | Глобална системна подкана, приложена към всички заявки                                                                       |
 | 📄 **API за отговори**                          | Пълна поддръжка на OpenAI Responses API (`/v1/responses`) за Codex                                                           |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS Fingerprint Spoofing**              | Заобикаляне на TLS-базирано откриване на бот чрез wreq-js                                       |
 | 🌐 **IP филтриране**                         | Списък с разрешени/блокирани за контрол на достъпа до API                                       |
 | 📊 **Редактируеми ограничения на скоростта** | Конфигурируеми обороти в минута, минимална разлика и максимална едновременност на системно ниво |
+| 💾 **Rate Limit Persistence**                | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness                    |
+| 🔄 **Token Refresh Resilience**              | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                          |
 | 🛡 **API Endpoint Protection**               | Удостоверяване + блокиране на доставчик за крайната точка `/models`                             |
 | 🔒 **Прокси видимост**                       | Цветно кодирани значки: 🟢 глобален, 🟡 доставчик, 🔵 за връзка с IP дисплей                    |
 | 🌐 **3-ниво на прокси конфигурация**         | Конфигуриране на прокси сървъри на глобално ниво, на ниво доставчик или на ниво връзка          |

README.da.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Hurtig start
 
 **1. Installer globalt:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Tilpassede modeller**         | Tilføj ethvert model-id til enhver udbyder                                             |
 | 🌐 **Wildcard-router**             | Rut `provider/*` mønstre til enhver udbyder dynamisk                                   |
 | 🧠 **Tænkende budget**             | Passthrough, auto, brugerdefinerede og adaptive tilstande til ræsonnerende modeller    |
+| 🔀 **Model Aliases**               | Auto-forward deprecated model IDs to current replacements (built-in + custom)          |
+| ⚡ **Background Degradation**      | Auto-route background tasks (titles, summaries) to cheaper models                      |
 | 💬 **System Prompt Injection**     | Global systemprompt anvendt på tværs af alle anmodninger                               |
 | 📄 **Responses API**               | Fuld OpenAI Responses API (`/v1/responses`) understøttelse af Codex                    |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS Fingerprint Spoofing**  | Omgå TLS-baseret botdetektion via wreq-js                                      |
 | 🌐 **IP-filtrering**             | Tilladelsesliste/blokeringsliste til API-adgangskontrol                        |
 | 📊 **Redigerbare satsgrænser**   | Konfigurerbar RPM, min. gap og maks. samtidighed på systemniveau               |
+| 💾 **Rate Limit Persistence**    | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness   |
+| 🔄 **Token Refresh Resilience**  | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt         |
 | 🛡 **API-endepunktsbeskyttelse** | Auth gating + udbyderblokering for `/models` slutpunktet                       |
 | 🔒 **Proxysynlighed**            | Farvekodede badges: 🟢 global, 🟡 udbyder, 🔵 per forbindelse med IP-skærm     |
 | 🌐 **3-Level Proxy Config**      | Konfigurer proxyer på globalt niveau, pr. udbyder eller pr. forbindelsesniveau |

README.de.md

@@ -157,6 +157,263 @@ Ergebnis: Nie aufhören zu programmieren, minimale Kosten
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Schnellstart
 
 **1. Global installieren:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Benutzerdefinierte Modelle**    | Jede Modell-ID zu jedem Anbieter hinzufügen                                    |
 | 🌐 **Wildcard-Router**               | `provider/*` Muster dynamisch an jeden Anbieter routen                         |
 | 🧠 **Reasoning-Budget**              | Passthrough, auto, custom und adaptive Modi für Reasoning-Modelle              |
+| 🔀 **Model Aliases**                 | Auto-forward deprecated model IDs to current replacements (built-in + custom)  |
+| ⚡ **Background Degradation**        | Auto-route background tasks (titles, summaries) to cheaper models              |
 | 💬 **System Prompt Injection**       | Globaler System Prompt für alle Anfragen                                       |
 | 📄 **API Responses**                 | Volle Unterstützung der OpenAI Responses API (`/v1/responses`) für Codex       |
 
@@ -327,15 +586,17 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🛡️ Resilienz & Sicherheit
 
-| Funktion                        | Was es macht                                                         |
-| ------------------------------- | -------------------------------------------------------------------- |
-| 🔌 **Circuit Breaker**          | Auto-Öffnung/-Schließung pro Anbieter mit konfigurierbaren Schwellen |
-| 🛡️ **Anti-Thundering Herd**     | Mutex + Semaphor Rate-Limit für API-Key-Anbieter                     |
-| 🧠 **Semantischer Cache**       | Zwei-Ebenen-Cache (Signatur + Semantik) senkt Kosten und Latenz      |
-| ⚡ **Anfrage-Idempotenz**       | 5s Dedup-Fenster für doppelte Anfragen                               |
-| 🔒 **TLS-Fingerprint-Spoofing** | Bot-Erkennung umgehen via wreq-js                                    |
-| 🌐 **IP-Filterung**             | Allowlist/Blocklist für API-Zugriffskontrolle                        |
-| 📊 **Editierbare Rate-Limits**  | Konfigurierbare RPM, minimaler Abstand, max. Konkurrenz              |
+| Funktion                        | Was es macht                                                                 |
+| ------------------------------- | ---------------------------------------------------------------------------- |
+| 🔌 **Circuit Breaker**          | Auto-Öffnung/-Schließung pro Anbieter mit konfigurierbaren Schwellen         |
+| 🛡️ **Anti-Thundering Herd**     | Mutex + Semaphor Rate-Limit für API-Key-Anbieter                             |
+| 🧠 **Semantischer Cache**       | Zwei-Ebenen-Cache (Signatur + Semantik) senkt Kosten und Latenz              |
+| ⚡ **Anfrage-Idempotenz**       | 5s Dedup-Fenster für doppelte Anfragen                                       |
+| 🔒 **TLS-Fingerprint-Spoofing** | Bot-Erkennung umgehen via wreq-js                                            |
+| 🌐 **IP-Filterung**             | Allowlist/Blocklist für API-Zugriffskontrolle                                |
+| 📊 **Editierbare Rate-Limits**  | Konfigurierbare RPM, minimaler Abstand, max. Konkurrenz                      |
+| 💾 **Rate Limit Persistence**   | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience** | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
 
 ### 📊 Observability & Analytics
 

README.es.md

@@ -157,6 +157,263 @@ Resultado: Nunca dejes de programar, costo mínimo
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Inicio Rápido
 
 **1. Instala globalmente:**
@@ -315,6 +572,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Modelos Personalizados**          | Agrega cualquier ID de modelo a cualquier proveedor                             |
 | 🌐 **Enrutador Wildcard**              | Enruta patrones `provider/*` a cualquier proveedor dinámicamente                |
 | 🧠 **Presupuesto de Razonamiento**     | Modos passthrough, auto, custom y adaptativo para modelos de razonamiento       |
+| 🔀 **Model Aliases**                   | Auto-forward deprecated model IDs to current replacements (built-in + custom)   |
+| ⚡ **Background Degradation**          | Auto-route background tasks (titles, summaries) to cheaper models               |
 | 💬 **Inyección de System Prompt**      | System prompt global aplicado en todas las solicitudes                          |
 | 📄 **API Responses**                   | Soporte completo de la API Responses de OpenAI (`/v1/responses`) para Codex     |
 
@@ -331,15 +590,17 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🛡️ Resiliencia y Seguridad
 
-| Característica                     | Qué Hace                                                         |
-| ---------------------------------- | ---------------------------------------------------------------- |
-| 🔌 **Circuit Breaker**             | Auto-apertura/cierre por proveedor con umbrales configurables    |
-| 🛡️ **Anti-Thundering Herd**        | Mutex + semáforo rate-limit para proveedores con API key         |
-| 🧠 **Caché Semántico**             | Caché de dos niveles (firma + semántico) reduce costo y latencia |
-| ⚡ **Idempotencia de Solicitud**   | Ventana de dedup de 5s para solicitudes duplicadas               |
-| 🔒 **Spoofing de Fingerprint TLS** | Bypass de detección de bot vía TLS con wreq-js                   |
-| 🌐 **Filtrado de IP**              | Allowlist/blocklist para control de acceso a la API              |
-| 📊 **Rate Limits Editables**       | RPM, gap mínimo y concurrencia máxima configurables              |
+| Característica                     | Qué Hace                                                                     |
+| ---------------------------------- | ---------------------------------------------------------------------------- |
+| 🔌 **Circuit Breaker**             | Auto-apertura/cierre por proveedor con umbrales configurables                |
+| 🛡️ **Anti-Thundering Herd**        | Mutex + semáforo rate-limit para proveedores con API key                     |
+| 🧠 **Caché Semántico**             | Caché de dos niveles (firma + semántico) reduce costo y latencia             |
+| ⚡ **Idempotencia de Solicitud**   | Ventana de dedup de 5s para solicitudes duplicadas                           |
+| 🔒 **Spoofing de Fingerprint TLS** | Bypass de detección de bot vía TLS con wreq-js                               |
+| 🌐 **Filtrado de IP**              | Allowlist/blocklist para control de acceso a la API                          |
+| 📊 **Rate Limits Editables**       | RPM, gap mínimo y concurrencia máxima configurables                          |
+| 💾 **Rate Limit Persistence**      | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience**    | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
 
 ### 📊 Observabilidad y Analytics
 

README.fi.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Pika-aloitus
 
 **1. Asenna maailmanlaajuisesti:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Räätälöidyt mallit**             | Lisää mikä tahansa mallitunnus mille tahansa toimittajalle                                    |
 | 🌐 **Wildcard-reititin**              | Reititä `provider/*` mallit mille tahansa palveluntarjoajalle dynaamisesti                    |
 | 🧠 **Ajatteleva budjetti**            | Läpivienti-, automaatti-, mukautetut ja mukautuvat tilat päättelymalleille                    |
+| 🔀 **Model Aliases**                  | Auto-forward deprecated model IDs to current replacements (built-in + custom)                 |
+| ⚡ **Background Degradation**         | Auto-route background tasks (titles, summaries) to cheaper models                             |
 | 💬 **Järjestelmän pikaruiskutus**     | Maailmanlaajuinen järjestelmäkehote käytössä kaikissa pyynnöissä                              |
 | 📄 **Responses API**                  | Täysi OpenAI Responses API (`/v1/responses`) tuki Codexille                                   |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS-sormenjälkien huijaus**          | Ohita TLS-pohjainen bot-tunnistus wreq-js:n avulla                                               |
 | 🌐 **IP-suodatus**                        | API-käyttöoikeuksien hallinnan sallittu-/estoluettelo                                            |
 | 📊 **Muokattavat hintarajat**             | Konfiguroitava kierrosluku, minimiväli ja suurin samanaikainen järjestelmätasolla                |
+| 💾 **Rate Limit Persistence**             | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness                     |
+| 🔄 **Token Refresh Resilience**           | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                           |
 | 🛡 **API Endpoint Protection**            | Todennusportin + tarjoajan esto `/models`-päätepisteelle                                         |
 | 🔒 **Välityspalvelimen näkyvyys**         | Värikoodatut merkit: 🟢 maailmanlaajuinen, 🟡 tarjoaja, 🔵 yhteyskohtainen IP-näytöllä           |
 | 🌐 **3-tason välityspalvelimen määritys** | Määritä välityspalvelimet maailmanlaajuisesti, palveluntarjoajakohtaisesti tai yhteyskohtaisesti |

README.fr.md

@@ -157,6 +157,263 @@ Résultat : Ne jamais arrêter de coder, coût minimal
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Démarrage rapide
 
 **1. Installer globalement :**
@@ -313,6 +570,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Modèles personnalisés**          | Ajoutez n'importe quel ID de modèle à n'importe quel fournisseur                |
 | 🌐 **Routeur wildcard**               | Routez les patterns `provider/*` vers n'importe quel fournisseur dynamiquement  |
 | 🧠 **Budget de raisonnement**         | Modes passthrough, auto, custom et adaptive pour les modèles de raisonnement    |
+| 🔀 **Model Aliases**                  | Auto-forward deprecated model IDs to current replacements (built-in + custom)   |
+| ⚡ **Background Degradation**         | Auto-route background tasks (titles, summaries) to cheaper models               |
 | 💬 **Injection System Prompt**        | System prompt global appliqué à toutes les requêtes                             |
 | 📄 **API Responses**                  | Support complet de l'API Responses d'OpenAI (`/v1/responses`) pour Codex        |
 
@@ -329,15 +588,17 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🛡️ Résilience & Sécurité
 
-| Fonctionnalité                  | Ce qu'elle fait                                                      |
-| ------------------------------- | -------------------------------------------------------------------- |
-| 🔌 **Circuit Breaker**          | Ouverture/fermeture auto par fournisseur avec seuils configurables   |
-| 🛡️ **Anti-Thundering Herd**     | Mutex + sémaphore de rate-limit pour les fournisseurs avec clé API   |
-| 🧠 **Cache sémantique**         | Cache à deux niveaux (signature + sémantique) réduit coût et latence |
-| ⚡ **Idempotence des requêtes** | Fenêtre de dédup 5s pour les requêtes dupliquées                     |
-| 🔒 **Spoofing TLS Fingerprint** | Contournement de détection de bot via wreq-js                        |
-| 🌐 **Filtrage IP**              | Allowlist/blocklist pour le contrôle d'accès API                     |
-| 📊 **Rate limits éditables**    | RPM configurable, intervalle minimum, concurrence max                |
+| Fonctionnalité                  | Ce qu'elle fait                                                              |
+| ------------------------------- | ---------------------------------------------------------------------------- |
+| 🔌 **Circuit Breaker**          | Ouverture/fermeture auto par fournisseur avec seuils configurables           |
+| 🛡️ **Anti-Thundering Herd**     | Mutex + sémaphore de rate-limit pour les fournisseurs avec clé API           |
+| 🧠 **Cache sémantique**         | Cache à deux niveaux (signature + sémantique) réduit coût et latence         |
+| ⚡ **Idempotence des requêtes** | Fenêtre de dédup 5s pour les requêtes dupliquées                             |
+| 🔒 **Spoofing TLS Fingerprint** | Contournement de détection de bot via wreq-js                                |
+| 🌐 **Filtrage IP**              | Allowlist/blocklist pour le contrôle d'accès API                             |
+| 📊 **Rate limits éditables**    | RPM configurable, intervalle minimum, concurrence max                        |
+| 💾 **Rate Limit Persistence**   | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience** | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
 
 ### 📊 Observabilité & Analytique
 

README.he.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ התחלה מהירה
 
 **1. התקן ברחבי העולם:**
@@ -300,19 +557,21 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🧠 ניתוב ליבה ומודיעין
 
-| תכונה                        | מה זה עושה                                                                       |
-| ---------------------------- | -------------------------------------------------------------------------------- |
-| 🎯 **Smart 4-tier Fallback** | מסלול אוטומטי: מנוי → מפתח API → זול → חינם                                      |
-| 📊 **מעקב מכסות בזמן אמת**   | ספירת אסימונים חיה + איפוס ספירה לאחור לכל ספק                                   |
-| 🔄 **תרגום פורמט**           | OpenAI ↔ קלוד ↔ תאומים ↔ סמן ↔ Kiro חלקה + חיטוי תגובה                           |
-| 👥 **תמיכה בריבוי חשבונות**  | מספר חשבונות לכל ספק עם בחירה חכמה                                               |
-| 🔄 **רענון אסימון אוטומטי**  | אסימוני OAuth מתרעננים אוטומטית עם ניסיון חוזר                                   |
-| 🎨 **שילובים מותאמים אישית** | 6 אסטרטגיות: מילוי ראשון, עגול רובין, p2c, אקראי, פחות בשימוש, אופטימיזציה לעלות |
-| 🧩 **דגמים מותאמים אישית**   | הוסף כל מזהה דגם לכל ספק                                                         |
-| 🌐 **נתב תווים כלליים** ​​   | נתב דפוסי `provider/*` לכל ספק באופן דינמי                                       |
-| 🧠 **תקציב חשיבה**           | מצבי מעבר, אוטומטי, מותאמים אישית והתאמה למודלים של חשיבה                        |
-| 💬 **הזרקת מערכת מיידית**    | הודעת מערכת גלובלית הוחלה בכל הבקשות                                             |
-| 📄 **Responses API**         | תמיכה מלאה של OpenAI Responses API (`/v1/responses`) עבור Codex                  |
+| תכונה                         | מה זה עושה                                                                       |
+| ----------------------------- | -------------------------------------------------------------------------------- |
+| 🎯 **Smart 4-tier Fallback**  | מסלול אוטומטי: מנוי → מפתח API → זול → חינם                                      |
+| 📊 **מעקב מכסות בזמן אמת**    | ספירת אסימונים חיה + איפוס ספירה לאחור לכל ספק                                   |
+| 🔄 **תרגום פורמט**            | OpenAI ↔ קלוד ↔ תאומים ↔ סמן ↔ Kiro חלקה + חיטוי תגובה                           |
+| 👥 **תמיכה בריבוי חשבונות**   | מספר חשבונות לכל ספק עם בחירה חכמה                                               |
+| 🔄 **רענון אסימון אוטומטי**   | אסימוני OAuth מתרעננים אוטומטית עם ניסיון חוזר                                   |
+| 🎨 **שילובים מותאמים אישית**  | 6 אסטרטגיות: מילוי ראשון, עגול רובין, p2c, אקראי, פחות בשימוש, אופטימיזציה לעלות |
+| 🧩 **דגמים מותאמים אישית**    | הוסף כל מזהה דגם לכל ספק                                                         |
+| 🌐 **נתב תווים כלליים** ​​    | נתב דפוסי `provider/*` לכל ספק באופן דינמי                                       |
+| 🧠 **תקציב חשיבה**            | מצבי מעבר, אוטומטי, מותאמים אישית והתאמה למודלים של חשיבה                        |
+| 🔀 **Model Aliases**          | Auto-forward deprecated model IDs to current replacements (built-in + custom)    |
+| ⚡ **Background Degradation** | Auto-route background tasks (titles, summaries) to cheaper models                |
+| 💬 **הזרקת מערכת מיידית**     | הודעת מערכת גלובלית הוחלה בכל הבקשות                                             |
+| 📄 **Responses API**          | תמיכה מלאה של OpenAI Responses API (`/v1/responses`) עבור Codex                  |
 
 ### 🎵 ממשקי API רב-מודאליים
 
@@ -327,18 +586,20 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🛡️ חוסן וביטחון
 
-| תכונה                                | מה זה עושה                                                     |
-| ------------------------------------ | -------------------------------------------------------------- |
-| 🔌 **מפסק מעגלים**                   | פתיחה/סגירה אוטומטית לכל ספק עם ערכי סף הניתנים להגדרה         |
-| 🛡️ **עדר נגד רעמים**                 | Mutex + מגבלת קצב סמפור עבור ספקי מפתח API                     |
-| 🧠 **מטמון סמנטי**                   | מטמון דו-שכבתי (חתימה + סמנטי) מפחית את העלות והשהייה          |
-| ⚡ **בקש אימפוטנציה**                | חלון ביטול 5s עבור בקשות כפולות                                |
-| 🔒 **זיוף טביעות אצבע TLS**          | עוקף זיהוי בוט מבוסס TLS באמצעות wreq-js                       |
-| 🌐 **סינון IP**                      | רשימת הרשאות/רשימת חסימות עבור בקרת גישה ל-API                 |
-| 📊 **מגבלות תעריפים הניתנות לעריכה** | RPM ניתן להגדרה, פער מינימלי ומקסימום במקביל ברמת המערכת       |
-| 🛡 **הגנת נקודת קצה API**            | Auth gating + חסימת ספק עבור נקודת הקצה `/models`              |
-| 🔒 **נראות פרוקסי**                  | תגים מקודדים בצבע: 🟢 גלובלי, 🟡 ספק, 🔵 לכל חיבור עם תצוגת IP |
-| 🌐 **תצורת פרוקסי בשלוש רמות**       | הגדר פרוקסי ברמה גלובלית, לכל ספק או לכל חיבור                 |
+| תכונה                                | מה זה עושה                                                                   |
+| ------------------------------------ | ---------------------------------------------------------------------------- |
+| 🔌 **מפסק מעגלים**                   | פתיחה/סגירה אוטומטית לכל ספק עם ערכי סף הניתנים להגדרה                       |
+| 🛡️ **עדר נגד רעמים**                 | Mutex + מגבלת קצב סמפור עבור ספקי מפתח API                                   |
+| 🧠 **מטמון סמנטי**                   | מטמון דו-שכבתי (חתימה + סמנטי) מפחית את העלות והשהייה                        |
+| ⚡ **בקש אימפוטנציה**                | חלון ביטול 5s עבור בקשות כפולות                                              |
+| 🔒 **זיוף טביעות אצבע TLS**          | עוקף זיהוי בוט מבוסס TLS באמצעות wreq-js                                     |
+| 🌐 **סינון IP**                      | רשימת הרשאות/רשימת חסימות עבור בקרת גישה ל-API                               |
+| 📊 **מגבלות תעריפים הניתנות לעריכה** | RPM ניתן להגדרה, פער מינימלי ומקסימום במקביל ברמת המערכת                     |
+| 💾 **Rate Limit Persistence**        | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience**      | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
+| 🛡 **הגנת נקודת קצה API**            | Auth gating + חסימת ספק עבור נקודת הקצה `/models`                            |
+| 🔒 **נראות פרוקסי**                  | תגים מקודדים בצבע: 🟢 גלובלי, 🟡 ספק, 🔵 לכל חיבור עם תצוגת IP               |
+| 🌐 **תצורת פרוקסי בשלוש רמות**       | הגדר פרוקסי ברמה גלובלית, לכל ספק או לכל חיבור                               |
 
 ### 📊 יכולת תצפית וניתוח
 

README.hu.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Gyors kezdés
 
 **1. Globális telepítés:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Egyedi modellek**                  | Adjon hozzá bármilyen modellazonosítót bármely szolgáltatóhoz                               |
 | 🌐 **Wildcard Router**                  | `provider/*` minták továbbítása bármely szolgáltatóhoz dinamikusan                          |
 | 🧠 **Átgondolt költségvetés**           | Átjárási, automatikus, egyéni és adaptív módok érvelési modellekhez                         |
+| 🔀 **Model Aliases**                    | Auto-forward deprecated model IDs to current replacements (built-in + custom)               |
+| ⚡ **Background Degradation**           | Auto-route background tasks (titles, summaries) to cheaper models                           |
 | 💬 **Rendszer azonnali befecskendezés** | Globális rendszerkérdés minden kérelemre érvényes                                           |
 | 📄 **Responses API**                    | Teljes OpenAI Responses API (`/v1/responses`) támogatás a Codexhez                          |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS ujjlenyomat-hamisítás**  | A TLS-alapú botészlelés megkerülése a wreq-js segítségével                                |
 | 🌐 **IP-szűrés**                  | Allowlist/blokkolista API hozzáférés-vezérléshez                                          |
 | 📊 **Szerkeszthető díjkorlátok**  | Konfigurálható fordulatszám, minimális rés és maximális egyidejű rendszerszinten          |
+| 💾 **Rate Limit Persistence**     | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness              |
+| 🔄 **Token Refresh Resilience**   | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                    |
 | 🛡 **API Endpoint Protection**    | Auth kapuzás + szolgáltató blokkolása a `/models` végponthoz                              |
 | 🔒 **Proxy láthatósága**          | Színkódolt jelvények: 🟢 globális, 🟡 szolgáltató, 🔵 kapcsolatonként IP kijelzővel       |
 | 🌐 **3-szintű proxykonfiguráció** | Proxyk konfigurálása globális, szolgáltatónkénti vagy kapcsolatonkénti szinten            |

README.id.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Mulai Cepat
 
 **1. Instal secara global:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Model Khusus**                  | Tambahkan ID model apa pun ke penyedia mana pun                                    |
 | 🌐 **Router Wildcard**               | Rutekan pola `provider/*` ke penyedia mana pun secara dinamis                      |
 | 🧠 **Memikirkan Anggaran**           | Mode passthrough, otomatis, kustom, dan adaptif untuk model penalaran              |
+| 🔀 **Model Aliases**                 | Auto-forward deprecated model IDs to current replacements (built-in + custom)      |
+| ⚡ **Background Degradation**        | Auto-route background tasks (titles, summaries) to cheaper models                  |
 | 💬 **Injeksi Perintah Sistem**       | Perintah sistem global diterapkan di semua permintaan                              |
 | 📄 **API Respons**                   | Dukungan penuh OpenAI Responses API (`/v1/responses`) untuk Codex                  |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **Spoofing Sidik Jari TLS**       | Lewati deteksi bot berbasis TLS melalui wreq-js                                            |
 | 🌐 **Pemfilteran IP**                | Daftar yang diizinkan/daftar blokir untuk kontrol akses API                                |
 | 📊 **Batas Tarif yang Dapat Diedit** | RPM yang dapat dikonfigurasi, celah minimum, dan maks secara bersamaan pada tingkat sistem |
+| 💾 **Rate Limit Persistence**        | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness               |
+| 🔄 **Token Refresh Resilience**      | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                     |
 | 🛡 **Perlindungan Titik Akhir API**  | Gerbang autentikasi + pemblokiran penyedia untuk titik akhir `/models`                     |
 | 🔒 **Visibilitas Proksi**            | Lencana berkode warna: 🟢 global, 🟡 penyedia, 🔵 per koneksi dengan tampilan IP           |
 | 🌐 **Konfigurasi Proksi 3 Tingkat**  | Konfigurasikan proxy di tingkat global, per penyedia, atau per koneksi                     |

README.in.md

@@ -80,6 +80,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ त्वरित शुरुआत
 
 **1. विश्व स्तर पर स्थापित करें:**
@@ -208,6 +465,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **कस्टम मॉडल**                 | किसी भी प्रदाता से कोई भी मॉडल आईडी जोड़ें                                           |
 | 🌐 **वाइल्डकार्ड राउटर**          | `provider/*` पैटर्न को गतिशील रूप से किसी भी प्रदाता तक रूट करें                     |
 | 🧠 **सोच बजट**                    | तर्क मॉडल के लिए पासथ्रू, ऑटो, कस्टम और अनुकूली मोड                                  |
+| 🔀 **Model Aliases**              | Auto-forward deprecated model IDs to current replacements (built-in + custom)        |
+| ⚡ **Background Degradation**     | Auto-route background tasks (titles, summaries) to cheaper models                    |
 | 💬 **सिस्टम प्रॉम्प्ट इंजेक्शन**  | ग्लोबल सिस्टम प्रॉम्प्ट सभी अनुरोधों पर लागू किया गया                                |
 | 📄 **प्रतिक्रियाएं एपीआई**        | कोडेक्स के लिए पूर्ण ओपनएआई रिस्पॉन्स एपीआई (`/v1/responses`) समर्थन                 |
 
@@ -233,6 +492,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **टीएलएस फ़िंगरप्रिंट स्पूफ़िंग**  | Wreq-js के माध्यम से टीएलएस-आधारित बॉट डिटेक्शन को बायपास करें               |
 | 🌐 **आईपी फ़िल्टरिंग**                | एपीआई अभिगम नियंत्रण के लिए अनुमति सूची/अवरुद्ध सूची                         |
 | 📊 **संपादन योग्य दर सीमाएँ**         | सिस्टम स्तर पर कॉन्फ़िगर करने योग्य आरपीएम, न्यूनतम अंतर और अधिकतम समवर्ती   |
+| 💾 **Rate Limit Persistence**         | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience**       | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
 | 🛡 **एपीआई एंडपॉइंट सुरक्षा**         | `/models` समापन बिंदु के लिए ऑथेंटिक गेटिंग + प्रदाता अवरोधन                 |
 | 🔒 **प्रॉक्सी दृश्यता**               | रंग-कोडित बैज: 🟢 वैश्विक, 🟡 प्रदाता, 🔵 आईपी डिस्प्ले के साथ प्रति-कनेक्शन |
 | 🌐 **3-स्तरीय प्रॉक्सी कॉन्फ़िगरेशन** | वैश्विक, प्रति-प्रदाता, या प्रति-कनेक्शन स्तर पर प्रॉक्सी कॉन्फ़िगर करें     |

README.it.md

@@ -157,6 +157,263 @@ Risultato: Non smettere mai di programmare, costo minimo
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Avvio Rapido
 
 **1. Installa globalmente:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Modelli personalizzati**            | Aggiungi qualsiasi ID modello a qualsiasi provider                            |
 | 🌐 **Router wildcard**                   | Instrada pattern `provider/*` verso qualsiasi provider dinamicamente          |
 | 🧠 **Budget di ragionamento**            | Modalità passthrough, auto, custom e adaptive per modelli di ragionamento     |
+| 🔀 **Model Aliases**                     | Auto-forward deprecated model IDs to current replacements (built-in + custom) |
+| ⚡ **Background Degradation**            | Auto-route background tasks (titles, summaries) to cheaper models             |
 | 💬 **Iniezione System Prompt**           | System prompt globale applicato a tutte le richieste                          |
 | 📄 **API Responses**                     | Supporto completo per OpenAI Responses API (`/v1/responses`) per Codex        |
 
@@ -327,15 +586,17 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🛡️ Resilienza & Sicurezza
 
-| Funzionalità                    | Cosa Fa                                                        |
-| ------------------------------- | -------------------------------------------------------------- |
-| 🔌 **Circuit Breaker**          | Apertura/chiusura auto per provider con soglie configurabili   |
-| 🛡️ **Anti-Thundering Herd**     | Mutex + semaforo rate-limit per provider con API key           |
-| 🧠 **Cache semantica**          | Cache a due livelli (firma + semantica) riduce costi e latenza |
-| ⚡ **Idempotenza richieste**    | Finestra dedup 5s per richieste duplicate                      |
-| 🔒 **Spoofing TLS Fingerprint** | Bypass rilevamento bot tramite wreq-js                         |
-| 🌐 **Filtro IP**                | Allowlist/blocklist per controllo accesso API                  |
-| 📊 **Rate limit modificabili**  | RPM, gap minimo e concorrenza massima configurabili            |
+| Funzionalità                    | Cosa Fa                                                                      |
+| ------------------------------- | ---------------------------------------------------------------------------- |
+| 🔌 **Circuit Breaker**          | Apertura/chiusura auto per provider con soglie configurabili                 |
+| 🛡️ **Anti-Thundering Herd**     | Mutex + semaforo rate-limit per provider con API key                         |
+| 🧠 **Cache semantica**          | Cache a due livelli (firma + semantica) riduce costi e latenza               |
+| ⚡ **Idempotenza richieste**    | Finestra dedup 5s per richieste duplicate                                    |
+| 🔒 **Spoofing TLS Fingerprint** | Bypass rilevamento bot tramite wreq-js                                       |
+| 🌐 **Filtro IP**                | Allowlist/blocklist per controllo accesso API                                |
+| 📊 **Rate limit modificabili**  | RPM, gap minimo e concorrenza massima configurabili                          |
+| 💾 **Rate Limit Persistence**   | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience** | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
 
 ### 📊 Osservabilità & Analytics
 

README.ja.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ クイックスタート
 
 **1.グローバルにインストール:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **カスタムモデル**                       | 任意のモデル ID を任意のプロバイダーに追加する                                      |
 | 🌐 **ワイルドカードルーター**               | `provider/*` パターンを任意のプロバイダーに動的にルーティングする                   |
 | 🧠 **予算を考える**                         | 推論モデルのパススルー、自動、カスタム、および適応モード                            |
+| 🔀 **Model Aliases**                        | Auto-forward deprecated model IDs to current replacements (built-in + custom)       |
+| ⚡ **Background Degradation**               | Auto-route background tasks (titles, summaries) to cheaper models                   |
 | 💬 **システム プロンプト インジェクション** | すべてのリクエストに適用されるグローバル システム プロンプト                        |
 | 📄 **レスポンス API**                       | Codex の OpenAI Response API (`/v1/responses`) の完全なサポート                     |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS 指紋スプーフィング**    | wreq-js 経由で TLS ベースのボット検出をバイパスする                          |
 | 🌐 **IP フィルタリング**         | API アクセス制御の許可リスト/ブロックリスト                                  |
 | 📊 **編集可能なレート制限**      | システム レベルで構成可能な RPM、最小ギャップ、最大同時実行                  |
+| 💾 **Rate Limit Persistence**    | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience**  | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
 | 🛡 **API エンドポイント保護**    | `/models` エンドポイントの認証ゲート + プロバイダー ブロック                 |
 | 🔒 **プロキシの可視性**          | 色分けされたバッジ: 🟢 グローバル、🟡 プロバイダー、🔵 IP 表示による接続ごと |
 | 🌐 **3 レベルのプロキシ構成**    | グローバル、プロバイダーごと、または接続ごとのレベルでプロキシを構成する     |

README.ko.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ 빠른 시작
 
 **1. 전역적으로 설치:**
@@ -300,19 +557,21 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🧠 코어 라우팅 및 인텔리전스
 
-| 기능                        | 그것이 하는 일                                                            |
-| --------------------------- | ------------------------------------------------------------------------- |
-| 🎯 **스마트 4계층 폴백**    | 자동 경로: 구독 → API 키 → 저렴한 → 무료                                  |
-| 📊 **실시간 할당량 추적**   | 라이브 토큰 수 + 공급자별 카운트다운 재설정                               |
-| 🔄 **형식 번역**            | OpenAI ⇔ Claude ⇔ Gemini ⇔ Cursor ⇔ Kiro 심리스 + 반응위생                |
-| 👥 **다중 계정 지원**       | 지능적인 선택을 통해 공급자당 여러 계정                                   |
-| 🔄 **자동 토큰 새로고침**   | 재시도 시 OAuth 토큰이 자동으로 새로 고쳐집니다.                          |
-| 🎨 **맞춤형 콤보**          | 6가지 전략: 채우기 우선, 라운드 로빈, p2c, 무작위, 최소 사용, 비용 최적화 |
-| 🧩 **맞춤형 모델**          | 모든 공급자에 모델 ID 추가                                                |
-| 🌐 **와일드카드 라우터**    | `provider/*` 패턴을 모든 공급자에게 동적으로 라우팅                       |
-| 🧠 **예산 고려**            | 추론 모델을 위한 패스스루, 자동, 사용자 정의 및 적응형 모드               |
-| 💬 **시스템 프롬프트 삽입** | 모든 요청에 ​​전역 시스템 프롬프트 적용                                   |
-| 📄 **응답 API**             | Codex에 대한 전체 OpenAI 응답 API(`/v1/responses`) 지원                   |
+| 기능                          | 그것이 하는 일                                                                |
+| ----------------------------- | ----------------------------------------------------------------------------- |
+| 🎯 **스마트 4계층 폴백**      | 자동 경로: 구독 → API 키 → 저렴한 → 무료                                      |
+| 📊 **실시간 할당량 추적**     | 라이브 토큰 수 + 공급자별 카운트다운 재설정                                   |
+| 🔄 **형식 번역**              | OpenAI ⇔ Claude ⇔ Gemini ⇔ Cursor ⇔ Kiro 심리스 + 반응위생                    |
+| 👥 **다중 계정 지원**         | 지능적인 선택을 통해 공급자당 여러 계정                                       |
+| 🔄 **자동 토큰 새로고침**     | 재시도 시 OAuth 토큰이 자동으로 새로 고쳐집니다.                              |
+| 🎨 **맞춤형 콤보**            | 6가지 전략: 채우기 우선, 라운드 로빈, p2c, 무작위, 최소 사용, 비용 최적화     |
+| 🧩 **맞춤형 모델**            | 모든 공급자에 모델 ID 추가                                                    |
+| 🌐 **와일드카드 라우터**      | `provider/*` 패턴을 모든 공급자에게 동적으로 라우팅                           |
+| 🧠 **예산 고려**              | 추론 모델을 위한 패스스루, 자동, 사용자 정의 및 적응형 모드                   |
+| 🔀 **Model Aliases**          | Auto-forward deprecated model IDs to current replacements (built-in + custom) |
+| ⚡ **Background Degradation** | Auto-route background tasks (titles, summaries) to cheaper models             |
+| 💬 **시스템 프롬프트 삽입**   | 모든 요청에 ​​전역 시스템 프롬프트 적용                                       |
+| 📄 **응답 API**               | Codex에 대한 전체 OpenAI 응답 API(`/v1/responses`) 지원                       |
 
 ### 🎵 다중 모드 API
 
@@ -327,18 +586,20 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🛡️ 복원력 및 보안
 
-| 기능                         | 그것이 하는 일                                                             |
-| ---------------------------- | -------------------------------------------------------------------------- |
-| 🔌 **회로 차단기**           | 구성 가능한 임계값을 사용하여 공급자별 자동 열기/닫기                      |
-| 🛡️ **천둥 방지 무리**        | API 키 공급자에 대한 뮤텍스 + 세마포 속도 제한                             |
-| 🧠 **의미론적 캐시**         | 2계층 캐시(서명 + 의미 체계)로 비용 및 대기 시간 감소                      |
-| ⚡ **멱등성 요청**           | 중복 요청에 대한 5초 중복 제거 기간                                        |
-| 🔒 **TLS 지문 스푸핑**       | wreq-js를 통해 TLS 기반 봇 감지 우회                                       |
-| 🌐 **IP 필터링**             | API 액세스 제어를 위한 허용 목록/차단 목록                                 |
-| 📊 **편집 가능한 속도 제한** | 시스템 수준에서 구성 가능한 RPM, 최소 간격 및 최대 동시                    |
-| 🛡 **API 엔드포인트 보호**   | `/models` 엔드포인트에 대한 인증 게이팅 + 공급자 차단                      |
-| 🔒 **프록시 가시성**         | 색상으로 구분된 배지: 🟢 글로벌, 🟡 공급자, 🔵 IP 디스플레이를 통한 연결별 |
-| 🌐 **3단계 프록시 구성**     | 글로벌, 공급자별 또는 연결별 수준에서 프록시 구성                          |
+| 기능                            | 그것이 하는 일                                                               |
+| ------------------------------- | ---------------------------------------------------------------------------- |
+| 🔌 **회로 차단기**              | 구성 가능한 임계값을 사용하여 공급자별 자동 열기/닫기                        |
+| 🛡️ **천둥 방지 무리**           | API 키 공급자에 대한 뮤텍스 + 세마포 속도 제한                               |
+| 🧠 **의미론적 캐시**            | 2계층 캐시(서명 + 의미 체계)로 비용 및 대기 시간 감소                        |
+| ⚡ **멱등성 요청**              | 중복 요청에 대한 5초 중복 제거 기간                                          |
+| 🔒 **TLS 지문 스푸핑**          | wreq-js를 통해 TLS 기반 봇 감지 우회                                         |
+| 🌐 **IP 필터링**                | API 액세스 제어를 위한 허용 목록/차단 목록                                   |
+| 📊 **편집 가능한 속도 제한**    | 시스템 수준에서 구성 가능한 RPM, 최소 간격 및 최대 동시                      |
+| 💾 **Rate Limit Persistence**   | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience** | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
+| 🛡 **API 엔드포인트 보호**      | `/models` 엔드포인트에 대한 인증 게이팅 + 공급자 차단                        |
+| 🔒 **프록시 가시성**            | 색상으로 구분된 배지: 🟢 글로벌, 🟡 공급자, 🔵 IP 디스플레이를 통한 연결별   |
+| 🌐 **3단계 프록시 구성**        | 글로벌, 공급자별 또는 연결별 수준에서 프록시 구성                            |
 
 ### 📊 관찰 가능성 및 분석
 

README.md

@@ -7,7 +7,7 @@
 
 _Your universal API proxy — one endpoint, 36+ providers, zero downtime._
 
-**Chat Completions • Embeddings • Image Generation • Audio • Reranking • 100% TypeScript**
+**Chat Completions • Embeddings • Image Generation • Video • Music • Audio • Reranking • 100% TypeScript**
 
 ---
 
@@ -32,7 +32,7 @@ _Connect any AI-powered IDE or CLI tool through OmniRoute — free API gateway f
   <table>
     <tr>
       <td align="center" width="110">
-        <a href="https://github.com/cline/cline">
+        <a href="https://github.com/openclaw/openclaw">
           <img src="./public/providers/openclaw.png" alt="OpenClaw" width="48"/><br/>
           <b>OpenClaw</b>
         </a><br/>
@@ -169,6 +169,267 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 10 providers and 20+ models (OpenAI, xAI, Together, Fireworks, Nebius, Hyperbolic, NanoBanana, Antigravity, SD WebUI, ComfyUI)
+- **Text-to-Video** — `/v1/videos/generations` — ComfyUI (AnimateDiff, SVD) and SD WebUI
+- **Text-to-Music** — `/v1/music/generations` — ComfyUI (Stable Audio Open, MusicGen)
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper + Nvidia NIM, HuggingFace, Qwen3
+- **Text-to-Speech** — `/v1/audio/speech` — ElevenLabs, Nvidia NIM, HuggingFace, Coqui, Tortoise, Qwen3, + existing providers
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
+---
+
 ## ⚡ Quick Start
 
 **1. Install globally:**
@@ -346,19 +607,23 @@ When minimized, OmniRoute lives in your system tray with quick actions:
 | 🧩 **Custom Models**            | Add any model ID to any provider                                               |
 | 🌐 **Wildcard Router**          | Route `provider/*` patterns to any provider dynamically                        |
 | 🧠 **Thinking Budget**          | Passthrough, auto, custom, and adaptive modes for reasoning models             |
+| 🔀 **Model Aliases**            | Auto-forward deprecated model IDs to current replacements (built-in + custom)  |
+| ⚡ **Background Degradation**   | Auto-route background tasks (titles, summaries) to cheaper models              |
 | 💬 **System Prompt Injection**  | Global system prompt applied across all requests                               |
 | 📄 **Responses API**            | Full OpenAI Responses API (`/v1/responses`) support for Codex                  |
 
 ### 🎵 Multi-Modal APIs
 
-| Feature                    | What It Does                                        |
-| -------------------------- | --------------------------------------------------- |
-| 🖼️ **Image Generation**    | `/v1/images/generations` — 4 providers, 9+ models   |
-| 📐 **Embeddings**          | `/v1/embeddings` — 6 providers, 9+ models           |
-| 🎤 **Audio Transcription** | `/v1/audio/transcriptions` — Whisper-compatible     |
-| 🔊 **Text-to-Speech**      | `/v1/audio/speech` — Multi-provider audio synthesis |
-| 🛡️ **Moderations**         | `/v1/moderations` — Content safety checks           |
-| 🔀 **Reranking**           | `/v1/rerank` — Document relevance reranking         |
+| Feature                    | What It Does                                                                     |
+| -------------------------- | -------------------------------------------------------------------------------- |
+| 🖼️ **Image Generation**    | `/v1/images/generations` — 10 providers, 20+ models (cloud + local)              |
+| 📐 **Embeddings**          | `/v1/embeddings` — 6 providers, 9+ models                                        |
+| 🎤 **Audio Transcription** | `/v1/audio/transcriptions` — Whisper + Nvidia NIM, HuggingFace, Qwen3            |
+| 🔊 **Text-to-Speech**      | `/v1/audio/speech` — ElevenLabs, Nvidia NIM, HuggingFace, Coqui, Tortoise, Qwen3 |
+| 🎬 **Video Generation**    | `/v1/videos/generations` — ComfyUI (AnimateDiff, SVD), SD WebUI                  |
+| 🎵 **Music Generation**    | `/v1/music/generations` — ComfyUI (Stable Audio Open, MusicGen)                  |
+| 🛡️ **Moderations**         | `/v1/moderations` — Content safety checks                                        |
+| 🔀 **Reranking**           | `/v1/rerank` — Document relevance reranking                                      |
 
 ### 🛡️ Resilience & Security
 
@@ -371,6 +636,8 @@ When minimized, OmniRoute lives in your system tray with quick actions:
 | 🔒 **TLS Fingerprint Spoofing** | Bypass TLS-based bot detection via wreq-js                                    |
 | 🌐 **IP Filtering**             | Allowlist/blocklist for API access control                                    |
 | 📊 **Editable Rate Limits**     | Configurable RPM, min gap, and max concurrent at system level                 |
+| 💾 **Rate Limit Persistence**   | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness  |
+| 🔄 **Token Refresh Resilience** | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt        |
 | 🛡 **API Endpoint Protection**  | Auth gating + provider blocking for the `/models` endpoint                    |
 | 🔒 **Proxy Visibility**         | Color-coded badges: 🟢 global, 🟡 provider, 🔵 per-connection with IP display |
 | 🌐 **3-Level Proxy Config**     | Configure proxies at global, per-provider, or per-connection level            |
@@ -828,6 +1095,47 @@ Settings → API Configuration:
   Model: if/kimi-k2-thinking
 ```
 
+### OpenCode
+
+**Step 1:** Add OmniRoute as a custom provider:
+
+```bash
+opencode
+/connect
+# Select "Other" → Enter ID: "omniroute" → Enter your OmniRoute API key
+```
+
+**Step 2:** Create/edit `opencode.json` in your project root:
+
+```json
+{
+  "$schema": "https://opencode.ai/config.json",
+  "provider": {
+    "omniroute": {
+      "npm": "@ai-sdk/openai-compatible",
+      "name": "OmniRoute",
+      "options": {
+        "baseURL": "http://localhost:20128/v1"
+      },
+      "models": {
+        "cc/claude-sonnet-4-20250514": { "name": "Claude Sonnet 4" },
+        "gg/gemini-2.5-pro": { "name": "Gemini 2.5 Pro" },
+        "if/kimi-k2-thinking": { "name": "Kimi K2 (Free)" }
+      }
+    }
+  }
+}
+```
+
+**Step 3:** Select the model in OpenCode:
+
+```bash
+/models
+# Select any OmniRoute model from the list
+```
+
+> **Tip:** Add any model available in your OmniRoute `/v1/models` endpoint to the `models` section. Use the format `provider/model-id` from your OmniRoute dashboard.
+
 </details>
 
 ---

README.ms.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Mula Pantas
 
 **1. Pasang secara global:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Model Tersuai**               | Tambahkan sebarang ID model pada mana-mana pembekal                                           |
 | 🌐 **Penghala Wildcard**           | Halakan corak `provider/*` kepada mana-mana pembekal secara dinamik                           |
 | 🧠 **Anggaran Berfikir**           | Mod laluan, auto, tersuai dan adaptif untuk model penaakulan                                  |
+| 🔀 **Model Aliases**               | Auto-forward deprecated model IDs to current replacements (built-in + custom)                 |
+| ⚡ **Background Degradation**      | Auto-route background tasks (titles, summaries) to cheaper models                             |
 | 💬 **System Prompt Suntikan**      | Gesaan sistem global digunakan merentas semua permintaan                                      |
 | 📄 **API Respons**                 | Sokongan OpenAI Responses API (`/v1/responses`) penuh untuk Codex                             |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS Fingerprint Spoofing**     | Pintas pengesanan bot berasaskan TLS melalui wreq-js                                |
 | 🌐 **Penapisan IP**                 | Senarai kebenaran/senarai sekat untuk kawalan akses API                             |
 | 📊 **Had Kadar Boleh Diedit**       | RPM boleh dikonfigurasikan, jurang min dan serentak maksimum pada tahap sistem      |
+| 💾 **Rate Limit Persistence**       | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness        |
+| 🔄 **Token Refresh Resilience**     | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt              |
 | 🛡 **Perlindungan Titik Akhir API** | Gating pengesahan + penyekatan penyedia untuk titik akhir `/models`                 |
 | 🔒 **Keterlihatan Proksi**          | Lencana berkod warna: 🟢 global, 🟡 pembekal, 🔵 setiap sambungan dengan paparan IP |
 | 🌐 **Konfigurasi Proksi 3 Tahap**   | Konfigurasikan proksi pada peringkat global, setiap pembekal atau setiap sambungan  |

README.nl.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Snelle start
 
 **1. Wereldwijd installeren:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Aangepaste modellen**                  | Voeg elke model-ID toe aan elke provider                                                          |
 | 🌐 **Wildcard-router**                      | Stuur `provider/*` patronen dynamisch naar elke provider                                          |
 | 🧠 **Denkbudget**                           | Passthrough-, automatische, aangepaste en adaptieve modi voor redeneermodellen                    |
+| 🔀 **Model Aliases**                        | Auto-forward deprecated model IDs to current replacements (built-in + custom)                     |
+| ⚡ **Background Degradation**               | Auto-route background tasks (titles, summaries) to cheaper models                                 |
 | 💬 **Systeempromptinjectie**                | Algemene systeemprompt toegepast op alle verzoeken                                                |
 | 📄 **Reacties-API**                         | Volledige OpenAI Responses API (`/v1/responses`) ondersteuning voor Codex                         |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS-vingerafdrukspoofing**       | Omzeil TLS-gebaseerde botdetectie via wreq-js                                            |
 | 🌐 **IP-filtering**                   | Toelatingslijst/blokkeerlijst voor API-toegangscontrole                                  |
 | 📊 **Bewerkbare tarieflimieten**      | Configureerbare RPM, minimale tussenruimte en maximale gelijktijdigheid op systeemniveau |
+| 💾 **Rate Limit Persistence**         | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness             |
+| 🔄 **Token Refresh Resilience**       | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                   |
 | 🛡 **API-eindpuntbescherming**        | Auth-gating + providerblokkering voor het `/models` eindpunt                             |
 | 🔒 **Proxyzichtbaarheid**             | Kleurgecodeerde badges: 🟢 wereldwijd, 🟡 provider, 🔵 per verbinding met IP-display     |
 | 🌐 **Proxyconfiguratie op 3 niveaus** | Configureer proxy's op globaal, per provider of per verbindingsniveau                    |

README.no.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Hurtigstart
 
 **1. Installer globalt:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Egendefinerte modeller**      | Legg til hvilken som helst modell-ID til en hvilken som helst leverandør                 |
 | 🌐 **Wildcard-ruter**              | Ruter `provider/*`-mønstre til enhver leverandør dynamisk                                |
 | 🧠 **Tenkebudsjett**               | Passthrough, auto, egendefinerte og adaptive moduser for resonnerende modeller           |
+| 🔀 **Model Aliases**               | Auto-forward deprecated model IDs to current replacements (built-in + custom)            |
+| ⚡ **Background Degradation**      | Auto-route background tasks (titles, summaries) to cheaper models                        |
 | 💬 **Systemprompt-injeksjon**      | Global systemforespørsel brukt på alle forespørsler                                      |
 | 📄 **Responses API**               | Full støtte for OpenAI Responses API (`/v1/responses`) for Codex                         |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS-fingeravtrykkspoofing**  | Omgå TLS-basert botdeteksjon via wreq-js                                      |
 | 🌐 **IP-filtrering**              | Tillatelsesliste/blokkeringsliste for API-tilgangskontroll                    |
 | 📊 **Redigerbare satsgrenser**    | Konfigurerbar RPM, min gap og maks samtidig på systemnivå                     |
+| 💾 **Rate Limit Persistence**     | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness  |
+| 🔄 **Token Refresh Resilience**   | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt        |
 | 🛡 **API-endepunktbeskyttelse**   | Auth-gate + leverandørblokkering for `/models`-endepunktet                    |
 | 🔒 **Proxy-synlighet**            | Fargekodede merker: 🟢 global, 🟡 leverandør, 🔵 per tilkobling med IP-skjerm |
 | 🌐 **3-nivå proxy-konfigurasjon** | Konfigurer proxyer på globalt nivå, per leverandør eller per tilkoblingsnivå  |

README.phi.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Mabilis na Pagsisimula
 
 **1. I-install sa buong mundo:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Mga Custom na Modelo**     | Magdagdag ng anumang ID ng modelo sa anumang provider                                        |
 | 🌐 **Wildcard Router**          | Iruta ang `provider/*` na mga pattern sa anumang provider nang dynamic na                    |
 | 🧠 **Badyet sa Pag-iisip**      | Passthrough, auto, custom, at adaptive mode para sa mga modelo ng pangangatwiran             |
+| 🔀 **Model Aliases**            | Auto-forward deprecated model IDs to current replacements (built-in + custom)                |
+| ⚡ **Background Degradation**   | Auto-route background tasks (titles, summaries) to cheaper models                            |
 | 💬 **System Prompt Injection**  | Inilapat ang global system prompt sa lahat ng kahilingan                                     |
 | 📄 **Responses API**            | Buong OpenAI Responses API (`/v1/responses`) na suporta para sa Codex                        |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS Fingerprint Spoofing**           | I-bypass ang TLS-based na bot detection sa pamamagitan ng wreq-js                     |
 | 🌐 **Pag-filter ng IP**                   | Allowlist/blocklist para sa API access control                                        |
 | 📊 **Mga Nae-edit na Limitasyon sa Rate** | Configurable RPM, min gap, at max na kasabay sa antas ng system                       |
+| 💾 **Rate Limit Persistence**             | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness          |
+| 🔄 **Token Refresh Resilience**           | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                |
 | 🛡 **Proteksyon sa Endpoint ng API**      | Auth gating + pagharang ng provider para sa `/models` endpoint                        |
 | 🔒 **Proxy Visibility**                   | Mga color-coded na badge: 🟢 global, 🟡 provider, 🔵 per-connection na may IP display |
 | 🌐 **3-Level Proxy Config**               | I-configure ang mga proxy sa global, per-provider, o per-connection level             |

README.pl.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Szybki start
 
 **1. Zainstaluj globalnie:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Modele niestandardowe**                   | Dodaj dowolny identyfikator modelu do dowolnego dostawcy                                                         |
 | 🌐 **Router z dziką kartą**                    | Dynamicznie kieruj `provider/*` wzorce do dowolnego dostawcy                                                     |
 | 🧠 **Myślący budżet**                          | Tryby przekazywania, automatyczne, niestandardowe i adaptacyjne dla modeli wnioskowania                          |
+| 🔀 **Model Aliases**                           | Auto-forward deprecated model IDs to current replacements (built-in + custom)                                    |
+| ⚡ **Background Degradation**                  | Auto-route background tasks (titles, summaries) to cheaper models                                                |
 | 💬 **Wstrzyknięcie monitu systemowego**        | Globalny monit systemowy stosowany do wszystkich żądań                                                           |
 | 📄 **API odpowiedzi**                          | Pełna obsługa OpenAI Responses API (`/v1/responses`) dla Codexu                                                  |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **Podrabianie odcisków palców TLS**        | Pomiń wykrywanie botów opartych na TLS poprzez wreq-js                                      |
 | 🌐 **Filtrowanie IP**                         | Lista dozwolonych/blokowanych dla kontroli dostępu API                                      |
 | 📊 **Edytowalne limity stawek**               | Konfigurowalne obroty, minimalna przerwa i maksymalna równowaga na poziomie systemu         |
+| 💾 **Rate Limit Persistence**                 | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness                |
+| 🔄 **Token Refresh Resilience**               | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                      |
 | 🛡 **Ochrona punktu końcowego API**           | Bramkowanie uwierzytelniania + blokowanie dostawcy dla punktu końcowego `/models`           |
 | 🔒 **Widoczność proxy**                       | Oznaczone kolorami plakietki: 🟢 globalny, 🟡 dostawca, 🔵 na połączenie z wyświetlaczem IP |
 | 🌐 **3-poziomowa konfiguracja serwera proxy** | Skonfiguruj serwery proxy na poziomie globalnym, dla dostawcy lub dla połączenia            |

README.pt-BR.md

@@ -7,7 +7,7 @@
 
 _Seu proxy de API universal — um endpoint, 36+ provedores, zero tempo de inatividade._
 
-**Chat Completions • Embeddings • Geração de Imagem • Áudio • Reranking • 100% TypeScript**
+**Chat Completions • Embeddings • Geração de Imagem • Vídeo • Música • Áudio • Reranking • 100% TypeScript**
 
 ---
 
@@ -157,6 +157,265 @@ Resultado: Nunca pare de programar, custo mínimo
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 10 providers and 20+ models (OpenAI, xAI, Together, Fireworks, Nebius, Hyperbolic, NanoBanana, Antigravity, SD WebUI, ComfyUI)
+- **Text-to-Video** — `/v1/videos/generations` — ComfyUI (AnimateDiff, SVD) and SD WebUI
+- **Text-to-Music** — `/v1/music/generations` — ComfyUI (Stable Audio Open, MusicGen)
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper + Nvidia NIM, HuggingFace, Qwen3
+- **Text-to-Speech** — `/v1/audio/speech` — ElevenLabs, Nvidia NIM, HuggingFace, Coqui, Tortoise, Qwen3
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Início Rápido
 
 **1. Instale globalmente:**
@@ -315,45 +574,51 @@ Quando minimizado, o OmniRoute fica na bandeja do sistema com ações rápidas:
 
 ### 🧠 Roteamento e Inteligência
 
-| Funcionalidade                            | O que Faz                                                                       |
-| ----------------------------------------- | ------------------------------------------------------------------------------- |
-| 🎯 **Fallback Inteligente 4 Tiers**       | Auto-roteamento: Assinatura → API Key → Barato → Gratuito                       |
-| 📊 **Rastreamento de Cota em Tempo Real** | Contagem de tokens ao vivo + countdown de reset por provedor                    |
-| 🔄 **Tradução de Formato**                | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro transparente                           |
-| 👥 **Suporte Multi-Conta**                | Múltiplas contas por provedor com seleção inteligente                           |
-| 🔄 **Renovação Automática de Token**      | Tokens OAuth renovam automaticamente com retry                                  |
-| 🎨 **Combos Personalizados**              | 6 estratégias: fill-first, round-robin, p2c, random, least-used, cost-optimized |
-| 🧩 **Modelos Personalizados**             | Adicione qualquer ID de modelo a qualquer provedor                              |
-| 🌐 **Roteador Wildcard**                  | Roteie padrões `provider/*` para qualquer provedor dinamicamente                |
-| 🧠 **Budget de Raciocínio**               | Modos passthrough, auto, custom e adaptativo para modelos de raciocínio         |
-| 💬 **Injeção de System Prompt**           | System prompt global aplicado em todas as requisições                           |
-| 📄 **API Responses**                      | Suporte completo à API Responses da OpenAI (`/v1/responses`) para Codex         |
+| Funcionalidade                            | O que Faz                                                                          |
+| ----------------------------------------- | ---------------------------------------------------------------------------------- |
+| 🎯 **Fallback Inteligente 4 Tiers**       | Auto-roteamento: Assinatura → API Key → Barato → Gratuito                          |
+| 📊 **Rastreamento de Cota em Tempo Real** | Contagem de tokens ao vivo + countdown de reset por provedor                       |
+| 🔄 **Tradução de Formato**                | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro transparente                              |
+| 👥 **Suporte Multi-Conta**                | Múltiplas contas por provedor com seleção inteligente                              |
+| 🔄 **Renovação Automática de Token**      | Tokens OAuth renovam automaticamente com retry                                     |
+| 🎨 **Combos Personalizados**              | 6 estratégias: fill-first, round-robin, p2c, random, least-used, cost-optimized    |
+| 🧩 **Modelos Personalizados**             | Adicione qualquer ID de modelo a qualquer provedor                                 |
+| 🌐 **Roteador Wildcard**                  | Roteie padrões `provider/*` para qualquer provedor dinamicamente                   |
+| 🧠 **Budget de Raciocínio**               | Modos passthrough, auto, custom e adaptativo para modelos de raciocínio            |
+| � **Aliases de Modelo**                   | Redireciona IDs de modelos depreciados para substitutos atuais (built-in + custom) |
+| ⚡ **Degradação em Background**           | Redireciona tarefas em background (títulos, resumos) para modelos mais baratos     |
+| �💬 **Injeção de System Prompt**          | System prompt global aplicado em todas as requisições                              |
+| 📄 **API Responses**                      | Suporte completo à API Responses da OpenAI (`/v1/responses`) para Codex            |
 
 ### 🎵 APIs Multi-Modal
 
-| Funcionalidade              | O que Faz                                            |
-| --------------------------- | ---------------------------------------------------- |
-| 🖼️ **Geração de Imagem**    | `/v1/images/generations` — 4 provedores, 9+ modelos  |
-| 📐 **Embeddings**           | `/v1/embeddings` — 6 provedores, 9+ modelos          |
-| 🎤 **Transcrição de Áudio** | `/v1/audio/transcriptions` — Compatível com Whisper  |
-| 🔊 **Texto para Fala**      | `/v1/audio/speech` — Síntese de áudio multi-provedor |
-| 🛡️ **Moderações**           | `/v1/moderations` — Verificações de segurança        |
-| 🔀 **Reranking**            | `/v1/rerank` — Reranking de relevância de documentos |
+| Funcionalidade              | O que Faz                                                                        |
+| --------------------------- | -------------------------------------------------------------------------------- |
+| 🖼️ **Geração de Imagem**    | `/v1/images/generations` — 10 provedores, 20+ modelos (cloud + local)            |
+| 📐 **Embeddings**           | `/v1/embeddings` — 6 provedores, 9+ modelos                                      |
+| 🎤 **Transcrição de Áudio** | `/v1/audio/transcriptions` — Whisper + Nvidia NIM, HuggingFace, Qwen3            |
+| 🔊 **Texto para Fala**      | `/v1/audio/speech` — ElevenLabs, Nvidia NIM, HuggingFace, Coqui, Tortoise, Qwen3 |
+| 🎬 **Geração de Vídeo**     | `/v1/videos/generations` — ComfyUI (AnimateDiff, SVD), SD WebUI                  |
+| 🎵 **Geração de Música**    | `/v1/music/generations` — ComfyUI (Stable Audio Open, MusicGen)                  |
+| 🛡️ **Moderações**           | `/v1/moderations` — Verificações de segurança                                    |
+| 🔀 **Reranking**            | `/v1/rerank` — Reranking de relevância de documentos                             |
 
 ### 🛡️ Resiliência e Segurança
 
-| Funcionalidade                     | O que Faz                                                                   |
-| ---------------------------------- | --------------------------------------------------------------------------- |
-| 🔌 **Circuit Breaker**             | Auto-abertura/fechamento por provedor com limites configuráveis             |
-| 🛡️ **Anti-Thundering Herd**        | Mutex + semáforo rate-limit para provedores com API key                     |
-| 🧠 **Cache Semântico**             | Cache de duas camadas (assinatura + semântico) reduz custo e latência       |
-| ⚡ **Idempotência de Requisição**  | Janela de dedup de 5s para requisições duplicadas                           |
-| 🔒 **Spoofing de Fingerprint TLS** | Bypass de detecção de bot via TLS com wreq-js                               |
-| 🌐 **Filtragem de IP**             | Allowlist/blocklist para controle de acesso à API                           |
-| 📊 **Rate Limits Editáveis**       | RPM, gap mínimo e concorrência máxima configuráveis                         |
-| 🛡 **Proteção de Endpoint API**    | Gateway de Auth + bloqueio de provedores para o endpoint `/models`          |
-| 🔒 **Visibilidade de Proxy**       | Badges coloridos: 🟢 global, 🟡 provedor, 🔵 por-conexão com exibição de IP |
-| 🌐 **Proxy em 3 Níveis**           | Configure proxies em nível global, por provedor ou por conexão              |
+| Funcionalidade                      | O que Faz                                                                     |
+| ----------------------------------- | ----------------------------------------------------------------------------- |
+| 🔌 **Circuit Breaker**              | Auto-abertura/fechamento por provedor com limites configuráveis               |
+| 🛡️ **Anti-Thundering Herd**         | Mutex + semáforo rate-limit para provedores com API key                       |
+| 🧠 **Cache Semântico**              | Cache de duas camadas (assinatura + semântico) reduz custo e latência         |
+| ⚡ **Idempotência de Requisição**   | Janela de dedup de 5s para requisições duplicadas                             |
+| 🔒 **Spoofing de Fingerprint TLS**  | Bypass de detecção de bot via TLS com wreq-js                                 |
+| 🌐 **Filtragem de IP**              | Allowlist/blocklist para controle de acesso à API                             |
+| 📊 **Rate Limits Editáveis**        | RPM, gap mínimo e concorrência máxima configuráveis                           |
+| 💾 **Persistência de Rate Limits**  | Limites aprendidos persistem via SQLite com debounce de 60s + 24h de validade |
+| 🔄 **Resiliência de Token Refresh** | Circuit breaker por provedor (5 falhas→30min) + timeout de 30s por tentativa  |
+| 🛡 **Proteção de Endpoint API**     | Gateway de Auth + bloqueio de provedores para o endpoint `/models`            |
+| 🔒 **Visibilidade de Proxy**        | Badges coloridos: 🟢 global, 🟡 provedor, 🔵 por-conexão com exibição de IP   |
+| 🌐 **Proxy em 3 Níveis**            | Configure proxies em nível global, por provedor ou por conexão                |
 
 ### 📊 Observabilidade e Analytics
 

README.pt.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Início rápido
 
 **1. Instale globalmente:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Modelos Personalizados**                | Adicione qualquer ID de modelo a qualquer provedor                                                 |
 | 🌐 **Roteador curinga**                      | Rotear padrões `provider/*` para qualquer provedor dinamicamente                                   |
 | 🧠 **Pensando no Orçamento**                 | Modos de passagem, automático, personalizado e adaptativo para modelos de raciocínio               |
+| 🔀 **Model Aliases**                         | Auto-forward deprecated model IDs to current replacements (built-in + custom)                      |
+| ⚡ **Background Degradation**                | Auto-route background tasks (titles, summaries) to cheaper models                                  |
 | 💬 **Injeção imediata do sistema**           | Prompt de sistema global aplicado em todas as solicitações                                         |
 | 📄 **API de respostas**                      | Suporte completo à API de respostas OpenAI (`/v1/responses`) para Codex                            |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **Falsificação de impressão digital TLS** | Ignore a detecção de bot baseada em TLS via wreq-js                                  |
 | 🌐 **Filtragem de IP**                       | Lista de permissões/lista de bloqueio para controle de acesso à API                  |
 | 📊 **Limites de taxas editáveis**            | RPM configurável, intervalo mínimo e simultâneo máximo no nível do sistema           |
+| 💾 **Rate Limit Persistence**                | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness         |
+| 🔄 **Token Refresh Resilience**              | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt               |
 | 🛡 **Proteção de endpoint de API**           | Autenticação + bloqueio de provedor para o endpoint `/models`                        |
 | 🔒 **Visibilidade do proxy**                 | Crachás codificados por cores: 🟢 global, 🟡 provedor, 🔵 por conexão com display IP |
 | 🌐 **Configuração de proxy de 3 níveis**     | Configurar proxies em nível global, por provedor ou por conexão                      |

README.ro.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Pornire rapidă
 
 **1. Instalați la nivel global:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Modele personalizate**                 | Adăugați orice ID de model oricărui furnizor                                                                              |
 | 🌐 **Wildcard Router**                      | Dirijați dinamic modelele `provider/*` către orice furnizor                                                               |
 | 🧠 **Buget de gândire**                     | Moduri de trecere, automat, personalizat și adaptiv pentru modelele de raționament                                        |
+| 🔀 **Model Aliases**                        | Auto-forward deprecated model IDs to current replacements (built-in + custom)                                             |
+| ⚡ **Background Degradation**               | Auto-route background tasks (titles, summaries) to cheaper models                                                         |
 | 💬 **System Prompt Injection**              | Prompt de sistem global aplicat pentru toate solicitările                                                                 |
 | 📄 **Responses API**                        | Compatibilitate completă cu OpenAI Responses API (`/v1/responses`) pentru Codex                                           |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS Fingerprint Spoofing**        | Ocoliți detectarea botului bazată pe TLS prin wreq-js                                |
 | 🌐 **Filtrare IP**                     | Lista permisă/lista blocată pentru controlul accesului API                           |
 | 📊 **Limite de rată editabile**        | RPM configurabil, interval minim și concurență maximă la nivel de sistem             |
+| 💾 **Rate Limit Persistence**          | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness         |
+| 🔄 **Token Refresh Resilience**        | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt               |
 | 🛡 **Protecție API Endpoint**          | Autentificare + blocare furnizor pentru punctul final `/models`                      |
 | 🔒 **Vizibilitatea proxy**             | Ecusoane cu coduri de culoare: 🟢 global, 🟡 furnizor, 🔵 per conexiune cu afișaj IP |
 | 🌐 **Configurare proxy pe 3 niveluri** | Configurați proxy-uri la nivel global, per furnizor sau per conexiune                |

README.ru.md

@@ -157,6 +157,263 @@ _Подключайте любую IDE или CLI-инструмент с AI ч
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Быстрый старт
 
 **1. Установите глобально:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Пользовательские модели**              | Добавьте любой ID модели к любому провайдеру                                  |
 | 🌐 **Wildcard-маршрутизатор**               | Маршрутизируйте паттерны `provider/*` к любому провайдеру динамически         |
 | 🧠 **Бюджет рассуждений**                   | Режимы passthrough, auto, custom и adaptive для моделей рассуждений           |
+| 🔀 **Model Aliases**                        | Auto-forward deprecated model IDs to current replacements (built-in + custom) |
+| ⚡ **Background Degradation**               | Auto-route background tasks (titles, summaries) to cheaper models             |
 | 💬 **Инъекция System Prompt**               | Глобальный system prompt для всех запросов                                    |
 | 📄 **API Responses**                        | Полная поддержка OpenAI Responses API (`/v1/responses`) для Codex             |
 
@@ -327,15 +586,17 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🛡️ Устойчивость и безопасность
 
-| Функция                          | Что делает                                                     |
-| -------------------------------- | -------------------------------------------------------------- |
-| 🔌 **Circuit Breaker**           | Авто-открытие/закрытие по провайдеру с настраиваемыми порогами |
-| 🛡️ **Anti-Thundering Herd**      | Mutex + семафор для API key провайдеров                        |
-| 🧠 **Семантический кеш**         | Двухуровневый кеш (сигнатура + семантика) снижает стоимость    |
-| ⚡ **Идемпотентность запросов**  | 5с окно дедупликации для дублирующихся запросов                |
-| 🔒 **Спуфинг TLS Fingerprint**   | Обход обнаружения ботов через wreq-js                          |
-| 🌐 **Фильтрация IP**             | Allowlist/blocklist для контроля доступа к API                 |
-| 📊 **Настраиваемые Rate Limits** | Настраиваемые RPM, минимальный интервал, макс. конкуррентность |
+| Функция                          | Что делает                                                                   |
+| -------------------------------- | ---------------------------------------------------------------------------- |
+| 🔌 **Circuit Breaker**           | Авто-открытие/закрытие по провайдеру с настраиваемыми порогами               |
+| 🛡️ **Anti-Thundering Herd**      | Mutex + семафор для API key провайдеров                                      |
+| 🧠 **Семантический кеш**         | Двухуровневый кеш (сигнатура + семантика) снижает стоимость                  |
+| ⚡ **Идемпотентность запросов**  | 5с окно дедупликации для дублирующихся запросов                              |
+| 🔒 **Спуфинг TLS Fingerprint**   | Обход обнаружения ботов через wreq-js                                        |
+| 🌐 **Фильтрация IP**             | Allowlist/blocklist для контроля доступа к API                               |
+| 📊 **Настраиваемые Rate Limits** | Настраиваемые RPM, минимальный интервал, макс. конкуррентность               |
+| 💾 **Rate Limit Persistence**    | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience**  | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
 
 ### 📊 Наблюдаемость и аналитика
 

README.sk.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Rýchly štart
 
 **1. Inštalovať globálne:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Vlastné modely**                         | Pridajte akékoľvek ID modelu k akémukoľvek poskytovateľovi                                      |
 | 🌐 **Wildcard Router**                        | Dynamicky smerujte vzory `provider/*` k akémukoľvek poskytovateľovi                             |
 | 🧠 **Premýšľajúci rozpočet**                  | Priechodný, automatický, vlastný a adaptívny režim pre modely uvažovania                        |
+| 🔀 **Model Aliases**                          | Auto-forward deprecated model IDs to current replacements (built-in + custom)                   |
+| ⚡ **Background Degradation**                 | Auto-route background tasks (titles, summaries) to cheaper models                               |
 | 💬 **Promptné vstrekovanie systému**          | Globálna systémová výzva aplikovaná na všetky požiadavky                                        |
 | 📄 **Responses API**                          | Plná podpora OpenAI Responses API (`/v1/responses`) pre Codex                                   |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 ** Spoofing odtlačkov prstov TLS** | Obíďte detekciu botov na báze TLS cez wreq-js                                                              |
 | 🌐 **Filtrovanie IP**                 | Zoznam povolených/blokovaných pre riadenie prístupu API                                                    |
 | 📊 **Upraviteľné limity sadzieb**     | Konfigurovateľné otáčky za minútu, minimálna medzera a maximálna súbežná rýchlosť na systémovej úrovni     |
+| 💾 **Rate Limit Persistence**         | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness                               |
+| 🔄 **Token Refresh Resilience**       | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                                     |
 | 🛡 **API Endpoint Protection**        | Auth gating + blokovanie poskytovateľa pre koncový bod `/models`                                           |
 | 🔒 **Viditeľnosť proxy**              | Farebne rozlíšené odznaky: 🟢 globálne, 🟡 poskytovateľ, 🔵 na pripojenie s IP displejom                   |
 | 🌐 **3-úrovňová konfigurácia proxy**  | Nakonfigurujte proxy na globálnej úrovni, na úrovni jednotlivých poskytovateľov alebo na úrovni pripojenia |

README.sv.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Snabbstart
 
 **1. Installera globalt:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Anpassade modeller**      | Lägg till valfritt modell-ID till valfri leverantör                                       |
 | 🌐 **Wildcard-router**         | Dirigera `provider/*`-mönster till valfri leverantör dynamiskt                            |
 | 🧠 **Tänkande budget**         | Genomgång, auto, anpassade och adaptiva lägen för resonerande modeller                    |
+| 🔀 **Model Aliases**           | Auto-forward deprecated model IDs to current replacements (built-in + custom)             |
+| ⚡ **Background Degradation**  | Auto-route background tasks (titles, summaries) to cheaper models                         |
 | 💬 **System Prompt Injection** | Global systemprompt tillämpas på alla förfrågningar                                       |
 | 📄 **Responses API**           | Fullständigt stöd för OpenAI Responses API (`/v1/responses`) för Codex                    |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **TLS Fingerprint Spoofing**        | Förbi TLS-baserad botdetektering via wreq-js                                      |
 | 🌐 **IP-filtrering**                   | Tillåtelselista/blockeringslista för API-åtkomstkontroll                          |
 | 📊 **Redigerbara hastighetsgränser**   | Konfigurerbart RPM, min gap och max samtidiga på systemnivå                       |
+| 💾 **Rate Limit Persistence**          | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness      |
+| 🔄 **Token Refresh Resilience**        | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt            |
 | 🛡 **API Endpoint Protection**         | Auth gating + leverantörsblockering för `/models` slutpunkt                       |
 | 🔒 **Proxysynlighet**                  | Färgkodade märken: 🟢 global, 🟡 leverantör, 🔵 per anslutning med IP-display     |
 | 🌐 **Proxykonfiguration med 3 nivåer** | Konfigurera proxyservrar på global nivå, per leverantör eller per anslutningsnivå |

README.th.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ เริ่มต้นอย่างรวดเร็ว
 
 **1. ติดตั้งทั่วโลก:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **โมเดลที่กำหนดเอง**              | เพิ่ม ID รุ่นใด ๆ ให้กับผู้ให้บริการ                                              |
 | 🌐 **เราเตอร์ตัวแทน**                | กำหนดเส้นทางรูปแบบ `provider/*` ไปยังผู้ให้บริการใดๆ แบบไดนามิก                   |
 | 🧠 **คิดงบประมาณ**                   | โหมดส่งผ่าน, อัตโนมัติ, กำหนดเอง และแบบปรับได้สำหรับโมเดลการให้เหตุผล             |
+| 🔀 **Model Aliases**                 | Auto-forward deprecated model IDs to current replacements (built-in + custom)     |
+| ⚡ **Background Degradation**        | Auto-route background tasks (titles, summaries) to cheaper models                 |
 | 💌 **ระบบพร้อมฉีด**                  | พร้อมท์ระบบสากลใช้กับคำขอทั้งหมด                                                  |
 | 📄 **API ตอบกลับ**                   | รองรับ OpenAI Responses API เต็มรูปแบบ (`/v1/responses`) สำหรับ Codex             |
 
@@ -327,18 +586,20 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🛡️ ความยืดหยุ่นและความปลอดภัย
 
-| คุณสมบัติ                         | มันทำอะไร                                                                 |
-| --------------------------------- | ------------------------------------------------------------------------- |
-| 🔌 **เซอร์กิตเบรกเกอร์**          | เปิด/ปิดอัตโนมัติต่อผู้ให้บริการพร้อมเกณฑ์ที่กำหนดค่าได้                  |
-| 🛡️ **ฝูงต่อต้านฟ้าร้อง**          | Mutex + ขีดจำกัดอัตราเซมาฟอร์สำหรับผู้ให้บริการคีย์ API                   |
-| 🧠 **แคชความหมาย**                | แคชสองชั้น (ลายเซ็น + ความหมาย) ช่วยลดต้นทุน & เวลาแฝง                    |
-| ⚡ **ขอ Idempotency**             | หน้าต่าง dedup 5s สำหรับคำขอซ้ำ                                           |
-| 🔒 **การปลอมแปลงลายนิ้วมือ TLS**  | เลี่ยงการตรวจจับบอทที่ใช้ TLS ผ่าน wreq-js                                |
-| 🌐 **การกรอง IP**                 | รายการที่อนุญาต/รายการบล็อกสำหรับการควบคุมการเข้าถึง API                  |
-| 📊 **ขีดจำกัดอัตราที่แก้ไขได้**   | RPM ที่กำหนดค่าได้ ช่องว่างขั้นต่ำ และสูงสุดพร้อมกันที่ระดับระบบ          |
-| 🛡 **การป้องกันปลายทาง API**      | การตรวจสอบสิทธิ์ + การบล็อกผู้ให้บริการสำหรับปลายทาง `/models`            |
-| 🔒 **การมองเห็นพร็อกซี**          | ป้ายรหัสสี: 🟢 ทั่วโลก 🟡 ผู้ให้บริการ 🔵 ต่อการเชื่อมต่อพร้อมจอแสดงผล IP |
-| 🌐 **การกำหนดค่าพร็อกซี 3 ระดับ** | กำหนดค่าพร็อกซีในระดับโกลบอล ต่อผู้ให้บริการ หรือต่อการเชื่อมต่อ          |
+| คุณสมบัติ                         | มันทำอะไร                                                                    |
+| --------------------------------- | ---------------------------------------------------------------------------- |
+| 🔌 **เซอร์กิตเบรกเกอร์**          | เปิด/ปิดอัตโนมัติต่อผู้ให้บริการพร้อมเกณฑ์ที่กำหนดค่าได้                     |
+| 🛡️ **ฝูงต่อต้านฟ้าร้อง**          | Mutex + ขีดจำกัดอัตราเซมาฟอร์สำหรับผู้ให้บริการคีย์ API                      |
+| 🧠 **แคชความหมาย**                | แคชสองชั้น (ลายเซ็น + ความหมาย) ช่วยลดต้นทุน & เวลาแฝง                       |
+| ⚡ **ขอ Idempotency**             | หน้าต่าง dedup 5s สำหรับคำขอซ้ำ                                              |
+| 🔒 **การปลอมแปลงลายนิ้วมือ TLS**  | เลี่ยงการตรวจจับบอทที่ใช้ TLS ผ่าน wreq-js                                   |
+| 🌐 **การกรอง IP**                 | รายการที่อนุญาต/รายการบล็อกสำหรับการควบคุมการเข้าถึง API                     |
+| 📊 **ขีดจำกัดอัตราที่แก้ไขได้**   | RPM ที่กำหนดค่าได้ ช่องว่างขั้นต่ำ และสูงสุดพร้อมกันที่ระดับระบบ             |
+| 💾 **Rate Limit Persistence**     | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience**   | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
+| 🛡 **การป้องกันปลายทาง API**      | การตรวจสอบสิทธิ์ + การบล็อกผู้ให้บริการสำหรับปลายทาง `/models`               |
+| 🔒 **การมองเห็นพร็อกซี**          | ป้ายรหัสสี: 🟢 ทั่วโลก 🟡 ผู้ให้บริการ 🔵 ต่อการเชื่อมต่อพร้อมจอแสดงผล IP    |
+| 🌐 **การกำหนดค่าพร็อกซี 3 ระดับ** | กำหนดค่าพร็อกซีในระดับโกลบอล ต่อผู้ให้บริการ หรือต่อการเชื่อมต่อ             |
 
 ### 📊 ความสามารถในการสังเกตและการวิเคราะห์
 

README.uk-UA.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Швидкий старт
 
 **1. Встановити глобально:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Користувацькі моделі**                  | Додайте будь-який ідентифікатор моделі до будь-якого постачальника                                               |
 | 🌐 **Wildcard Router**                       | Динамічно направляйте шаблони `provider/*` до будь-якого постачальника                                           |
 | 🧠 **Мислення про бюджет**                   | Наскрізний, автоматичний, настроюваний і адаптивний режими для моделей міркування                                |
+| 🔀 **Model Aliases**                         | Auto-forward deprecated model IDs to current replacements (built-in + custom)                                    |
+| ⚡ **Background Degradation**                | Auto-route background tasks (titles, summaries) to cheaper models                                                |
 | 💬 **Швидке впровадження системи**           | Глобальне системне підказка застосовується до всіх запитів                                                       |
 | 📄 **API відповідей**                        | Повна підтримка OpenAI Responses API (`/v1/responses`) для Codex                                                 |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **Підробка відбитків пальців TLS** | Обійти виявлення ботів на основі TLS через wreq-js                                                    |
 | 🌐 **IP-фільтрація**                  | Білий/чорний список для керування доступом API                                                        |
 | 📊 **Редаговані ліміти ставок**       | Конфігурація RPM, мінімальний проміжок і максимальна одночасність на рівні системи                    |
+| 💾 **Rate Limit Persistence**         | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness                          |
+| 🔄 **Token Refresh Resilience**       | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                                |
 | 🛡 **API Endpoint Protection**        | Аутентифікація + блокування постачальника для кінцевої точки `/models`                                |
 | 🔒 **Видимість проксі**               | Кольорові значки: 🟢 глобальний, 🟡 постачальник, 🔵 кожне підключення з відображенням IP             |
 | 🌐 **3-рівнева конфігурація проксі**  | Налаштуйте проксі-сервери на глобальному рівні, на рівні кожного постачальника чи кожного підключення |

README.vi.md

@@ -157,6 +157,263 @@ Result: Never stop coding, minimal cost
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ Bắt đầu nhanh
 
 **1. Cài đặt trên toàn cầu:**
@@ -311,6 +568,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🧩 **Mẫu tùy chỉnh**                          | Thêm bất kỳ ID mẫu nào vào bất kỳ nhà cung cấp nào                                        |
 | 🌐 **Bộ định tuyến ký tự đại diện**           | Định tuyến động các mẫu `provider/*` tới bất kỳ nhà cung cấp nào                          |
 | 🧠 **Ngân sách suy nghĩ**                     | Các chế độ truyền qua, tự động, tùy chỉnh và thích ứng cho các mô hình lý luận            |
+| 🔀 **Model Aliases**                          | Auto-forward deprecated model IDs to current replacements (built-in + custom)             |
+| ⚡ **Background Degradation**                 | Auto-route background tasks (titles, summaries) to cheaper models                         |
 | 💬 **Tiêm nhắc nhở hệ thống**                 | Lời nhắc hệ thống toàn cầu được áp dụng cho tất cả các yêu cầu                            |
 | 📄 **API phản hồi**                           | Hỗ trợ đầy đủ API phản hồi OpenAI (`/v1/responses`) cho Codex                             |
 
@@ -336,6 +595,8 @@ npm run electron:build:linux   # Linux (.AppImage)
 | 🔒 **Giả mạo vân tay TLS**             | Bỏ qua việc phát hiện bot dựa trên TLS thông qua wreq-js                               |
 | 🌐 **Lọc IP**                          | Danh sách cho phép/danh sách chặn để kiểm soát truy cập API                            |
 | 📊 **Giới hạn tỷ lệ có thể chỉnh sửa** | RPM có thể định cấu hình, khoảng cách tối thiểu và đồng thời tối đa ở cấp hệ thống     |
+| 💾 **Rate Limit Persistence**          | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness           |
+| 🔄 **Token Refresh Resilience**        | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt                 |
 | 🛡 **Bảo vệ điểm cuối API**            | Kiểm soát xác thực + chặn nhà cung cấp cho điểm cuối `/models`                         |
 | 🔒 **Khả năng hiển thị proxy**         | Huy hiệu được mã hóa màu: 🟢 toàn cầu, 🟡 nhà cung cấp, 🔵 mỗi kết nối với màn hình IP |
 | 🌐 **Cấu hình proxy 3 cấp**            | Định cấu hình proxy ở cấp độ toàn cầu, theo nhà cung cấp hoặc theo từng kết nối        |

README.zh-CN.md

@@ -157,6 +157,263 @@ _通过 OmniRoute 连接任何 AI 驱动的 IDE 或 CLI 工具 — 免费 API
 
 ---
 
+## 🎯 What OmniRoute Solves — 16 Real Pain Points
+
+> **Every developer using AI tools faces these problems daily.** OmniRoute was built to solve them all — from cost overruns to regional blocks, from broken OAuth flows to zero observability.
+
+<details>
+<summary><b>💸 1. "I pay for an expensive subscription but still get interrupted by limits"</b></summary>
+
+Developers pay $20–200/month for Claude Pro, Codex Pro, or GitHub Copilot. Even paying, quota has a ceiling — 5h of usage, weekly limits, or per-minute rate limits. Mid-coding session, the provider stops responding and the developer loses flow and productivity.
+
+**How OmniRoute solves it:**
+
+- **Smart 4-Tier Fallback** — If subscription quota runs out, automatically redirects to API Key → Cheap → Free with zero manual intervention
+- **Real-Time Quota Tracking** — Shows token consumption in real-time with reset countdown (5h, daily, weekly)
+- **Multi-Account Support** — Multiple accounts per provider with auto round-robin — when one runs out, switches to the next
+- **Custom Combos** — Customizable fallback chains with 6 balancing strategies (fill-first, round-robin, P2C, random, least-used, cost-optimized)
+- **Codex Business Quotas** — Business/Team workspace quota monitoring directly in the dashboard
+
+</details>
+
+<details>
+<summary><b>🔌 2. "I need to use multiple providers but each has a different API"</b></summary>
+
+OpenAI uses one format, Claude (Anthropic) uses another, Gemini yet another. If a dev wants to test models from different providers or fallback between them, they need to reconfigure SDKs, change endpoints, deal with incompatible formats. Custom providers (FriendLI, NIM) have non-standard model endpoints.
+
+**How OmniRoute solves it:**
+
+- **Unified Endpoint** — A single `http://localhost:20128/v1` serves as proxy for all 36+ providers
+- **Format Translation** — Automatic and transparent: OpenAI ↔ Claude ↔ Gemini ↔ Responses API
+- **Response Sanitization** — Strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`) that break OpenAI SDK v1.83+
+- **Role Normalization** — Converts `developer` → `system` for non-OpenAI providers; `system` → `user` for GLM/ERNIE
+- **Think Tag Extraction** — Extracts `<think>` blocks from models like DeepSeek R1 into standardized `reasoning_content`
+- **Structured Output for Gemini** — `json_schema` → `responseMimeType`/`responseSchema` automatic conversion
+- **`stream` defaults to `false`** — Aligns with OpenAI spec, avoiding unexpected SSE in Python/Rust/Go SDKs
+
+</details>
+
+<details>
+<summary><b>🌐 3. "My AI provider blocks my region/country"</b></summary>
+
+Providers like OpenAI/Codex block access from certain geographic regions. Users get errors like `unsupported_country_region_territory` during OAuth and API connections. This is especially frustrating for developers from developing countries.
+
+**How OmniRoute solves it:**
+
+- **3-Level Proxy Config** — Configurable proxy at 3 levels: global (all traffic), per-provider (one provider only), and per-connection/key
+- **Color-Coded Proxy Badges** — Visual indicators: 🟢 global proxy, 🟡 provider proxy, 🔵 connection proxy, always showing the IP
+- **OAuth Token Exchange Through Proxy** — OAuth flow also goes through the proxy, solving `unsupported_country_region_territory`
+- **Connection Tests via Proxy** — Connection tests use the configured proxy (no more direct bypass)
+- **SOCKS5 Support** — Full SOCKS5 proxy support for outbound routing
+- **TLS Fingerprint Spoofing** — Browser-like TLS fingerprint via `wreq-js` to bypass bot detection
+
+</details>
+
+<details>
+<summary><b>🆓 4. "I want to use AI for coding but I have no money"</b></summary>
+
+Not everyone can pay $20–200/month for AI subscriptions. Students, devs from emerging countries, hobbyists, and freelancers need access to quality models at zero cost.
+
+**How OmniRoute solves it:**
+
+- **Free Tier Providers Built-in** — Native support for 100% free providers: iFlow (8 unlimited models), Qwen (3 unlimited models), Kiro (Claude for free), Gemini CLI (180K/month free)
+- **Free-Only Combos** — Chain `gc/gemini-3-flash → if/kimi-k2-thinking → qw/qwen3-coder-plus` = $0/month with zero downtime
+- **NVIDIA NIM Free Credits** — 1000 free credits integrated
+- **Cost Optimized Strategy** — Routing strategy that automatically chooses the cheapest available provider
+
+</details>
+
+<details>
+<summary><b>🔒 5. "I need to protect my AI gateway from unauthorized access"</b></summary>
+
+When exposing an AI gateway to the network (LAN, VPS, Docker), anyone with the address can consume the developer's tokens/quota. Without protection, APIs are vulnerable to misuse, prompt injection, and abuse.
+
+**How OmniRoute solves it:**
+
+- **API Key Management** — Generation, rotation, and scoping per provider with a dedicated `/dashboard/api-manager` page
+- **Model-Level Permissions** — Restrict API keys to specific models (`openai/*`, wildcard patterns), with Allow All/Restrict toggle
+- **API Endpoint Protection** — Require a key for `/v1/models` and block specific providers from the listing
+- **Auth Guard + CSRF Protection** — All dashboard routes protected with `withAuth` middleware + CSRF tokens
+- **Rate Limiter** — Per-IP rate limiting with configurable windows
+- **IP Filtering** — Allowlist/blocklist for access control
+- **Prompt Injection Guard** — Sanitization against malicious prompt patterns
+- **AES-256-GCM Encryption** — Credentials encrypted at rest
+
+</details>
+
+<details>
+<summary><b>🛑 6. "My provider went down and I lost my coding flow"</b></summary>
+
+AI providers can become unstable, return 5xx errors, or hit temporary rate limits. If a dev depends on a single provider, they're interrupted. Without circuit breakers, repeated retries can crash the application.
+
+**How OmniRoute solves it:**
+
+- **Circuit Breaker per-provider** — Auto-open/close with configurable thresholds and cooldown (Closed/Open/Half-Open)
+- **Exponential Backoff** — Progressive retry delays
+- **Anti-Thundering Herd** — Mutex + semaphore protection against concurrent retry storms
+- **Combo Fallback Chains** — If the primary provider fails, automatically falls through the chain with no intervention
+- **Combo Circuit Breaker** — Auto-disables failing providers within a combo chain
+- **Health Dashboard** — Uptime monitoring, circuit breaker states, lockouts, cache stats, p50/p95/p99 latency
+
+</details>
+
+<details>
+<summary><b>🔧 7. "Configuring each AI tool is tedious and repetitive"</b></summary>
+
+Developers use Cursor, Claude Code, Codex CLI, OpenClaw, Gemini CLI, Kilo Code... Each tool needs a different config (API endpoint, key, model). Reconfiguring when switching providers or models is a waste of time.
+
+**How OmniRoute solves it:**
+
+- **CLI Tools Dashboard** — Dedicated page with one-click setup for Claude Code, Codex CLI, OpenClaw, Kilo Code, Antigravity, Cline
+- **GitHub Copilot Config Generator** — Generates `chatLanguageModels.json` for VS Code with bulk model selection
+- **Onboarding Wizard** — Guided 4-step setup for first-time users
+- **One endpoint, all models** — Configure `http://localhost:20128/v1` once, access 36+ providers
+
+</details>
+
+<details>
+<summary><b>🔑 8. "Managing OAuth tokens from multiple providers is hell"</b></summary>
+
+Claude Code, Codex, Gemini CLI, Copilot — all use OAuth 2.0 with expiring tokens. Developers need to re-authenticate constantly, deal with `client_secret is missing`, `redirect_uri_mismatch`, and failures on remote servers. OAuth on LAN/VPS is particularly problematic.
+
+**How OmniRoute solves it:**
+
+- **Auto Token Refresh** — OAuth tokens refresh in background before expiration
+- **OAuth 2.0 (PKCE) Built-in** — Automatic flow for Claude Code, Codex, Gemini CLI, Copilot, Kiro, Qwen, iFlow
+- **Multi-Account OAuth** — Multiple accounts per provider via JWT/ID token extraction
+- **OAuth LAN/Remote Fix** — Private IP detection for `redirect_uri` + manual URL mode for remote servers
+- **OAuth Behind Nginx** — Uses `window.location.origin` for reverse proxy compatibility
+- **Remote OAuth Guide** — Step-by-step guide for Google Cloud credentials on VPS/Docker
+
+</details>
+
+<details>
+<summary><b>📊 9. "I don't know how much I'm spending or where"</b></summary>
+
+Developers use multiple paid providers but have no unified view of spending. Each provider has its own billing dashboard, but there's no consolidated view. Unexpected costs can pile up.
+
+**How OmniRoute solves it:**
+
+- **Cost Analytics Dashboard** — Per-token cost tracking and budget management per provider
+- **Budget Limits per Tier** — Spending ceiling per tier that triggers automatic fallback
+- **Per-Model Pricing Configuration** — Configurable prices per model
+- **Usage Statistics Per API Key** — Request count and last-used timestamp per key
+- **Analytics Dashboard** — Stat cards, model usage chart, provider table with success rates and latency
+
+</details>
+
+<details>
+<summary><b>🐛 10. "I can't diagnose errors and problems in AI calls"</b></summary>
+
+When a call fails, the dev doesn't know if it was a rate limit, expired token, wrong format, or provider error. Fragmented logs across different terminals. Without observability, debugging is trial-and-error.
+
+**How OmniRoute solves it:**
+
+- **Unified Logs Dashboard** — 4 tabs: Request Logs, Proxy Logs, Audit Logs, Console
+- **Console Log Viewer** — Real-time terminal-style viewer with color-coded levels, auto-scroll, search, filter
+- **SQLite Proxy Logs** — Persistent logs that survive server restarts
+- **Translator Playground** — 4 debugging modes: Playground (format translation), Chat Tester (round-trip), Test Bench (batch), Live Monitor (real-time)
+- **Request Telemetry** — p50/p95/p99 latency + X-Request-Id tracing
+- **File-Based Logging with Rotation** — Console interceptor captures everything to JSON log with size-based rotation
+
+</details>
+
+<details>
+<summary><b>🏗️ 11. "Deploying and maintaining the gateway is complex"</b></summary>
+
+Installing, configuring, and maintaining an AI proxy across different environments (local, VPS, Docker, cloud) is labor-intensive. Problems like hardcoded paths, `EACCES` on directories, port conflicts, and cross-platform builds add friction.
+
+**How OmniRoute solves it:**
+
+- **npm global install** — `npm install -g omniroute && omniroute` — done
+- **Docker Multi-Platform** — AMD64 + ARM64 native (Apple Silicon, AWS Graviton, Raspberry Pi)
+- **Docker Compose Profiles** — `base` (no CLI tools) and `cli` (with Claude Code, Codex, OpenClaw)
+- **Electron Desktop App** — Native app for Windows/macOS/Linux with system tray, auto-start, offline mode
+- **Split-Port Mode** — API and Dashboard on separate ports for advanced scenarios (reverse proxy, container networking)
+- **Cloud Sync** — Config synchronization across devices via Cloudflare Workers
+- **DB Backups** — Automatic backup, restore, export and import of all settings
+
+</details>
+
+<details>
+<summary><b>🌍 12. "The interface is English-only and my team doesn't speak English"</b></summary>
+
+Teams in non-English-speaking countries, especially in Latin America, Asia, and Europe, struggle with English-only interfaces. Language barriers reduce adoption and increase configuration errors.
+
+**How OmniRoute solves it:**
+
+- **Dashboard i18n — 30 Languages** — All 500+ keys translated including Arabic, Bulgarian, Danish, German, Spanish, Finnish, French, Hebrew, Hindi, Hungarian, Indonesian, Italian, Japanese, Korean, Malay, Dutch, Norwegian, Polish, Portuguese (PT/BR), Romanian, Russian, Slovak, Swedish, Thai, Ukrainian, Vietnamese, Chinese, Filipino, English
+- **RTL Support** — Right-to-left support for Arabic and Hebrew
+- **Multi-Language READMEs** — 30 complete documentation translations
+- **Language Selector** — Globe icon in header for real-time switching
+
+</details>
+
+<details>
+<summary><b>🔄 13. "I need more than chat — I need embeddings, images, audio"</b></summary>
+
+AI isn't just chat completion. Devs need to generate images, transcribe audio, create embeddings for RAG, rerank documents, and moderate content. Each API has a different endpoint and format.
+
+**How OmniRoute solves it:**
+
+- **Embeddings** — `/v1/embeddings` with 6 providers and 9+ models
+- **Image Generation** — `/v1/images/generations` with 4 providers and 9+ models
+- **Audio Transcription** — `/v1/audio/transcriptions` — Whisper-compatible
+- **Text-to-Speech** — `/v1/audio/speech` — Multi-provider audio synthesis
+- **Moderations** — `/v1/moderations` — Content safety checks
+- **Reranking** — `/v1/rerank` — Document relevance reranking
+- **Responses API** — Full `/v1/responses` support for Codex
+
+</details>
+
+<details>
+<summary><b>🧪 14. "I have no way to test and compare quality across models"</b></summary>
+
+Developers want to know which model is best for their use case — code, translation, reasoning — but comparing manually is slow. No integrated eval tools exist.
+
+**How OmniRoute solves it:**
+
+- **LLM Evaluations** — Golden set testing with 10 pre-loaded cases covering greetings, math, geography, code generation, JSON compliance, translation, markdown, safety refusal
+- **4 Match Strategies** — `exact`, `contains`, `regex`, `custom` (JS function)
+- **Translator Playground Test Bench** — Batch testing with multiple inputs and expected outputs, cross-provider comparison
+- **Chat Tester** — Full round-trip with visual response rendering
+- **Live Monitor** — Real-time stream of all requests flowing through the proxy
+
+</details>
+
+<details>
+<summary><b>📈 15. "I need to scale without losing performance"</b></summary>
+
+As request volume grows, without caching the same questions generate duplicate costs. Without idempotency, duplicate requests waste processing. Per-provider rate limits must be respected.
+
+**How OmniRoute solves it:**
+
+- **Semantic Cache** — Two-tier cache (signature + semantic) reduces cost and latency
+- **Request Idempotency** — 5s deduplication window for identical requests
+- **Rate Limit Detection** — Per-provider RPM, min gap, and max concurrent tracking
+- **Editable Rate Limits** — Configurable defaults in Settings → Resilience with persistence
+- **API Key Validation Cache** — 3-tier cache for production performance
+- **Health Dashboard with Telemetry** — p50/p95/p99 latency, cache stats, uptime
+
+</details>
+
+<details>
+<summary><b>🤖 16. "I want to control model behavior globally"</b></summary>
+
+Developers who want all responses in a specific language, with a specific tone, or want to limit reasoning tokens. Configuring this in every tool/request is impractical.
+
+**How OmniRoute solves it:**
+
+- **System Prompt Injection** — Global prompt applied to all requests
+- **Thinking Budget Validation** — Reasoning token allocation control per request (passthrough, auto, custom, adaptive)
+- **6 Routing Strategies** — Global strategies that determine how requests are distributed
+- **Wildcard Router** — `provider/*` patterns route dynamically to any provider
+- **Combo Enable/Disable Toggle** — Toggle combos directly from the dashboard
+- **Provider Toggle** — Enable/disable all connections for a provider with one click
+- **Blocked Providers** — Exclude specific providers from `/v1/models` listing
+
+</details>
+
 ## ⚡ 快速开始
 
 **1. 全局安装：**
@@ -300,19 +557,21 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🧠 路由与智能
 
-| 功能                      | 功能描述                                                                   |
-| ------------------------- | -------------------------------------------------------------------------- |
-| 🎯 **智能 4 层故障转移**  | 自动路由：订阅 → API Key → 低价 → 免费                                     |
-| 📊 **实时配额追踪**       | 实时 Token 计数 + 每个提供商的重置倒计时                                   |
-| 🔄 **格式转换**           | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro 无缝切换                          |
-| 👥 **多账号支持**         | 每个提供商多个账号，智能选择                                               |
-| 🔄 **自动令牌刷新**       | OAuth 令牌自动刷新并重试                                                   |
-| 🎨 **自定义组合**         | 6 种策略：fill-first、round-robin、p2c、random、least-used、cost-optimized |
-| 🧩 **自定义模型**         | 为任何提供商添加任何模型 ID                                                |
-| 🌐 **通配符路由**         | 动态路由 `provider/*` 模式到任何提供商                                     |
-| 🧠 **推理预算**           | passthrough、auto、custom 和 adaptive 模式用于推理模型                     |
-| 💬 **System Prompt 注入** | 全局 System Prompt 应用于所有请求                                          |
-| 📄 **Responses API**      | 完整支持 OpenAI Responses API (`/v1/responses`) 用于 Codex                 |
+| 功能                          | 功能描述                                                                      |
+| ----------------------------- | ----------------------------------------------------------------------------- |
+| 🎯 **智能 4 层故障转移**      | 自动路由：订阅 → API Key → 低价 → 免费                                        |
+| 📊 **实时配额追踪**           | 实时 Token 计数 + 每个提供商的重置倒计时                                      |
+| 🔄 **格式转换**               | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro 无缝切换                             |
+| 👥 **多账号支持**             | 每个提供商多个账号，智能选择                                                  |
+| 🔄 **自动令牌刷新**           | OAuth 令牌自动刷新并重试                                                      |
+| 🎨 **自定义组合**             | 6 种策略：fill-first、round-robin、p2c、random、least-used、cost-optimized    |
+| 🧩 **自定义模型**             | 为任何提供商添加任何模型 ID                                                   |
+| 🌐 **通配符路由**             | 动态路由 `provider/*` 模式到任何提供商                                        |
+| 🧠 **推理预算**               | passthrough、auto、custom 和 adaptive 模式用于推理模型                        |
+| 🔀 **Model Aliases**          | Auto-forward deprecated model IDs to current replacements (built-in + custom) |
+| ⚡ **Background Degradation** | Auto-route background tasks (titles, summaries) to cheaper models             |
+| 💬 **System Prompt 注入**     | 全局 System Prompt 应用于所有请求                                             |
+| 📄 **Responses API**          | 完整支持 OpenAI Responses API (`/v1/responses`) 用于 Codex                    |
 
 ### 🎵 多模态 API
 
@@ -327,15 +586,17 @@ npm run electron:build:linux   # Linux (.AppImage)
 
 ### 🛡️ 弹性与安全
 
-| 功能                  | 功能描述                               |
-| --------------------- | -------------------------------------- |
-| 🔌 **断路器**         | 每个提供商自动打开/关闭，可配置阈值    |
-| 🛡️ **反惊群**         | Mutex + 信号量限速用于 API Key 提供商  |
-| 🧠 **语义缓存**       | 两层缓存（签名 + 语义）降低成本和延迟  |
-| ⚡ **请求幂等性**     | 5 秒去重窗口防止重复请求               |
-| 🔒 **TLS 指纹伪装**   | 通过 wreq-js 绕过基于 TLS 的机器人检测 |
-| 🌐 **IP 过滤**        | 白名单/黑名单用于 API 访问控制         |
-| 📊 **可编辑速率限制** | 可配置的 RPM、最小间隔和最大并发       |
+| 功能                            | 功能描述                                                                     |
+| ------------------------------- | ---------------------------------------------------------------------------- |
+| 🔌 **断路器**                   | 每个提供商自动打开/关闭，可配置阈值                                          |
+| 🛡️ **反惊群**                   | Mutex + 信号量限速用于 API Key 提供商                                        |
+| 🧠 **语义缓存**                 | 两层缓存（签名 + 语义）降低成本和延迟                                        |
+| ⚡ **请求幂等性**               | 5 秒去重窗口防止重复请求                                                     |
+| 🔒 **TLS 指纹伪装**             | 通过 wreq-js 绕过基于 TLS 的机器人检测                                       |
+| 🌐 **IP 过滤**                  | 白名单/黑名单用于 API 访问控制                                               |
+| 📊 **可编辑速率限制**           | 可配置的 RPM、最小间隔和最大并发                                             |
+| 💾 **Rate Limit Persistence**   | Learned limits survive restarts via SQLite with 60s debounce + 24h staleness |
+| 🔄 **Token Refresh Resilience** | Per-provider circuit breaker (5 fails→30min) + 30s timeout per attempt       |
 
 ### 📊 可观察性与分析
 

docs/FEATURES.md

@@ -48,7 +48,7 @@ Four modes for debugging API translations: **Playground** (format converter), **
 
 ## ⚙️ Settings
 
-General settings, system storage, backup management (export/import database), appearance (dark/light mode), security (includes API endpoint protection and custom provider blocking), routing, resilience, and advanced configuration.
+General settings, system storage, backup management (export/import database), appearance (dark/light mode), security (includes API endpoint protection and custom provider blocking), routing (model aliases, background task degradation), resilience (rate limit persistence), and advanced configuration.
 
 ![Settings Dashboard](screenshots/06-settings.png)
 

docs/TROUBLESHOOTING.md

@@ -210,6 +210,41 @@ When many concurrent requests hit a rate-limited provider, OmniRoute uses mutex
 
 ---
 
+## Optional RAG / LLM failure taxonomy (16 problems)
+
+Some OmniRoute users place the gateway in front of RAG or agent stacks. In those setups it is common to see a strange pattern: OmniRoute looks healthy (providers up, routing profiles ok, no rate limit alerts) but the final answer is still wrong.
+
+In practice these incidents usually come from the downstream RAG pipeline, not from the gateway itself.
+
+If you want a shared vocabulary to describe those failures you can use the WFGY ProblemMap, an external MIT license text resource that defines sixteen recurring RAG / LLM failure patterns. At a high level it covers:
+
+- retrieval drift and broken context boundaries
+- empty or stale indexes and vector stores
+- embedding versus semantic mismatch
+- prompt assembly and context window issues
+- logic collapse and overconfident answers
+- long chain and agent coordination failures
+- multi agent memory and role drift
+- deployment and bootstrap ordering problems
+
+The idea is simple:
+
+1. When you investigate a bad response, capture:
+   - user task and request
+   - route or provider combo in OmniRoute
+   - any RAG context used downstream (retrieved documents, tool calls, etc)
+2. Map the incident to one or two WFGY ProblemMap numbers (`No.1` … `No.16`).
+3. Store the number in your own dashboard, runbook, or incident tracker next to the OmniRoute logs.
+4. Use the corresponding WFGY page to decide whether you need to change your RAG stack, retriever, or routing strategy.
+
+Full text and concrete recipes live here (MIT license, text only):
+
+[WFGY ProblemMap README](https://github.com/onestardao/WFGY/blob/main/ProblemMap/README.md)
+
+You can ignore this section if you do not run RAG or agent pipelines behind OmniRoute.
+
+---
+
 ## Still Stuck?
 
 - **GitHub Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)

docs/i18n/da/FEATURES.md

@@ -16,7 +16,7 @@ Administrer AI-udbyderforbindelser: OAuth-udbydere (Claude Code, Codex, Gemini C
 
 ## 🎨 Kombinationer
 
-Opret modelrouting-kombinationer med 6 strategier: Fyld-først, round-robin, power-of-to-choices, tilfældig, mindst brugt og omkostningsoptimeret. Hver combo kæder flere modeller med automatisk fallback.
+Opret modelrouting (model aliases, background task degradation)-kombinationer med 6 strategier: Fyld-først, round-robin, power-of-to-choices, tilfældig, mindst brugt og omkostningsoptimeret. Hver combo kæder flere modeller med automatisk fallback.
 
 ![Combos Dashboard](screenshots/02-combos.png)
 

docs/i18n/it/FEATURES.md

@@ -16,7 +16,7 @@ Gestisci le connessioni dei provider AI: provider OAuth (Claude Code, Codex, Gem
 
 ## 🎨Combo
 
-Crea combinazioni di routing del modello con 6 strategie: riempimento prima, round robin, scelta potenza di due, casuale, meno utilizzata e con ottimizzazione dei costi. Ogni combo concatena più modelli con fallback automatico.
+Crea combinazioni di routing (model aliases, background task degradation) del modello con 6 strategie: riempimento prima, round robin, scelta potenza di due, casuale, meno utilizzata e con ottimizzazione dei costi. Ogni combo concatena più modelli con fallback automatico.
 
 ![Combos Dashboard](screenshots/02-combos.png)
 

docs/i18n/nl/FEATURES.md

@@ -48,7 +48,7 @@ Vier modi voor het debuggen van API-vertalingen: **Playground** (formaatconverte
 
 ## ⚙️ Instellingen
 
-Algemene instellingen, systeemopslag, back-upbeheer (database exporteren/importeren), uiterlijk (donker/licht-modus), beveiliging (inclusief API-eindpuntbescherming en aangepaste providerblokkering), routing, veerkracht en geavanceerde configuratie.
+Algemene instellingen, systeemopslag, back-upbeheer (database exporteren/importeren), uiterlijk (donker/licht-modus), beveiliging (inclusief API-eindpuntbescherming en aangepaste providerblokkering), routing (model aliases, background task degradation), veerkracht en geavanceerde configuratie.
 
 ![Settings Dashboard](screenshots/06-settings.png)
 

docs/i18n/phi/FEATURES.md

@@ -48,7 +48,7 @@ Apat na mode para sa pag-debug ng mga pagsasalin ng API: **Playground** (format
 
 ## ⚙️ Mga Setting
 
-Mga pangkalahatang setting, system storage, backup management (export/import database), hitsura (dark/light mode), seguridad (kasama ang API endpoint protection at custom provider blocking), routing, resilience, at advanced configuration.
+Mga pangkalahatang setting, system storage, backup management (export/import database), hitsura (dark/light mode), seguridad (kasama ang API endpoint protection at custom provider blocking), routing (model aliases, background task degradation), resilience, at advanced configuration.
 
 ![Settings Dashboard](screenshots/06-settings.png)
 

docs/i18n/pl/FEATURES.md

@@ -16,7 +16,7 @@ Zarządzaj połączeniami dostawców AI: dostawcy OAuth (Claude Code, Codex, Gem
 
 ## 🎨 Kombinacje
 
-Twórz kombinacje routingu modeli za pomocą 6 strategii: najpierw wypełnij, okrężnie, siła dwóch wyborów, losowa, najrzadziej używana i zoptymalizowana pod względem kosztów. Każda kombinacja łączy wiele modeli z automatycznym cofaniem.
+Twórz kombinacje routing (model aliases, background task degradation)u modeli za pomocą 6 strategii: najpierw wypełnij, okrężnie, siła dwóch wyborów, losowa, najrzadziej używana i zoptymalizowana pod względem kosztów. Każda kombinacja łączy wiele modeli z automatycznym cofaniem.
 
 ![Combos Dashboard](screenshots/02-combos.png)
 

docs/i18n/sv/FEATURES.md

@@ -16,7 +16,7 @@ Hantera AI-leverantörsanslutningar: OAuth-leverantörer (Claude Code, Codex, Ge
 
 ## 🎨 Combos
 
-Skapa modell routing-kombinationer med 6 strategier: fyll först, round-robin, kraft-av-två-val, slumpmässig, minst använda och kostnadsoptimerad. Varje combo kedjer flera modeller med automatisk reserv.
+Skapa modell routing (model aliases, background task degradation)-kombinationer med 6 strategier: fyll först, round-robin, kraft-av-två-val, slumpmässig, minst använda och kostnadsoptimerad. Varje combo kedjer flera modeller med automatisk reserv.
 
 ![Combos Dashboard](screenshots/02-combos.png)
 

electron/package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute-desktop",
-  "version": "1.6.8",
+  "version": "1.6.9",
   "description": "OmniRoute Desktop Application",
   "main": "main.js",
   "author": "OmniRoute Team",

open-sse/config/audioRegistry.ts

@@ -70,6 +70,40 @@ export const AUDIO_TRANSCRIPTION_PROVIDERS: Record<string, AudioProvider> = {
       { id: "universal-2", name: "Universal 2" },
     ],
   },
+
+  nvidia: {
+    id: "nvidia",
+    baseUrl: "https://integrate.api.nvidia.com/v1/audio/transcriptions",
+    authType: "apikey",
+    authHeader: "bearer",
+    format: "nvidia-asr",
+    models: [
+      { id: "nvidia/parakeet-ctc-1.1b-asr", name: "Parakeet CTC 1.1B" },
+    ],
+  },
+
+  huggingface: {
+    id: "huggingface",
+    baseUrl: "https://api-inference.huggingface.co/models",
+    authType: "apikey",
+    authHeader: "bearer",
+    format: "huggingface-asr",
+    models: [
+      { id: "openai/whisper-large-v3", name: "Whisper Large v3 (HF)" },
+      { id: "openai/whisper-small", name: "Whisper Small (HF)" },
+    ],
+  },
+
+  qwen: {
+    id: "qwen",
+    baseUrl: "http://localhost:8000/v1/audio/transcriptions",
+    authType: "none",
+    authHeader: "none",
+    format: "openai",
+    models: [
+      { id: "qwen3-asr", name: "Qwen3 ASR" },
+    ],
+  },
 };
 
 export const AUDIO_SPEECH_PROVIDERS: Record<string, AudioProvider> = {
@@ -106,6 +140,75 @@ export const AUDIO_SPEECH_PROVIDERS: Record<string, AudioProvider> = {
       { id: "aura-stella-en", name: "Aura Stella (EN)" },
     ],
   },
+
+  nvidia: {
+    id: "nvidia",
+    baseUrl: "https://integrate.api.nvidia.com/v1/audio/speech",
+    authType: "apikey",
+    authHeader: "bearer",
+    format: "nvidia-tts",
+    models: [
+      { id: "nvidia/fastpitch", name: "FastPitch" },
+      { id: "nvidia/tacotron2", name: "Tacotron2" },
+    ],
+  },
+
+  elevenlabs: {
+    id: "elevenlabs",
+    baseUrl: "https://api.elevenlabs.io/v1/text-to-speech",
+    authType: "apikey",
+    authHeader: "xi-api-key",
+    format: "elevenlabs",
+    models: [
+      { id: "eleven_multilingual_v2", name: "Eleven Multilingual v2" },
+      { id: "eleven_turbo_v2_5", name: "Eleven Turbo v2.5" },
+    ],
+  },
+
+  huggingface: {
+    id: "huggingface",
+    baseUrl: "https://api-inference.huggingface.co/models",
+    authType: "apikey",
+    authHeader: "bearer",
+    format: "huggingface-tts",
+    models: [
+      { id: "facebook/mms-tts-eng", name: "MMS TTS English" },
+      { id: "microsoft/speecht5_tts", name: "SpeechT5 TTS" },
+    ],
+  },
+
+  coqui: {
+    id: "coqui",
+    baseUrl: "http://localhost:5002/api/tts",
+    authType: "none",
+    authHeader: "none",
+    format: "coqui",
+    models: [
+      { id: "tts_models/en/ljspeech/tacotron2-DDC", name: "Tacotron2 DDC (LJSpeech)" },
+    ],
+  },
+
+  tortoise: {
+    id: "tortoise",
+    baseUrl: "http://localhost:5000/api/tts",
+    authType: "none",
+    authHeader: "none",
+    format: "tortoise",
+    models: [
+      { id: "tortoise-v2", name: "Tortoise v2" },
+    ],
+  },
+
+  qwen: {
+    id: "qwen",
+    baseUrl: "http://localhost:8000/v1/audio/speech",
+    authType: "none",
+    authHeader: "none",
+    format: "openai",
+    models: [
+      { id: "qwen3-tts", name: "Qwen3 TTS" },
+    ],
+  },
 };
 
 /**

open-sse/config/imageRegistry.ts

@@ -108,6 +108,32 @@ export const IMAGE_PROVIDERS = {
     ],
     supportedSizes: ["1024x1024"],
   },
+
+  sdwebui: {
+    id: "sdwebui",
+    baseUrl: "http://localhost:7860/sdapi/v1/txt2img",
+    authType: "none",
+    authHeader: "none",
+    format: "sdwebui",
+    models: [
+      { id: "stable-diffusion-v1-5", name: "Stable Diffusion v1.5" },
+      { id: "sdxl-base-1.0", name: "SDXL Base 1.0" },
+    ],
+    supportedSizes: ["512x512", "768x768", "1024x1024"],
+  },
+
+  comfyui: {
+    id: "comfyui",
+    baseUrl: "http://localhost:8188",
+    authType: "none",
+    authHeader: "none",
+    format: "comfyui",
+    models: [
+      { id: "flux-dev", name: "FLUX Dev" },
+      { id: "sdxl", name: "SDXL" },
+    ],
+    supportedSizes: ["512x512", "768x768", "1024x1024"],
+  },
 };
 
 /**

open-sse/config/musicRegistry.ts

@@ -0,0 +1,57 @@
+/**
+ * Music Generation Provider Registry
+ *
+ * Defines providers that support the /v1/music/generations endpoint.
+ * Currently supports local providers (ComfyUI with audio models).
+ */
+
+import { parseModelFromRegistry, getAllModelsFromRegistry } from "./registryUtils.ts";
+
+interface MusicModel {
+  id: string;
+  name: string;
+}
+
+interface MusicProvider {
+  id: string;
+  baseUrl: string;
+  authType: string;
+  authHeader: string;
+  format: string;
+  models: MusicModel[];
+}
+
+export const MUSIC_PROVIDERS: Record<string, MusicProvider> = {
+  comfyui: {
+    id: "comfyui",
+    baseUrl: "http://localhost:8188",
+    authType: "none",
+    authHeader: "none",
+    format: "comfyui",
+    models: [
+      { id: "stable-audio-open", name: "Stable Audio Open" },
+      { id: "musicgen-medium", name: "MusicGen Medium" },
+    ],
+  },
+};
+
+/**
+ * Get music provider config by ID
+ */
+export function getMusicProvider(providerId: string): MusicProvider | null {
+  return MUSIC_PROVIDERS[providerId] || null;
+}
+
+/**
+ * Parse music model string (format: "provider/model" or just "model")
+ */
+export function parseMusicModel(modelStr: string | null) {
+  return parseModelFromRegistry(modelStr, MUSIC_PROVIDERS);
+}
+
+/**
+ * Get all music models as a flat list
+ */
+export function getAllMusicModels() {
+  return getAllModelsFromRegistry(MUSIC_PROVIDERS);
+}

open-sse/config/providerRegistry.ts

@@ -111,7 +111,10 @@ export const REGISTRY: Record<string, RegistryEntry> = {
       clientSecretDefault: "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",
     },
     models: [
-      { id: "gemini-3-pro-preview", name: "Gemini 3 Pro Preview" },
+      { id: "gemini-3.1-pro", name: "Gemini 3.1 Pro" },
+      { id: "gemini-3.1-flash", name: "Gemini 3.1 Flash" },
+      { id: "gemini-3-pro-preview", name: "Gemini 3.0 Pro Preview" },
+      { id: "gemini-3-flash-preview", name: "Gemini 3.0 Flash Preview" },
       { id: "gemini-2.5-pro", name: "Gemini 2.5 Pro" },
       { id: "gemini-2.5-flash", name: "Gemini 2.5 Flash" },
       { id: "gemini-2.5-flash-lite", name: "Gemini 2.5 Flash Lite" },
@@ -137,8 +140,10 @@ export const REGISTRY: Record<string, RegistryEntry> = {
       clientSecretDefault: "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",
     },
     models: [
-      { id: "gemini-3-flash-preview", name: "Gemini 3 Flash Preview" },
-      { id: "gemini-3-pro-preview", name: "Gemini 3 Pro Preview" },
+      { id: "gemini-3.1-pro", name: "Gemini 3.1 Pro" },
+      { id: "gemini-3.1-flash", name: "Gemini 3.1 Flash" },
+      { id: "gemini-3-flash-preview", name: "Gemini 3.0 Flash Preview" },
+      { id: "gemini-3-pro-preview", name: "Gemini 3.0 Pro Preview" },
       { id: "gemini-2.5-pro", name: "Gemini 2.5 Pro" },
       { id: "gemini-2.5-flash", name: "Gemini 2.5 Flash" },
       { id: "gemini-2.5-flash-lite", name: "Gemini 2.5 Flash Lite" },
@@ -268,7 +273,8 @@ export const REGISTRY: Record<string, RegistryEntry> = {
       { id: "claude-sonnet-4-6", name: "Claude Sonnet 4.6" },
       { id: "gemini-3.1-pro-high", name: "Gemini 3.1 Pro High" },
       { id: "gemini-3.1-pro-low", name: "Gemini 3.1 Pro Low" },
-      { id: "gemini-3-flash", name: "Gemini 3 Flash" },
+      { id: "gemini-3.1-flash", name: "Gemini 3.1 Flash" },
+      { id: "gemini-3-flash", name: "Gemini 3.0 Flash" },
       { id: "gpt-oss-120b-medium", name: "GPT OSS 120B Medium" },
     ],
   },
@@ -635,6 +641,25 @@ export const REGISTRY: Record<string, RegistryEntry> = {
     ],
   },
 
+  blackbox: {
+    id: "blackbox",
+    alias: "bb",
+    format: "openai",
+    executor: "default",
+    baseUrl: "https://api.blackbox.ai/v1/chat/completions",
+    modelsUrl: "https://api.blackbox.ai/v1/models",
+    authType: "apikey",
+    authHeader: "bearer",
+    models: [
+      { id: "gpt-4o", name: "GPT-4o" },
+      { id: "gemini-2.5-flash", name: "Gemini 2.5 Flash" },
+      { id: "claude-sonnet-4", name: "Claude Sonnet 4" },
+      { id: "deepseek-v3", name: "DeepSeek V3" },
+      { id: "blackboxai", name: "Blackbox AI" },
+      { id: "blackboxai-pro", name: "Blackbox AI Pro" },
+    ],
+  },
+
   xai: {
     id: "xai",
     alias: "xai",

open-sse/config/registryUtils.ts

@@ -0,0 +1,99 @@
+/**
+ * Shared Registry Utilities
+ *
+ * Common interfaces and helpers used by all provider registries
+ * (audio, image, video, music). Extracts duplicated patterns into
+ * reusable functions.
+ */
+
+export interface BaseModel {
+  id: string;
+  name: string;
+}
+
+export interface BaseProvider<M extends BaseModel = BaseModel> {
+  id: string;
+  baseUrl: string;
+  authType: string; // "apikey" | "oauth" | "none"
+  authHeader: string; // "bearer" | "token" | "xi-api-key" | "x-api-key" | "none"
+  format?: string;
+  models: M[];
+}
+
+/**
+ * Parse a "provider/model" string against a registry.
+ * Supports both "provider/model" prefix and bare "model" lookup.
+ */
+export function parseModelFromRegistry<P extends BaseProvider>(
+  modelStr: string | null,
+  registry: Record<string, P>
+): { provider: string | null; model: string | null } {
+  if (!modelStr) return { provider: null, model: null };
+
+  // Try each provider prefix
+  for (const [providerId] of Object.entries(registry)) {
+    if (modelStr.startsWith(providerId + "/")) {
+      return { provider: providerId, model: modelStr.slice(providerId.length + 1) };
+    }
+  }
+
+  // No provider prefix — try to find the model in any provider
+  for (const [providerId, config] of Object.entries(registry)) {
+    if (config.models.some((m) => m.id === modelStr)) {
+      return { provider: providerId, model: modelStr };
+    }
+  }
+
+  return { provider: null, model: modelStr };
+}
+
+/**
+ * Flatten all models from a registry into a list with provider info.
+ * Optionally merge extra fields per provider via the `extra` callback.
+ */
+export function getAllModelsFromRegistry<P extends BaseProvider>(
+  registry: Record<string, P>,
+  extra?: (providerId: string, config: P) => Record<string, unknown>
+): Array<{ id: string; name: string; provider: string } & Record<string, unknown>> {
+  const models: Array<{ id: string; name: string; provider: string } & Record<string, unknown>> =
+    [];
+
+  for (const [providerId, config] of Object.entries(registry)) {
+    const extraFields = extra ? extra(providerId, config) : {};
+    for (const model of config.models) {
+      models.push({
+        id: `${providerId}/${model.id}`,
+        name: model.name,
+        provider: providerId,
+        ...extraFields,
+      });
+    }
+  }
+
+  return models;
+}
+
+/**
+ * Build auth headers for a provider.
+ * Handles bearer, token, xi-api-key, x-api-key, and none.
+ */
+export function buildAuthHeaders(
+  provider: BaseProvider,
+  token: string | null
+): Record<string, string> {
+  if (provider.authType === "none" || provider.authHeader === "none" || !token) {
+    return {};
+  }
+
+  switch (provider.authHeader) {
+    case "token":
+      return { Authorization: `Token ${token}` };
+    case "xi-api-key":
+      return { "xi-api-key": token };
+    case "x-api-key":
+      return { "x-api-key": token };
+    case "bearer":
+    default:
+      return { Authorization: `Bearer ${token}` };
+  }
+}

open-sse/config/videoRegistry.ts

@@ -0,0 +1,68 @@
+/**
+ * Video Generation Provider Registry
+ *
+ * Defines providers that support the /v1/videos/generations endpoint.
+ * Currently supports local providers (ComfyUI, SD WebUI with AnimateDiff).
+ */
+
+import { parseModelFromRegistry, getAllModelsFromRegistry } from "./registryUtils.ts";
+
+interface VideoModel {
+  id: string;
+  name: string;
+}
+
+interface VideoProvider {
+  id: string;
+  baseUrl: string;
+  authType: string;
+  authHeader: string;
+  format: string;
+  models: VideoModel[];
+}
+
+export const VIDEO_PROVIDERS: Record<string, VideoProvider> = {
+  comfyui: {
+    id: "comfyui",
+    baseUrl: "http://localhost:8188",
+    authType: "none",
+    authHeader: "none",
+    format: "comfyui",
+    models: [
+      { id: "animatediff", name: "AnimateDiff" },
+      { id: "svd-xt", name: "Stable Video Diffusion XT" },
+    ],
+  },
+
+  sdwebui: {
+    id: "sdwebui",
+    baseUrl: "http://localhost:7860",
+    authType: "none",
+    authHeader: "none",
+    format: "sdwebui-video",
+    models: [
+      { id: "animatediff-webui", name: "AnimateDiff (WebUI)" },
+    ],
+  },
+};
+
+/**
+ * Get video provider config by ID
+ */
+export function getVideoProvider(providerId: string): VideoProvider | null {
+  return VIDEO_PROVIDERS[providerId] || null;
+}
+
+/**
+ * Parse video model string (format: "provider/model" or just "model")
+ */
+export function parseVideoModel(modelStr: string | null) {
+  return parseModelFromRegistry(modelStr, VIDEO_PROVIDERS);
+}
+
+/**
+ * Get all video models as a flat list
+ */
+export function getAllVideoModels() {
+  return getAllModelsFromRegistry(VIDEO_PROVIDERS);
+}

open-sse/executors/antigravity.ts

@@ -36,7 +36,18 @@ export class AntigravityExecutor extends BaseExecutor {
   }
 
   transformRequest(model, body, stream, credentials) {
-    const projectId = credentials?.projectId || this.generateProjectId();
+    const bodyProjectId = body?.project;
+    const credentialsProjectId = credentials?.projectId;
+    const hasExplicitProject = !!(bodyProjectId || credentialsProjectId);
+    const projectId = bodyProjectId || credentialsProjectId || this.generateProjectId();
+
+    if (!hasExplicitProject) {
+      console.warn(
+        `[Antigravity] ⚠️ No projectId provided via body or credentials — using generated fallback "${projectId}". ` +
+          `This may cause 404 errors if the account has no active GCP project. ` +
+          `Ensure the OAuth token includes a valid project or the request includes a project field.`
+      );
+    }
 
     // Fix contents for Claude models via Antigravity
     const normalizedContents =

open-sse/executors/base.ts

@@ -43,6 +43,19 @@ export class BaseExecutor {
       ...this.config.headers,
     };
 
+    // Allow per-provider User-Agent override via environment variable.
+    // Example: CLAUDE_USER_AGENT="my-agent/2.0" overrides the default for the Claude provider.
+    const providerId = this.config?.id || this.provider;
+    if (providerId) {
+      const envKey = `${providerId.toUpperCase().replace(/[^A-Z0-9]/g, "_")}_USER_AGENT`;
+      const envUA = process.env[envKey]?.trim();
+      if (envUA) {
+        // Override both common casing variants
+        headers["User-Agent"] = envUA;
+        if (headers["user-agent"]) headers["user-agent"] = envUA;
+      }
+    }
+
     if (credentials.accessToken) {
       headers["Authorization"] = `Bearer ${credentials.accessToken}`;
     } else if (credentials.apiKey) {

open-sse/handlers/audioSpeech.ts

@@ -6,22 +6,54 @@ import { getCorsOrigin } from "../utils/cors.ts";
  * Returns audio binary stream.
  *
  * Supported provider formats:
- * - OpenAI: standard JSON → audio stream proxy
+ * - OpenAI / Qwen3 (openai-compatible): standard JSON → audio stream proxy
  * - Hyperbolic: POST { text } → { audio: base64 }
  * - Deepgram: POST { text } with model via query param, Token auth
+ * - ElevenLabs: POST { text, model_id } to /v1/text-to-speech/{voice_id}
+ * - Nvidia NIM: POST { input: { text }, voice, model } → audio binary
+ * - HuggingFace Inference: POST { inputs: text } to /models/{model_id}
+ * - Coqui TTS: POST { text, speaker_id } → WAV audio (local, no auth)
+ * - Tortoise TTS: POST { text, voice } → audio binary (local, no auth)
  */
 
 import { getSpeechProvider, parseSpeechModel } from "../config/audioRegistry.ts";
+import { buildAuthHeaders } from "../config/registryUtils.ts";
 import { errorResponse } from "../utils/error.ts";
 
 /**
- * Build auth header for a speech provider
+ * Return a CORS error response from an upstream fetch failure
  */
-function buildAuthHeader(providerConfig, token) {
-  if (providerConfig.authHeader === "token") {
-    return { Authorization: `Token ${token}` };
-  }
-  return { Authorization: `Bearer ${token}` };
+function upstreamErrorResponse(res, errText) {
+  return new Response(errText, {
+    status: res.status,
+    headers: {
+      "Content-Type": "application/json",
+      "Access-Control-Allow-Origin": getCorsOrigin(),
+    },
+  });
+}
+
+/**
+ * Return a CORS audio stream response
+ */
+function audioStreamResponse(res, defaultContentType = "audio/mpeg") {
+  const contentType = res.headers.get("content-type") || defaultContentType;
+  return new Response(res.body, {
+    status: 200,
+    headers: {
+      "Content-Type": contentType,
+      "Access-Control-Allow-Origin": getCorsOrigin(),
+      "Transfer-Encoding": "chunked",
+    },
+  });
+}
+
+/**
+ * Validate a path segment to prevent path traversal / SSRF.
+ * Returns true if safe, false if it contains traversal sequences.
+ */
+function isValidPathSegment(segment: string): boolean {
+  return !segment.includes("..") && !segment.includes("//");
 }
 
 /**
@@ -32,20 +64,13 @@ async function handleHyperbolicSpeech(providerConfig, body, token) {
     method: "POST",
     headers: {
       "Content-Type": "application/json",
-      ...buildAuthHeader(providerConfig, token),
+      ...buildAuthHeaders(providerConfig, token),
     },
     body: JSON.stringify({ text: body.input }),
   });
 
   if (!res.ok) {
-    const errText = await res.text();
-    return new Response(errText, {
-      status: res.status,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-      },
-    });
+    return upstreamErrorResponse(res, await res.text());
   }
 
   const data = await res.json();
@@ -72,29 +97,153 @@ async function handleDeepgramSpeech(providerConfig, body, modelId, token) {
     method: "POST",
     headers: {
       "Content-Type": "application/json",
-      ...buildAuthHeader(providerConfig, token),
+      ...buildAuthHeaders(providerConfig, token),
     },
     body: JSON.stringify({ text: body.input }),
   });
 
   if (!res.ok) {
-    const errText = await res.text();
-    return new Response(errText, {
-      status: res.status,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-      },
-    });
+    return upstreamErrorResponse(res, await res.text());
   }
 
-  const contentType = res.headers.get("content-type") || "audio/mpeg";
+  return audioStreamResponse(res);
+}
+
+/**
+ * Handle ElevenLabs TTS
+ * POST {baseUrl}/{voice_id} with { text, model_id }
+ * voice_id is mapped from the OpenAI `voice` parameter
+ */
+async function handleElevenLabsSpeech(providerConfig, body, modelId, token) {
+  // ElevenLabs uses voice_id in URL path; default to "21m00Tcm4TlvDq8ikWAM" (Rachel)
+  const voiceId = body.voice || "21m00Tcm4TlvDq8ikWAM";
+  if (!isValidPathSegment(voiceId)) {
+    return errorResponse(400, "Invalid voice ID");
+  }
+  const url = `${providerConfig.baseUrl}/${voiceId}`;
+
+  const res = await fetch(url, {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      ...buildAuthHeaders(providerConfig, token),
+    },
+    body: JSON.stringify({
+      text: body.input,
+      model_id: modelId,
+    }),
+  });
+
+  if (!res.ok) {
+    return upstreamErrorResponse(res, await res.text());
+  }
+
+  return audioStreamResponse(res);
+}
+
+/**
+ * Handle Nvidia NIM TTS
+ * POST with { input: { text }, voice, model } → audio binary
+ */
+async function handleNvidiaTtsSpeech(providerConfig, body, modelId, token) {
+  const res = await fetch(providerConfig.baseUrl, {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      ...buildAuthHeaders(providerConfig, token),
+    },
+    body: JSON.stringify({
+      input: { text: body.input },
+      voice: body.voice || "default",
+      model: modelId,
+    }),
+  });
+
+  if (!res.ok) {
+    return upstreamErrorResponse(res, await res.text());
+  }
+
+  return audioStreamResponse(res, "audio/wav");
+}
+
+/**
+ * Handle HuggingFace Inference TTS
+ * POST {baseUrl}/{model_id} with { inputs: text } → audio binary
+ */
+async function handleHuggingFaceTtsSpeech(providerConfig, body, modelId, token) {
+  if (!isValidPathSegment(modelId)) {
+    return errorResponse(400, "Invalid model ID");
+  }
+  const url = `${providerConfig.baseUrl}/${modelId}`;
+
+  const res = await fetch(url, {
+    method: "POST",
+    headers: {
+      "Content-Type": "application/json",
+      ...buildAuthHeaders(providerConfig, token),
+    },
+    body: JSON.stringify({ inputs: body.input }),
+  });
+
+  if (!res.ok) {
+    return upstreamErrorResponse(res, await res.text());
+  }
+
+  return audioStreamResponse(res, "audio/wav");
+}
+
+/**
+ * Handle Coqui TTS (local, no auth)
+ * POST {baseUrl} with { text, speaker_id } → WAV audio
+ */
+async function handleCoquiSpeech(providerConfig, body) {
+  const res = await fetch(providerConfig.baseUrl, {
+    method: "POST",
+    headers: { "Content-Type": "application/json" },
+    body: JSON.stringify({
+      text: body.input,
+      speaker_id: body.voice || undefined,
+    }),
+  });
+
+  if (!res.ok) {
+    return upstreamErrorResponse(res, await res.text());
+  }
+
+  const contentType = res.headers.get("content-type") || "audio/wav";
+  return new Response(res.body, {
+    status: 200,
+    headers: {
+      "Content-Type": contentType,
+      "Access-Control-Allow-Origin": getCorsOrigin(),
+    },
+  });
+}
+
+/**
+ * Handle Tortoise TTS (local, no auth)
+ * POST {baseUrl} with { text, voice } → audio binary
+ */
+async function handleTortoiseSpeech(providerConfig, body) {
+  const res = await fetch(providerConfig.baseUrl, {
+    method: "POST",
+    headers: { "Content-Type": "application/json" },
+    body: JSON.stringify({
+      text: body.input,
+      voice: body.voice || "random",
+    }),
+  });
+
+  if (!res.ok) {
+    return upstreamErrorResponse(res, await res.text());
+  }
+
+  const contentType = res.headers.get("content-type") || "audio/wav";
   return new Response(res.body, {
     status: 200,
     headers: {
       "Content-Type": contentType,
       "Access-Control-Allow-Origin": getCorsOrigin(),
-      "Transfer-Encoding": "chunked",
     },
   });
 }
@@ -122,12 +271,13 @@ export async function handleAudioSpeech({ body, credentials }) {
   if (!providerConfig) {
     return errorResponse(
       400,
-      `No speech provider found for model "${body.model}". Available: openai, hyperbolic, deepgram`
+      `No speech provider found for model "${body.model}". Available: openai, hyperbolic, deepgram, nvidia, elevenlabs, huggingface, coqui, tortoise, qwen`
     );
   }
 
-  const token = credentials?.apiKey || credentials?.accessToken;
-  if (!token) {
+  // Skip credential check for local providers (authType: "none")
+  const token = providerConfig.authType === "none" ? null : (credentials?.apiKey || credentials?.accessToken);
+  if (providerConfig.authType !== "none" && !token) {
     return errorResponse(401, `No credentials for speech provider: ${providerId}`);
   }
 
@@ -141,12 +291,32 @@ export async function handleAudioSpeech({ body, credentials }) {
       return handleDeepgramSpeech(providerConfig, body, modelId, token);
     }
 
-    // Default: OpenAI-compatible JSON → audio stream proxy
+    if (providerConfig.format === "elevenlabs") {
+      return handleElevenLabsSpeech(providerConfig, body, modelId, token);
+    }
+
+    if (providerConfig.format === "nvidia-tts") {
+      return handleNvidiaTtsSpeech(providerConfig, body, modelId, token);
+    }
+
+    if (providerConfig.format === "huggingface-tts") {
+      return handleHuggingFaceTtsSpeech(providerConfig, body, modelId, token);
+    }
+
+    if (providerConfig.format === "coqui") {
+      return handleCoquiSpeech(providerConfig, body);
+    }
+
+    if (providerConfig.format === "tortoise") {
+      return handleTortoiseSpeech(providerConfig, body);
+    }
+
+    // Default: OpenAI-compatible JSON → audio stream proxy (also used by Qwen3)
     const res = await fetch(providerConfig.baseUrl, {
       method: "POST",
       headers: {
         "Content-Type": "application/json",
-        ...buildAuthHeader(providerConfig, token),
+        ...buildAuthHeaders(providerConfig, token),
       },
       body: JSON.stringify({
         model: modelId,
@@ -158,27 +328,11 @@ export async function handleAudioSpeech({ body, credentials }) {
     });
 
     if (!res.ok) {
-      const errText = await res.text();
-      return new Response(errText, {
-        status: res.status,
-        headers: {
-          "Content-Type": "application/json",
-          "Access-Control-Allow-Origin": getCorsOrigin(),
-        },
-      });
+      return upstreamErrorResponse(res, await res.text());
     }
 
-    // Stream audio response back to client
-    const contentType = res.headers.get("content-type") || "audio/mpeg";
-    return new Response(res.body, {
-      status: 200,
-      headers: {
-        "Content-Type": contentType,
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-        "Transfer-Encoding": "chunked",
-      },
-    });
+    return audioStreamResponse(res);
   } catch (err) {
     return errorResponse(500, `Speech request failed: ${err.message}`);
   }
-}
+}

open-sse/handlers/audioTranscription.ts

@@ -6,22 +6,35 @@ import { getCorsOrigin } from "../utils/cors.ts";
  * Proxies multipart/form-data to upstream providers.
  *
  * Supported provider formats:
- * - OpenAI/Groq: standard multipart form-data proxy
+ * - OpenAI/Groq/Qwen3: standard multipart form-data proxy
  * - Deepgram: raw binary audio POST with model via query param
  * - AssemblyAI: async workflow (upload → submit → poll)
+ * - Nvidia NIM: multipart POST, transform response to { text }
+ * - HuggingFace Inference: POST raw binary to /models/{model_id}
  */
 
 import { getTranscriptionProvider, parseTranscriptionModel } from "../config/audioRegistry.ts";
+import { buildAuthHeaders } from "../config/registryUtils.ts";
 import { errorResponse } from "../utils/error.ts";
 
 /**
- * Build auth header for a transcription provider
+ * Return a CORS error response from an upstream fetch failure
  */
-function buildAuthHeader(providerConfig, token) {
-  if (providerConfig.authHeader === "token") {
-    return { Authorization: `Token ${token}` };
-  }
-  return { Authorization: `Bearer ${token}` };
+function upstreamErrorResponse(res, errText) {
+  return new Response(errText, {
+    status: res.status,
+    headers: {
+      "Content-Type": "application/json",
+      "Access-Control-Allow-Origin": getCorsOrigin(),
+    },
+  });
+}
+
+/**
+ * Validate a path segment to prevent path traversal / SSRF.
+ */
+function isValidPathSegment(segment: string): boolean {
+  return !segment.includes("..") && !segment.includes("//");
 }
 
 /**
@@ -37,21 +50,14 @@ async function handleDeepgramTranscription(providerConfig, file, modelId, token)
   const res = await fetch(url.toString(), {
     method: "POST",
     headers: {
-      ...buildAuthHeader(providerConfig, token),
+      ...buildAuthHeaders(providerConfig, token),
       "Content-Type": file.type || "audio/wav",
     },
     body: arrayBuffer,
   });
 
   if (!res.ok) {
-    const errText = await res.text();
-    return new Response(errText, {
-      status: res.status,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-      },
-    });
+    return upstreamErrorResponse(res, await res.text());
   }
 
   const data = await res.json();
@@ -65,7 +71,7 @@ async function handleDeepgramTranscription(providerConfig, file, modelId, token)
  * Handle AssemblyAI transcription (async: upload file → submit → poll)
  */
 async function handleAssemblyAITranscription(providerConfig, file, modelId, token) {
-  const authHeaders = buildAuthHeader(providerConfig, token);
+  const authHeaders = buildAuthHeaders(providerConfig, token);
 
   // Step 1: Upload the audio file
   const arrayBuffer = await file.arrayBuffer();
@@ -79,14 +85,7 @@ async function handleAssemblyAITranscription(providerConfig, file, modelId, toke
   });
 
   if (!uploadRes.ok) {
-    const errText = await uploadRes.text();
-    return new Response(errText, {
-      status: uploadRes.status,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-      },
-    });
+    return upstreamErrorResponse(uploadRes, await uploadRes.text());
   }
 
   const { upload_url } = await uploadRes.json();
@@ -106,14 +105,7 @@ async function handleAssemblyAITranscription(providerConfig, file, modelId, toke
   });
 
   if (!submitRes.ok) {
-    const errText = await submitRes.text();
-    return new Response(errText, {
-      status: submitRes.status,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-      },
-    });
+    return upstreamErrorResponse(submitRes, await submitRes.text());
   }
 
   const { id: transcriptId } = await submitRes.json();
@@ -146,6 +138,63 @@ async function handleAssemblyAITranscription(providerConfig, file, modelId, toke
   return errorResponse(504, "AssemblyAI transcription timed out after 120s");
 }
 
+/**
+ * Handle Nvidia NIM transcription
+ * Multipart POST, transform response to { text }
+ */
+async function handleNvidiaTranscription(providerConfig, file, modelId, token) {
+  const upstreamForm = new FormData();
+  upstreamForm.append("file", /** @type {Blob} */ file, /** @type {any} */ file.name || "audio.wav");
+  upstreamForm.append("model", modelId);
+
+  const res = await fetch(providerConfig.baseUrl, {
+    method: "POST",
+    headers: buildAuthHeaders(providerConfig, token),
+    body: upstreamForm,
+  });
+
+  if (!res.ok) {
+    return upstreamErrorResponse(res, await res.text());
+  }
+
+  const data = await res.json();
+  // Normalize to { text } — Nvidia may return { text } directly or nested
+  const text = data.text || data.transcript || "";
+
+  return Response.json({ text }, { headers: { "Access-Control-Allow-Origin": getCorsOrigin() } });
+}
+
+/**
+ * Handle HuggingFace Inference transcription
+ * POST raw binary audio to {baseUrl}/{model_id}, returns { text }
+ */
+async function handleHuggingFaceTranscription(providerConfig, file, modelId, token) {
+  if (!isValidPathSegment(modelId)) {
+    return errorResponse(400, "Invalid model ID");
+  }
+  const url = `${providerConfig.baseUrl}/${modelId}`;
+  const arrayBuffer = await file.arrayBuffer();
+
+  const res = await fetch(url, {
+    method: "POST",
+    headers: {
+      ...buildAuthHeaders(providerConfig, token),
+      "Content-Type": file.type || "audio/wav",
+    },
+    body: arrayBuffer,
+  });
+
+  if (!res.ok) {
+    return upstreamErrorResponse(res, await res.text());
+  }
+
+  const data = await res.json();
+  // HuggingFace returns { text } directly
+  const text = data.text || "";
+
+  return Response.json({ text }, { headers: { "Access-Control-Allow-Origin": getCorsOrigin() } });
+}
+
 /**
  * Handle audio transcription request
  *
@@ -172,12 +221,13 @@ export async function handleAudioTranscription({ formData, credentials }) {
   if (!providerConfig) {
     return errorResponse(
       400,
-      `No transcription provider found for model "${model}". Available: openai, groq, deepgram, assemblyai`
+      `No transcription provider found for model "${model}". Available: openai, groq, deepgram, assemblyai, nvidia, huggingface, qwen`
     );
   }
 
-  const token = credentials?.apiKey || credentials?.accessToken;
-  if (!token) {
+  // Skip credential check for local providers (authType: "none")
+  const token = providerConfig.authType === "none" ? null : (credentials?.apiKey || credentials?.accessToken);
+  if (providerConfig.authType !== "none" && !token) {
     return errorResponse(401, `No credentials for transcription provider: ${providerId}`);
   }
 
@@ -190,7 +240,15 @@ export async function handleAudioTranscription({ formData, credentials }) {
     return handleAssemblyAITranscription(providerConfig, file, modelId, token);
   }
 
-  // Default: OpenAI/Groq-compatible multipart proxy
+  if (providerConfig.format === "nvidia-asr") {
+    return handleNvidiaTranscription(providerConfig, file, modelId, token);
+  }
+
+  if (providerConfig.format === "huggingface-asr") {
+    return handleHuggingFaceTranscription(providerConfig, file, modelId, token);
+  }
+
+  // Default: OpenAI/Groq/Qwen3-compatible multipart proxy
   const upstreamForm = new FormData();
   upstreamForm.append(
     "file",
@@ -216,19 +274,12 @@ export async function handleAudioTranscription({ formData, credentials }) {
   try {
     const res = await fetch(providerConfig.baseUrl, {
       method: "POST",
-      headers: buildAuthHeader(providerConfig, token),
+      headers: buildAuthHeaders(providerConfig, token),
       body: upstreamForm,
     });
 
     if (!res.ok) {
-      const errText = await res.text();
-      return new Response(errText, {
-        status: res.status,
-        headers: {
-          "Content-Type": "application/json",
-          "Access-Control-Allow-Origin": getCorsOrigin(),
-        },
-      });
+      return upstreamErrorResponse(res, await res.text());
     }
 
     const data = await res.text();
@@ -241,4 +292,4 @@ export async function handleAudioTranscription({ formData, credentials }) {
   } catch (err) {
     return errorResponse(500, `Transcription request failed: ${err.message}`);
   }
-}
+}

open-sse/handlers/imageGeneration.ts

@@ -17,6 +17,12 @@
 
 import { getImageProvider, parseImageModel } from "../config/imageRegistry.ts";
 import { saveCallLog } from "@/lib/usageDb";
+import {
+  submitComfyWorkflow,
+  pollComfyResult,
+  fetchComfyOutput,
+  extractComfyOutputFiles,
+} from "../utils/comfyuiClient.ts";
 
 /**
  * Handle image generation request
@@ -72,6 +78,14 @@ export async function handleImageGeneration({ body, credentials, log }) {
     });
   }
 
+  if (providerConfig.format === "sdwebui") {
+    return handleSDWebUIImageGeneration({ model, provider, providerConfig, body, log });
+  }
+
+  if (providerConfig.format === "comfyui") {
+    return handleComfyUIImageGeneration({ model, provider, providerConfig, body, log });
+  }
+
   return handleOpenAIImageGeneration({ model, provider, providerConfig, body, credentials, log });
 }
 
@@ -560,3 +574,193 @@ async function handleNanoBananaImageGeneration({
     return { success: false, status: 502, error: `Image provider error: ${err.message}` };
   }
 }
+
+/**
+ * Handle SD WebUI image generation (local, no auth)
+ * POST {baseUrl} with { prompt, negative_prompt, width, height, steps }
+ * Response: { images: ["base64..."] }
+ */
+async function handleSDWebUIImageGeneration({ model, provider, providerConfig, body, log }) {
+  const startTime = Date.now();
+  const [width, height] = (body.size || "512x512").split("x").map(Number);
+
+  const upstreamBody = {
+    prompt: body.prompt,
+    negative_prompt: body.negative_prompt || "",
+    width: width || 512,
+    height: height || 512,
+    steps: body.steps || 20,
+    cfg_scale: body.cfg_scale || 7,
+    sampler_name: body.sampler || "Euler a",
+    batch_size: body.n || 1,
+    override_settings: {
+      sd_model_checkpoint: model,
+    },
+  };
+
+  if (log) {
+    const promptPreview = String(body.prompt ?? "").slice(0, 60);
+    log.info("IMAGE", `${provider}/${model} (sdwebui) | prompt: "${promptPreview}..."`);
+  }
+
+  try {
+    const response = await fetch(providerConfig.baseUrl, {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify(upstreamBody),
+    });
+
+    if (!response.ok) {
+      const errorText = await response.text();
+      if (log) log.error("IMAGE", `${provider} error ${response.status}: ${errorText.slice(0, 200)}`);
+
+      saveCallLog({
+        method: "POST",
+        path: "/v1/images/generations",
+        status: response.status,
+        model: `${provider}/${model}`,
+        provider,
+        duration: Date.now() - startTime,
+        error: errorText.slice(0, 500),
+      }).catch(() => {});
+
+      return { success: false, status: response.status, error: errorText };
+    }
+
+    const data = await response.json();
+    // SD WebUI returns { images: ["base64...", ...] }
+    const images = (data.images || []).map((b64) => ({
+      b64_json: b64,
+      revised_prompt: body.prompt,
+    }));
+
+    saveCallLog({
+      method: "POST",
+      path: "/v1/images/generations",
+      status: 200,
+      model: `${provider}/${model}`,
+      provider,
+      duration: Date.now() - startTime,
+      responseBody: { images_count: images.length },
+    }).catch(() => {});
+
+    return {
+      success: true,
+      data: { created: Math.floor(Date.now() / 1000), data: images },
+    };
+  } catch (err) {
+    if (log) log.error("IMAGE", `${provider} sdwebui error: ${err.message}`);
+    saveCallLog({
+      method: "POST",
+      path: "/v1/images/generations",
+      status: 502,
+      model: `${provider}/${model}`,
+      provider,
+      duration: Date.now() - startTime,
+      error: err.message,
+    }).catch(() => {});
+    return { success: false, status: 502, error: `Image provider error: ${err.message}` };
+  }
+}
+
+/**
+ * Handle ComfyUI image generation (local, no auth)
+ * Submits a txt2img workflow, polls for completion, fetches output
+ */
+async function handleComfyUIImageGeneration({ model, provider, providerConfig, body, log }) {
+  const startTime = Date.now();
+  const [width, height] = (body.size || "1024x1024").split("x").map(Number);
+
+  // Default txt2img workflow template for ComfyUI
+  const workflow = {
+    "3": {
+      class_type: "KSampler",
+      inputs: {
+        seed: Math.floor(Math.random() * 2 ** 32),
+        steps: body.steps || 20,
+        cfg: body.cfg_scale || 7,
+        sampler_name: "euler",
+        scheduler: "normal",
+        denoise: 1,
+        model: ["4", 0],
+        positive: ["6", 0],
+        negative: ["7", 0],
+        latent_image: ["5", 0],
+      },
+    },
+    "4": {
+      class_type: "CheckpointLoaderSimple",
+      inputs: { ckpt_name: model },
+    },
+    "5": {
+      class_type: "EmptyLatentImage",
+      inputs: { width: width || 1024, height: height || 1024, batch_size: body.n || 1 },
+    },
+    "6": {
+      class_type: "CLIPTextEncode",
+      inputs: { text: body.prompt, clip: ["4", 1] },
+    },
+    "7": {
+      class_type: "CLIPTextEncode",
+      inputs: { text: body.negative_prompt || "", clip: ["4", 1] },
+    },
+    "8": {
+      class_type: "VAEDecode",
+      inputs: { samples: ["3", 0], vae: ["4", 2] },
+    },
+    "9": {
+      class_type: "SaveImage",
+      inputs: { filename_prefix: "omniroute", images: ["8", 0] },
+    },
+  };
+
+  if (log) {
+    const promptPreview = String(body.prompt ?? "").slice(0, 60);
+    log.info("IMAGE", `${provider}/${model} (comfyui) | prompt: "${promptPreview}..."`);
+  }
+
+  try {
+    const promptId = await submitComfyWorkflow(providerConfig.baseUrl, workflow);
+    const historyEntry = await pollComfyResult(providerConfig.baseUrl, promptId);
+    const outputFiles = extractComfyOutputFiles(historyEntry);
+
+    const images = [];
+    for (const file of outputFiles) {
+      const buffer = await fetchComfyOutput(
+        providerConfig.baseUrl,
+        file.filename,
+        file.subfolder,
+        file.type
+      );
+      const base64 = Buffer.from(buffer).toString("base64");
+      images.push({ b64_json: base64, revised_prompt: body.prompt });
+    }
+
+    saveCallLog({
+      method: "POST",
+      path: "/v1/images/generations",
+      status: 200,
+      model: `${provider}/${model}`,
+      provider,
+      duration: Date.now() - startTime,
+      responseBody: { images_count: images.length },
+    }).catch(() => {});
+
+    return {
+      success: true,
+      data: { created: Math.floor(Date.now() / 1000), data: images },
+    };
+  } catch (err) {
+    if (log) log.error("IMAGE", `${provider} comfyui error: ${err.message}`);
+    saveCallLog({
+      method: "POST",
+      path: "/v1/images/generations",
+      status: 502,
+      model: `${provider}/${model}`,
+      provider,
+      duration: Date.now() - startTime,
+      error: err.message,
+    }).catch(() => {});
+    return { success: false, status: 502, error: `Image provider error: ${err.message}` };
+  }
+}

open-sse/handlers/musicGeneration.ts

@@ -0,0 +1,159 @@
+/**
+ * Music Generation Handler
+ *
+ * Handles POST /v1/music/generations requests.
+ * Proxies to upstream music generation providers.
+ *
+ * Supported provider formats:
+ * - ComfyUI: submit audio workflow → poll → fetch output
+ *
+ * Response format (OpenAI-like):
+ * {
+ *   "created": 1234567890,
+ *   "data": [{ "b64_json": "...", "format": "wav" }]
+ * }
+ */
+
+import { getMusicProvider, parseMusicModel } from "../config/musicRegistry.ts";
+import {
+  submitComfyWorkflow,
+  pollComfyResult,
+  fetchComfyOutput,
+  extractComfyOutputFiles,
+} from "../utils/comfyuiClient.ts";
+import { saveCallLog } from "@/lib/usageDb";
+
+/**
+ * Handle music generation request
+ */
+export async function handleMusicGeneration({ body, credentials, log }) {
+  const { provider, model } = parseMusicModel(body.model);
+
+  if (!provider) {
+    return {
+      success: false,
+      status: 400,
+      error: `Invalid music model: ${body.model}. Use format: provider/model`,
+    };
+  }
+
+  const providerConfig = getMusicProvider(provider);
+  if (!providerConfig) {
+    return {
+      success: false,
+      status: 400,
+      error: `Unknown music provider: ${provider}`,
+    };
+  }
+
+  if (providerConfig.format === "comfyui") {
+    return handleComfyUIMusicGeneration({ model, provider, providerConfig, body, log });
+  }
+
+  return { success: false, status: 400, error: `Unsupported music format: ${providerConfig.format}` };
+}
+
+/**
+ * Handle ComfyUI music generation
+ * Submits an audio generation workflow (Stable Audio / MusicGen), polls, fetches output
+ */
+async function handleComfyUIMusicGeneration({ model, provider, providerConfig, body, log }) {
+  const startTime = Date.now();
+  const duration = body.duration || 10; // seconds
+
+  // Audio generation workflow template for ComfyUI
+  const workflow = {
+    "1": {
+      class_type: "CheckpointLoaderSimple",
+      inputs: { ckpt_name: model },
+    },
+    "2": {
+      class_type: "CLIPTextEncode",
+      inputs: { text: body.prompt, clip: ["1", 1] },
+    },
+    "3": {
+      class_type: "CLIPTextEncode",
+      inputs: { text: body.negative_prompt || "", clip: ["1", 1] },
+    },
+    "4": {
+      class_type: "EmptyLatentAudio",
+      inputs: { seconds: duration },
+    },
+    "5": {
+      class_type: "KSampler",
+      inputs: {
+        seed: Math.floor(Math.random() * 2 ** 32),
+        steps: body.steps || 100,
+        cfg: body.cfg_scale || 7,
+        sampler_name: "euler",
+        scheduler: "normal",
+        denoise: 1,
+        model: ["1", 0],
+        positive: ["2", 0],
+        negative: ["3", 0],
+        latent_image: ["4", 0],
+      },
+    },
+    "6": {
+      class_type: "VAEDecodeAudio",
+      inputs: { samples: ["5", 0], vae: ["1", 2] },
+    },
+    "7": {
+      class_type: "SaveAudio",
+      inputs: {
+        filename_prefix: "omniroute_music",
+        audio: ["6", 0],
+      },
+    },
+  };
+
+  if (log) {
+    const promptPreview = String(body.prompt ?? "").slice(0, 60);
+    log.info("MUSIC", `${provider}/${model} (comfyui) | prompt: "${promptPreview}..." | duration: ${duration}s`);
+  }
+
+  try {
+    const promptId = await submitComfyWorkflow(providerConfig.baseUrl, workflow);
+    const historyEntry = await pollComfyResult(providerConfig.baseUrl, promptId, 300_000);
+    const outputFiles = extractComfyOutputFiles(historyEntry);
+
+    const audioFiles = [];
+    for (const file of outputFiles) {
+      const buffer = await fetchComfyOutput(
+        providerConfig.baseUrl,
+        file.filename,
+        file.subfolder,
+        file.type
+      );
+      const base64 = Buffer.from(buffer).toString("base64");
+      audioFiles.push({ b64_json: base64, format: "wav" });
+    }
+
+    saveCallLog({
+      method: "POST",
+      path: "/v1/music/generations",
+      status: 200,
+      model: `${provider}/${model}`,
+      provider,
+      duration: Date.now() - startTime,
+      responseBody: { audio_count: audioFiles.length },
+    }).catch(() => {});
+
+    return {
+      success: true,
+      data: { created: Math.floor(Date.now() / 1000), data: audioFiles },
+    };
+  } catch (err) {
+    if (log) log.error("MUSIC", `${provider} comfyui error: ${err.message}`);
+    saveCallLog({
+      method: "POST",
+      path: "/v1/music/generations",
+      status: 502,
+      model: `${provider}/${model}`,
+      provider,
+      duration: Date.now() - startTime,
+      error: err.message,
+    }).catch(() => {});
+    return { success: false, status: 502, error: `Music provider error: ${err.message}` };
+  }
+}

open-sse/handlers/videoGeneration.ts

@@ -0,0 +1,256 @@
+/**
+ * Video Generation Handler
+ *
+ * Handles POST /v1/videos/generations requests.
+ * Proxies to upstream video generation providers.
+ *
+ * Supported provider formats:
+ * - ComfyUI: submit AnimateDiff/SVD workflow → poll → fetch video
+ * - SD WebUI: POST to AnimateDiff extension endpoint
+ *
+ * Response format (OpenAI-like):
+ * {
+ *   "created": 1234567890,
+ *   "data": [{ "b64_json": "...", "format": "mp4" }]
+ * }
+ */
+
+import { getVideoProvider, parseVideoModel } from "../config/videoRegistry.ts";
+import {
+  submitComfyWorkflow,
+  pollComfyResult,
+  fetchComfyOutput,
+  extractComfyOutputFiles,
+} from "../utils/comfyuiClient.ts";
+import { saveCallLog } from "@/lib/usageDb";
+
+/**
+ * Handle video generation request
+ */
+export async function handleVideoGeneration({ body, credentials, log }) {
+  const { provider, model } = parseVideoModel(body.model);
+
+  if (!provider) {
+    return {
+      success: false,
+      status: 400,
+      error: `Invalid video model: ${body.model}. Use format: provider/model`,
+    };
+  }
+
+  const providerConfig = getVideoProvider(provider);
+  if (!providerConfig) {
+    return {
+      success: false,
+      status: 400,
+      error: `Unknown video provider: ${provider}`,
+    };
+  }
+
+  if (providerConfig.format === "comfyui") {
+    return handleComfyUIVideoGeneration({ model, provider, providerConfig, body, log });
+  }
+
+  if (providerConfig.format === "sdwebui-video") {
+    return handleSDWebUIVideoGeneration({ model, provider, providerConfig, body, log });
+  }
+
+  return { success: false, status: 400, error: `Unsupported video format: ${providerConfig.format}` };
+}
+
+/**
+ * Handle ComfyUI video generation
+ * Submits an AnimateDiff or SVD workflow, polls for completion, fetches output video
+ */
+async function handleComfyUIVideoGeneration({ model, provider, providerConfig, body, log }) {
+  const startTime = Date.now();
+  const [width, height] = (body.size || "512x512").split("x").map(Number);
+  const frames = body.frames || 16;
+
+  // AnimateDiff workflow template
+  const workflow = {
+    "1": {
+      class_type: "CheckpointLoaderSimple",
+      inputs: { ckpt_name: model },
+    },
+    "2": {
+      class_type: "CLIPTextEncode",
+      inputs: { text: body.prompt, clip: ["1", 1] },
+    },
+    "3": {
+      class_type: "CLIPTextEncode",
+      inputs: { text: body.negative_prompt || "", clip: ["1", 1] },
+    },
+    "4": {
+      class_type: "EmptyLatentImage",
+      inputs: { width: width || 512, height: height || 512, batch_size: frames },
+    },
+    "5": {
+      class_type: "KSampler",
+      inputs: {
+        seed: Math.floor(Math.random() * 2 ** 32),
+        steps: body.steps || 20,
+        cfg: body.cfg_scale || 7,
+        sampler_name: "euler",
+        scheduler: "normal",
+        denoise: 1,
+        model: ["1", 0],
+        positive: ["2", 0],
+        negative: ["3", 0],
+        latent_image: ["4", 0],
+      },
+    },
+    "6": {
+      class_type: "VAEDecode",
+      inputs: { samples: ["5", 0], vae: ["1", 2] },
+    },
+    "7": {
+      class_type: "SaveAnimatedWEBP",
+      inputs: {
+        filename_prefix: "omniroute_video",
+        fps: body.fps || 8,
+        lossless: false,
+        quality: 80,
+        method: "default",
+        images: ["6", 0],
+      },
+    },
+  };
+
+  if (log) {
+    const promptPreview = String(body.prompt ?? "").slice(0, 60);
+    log.info("VIDEO", `${provider}/${model} (comfyui) | prompt: "${promptPreview}..." | frames: ${frames}`);
+  }
+
+  try {
+    const promptId = await submitComfyWorkflow(providerConfig.baseUrl, workflow);
+    const historyEntry = await pollComfyResult(providerConfig.baseUrl, promptId, 300_000);
+    const outputFiles = extractComfyOutputFiles(historyEntry);
+
+    const videos = [];
+    for (const file of outputFiles) {
+      const buffer = await fetchComfyOutput(
+        providerConfig.baseUrl,
+        file.filename,
+        file.subfolder,
+        file.type
+      );
+      const base64 = Buffer.from(buffer).toString("base64");
+      videos.push({ b64_json: base64, format: "webp" });
+    }
+
+    saveCallLog({
+      method: "POST",
+      path: "/v1/videos/generations",
+      status: 200,
+      model: `${provider}/${model}`,
+      provider,
+      duration: Date.now() - startTime,
+      responseBody: { videos_count: videos.length },
+    }).catch(() => {});
+
+    return {
+      success: true,
+      data: { created: Math.floor(Date.now() / 1000), data: videos },
+    };
+  } catch (err) {
+    if (log) log.error("VIDEO", `${provider} comfyui error: ${err.message}`);
+    saveCallLog({
+      method: "POST",
+      path: "/v1/videos/generations",
+      status: 502,
+      model: `${provider}/${model}`,
+      provider,
+      duration: Date.now() - startTime,
+      error: err.message,
+    }).catch(() => {});
+    return { success: false, status: 502, error: `Video provider error: ${err.message}` };
+  }
+}
+
+/**
+ * Handle SD WebUI video generation via AnimateDiff extension
+ * POST to the AnimateDiff API endpoint
+ */
+async function handleSDWebUIVideoGeneration({ model, provider, providerConfig, body, log }) {
+  const startTime = Date.now();
+  const [width, height] = (body.size || "512x512").split("x").map(Number);
+  const url = `${providerConfig.baseUrl}/animatediff/v1/generate`;
+
+  const upstreamBody = {
+    prompt: body.prompt,
+    negative_prompt: body.negative_prompt || "",
+    width: width || 512,
+    height: height || 512,
+    steps: body.steps || 20,
+    cfg_scale: body.cfg_scale || 7,
+    frames: body.frames || 16,
+    fps: body.fps || 8,
+  };
+
+  if (log) {
+    const promptPreview = String(body.prompt ?? "").slice(0, 60);
+    log.info("VIDEO", `${provider}/${model} (sdwebui) | prompt: "${promptPreview}..."`);
+  }
+
+  try {
+    const response = await fetch(url, {
+      method: "POST",
+      headers: { "Content-Type": "application/json" },
+      body: JSON.stringify(upstreamBody),
+    });
+
+    if (!response.ok) {
+      const errorText = await response.text();
+      if (log) log.error("VIDEO", `${provider} error ${response.status}: ${errorText.slice(0, 200)}`);
+      saveCallLog({
+        method: "POST",
+        path: "/v1/videos/generations",
+        status: response.status,
+        model: `${provider}/${model}`,
+        provider,
+        duration: Date.now() - startTime,
+        error: errorText.slice(0, 500),
+      }).catch(() => {});
+      return { success: false, status: response.status, error: errorText };
+    }
+
+    const data = await response.json();
+    // SD WebUI AnimateDiff returns { video: "base64..." } or { images: [...] }
+    const videos = [];
+    if (data.video) {
+      videos.push({ b64_json: data.video, format: "mp4" });
+    } else if (data.images) {
+      for (const img of data.images) {
+        videos.push({ b64_json: typeof img === "string" ? img : img.image, format: "mp4" });
+      }
+    }
+
+    saveCallLog({
+      method: "POST",
+      path: "/v1/videos/generations",
+      status: 200,
+      model: `${provider}/${model}`,
+      provider,
+      duration: Date.now() - startTime,
+      responseBody: { videos_count: videos.length },
+    }).catch(() => {});
+
+    return {
+      success: true,
+      data: { created: Math.floor(Date.now() / 1000), data: videos },
+    };
+  } catch (err) {
+    if (log) log.error("VIDEO", `${provider} sdwebui error: ${err.message}`);
+    saveCallLog({
+      method: "POST",
+      path: "/v1/videos/generations",
+      status: 502,
+      model: `${provider}/${model}`,
+      provider,
+      duration: Date.now() - startTime,
+      error: err.message,
+    }).catch(() => {});
+    return { success: false, status: 502, error: `Video provider error: ${err.message}` };
+  }
+}

open-sse/index.ts

@@ -139,3 +139,28 @@ export {
   parseModerationModel,
   getAllModerationModels,
 } from "./config/moderationRegistry.ts";
+
+// Video Generation
+export { handleVideoGeneration } from "./handlers/videoGeneration.ts";
+export {
+  VIDEO_PROVIDERS,
+  getVideoProvider,
+  parseVideoModel,
+  getAllVideoModels,
+} from "./config/videoRegistry.ts";
+
+// Music Generation
+export { handleMusicGeneration } from "./handlers/musicGeneration.ts";
+export {
+  MUSIC_PROVIDERS,
+  getMusicProvider,
+  parseMusicModel,
+  getAllMusicModels,
+} from "./config/musicRegistry.ts";
+
+// Registry Utilities
+export {
+  parseModelFromRegistry,
+  getAllModelsFromRegistry,
+  buildAuthHeaders,
+} from "./config/registryUtils.ts";

open-sse/services/accountFallback.ts

@@ -24,14 +24,25 @@ export function getProviderProfile(provider) {
 // In-memory map: "provider:connectionId:model" → { reason, until, lockedAt }
 const modelLockouts = new Map();
 
-// Auto-cleanup expired lockouts every 15 seconds
-const _cleanupTimer = setInterval(() => {
-  const now = Date.now();
-  for (const [key, entry] of modelLockouts) {
-    if (now > entry.until) modelLockouts.delete(key);
+// Auto-cleanup expired lockouts every 15 seconds (lazy init for Cloudflare Workers compatibility)
+let _cleanupTimer: ReturnType<typeof setInterval> | null = null;
+
+function ensureCleanupTimer() {
+  if (_cleanupTimer) return;
+  try {
+    _cleanupTimer = setInterval(() => {
+      const now = Date.now();
+      for (const [key, entry] of modelLockouts) {
+        if (now > entry.until) modelLockouts.delete(key);
+      }
+    }, 15_000);
+    if (typeof _cleanupTimer === "object" && "unref" in _cleanupTimer) {
+      (_cleanupTimer as any).unref(); // Don't prevent process exit (Node.js only)
+    }
+  } catch {
+    // Cloudflare Workers may not support setInterval outside handlers — skip cleanup timer
   }
-}, 15_000);
-_cleanupTimer.unref(); // Don't prevent process exit
+}
 
 /**
  * Lock a specific model on a specific account
@@ -43,6 +54,7 @@ _cleanupTimer.unref(); // Don't prevent process exit
  */
 export function lockModel(provider, connectionId, model, reason, cooldownMs) {
   if (!model) return; // No model → skip model-level locking
+  ensureCleanupTimer();
   const key = `${provider}:${connectionId}:${model}`;
   modelLockouts.set(key, {
     reason,

open-sse/services/backgroundTaskDetector.ts

@@ -0,0 +1,187 @@
+/**
+ * Background Task Detector — Feature 3
+ *
+ * Detects when CLI tools send "background" requests (title generation,
+ * summarization, short descriptions) and provides model degradation
+ * recommendations to save premium model quota.
+ *
+ * Detection heuristics:
+ * - System prompt patterns indicating background/utility tasks
+ * - Very short conversations with summary-like system prompts
+ * - X-Request-Priority header
+ */
+
+// ── Configuration ───────────────────────────────────────────────────────────
+
+interface DegradationConfig {
+  enabled: boolean;
+  degradationMap: Record<string, string>; // original → cheaper model
+  detectionPatterns: string[]; // regex patterns for system prompt matching
+  stats: {
+    detected: number;
+    tokensSaved: number;
+  };
+}
+
+const DEFAULT_DETECTION_PATTERNS = [
+  "generate a title",
+  "generate title",
+  "create a title",
+  "create a short",
+  "summarize this",
+  "summarize the",
+  "write a brief",
+  "write a summary",
+  "one-line summary",
+  "one line summary",
+  "short description",
+  "brief description",
+  "conversation title",
+  "chat title",
+  "name this conversation",
+  "name this chat",
+  "title for this",
+  "suggest a title",
+  "label this",
+];
+
+const DEFAULT_DEGRADATION_MAP: Record<string, string> = {
+  // Premium → Cheap alternatives
+  "claude-opus-4-6": "gemini-2.5-flash",
+  "claude-opus-4-6-thinking": "gemini-2.5-flash",
+  "claude-opus-4-5-20251101": "gemini-2.5-flash",
+  "claude-sonnet-4-5-20250929": "gemini-2.5-flash",
+  "claude-sonnet-4-20250514": "gemini-2.5-flash",
+  "claude-sonnet-4": "gemini-2.5-flash",
+  "gemini-3.1-pro": "gemini-3.1-flash",
+  "gemini-3.1-pro-high": "gemini-3.1-flash",
+  "gemini-3-pro-preview": "gemini-3-flash-preview",
+  "gemini-2.5-pro": "gemini-2.5-flash",
+  "gpt-4o": "gpt-4o-mini",
+  "gpt-5": "gpt-5-mini",
+  "gpt-5.1": "gpt-5-mini",
+  "gpt-5.1-codex": "gpt-5.1-codex-mini",
+};
+
+// ── State ───────────────────────────────────────────────────────────────────
+
+let _config: DegradationConfig = {
+  enabled: false, // Disabled by default — user must opt in
+  degradationMap: { ...DEFAULT_DEGRADATION_MAP },
+  detectionPatterns: [...DEFAULT_DETECTION_PATTERNS],
+  stats: { detected: 0, tokensSaved: 0 },
+};
+
+// ── Config Management ───────────────────────────────────────────────────────
+
+/**
+ * Set the background degradation config (called from settings API or startup).
+ */
+export function setBackgroundDegradationConfig(config: Partial<DegradationConfig>): void {
+  _config = {
+    ..._config,
+    ...config,
+    stats: _config.stats, // preserve stats across config changes
+  };
+}
+
+/**
+ * Get current background degradation config.
+ */
+export function getBackgroundDegradationConfig(): DegradationConfig {
+  return {
+    ..._config,
+    degradationMap: { ..._config.degradationMap },
+    detectionPatterns: [..._config.detectionPatterns],
+    stats: { ..._config.stats },
+  };
+}
+
+/**
+ * Reset stats counters.
+ */
+export function resetStats(): void {
+  _config.stats = { detected: 0, tokensSaved: 0 };
+}
+
+// ── Detection ───────────────────────────────────────────────────────────────
+
+/**
+ * Check if a request is a background/utility task.
+ *
+ * @param {object} body - Request body
+ * @param {object} [headers] - Request headers (optional)
+ * @returns {boolean} True if the request looks like a background task
+ */
+export function isBackgroundTask(
+  body: any,
+  headers: Record<string, string> | null = null
+): boolean {
+  if (!body || typeof body !== "object") return false;
+
+  // 1. Check explicit header
+  if (headers) {
+    const priority =
+      headers["x-request-priority"] || headers["X-Request-Priority"] || headers["x-initiator"];
+    if (priority === "background" || priority === "Background") return true;
+  }
+
+  // 2. Check system prompt for background task patterns
+  const messages = body.messages || body.input || [];
+  if (!Array.isArray(messages) || messages.length === 0) return false;
+
+  // Find system message
+  const systemMsg = messages.find((m: any) => m.role === "system" || m.role === "developer");
+  if (!systemMsg) return false;
+
+  const systemContent =
+    typeof systemMsg.content === "string" ? systemMsg.content.toLowerCase() : "";
+
+  if (!systemContent) return false;
+
+  // Check against detection patterns
+  const matched = _config.detectionPatterns.some((pattern) =>
+    systemContent.includes(pattern.toLowerCase())
+  );
+
+  if (!matched) return false;
+
+  // 3. Additional heuristic: background tasks typically have very few messages
+  // (system + 1-2 user messages)
+  const userMessages = messages.filter((m: any) => m.role === "user");
+  if (userMessages.length > 3) return false; // Too many turns for a background task
+
+  return true;
+}
+
+/**
+ * Get the degraded (cheaper) model for a given model.
+ *
+ * @param {string} originalModel - The original model ID
+ * @returns {string} The cheaper model or original if no mapping exists
+ */
+export function getDegradedModel(originalModel: string): string {
+  if (!originalModel) return originalModel;
+
+  const degraded = _config.degradationMap[originalModel];
+  if (degraded) {
+    _config.stats.detected++;
+    return degraded;
+  }
+
+  return originalModel;
+}
+
+/**
+ * Get default degradation map (for UI reset).
+ */
+export function getDefaultDegradationMap(): Record<string, string> {
+  return { ...DEFAULT_DEGRADATION_MAP };
+}
+
+/**
+ * Get default detection patterns (for UI reset).
+ */
+export function getDefaultDetectionPatterns(): string[] {
+  return [...DEFAULT_DETECTION_PATTERNS];
+}

open-sse/services/modelDeprecation.ts

@@ -0,0 +1,125 @@
+/**
+ * Model Deprecation Auto-Forward — Feature 2
+ *
+ * Maps deprecated model IDs to their replacements so user configs
+ * don't break when providers rename or retire models.
+ *
+ * Supports both built-in aliases (static) and custom aliases (persisted via Settings API).
+ */
+
+// ── Built-in Deprecation Aliases ────────────────────────────────────────────
+// These are known renames/retirements across providers.
+// Format: deprecated ID → current ID
+const BUILT_IN_ALIASES: Record<string, string> = {
+  // Gemini legacy → current
+  "gemini-pro": "gemini-2.5-pro",
+  "gemini-pro-vision": "gemini-2.5-pro",
+  "gemini-1.5-pro": "gemini-2.5-pro",
+  "gemini-1.5-flash": "gemini-2.5-flash",
+  "gemini-1.0-pro": "gemini-2.5-pro",
+  "gemini-2.0-flash": "gemini-2.5-flash",
+
+  // Claude legacy → current
+  "claude-3-opus-20240229": "claude-opus-4-20250514",
+  "claude-3-sonnet-20240229": "claude-sonnet-4-20250514",
+  "claude-3-haiku-20240307": "claude-3-5-sonnet-20241022",
+  "claude-3-5-sonnet-latest": "claude-sonnet-4-20250514",
+  "claude-3-5-haiku-latest": "claude-3-5-sonnet-20241022",
+
+  // OpenAI legacy → current
+  "gpt-4-turbo-preview": "gpt-4-turbo",
+  "gpt-4-0125-preview": "gpt-4-turbo",
+  "gpt-4-1106-preview": "gpt-4-turbo",
+  "gpt-3.5-turbo-0125": "gpt-3.5-turbo",
+};
+
+// ── Custom Aliases (persisted via Settings API) ─────────────────────────────
+let _customAliases: Record<string, string> = {};
+
+/**
+ * Set custom aliases (called from settings API or startup).
+ */
+export function setCustomAliases(aliases: Record<string, string>): void {
+  _customAliases = { ...aliases };
+}
+
+/**
+ * Get current custom aliases.
+ */
+export function getCustomAliases(): Record<string, string> {
+  return { ..._customAliases };
+}
+
+/**
+ * Get the full alias map (built-in + custom).
+ * Custom aliases take precedence over built-in.
+ */
+export function getAllAliases(): Record<string, string> {
+  return { ...BUILT_IN_ALIASES, ..._customAliases };
+}
+
+/**
+ * Resolve a model alias to its current ID.
+ * Custom aliases override built-in ones.
+ *
+ * @param {string} modelId - The model ID to resolve
+ * @returns {string} The resolved model ID, or the original if not deprecated
+ */
+export function resolveModelAlias(modelId: string): string {
+  if (!modelId) return modelId;
+
+  // Check custom aliases first (higher priority)
+  if (_customAliases[modelId]) return _customAliases[modelId];
+
+  // Then check built-in
+  if (BUILT_IN_ALIASES[modelId]) return BUILT_IN_ALIASES[modelId];
+
+  return modelId;
+}
+
+/**
+ * Get a deprecation notice if the model is deprecated.
+ *
+ * @param {string} modelId - The model ID to check
+ * @returns {string | null} Deprecation message or null if not deprecated
+ */
+export function getDeprecationNotice(modelId: string): string | null {
+  if (!modelId) return null;
+
+  const resolved = resolveModelAlias(modelId);
+  if (resolved === modelId) return null;
+
+  return `Model "${modelId}" is deprecated. Forwarding to "${resolved}".`;
+}
+
+/**
+ * Check if a model is deprecated.
+ */
+export function isDeprecated(modelId: string): boolean {
+  return getDeprecationNotice(modelId) !== null;
+}
+
+/**
+ * Add a custom alias.
+ */
+export function addCustomAlias(from: string, to: string): void {
+  _customAliases[from] = to;
+}
+
+/**
+ * Remove a custom alias.
+ */
+export function removeCustomAlias(from: string): boolean {
+  if (_customAliases[from]) {
+    delete _customAliases[from];
+    return true;
+  }
+  return false;
+}
+
+/**
+ * Get the built-in aliases (read-only reference).
+ */
+export function getBuiltInAliases(): Record<string, string> {
+  return { ...BUILT_IN_ALIASES };
+}

open-sse/services/rateLimitManager.ts

@@ -19,6 +19,11 @@ const limiters = new Map();
 // Store connections that have rate limit protection enabled
 const enabledConnections = new Set();
 
+// Store learned limits for persistence (debounced)
+const learnedLimits: Record<string, any> = {};
+let persistTimer: ReturnType<typeof setTimeout> | null = null;
+const PERSIST_DEBOUNCE_MS = 60_000; // Debounce persistence to every 60s max
+
 // Track initialization
 let initialized = false;
 
@@ -82,6 +87,9 @@ export async function initializeRateLimits() {
         `🛡️ [RATE-LIMIT] Loaded ${explicitCount} explicit + ${autoCount} auto-enabled (API key) protection(s)`
       );
     }
+
+    // Load persisted learned limits
+    await loadPersistedLimits();
   } catch (err) {
     console.error("[RATE-LIMIT] Failed to load settings:", err.message);
   }
@@ -314,6 +322,9 @@ export function updateFromHeaders(provider, connectionId, headers, status, model
     }
 
     limiter.updateSettings(updates);
+
+    // Persist learned limits (debounced)
+    recordLearnedLimit(provider, connectionId, { limit, remaining, minTime: updates.minTime });
   }
 }
 
@@ -360,6 +371,82 @@ export function getAllRateLimitStatus() {
   return result;
 }
 
+/**
+ * Get all learned limits (for dashboard display).
+ */
+export function getLearnedLimits() {
+  return { ...learnedLimits };
+}
+
+// ─── Persistence ────────────────────────────────────────────────────────────
+
+/**
+ * Record a learned limit for debounced persistence.
+ */
+function recordLearnedLimit(provider: string, connectionId: string, limits: any) {
+  const key = `${provider}:${connectionId}`;
+  learnedLimits[key] = {
+    ...limits,
+    provider,
+    connectionId,
+    lastUpdated: Date.now(),
+  };
+
+  // Debounce: save at most once per PERSIST_DEBOUNCE_MS
+  if (!persistTimer) {
+    persistTimer = setTimeout(async () => {
+      persistTimer = null;
+      try {
+        const { updateSettings } = await import("@/lib/db/settings");
+        await updateSettings({ learnedRateLimits: JSON.stringify(learnedLimits) });
+        console.log(
+          `💾 [RATE-LIMIT] Persisted learned limits for ${Object.keys(learnedLimits).length} provider(s)`
+        );
+      } catch (err) {
+        console.error("[RATE-LIMIT] Failed to persist learned limits:", err.message);
+      }
+    }, PERSIST_DEBOUNCE_MS);
+  }
+}
+
+/**
+ * Load persisted learned limits on startup.
+ */
+async function loadPersistedLimits() {
+  try {
+    const { getSettings } = await import("@/lib/db/settings");
+    const settings = await getSettings();
+    const raw = settings?.learnedRateLimits;
+    if (!raw) return;
+
+    const parsed = JSON.parse(raw);
+    let count = 0;
+
+    for (const [key, data] of Object.entries<any>(parsed)) {
+      // Skip stale entries (older than 24h)
+      if (data.lastUpdated && Date.now() - data.lastUpdated > 24 * 60 * 60 * 1000) continue;
+
+      learnedLimits[key] = data;
+
+      // Apply to limiter if it exists and has rate limit enabled
+      if (data.connectionId && enabledConnections.has(data.connectionId)) {
+        const limiter = limiters.get(key);
+        if (limiter && data.limit) {
+          const minTime = data.minTime || Math.max(0, Math.floor(60000 / data.limit) - 10);
+          limiter.updateSettings({ minTime });
+          count++;
+        }
+      }
+    }
+
+    if (count > 0) {
+      console.log(`📥 [RATE-LIMIT] Restored ${count} learned rate limit(s) from persistence`);
+    }
+  } catch (err) {
+    console.error("[RATE-LIMIT] Failed to load persisted limits:", err.message);
+  }
+}
+
 /**
  * Update rate limiter based on API response body (JSON error responses).
  * Providers embed retry info in JSON payloads in different formats.

open-sse/services/thinkingBudget.ts

@@ -21,6 +21,15 @@ export const EFFORT_BUDGETS = {
   high: 131072,
 };
 
+// thinkingLevel string → budget token mapping
+// Used when clients send string-based thinking levels (e.g., VS Code Copilot)
+export const THINKING_LEVEL_MAP = {
+  none: 0,
+  low: 1024,
+  medium: 10240,
+  high: 131072,
+};
+
 // Default config (passthrough = backward compatible)
 export const DEFAULT_THINKING_CONFIG = {
   mode: ThinkingMode.PASSTHROUGH,
@@ -45,10 +54,81 @@ export function getThinkingBudgetConfig() {
   return { ..._config };
 }
 
+/**
+ * Normalize thinkingLevel string fields into numeric budget.
+ * Handles: body.thinkingLevel, body.thinking_level,
+ * and Gemini's generationConfig.thinkingConfig.thinkingLevel
+ *
+ * @param {object} body - Request body
+ * @returns {object} Body with string thinkingLevel converted to numeric budget
+ */
+export function normalizeThinkingLevel(body) {
+  if (!body || typeof body !== "object") return body;
+  const result = { ...body };
+
+  // Handle top-level thinkingLevel or thinking_level string fields
+  const levelStr = result.thinkingLevel || result.thinking_level;
+  if (typeof levelStr === "string" && THINKING_LEVEL_MAP[levelStr] !== undefined) {
+    const budget = THINKING_LEVEL_MAP[levelStr];
+    // Convert to Claude thinking format as canonical representation
+    result.thinking = {
+      type: budget > 0 ? "enabled" : "disabled",
+      budget_tokens: budget,
+    };
+    delete result.thinkingLevel;
+    delete result.thinking_level;
+  }
+
+  // Handle Gemini's generationConfig.thinkingConfig.thinkingLevel
+  const geminiLevel =
+    result.generationConfig?.thinkingConfig?.thinkingLevel ||
+    result.generationConfig?.thinking_config?.thinkingLevel;
+  if (typeof geminiLevel === "string" && THINKING_LEVEL_MAP[geminiLevel] !== undefined) {
+    const budget = THINKING_LEVEL_MAP[geminiLevel];
+    result.generationConfig = {
+      ...result.generationConfig,
+      thinking_config: { thinking_budget: budget },
+    };
+    // Clean up camelCase variant if it was the source
+    if (result.generationConfig.thinkingConfig) {
+      delete result.generationConfig.thinkingConfig;
+    }
+  }
+
+  return result;
+}
+
+/**
+ * Ensure models with -thinking suffix have thinking config injected.
+ * Prevents 400 errors from Claude API when thinking params are missing.
+ *
+ * @param {object} body - Request body
+ * @returns {object} Body with thinking config auto-injected if needed
+ */
+export function ensureThinkingConfig(body) {
+  if (!body || typeof body !== "object") return body;
+  const model = body.model || "";
+
+  // Only auto-inject for models with -thinking suffix
+  if (!model.endsWith("-thinking")) return body;
+
+  // If thinking config already present, don't override
+  if (body.thinking) return body;
+
+  const result = { ...body };
+  result.thinking = {
+    type: "enabled",
+    budget_tokens: EFFORT_BUDGETS.medium, // 10240 default
+  };
+  return result;
+}
+
 /**
  * Apply thinking budget control to a request body.
  * Called before format-specific translation.
  *
+ * Pipeline: normalizeThinkingLevel → ensureThinkingConfig → mode processing
+ *
  * @param {object} body - Request body (any format)
  * @param {object} [config] - Override config (defaults to stored config)
  * @returns {object} Modified body
@@ -57,21 +137,27 @@ export function applyThinkingBudget(body, config = null) {
   const cfg = config || _config;
   if (!body || typeof body !== "object") return body;
 
+  // Pre-processing: convert string thinkingLevel to numeric budget
+  let processed = normalizeThinkingLevel(body);
+
+  // Pre-processing: auto-inject thinking config for -thinking suffix models
+  processed = ensureThinkingConfig(processed);
+
   switch (cfg.mode) {
     case ThinkingMode.AUTO:
-      return stripThinkingConfig(body);
+      return stripThinkingConfig(processed);
 
     case ThinkingMode.PASSTHROUGH:
-      return body; // No changes
+      return processed;
 
     case ThinkingMode.CUSTOM:
-      return setCustomBudget(body, cfg.customBudget);
+      return setCustomBudget(processed, cfg.customBudget);
 
     case ThinkingMode.ADAPTIVE:
-      return applyAdaptiveBudget(body, cfg);
+      return applyAdaptiveBudget(processed, cfg);
 
     default:
-      return body;
+      return processed;
   }
 }
 
@@ -151,9 +237,10 @@ function applyAdaptiveBudget(body, cfg) {
   for (let i = messages.length - 1; i >= 0; i--) {
     const msg = messages[i];
     if (msg.role === "user") {
-      lastMsgLength = typeof msg.content === "string"
-        ? msg.content.length
-        : JSON.stringify(msg.content || "").length;
+      lastMsgLength =
+        typeof msg.content === "string"
+          ? msg.content.length
+          : JSON.stringify(msg.content || "").length;
       break;
     }
   }
@@ -173,7 +260,7 @@ function applyAdaptiveBudget(body, cfg) {
 /**
  * Check if model name suggests thinking capability
  */
-function hasThinkingCapableModel(body) {
+export function hasThinkingCapableModel(body) {
   const model = body.model || "";
   return (
     model.includes("claude") ||
@@ -181,6 +268,7 @@ function hasThinkingCapableModel(body) {
     model.includes("o3") ||
     model.includes("o4") ||
     model.includes("gemini") ||
+    model.endsWith("-thinking") ||
     model.includes("thinking")
   );
 }

open-sse/services/tokenRefresh.ts

@@ -323,9 +323,13 @@ export async function refreshQwenToken(refreshToken, log) {
       }
 
       if (errorCode === "invalid_request") {
-        log?.error?.("TOKEN_REFRESH", "Qwen refresh token is invalid or expired. Re-authentication required.", {
-          status: response.status,
-        });
+        log?.error?.(
+          "TOKEN_REFRESH",
+          "Qwen refresh token is invalid or expired. Re-authentication required.",
+          {
+            status: response.status,
+          }
+        );
         return { error: "invalid_request" };
       }
 
@@ -720,8 +724,11 @@ export function supportsTokenRefresh(provider) {
  * Callers should stop retrying and request re-authentication.
  */
 export function isUnrecoverableRefreshError(result) {
-  return result && typeof result === "object" &&
-    (result.error === "refresh_token_reused" || result.error === "invalid_request");
+  return (
+    result &&
+    typeof result === "object" &&
+    (result.error === "refresh_token_reused" || result.error === "invalid_request")
+  );
 }
 
 /**
@@ -841,12 +848,103 @@ export async function getAllAccessTokens(userInfo, log) {
 /**
  * Refresh token with retry and exponential backoff
  * Retries on failure with increasing delay: 1s, 2s, 3s...
+ *
+ * Includes:
+ * - Per-provider circuit breaker (5 consecutive failures → 30min pause)
+ * - 30s timeout per refresh attempt to prevent hanging connections
+ *
  * @param {function} refreshFn - Async function that returns token or null
  * @param {number} maxRetries - Max retry attempts (default 3)
  * @param {object} log - Logger instance (optional)
+ * @param {string} provider - Provider ID for circuit breaker tracking (optional)
  * @returns {Promise<object|null>} Token result or null if all retries fail
  */
-export async function refreshWithRetry(refreshFn, maxRetries = 3, log = null) {
+
+// ─── Circuit Breaker State ──────────────────────────────────────────────────
+const _circuitBreaker: Record<string, { failures: number; blockedUntil: number }> = {};
+const CIRCUIT_BREAKER_THRESHOLD = 5; // consecutive failures before tripping
+const CIRCUIT_BREAKER_COOLDOWN = 30 * 60 * 1000; // 30 minutes
+const REFRESH_TIMEOUT_MS = 30_000; // 30s max per refresh attempt
+
+/**
+ * Check if a provider is circuit-breaker blocked.
+ */
+export function isProviderBlocked(provider: string): boolean {
+  const state = _circuitBreaker[provider];
+  if (!state) return false;
+  if (state.blockedUntil > Date.now()) return true;
+  // Cooldown expired — reset
+  delete _circuitBreaker[provider];
+  return false;
+}
+
+/**
+ * Get circuit breaker status for all providers (for diagnostics).
+ */
+export function getCircuitBreakerStatus(): Record<string, any> {
+  const result: Record<string, any> = {};
+  for (const [provider, state] of Object.entries(_circuitBreaker)) {
+    result[provider] = {
+      failures: state.failures,
+      blocked: state.blockedUntil > Date.now(),
+      blockedUntil:
+        state.blockedUntil > Date.now() ? new Date(state.blockedUntil).toISOString() : null,
+      remainingMs: Math.max(0, state.blockedUntil - Date.now()),
+    };
+  }
+  return result;
+}
+
+/**
+ * Record a successful refresh — resets circuit breaker for provider.
+ */
+function recordSuccess(provider: string) {
+  if (_circuitBreaker[provider]) {
+    delete _circuitBreaker[provider];
+  }
+}
+
+/**
+ * Record a failed refresh — increments circuit breaker counter.
+ */
+function recordFailure(provider: string, log: any = null) {
+  if (!_circuitBreaker[provider]) {
+    _circuitBreaker[provider] = { failures: 0, blockedUntil: 0 };
+  }
+  _circuitBreaker[provider].failures++;
+
+  if (_circuitBreaker[provider].failures >= CIRCUIT_BREAKER_THRESHOLD) {
+    _circuitBreaker[provider].blockedUntil = Date.now() + CIRCUIT_BREAKER_COOLDOWN;
+    log?.error?.(
+      "TOKEN_REFRESH",
+      `🔴 Circuit breaker tripped for ${provider}: ${CIRCUIT_BREAKER_THRESHOLD} consecutive failures. ` +
+        `Blocked for ${CIRCUIT_BREAKER_COOLDOWN / 60000}min. Provider needs re-authentication.`
+    );
+  }
+}
+
+/**
+ * Execute a function with a timeout.
+ */
+async function withTimeout<T>(fn: () => Promise<T>, timeoutMs: number): Promise<T | null> {
+  return Promise.race([
+    fn(),
+    new Promise<null>((resolve) => setTimeout(() => resolve(null), timeoutMs)),
+  ]);
+}
+
+export async function refreshWithRetry(
+  refreshFn,
+  maxRetries = 3,
+  log = null,
+  provider = "unknown"
+) {
+  // Circuit breaker check
+  if (isProviderBlocked(provider)) {
+    log?.warn?.("TOKEN_REFRESH", `⚡ Circuit breaker active for ${provider}, skipping refresh`);
+    return null;
+  }
+
   for (let attempt = 0; attempt < maxRetries; attempt++) {
     if (attempt > 0) {
       const delay = attempt * 1000;
@@ -855,13 +953,18 @@ export async function refreshWithRetry(refreshFn, maxRetries = 3, log = null) {
     }
 
     try {
-      const result = await refreshFn();
-      if (result) return result;
+      const result = await withTimeout(refreshFn, REFRESH_TIMEOUT_MS);
+      if (result) {
+        recordSuccess(provider);
+        return result;
+      }
     } catch (error) {
       log?.warn?.("TOKEN_REFRESH", `Attempt ${attempt + 1}/${maxRetries} failed: ${error.message}`);
     }
   }
 
-  log?.error?.("TOKEN_REFRESH", `All ${maxRetries} retry attempts failed`);
+  // All retries exhausted — record failure for circuit breaker
+  recordFailure(provider, log);
+  log?.error?.("TOKEN_REFRESH", `All ${maxRetries} retry attempts failed for ${provider}`);
   return null;
 }

open-sse/translator/request/openai-to-gemini.ts

@@ -180,7 +180,9 @@ function openaiToGeminiBase(model, body, stream) {
         functionDeclarations.push({
           name: t.name,
           description: t.description || "",
-          parameters: t.input_schema || { type: "object", properties: {} },
+          parameters: cleanJSONSchemaForAntigravity(
+            t.input_schema || { type: "object", properties: {} }
+          ),
         });
       }
       // OpenAI format
@@ -189,7 +191,9 @@ function openaiToGeminiBase(model, body, stream) {
         functionDeclarations.push({
           name: fn.name,
           description: fn.description || "",
-          parameters: fn.parameters || { type: "object", properties: {} },
+          parameters: cleanJSONSchemaForAntigravity(
+            fn.parameters || { type: "object", properties: {} }
+          ),
         });
       }
     }
@@ -206,9 +210,7 @@ function openaiToGeminiBase(model, body, stream) {
       // Extract the schema (may be nested under .schema key)
       const schema = body.response_format.json_schema.schema || body.response_format.json_schema;
       if (schema && typeof schema === "object") {
-        // Remove unsupported keywords for Gemini (it uses a subset of JSON Schema)
-        const { $schema, additionalProperties, ...cleanSchema } = schema;
-        result.generationConfig.responseSchema = cleanSchema;
+        result.generationConfig.responseSchema = cleanJSONSchemaForAntigravity(schema);
       }
     } else if (body.response_format.type === "json_object") {
       result.generationConfig.responseMimeType = "application/json";
@@ -269,8 +271,16 @@ export function openaiToGeminiCLIRequest(model, body, stream) {
 
 // Wrap Gemini CLI format in Cloud Code wrapper
 function wrapInCloudCodeEnvelope(model, geminiCLI, credentials = null, isAntigravity = false) {
+  const hasRealProject = !!credentials?.projectId;
   const projectId = credentials?.projectId || generateProjectId();
 
+  if (!hasRealProject) {
+    console.warn(
+      `[${isAntigravity ? "Antigravity" : "GeminiCLI"}] ⚠️ No projectId in credentials — using generated fallback "${projectId}". ` +
+        `This may cause 404 errors. Ensure the OAuth token includes a valid GCP project.`
+    );
+  }
+
   const cleanModel = model.includes("/") ? model.split("/").pop()! : model;
 
   const envelope: Record<string, any> = {
@@ -313,10 +323,17 @@ function wrapInCloudCodeEnvelope(model, geminiCLI, credentials = null, isAntigra
   return envelope;
 }
 
-// Wrap Claude format in Cloud Code envelope for Antigravity
 function wrapInCloudCodeEnvelopeForClaude(model, claudeRequest, credentials = null) {
+  const hasRealProject = !!credentials?.projectId;
   const projectId = credentials?.projectId || generateProjectId();
 
+  if (!hasRealProject) {
+    console.warn(
+      `[Antigravity/Claude] ⚠️ No projectId in credentials — using generated fallback "${projectId}". ` +
+        `This may cause 404 errors. Ensure the OAuth token includes a valid GCP project.`
+    );
+  }
+
   const cleanModel = model.includes("/") ? model.split("/").pop()! : model;
 
   const envelope: Record<string, any> = {

open-sse/translator/response/openai-responses.ts

@@ -364,6 +364,7 @@ export function openaiResponsesToOpenAIResponse(chunk, state) {
     // Flush: send final chunk with finish_reason
     if (!state.finishReasonSent && state.started) {
       state.finishReasonSent = true;
+      const hadToolCalls = (state.toolCallIndex || 0) > 0;
       return {
         id: state.chatId || `chatcmpl-${Date.now()}`,
         object: "chat.completion.chunk",
@@ -373,7 +374,7 @@ export function openaiResponsesToOpenAIResponse(chunk, state) {
           {
             index: 0,
             delta: {},
-            finish_reason: "stop",
+            finish_reason: hadToolCalls ? "tool_calls" : "stop",
           },
         ],
       };
@@ -468,6 +469,8 @@ export function openaiResponsesToOpenAIResponse(chunk, state) {
             tool_calls: [
               {
                 index: state.toolCallIndex,
+                id: state.currentToolCallId,
+                type: "function",
                 function: { arguments: argsDelta },
               },
             ],
@@ -517,7 +520,9 @@ export function openaiResponsesToOpenAIResponse(chunk, state) {
 
     if (!state.finishReasonSent) {
       state.finishReasonSent = true;
-      state.finishReason = "stop"; // Mark for usage injection in stream.js
+      const hadToolCalls = (state.toolCallIndex || 0) > 0;
+      const reason = hadToolCalls ? "tool_calls" : "stop";
+      state.finishReason = reason; // Mark for usage injection in stream.js
 
       const finalChunk: Record<string, any> = {
         id: state.chatId,
@@ -528,7 +533,7 @@ export function openaiResponsesToOpenAIResponse(chunk, state) {
           {
             index: 0,
             delta: {},
-            finish_reason: "stop",
+            finish_reason: reason,
           },
         ],
       };

open-sse/utils/comfyuiClient.ts

@@ -0,0 +1,103 @@
+/**
+ * Shared ComfyUI API Client
+ *
+ * Used by image, video, and music handlers to submit workflows,
+ * poll for completion, and fetch output files from a ComfyUI server.
+ */
+
+/**
+ * Submit a workflow to ComfyUI for execution.
+ * @returns The prompt_id for polling
+ */
+export async function submitComfyWorkflow(
+  baseUrl: string,
+  workflow: object
+): Promise<string> {
+  const res = await fetch(`${baseUrl}/prompt`, {
+    method: "POST",
+    headers: { "Content-Type": "application/json" },
+    body: JSON.stringify({ prompt: workflow }),
+  });
+
+  if (!res.ok) {
+    const errText = await res.text();
+    throw new Error(`ComfyUI submit failed (${res.status}): ${errText}`);
+  }
+
+  const data = await res.json();
+  return data.prompt_id;
+}
+
+/**
+ * Poll ComfyUI history endpoint until the prompt completes or times out.
+ * @returns The history entry for the completed prompt
+ */
+export async function pollComfyResult(
+  baseUrl: string,
+  promptId: string,
+  timeoutMs: number = 120_000
+): Promise<any> {
+  const start = Date.now();
+
+  while (Date.now() - start < timeoutMs) {
+    await new Promise((r) => setTimeout(r, 2000));
+
+    const res = await fetch(`${baseUrl}/history/${promptId}`);
+    if (!res.ok) continue;
+
+    const data = await res.json();
+    const entry = data[promptId];
+
+    if (entry && entry.outputs && Object.keys(entry.outputs).length > 0) {
+      return entry;
+    }
+  }
+
+  throw new Error(`ComfyUI prompt ${promptId} timed out after ${timeoutMs}ms`);
+}
+
+/**
+ * Fetch an output file from ComfyUI.
+ * @returns The file contents as ArrayBuffer
+ */
+export async function fetchComfyOutput(
+  baseUrl: string,
+  filename: string,
+  subfolder: string,
+  type: string
+): Promise<ArrayBuffer> {
+  const url = new URL(`${baseUrl}/view`);
+  url.searchParams.set("filename", filename);
+  url.searchParams.set("subfolder", subfolder);
+  url.searchParams.set("type", type);
+
+  const res = await fetch(url.toString());
+  if (!res.ok) {
+    throw new Error(`ComfyUI fetch output failed (${res.status})`);
+  }
+
+  return res.arrayBuffer();
+}
+
+/**
+ * Extract output files from a ComfyUI history entry.
+ * Returns an array of { filename, subfolder, type } for each output.
+ */
+export function extractComfyOutputFiles(
+  historyEntry: any
+): Array<{ filename: string; subfolder: string; type: string }> {
+  const files: Array<{ filename: string; subfolder: string; type: string }> = [];
+
+  for (const nodeOutput of Object.values(historyEntry.outputs || {})) {
+    const outputs = (nodeOutput as any).images || (nodeOutput as any).gifs || (nodeOutput as any).audio || [];
+    for (const file of outputs) {
+      files.push({
+        filename: file.filename,
+        subfolder: file.subfolder || "",
+        type: file.type || "output",
+      });
+    }
+  }
+
+  return files;
+}

open-sse/utils/proxyDispatcher.ts

@@ -4,13 +4,39 @@ import { socksDispatcher } from "fetch-socks";
 const DISPATCHER_CACHE_KEY = Symbol.for("omniroute.proxyDispatcher.cache");
 const SUPPORTED_PROTOCOLS = new Set(["http:", "https:", "socks5:"]);
 
-function getDispatcherCache() {
+function getDispatcherCache(): Map<string, any> {
   if (!globalThis[DISPATCHER_CACHE_KEY]) {
     globalThis[DISPATCHER_CACHE_KEY] = new Map();
   }
   return globalThis[DISPATCHER_CACHE_KEY];
 }
 
+/**
+ * Clear all cached proxy dispatchers.
+ * Call this when proxy configuration changes to avoid stale connections.
+ */
+export function clearDispatcherCache() {
+  const cache = getDispatcherCache();
+  cache.clear();
+}
+
+/**
+ * Extract the port from a proxy URL string before URL parsing.
+ * `new URL("http://host:80")` strips port 80 since it's the HTTP default,
+ * but proxy servers commonly listen on port 80/443, so we need to preserve it.
+ */
+function extractExplicitPort(urlStr) {
+  try {
+    // Match port in the host portion: "scheme://[user:pass@]host:PORT[/...]"
+    const match = urlStr.match(/:\/\/(?:[^@]*@)?[^:/\s]+:(\d+)/);
+    if (match) {
+      const port = Number(match[1]);
+      if (Number.isInteger(port) && port >= 1 && port <= 65535) return String(port);
+    }
+  } catch {}
+  return null;
+}
+
 function defaultPortForProtocol(protocol) {
   if (protocol === "https:" || protocol === "wss:") return "443";
   if (protocol === "socks5:") return "1080";
@@ -26,13 +52,28 @@ function normalizePort(port, protocol) {
   return String(parsed);
 }
 
+/**
+ * Build a proxy URL string manually from parsed URL components.
+ * We cannot use URL.toString() because the URL serializer silently strips
+ * default ports (80 for http, 443 for https). Proxy servers commonly
+ * listen on these ports, so we must always include the port explicitly.
+ */
+function buildProxyUrlString(parsed, port) {
+  const auth =
+    parsed.username
+      ? `${parsed.username}${parsed.password ? `:${parsed.password}` : ""}@`
+      : "";
+  return `${parsed.protocol}//${auth}${parsed.hostname}:${port}`;
+}
+
 export function isSocks5ProxyEnabled() {
   return process.env.ENABLE_SOCKS5_PROXY === "true";
 }
 
 export function proxyUrlForLogs(proxyUrl) {
+  const explicitPort = extractExplicitPort(proxyUrl);
   const parsed = new URL(proxyUrl);
-  const port = parsed.port || defaultPortForProtocol(parsed.protocol);
+  const port = explicitPort || parsed.port || defaultPortForProtocol(parsed.protocol);
   return `${parsed.protocol}//${parsed.hostname}:${port}`;
 }
 
@@ -41,6 +82,11 @@ export function normalizeProxyUrl(
   source = "proxy",
   { allowSocks5 = isSocks5ProxyEnabled() } = {}
 ) {
+  // Extract the explicit port from the raw URL string BEFORE parsing,
+  // because `new URL()` silently strips default ports (80 for http,
+  // 443 for https), which are valid and common for proxy servers.
+  const explicitPort = extractExplicitPort(proxyUrl);
+
   let parsed;
   try {
     parsed = new URL(proxyUrl);
@@ -62,8 +108,12 @@ export function normalizeProxyUrl(
     throw new Error(`[ProxyDispatcher] Invalid ${source} host`);
   }
 
-  parsed.port = normalizePort(parsed.port, parsed.protocol);
-  return parsed.toString();
+  // Use the explicit port from the raw string if present, otherwise apply default.
+  const port = explicitPort || normalizePort(parsed.port, parsed.protocol);
+
+  // Build the URL string manually instead of using parsed.toString(),
+  // which would strip default ports (80/443) and break the proxy connection.
+  return buildProxyUrlString(parsed, port);
 }
 
 export function proxyConfigToUrl(proxyConfig, { allowSocks5 = isSocks5ProxyEnabled() } = {}) {
@@ -93,14 +143,15 @@ export function proxyConfigToUrl(proxyConfig, { allowSocks5 = isSocks5ProxyEnabl
   }
 
   const port = normalizePort(proxyConfig.port, protocol);
-  const proxyUrl = new URL(`${type}://${proxyConfig.host}:${port}`);
 
-  if (proxyConfig.username) {
-    proxyUrl.username = proxyConfig.username;
-    proxyUrl.password = proxyConfig.password || "";
-  }
+  // Build the URL string manually to preserve the port through normalization.
+  const auth = proxyConfig.username
+    ? `${encodeURIComponent(proxyConfig.username)}:${proxyConfig.password ? encodeURIComponent(proxyConfig.password) : ""}@`
+    : "";
 
-  return normalizeProxyUrl(proxyUrl.toString(), "context proxy", { allowSocks5 });
+  const proxyUrlStr = `${type}://${auth}${proxyConfig.host}:${port}`;
+
+  return normalizeProxyUrl(proxyUrlStr, "context proxy", { allowSocks5 });
 }
 
 export function createProxyDispatcher(proxyUrl) {
@@ -111,11 +162,14 @@ export function createProxyDispatcher(proxyUrl) {
   if (dispatcher) return dispatcher;
 
   const parsed = new URL(normalizedUrl);
+  const explicitPort = extractExplicitPort(normalizedUrl);
+  const port = explicitPort || normalizePort(parsed.port, parsed.protocol);
+
   if (parsed.protocol === "socks5:") {
     const socksOptions: Record<string, any> = {
       type: 5,
       host: parsed.hostname,
-      port: Number(normalizePort(parsed.port, parsed.protocol)),
+      port: Number(port),
     };
     if (parsed.username) socksOptions.userId = decodeURIComponent(parsed.username);
     if (parsed.password) socksOptions.password = decodeURIComponent(parsed.password);
@@ -126,4 +180,4 @@ export function createProxyDispatcher(proxyUrl) {
 
   dispatcherCache.set(normalizedUrl, dispatcher);
   return dispatcher;
-}
+}

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "omniroute",
-  "version": "1.6.4",
+  "version": "1.7.12",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "omniroute",
-      "version": "1.6.4",
+      "version": "1.7.12",
       "hasInstallScript": true,
       "license": "MIT",
       "workspaces": [
@@ -3063,9 +3063,9 @@
       "license": "MIT"
     },
     "node_modules/@types/node": {
-      "version": "25.3.0",
-      "resolved": "https://registry.npmjs.org/@types/node/-/node-25.3.0.tgz",
-      "integrity": "sha512-4K3bqJpXpqfg2XKGK9bpDTc6xO/xoUP/RBWS7AtRMug6zZFaRekiLzjVtAoZMquxoAbzBvy5nxQ7veS5eYzf8A==",
+      "version": "25.3.3",
+      "resolved": "https://registry.npmjs.org/@types/node/-/node-25.3.3.tgz",
+      "integrity": "sha512-DpzbrH7wIcBaJibpKo9nnSQL0MTRdnWttGyE5haGwK86xgMOkFLp7vEyfQPGLOJh5wNYiJ3V9PmUMDhV9u8kkQ==",
       "license": "MIT",
       "dependencies": {
         "undici-types": "~7.18.0"
@@ -7763,19 +7763,18 @@
       }
     },
     "node_modules/lint-staged": {
-      "version": "16.2.7",
-      "resolved": "https://registry.npmjs.org/lint-staged/-/lint-staged-16.2.7.tgz",
-      "integrity": "sha512-lDIj4RnYmK7/kXMya+qJsmkRFkGolciXjrsZ6PC25GdTfWOAWetR0ZbsNXRAj1EHHImRSalc+whZFg56F5DVow==",
+      "version": "16.3.1",
+      "resolved": "https://registry.npmjs.org/lint-staged/-/lint-staged-16.3.1.tgz",
+      "integrity": "sha512-bqvvquXzFBAlSbluugR4KXAe4XnO/QZcKVszpkBtqLWa2KEiVy8n6Xp38OeUbv/gOJOX4Vo9u5pFt/ADvbm42Q==",
       "dev": true,
       "license": "MIT",
       "dependencies": {
-        "commander": "^14.0.2",
+        "commander": "^14.0.3",
         "listr2": "^9.0.5",
         "micromatch": "^4.0.8",
-        "nano-spawn": "^2.0.0",
-        "pidtree": "^0.6.0",
         "string-argv": "^0.3.2",
-        "yaml": "^2.8.1"
+        "tinyexec": "^1.0.2",
+        "yaml": "^2.8.2"
       },
       "bin": {
         "lint-staged": "bin/lint-staged.js"
@@ -8084,19 +8083,6 @@
       "integrity": "sha512-6FlzubTLZG3J2a/NVCAleEhjzq5oxgHyaCU9yYXvcLsvoVaHJq/s5xXI6/XXP6tz7R9xAOtHnSO/tXtF3WRTlA==",
       "license": "MIT"
     },
-    "node_modules/nano-spawn": {
-      "version": "2.0.0",
-      "resolved": "https://registry.npmjs.org/nano-spawn/-/nano-spawn-2.0.0.tgz",
-      "integrity": "sha512-tacvGzUY5o2D8CBh2rrwxyNojUsZNU2zjNTzKQrkgGJQTbGAfArVWXSKMBokBeeg6C7OLRGUEyoFlYbfeWQIqw==",
-      "dev": true,
-      "license": "MIT",
-      "engines": {
-        "node": ">=20.17"
-      },
-      "funding": {
-        "url": "https://github.com/sindresorhus/nano-spawn?sponsor=1"
-      }
-    },
     "node_modules/nanoid": {
       "version": "3.3.11",
       "resolved": "https://registry.npmjs.org/nanoid/-/nanoid-3.3.11.tgz",
@@ -8730,19 +8716,6 @@
         "url": "https://github.com/sponsors/jonschlinkert"
       }
     },
-    "node_modules/pidtree": {
-      "version": "0.6.0",
-      "resolved": "https://registry.npmjs.org/pidtree/-/pidtree-0.6.0.tgz",
-      "integrity": "sha512-eG2dWTVw5bzqGRztnHExczNxt5VGsE6OwTeCG3fdUf9KBsZzO3R5OIIIzWR+iZA0NtZ+RDVdaoE2dK1cn6jH4g==",
-      "dev": true,
-      "license": "MIT",
-      "bin": {
-        "pidtree": "bin/pidtree.js"
-      },
-      "engines": {
-        "node": ">=0.10"
-      }
-    },
     "node_modules/pino": {
       "version": "10.3.1",
       "resolved": "https://registry.npmjs.org/pino/-/pino-10.3.1.tgz",
@@ -10384,6 +10357,16 @@
       "integrity": "sha512-+FbBPE1o9QAYvviau/qC5SE3caw21q3xkvWKBtja5vgqOWIHHJ3ioaq1VPfn/Szqctz2bU/oYeKd9/z5BL+PVg==",
       "license": "MIT"
     },
+    "node_modules/tinyexec": {
+      "version": "1.0.2",
+      "resolved": "https://registry.npmjs.org/tinyexec/-/tinyexec-1.0.2.tgz",
+      "integrity": "sha512-W/KYk+NFhkmsYpuHq5JykngiOCnxeVL8v8dFnqxSD8qEEdRfXk1SDM6JzNqcERbcGYj9tMrDQBYV9cjgnunFIg==",
+      "dev": true,
+      "license": "MIT",
+      "engines": {
+        "node": ">=18"
+      }
+    },
     "node_modules/tinyglobby": {
       "version": "0.2.15",
       "resolved": "https://registry.npmjs.org/tinyglobby/-/tinyglobby-0.2.15.tgz",
@@ -11100,9 +11083,9 @@
       "license": "ISC"
     },
     "node_modules/wreq-js": {
-      "version": "2.0.1",
-      "resolved": "https://registry.npmjs.org/wreq-js/-/wreq-js-2.0.1.tgz",
-      "integrity": "sha512-7GcZpzVtRX/A5pqu2QXTcqKTiYJZZRIRiosJ94GT1+taQivysZmjvkwzk8IvLz1oE1P1rGWG8ujDLCYxusM1aQ==",
+      "version": "2.1.1",
+      "resolved": "https://registry.npmjs.org/wreq-js/-/wreq-js-2.1.1.tgz",
+      "integrity": "sha512-nJBOMBTczqcyHpF8a8YdPyxb30htK2RxuAfr6O8a6oyKHj2nRPjXbZcGXrquIdZx1b+6NV/GHweD3OqWwE7n4A==",
       "cpu": [
         "x64",
         "arm64"

package.json

@@ -1,6 +1,6 @@
 {
   "name": "omniroute",
-  "version": "1.6.8",
+  "version": "1.7.12",
   "description": "Smart AI Router with auto fallback — route to FREE & cheap models, zero downtime. Works with Cursor, Cline, Claude Desktop, Codex, and any OpenAI-compatible tool.",
   "type": "module",
   "bin": {

src/app/(dashboard)/dashboard/cli-tools/CLIToolsPageClient.tsx

@@ -33,7 +33,6 @@ export default function CLIToolsPageClient({ machineId }) {
   const [apiKeys, setApiKeys] = useState([]);
   const [toolStatuses, setToolStatuses] = useState({});
   const [statusesLoaded, setStatusesLoaded] = useState(false);
-  const [apiBaseUrl, setApiBaseUrl] = useState("");
 
   useEffect(() => {
     fetchConnections();
@@ -48,12 +47,6 @@ export default function CLIToolsPageClient({ machineId }) {
       if (res.ok) {
         const data = await res.json();
         setCloudEnabled(data.cloudEnabled || false);
-        if (typeof window !== "undefined") {
-          const protocol = window.location.protocol;
-          const hostname = window.location.hostname;
-          const apiPort = data?.apiPort || 20128;
-          setApiBaseUrl(`${protocol}//${hostname}:${apiPort}`);
-        }
       }
     } catch (error) {
       console.log("Error loading cloud settings:", error);
@@ -155,9 +148,8 @@ export default function CLIToolsPageClient({ machineId }) {
     if (cloudEnabled && CLOUD_URL) {
       return CLOUD_URL;
     }
-    if (apiBaseUrl) {
-      return apiBaseUrl;
-    }
+    // Use window.location.origin directly — works correctly in Docker/reverse-proxy
+    // Per @alpgul feedback: don't use baseUrl prop (has port duplication issues)
     if (typeof window !== "undefined") {
       return window.location.origin;
     }

src/app/(dashboard)/dashboard/cli-tools/components/CopilotToolCard.tsx

@@ -60,7 +60,7 @@ export default function CopilotToolCard({
       .then((data) => {
         if (cancelled) return;
         const modelList = (data.data || [])
-          .filter((m: any) => m.id) // Only models with valid IDs
+          .filter((m: any) => m && !m.type && !m.parent && m.id) // Only chat models with valid IDs
           .map((m: any) => ({
             value: m.id,
             label: m.id,
@@ -112,11 +112,8 @@ export default function CopilotToolCard({
   };
 
   const getBaseUrlForConfig = () => {
-    // Use window.location.origin directly — works correctly in Docker/reverse-proxy
-    // Per @alpgul feedback: don't use baseUrl prop (has port duplication issues)
-    const origin =
-      typeof window !== "undefined" ? window.location.origin : "http://localhost:20128";
-    return `${origin}/v1/chat/completions`;
+    const url = baseUrl;
+    return `${url}/v1/chat/completions`;
   };
 
   // Generate the Copilot chatLanguageModels.json config

src/app/(dashboard)/dashboard/endpoint/EndpointPageClient.tsx

@@ -7,7 +7,7 @@ import { useCopyToClipboard } from "@/shared/hooks/useCopyToClipboard";
 import { AI_PROVIDERS, getProviderByAlias } from "@/shared/constants/providers";
 import { useTranslations } from "next-intl";
 
-const CLOUD_URL = process.env.NEXT_PUBLIC_CLOUD_URL;
+const CLOUD_URL = process.env.NEXT_PUBLIC_CLOUD_URL || null;
 const CLOUD_ACTION_TIMEOUT_MS = 15000;
 
 export default function APIPageClient({ machineId }) {
@@ -29,6 +29,7 @@ export default function APIPageClient({ machineId }) {
   const [syncStep, setSyncStep] = useState(""); // "syncing" | "verifying" | "disabling" | "done" | ""
   const [modalSuccess, setModalSuccess] = useState(false); // show success state in modal before closing
   const [selectedProvider, setSelectedProvider] = useState(null); // for provider models popup
+  const [cloudBaseUrl, setCloudBaseUrl] = useState(CLOUD_URL); // dynamic cloud URL from API response
 
   const { copied, copy } = useCopyToClipboard();
 
@@ -204,6 +205,10 @@ export default function APIPageClient({ machineId }) {
         if (data.createdKey) {
           await fetchData();
         }
+        // Update cloud URL from API response (fixes undefined/v1 when env var not set)
+        if (data.cloudUrl) {
+          setCloudBaseUrl(data.cloudUrl);
+        }
         // Reload settings to ensure fresh state
         await loadCloudSettings();
       } else {
@@ -274,7 +279,7 @@ export default function APIPageClient({ machineId }) {
   };
 
   const [baseUrl, setBaseUrl] = useState("/v1");
-  const cloudEndpointNew = `${CLOUD_URL}/v1`;
+  const cloudEndpointNew = cloudBaseUrl ? `${cloudBaseUrl}/v1` : null;
 
   // Hydration fix: Only access window on client side
   useEffect(() => {
@@ -293,7 +298,7 @@ export default function APIPageClient({ machineId }) {
   }
 
   // Use new format endpoint (machineId embedded in key)
-  const currentEndpoint = cloudEnabled ? cloudEndpointNew : baseUrl;
+  const currentEndpoint = cloudEnabled && cloudEndpointNew ? cloudEndpointNew : baseUrl;
 
   return (
     <div className="flex flex-col gap-8">
@@ -382,7 +387,7 @@ export default function APIPageClient({ machineId }) {
         </div>
       </Card>
 
-      {/* Available Endpoints */}
+        {/* Available Endpoints */}
       <Card>
         <div className="flex items-center justify-between mb-4">
           <div>
@@ -398,134 +403,200 @@ export default function APIPageClient({ machineId }) {
                   endpointData.audioTranscription,
                   endpointData.audioSpeech,
                   endpointData.moderation,
-                ].filter((a) => a.length > 0).length,
+                ].filter((a) => a.length > 0).length + 2,
               })}
             </p>
           </div>
         </div>
 
-        <div className="flex flex-col gap-3">
-          {/* Chat Completions */}
-          <EndpointSection
-            icon="chat"
-            iconColor="text-blue-500"
-            iconBg="bg-blue-500/10"
-            title={t("chatCompletions")}
-            path="/v1/chat/completions"
-            description={t("chatDesc")}
-            models={endpointData.chat}
-            expanded={expandedEndpoint === "chat"}
-            onToggle={() => setExpandedEndpoint(expandedEndpoint === "chat" ? null : "chat")}
-            copy={copy}
-            copied={copied}
-            baseUrl={currentEndpoint}
-          />
+        {/* Core APIs */}
+        <div className="mb-6">
+          <div className="flex items-center gap-2 mb-3">
+            <span className="material-symbols-outlined text-sm text-primary">hub</span>
+            <h3 className="text-xs font-semibold text-text-muted uppercase tracking-wider">
+              {t("categoryCore") || "Core APIs"}
+            </h3>
+            <div className="flex-1 h-px bg-border/50" />
+          </div>
+          <div className="flex flex-col gap-3">
+            {/* Chat Completions */}
+            <EndpointSection
+              icon="chat"
+              iconColor="text-blue-500"
+              iconBg="bg-blue-500/10"
+              title={t("chatCompletions")}
+              path="/v1/chat/completions"
+              description={t("chatDesc")}
+              models={endpointData.chat}
+              expanded={expandedEndpoint === "chat"}
+              onToggle={() => setExpandedEndpoint(expandedEndpoint === "chat" ? null : "chat")}
+              copy={copy}
+              copied={copied}
+              baseUrl={currentEndpoint}
+            />
 
-          {/* Embeddings */}
-          <EndpointSection
-            icon="data_array"
-            iconColor="text-emerald-500"
-            iconBg="bg-emerald-500/10"
-            title={t("embeddings")}
-            path="/v1/embeddings"
-            description={t("embeddingsDesc")}
-            models={endpointData.embeddings}
-            expanded={expandedEndpoint === "embeddings"}
-            onToggle={() =>
-              setExpandedEndpoint(expandedEndpoint === "embeddings" ? null : "embeddings")
-            }
-            copy={copy}
-            copied={copied}
-            baseUrl={currentEndpoint}
-          />
+            {/* Responses API */}
+            <EndpointSection
+              icon="code"
+              iconColor="text-indigo-500"
+              iconBg="bg-indigo-500/10"
+              title={t("responses") || "Responses API"}
+              path="/v1/responses"
+              description={t("responsesDesc") || "OpenAI Responses API for Codex and advanced agentic workflows"}
+              models={endpointData.chat}
+              expanded={expandedEndpoint === "responses"}
+              onToggle={() => setExpandedEndpoint(expandedEndpoint === "responses" ? null : "responses")}
+              copy={copy}
+              copied={copied}
+              baseUrl={currentEndpoint}
+            />
+          </div>
+        </div>
 
-          {/* Image Generation */}
-          <EndpointSection
-            icon="image"
-            iconColor="text-purple-500"
-            iconBg="bg-purple-500/10"
-            title={t("imageGeneration")}
-            path="/v1/images/generations"
-            description={t("imageDesc")}
-            models={endpointData.images}
-            expanded={expandedEndpoint === "images"}
-            onToggle={() => setExpandedEndpoint(expandedEndpoint === "images" ? null : "images")}
-            copy={copy}
-            copied={copied}
-            baseUrl={currentEndpoint}
-          />
+        {/* Media & Multi-Modal */}
+        <div className="mb-6">
+          <div className="flex items-center gap-2 mb-3">
+            <span className="material-symbols-outlined text-sm text-purple-400">perm_media</span>
+            <h3 className="text-xs font-semibold text-text-muted uppercase tracking-wider">
+              {t("categoryMedia") || "Media & Multi-Modal"}
+            </h3>
+            <div className="flex-1 h-px bg-border/50" />
+          </div>
+          <div className="flex flex-col gap-3">
+            {/* Embeddings */}
+            <EndpointSection
+              icon="data_array"
+              iconColor="text-emerald-500"
+              iconBg="bg-emerald-500/10"
+              title={t("embeddings")}
+              path="/v1/embeddings"
+              description={t("embeddingsDesc")}
+              models={endpointData.embeddings}
+              expanded={expandedEndpoint === "embeddings"}
+              onToggle={() =>
+                setExpandedEndpoint(expandedEndpoint === "embeddings" ? null : "embeddings")
+              }
+              copy={copy}
+              copied={copied}
+              baseUrl={currentEndpoint}
+            />
 
-          {/* Rerank */}
-          <EndpointSection
-            icon="sort"
-            iconColor="text-amber-500"
-            iconBg="bg-amber-500/10"
-            title={t("rerank")}
-            path="/v1/rerank"
-            description={t("rerankDesc")}
-            models={endpointData.rerank}
-            expanded={expandedEndpoint === "rerank"}
-            onToggle={() => setExpandedEndpoint(expandedEndpoint === "rerank" ? null : "rerank")}
-            copy={copy}
-            copied={copied}
-            baseUrl={currentEndpoint}
-          />
+            {/* Image Generation */}
+            <EndpointSection
+              icon="image"
+              iconColor="text-purple-500"
+              iconBg="bg-purple-500/10"
+              title={t("imageGeneration")}
+              path="/v1/images/generations"
+              description={t("imageDesc")}
+              models={endpointData.images}
+              expanded={expandedEndpoint === "images"}
+              onToggle={() => setExpandedEndpoint(expandedEndpoint === "images" ? null : "images")}
+              copy={copy}
+              copied={copied}
+              baseUrl={currentEndpoint}
+            />
 
-          {/* Audio Transcription */}
-          <EndpointSection
-            icon="mic"
-            iconColor="text-rose-500"
-            iconBg="bg-rose-500/10"
-            title={t("audioTranscription")}
-            path="/v1/audio/transcriptions"
-            description={t("audioTranscriptionDesc")}
-            models={endpointData.audioTranscription}
-            expanded={expandedEndpoint === "audioTranscription"}
-            onToggle={() =>
-              setExpandedEndpoint(
-                expandedEndpoint === "audioTranscription" ? null : "audioTranscription"
-              )
-            }
-            copy={copy}
-            copied={copied}
-            baseUrl={currentEndpoint}
-          />
+            {/* Audio Transcription */}
+            <EndpointSection
+              icon="mic"
+              iconColor="text-rose-500"
+              iconBg="bg-rose-500/10"
+              title={t("audioTranscription")}
+              path="/v1/audio/transcriptions"
+              description={t("audioTranscriptionDesc")}
+              models={endpointData.audioTranscription}
+              expanded={expandedEndpoint === "audioTranscription"}
+              onToggle={() =>
+                setExpandedEndpoint(
+                  expandedEndpoint === "audioTranscription" ? null : "audioTranscription"
+                )
+              }
+              copy={copy}
+              copied={copied}
+              baseUrl={currentEndpoint}
+            />
 
-          {/* Audio Speech (TTS) */}
-          <EndpointSection
-            icon="record_voice_over"
-            iconColor="text-cyan-500"
-            iconBg="bg-cyan-500/10"
-            title={t("textToSpeech")}
-            path="/v1/audio/speech"
-            description={t("textToSpeechDesc")}
-            models={endpointData.audioSpeech}
-            expanded={expandedEndpoint === "audioSpeech"}
-            onToggle={() =>
-              setExpandedEndpoint(expandedEndpoint === "audioSpeech" ? null : "audioSpeech")
-            }
-            copy={copy}
-            copied={copied}
-            baseUrl={currentEndpoint}
-          />
+            {/* Audio Speech (TTS) */}
+            <EndpointSection
+              icon="record_voice_over"
+              iconColor="text-cyan-500"
+              iconBg="bg-cyan-500/10"
+              title={t("textToSpeech")}
+              path="/v1/audio/speech"
+              description={t("textToSpeechDesc")}
+              models={endpointData.audioSpeech}
+              expanded={expandedEndpoint === "audioSpeech"}
+              onToggle={() =>
+                setExpandedEndpoint(expandedEndpoint === "audioSpeech" ? null : "audioSpeech")
+              }
+              copy={copy}
+              copied={copied}
+              baseUrl={currentEndpoint}
+            />
+          </div>
+        </div>
 
-          {/* Moderations */}
-          <EndpointSection
-            icon="shield"
-            iconColor="text-orange-500"
-            iconBg="bg-orange-500/10"
-            title={t("moderations")}
-            path="/v1/moderations"
-            description={t("moderationsDesc")}
-            models={endpointData.moderation}
-            expanded={expandedEndpoint === "moderation"}
-            onToggle={() =>
-              setExpandedEndpoint(expandedEndpoint === "moderation" ? null : "moderation")
-            }
-            copy={copy}
-            copied={copied}
-            baseUrl={currentEndpoint}
-          />
+        {/* Utility & Management */}
+        <div>
+          <div className="flex items-center gap-2 mb-3">
+            <span className="material-symbols-outlined text-sm text-amber-400">build</span>
+            <h3 className="text-xs font-semibold text-text-muted uppercase tracking-wider">
+              {t("categoryUtility") || "Utility & Management"}
+            </h3>
+            <div className="flex-1 h-px bg-border/50" />
+          </div>
+          <div className="flex flex-col gap-3">
+            {/* Rerank */}
+            <EndpointSection
+              icon="sort"
+              iconColor="text-amber-500"
+              iconBg="bg-amber-500/10"
+              title={t("rerank")}
+              path="/v1/rerank"
+              description={t("rerankDesc")}
+              models={endpointData.rerank}
+              expanded={expandedEndpoint === "rerank"}
+              onToggle={() => setExpandedEndpoint(expandedEndpoint === "rerank" ? null : "rerank")}
+              copy={copy}
+              copied={copied}
+              baseUrl={currentEndpoint}
+            />
+
+            {/* Moderations */}
+            <EndpointSection
+              icon="shield"
+              iconColor="text-orange-500"
+              iconBg="bg-orange-500/10"
+              title={t("moderations")}
+              path="/v1/moderations"
+              description={t("moderationsDesc")}
+              models={endpointData.moderation}
+              expanded={expandedEndpoint === "moderation"}
+              onToggle={() =>
+                setExpandedEndpoint(expandedEndpoint === "moderation" ? null : "moderation")
+              }
+              copy={copy}
+              copied={copied}
+              baseUrl={currentEndpoint}
+            />
+
+            {/* List Models */}
+            <EndpointSection
+              icon="list"
+              iconColor="text-teal-500"
+              iconBg="bg-teal-500/10"
+              title={t("listModels") || "List Models"}
+              path="/v1/models"
+              description={t("listModelsDesc") || "List all available models across all connected providers"}
+              models={[]}
+              expanded={expandedEndpoint === "models"}
+              onToggle={() => setExpandedEndpoint(expandedEndpoint === "models" ? null : "models")}
+              copy={copy}
+              copied={copied}
+              baseUrl={currentEndpoint}
+            />
+          </div>
         </div>
       </Card>
 

src/app/(dashboard)/dashboard/media/MediaPageClient.tsx

@@ -0,0 +1,261 @@
+"use client";
+
+import { useState } from "react";
+import { useTranslations } from "next-intl";
+
+type Modality = "image" | "video" | "music";
+type GenerationResult = {
+  type: Modality;
+  data: any;
+  timestamp: number;
+};
+
+const MODALITY_CONFIG: Record<
+  Modality,
+  { icon: string; endpoint: string; label: string; placeholder: string; color: string }
+> = {
+  image: {
+    icon: "image",
+    endpoint: "/api/v1/images/generations",
+    label: "Image Generation",
+    placeholder: "A serene landscape with mountains at sunset...",
+    color: "from-purple-500 to-pink-500",
+  },
+  video: {
+    icon: "videocam",
+    endpoint: "/api/v1/videos/generations",
+    label: "Video Generation",
+    placeholder: "A timelapse of a flower blooming...",
+    color: "from-blue-500 to-cyan-500",
+  },
+  music: {
+    icon: "music_note",
+    endpoint: "/api/v1/music/generations",
+    label: "Music Generation",
+    placeholder: "Upbeat electronic music with synth pads...",
+    color: "from-orange-500 to-yellow-500",
+  },
+};
+
+export default function MediaPageClient() {
+  const t = useTranslations("media");
+  const [activeTab, setActiveTab] = useState<Modality>("image");
+  const [prompt, setPrompt] = useState("");
+  const [model, setModel] = useState("");
+  const [models, setModels] = useState<any[]>([]);
+  const [loading, setLoading] = useState(false);
+  const [loadingModels, setLoadingModels] = useState(false);
+  const [result, setResult] = useState<GenerationResult | null>(null);
+  const [error, setError] = useState<string | null>(null);
+
+  // Fetch available models for each modality
+  const fetchModels = async (modality: Modality) => {
+    setLoadingModels(true);
+    try {
+      const res = await fetch(MODALITY_CONFIG[modality].endpoint);
+      if (res.ok) {
+        const data = await res.json();
+        const modelList = data.data || [];
+        setModels(modelList);
+        if (modelList.length > 0) setModel(modelList[0].id);
+      }
+    } catch {
+      setModels([]);
+    }
+    setLoadingModels(false);
+  };
+
+  const switchTab = (tab: Modality) => {
+    setActiveTab(tab);
+    setPrompt("");
+    setResult(null);
+    setError(null);
+    fetchModels(tab);
+  };
+
+  const handleGenerate = async () => {
+    if (!prompt.trim()) return;
+    setLoading(true);
+    setError(null);
+    setResult(null);
+
+    try {
+      const config = MODALITY_CONFIG[activeTab];
+      const res = await fetch(config.endpoint, {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({
+          model: model || undefined,
+          prompt: prompt.trim(),
+          ...(activeTab === "image" ? { size: "1024x1024", n: 1 } : {}),
+        }),
+      });
+
+      if (!res.ok) {
+        const errData = await res.json().catch(() => ({}));
+        throw new Error(errData?.error?.message || `Generation failed (${res.status})`);
+      }
+
+      const data = await res.json();
+      setResult({ type: activeTab, data, timestamp: Date.now() });
+    } catch (err: any) {
+      setError(err.message || "Generation failed");
+    }
+    setLoading(false);
+  };
+
+  // Load models on first render
+  useState(() => {
+    fetchModels("image");
+  });
+
+  const config = MODALITY_CONFIG[activeTab];
+
+  return (
+    <div className="space-y-6">
+      {/* Header */}
+      <div>
+        <h1 className="text-2xl font-bold text-text-main">{t("title")}</h1>
+        <p className="text-text-muted text-sm mt-1">{t("subtitle")}</p>
+      </div>
+
+      {/* Modality Tabs */}
+      <div className="flex gap-2 p-1 bg-surface/50 rounded-xl border border-black/5 dark:border-white/5">
+        {(Object.keys(MODALITY_CONFIG) as Modality[]).map((key) => {
+          const cfg = MODALITY_CONFIG[key];
+          const isActive = key === activeTab;
+          return (
+            <button
+              key={key}
+              onClick={() => switchTab(key)}
+              className={`flex-1 flex items-center justify-center gap-2 px-4 py-2.5 rounded-lg text-sm font-medium transition-all ${
+                isActive
+                  ? "bg-primary/10 text-primary shadow-sm border border-primary/20"
+                  : "text-text-muted hover:text-text-main hover:bg-surface/80"
+              }`}
+            >
+              <span className="material-symbols-outlined text-[18px]">{cfg.icon}</span>
+              {cfg.label}
+            </button>
+          );
+        })}
+      </div>
+
+      {/* Generation Form */}
+      <div className="bg-surface/30 rounded-xl border border-black/5 dark:border-white/5 p-6 space-y-4">
+        {/* Model selector */}
+        <div>
+          <label className="block text-sm font-medium text-text-main mb-2">{t("model")}</label>
+          {loadingModels ? (
+            <div className="flex items-center gap-2 text-text-muted text-sm">
+              <span className="material-symbols-outlined animate-spin text-[16px]">progress_activity</span>
+              {t("loadingModels")}
+            </div>
+          ) : models.length > 0 ? (
+            <select
+              value={model}
+              onChange={(e) => setModel(e.target.value)}
+              className="w-full px-3 py-2 rounded-lg bg-surface border border-black/10 dark:border-white/10 text-text-main text-sm focus:outline-none focus:ring-2 focus:ring-primary/30"
+            >
+              {models.map((m) => (
+                <option key={m.id} value={m.id}>
+                  {m.id}
+                </option>
+              ))}
+            </select>
+          ) : (
+            <p className="text-text-muted text-sm">{t("noModels")}</p>
+          )}
+        </div>
+
+        {/* Prompt */}
+        <div>
+          <label className="block text-sm font-medium text-text-main mb-2">{t("prompt")}</label>
+          <textarea
+            rows={3}
+            value={prompt}
+            onChange={(e) => setPrompt(e.target.value)}
+            placeholder={config.placeholder}
+            className="w-full px-3 py-2 rounded-lg bg-surface border border-black/10 dark:border-white/10 text-text-main text-sm placeholder:text-text-muted/50 focus:outline-none focus:ring-2 focus:ring-primary/30 resize-none"
+          />
+        </div>
+
+        {/* Generate button */}
+        <button
+          onClick={handleGenerate}
+          disabled={loading || !prompt.trim()}
+          className={`w-full flex items-center justify-center gap-2 px-4 py-3 rounded-lg text-white font-medium transition-all bg-gradient-to-r ${config.color} ${
+            loading || !prompt.trim() ? "opacity-50 cursor-not-allowed" : "hover:opacity-90 hover:shadow-lg"
+          }`}
+        >
+          {loading ? (
+            <>
+              <span className="material-symbols-outlined animate-spin text-[18px]">progress_activity</span>
+              {t("generating")}
+            </>
+          ) : (
+            <>
+              <span className="material-symbols-outlined text-[18px]">auto_awesome</span>
+              {t("generate")} {config.label}
+            </>
+          )}
+        </button>
+      </div>
+
+      {/* Error */}
+      {error && (
+        <div className="bg-red-500/10 border border-red-500/20 rounded-xl p-4 flex items-start gap-3">
+          <span className="material-symbols-outlined text-red-500 text-[20px] mt-0.5">error</span>
+          <div>
+            <p className="text-sm font-medium text-red-500">{t("error")}</p>
+            <p className="text-sm text-text-muted mt-1">{error}</p>
+          </div>
+        </div>
+      )}
+
+      {/* Result */}
+      {result && (
+        <div className="bg-surface/30 rounded-xl border border-black/5 dark:border-white/5 p-6">
+          <div className="flex items-center gap-2 mb-4">
+            <span className={`material-symbols-outlined text-[20px] bg-gradient-to-r ${config.color} bg-clip-text text-transparent`}>
+              {config.icon}
+            </span>
+            <h3 className="text-sm font-medium text-text-main">{t("result")}</h3>
+            <span className="text-xs text-text-muted ml-auto">
+              {new Date(result.timestamp).toLocaleTimeString()}
+            </span>
+          </div>
+          <pre className="bg-surface rounded-lg p-4 text-xs text-text-muted overflow-auto max-h-96 custom-scrollbar">
+            {JSON.stringify(result.data, null, 2)}
+          </pre>
+        </div>
+      )}
+
+      {/* Info cards */}
+      <div className="grid grid-cols-1 md:grid-cols-3 gap-4">
+        {(Object.keys(MODALITY_CONFIG) as Modality[]).map((key) => {
+          const cfg = MODALITY_CONFIG[key];
+          return (
+            <div
+              key={key}
+              className="bg-surface/30 rounded-xl border border-black/5 dark:border-white/5 p-4"
+            >
+              <div className="flex items-center gap-2 mb-2">
+                <div className={`flex items-center justify-center size-8 rounded-lg bg-gradient-to-r ${cfg.color}`}>
+                  <span className="material-symbols-outlined text-white text-[16px]">{cfg.icon}</span>
+                </div>
+                <span className="text-sm font-medium text-text-main">{cfg.label}</span>
+              </div>
+              <p className="text-xs text-text-muted">
+                {t(`${key}Description`)}
+              </p>
+              <code className="block mt-2 text-xs text-primary/70 bg-primary/5 rounded px-2 py-1">
+                POST {cfg.endpoint}
+              </code>
+            </div>
+          );
+        })}
+      </div>
+    </div>
+  );
+}

src/app/(dashboard)/dashboard/media/page.tsx

@@ -0,0 +1,5 @@
+import MediaPageClient from "./MediaPageClient";
+
+export default function MediaPage() {
+  return <MediaPageClient />;
+}

src/app/(dashboard)/dashboard/settings/components/AppearanceTab.tsx

@@ -1,16 +1,30 @@
 "use client";
 
 import { useState, useEffect } from "react";
-import { Card, Toggle } from "@/shared/components";
+import { Button, Card, Toggle } from "@/shared/components";
 import { useTheme } from "@/shared/hooks/useTheme";
+import useThemeStore, { COLOR_THEMES } from "@/store/themeStore";
 import { cn } from "@/shared/utils/cn";
 import { useTranslations } from "next-intl";
 
 export default function AppearanceTab() {
   const { theme, setTheme, isDark } = useTheme();
+  const { colorTheme, customColor, setColorTheme, setCustomColorTheme } = useThemeStore();
   const t = useTranslations("settings");
   const [settings, setSettings] = useState<Record<string, any>>({});
   const [loading, setLoading] = useState(true);
+  const [customThemeColor, setCustomThemeColor] = useState(customColor || "#3b82f6");
+  const isValidHex = /^#([0-9a-fA-F]{6})$/.test(customThemeColor.startsWith("#") ? customThemeColor : `#${customThemeColor}`);
+
+  // Subscribe to store changes (e.g. from another tab) via Zustand external subscription
+  useEffect(() => {
+    const unsubscribe = useThemeStore.subscribe((state) => {
+      if (state.customColor && state.customColor !== customThemeColor) {
+        setCustomThemeColor(state.customColor);
+      }
+    });
+    return unsubscribe;
+  }, []); // eslint-disable-line react-hooks/exhaustive-deps
   const themeOptionLabels: Record<string, string> = {
     light: t("themeLight"),
     dark: t("themeDark"),
@@ -47,6 +61,16 @@ export default function AppearanceTab() {
     }
   };
 
+  const presetThemes = [
+    { id: "coral", color: COLOR_THEMES.coral, label: t("themeCoral") },
+    { id: "blue", color: COLOR_THEMES.blue, label: t("themeBlue") },
+    { id: "red", color: COLOR_THEMES.red, label: t("themeRed") },
+    { id: "green", color: COLOR_THEMES.green, label: t("themeGreen") },
+    { id: "violet", color: COLOR_THEMES.violet, label: t("themeViolet") },
+    { id: "orange", color: COLOR_THEMES.orange, label: t("themeOrange") },
+    { id: "cyan", color: COLOR_THEMES.cyan, label: t("themeCyan") },
+  ];
+
   return (
     <Card>
       <div className="flex items-center gap-3 mb-4">
@@ -94,6 +118,56 @@ export default function AppearanceTab() {
           </div>
         </div>
 
+        <div className="pt-4 border-t border-border">
+          <p className="font-medium mb-1">{t("themeAccent")}</p>
+          <p className="text-sm text-text-muted mb-3">{t("themeAccentDesc")}</p>
+
+          <div className="grid grid-cols-1 sm:grid-cols-2 gap-2 mb-3">
+            {presetThemes.map((item) => {
+              const active = colorTheme === item.id;
+              return (
+                <button
+                  key={item.id}
+                  onClick={() => setColorTheme(item.id)}
+                  className={cn(
+                    "flex items-center justify-between gap-2 p-2 rounded-lg border transition-colors",
+                    active
+                      ? "border-primary bg-primary/10 text-primary"
+                      : "border-border hover:bg-surface/50 text-text-main"
+                  )}
+                >
+                  <span className="flex items-center gap-2">
+                    <span
+                      className="size-4 rounded-full border border-black/10 dark:border-white/20"
+                      style={{ backgroundColor: item.color }}
+                    />
+                    <span className="text-sm font-medium">{item.label}</span>
+                  </span>
+                </button>
+              );
+            })}
+          </div>
+
+          <div className="flex items-center gap-2">
+            <input
+              type="color"
+              value={customThemeColor}
+              onChange={(e) => setCustomThemeColor(e.target.value)}
+              className="h-10 w-12 rounded border border-border bg-surface cursor-pointer"
+              aria-label={t("themeCustom")}
+            />
+            <input
+              type="text"
+              value={customThemeColor}
+              onChange={(e) => setCustomThemeColor(e.target.value)}
+              placeholder="#3b82f6"
+              maxLength={7}
+              className={`flex-1 h-10 px-3 rounded-lg bg-surface border text-sm text-text-main focus:outline-none ${isValidHex ? "border-border focus:border-primary" : "border-red-400 focus:border-red-500"}`}
+            />
+            <Button onClick={() => setCustomColorTheme(customThemeColor)} disabled={!isValidHex}>{t("themeCreate")}</Button>
+          </div>
+        </div>
+
         <div className="pt-4 border-t border-border">
           <div className="flex items-center justify-between">
             <div>

src/app/(dashboard)/dashboard/settings/components/BackgroundDegradationTab.tsx

@@ -0,0 +1,261 @@
+"use client";
+
+import { useState, useEffect } from "react";
+import { Card } from "@/shared/components";
+import { useTranslations } from "next-intl";
+
+export default function BackgroundDegradationTab() {
+  const [config, setConfig] = useState({
+    enabled: false,
+    degradationMap: {},
+    detectionPatterns: [],
+    stats: { detected: 0, tokensSaved: 0 },
+  });
+  const [loading, setLoading] = useState(true);
+  const [saving, setSaving] = useState(false);
+  const [status, setStatus] = useState("");
+  const [newFrom, setNewFrom] = useState("");
+  const [newTo, setNewTo] = useState("");
+  const [newPattern, setNewPattern] = useState("");
+  const t = useTranslations("settings");
+
+  useEffect(() => {
+    fetch("/api/settings/background-degradation")
+      .then((res) => res.json())
+      .then((data) => {
+        setConfig(data);
+        setLoading(false);
+      })
+      .catch(() => setLoading(false));
+  }, []);
+
+  const save = async (updates) => {
+    const newConfig = { ...config, ...updates };
+    setConfig(newConfig);
+    setSaving(true);
+    setStatus("");
+    try {
+      const { stats, ...persistable } = newConfig;
+      const res = await fetch("/api/settings/background-degradation", {
+        method: "PUT",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify(persistable),
+      });
+      if (res.ok) {
+        const data = await res.json();
+        setConfig(data);
+        setStatus("saved");
+        setTimeout(() => setStatus(""), 2000);
+      } else {
+        setStatus("error");
+      }
+    } catch {
+      setStatus("error");
+    } finally {
+      setSaving(false);
+    }
+  };
+
+  const addMapping = () => {
+    if (!newFrom.trim() || !newTo.trim()) return;
+    const map = { ...config.degradationMap, [newFrom.trim()]: newTo.trim() };
+    save({ degradationMap: map });
+    setNewFrom("");
+    setNewTo("");
+  };
+
+  const removeMapping = (key) => {
+    const map = { ...config.degradationMap };
+    delete map[key];
+    save({ degradationMap: map });
+  };
+
+  const addPattern = () => {
+    if (!newPattern.trim()) return;
+    const patterns = [...config.detectionPatterns, newPattern.trim()];
+    save({ detectionPatterns: patterns });
+    setNewPattern("");
+  };
+
+  const removePattern = (idx) => {
+    const patterns = config.detectionPatterns.filter((_, i) => i !== idx);
+    save({ detectionPatterns: patterns });
+  };
+
+  const mapEntries = Object.entries(config.degradationMap || {}) as [string, string][];
+
+  return (
+    <Card>
+      <div className="flex items-center gap-3 mb-5">
+        <div className="p-2 rounded-lg bg-sky-500/10 text-sky-500">
+          <span className="material-symbols-outlined text-[20px]" aria-hidden="true">
+            speed
+          </span>
+        </div>
+        <div className="flex-1">
+          <h3 className="text-lg font-semibold">
+            {t("backgroundDegradationTitle") || "Background Task Degradation"}
+          </h3>
+          <p className="text-sm text-text-muted">
+            {t("backgroundDegradationDesc") ||
+              "Auto-redirect background requests (titles, summaries) to cheaper models"}
+          </p>
+        </div>
+        {status === "saved" && (
+          <span className="text-xs font-medium text-emerald-500 flex items-center gap-1">
+            <span className="material-symbols-outlined text-[14px]">check_circle</span>{" "}
+            {t("saved") || "Saved"}
+          </span>
+        )}
+      </div>
+
+      {/* Toggle */}
+      <div className="flex items-center justify-between p-4 rounded-lg bg-surface/30 border border-border/30 mb-4">
+        <div>
+          <p className="text-sm font-medium">
+            {t("enableDegradation") || "Enable Background Degradation"}
+          </p>
+          <p className="text-xs text-text-muted mt-0.5">
+            {t("enableDegradationHint") ||
+              "Automatically use cheaper models for background utility tasks"}
+          </p>
+        </div>
+        <button
+          onClick={() => save({ enabled: !config.enabled })}
+          disabled={loading || saving}
+          className={`relative inline-flex h-6 w-11 items-center rounded-full transition-colors ${
+            config.enabled ? "bg-sky-500" : "bg-white/10"
+          }`}
+        >
+          <span
+            className={`inline-block h-4 w-4 rounded-full bg-white transition-transform ${
+              config.enabled ? "translate-x-6" : "translate-x-1"
+            }`}
+          />
+        </button>
+      </div>
+
+      {/* Stats */}
+      {config.stats && config.stats.detected > 0 && (
+        <div className="flex items-center gap-4 p-3 rounded-lg bg-sky-500/5 border border-sky-500/20 mb-4">
+          <div className="flex items-center gap-2">
+            <span className="material-symbols-outlined text-[16px] text-sky-400">analytics</span>
+            <span className="text-xs text-text-muted">
+              {t("tasksDetected") || "Tasks detected"}:
+            </span>
+            <span className="text-sm font-mono font-semibold text-sky-400">
+              {config.stats.detected}
+            </span>
+          </div>
+        </div>
+      )}
+
+      {config.enabled && (
+        <>
+          {/* Degradation Map */}
+          <div className="mb-4">
+            <p className="text-xs font-medium text-text-muted uppercase tracking-wider mb-2">
+              {t("degradationMap") || "Model Degradation Map"}
+            </p>
+
+            {/* Add new mapping */}
+            <div className="flex items-center gap-2 mb-3">
+              <input
+                type="text"
+                placeholder={t("premiumModel") || "Premium model"}
+                value={newFrom}
+                onChange={(e) => setNewFrom(e.target.value)}
+                className="flex-1 px-3 py-2 rounded-lg text-sm bg-surface border border-border/50 focus:border-sky-500/50 focus:outline-none"
+              />
+              <span className="text-text-muted text-lg">→</span>
+              <input
+                type="text"
+                placeholder={t("cheapModel") || "Cheap model"}
+                value={newTo}
+                onChange={(e) => setNewTo(e.target.value)}
+                className="flex-1 px-3 py-2 rounded-lg text-sm bg-surface border border-border/50 focus:border-sky-500/50 focus:outline-none"
+              />
+              <button
+                onClick={addMapping}
+                disabled={saving || !newFrom.trim() || !newTo.trim()}
+                className="px-3 py-2 rounded-lg text-sm font-medium bg-sky-500/10 text-sky-500 hover:bg-sky-500/20 disabled:opacity-50 transition-all"
+              >
+                {t("add") || "Add"}
+              </button>
+            </div>
+
+            {/* Existing mappings */}
+            {mapEntries.length > 0 && (
+              <div className="rounded-lg border border-border/30 divide-y divide-border/20 max-h-48 overflow-y-auto">
+                {mapEntries.map(([from, to]) => (
+                  <div key={from} className="flex items-center gap-3 px-4 py-2">
+                    <code className="text-xs text-orange-400/80 flex-1 truncate">{from}</code>
+                    <span className="material-symbols-outlined text-[14px] text-text-muted">
+                      arrow_forward
+                    </span>
+                    <code className="text-xs text-sky-400/80 flex-1 truncate">{to}</code>
+                    <button
+                      onClick={() => removeMapping(from)}
+                      disabled={saving}
+                      className="p-1 rounded hover:bg-red-500/10 text-text-muted hover:text-red-400 transition-all"
+                    >
+                      <span className="material-symbols-outlined text-[16px]">close</span>
+                    </button>
+                  </div>
+                ))}
+              </div>
+            )}
+          </div>
+
+          {/* Detection Patterns */}
+          <details className="group">
+            <summary className="text-xs font-medium text-text-muted uppercase tracking-wider cursor-pointer flex items-center gap-1 mb-2">
+              <span className="material-symbols-outlined text-[14px] group-open:rotate-90 transition-transform">
+                chevron_right
+              </span>
+              {t("detectionPatterns") || "Detection Patterns"} (
+              {config.detectionPatterns?.length || 0})
+            </summary>
+
+            {/* Add new pattern */}
+            <div className="flex items-center gap-2 mb-3">
+              <input
+                type="text"
+                placeholder={t("newPattern") || 'e.g. "generate a title"'}
+                value={newPattern}
+                onChange={(e) => setNewPattern(e.target.value)}
+                className="flex-1 px-3 py-2 rounded-lg text-sm bg-surface border border-border/50 focus:border-sky-500/50 focus:outline-none"
+              />
+              <button
+                onClick={addPattern}
+                disabled={saving || !newPattern.trim()}
+                className="px-3 py-2 rounded-lg text-sm font-medium bg-sky-500/10 text-sky-500 hover:bg-sky-500/20 disabled:opacity-50 transition-all"
+              >
+                {t("add") || "Add"}
+              </button>
+            </div>
+
+            {/* Existing patterns */}
+            <div className="flex flex-wrap gap-2">
+              {(config.detectionPatterns || []).map((pattern, idx) => (
+                <span
+                  key={idx}
+                  className="inline-flex items-center gap-1 px-2.5 py-1 rounded-full text-xs bg-sky-500/10 text-sky-400 border border-sky-500/20"
+                >
+                  {pattern}
+                  <button
+                    onClick={() => removePattern(idx)}
+                    className="hover:text-red-400 transition-colors"
+                    disabled={saving}
+                  >
+                    <span className="material-symbols-outlined text-[12px]">close</span>
+                  </button>
+                </span>
+              ))}
+            </div>
+          </details>
+        </>
+      )}
+    </Card>
+  );
+}

src/app/(dashboard)/dashboard/settings/components/ModelAliasesTab.tsx

@@ -0,0 +1,179 @@
+"use client";
+
+import { useState, useEffect } from "react";
+import { Card } from "@/shared/components";
+import { useTranslations } from "next-intl";
+
+export default function ModelAliasesTab() {
+  const [builtIn, setBuiltIn] = useState({});
+  const [custom, setCustom] = useState({});
+  const [loading, setLoading] = useState(true);
+  const [saving, setSaving] = useState(false);
+  const [status, setStatus] = useState("");
+  const [newFrom, setNewFrom] = useState("");
+  const [newTo, setNewTo] = useState("");
+  const t = useTranslations("settings");
+
+  useEffect(() => {
+    fetch("/api/settings/model-aliases")
+      .then((res) => res.json())
+      .then((data) => {
+        setBuiltIn(data.builtIn || {});
+        setCustom(data.custom || {});
+        setLoading(false);
+      })
+      .catch(() => setLoading(false));
+  }, []);
+
+  const addAlias = async () => {
+    if (!newFrom.trim() || !newTo.trim()) return;
+    setSaving(true);
+    try {
+      const res = await fetch("/api/settings/model-aliases", {
+        method: "POST",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({ from: newFrom.trim(), to: newTo.trim() }),
+      });
+      if (res.ok) {
+        const data = await res.json();
+        setCustom(data.custom);
+        setNewFrom("");
+        setNewTo("");
+        setStatus("saved");
+        setTimeout(() => setStatus(""), 2000);
+      }
+    } catch {
+      setStatus("error");
+    } finally {
+      setSaving(false);
+    }
+  };
+
+  const removeAlias = async (from) => {
+    setSaving(true);
+    try {
+      const res = await fetch("/api/settings/model-aliases", {
+        method: "DELETE",
+        headers: { "Content-Type": "application/json" },
+        body: JSON.stringify({ from }),
+      });
+      if (res.ok) {
+        const data = await res.json();
+        setCustom(data.custom);
+        setStatus("saved");
+        setTimeout(() => setStatus(""), 2000);
+      }
+    } catch {
+      setStatus("error");
+    } finally {
+      setSaving(false);
+    }
+  };
+
+  const builtInEntries = Object.entries(builtIn);
+  const customEntries = Object.entries(custom);
+
+  return (
+    <Card>
+      <div className="flex items-center gap-3 mb-5">
+        <div className="p-2 rounded-lg bg-amber-500/10 text-amber-500">
+          <span className="material-symbols-outlined text-[20px]" aria-hidden="true">
+            swap_horiz
+          </span>
+        </div>
+        <div>
+          <h3 className="text-lg font-semibold">{t("modelAliasesTitle") || "Model Aliases"}</h3>
+          <p className="text-sm text-text-muted">
+            {t("modelAliasesDesc") || "Auto-forward deprecated model IDs to their replacements"}
+          </p>
+        </div>
+        {status === "saved" && (
+          <span className="ml-auto text-xs font-medium text-emerald-500 flex items-center gap-1">
+            <span className="material-symbols-outlined text-[14px]">check_circle</span>{" "}
+            {t("saved") || "Saved"}
+          </span>
+        )}
+      </div>
+
+      {/* Add custom alias */}
+      <div className="p-4 rounded-lg bg-surface/30 border border-border/30 mb-4">
+        <p className="text-sm font-medium mb-3">
+          {t("addCustomAlias") || "Add Custom Alias"}
+        </p>
+        <div className="flex items-center gap-2">
+          <input
+            type="text"
+            placeholder={t("deprecatedModelId") || "Deprecated model ID"}
+            value={newFrom}
+            onChange={(e) => setNewFrom(e.target.value)}
+            className="flex-1 px-3 py-2 rounded-lg text-sm bg-surface border border-border/50 focus:border-amber-500/50 focus:outline-none"
+          />
+          <span className="text-text-muted text-lg">→</span>
+          <input
+            type="text"
+            placeholder={t("newModelId") || "New model ID"}
+            value={newTo}
+            onChange={(e) => setNewTo(e.target.value)}
+            className="flex-1 px-3 py-2 rounded-lg text-sm bg-surface border border-border/50 focus:border-amber-500/50 focus:outline-none"
+          />
+          <button
+            onClick={addAlias}
+            disabled={saving || !newFrom.trim() || !newTo.trim()}
+            className="px-4 py-2 rounded-lg text-sm font-medium bg-amber-500/10 text-amber-500 hover:bg-amber-500/20 disabled:opacity-50 transition-all"
+          >
+            {t("add") || "Add"}
+          </button>
+        </div>
+      </div>
+
+      {/* Custom aliases */}
+      {customEntries.length > 0 && (
+        <div className="mb-4">
+          <p className="text-xs font-medium text-text-muted uppercase tracking-wider mb-2">
+            {t("customAliases") || "Custom Aliases"}
+          </p>
+          <div className="rounded-lg border border-border/30 divide-y divide-border/20">
+            {customEntries.map(([from, to]) => (
+              <div key={from} className="flex items-center gap-3 px-4 py-2.5">
+                <code className="text-xs text-red-400/80 flex-1 truncate">{from}</code>
+                <span className="material-symbols-outlined text-[14px] text-text-muted">
+                  arrow_forward
+                </span>
+                <code className="text-xs text-emerald-400/80 flex-1 truncate">{to}</code>
+                <button
+                  onClick={() => removeAlias(from)}
+                  disabled={saving}
+                  className="p-1 rounded hover:bg-red-500/10 text-text-muted hover:text-red-400 transition-all"
+                >
+                  <span className="material-symbols-outlined text-[16px]">close</span>
+                </button>
+              </div>
+            ))}
+          </div>
+        </div>
+      )}
+
+      {/* Built-in aliases (collapsed by default) */}
+      <details className="group">
+        <summary className="text-xs font-medium text-text-muted uppercase tracking-wider cursor-pointer flex items-center gap-1 mb-2">
+          <span className="material-symbols-outlined text-[14px] group-open:rotate-90 transition-transform">
+            chevron_right
+          </span>
+          {t("builtInAliases") || "Built-in Aliases"} ({builtInEntries.length})
+        </summary>
+        <div className="rounded-lg border border-border/30 divide-y divide-border/20 max-h-60 overflow-y-auto">
+          {builtInEntries.map(([from, to]) => (
+            <div key={from} className="flex items-center gap-3 px-4 py-2 opacity-60">
+              <code className="text-xs text-red-400/60 flex-1 truncate">{from}</code>
+              <span className="material-symbols-outlined text-[14px] text-text-muted">
+                arrow_forward
+              </span>
+              <code className="text-xs text-emerald-400/60 flex-1 truncate">{to}</code>
+              <span className="material-symbols-outlined text-[14px] text-text-muted">lock</span>
+            </div>
+          ))}
+        </div>
+      </details>
+    </Card>
+  );
+}

src/app/(dashboard)/dashboard/settings/page.tsx

@@ -13,6 +13,8 @@ import ProxyTab from "./components/ProxyTab";
 import AppearanceTab from "./components/AppearanceTab";
 import ThinkingBudgetTab from "./components/ThinkingBudgetTab";
 import SystemPromptTab from "./components/SystemPromptTab";
+import ModelAliasesTab from "./components/ModelAliasesTab";
+import BackgroundDegradationTab from "./components/BackgroundDegradationTab";
 
 import CacheStatsCard from "./components/CacheStatsCard";
 import ResilienceTab from "./components/ResilienceTab";
@@ -94,6 +96,8 @@ export default function SettingsPage() {
             <div className="flex flex-col gap-6">
               <RoutingTab />
               <ComboDefaultsTab />
+              <ModelAliasesTab />
+              <BackgroundDegradationTab />
             </div>
           )}
 

src/app/api/cli-tools/codex-profiles/route.ts

@@ -3,10 +3,10 @@
 import { NextResponse } from "next/server";
 import fs from "fs/promises";
 import path from "path";
-import os from "os";
 import { ensureCliConfigWriteAllowed, getCliConfigPaths } from "@/shared/services/cliRuntime";
+import { resolveDataDir } from "@/lib/dataPaths";
 
-const PROFILES_DIR = path.join(os.homedir(), ".omniroute", "codex-profiles");
+const PROFILES_DIR = path.join(resolveDataDir(), "codex-profiles");
 
 /**
  * Ensure profiles directory exists

src/app/api/oauth/[provider]/[action]/route.ts

@@ -6,7 +6,7 @@ import {
   requestDeviceCode,
   pollForToken,
 } from "@/lib/oauth/providers";
-import { createProviderConnection, isCloudEnabled } from "@/models";
+import { createProviderConnection, updateProviderConnection, getProviderConnections, isCloudEnabled } from "@/models";
 import { getConsistentMachineId } from "@/shared/utils/machineId";
 import { syncToCloud } from "@/lib/cloudSync";
 import { startLocalServer } from "@/lib/oauth/utils/server";
@@ -170,16 +170,33 @@ export async function POST(
         exchangeTokens(provider, code, redirectUri, codeVerifier, state)
       );
 
-      // Save to database
-      const connection: any = await createProviderConnection({
-        provider,
-        authType: "oauth",
-        ...tokenData,
-        expiresAt: tokenData.expiresIn
-          ? new Date(Date.now() + tokenData.expiresIn * 1000).toISOString()
-          : null,
-        testStatus: "active",
-      });
+      // Upsert: update existing connection if same provider+email, else create new
+      const expiresAt = tokenData.expiresIn
+        ? new Date(Date.now() + tokenData.expiresIn * 1000).toISOString()
+        : null;
+
+      let connection: any;
+      if (tokenData.email) {
+        const existing = await getProviderConnections({ provider });
+        const match = existing.find((c: any) => c.email === tokenData.email && c.authType === "oauth");
+        if (match) {
+          connection = await updateProviderConnection(match.id, {
+            ...tokenData,
+            expiresAt,
+            testStatus: "active",
+            isActive: true,
+          });
+        }
+      }
+      if (!connection) {
+        connection = await createProviderConnection({
+          provider,
+          authType: "oauth",
+          ...tokenData,
+          expiresAt,
+          testStatus: "active",
+        });
+      }
 
       // Auto sync to Cloud if enabled
       await syncToCloudIfEnabled();
@@ -218,16 +235,33 @@ export async function POST(
       }
 
       if (result.success) {
-        // Save to database
-        const connection: any = await createProviderConnection({
-          provider,
-          authType: "oauth",
-          ...result.tokens,
-          expiresAt: result.tokens.expiresIn
-            ? new Date(Date.now() + result.tokens.expiresIn * 1000).toISOString()
-            : null,
-          testStatus: "active",
-        });
+        // Upsert: update existing connection if same provider+email, else create new
+        const expiresAt = result.tokens.expiresIn
+          ? new Date(Date.now() + result.tokens.expiresIn * 1000).toISOString()
+          : null;
+
+        let connection: any;
+        if (result.tokens.email) {
+          const existing = await getProviderConnections({ provider });
+          const match = existing.find((c: any) => c.email === result.tokens.email && c.authType === "oauth");
+          if (match) {
+            connection = await updateProviderConnection(match.id, {
+              ...result.tokens,
+              expiresAt,
+              testStatus: "active",
+              isActive: true,
+            });
+          }
+        }
+        if (!connection) {
+          connection = await createProviderConnection({
+            provider,
+            authType: "oauth",
+            ...result.tokens,
+            expiresAt,
+            testStatus: "active",
+          });
+        }
 
         // Auto sync to Cloud if enabled
         await syncToCloudIfEnabled();
@@ -312,16 +346,33 @@ export async function POST(
           exchangeTokens(provider, params.code, redirectUri, codeVerifier, params.state)
         );
 
-        // Save to database
-        const connection: any = await createProviderConnection({
-          provider,
-          authType: "oauth",
-          ...tokenData,
-          expiresAt: tokenData.expiresIn
-            ? new Date(Date.now() + tokenData.expiresIn * 1000).toISOString()
-            : null,
-          testStatus: "active",
-        });
+        // Upsert: update existing connection if same provider+email, else create new
+        const expiresAt = tokenData.expiresIn
+          ? new Date(Date.now() + tokenData.expiresIn * 1000).toISOString()
+          : null;
+
+        let connection: any;
+        if (tokenData.email) {
+          const existing = await getProviderConnections({ provider });
+          const match = existing.find((c: any) => c.email === tokenData.email && c.authType === "oauth");
+          if (match) {
+            connection = await updateProviderConnection(match.id, {
+              ...tokenData,
+              expiresAt,
+              testStatus: "active",
+              isActive: true,
+            });
+          }
+        }
+        if (!connection) {
+          connection = await createProviderConnection({
+            provider,
+            authType: "oauth",
+            ...tokenData,
+            expiresAt,
+            testStatus: "active",
+          });
+        }
 
         await syncToCloudIfEnabled();
 

src/app/api/providers/[id]/models/route.ts

@@ -49,7 +49,12 @@ const PROVIDER_MODELS_CONFIG = {
     method: "GET",
     headers: { "Content-Type": "application/json" },
     authQuery: "key", // Use query param for API key
-    parseResponse: (data) => data.models || [],
+    parseResponse: (data) =>
+      (data.models || []).map((m) => ({
+        ...m,
+        id: (m.name || m.id || "").replace(/^models\//, ""),
+        name: m.displayName || (m.name || "").replace(/^models\//, ""),
+      })),
   },
   "gemini-cli": {
     url: "https://generativelanguage.googleapis.com/v1beta/models",
@@ -57,7 +62,12 @@ const PROVIDER_MODELS_CONFIG = {
     headers: { "Content-Type": "application/json" },
     authHeader: "Authorization",
     authPrefix: "Bearer ",
-    parseResponse: (data) => data.models || [],
+    parseResponse: (data) =>
+      (data.models || []).map((m) => ({
+        ...m,
+        id: (m.name || m.id || "").replace(/^models\//, ""),
+        name: m.displayName || (m.name || "").replace(/^models\//, ""),
+      })),
   },
   qwen: {
     url: "https://portal.qwen.ai/v1/models",
@@ -133,6 +143,14 @@ const PROVIDER_MODELS_CONFIG = {
     authPrefix: "Bearer ",
     parseResponse: (data) => data.data || data.models || [],
   },
+  blackbox: {
+    url: "https://api.blackbox.ai/v1/models",
+    method: "GET",
+    headers: { "Content-Type": "application/json" },
+    authHeader: "Authorization",
+    authPrefix: "Bearer ",
+    parseResponse: (data) => data.data || data.models || [],
+  },
   xai: {
     url: "https://api.x.ai/v1/models",
     method: "GET",

src/app/api/settings/background-degradation/route.ts

@@ -0,0 +1,60 @@
+import { NextResponse } from "next/server";
+import {
+  getBackgroundDegradationConfig,
+  setBackgroundDegradationConfig,
+  resetStats,
+} from "@omniroute/open-sse/services/backgroundTaskDetector.ts";
+import { updateSettings } from "@/lib/db/settings";
+
+/**
+ * GET /api/settings/background-degradation
+ * Returns the current background degradation configuration.
+ */
+export async function GET() {
+  try {
+    return NextResponse.json(getBackgroundDegradationConfig());
+  } catch (error) {
+    console.error("[API ERROR] /api/settings/background-degradation GET:", error);
+    return NextResponse.json({ error: "Failed to get config" }, { status: 500 });
+  }
+}
+
+/**
+ * PUT /api/settings/background-degradation
+ * Update the background degradation configuration.
+ * Body: { enabled?: boolean, degradationMap?: {...}, detectionPatterns?: [...] }
+ */
+export async function PUT(request) {
+  try {
+    const config = await request.json();
+    setBackgroundDegradationConfig(config);
+
+    // Persist to database (excluding stats)
+    const { stats, ...persistable } = getBackgroundDegradationConfig();
+    await updateSettings({ backgroundDegradation: JSON.stringify(persistable) });
+
+    return NextResponse.json({ success: true, ...getBackgroundDegradationConfig() });
+  } catch (error) {
+    console.error("[API ERROR] /api/settings/background-degradation PUT:", error);
+    return NextResponse.json({ error: "Failed to update config" }, { status: 500 });
+  }
+}
+
+/**
+ * POST /api/settings/background-degradation
+ * Reset stats counters.
+ * Body: { action: "reset-stats" }
+ */
+export async function POST(request) {
+  try {
+    const { action } = await request.json();
+    if (action === "reset-stats") {
+      resetStats();
+      return NextResponse.json({ success: true, stats: getBackgroundDegradationConfig().stats });
+    }
+    return NextResponse.json({ error: "Unknown action" }, { status: 400 });
+  } catch (error) {
+    console.error("[API ERROR] /api/settings/background-degradation POST:", error);
+    return NextResponse.json({ error: "Failed to execute action" }, { status: 500 });
+  }
+}

src/app/api/settings/model-aliases/route.ts

@@ -0,0 +1,90 @@
+import { NextResponse } from "next/server";
+import {
+  getAllAliases,
+  getCustomAliases,
+  getBuiltInAliases,
+  setCustomAliases,
+  addCustomAlias,
+  removeCustomAlias,
+} from "@omniroute/open-sse/services/modelDeprecation.ts";
+import { getSettings, updateSettings } from "@/lib/db/settings";
+
+/**
+ * GET /api/settings/model-aliases
+ * Returns the full alias map, separated into built-in and custom.
+ */
+export async function GET() {
+  try {
+    return NextResponse.json({
+      builtIn: getBuiltInAliases(),
+      custom: getCustomAliases(),
+      all: getAllAliases(),
+    });
+  } catch (error) {
+    console.error("[API ERROR] /api/settings/model-aliases GET:", error);
+    return NextResponse.json({ error: "Failed to get model aliases" }, { status: 500 });
+  }
+}
+
+/**
+ * PUT /api/settings/model-aliases
+ * Update the custom aliases map.
+ * Body: { aliases: { "old-model": "new-model", ... } }
+ */
+export async function PUT(request) {
+  try {
+    const { aliases } = await request.json();
+    if (!aliases || typeof aliases !== "object") {
+      return NextResponse.json({ error: "Missing or invalid 'aliases' object" }, { status: 400 });
+    }
+    setCustomAliases(aliases);
+    await updateSettings({ modelAliases: JSON.stringify(aliases) });
+    return NextResponse.json({ success: true, custom: getCustomAliases() });
+  } catch (error) {
+    console.error("[API ERROR] /api/settings/model-aliases PUT:", error);
+    return NextResponse.json({ error: "Failed to update model aliases" }, { status: 500 });
+  }
+}
+
+/**
+ * POST /api/settings/model-aliases
+ * Add a single custom alias.
+ * Body: { from: "old-model", to: "new-model" }
+ */
+export async function POST(request) {
+  try {
+    const { from, to } = await request.json();
+    if (!from || !to) {
+      return NextResponse.json({ error: "Missing 'from' or 'to'" }, { status: 400 });
+    }
+    addCustomAlias(from, to);
+    await updateSettings({ modelAliases: JSON.stringify(getCustomAliases()) });
+    return NextResponse.json({ success: true, custom: getCustomAliases() });
+  } catch (error) {
+    console.error("[API ERROR] /api/settings/model-aliases POST:", error);
+    return NextResponse.json({ error: "Failed to add alias" }, { status: 500 });
+  }
+}
+
+/**
+ * DELETE /api/settings/model-aliases
+ * Remove a custom alias.
+ * Body: { from: "old-model" }
+ */
+export async function DELETE(request) {
+  try {
+    const { from } = await request.json();
+    if (!from) {
+      return NextResponse.json({ error: "Missing 'from'" }, { status: 400 });
+    }
+    const removed = removeCustomAlias(from);
+    if (!removed) {
+      return NextResponse.json({ error: "Alias not found" }, { status: 404 });
+    }
+    await updateSettings({ modelAliases: JSON.stringify(getCustomAliases()) });
+    return NextResponse.json({ success: true, custom: getCustomAliases() });
+  } catch (error) {
+    console.error("[API ERROR] /api/settings/model-aliases DELETE:", error);
+    return NextResponse.json({ error: "Failed to remove alias" }, { status: 500 });
+  }
+}

src/app/api/settings/proxy/route.ts

@@ -5,6 +5,7 @@ import {
   deleteProxyForLevel,
   resolveProxyForConnection,
 } from "../../../../lib/localDb";
+import { clearDispatcherCache } from "@omniroute/open-sse/utils/proxyDispatcher";
 
 const BASE_SUPPORTED_PROXY_TYPES = new Set(["http", "https"]);
 
@@ -129,6 +130,7 @@ export async function PUT(request) {
     const body = await request.json();
     const normalizedBody = normalizeProxyPayload(body);
     const updated = await setProxyConfig(normalizedBody);
+    clearDispatcherCache();
     return Response.json(updated);
   } catch (error) {
     const status = Number(error?.status) || 500;
@@ -155,6 +157,7 @@ export async function DELETE(request) {
     }
 
     const updated = await deleteProxyForLevel(level, id);
+    clearDispatcherCache();
     return Response.json(updated);
   } catch (error) {
     return Response.json(

src/app/api/sync/cloud/route.ts

@@ -114,11 +114,15 @@ async function syncAndVerify(machineId: string, createdKey: any, existingKeys: a
     );
   }
 
+  // Build the cloud URL for the frontend to use
+  const cloudUrl = CLOUD_URL ? `${CLOUD_URL}/${machineId}` : null;
+
   // Step 2: Verify connection by pinging the cloud (with retry)
   const apiKey = createdKey || existingKeys[0]?.key;
   if (!apiKey) {
     return NextResponse.json({
       ...syncResult,
+      cloudUrl,
       verified: false,
       verifyError: "No API key available",
     });
@@ -146,6 +150,7 @@ async function syncAndVerify(machineId: string, createdKey: any, existingKeys: a
       if (pingResponse.ok) {
         return NextResponse.json({
           ...syncResult,
+          cloudUrl,
           verified: true,
         });
       }
@@ -163,6 +168,7 @@ async function syncAndVerify(machineId: string, createdKey: any, existingKeys: a
   // Sync succeeded but verify failed — still return success with warning
   return NextResponse.json({
     ...syncResult,
+    cloudUrl,
     verified: false,
     verifyError: lastVerifyError || "Verification failed after retries",
   });

src/app/api/v1/audio/speech/route.ts

@@ -1,7 +1,7 @@
 import { CORS_ORIGIN } from "@/shared/utils/cors";
 import { handleAudioSpeech } from "@omniroute/open-sse/handlers/audioSpeech.ts";
 import { getProviderCredentials, extractApiKey, isValidApiKey } from "@/sse/services/auth";
-import { parseSpeechModel } from "@omniroute/open-sse/config/audioRegistry.ts";
+import { parseSpeechModel, getSpeechProvider } from "@omniroute/open-sse/config/audioRegistry.ts";
 import { errorResponse } from "@omniroute/open-sse/utils/error.ts";
 import { HTTP_STATUS } from "@omniroute/open-sse/config/constants.ts";
 import { enforceApiKeyPolicy } from "@/shared/utils/apiKeyPolicy";
@@ -54,9 +54,16 @@ export async function POST(request) {
     );
   }
 
-  const credentials = await getProviderCredentials(provider);
-  if (!credentials) {
-    return errorResponse(HTTP_STATUS.BAD_REQUEST, `No credentials for provider: ${provider}`);
+  // Check provider config for auth bypass
+  const providerConfig = getSpeechProvider(provider);
+
+  // Get credentials — skip for local providers (authType: "none")
+  let credentials = null;
+  if (providerConfig && providerConfig.authType !== "none") {
+    credentials = await getProviderCredentials(provider);
+    if (!credentials) {
+      return errorResponse(HTTP_STATUS.BAD_REQUEST, `No credentials for provider: ${provider}`);
+    }
   }
 
   return handleAudioSpeech({ body, credentials });

src/app/api/v1/audio/transcriptions/route.ts

@@ -1,7 +1,7 @@
 import { CORS_ORIGIN } from "@/shared/utils/cors";
 import { handleAudioTranscription } from "@omniroute/open-sse/handlers/audioTranscription.ts";
 import { getProviderCredentials, extractApiKey, isValidApiKey } from "@/sse/services/auth";
-import { parseTranscriptionModel } from "@omniroute/open-sse/config/audioRegistry.ts";
+import { parseTranscriptionModel, getTranscriptionProvider } from "@omniroute/open-sse/config/audioRegistry.ts";
 import { errorResponse } from "@omniroute/open-sse/utils/error.ts";
 import { HTTP_STATUS } from "@omniroute/open-sse/config/constants.ts";
 import { enforceApiKeyPolicy } from "@/shared/utils/apiKeyPolicy";
@@ -56,9 +56,16 @@ export async function POST(request) {
     );
   }
 
-  const credentials = await getProviderCredentials(provider);
-  if (!credentials) {
-    return errorResponse(HTTP_STATUS.BAD_REQUEST, `No credentials for provider: ${provider}`);
+  // Check provider config for auth bypass
+  const providerConfig = getTranscriptionProvider(provider);
+
+  // Get credentials — skip for local providers (authType: "none")
+  let credentials = null;
+  if (providerConfig && providerConfig.authType !== "none") {
+    credentials = await getProviderCredentials(provider);
+    if (!credentials) {
+      return errorResponse(HTTP_STATUS.BAD_REQUEST, `No credentials for provider: ${provider}`);
+    }
   }
 
   return handleAudioTranscription({ formData, credentials });

src/app/api/v1/images/generations/route.ts

@@ -1,7 +1,7 @@
 import { CORS_ORIGIN } from "@/shared/utils/cors";
 import { handleImageGeneration } from "@omniroute/open-sse/handlers/imageGeneration.ts";
 import { getProviderCredentials, extractApiKey, isValidApiKey } from "@/sse/services/auth";
-import { parseImageModel, getAllImageModels } from "@omniroute/open-sse/config/imageRegistry.ts";
+import { parseImageModel, getAllImageModels, getImageProvider } from "@omniroute/open-sse/config/imageRegistry.ts";
 import { errorResponse } from "@omniroute/open-sse/utils/error.ts";
 import { HTTP_STATUS } from "@omniroute/open-sse/config/constants.ts";
 import * as log from "@/sse/utils/logger";
@@ -89,10 +89,16 @@ export async function POST(request) {
     );
   }
 
-  // Get credentials for the image provider
-  const credentials = await getProviderCredentials(provider);
-  if (!credentials) {
-    return errorResponse(HTTP_STATUS.BAD_REQUEST, `No credentials for image provider: ${provider}`);
+  // Check provider config for auth bypass
+  const providerConfig = getImageProvider(provider);
+
+  // Get credentials — skip for local providers (authType: "none")
+  let credentials = null;
+  if (providerConfig && providerConfig.authType !== "none") {
+    credentials = await getProviderCredentials(provider);
+    if (!credentials) {
+      return errorResponse(HTTP_STATUS.BAD_REQUEST, `No credentials for image provider: ${provider}`);
+    }
   }
 
   const result = await handleImageGeneration({ body, credentials, log });

src/app/api/v1/models/route.ts

@@ -14,6 +14,8 @@ import { getAllImageModels } from "@omniroute/open-sse/config/imageRegistry.ts";
 import { getAllRerankModels } from "@omniroute/open-sse/config/rerankRegistry.ts";
 import { getAllAudioModels } from "@omniroute/open-sse/config/audioRegistry.ts";
 import { getAllModerationModels } from "@omniroute/open-sse/config/moderationRegistry.ts";
+import { getAllVideoModels, getVideoProvider } from "@omniroute/open-sse/config/videoRegistry.ts";
+import { getAllMusicModels, getMusicProvider } from "@omniroute/open-sse/config/musicRegistry.ts";
 
 const FALLBACK_ALIAS_TO_PROVIDER = {
   ag: "antigravity",
@@ -310,6 +312,32 @@ export async function GET(request: Request) {
       });
     }
 
+    // Add video models (local providers always listed, cloud filtered by active)
+    for (const videoModel of getAllVideoModels()) {
+      const vConfig = getVideoProvider(videoModel.provider);
+      if (vConfig?.authType !== "none" && !isProviderActive(videoModel.provider)) continue;
+      models.push({
+        id: videoModel.id,
+        object: "model",
+        created: timestamp,
+        owned_by: videoModel.provider,
+        type: "video",
+      });
+    }
+
+    // Add music models (local providers always listed, cloud filtered by active)
+    for (const musicModel of getAllMusicModels()) {
+      const mConfig = getMusicProvider(musicModel.provider);
+      if (mConfig?.authType !== "none" && !isProviderActive(musicModel.provider)) continue;
+      models.push({
+        id: musicModel.id,
+        object: "model",
+        created: timestamp,
+        owned_by: musicModel.provider,
+        type: "music",
+      });
+    }
+
     // Add custom models (user-defined)
     try {
       const customModelsMap: Record<string, any[]> = await getAllCustomModels();

src/app/api/v1/music/generations/route.ts

@@ -0,0 +1,117 @@
+import { CORS_ORIGIN } from "@/shared/utils/cors";
+import { handleMusicGeneration } from "@omniroute/open-sse/handlers/musicGeneration.ts";
+import { getProviderCredentials, extractApiKey, isValidApiKey } from "@/sse/services/auth";
+import { parseMusicModel, getAllMusicModels, getMusicProvider } from "@omniroute/open-sse/config/musicRegistry.ts";
+import { errorResponse } from "@omniroute/open-sse/utils/error.ts";
+import { HTTP_STATUS } from "@omniroute/open-sse/config/constants.ts";
+import * as log from "@/sse/utils/logger";
+import { toJsonErrorPayload } from "@/shared/utils/upstreamError";
+import { enforceApiKeyPolicy } from "@/shared/utils/apiKeyPolicy";
+
+/**
+ * Handle CORS preflight
+ */
+export async function OPTIONS() {
+  return new Response(null, {
+    headers: {
+      "Access-Control-Allow-Origin": CORS_ORIGIN,
+      "Access-Control-Allow-Methods": "GET, POST, OPTIONS",
+      "Access-Control-Allow-Headers": "*",
+    },
+  });
+}
+
+/**
+ * GET /v1/music/generations — list available music models
+ */
+export async function GET() {
+  const models = getAllMusicModels();
+  return new Response(
+    JSON.stringify({
+      object: "list",
+      data: models.map((m) => ({
+        id: m.id,
+        object: "model",
+        created: Math.floor(Date.now() / 1000),
+        owned_by: m.provider,
+        type: "music",
+      })),
+    }),
+    {
+      headers: { "Content-Type": "application/json" },
+    }
+  );
+}
+
+/**
+ * POST /v1/music/generations — generate music
+ */
+export async function POST(request) {
+  let body;
+  try {
+    body = await request.json();
+  } catch {
+    log.warn("MUSIC", "Invalid JSON body");
+    return errorResponse(HTTP_STATUS.BAD_REQUEST, "Invalid JSON body");
+  }
+
+  // Optional API key validation
+  if (process.env.REQUIRE_API_KEY === "true") {
+    const apiKey = extractApiKey(request);
+    if (!apiKey) {
+      return errorResponse(HTTP_STATUS.UNAUTHORIZED, "Missing API key");
+    }
+    const valid = await isValidApiKey(apiKey);
+    if (!valid) {
+      return errorResponse(HTTP_STATUS.UNAUTHORIZED, "Invalid API key");
+    }
+  }
+
+  if (!body.model) {
+    return errorResponse(HTTP_STATUS.BAD_REQUEST, "Missing model");
+  }
+
+  if (typeof body.prompt !== "string" || body.prompt.trim().length === 0) {
+    return errorResponse(HTTP_STATUS.BAD_REQUEST, "Invalid prompt: expected a non-empty string");
+  }
+
+  // Enforce API key policies (model restrictions + budget limits)
+  const policy = await enforceApiKeyPolicy(request, body.model);
+  if (policy.rejection) return policy.rejection;
+
+  // Parse model to get provider
+  const { provider } = parseMusicModel(body.model);
+  if (!provider) {
+    return errorResponse(
+      HTTP_STATUS.BAD_REQUEST,
+      `Invalid music model: ${body.model}. Use format: provider/model`
+    );
+  }
+
+  // Check provider config for auth bypass
+  const providerConfig = getMusicProvider(provider);
+
+  // Get credentials — skip for local providers (authType: "none")
+  let credentials = null;
+  if (providerConfig && providerConfig.authType !== "none") {
+    credentials = await getProviderCredentials(provider);
+    if (!credentials) {
+      return errorResponse(HTTP_STATUS.BAD_REQUEST, `No credentials for music provider: ${provider}`);
+    }
+  }
+
+  const result = await handleMusicGeneration({ body, credentials, log });
+
+  if (result.success) {
+    return new Response(JSON.stringify((result as any).data), {
+      status: 200,
+      headers: { "Content-Type": "application/json" },
+    });
+  }
+
+  const errorPayload = toJsonErrorPayload((result as any).error, "Music generation provider error");
+  return new Response(JSON.stringify(errorPayload), {
+    status: (result as any).status,
+    headers: { "Content-Type": "application/json" },
+  });
+}

src/app/api/v1/videos/generations/route.ts

@@ -0,0 +1,117 @@
+import { CORS_ORIGIN } from "@/shared/utils/cors";
+import { handleVideoGeneration } from "@omniroute/open-sse/handlers/videoGeneration.ts";
+import { getProviderCredentials, extractApiKey, isValidApiKey } from "@/sse/services/auth";
+import { parseVideoModel, getAllVideoModels, getVideoProvider } from "@omniroute/open-sse/config/videoRegistry.ts";
+import { errorResponse } from "@omniroute/open-sse/utils/error.ts";
+import { HTTP_STATUS } from "@omniroute/open-sse/config/constants.ts";
+import * as log from "@/sse/utils/logger";
+import { toJsonErrorPayload } from "@/shared/utils/upstreamError";
+import { enforceApiKeyPolicy } from "@/shared/utils/apiKeyPolicy";
+
+/**
+ * Handle CORS preflight
+ */
+export async function OPTIONS() {
+  return new Response(null, {
+    headers: {
+      "Access-Control-Allow-Origin": CORS_ORIGIN,
+      "Access-Control-Allow-Methods": "GET, POST, OPTIONS",
+      "Access-Control-Allow-Headers": "*",
+    },
+  });
+}
+
+/**
+ * GET /v1/videos/generations — list available video models
+ */
+export async function GET() {
+  const models = getAllVideoModels();
+  return new Response(
+    JSON.stringify({
+      object: "list",
+      data: models.map((m) => ({
+        id: m.id,
+        object: "model",
+        created: Math.floor(Date.now() / 1000),
+        owned_by: m.provider,
+        type: "video",
+      })),
+    }),
+    {
+      headers: { "Content-Type": "application/json" },
+    }
+  );
+}
+
+/**
+ * POST /v1/videos/generations — generate videos
+ */
+export async function POST(request) {
+  let body;
+  try {
+    body = await request.json();
+  } catch {
+    log.warn("VIDEO", "Invalid JSON body");
+    return errorResponse(HTTP_STATUS.BAD_REQUEST, "Invalid JSON body");
+  }
+
+  // Optional API key validation
+  if (process.env.REQUIRE_API_KEY === "true") {
+    const apiKey = extractApiKey(request);
+    if (!apiKey) {
+      return errorResponse(HTTP_STATUS.UNAUTHORIZED, "Missing API key");
+    }
+    const valid = await isValidApiKey(apiKey);
+    if (!valid) {
+      return errorResponse(HTTP_STATUS.UNAUTHORIZED, "Invalid API key");
+    }
+  }
+
+  if (!body.model) {
+    return errorResponse(HTTP_STATUS.BAD_REQUEST, "Missing model");
+  }
+
+  if (typeof body.prompt !== "string" || body.prompt.trim().length === 0) {
+    return errorResponse(HTTP_STATUS.BAD_REQUEST, "Invalid prompt: expected a non-empty string");
+  }
+
+  // Enforce API key policies (model restrictions + budget limits)
+  const policy = await enforceApiKeyPolicy(request, body.model);
+  if (policy.rejection) return policy.rejection;
+
+  // Parse model to get provider
+  const { provider } = parseVideoModel(body.model);
+  if (!provider) {
+    return errorResponse(
+      HTTP_STATUS.BAD_REQUEST,
+      `Invalid video model: ${body.model}. Use format: provider/model`
+    );
+  }
+
+  // Check provider config for auth bypass
+  const providerConfig = getVideoProvider(provider);
+
+  // Get credentials — skip for local providers (authType: "none")
+  let credentials = null;
+  if (providerConfig && providerConfig.authType !== "none") {
+    credentials = await getProviderCredentials(provider);
+    if (!credentials) {
+      return errorResponse(HTTP_STATUS.BAD_REQUEST, `No credentials for video provider: ${provider}`);
+    }
+  }
+
+  const result = await handleVideoGeneration({ body, credentials, log });
+
+  if (result.success) {
+    return new Response(JSON.stringify((result as any).data), {
+      status: 200,
+      headers: { "Content-Type": "application/json" },
+    });
+  }
+
+  const errorPayload = toJsonErrorPayload((result as any).error, "Video generation provider error");
+  return new Response(JSON.stringify(errorPayload), {
+    status: (result as any).status,
+    headers: { "Content-Type": "application/json" },
+  });
+}

src/app/globals.css

@@ -1,6 +1,12 @@
 @import url("https://fonts.googleapis.com/css2?family=Material+Symbols+Outlined:wght,FILL@100..700,0..1&display=swap");
 @import "tailwindcss";
 
+/* Tailwind v4 auto-detection cannot scan directories with parentheses
+   (e.g. Next.js route groups like "(dashboard)"). Explicit @source
+   directives ensure all utility classes in route groups are included. */
+@source "../app/(dashboard)";
+@source "../../open-sse";
+
 @custom-variant dark (&:where(.dark, .dark *));
 
 /* OpenClaw × ClawHub Color Palette */
@@ -135,9 +141,10 @@ body {
   -moz-osx-font-smoothing: grayscale;
 }
 
-/* Selection */
+/* Selection — with fallback for browsers that don't support color-mix() */
 ::selection {
-  background-color: rgba(229, 77, 94, 0.2);
+  background-color: rgba(229, 77, 94, 0.22);
+  background-color: color-mix(in srgb, var(--color-primary) 22%, transparent);
   color: var(--color-primary);
 }
 

src/domain/types.ts

@@ -8,7 +8,7 @@
  */
 
 /**
- * @typedef {'openai'|'claude'|'gemini'|'codex'|'qwen'|'deepseek'|'cohere'|'groq'|'mistral'|'openrouter'} ProviderId
+ * @typedef {'openai'|'claude'|'gemini'|'codex'|'qwen'|'deepseek'|'cohere'|'groq'|'blackbox'|'mistral'|'openrouter'} ProviderId
  */
 
 /**