fix(ci): reference NPM_TOKEN environment for environment-scoped secrets (#18)

Co-authored-by: diegosouzapw <diegosouzapw@users.noreply.github.com>

.agent/workflows/git-workflow.md

@@ -0,0 +1,54 @@
+---
+description: Git workflow — NEVER commit directly to main. Always use feature branches.
+---
+
+# Git Workflow
+
+## ⚠️ CRITICAL RULE: NEVER commit directly to `main`
+
+## Steps
+
+1. **Before starting any work**, create a feature branch from `main`:
+
+   ```bash
+   git checkout main && git pull origin main
+   git checkout -b feature/<feature-name>
+   ```
+
+2. **During development**, commit to the feature branch:
+
+   ```bash
+   git add -A && git commit -m "<type>(<scope>): <description>"
+   ```
+
+3. **Before pushing**, verify the build passes:
+
+   ```bash
+   npm run build
+   ```
+
+4. **When the feature is complete and verified**, push the branch and STOP:
+
+   ```bash
+   git push origin feature/<feature-name>
+   ```
+
+5. **DO NOT** create a PR, merge, or push to `main`. Let the user handle that.
+
+## Branch naming convention
+
+- `feature/<name>` — new features
+- `fix/<name>` — bugfixes
+- `refactor/<name>` — refactoring
+- `docker/<name>` — Docker / infrastructure changes
+- `style/<name>` — UI / CSS changes
+
+## Commit types
+
+- `feat` — new feature
+- `fix` — bugfix
+- `refactor` — code refactoring
+- `style` — UI / CSS changes
+- `docker` — Docker / infrastructure
+- `docs` — documentation
+- `chore` — maintenance

.env.example

@@ -1,22 +1,14 @@
 # OmniRoute environment contract
 # This file reflects actual runtime usage in the current codebase.
 
-# ═══════════════════════════════════════════════════
-#   REQUIRED SECRETS — Generate strong values!
-# ═══════════════════════════════════════════════════
-# Generate with: openssl rand -base64 48
-JWT_SECRET=
-# Generate with: openssl rand -hex 32
-API_KEY_SECRET=
-
-# Initial admin password — CHANGE THIS before first use!
-INITIAL_PASSWORD=CHANGEME
+# Required
+JWT_SECRET=change-me-to-a-long-random-secret
+INITIAL_PASSWORD=123456
 DATA_DIR=/var/lib/omniroute
 
 # Storage (SQLite)
 STORAGE_DRIVER=sqlite
-# Generate with: openssl rand -hex 32
-STORAGE_ENCRYPTION_KEY=
+STORAGE_ENCRYPTION_KEY=change-me-storage-encryption-key
 STORAGE_ENCRYPTION_KEY_VERSION=v1
 LOG_RETENTION_DAYS=90
 SQLITE_MAX_SIZE_MB=2048
@@ -28,25 +20,18 @@ NODE_ENV=production
 INSTANCE_NAME=omniroute
 
 # Recommended security and ops variables
+API_KEY_SECRET=endpoint-proxy-api-key-secret
 MACHINE_ID_SALT=endpoint-proxy-salt
 ENABLE_REQUEST_LOGS=false
 AUTH_COOKIE_SECURE=false
 REQUIRE_API_KEY=false
 
-# Input Sanitizer (FASE-01 — prompt injection & PII protection)
-# INPUT_SANITIZER_ENABLED=true
-# INPUT_SANITIZER_MODE=warn    # warn | block | redact
-# PII_REDACTION_ENABLED=false
-
 # Cloud sync variables
 # Must point to this running instance so internal sync jobs can call /api/sync/cloud.
 # Server-side preferred variables:
 BASE_URL=http://localhost:20128
 CLOUD_URL=
 # Backward-compatible/public variables:
-# NEXT_PUBLIC_BASE_URL is also used as the OAuth redirect_uri origin when running behind a
-# reverse proxy (e.g., nginx). Set this to your public-facing URL so OAuth callbacks work.
-# Example: NEXT_PUBLIC_BASE_URL=https://omniroute.example.com
 NEXT_PUBLIC_BASE_URL=http://localhost:20128
 NEXT_PUBLIC_CLOUD_URL=
 
@@ -60,11 +45,6 @@ NEXT_PUBLIC_ENABLE_SOCKS5_PROXY=true
 # ALL_PROXY=socks5://127.0.0.1:7890
 # NO_PROXY=localhost,127.0.0.1
 
-# TLS fingerprint spoofing (opt-in) — mimics Chrome 124 TLS handshake via wreq-js
-# Reduces risk of JA3/JA4 fingerprint-based blocking by providers (e.g., Google)
-# Requires wreq-js to be installed (included in dependencies)
-# ENABLE_TLS_FINGERPRINT=true
-
 # Optional CLI runtime overrides (Docker/host integration)
 # CLI_MODE=auto
 # CLI_EXTRA_PATHS=/host-cli/bin
@@ -82,45 +62,17 @@ NEXT_PUBLIC_ENABLE_SOCKS5_PROXY=true
 # Provider OAuth Credentials (optional — override hardcoded defaults)
 # These can also be set via data/provider-credentials.json
 # CLAUDE_OAUTH_CLIENT_ID=
-
-# ─────────────────────────────────────────────────────────────────────────────
-# ⚠️  GOOGLE OAUTH (Antigravity, Gemini CLI) — IMPORTANT FOR REMOTE SERVERS
-# ─────────────────────────────────────────────────────────────────────────────
-# The built-in Google OAuth credentials ONLY work when OmniRoute runs on
-# localhost (127.0.0.1 / local network). They are registered with
-# redirect_uri = http://localhost:PORT/callback and Google will reject any
-# other redirect URI with: redirect_uri_mismatch.
-#
-# If you are hosting OmniRoute on a remote server (VPS, Docker, cloud), you
-# MUST register your own Google Cloud OAuth 2.0 credentials:
-#
-#   1. Go to https://console.cloud.google.com/apis/credentials
-#   2. Create an OAuth 2.0 Client ID (type: "Web application")
-#   3. Add your server URL as Authorized redirect URI:
-#        https://your-server.com/callback
-#   4. Copy the Client ID and Client Secret below.
-#
-# See the full tutorial in README.md → "OAuth em Servidor Remoto" section.
-#
-# Antigravity (Google Gemini Code Assist):
-# ANTIGRAVITY_OAUTH_CLIENT_ID=your-client-id.apps.googleusercontent.com
-# ANTIGRAVITY_OAUTH_CLIENT_SECRET=GOCSPX-your-secret
-ANTIGRAVITY_OAUTH_CLIENT_SECRET=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
-
-# Gemini CLI (Google AI):
-# GEMINI_OAUTH_CLIENT_ID=your-client-id.apps.googleusercontent.com
-# GEMINI_OAUTH_CLIENT_SECRET=GOCSPX-your-secret
+# GEMINI_OAUTH_CLIENT_ID=
+# GEMINI_OAUTH_CLIENT_SECRET=
 # GEMINI_CLI_OAUTH_CLIENT_ID=
-GEMINI_OAUTH_CLIENT_SECRET=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
-GEMINI_CLI_OAUTH_CLIENT_SECRET=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
-# ─────────────────────────────────────────────────────────────────────────────
-
-# CLAUDE_OAUTH_CLIENT_ID=
+# GEMINI_CLI_OAUTH_CLIENT_SECRET=
 # CODEX_OAUTH_CLIENT_ID=
 # CODEX_OAUTH_CLIENT_SECRET=
 # QWEN_OAUTH_CLIENT_ID=
 # IFLOW_OAUTH_CLIENT_ID=
-IFLOW_OAUTH_CLIENT_SECRET=4Z3YjXycVsQvyGF1etiNlIBB4RsqSDtW
+# IFLOW_OAUTH_CLIENT_SECRET=
+# ANTIGRAVITY_OAUTH_CLIENT_ID=
+# ANTIGRAVITY_OAUTH_CLIENT_SECRET=
 
 # API Key Providers (Phase 1 + Phase 4)
 # Add via Dashboard → Providers → Add API Key, or set here
@@ -149,7 +101,3 @@ IFLOW_OAUTH_CLIENT_SECRET=4Z3YjXycVsQvyGF1etiNlIBB4RsqSDtW
 # Logging
 # LOG_LEVEL=info
 # LOG_FORMAT=text
-LOG_TO_FILE=true
-# LOG_FILE_PATH=logs/application/app.log
-# LOG_MAX_FILE_SIZE=50M
-# LOG_RETENTION_DAYS=7

.github/dependabot.yml

@@ -20,10 +20,6 @@ updates:
         update-types: ["version-update:semver-major"]
       - dependency-name: "next"
         update-types: ["version-update:semver-major"]
-      - dependency-name: "eslint"
-        update-types: ["version-update:semver-major"]
-      - dependency-name: "eslint-config-next"
-        update-types: ["version-update:semver-major"]
 
   - package-ecosystem: "github-actions"
     directory: "/"

.github/workflows/ci.yml

@@ -1,147 +0,0 @@
-name: CI
-
-on:
-  push:
-    branches: [main]
-  pull_request:
-    branches: [main]
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}
-  cancel-in-progress: true
-
-jobs:
-  lint:
-    name: Lint
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v6
-      - uses: actions/setup-node@v6
-        with:
-          node-version: 22
-          cache: npm
-      - run: npm ci
-      - run: npm run lint
-
-  security:
-    name: Security Audit
-    runs-on: ubuntu-latest
-    steps:
-      - uses: actions/checkout@v6
-      - uses: actions/setup-node@v6
-        with:
-          node-version: 22
-          cache: npm
-      - run: npm ci
-      - name: Dependency audit
-        run: npm audit --audit-level=high --omit=dev
-      - name: Check for known vulnerabilities
-        run: npx is-my-node-vulnerable
-        continue-on-error: true
-
-  build:
-    name: Build
-    runs-on: ubuntu-latest
-    strategy:
-      matrix:
-        node-version: [20, 22]
-    steps:
-      - uses: actions/checkout@v6
-      - uses: actions/setup-node@v6
-        with:
-          node-version: ${{ matrix.node-version }}
-          cache: npm
-      - run: npm ci
-      - run: npm run build
-
-  test-unit:
-    name: Unit Tests
-    runs-on: ubuntu-latest
-    needs: build
-    strategy:
-      matrix:
-        node-version: [20, 22]
-    env:
-      JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-test-api-key-secret-long
-    steps:
-      - uses: actions/checkout@v6
-      - uses: actions/setup-node@v6
-        with:
-          node-version: ${{ matrix.node-version }}
-          cache: npm
-      - run: npm ci
-      - run: npm run test:unit
-
-  test-coverage:
-    name: Coverage
-    runs-on: ubuntu-latest
-    needs: build
-    env:
-      JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-test-api-key-secret-long
-    steps:
-      - uses: actions/checkout@v6
-      - uses: actions/setup-node@v6
-        with:
-          node-version: 22
-          cache: npm
-      - run: npm ci
-      - run: npm run test:coverage
-      - name: Check coverage threshold
-        run: |
-          echo "Coverage report generated. Check output for threshold compliance."
-
-  test-e2e:
-    name: E2E Tests
-    runs-on: ubuntu-latest
-    needs: build
-    env:
-      JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-test-api-key-secret-long
-    steps:
-      - uses: actions/checkout@v6
-      - uses: actions/setup-node@v6
-        with:
-          node-version: 22
-          cache: npm
-      - run: npm ci
-      - run: npx playwright install --with-deps chromium
-      - run: npm run build
-      - run: npm run test:e2e
-
-  test-integration:
-    name: Integration Tests
-    runs-on: ubuntu-latest
-    needs: build
-    env:
-      JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-test-api-key-secret-long
-      INITIAL_PASSWORD: ci-test-password-for-integration
-      DATA_DIR: /tmp/omniroute-ci
-    steps:
-      - uses: actions/checkout@v6
-      - uses: actions/setup-node@v6
-        with:
-          node-version: 22
-          cache: npm
-      - run: npm ci
-      - run: npm run test:integration
-        continue-on-error: true
-
-  test-security:
-    name: Security Tests
-    runs-on: ubuntu-latest
-    needs: build
-    env:
-      JWT_SECRET: ci-test-secret-with-sufficient-length-for-validation
-      API_KEY_SECRET: ci-test-api-key-secret-long
-    steps:
-      - uses: actions/checkout@v6
-      - uses: actions/setup-node@v6
-        with:
-          node-version: 22
-          cache: npm
-      - run: npm ci
-      - run: npm run test:security
-        continue-on-error: true

.github/workflows/docker-publish.yml

@@ -1,55 +0,0 @@
-name: Publish to Docker Hub
-
-on:
-  release:
-    types: [published]
-
-permissions:
-  contents: read
-
-jobs:
-  docker:
-    name: Build & Push Docker Image
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout
-        uses: actions/checkout@v6
-
-      - name: Extract version from release tag
-        id: version
-        run: |
-          VERSION="${GITHUB_REF_NAME}"
-          VERSION="${VERSION#v}"
-          echo "version=$VERSION" >> "$GITHUB_OUTPUT"
-          echo "Publishing Docker image version: $VERSION"
-
-      - name: Set up Docker Buildx
-        uses: docker/setup-buildx-action@v3
-
-      - name: Login to Docker Hub
-        uses: docker/login-action@v3
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-
-      - name: Build and push
-        uses: docker/build-push-action@v6
-        with:
-          context: .
-          target: runner-base
-          push: true
-          tags: |
-            diegosouzapw/omniroute:${{ steps.version.outputs.version }}
-            diegosouzapw/omniroute:latest
-          cache-from: type=gha
-          cache-to: type=gha,mode=max
-          platforms: linux/amd64
-
-      - name: Update Docker Hub description
-        uses: peter-evans/dockerhub-description@v5
-        with:
-          username: ${{ secrets.DOCKERHUB_USERNAME }}
-          password: ${{ secrets.DOCKERHUB_TOKEN }}
-          repository: diegosouzapw/omniroute
-          short-description: "OmniRoute — Unified AI proxy. Route any LLM through one endpoint."
-          readme-filepath: ./README.md

.github/workflows/npm-publish.yml

@@ -14,10 +14,10 @@ jobs:
     environment: NPM_TOKEN
     steps:
       - name: Checkout
-        uses: actions/checkout@v6
+        uses: actions/checkout@v4
 
       - name: Setup Node.js
-        uses: actions/setup-node@v6
+        uses: actions/setup-node@v4
         with:
           node-version: 22
           registry-url: https://registry.npmjs.org

.gitignore

@@ -47,33 +47,20 @@ next-env.d.ts
 data/
 logs/*
 
-# analysis directories (generated, not tracked)
-.analysis/
-antigravity-manager-analysis/
-
 # docs (allow specific tracked files)
 docs/*
 !docs/ARCHITECTURE.md
 !docs/CODEBASE_DOCUMENTATION.md
 !docs/CONTRIBUTING.md
-!docs/USER_GUIDE.md
-!docs/API_REFERENCE.md
-!docs/TROUBLESHOOTING.md
 !docs/EXECUTION_CONTEXT_PROVIDER_SYNC.md
 !docs/TASK_NEBIUS_BACKEND_ENABLEMENT.md
 !docs/frontend-backend-provider-gap-report.md
 !docs/openapi.yaml
-!docs/PLANO-IMPLANTACAO.md
-!docs/TASKS.md
-!docs/FASE-*.md
 !docs/adr/
 !docs/cli-tools/
 !docs/planning/
 !docs/improvement-plans/
 !docs/api/
-!docs/VM_DEPLOYMENT_GUIDE.md
-!docs/FEATURES.md
-!docs/screenshots/
 
 # open-sse tests
 open-sse/test/*
@@ -85,13 +72,3 @@ open-sse/test/*
 test-results/
 playwright-report/
 blob-report/
-cloud/
-omnirouteCloud/
-omnirouteSite/
-
-# Security Analysis (standalone project with own git)
-security-analysis/
-
-# Deploy workflow (contains sensitive VPS credentials)
-.agent/workflows/deploy.md
-clipr/

AGENTS.md

@@ -8,7 +8,6 @@ Unified AI proxy/router — route any LLM through one endpoint. Multi-provider s
 ## Stack
 
 - **Runtime**: Next.js 16 (App Router), Node.js, ES Modules
-- **Language**: TypeScript 5.9 (`src/`) + JavaScript (`open-sse/`)
 - **Database**: better-sqlite3 (SQLite) — `DATA_DIR` configurable, default `~/.omniroute/`
 - **Streaming**: SSE via `open-sse` internal package
 - **Styling**: Tailwind CSS v4
@@ -22,15 +21,15 @@ All persistence uses SQLite through domain-specific modules:
 
 | Module         | Responsibility                             |
 | -------------- | ------------------------------------------ |
-| `core.ts`      | SQLite engine, migrations, WAL, encryption |
-| `providers.ts` | Provider connections & nodes               |
-| `models.ts`    | Model aliases, MITM aliases, custom models |
-| `combos.ts`    | Combo configurations                       |
-| `apiKeys.ts`   | API key management & validation            |
-| `settings.ts`  | Settings, pricing, proxy config            |
-| `backup.ts`    | Backup / restore operations                |
+| `core.js`      | SQLite engine, migrations, WAL, encryption |
+| `providers.js` | Provider connections & nodes               |
+| `models.js`    | Model aliases, MITM aliases, custom models |
+| `combos.js`    | Combo configurations                       |
+| `apiKeys.js`   | API key management & validation            |
+| `settings.js`  | Settings, pricing, proxy config            |
+| `backup.js`    | Backup / restore operations                |
 
-`src/lib/localDb.ts` is a **re-export layer only** — all 27+ consumers import from it,
+`src/lib/localDb.js` is a **re-export layer only** — all 27+ consumers import from it,
 but the real logic lives in `src/lib/db/`.
 
 ### Request Pipeline (`open-sse/`)
@@ -50,25 +49,25 @@ Translation between provider formats: `open-sse/translator/`
 ### OAuth & Tokens (`src/lib/oauth/`)
 
 18 modules handling OAuth flows, token refresh, and provider credentials.
-Default credentials are hardcoded in `src/lib/oauth/constants/oauth.ts`,
+Default credentials are hardcoded in `src/lib/oauth/constants/oauth.js`,
 overridable via env vars or `data/provider-credentials.json`.
 
 ### Supporting Systems
 
 | System                     | Location                                          |
 | -------------------------- | ------------------------------------------------- |
-| Usage tracking & analytics | `src/lib/usageDb.ts`, `src/lib/usageAnalytics.ts` |
-| Token health checks        | `src/lib/tokenHealthCheck.ts`                     |
-| Cloud sync                 | `src/lib/cloudSync.ts`                            |
-| Proxy logging              | `src/lib/proxyLogger.ts`                          |
-| Data paths resolution      | `src/lib/dataPaths.ts`                            |
+| Usage tracking & analytics | `src/lib/usageDb.js`, `src/lib/usageAnalytics.js` |
+| Token health checks        | `src/lib/tokenHealthCheck.js`                     |
+| Cloud sync                 | `src/lib/cloudSync.js`                            |
+| Proxy logging              | `src/lib/proxyLogger.js`                          |
+| Data paths resolution      | `src/lib/dataPaths.js`                            |
 
 ### Adding a New Provider
 
-1. Register in `src/shared/constants/providers.ts`
+1. Register in `src/shared/constants/providers.js`
 2. Add executor in `open-sse/executors/`
 3. Add translator rules in `open-sse/translator/` (if non-OpenAI format)
-4. Add OAuth config in `src/lib/oauth/constants/oauth.ts` (if OAuth-based)
+4. Add OAuth config in `src/lib/oauth/constants/oauth.js` (if OAuth-based)
 
 ## Review Focus
 
@@ -84,7 +83,7 @@ overridable via env vars or `data/provider-credentials.json`.
 - DB operations go through `src/lib/db/` modules, never raw SQL in routes
 - Provider requests flow through `open-sse/handlers/`
 - Translations use `open-sse/translator/` modules
-- `localDb.ts` is re-exports only — add new functions to the proper `db/*.ts` module
+- `localDb.js` is re-exports only — add new functions to the proper `db/*.js` module
 
 ### Code Quality
 

CHANGELOG.md

@@ -2,409 +2,151 @@
 
 All notable changes to OmniRoute are documented in this file.
 
-The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/),
-and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0.html).
+The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.1.0/).
 
 ---
 
-## [1.0.8] — 2026-02-21
+## [Unreleased]
 
-> ### 🔒 API Security & Windows Support
->
-> Adds API Endpoint Protection for `/models`, Windows server startup fixes, and UI improvements.
+### Added
 
-### ✨ New Features
+- Model selector with autocomplete in Chat Tester and Test Bench modes — prevents "model does not exist" errors by letting users choose available models (`c25230c`)
+- OpenAPI specification at `docs/openapi.yaml` covering all 89 API endpoints (`7abda4d`)
+- Enhanced `restart.sh` with clean build, health check, graceful shutdown (Ctrl+C), and real-time log tailing (`0db8f3d`)
 
-- **API Endpoint Protection (`/models`)** — New Security Tab settings to optionally require an API key for the `/v1/models` endpoint (returns 404 when unauthorized) and to selectively block specific providers from appearing in the models list ([#100](https://github.com/diegosouzapw/OmniRoute/issues/100), [#96](https://github.com/diegosouzapw/OmniRoute/issues/96))
-- **Interactive Provider UI** — Blocked Providers setting features an interactive chip selector with visual badges for all available AI providers
+### Fixed
 
-### 🐛 Bug Fixes
-
-- **Windows Server Startup** — Fixed `ERR_INVALID_FILE_URL_PATH` crash on Windows by safely wrapping `import.meta.url` resolution with a fallback to `process.cwd()` for globally installed npm packages ([#98](https://github.com/diegosouzapw/OmniRoute/issues/98))
-- **Combo buttons visibility** — Fixed layout overlap and tight spacing for the Quick Action buttons (Clone / Delete / Test) on the Combos page on narrower screens ([#95](https://github.com/diegosouzapw/OmniRoute/issues/95))
+- Server port collision (EADDRINUSE) during restart — now kills port before `next start` (`e4c5c0c`)
 
 ---
 
-## [1.0.7] — 2026-02-20
+## [0.0.1] — 2026-02-13
 
-> ### 🐛 Bugfix Release — OpenAI Compatibility, Custom Models & OAuth UX
->
-> Fixes three community-reported issues: stream default now follows OpenAI spec, custom OpenAI-compatible providers appear in `/v1/models`, and Google OAuth shows a clear error + tutorial for remote deployments.
+Initial public release of OmniRoute (rebranded from 9router).
 
-### 🐛 Bug Fixes
+### Added
 
-- **`stream` defaults to `false`** — Aligns with the OpenAI specification which explicitly states `stream` defaults to `false`. Previously OmniRoute defaulted to `true`, causing SSE data to be returned instead of a JSON object, breaking clients like Spacebot, OpenCode, and standard Python/Rust/Go OpenAI SDKs that don't explicitly set `stream: true` ([#89](https://github.com/diegosouzapw/OmniRoute/issues/89))
-- **Custom AI providers now appear in `/v1/models`** — OpenAI-compatible custom providers (e.g. FriendLI) whose provider ID wasn't in the built-in alias map were silently excluded from the models list even when active. Fixed by also checking the raw provider ID from the database against active connections ([#90](https://github.com/diegosouzapw/OmniRoute/issues/90))
-- **OAuth `redirect_uri_mismatch` — improved UX for remote deployments** — Google OAuth providers (Antigravity, Gemini CLI) now always use `localhost` as redirect URI matching the registered credentials. Remote-access users see a targeted amber warning with a link to the new setup guide. The token exchange error message explains the root cause and guides users to configure their own credentials ([#91](https://github.com/diegosouzapw/OmniRoute/issues/91))
+- **28 AI Providers** — OpenAI, Anthropic, Google Gemini, DeepSeek, Groq, xAI, Mistral, Perplexity, Together AI, Fireworks AI, Cerebras, Cohere, NVIDIA NIM, Nebius, GitHub Copilot, Cursor, Kiro, Kimi, MiniMax, iFlow, and more
+- **OpenAI-compatible proxy** at `/api/v1/chat/completions` with automatic format translation, load balancing, and failover
+- **Anthropic Messages API** at `/api/v1/messages` for Claude-native clients
+- **OpenAI Responses API** at `/api/v1/responses` for modern OpenAI workflows
+- **Embeddings API** at `/api/v1/embeddings` with 6 providers and 9 models
+- **Image Generation API** at `/api/v1/images/generations` with 4 providers and 9 models
+- **Format Translator** — automatic request/response conversion between OpenAI, Anthropic, Gemini, and OpenAI Responses formats
+- **Translator Playground** with 4 modes: Playground, Chat Tester, Test Bench, Live Monitor
+- **Combo Routing** — named route configurations with priority, weighted, and round-robin strategies
+- **API Key Management** — create/revoke keys with usage attribution
+- **Usage Dashboard** — analytics, call logs, request logger with API key filtering and cost tracking
+- **Provider Health Diagnostics** — structured status (runtime errors, auth failures, token refresh) with per-connection retest
+- **CLI Tools Integration** — runtime detection for Cline, Kiro, Droid, OpenClaw with backup/restore
+- **OAuth Flows** — for Cursor, Kiro, Kimi, and GitHub Copilot
+- **Docker Support** — multi-stage Dockerfile, docker-compose with 3 profiles (base, cli, host), production compose
+- **SOCKS5 Proxy** — outbound proxy support enabled by default (`ab8d752`)
+- **Unified Storage** — `DATA_DIR` / `XDG_CONFIG_HOME` resolution with auto-migration from `~/.omniroute`
+- **In-app Documentation** at `/docs` with quick start, endpoint reference, and client compatibility notes
+- **Dark Theme UI** — modern dashboard with glassmorphism, responsive layout
+- `<think>` tag parser for reasoning models (DeepSeek, Qwen)
+- Non-stream response translation for all formats
+- Secure cookie handling for LAN/reverse-proxy deployments
 
-### 📖 Documentation
+### Fixed
 
-- **OAuth em Servidor Remoto tutorial** — New README section with step-by-step guide to configure custom Google Cloud OAuth 2.0 credentials for remote/VPS/Docker deployments
-- **`.env.example` Google OAuth block** — Added prominent warning block explaining remote credential requirements with direct links to Google Cloud Console
+- OAuth re-authentication no longer creates duplicate connections (`773f117`, `510aedd`)
+- Connection test no longer corrupts valid OAuth tokens (`a2ba189`)
+- Cloud sync disabled to prevent 404 log spam (`71d132e`)
+- `.env.example` synced with current environment structure (`6bdc74b`)
+- Select dropdown dark theme inconsistency (`1bd734d`)
 
-### 📁 Files Modified
+### Dependencies
 
-| File                                   | Change                                                                                      |
-| -------------------------------------- | ------------------------------------------------------------------------------------------- |
-| `open-sse/handlers/chatCore.ts`        | `stream` defaults to `false` (was `true`) per OpenAI spec                                   |
-| `src/app/api/v1/models/route.ts`       | Added raw `providerId` check for custom models active-provider filter                       |
-| `src/shared/components/OAuthModal.tsx` | Force `localhost` redirect for Google OAuth; improved `redirect_uri_mismatch` error message |
-| `.env.example`                         | Added ⚠️ Google OAuth remote credentials block with step-by-step instructions               |
-| `README.md`                            | New "🔐 OAuth em Servidor Remoto" tutorial section                                          |
+- `actions/github-script` bumped from 7 to 8 (`f6a994a`)
+- `eslint` bumped from 9.39.2 to 10.0.0 (`ecd4aea`)
 
 ---
 
-## [1.0.6] — 2026-02-20
+## Pre-Release History (9router)
 
-> ### ✨ Provider & Combo Toggles — Strict Model Filtering
->
-> `/v1/models` now shows only models from providers with active connections. Combos and providers can be toggled on/off directly from the dashboard.
+> The following entries document the legacy 9router project before it was
+> rebranded to OmniRoute. All changes below were included in the initial
+> `0.0.1` release.
 
-### ✨ New Features
+### 0.2.75 — 2026-02-11
 
-- **Provider toggle on Providers page** — Enable/disable all connections for a provider directly from the main Providers list. Toggle is always visible, no hover needed
-- **Combo enable/disable toggle** — Each combo on the Combos page now has a toggle. Disabled combos are excluded from `/v1/models`
-- **OAuth private IP support** — Expanded localhost detection to include private/LAN IPs (`192.168.x.x`, `10.x.x.x`, `172.16-31.x.x`) for correct OAuth redirect URIs
+- API key attribution in usage/call logs with per-key analytics aggregates
+- Usage dashboard API key observability (distribution donut, filterable table)
+- In-app docs page (`/docs`) with quick start, endpoint reference, and client compatibility notes
+- Unified storage path policy (`DATA_DIR` → `XDG_CONFIG_HOME` → `~/.omniroute`)
+- Build-phase guard for `usageDb` (in-memory during `next build`)
+- LAN/reverse-proxy cookie security detection
+- Hardened Gemini 3 Flash normalization and non-stream SSE fallback parsing
+- CLI tool runtime and OAuth refresh reliability improvements
+- Provider health diagnostics with structured error types
 
-### 🐛 Bug Fixes
+### 0.2.74 — 2026-02-11
 
-- **`/v1/models` strict filtering** — Models are now shown only from providers with active, enabled connections. Previously, if no connections existed or all were disabled, all 378+ models were shown as a fallback
-- **Disabled provider models hidden** — Toggling off a provider immediately removes its models from `/v1/models`
+- Model resolution fallback fix for unprefixed models
+- GitHub Copilot dynamic endpoint selection (Codex → `/responses`)
+- Non-stream translation path for OpenAI Responses
+- Updated GitHub model catalog with compatibility aliases
 
----
+### 0.2.73 — 2026-02-09
 
-## [1.0.5] — 2026-02-20
+- Expanded provider registry from 18 → 28 providers (DeepSeek, Groq, xAI, Mistral, Perplexity, Together AI, Fireworks AI, Cerebras, Cohere, NVIDIA NIM)
+- `/v1/embeddings` endpoint with 6 providers and 9 models
+- `/v1/images/generations` endpoint with 4 providers and 9 models
+- `<think>` tag parser for reasoning models
+- Available Endpoints card on Endpoint page (127 chat, 9 embedding, 9 image models)
 
-> ### 🐛 Hotfix — Model Filtering & Docker DATA_DIR
->
-> Filters all model types in `/v1/models` by active providers and fixes Docker data directory mismatch.
+### 0.2.72 — 2026-02-08
 
-### 🐛 Bug Fixes
+- Split Kimi into dual providers: `kimi` (OpenAI-compatible) and `kimi-coding` (Moonshot API)
+- Hybrid CLI runtime support with Docker profiles (`runner-base`, `runner-cli`)
+- Hardened cloud sync/auth flow with SSE fallback
 
-- **`/v1/models` full filtering** — Embedding, image, rerank, audio, and moderation models are now filtered by active provider connections, matching chat model behavior. Providers like Together AI no longer appear without a configured API key (#88)
-- **Docker `DATA_DIR`** — Added `ENV DATA_DIR=/app/data` to Dockerfile and `docker-compose.yml` ensuring the volume mount always matches the app data directory — prevents empty database on container recreation
+### 0.2.66 — 2026-02-06
 
----
+- Cursor provider end-to-end support with OAuth import flow
+- `requireLogin` control and `hasPassword` state handling
+- Usage/quota UX improvements
+- Model support for custom providers
+- Codex updates (GPT-5.3, thinking levels), Claude Opus 4.6, MiniMax Coding
+- Auto-validation for provider API keys
 
-## [1.0.4] — 2026-02-19
+### 0.2.56 — 2026-02-04
 
-> ### 🔧 Provider Filtering, OAuth Proxy Fix & Documentation
->
-> Dashboard model filtering by active providers, provider enable/disable visual indicators, OAuth login fix for nginx reverse proxy, and LLM onboarding documentation.
+- Anthropic-compatible provider support
+- Provider icons across dashboard
+- Enhanced usage tracking pipeline
 
-### ✨ Features
+### 0.2.52 — 2026-02-02
 
-- **API Models filtering** — `GET /api/models` now returns only models from active providers; use `?all=true` for all models (#85)
-- **Provider disabled indicator** — Provider cards show ⏸ "Disabled" badge with reduced opacity when all connections are inactive (#85)
-- **`llm.txt`** — Comprehensive LLM onboarding file with project overview, architecture, flows, and conventions (#84)
-- **WhatsApp Community** — Added WhatsApp group link to README badges and Support section
+- Codex Cursor compatibility and Next.js 16 proxy migration
+- OpenAI-compatible provider nodes (CRUD/validation/test)
+- Token expiration and key-validity checks
+- Non-streaming response translation for multiple formats
+- Kiro OAuth wiring and token refresh support
 
-### 🐛 Bug Fixes
+### 0.2.43 — 2026-01-27
 
-- **OAuth behind nginx** — Fixed OAuth login failing when behind a reverse proxy by using `window.location.origin` for redirect URI instead of hardcoded `localhost` (#86)
-- **`NEXT_PUBLIC_BASE_URL` for OAuth** — Documented env var usage as redirect URI override for proxy deployments (#86)
+- Fixed CLI tools model selection
+- Fixed Kiro translator request handling
 
-### 📁 Files Added
+### 0.2.36 — 2026-01-19
 
-| File      | Purpose                                            |
-| --------- | -------------------------------------------------- |
-| `llm.txt` | LLM and contributor onboarding (llms.txt standard) |
+- Usage dashboard page
+- Outbound proxy support in Open SSE fetch pipeline
+- Fixed combo fallback behavior
 
-### 📁 Files Modified
+### 0.2.31 — 2026-01-18
 
-| File                                               | Change                                                           |
-| -------------------------------------------------- | ---------------------------------------------------------------- |
-| `src/app/api/models/route.ts`                      | Filter by active providers, `?all=true` param, `available` field |
-| `src/app/(dashboard)/dashboard/providers/page.tsx` | `allDisabled` detection + ⏸ badge + opacity-50 on provider cards |
-| `src/shared/components/OAuthModal.tsx`             | Proxy-aware redirect URI using `window.location.origin`          |
-| `.env.example`                                     | Documented `NEXT_PUBLIC_BASE_URL` for OAuth behind proxy         |
+- Fixed Kiro token refresh and executor behavior
+- Fixed Kiro request translation handling
 
----
+### 0.2.27 — 2026-01-15
 
-## [1.0.3] — 2026-02-19
+- Added Kiro provider support with OAuth flow
+- Fixed Codex provider behavior
 
-> ### 📊 Logs Dashboard & Real-Time Console Viewer
->
-> Unified logs interface with real-time console log viewer, file-based logging via console interception, and server initialization improvements.
+### 0.2.21 — 2026-01-12
 
-### ✨ Features
-
-- **Logs Dashboard** — Consolidated 4-tab page at `/dashboard/logs` with Request Logs, Proxy Logs, Audit Logs, and Console tabs
-- **Console Log Viewer** — Terminal-style real-time log viewer with color-coded log levels, auto-scroll, search/filtering, level filter, and 5-second polling
-- **Console Interceptor** — Monkey-patches `console.log/info/warn/error/debug` at server start to capture all application output as JSON lines to `logs/application/app.log`
-- **Log Rotation** — Size-based rotation and retention-based cleanup for log files
-
-### 🔧 Improvements
-
-- **Instrumentation consolidation** — Moved `initAuditLog()`, `cleanupExpiredLogs()`, and console interceptor initialization to Next.js `instrumentation.ts` (runs on both dev and prod server start)
-- **Structured Logger file output** — `structuredLogger.ts` now also appends JSON log entries to the log file
-- **Pino Logger fix** — Fixed broken mix of pino `transport` targets + manual `createWriteStream`; now uses `pino/file` transport targets exclusively with absolute paths
-
-### 🗂️ Files Added
-
-| File                                                 | Purpose                                                           |
-| ---------------------------------------------------- | ----------------------------------------------------------------- |
-| `src/app/(dashboard)/dashboard/logs/page.tsx`        | Tabbed Logs Dashboard page                                        |
-| `src/app/(dashboard)/dashboard/logs/AuditLogTab.tsx` | Audit log tab component extracted from standalone page            |
-| `src/shared/components/ConsoleLogViewer.tsx`         | Terminal-style real-time log viewer                               |
-| `src/app/api/logs/console/route.ts`                  | API endpoint to read log file (filters last 1h, level, component) |
-| `src/lib/consoleInterceptor.ts`                      | Console method monkey-patching for file capture                   |
-| `src/lib/logRotation.ts`                             | Log rotation by size and cleanup by retention days                |
-
-### 🗂️ Files Modified
-
-| File                                    | Change                                                                          |
-| --------------------------------------- | ------------------------------------------------------------------------------- |
-| `src/shared/components/Sidebar.tsx`     | Nav: "Request Logs" → "Logs" with `description` icon                            |
-| `src/shared/components/Breadcrumbs.tsx` | Added breadcrumb labels for `logs`, `audit-log`, `console`                      |
-| `src/instrumentation.ts`                | Added console interceptor + audit log init + expired log cleanup                |
-| `src/server-init.ts`                    | Added console interceptor import (backup init)                                  |
-| `src/shared/utils/logger.ts`            | Fixed pino file transport using `pino/file` targets                             |
-| `src/shared/utils/structuredLogger.ts`  | Added `appendFileSync` file writing + log file config                           |
-| `.env.example`                          | Added `LOG_TO_FILE`, `LOG_FILE_PATH`, `LOG_MAX_FILE_SIZE`, `LOG_RETENTION_DAYS` |
-
-### ⚙️ Configuration
-
-New environment variables:
-
-| Variable             | Default                    | Description                   |
-| -------------------- | -------------------------- | ----------------------------- |
-| `LOG_TO_FILE`        | `true`                     | Enable/disable file logging   |
-| `LOG_FILE_PATH`      | `logs/application/app.log` | Log file path                 |
-| `LOG_MAX_FILE_SIZE`  | `50M`                      | Max file size before rotation |
-| `LOG_RETENTION_DAYS` | `7`                        | Days to retain old log files  |
-
----
-
-## [1.0.2] — 2026-02-18
-
-> ### 🔒 Security Hardening, Architecture Improvements & UX Polish
->
-> Comprehensive audit-driven improvements across security, architecture, testing, and user experience.
-
-### 🛡️ Security (Phase 0)
-
-- **Auth guard** — API route protection via `withAuth` middleware for all dashboard routes
-- **CSRF protection** — Token-based CSRF guard for all state-changing API routes
-- **Request payload validation** — Zod schemas for provider, combo, key, and settings endpoints
-- **Prompt injection guard** — Input sanitization against malicious prompt patterns
-- **Body size guard** — Route-specific body size limits with dedicated audio upload threshold
-- **Rate limiter** — Per-IP rate limiting with configurable windows and thresholds
-
-### 🏗️ Architecture (Phase 1–2)
-
-- **DI container** — Simple dependency injection container for service registration
-- **Policy engine** — Consolidated `PolicyEngine` for routing, security, and rate limiting
-- **SQLite migration** — Database migration system with versioned migration runner
-- **Graceful shutdown** — Clean server shutdown with connection draining
-- **TypeScript fixes** — Resolved all `tsc` errors; removed redundant `@ts-check` directives
-- **Pipeline decomposition** — `handleSingleModelChat` decomposed into composable pipeline stages
-- **Prompt template versioning** — Version-tracked prompt templates with rollback support
-- **Eval scheduling** — Automated evaluation suite scheduling with cron-based runner
-- **Plugin architecture** — Extensible plugin system for custom middleware and handlers
-
-### 🧪 Testing & CI (Phase 2)
-
-- **Coverage thresholds** — Jest coverage thresholds enforced in CI (368 tests passing)
-- **Proxy pipeline integration tests** — End-to-end tests for the proxy request pipeline
-- **CI audit workflow** — npm audit and security scanning in GitHub Actions
-- **k6 load tests** — Performance testing with ramping VUs and custom metrics
-
-### ✨ UX & Polish (Phase 3–4)
-
-- **Session management** — Session info card with login time, age, user agent, and logout
-- **Focus indicators** — Global `:focus-visible` styles and `--focus-ring` CSS utility
-- **Audit log viewer** — Security event audit log with structured data display
-- **Dashboard cleanup** — Removed unused files, fixed Quick Start links to Endpoint page
-- **Documentation** — Troubleshooting guide, deployment improvements
-
----
-
-## [1.1.0] — 2026-02-18
-
-> ### 🔧 API Compatibility & SDK Hardening
->
-> Response sanitization, role normalization, and structured output improvements for strict OpenAI SDK compatibility and cross-provider robustness.
-
-### 🛡️ Response Sanitization (NEW)
-
-- **Response sanitizer module** — New `responseSanitizer.ts` strips non-standard fields (`x_groq`, `usage_breakdown`, `service_tier`, etc.) from all OpenAI-format provider responses, fixing OpenAI Python SDK v1.83+ Pydantic validation failures that returned raw strings instead of parsed `ChatCompletion` objects
-- **Streaming chunk sanitization** — Passthrough streaming mode now sanitizes each SSE chunk in real-time via `sanitizeStreamingChunk()`, ensuring strict `chat.completion.chunk` schema compliance
-- **ID/Object/Usage normalization** — Ensures `id`, `object`, `created`, `model`, `choices`, and `usage` fields always exist with correct types
-- **Usage field cleanup** — Strips non-standard usage sub-fields, keeps only `prompt_tokens`, `completion_tokens`, `total_tokens`, and OpenAI detail fields
-
-### 🧠 Think Tag Extraction (NEW)
-
-- **`<think>` tag extraction** — Automatically extracts `<think>...</think>` blocks from thinking model responses (DeepSeek R1, Kimi K2 Thinking, etc.) into OpenAI's standard `reasoning_content` field
-- **Streaming think-tag stripping** — Real-time `<think>` extraction in passthrough SSE stream, preventing JSON parsing errors in downstream tools
-- **Preserves native reasoning** — Providers that already send `reasoning_content` natively (e.g., OpenAI o1) are not overwritten
-
-### 🔄 Role Normalization (NEW)
-
-- **`developer` → `system` conversion** — OpenAI's new `developer` role is automatically converted to `system` for all non-OpenAI providers (Claude, Gemini, Kiro, etc.)
-- **`system` → `user` merging** — For models that reject the `system` role (GLM, ERNIE), system messages are intelligently merged into the first user message with clear delimiters
-- **Model-aware normalization** — Uses model name prefix matching (`glm-*`, `ernie-*`) for compatibility decisions, avoiding hardcoded provider-level flags
-
-### 📐 Structured Output for Gemini (NEW)
-
-- **`response_format` → Gemini conversion** — OpenAI's `json_schema` structured output is now translated to Gemini's `responseMimeType` + `responseSchema` in the translator pipeline
-- **`json_object` support** — `response_format: { type: "json_object" }` maps to Gemini's `application/json` MIME type
-- **Schema cleanup** — Automatically removes unsupported JSON Schema keywords (`$schema`, `additionalProperties`) for Gemini compatibility
-
-### 📁 Files Added
-
-| File                                     | Purpose                                                                |
-| ---------------------------------------- | ---------------------------------------------------------------------- |
-| `open-sse/handlers/responseSanitizer.ts` | Response field stripping, think-tag extraction, ID/usage normalization |
-| `open-sse/services/roleNormalizer.ts`    | Developer→system, system→user role conversion pipeline                 |
-
-### 📁 Files Modified
-
-| File                                              | Change                                                                          |
-| ------------------------------------------------- | ------------------------------------------------------------------------------- |
-| `open-sse/handlers/chatCore.ts`                   | Integrated response sanitizer for non-streaming OpenAI responses                |
-| `open-sse/utils/stream.ts`                        | Integrated streaming chunk sanitizer + think-tag extraction in passthrough mode |
-| `open-sse/translator/index.ts`                    | Integrated role normalizer into the request translation pipeline                |
-| `open-sse/translator/request/openai-to-gemini.ts` | Added `response_format` → `responseMimeType`/`responseSchema` conversion        |
-
----
-
-## [1.0.0] — 2026-02-18
-
-> ### 🎉 First Major Release — OmniRoute 1.0
->
-> OmniRoute is an intelligent API gateway that unifies 20+ AI providers behind a single OpenAI-compatible endpoint. This release represents the culmination of the entire development effort — from initial prototype to production-ready platform.
-
-### 🧠 Core Routing & Intelligence
-
-- **Smart 4-tier fallback** — Auto-routing: Subscription → Cheap → Free → Emergency
-- **6 routing strategies** — Fill First, Round Robin, Power-of-Two-Choices, Random, Least Used, Cost Optimized
-- **Semantic caching** — Auto-cache responses for deduplication with configurable TTL
-- **Request idempotency** — Prevent duplicate processing of identical requests
-- **Thinking budget validation** — Control reasoning token allocation per request
-- **System prompt injection** — Configurable global system prompts for all requests
-
-### 🔌 Providers & Models
-
-- **20+ AI providers** — OpenAI, Claude (Anthropic), Gemini, GitHub Copilot, DeepSeek, Groq, xAI, Mistral, Qwen, iFlow, Kiro, OpenRouter, GLM, MiniMax, Kimi, NVIDIA NIM, and more
-- **Multi-account support** — Multiple accounts per provider with automatic rotation
-- **OAuth 2.0 (PKCE)** — Automatic token management and refresh for Claude Code, Codex, Gemini CLI, Copilot, Kiro
-- **Auto token refresh** — Background refresh with expiry detection and unrecoverable error handling
-- **Model import** — Import models from API-compatible passthrough providers
-- **OpenAI-compatible validation** — Fallback validation via chat completions for providers without `/models` endpoint
-- **TLS fingerprint spoofing** — Browser-like TLS fingerprinting via `wreq-js` to bypass bot detection
-
-### 🔄 Format Translation
-
-- **Multi-format translation** — Seamless OpenAI ↔ Claude ↔ Gemini ↔ OpenAI Responses API conversion
-- **Translator Playground** — 4 interactive modes:
-  - **Playground** — Test format translations between any provider formats
-  - **Chat Tester** — Send real requests through the proxy with visual response rendering
-  - **Test Bench** — Automated batch testing across multiple providers
-  - **Live Monitor** — Real-time stream of active proxy requests and translations
-
-### 🎯 Combos & Fallback Chains
-
-- **Custom combos** — Create model combinations with multi-provider fallback chains
-- **6 combo balancing strategies** — Fill First, Round Robin, Random, Least Used, P2C, Cost Optimized
-- **Combo circuit breaker** — Auto-disable failing providers within a combo chain
-
-### 🛡️ Resilience & Security
-
-- **Circuit breakers** — Auto-recovery with configurable thresholds and cooldown periods
-- **Exponential backoff** — Progressive retry delays for failed requests
-- **Anti-thundering herd** — Mutex-based protection against concurrent retry storms
-- **Rate limit detection** — Per-provider RPM, min gap, and max concurrent request tracking
-- **Editable rate limits** — Configurable defaults via Settings → Resilience with persistence
-- **Prompt injection guard** — Input sanitization for malicious prompt patterns
-- **PII redaction** — Automatic detection and masking of personally identifiable information
-- **AES-256-GCM encryption** — Credential encryption at rest
-- **IP access control** — Whitelist/blacklist IP filtering
-- **SOCKS5 proxy support** — Outbound proxy for upstream provider calls
-
-### 📊 Observability & Analytics
-
-- **Analytics dashboard** — Recharts-based SVG charts: stat cards, model usage bar chart, provider breakdown table with success rates and latency
-- **Real-time health monitoring** — Provider health, rate limits, latency telemetry
-- **Request logs** — Dedicated page with SQLite-persisted proxy request/response logs
-- **Limits & Quotas** — Separate dashboard for quota monitoring with reset countdowns
-- **Cost analytics** — Token cost tracking and budget management per provider
-- **Request telemetry** — Correlation IDs, structured logging, request timing
-
-### 💾 Database & Backup
-
-- **Dual database** — LowDB (JSON) for config + SQLite for domain state and proxy logs
-- **Export database** — `GET /api/db-backups/export` — Download SQLite database file
-- **Export all** — `GET /api/db-backups/exportAll` — Full backup as `.tar.gz` archive (DB + settings + combos + providers + masked API keys)
-- **Import database** — `POST /api/db-backups/import` — Upload and restore with validation, integrity check, and pre-import backup
-- **Automatic backups** — Configurable backup schedule with retention
-- **Storage health** — Dashboard widget with database size, path, and backup status
-
-### 🖥️ Dashboard & UI
-
-- **Full dashboard** — Provider management, analytics, health monitoring, settings, CLI tools
-- **9 dashboard sections** — Providers, Combos, Analytics, Health, Translator, Settings, CLI Tools, Usage, Endpoint
-- **Settings restructure** — 6 tabs: Security, Routing, Resilience, AI, System/Storage, Advanced
-- **Shared UI component library** — Reusable components (Avatar, Badge, Button, Card, DataTable, Modal, etc.)
-- **Dark/Light/System theme** — Persistent theme selection with system preference detection
-- **Agent showcase grid** — Visual grid of 10 AI coding agents in README header
-- **Provider logos** — Logo assets for all supported agents and providers
-- **Red shield badges** — Styled badge icons across all documentation
-
-### ☁️ Deployment & Infrastructure
-
-- **Docker support** — Multi-stage Dockerfile with `base` and `cli` profiles
-- **Docker Hub** — `diegosouzapw/omniroute` with `latest` and versioned tags
-- **Docker CI/CD** — GitHub Actions auto-build and push on release
-- **npm CLI package** — `npx omniroute` with auto-launch
-- **npm CI/CD** — GitHub Actions auto-publish to npm on release
-- **Akamai VM deployment** — Production deployment on Nanode 1GB with nginx reverse proxy
-- **Cloud sync** — Sync configuration across devices via Cloudflare Worker
-- **Edge compatibility** — Native `crypto.randomUUID()` for Cloudflare Workers
-
-### 🧪 Testing & Quality
-
-- **100% TypeScript** — Full migration of `src/` (200+ files) and `open-sse/` (94 files) — zero `@ts-ignore`, zero TypeScript errors
-- **CI/CD pipeline** — GitHub Actions for lint, build, test, npm publish, Docker publish
-- **Unit tests** — 20+ test suites covering domain logic, security, caching, routing
-- **E2E tests** — Playwright specs for API, navigation, and responsive behavior
-- **LLM evaluations** — Golden set testing framework with 4 match strategies (`exact`, `contains`, `regex`, `custom`)
-- **Security tests** — CLI runtime, Docker hardening, cloud sync, and OpenAI compatibility
-
-### 📖 Documentation
-
-- **8 language READMEs** — English, Portuguese (pt-BR), Spanish, Russian, Chinese (zh-CN), German, French, Italian
-- **VM Deployment Guide** — Complete guide (VM + Docker + nginx + Cloudflare + security)
-- **Features Gallery** — 9 dashboard screenshots with descriptions
-- **API Reference** — Full endpoint documentation including backup/export/import
-- **User Guide** — Step-by-step setup, configuration, and usage instructions
-- **Architecture docs** — System design, component decomposition, ADRs
-- **OpenAPI specification** — Machine-readable API documentation
-- **Troubleshooting guide** — Common issues and solutions
-- **Security policy** — `SECURITY.md` with vulnerability reporting via GitHub Security Advisories
-- **Roadmap** — 150+ planned features across 6 categories
-
-### 🔌 API Endpoints
-
-- `/v1/chat/completions` — OpenAI-compatible chat endpoint with format translation
-- `/v1/embeddings` — Embedding generation
-- `/v1/images/generations` — Image generation
-- `/v1/models` — Model listing with provider filtering
-- `/v1/rerank` — Re-ranking endpoint
-- `/v1/audio/*` — Audio transcription and translation
-- `/v1/moderations` — Content moderation
-- `/api/db-backups/export` — Database export
-- `/api/db-backups/exportAll` — Full archive export
-- `/api/db-backups/import` — Database import with validation
-- 30+ dashboard API routes for providers, combos, settings, analytics, health, CLI tools
-
----
-
-[1.0.7]: https://github.com/diegosouzapw/OmniRoute/releases/tag/v1.0.7
-[1.0.6]: https://github.com/diegosouzapw/OmniRoute/releases/tag/v1.0.6
-[1.0.5]: https://github.com/diegosouzapw/OmniRoute/releases/tag/v1.0.5
-[1.0.4]: https://github.com/diegosouzapw/OmniRoute/releases/tag/v1.0.4
-[1.1.0]: https://github.com/diegosouzapw/OmniRoute/releases/tag/v1.1.0
-[1.0.3]: https://github.com/diegosouzapw/OmniRoute/releases/tag/v1.0.3
-[1.0.2]: https://github.com/diegosouzapw/OmniRoute/releases/tag/v1.0.2
-[1.0.0]: https://github.com/diegosouzapw/OmniRoute/releases/tag/v1.0.0
+- Initial README and project setup

CONTRIBUTING.md

@@ -1,273 +0,0 @@
-# Contributing to OmniRoute
-
-Thank you for your interest in contributing! This guide covers everything you need to get started.
-
----
-
-## Development Setup
-
-### Prerequisites
-
-- **Node.js** 20+ (recommended: 22 LTS)
-- **npm** 10+
-- **Git**
-
-### Clone & Install
-
-```bash
-git clone https://github.com/diegosouzapw/OmniRoute.git
-cd OmniRoute
-npm install
-```
-
-### Environment Variables
-
-```bash
-# Create your .env from the template
-cp .env.example .env
-
-# Generate required secrets
-echo "JWT_SECRET=$(openssl rand -base64 48)" >> .env
-echo "API_KEY_SECRET=$(openssl rand -hex 32)" >> .env
-```
-
-Key variables for development:
-
-| Variable               | Development Default     | Description               |
-| ---------------------- | ----------------------- | ------------------------- |
-| `PORT`                 | `3000`                  | Server port               |
-| `NEXT_PUBLIC_BASE_URL` | `http://localhost:3000` | Base URL for frontend     |
-| `JWT_SECRET`           | (generate above)        | JWT signing secret        |
-| `INITIAL_PASSWORD`     | `123456`                | First login password      |
-| `ENABLE_REQUEST_LOGS`  | `false`                 | Enable debug request logs |
-
-### Running Locally
-
-```bash
-# Development mode (hot reload)
-npm run dev
-
-# Production build
-npm run build
-npm run start
-
-# Common port configuration
-PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev
-```
-
-Default URLs:
-
-- **Dashboard**: `http://localhost:3000/dashboard`
-- **API**: `http://localhost:3000/v1`
-
----
-
-## Git Workflow
-
-> ⚠️ **NEVER commit directly to `main`.** Always use feature branches.
-
-```bash
-git checkout -b feat/your-feature-name
-# ... make changes ...
-git commit -m "feat: describe your change"
-git push -u origin feat/your-feature-name
-# Open a Pull Request on GitHub
-```
-
-### Branch Naming
-
-| Prefix      | Purpose                   |
-| ----------- | ------------------------- |
-| `feat/`     | New features              |
-| `fix/`      | Bug fixes                 |
-| `refactor/` | Code restructuring        |
-| `docs/`     | Documentation changes     |
-| `test/`     | Test additions/fixes      |
-| `chore/`    | Tooling, CI, dependencies |
-
-### Commit Messages
-
-Follow [Conventional Commits](https://www.conventionalcommits.org/):
-
-```
-feat: add circuit breaker for provider calls
-fix: resolve JWT secret validation edge case
-docs: update SECURITY.md with PII protection
-test: add observability unit tests
-refactor(db): consolidate rate limit tables
-```
-
-Scopes: `db`, `sse`, `oauth`, `dashboard`, `api`, `cli`, `docker`, `ci`.
-
----
-
-## Running Tests
-
-```bash
-# All unit tests
-npm test
-npm run test:unit
-
-# Specific test suites
-npm run test:security     # Security tests
-npm run test:fixes        # Fix verification tests
-
-# With coverage
-npm run test:coverage
-
-# E2E tests (requires Playwright)
-npm run test:e2e
-
-# Lint + format check
-npm run lint
-npm run check
-```
-
-Current test status: **368+ unit tests** covering:
-
-- Provider translators and format conversion
-- Rate limiting, circuit breaker, and resilience
-- Semantic cache, idempotency, progress tracking
-- Database operations and schema
-- OAuth flows and authentication
-- API endpoint validation
-
----
-
-## Code Style
-
-- **ESLint** — Run `npm run lint` before committing
-- **Prettier** — Auto-formatted via `lint-staged` on commit
-- **TypeScript** — All `src/` code uses `.ts`/`.tsx`; document with TSDoc (`@param`, `@returns`, `@throws`)
-- **No `eval()`** — ESLint enforces `no-eval`, `no-implied-eval`, `no-new-func`
-- **Zod validation** — Use Zod schemas for API input validation
-
----
-
-## Project Structure
-
-```
-src/                        # TypeScript (.ts / .tsx)
-├── app/                    # Next.js App Router
-│   ├── (dashboard)/        # Dashboard pages (.tsx)
-│   ├── api/                # API routes (.ts)
-│   └── login/              # Auth pages (.tsx)
-├── domain/                 # Domain types and response helpers (.ts)
-├── lib/                    # Core business logic (.ts)
-│   ├── db/                 # SQLite database layer
-│   ├── oauth/              # OAuth services per provider
-│   ├── cacheLayer.ts       # LRU cache
-│   ├── semanticCache.ts    # Semantic response cache
-│   ├── idempotencyLayer.ts # Request deduplication
-│   └── localDb.ts          # Settings facade (LowDB for config, SQLite for domain data)
-├── shared/
-│   ├── components/         # React components (.tsx)
-│   ├── middleware/          # Correlation IDs, etc.
-│   ├── utils/              # Circuit breaker, sanitizer, etc.
-│   └── validation/         # Zod schemas
-└── sse/                    # SSE chat handlers (.ts)
-
-open-sse/                   # @omniroute/open-sse workspace (JavaScript)
-├── handlers/               # chatCore.js — main request handler
-├── services/               # Rate limit, fallback
-├── translators/            # Format converters (OpenAI ↔ Claude ↔ Gemini)
-└── utils/                  # Progress tracker, stream helpers
-
-tests/
-├── unit/                   # Node.js test runner (.test.mjs)
-└── e2e/                    # Playwright tests
-
-docs/                       # Documentation
-├── USER_GUIDE.md           # Provider setup, CLI integration
-├── API_REFERENCE.md        # All endpoints
-├── TROUBLESHOOTING.md      # Common issues
-├── ARCHITECTURE.md         # System architecture
-└── adr/                    # Architecture Decision Records
-```
-
----
-
-## Adding a New Provider
-
-### Step 1: OAuth Service (if using OAuth)
-
-Create `src/lib/oauth/services/your-provider.ts` extending `OAuthService`:
-
-```typescript
-import { OAuthService } from "../OAuthService";
-
-export class YourProviderService extends OAuthService {
-  constructor() {
-    super({
-      name: "your-provider",
-      authUrl: "https://provider.com/oauth/authorize",
-      tokenUrl: "https://provider.com/oauth/token",
-      clientId: "...",
-      scopes: ["..."],
-    });
-  }
-}
-```
-
-### Step 2: Register Provider
-
-Add to `src/lib/oauth/providers.ts`:
-
-```typescript
-import { YourProviderService } from "./services/your-provider";
-// Add to the providers map
-```
-
-### Step 3: Add Constants
-
-Add provider constants in `src/lib/providerConstants.ts`:
-
-- Provider prefix (e.g., `yp/`)
-- Default models
-- Pricing info
-
-### Step 4: Add Translator (if non-OpenAI format)
-
-Create translator in `open-sse/translators/` if the provider uses a custom API format.
-
-### Step 5: Add Timeout
-
-Add request timeout configuration in `src/shared/utils/requestTimeout.ts`.
-
-### Step 6: Add Tests
-
-Write unit tests in `tests/unit/` covering at minimum:
-
-- Provider registration
-- Request/response translation
-- Error handling
-
----
-
-## Pull Request Checklist
-
-- [ ] Tests pass (`npm test`)
-- [ ] Linting passes (`npm run lint`)
-- [ ] Build succeeds (`npm run build`)
-- [ ] TypeScript types added for new public functions and interfaces
-- [ ] No hardcoded secrets or fallback values
-- [ ] CHANGELOG updated (if user-facing change)
-- [ ] Documentation updated (if applicable)
-
----
-
-## Releasing
-
-When a new GitHub Release is created (e.g. `v0.4.0`), the package is **automatically published to npm** via GitHub Actions:
-
-```bash
-gh release create v0.4.0 --title "v0.4.0" --generate-notes
-```
-
----
-
-## Getting Help
-
-- **Architecture**: See [`docs/ARCHITECTURE.md`](docs/ARCHITECTURE.md)
-- **Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
-- **ADRs**: See `docs/adr/` for architectural decision records

Dockerfile

@@ -12,7 +12,6 @@ WORKDIR /app
 
 LABEL org.opencontainers.image.title="omniroute" \
   org.opencontainers.image.description="Unified AI proxy — route any LLM through one endpoint" \
-  org.opencontainers.image.url="https://omniroute.online" \
   org.opencontainers.image.source="https://github.com/diegosouzapw/OmniRoute" \
   org.opencontainers.image.licenses="MIT"
 
@@ -20,8 +19,7 @@ ENV NODE_ENV=production
 ENV PORT=20128
 ENV HOSTNAME=0.0.0.0
 
-# Data directory inside Docker — must match the volume mount in docker-compose.yml
-ENV DATA_DIR=/app/data
+# Runtime writable location for localDb when DATA_DIR is configured to /app/data
 RUN mkdir -p /app/data
 
 COPY --from=builder /app/public ./public

README.es.md

@@ -1,999 +0,0 @@
-<div align="center">
-  <img src="./docs/screenshots/MainOmniRoute.png" alt="OmniRoute Dashboard" width="800"/>
-  
-  # 🚀 OmniRoute — El Gateway de IA Gratuito
-
-### Nunca dejes de programar. Enrutamiento inteligente hacia **modelos de IA GRATUITOS y económicos** con fallback automático.
-
-_Tu proxy de API universal — un endpoint, 36+ proveedores, cero tiempo de inactividad._
-
-**Chat Completions • Embeddings • Generación de Imágenes • Audio • Reranking • 100% TypeScript**
-
----
-
-### 🤖 Proveedor de IA Gratuito para tus agentes de programación favoritos
-
-_Conecta cualquier IDE o herramienta CLI con IA a través de OmniRoute — gateway de API gratuito para programación ilimitada._
-
-  <table>
-    <tr>
-      <td align="center" width="110">
-        <a href="https://github.com/cline/cline">
-          <img src="./public/providers/openclaw.png" alt="OpenClaw" width="48"/><br/>
-          <b>OpenClaw</b>
-        </a><br/>
-        <sub>⭐ 205K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/HKUDS/nanobot">
-          <img src="./public/providers/nanobot.png" alt="NanoBot" width="48"/><br/>
-          <b>NanoBot</b>
-        </a><br/>
-        <sub>⭐ 20.9K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/sipeed/picoclaw">
-          <img src="./public/providers/picoclaw.jpg" alt="PicoClaw" width="48"/><br/>
-          <b>PicoClaw</b>
-        </a><br/>
-        <sub>⭐ 14.6K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/zeroclaw-labs/zeroclaw">
-          <img src="./public/providers/zeroclaw.png" alt="ZeroClaw" width="48"/><br/>
-          <b>ZeroClaw</b>
-        </a><br/>
-        <sub>⭐ 9.9K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/nearai/ironclaw">
-          <img src="./public/providers/ironclaw.png" alt="IronClaw" width="48"/><br/>
-          <b>IronClaw</b>
-        </a><br/>
-        <sub>⭐ 2.1K</sub>
-      </td>
-    </tr>
-    <tr>
-      <td align="center" width="110">
-        <a href="https://github.com/anomalyco/opencode">
-          <img src="./public/providers/opencode.svg" alt="OpenCode" width="48"/><br/>
-          <b>OpenCode</b>
-        </a><br/>
-        <sub>⭐ 106K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/openai/codex">
-          <img src="./public/providers/codex.png" alt="Codex CLI" width="48"/><br/>
-          <b>Codex CLI</b>
-        </a><br/>
-        <sub>⭐ 60.8K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/anthropics/claude-code">
-          <img src="./public/providers/claude.png" alt="Claude Code" width="48"/><br/>
-          <b>Claude Code</b>
-        </a><br/>
-        <sub>⭐ 67.3K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/google-gemini/gemini-cli">
-          <img src="./public/providers/gemini-cli.png" alt="Gemini CLI" width="48"/><br/>
-          <b>Gemini CLI</b>
-        </a><br/>
-        <sub>⭐ 94.7K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/Kilo-Org/kilocode">
-          <img src="./public/providers/kilocode.png" alt="Kilo Code" width="48"/><br/>
-          <b>Kilo Code</b>
-        </a><br/>
-        <sub>⭐ 15.5K</sub>
-      </td>
-    </tr>
-  </table>
-
-<sub>📡 Todos los agentes se conectan vía <code>http://localhost:20128/v1</code> o <code>http://cloud.omniroute.online/v1</code> — una configuración, modelos y cuota ilimitados</sub>
-
----
-
-[![npm version](https://img.shields.io/npm/v/omniroute?color=cb3837&logo=npm)](https://www.npmjs.com/package/omniroute)
-[![Docker Hub](https://img.shields.io/docker/v/diegosouzapw/omniroute?label=Docker%20Hub&logo=docker&color=2496ED)](https://hub.docker.com/r/diegosouzapw/omniroute)
-[![License](https://img.shields.io/github/license/diegosouzapw/OmniRoute)](https://github.com/diegosouzapw/OmniRoute/blob/main/LICENSE)
-[![Website](https://img.shields.io/badge/Website-omniroute.online-blue?logo=google-chrome&logoColor=white)](https://omniroute.online)
-[![WhatsApp](https://img.shields.io/badge/WhatsApp-Community-25D366?logo=whatsapp&logoColor=white)](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-
-[🌐 Website](https://omniroute.online) • [🚀 Inicio Rápido](#-inicio-rápido) • [💡 Características](#-características-principales) • [📖 Docs](#-documentación) • [💰 Precios](#-precios-resumidos)
-
-🌐 **Disponible en:** [English](README.md) | [Português](README.pt-BR.md) | [Español](README.es.md) | [Русский](README.ru.md) | [中文](README.zh-CN.md) | [Deutsch](README.de.md) | [Français](README.fr.md) | [Italiano](README.it.md)
-
-</div>
-
----
-
-## 🤔 ¿Por qué OmniRoute?
-
-**Deja de desperdiciar dinero y chocar con límites:**
-
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> La cuota de suscripción expira sin usar cada mes
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Los límites de tasa te detienen en medio de la programación
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> APIs caras ($20-50/mes por proveedor)
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Cambiar manualmente entre proveedores
-
-**OmniRoute resuelve esto:**
-
-- ✅ **Maximiza suscripciones** - Rastrea cuotas, usa cada bit antes del reset
-- ✅ **Fallback automático** - Suscripción → API Key → Barato → Gratuito, cero tiempo de inactividad
-- ✅ **Multi-cuenta** - Round-robin entre cuentas por proveedor
-- ✅ **Universal** - Funciona con Claude Code, Codex, Gemini CLI, Cursor, Cline, OpenClaw, cualquier herramienta CLI
-
----
-
-## 🔄 Cómo Funciona
-
-```
-┌─────────────┐
-│  Tu CLI     │  (Claude Code, Codex, Gemini CLI, OpenClaw, Cursor, Cline...)
-│   Tool      │
-└──────┬──────┘
-       │ http://localhost:20128/v1
-       ↓
-┌─────────────────────────────────────────┐
-│        OmniRoute (Enrutador Inteligente)  │
-│  • Traducción de formato (OpenAI ↔ Claude) │
-│  • Rastreo de cuota + Embeddings + Imágenes │
-│  • Renovación automática de tokens        │
-└──────┬──────────────────────────────────┘
-       │
-       ├─→ [Tier 1: SUSCRIPCIÓN] Claude Code, Codex, Gemini CLI
-       │   ↓ cuota agotada
-       ├─→ [Tier 2: API KEY] DeepSeek, Groq, xAI, Mistral, NVIDIA NIM, etc.
-       │   ↓ límite de presupuesto
-       ├─→ [Tier 3: BARATO] GLM ($0.6/1M), MiniMax ($0.2/1M)
-       │   ↓ límite de presupuesto
-       └─→ [Tier 4: GRATUITO] iFlow, Qwen, Kiro (ilimitado)
-
-Resultado: Nunca dejes de programar, costo mínimo
-```
-
----
-
-## ⚡ Inicio Rápido
-
-**1. Instala globalmente:**
-
-```bash
-npm install -g omniroute
-omniroute
-```
-
-🎉 El Dashboard se abre en `http://localhost:20128`
-
-| Comando                 | Descripción                                    |
-| ----------------------- | ---------------------------------------------- |
-| `omniroute`             | Iniciar servidor (puerto predeterminado 20128) |
-| `omniroute --port 3000` | Usar puerto personalizado                      |
-| `omniroute --no-open`   | No abrir navegador automáticamente             |
-| `omniroute --help`      | Mostrar ayuda                                  |
-
-**2. Conecta un proveedor GRATUITO:**
-
-Dashboard → Proveedores → Conectar **Claude Code** o **Antigravity** → Login OAuth → ¡Listo!
-
-**3. Usa en tu herramienta CLI:**
-
-```
-Claude Code/Codex/Gemini CLI/OpenClaw/Cursor/Cline Configuración:
-  Endpoint: http://localhost:20128/v1
-  API Key: [copiar del dashboard]
-  Model: if/kimi-k2-thinking
-```
-
-**¡Eso es todo!** Comienza a programar con modelos de IA GRATUITOS.
-
-**Alternativa — ejecutar desde código fuente:**
-
-```bash
-cp .env.example .env
-npm install
-PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev
-```
-
----
-
-## 🐳 Docker
-
-OmniRoute está disponible como imagen Docker pública en [Docker Hub](https://hub.docker.com/r/diegosouzapw/omniroute).
-
-**Ejecución rápida:**
-
-```bash
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-**Con archivo de entorno:**
-
-```bash
-# Copia y edita el .env primero
-cp .env.example .env
-
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  --env-file .env \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-**Usando Docker Compose:**
-
-```bash
-# Perfil base (sin herramientas CLI)
-docker compose --profile base up -d
-
-# Perfil CLI (Claude Code, Codex, OpenClaw integrados)
-docker compose --profile cli up -d
-```
-
-| Imagen                   | Tag      | Tamaño | Descripción            |
-| ------------------------ | -------- | ------ | ---------------------- |
-| `diegosouzapw/omniroute` | `latest` | ~250MB | Última versión estable |
-| `diegosouzapw/omniroute` | `1.0.6`  | ~250MB | Versión actual         |
-
----
-
-## 💰 Precios Resumidos
-
-| Tier               | Proveedor         | Costo                        | Reset de Cuota    | Mejor Para              |
-| ------------------ | ----------------- | ---------------------------- | ----------------- | ----------------------- |
-| **💳 SUSCRIPCIÓN** | Claude Code (Pro) | $20/mes                      | 5h + semanal      | Ya suscrito             |
-|                    | Codex (Plus/Pro)  | $20-200/mes                  | 5h + semanal      | Usuarios OpenAI         |
-|                    | Gemini CLI        | **GRATUITO**                 | 180K/mes + 1K/día | ¡Todos!                 |
-|                    | GitHub Copilot    | $10-19/mes                   | Mensual           | Usuarios GitHub         |
-| **🔑 API KEY**     | NVIDIA NIM        | **GRATUITO** (1000 créditos) | Único             | Pruebas gratuitas       |
-|                    | DeepSeek          | Por uso                      | Ninguno           | Mejor precio/calidad    |
-|                    | Groq              | Tier gratuito + pago         | Limitado          | Inferencia ultra-rápida |
-|                    | xAI (Grok)        | Por uso                      | Ninguno           | Modelos Grok            |
-|                    | Mistral           | Tier gratuito + pago         | Limitado          | IA Europea              |
-|                    | OpenRouter        | Por uso                      | Ninguno           | 100+ modelos            |
-| **💰 BARATO**      | GLM-4.7           | $0.6/1M                      | Diario 10h        | Respaldo económico      |
-|                    | MiniMax M2.1      | $0.2/1M                      | Rotativo 5h       | Opción más barata       |
-|                    | Kimi K2           | $9/mes fijo                  | 10M tokens/mes    | Costo predecible        |
-| **🆓 GRATUITO**    | iFlow             | $0                           | Ilimitado         | 8 modelos gratuitos     |
-|                    | Qwen              | $0                           | Ilimitado         | 3 modelos gratuitos     |
-|                    | Kiro              | $0                           | Ilimitado         | Claude gratuito         |
-
-**💡 Consejo Pro:** ¡Comienza con Gemini CLI (180K gratis/mes) + iFlow (ilimitado gratis) = $0 de costo!
-
----
-
-## 🎯 Casos de Uso
-
-### Caso 1: "Tengo suscripción Claude Pro"
-
-**Problema:** La cuota expira sin usar, límites de tasa durante programación intensa
-
-```
-Combo: "maximize-claude"
-  1. cc/claude-opus-4-6        (usar suscripción al máximo)
-  2. glm/glm-4.7               (respaldo barato cuando la cuota se agota)
-  3. if/kimi-k2-thinking       (fallback de emergencia gratuito)
-
-Costo mensual: $20 (suscripción) + ~$5 (respaldo) = $25 total
-vs. $20 + chocar con límites = frustración
-```
-
-### Caso 2: "Quiero costo cero"
-
-**Problema:** No puede pagar suscripciones, necesita IA confiable para programar
-
-```
-Combo: "free-forever"
-  1. gc/gemini-3-flash         (180K gratis/mes)
-  2. if/kimi-k2-thinking       (ilimitado gratis)
-  3. qw/qwen3-coder-plus       (ilimitado gratis)
-
-Costo mensual: $0
-Calidad: Modelos listos para producción
-```
-
-### Caso 3: "Necesito programar 24/7, sin interrupciones"
-
-**Problema:** Plazos ajustados, no puede permitirse tiempo de inactividad
-
-```
-Combo: "always-on"
-  1. cc/claude-opus-4-6        (mejor calidad)
-  2. cx/gpt-5.2-codex          (segunda suscripción)
-  3. glm/glm-4.7               (barato, reset diario)
-  4. minimax/MiniMax-M2.1      (más barato, reset 5h)
-  5. if/kimi-k2-thinking       (gratuito ilimitado)
-
-Resultado: 5 capas de fallback = cero tiempo de inactividad
-```
-
-### Caso 4: "Quiero IA GRATUITA en OpenClaw"
-
-**Problema:** Necesita asistente de IA en apps de mensajería, completamente gratuito
-
-```
-Combo: "openclaw-free"
-  1. if/glm-4.7                (ilimitado gratis)
-  2. if/minimax-m2.1           (ilimitado gratis)
-  3. if/kimi-k2-thinking       (ilimitado gratis)
-
-Costo mensual: $0
-Acceso vía: WhatsApp, Telegram, Slack, Discord, iMessage, Signal...
-```
-
----
-
-## 💡 Características Principales
-
-### 🧠 Enrutamiento e Inteligencia
-
-| Característica                         | Qué Hace                                                                        |
-| -------------------------------------- | ------------------------------------------------------------------------------- |
-| 🎯 **Fallback Inteligente 4 Tiers**    | Auto-enrutamiento: Suscripción → API Key → Barato → Gratuito                    |
-| 📊 **Rastreo de Cuota en Tiempo Real** | Conteo de tokens en vivo + countdown de reset por proveedor                     |
-| 🔄 **Traducción de Formato**           | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro transparente                           |
-| 👥 **Soporte Multi-Cuenta**            | Múltiples cuentas por proveedor con selección inteligente                       |
-| 🔄 **Renovación Automática de Token**  | Tokens OAuth se renuevan automáticamente con reintentos                         |
-| 🎨 **Combos Personalizados**           | 6 estrategias: fill-first, round-robin, p2c, random, least-used, cost-optimized |
-| 🧩 **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       |
-| 💬 **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     |
-
-### 🎵 APIs Multi-Modal
-
-| Característica                | Qué Hace                                               |
-| ----------------------------- | ------------------------------------------------------ |
-| 🖼️ **Generación de Imágenes** | `/v1/images/generations` — 4 proveedores, 9+ modelos   |
-| 📐 **Embeddings**             | `/v1/embeddings` — 6 proveedores, 9+ modelos           |
-| 🎤 **Transcripción de Audio** | `/v1/audio/transcriptions` — Compatible con Whisper    |
-| 🔊 **Texto a Voz**            | `/v1/audio/speech` — Síntesis de audio multi-proveedor |
-| 🛡️ **Moderaciones**           | `/v1/moderations` — Verificaciones de seguridad        |
-| 🔀 **Reranking**              | `/v1/rerank` — Reranking de relevancia de documentos   |
-
-### 🛡️ 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              |
-
-### 📊 Observabilidad y Analytics
-
-| Característica                 | Qué Hace                                                              |
-| ------------------------------ | --------------------------------------------------------------------- |
-| 📝 **Logs de Solicitud**       | Modo debug con logs completos de request/response                     |
-| 💾 **Logs SQLite**             | Logs de proxy persistentes sobreviven a reinicios                     |
-| 📊 **Dashboard de Analytics**  | Recharts: cards de estadísticas, gráfico de uso, tabla de proveedores |
-| 📈 **Rastreo de Progreso**     | Eventos de progreso SSE opt-in para streaming                         |
-| 🧪 **Evaluaciones de LLM**     | Pruebas con conjunto golden y 4 estrategias de match                  |
-| 🔍 **Telemetría de Solicitud** | Agregación de latencia p50/p95/p99 + rastreo X-Request-Id             |
-| 📋 **Logs + Cuotas**           | Páginas dedicadas para navegación de logs y rastreo de cuotas         |
-| 🏥 **Dashboard de Salud**      | Uptime, estados de circuit breaker, lockouts, stats de caché          |
-| 💰 **Rastreo de Costos**       | Gestión de presupuesto + configuración de precios por modelo          |
-
-### ☁️ Deploy y Sincronización
-
-| Característica                    | Qué Hace                                                                        |
-| --------------------------------- | ------------------------------------------------------------------------------- |
-| 💾 **Cloud Sync**                 | Sincroniza configuraciones entre dispositivos vía Cloudflare Workers            |
-| 🌐 **Deploy en Cualquier Lugar**  | Localhost, VPS, Docker, Cloudflare Workers                                      |
-| 🔑 **Gestión de API Keys**        | Genera, rota y define alcance de API keys por proveedor                         |
-| 🧙 **Asistente de Configuración** | Setup guiado en 4 pasos para nuevos usuarios                                    |
-| 🔧 **Dashboard CLI Tools**        | Configuración en un clic para Claude, Codex, Cline, OpenClaw, Kilo, Antigravity |
-| 🔄 **Backups de DB**              | Backup y restauración automáticos de todas las configuraciones                  |
-
-<details>
-<summary><b>📖 Detalles de Características</b></summary>
-
-### 🎯 Fallback Inteligente 4 Tiers
-
-Crea combos con fallback automático:
-
-```
-Combo: "my-coding-stack"
-  1. cc/claude-opus-4-6        (tu suscripción)
-  2. nvidia/llama-3.3-70b      (API NVIDIA gratuita)
-  3. glm/glm-4.7               (respaldo barato, $0.6/1M)
-  4. if/kimi-k2-thinking       (fallback gratuito)
-
-→ Cambia automáticamente cuando la cuota se agota o ocurren errores
-```
-
-### 📊 Rastreo de Cuota en Tiempo Real
-
-- Consumo de tokens por proveedor
-- Countdown de reset (5 horas, diario, semanal)
-- Estimación de costo para tiers pagos
-- Reportes de gastos mensuales
-
-### 🔄 Traducción de Formato
-
-Traducción transparente entre formatos:
-
-- **OpenAI** ↔ **Claude** ↔ **Gemini** ↔ **OpenAI Responses**
-- Tu herramienta CLI envía formato OpenAI → OmniRoute traduce → El proveedor recibe formato nativo
-- Funciona con cualquier herramienta que soporte endpoints OpenAI personalizados
-
-### 👥 Soporte Multi-Cuenta
-
-- Agrega múltiples cuentas por proveedor
-- Round-robin automático o enrutamiento por prioridad
-- Fallback a la siguiente cuenta cuando una alcanza la cuota
-
-### 🔄 Renovación Automática de Token
-
-- Los tokens OAuth se renuevan automáticamente antes de expirar
-- Sin necesidad de re-autenticación manual
-- Experiencia transparente en todos los proveedores
-
-### 🎨 Combos Personalizados
-
-- Crea combinaciones ilimitadas de modelos
-- 6 estrategias: fill-first, round-robin, power-of-two-choices, random, least-used, cost-optimized
-- Comparte combos entre dispositivos con Cloud Sync
-
-### 🏥 Dashboard de Salud
-
-- Estado del sistema (uptime, versión, uso de memoria)
-- Estados de circuit breaker por proveedor (Closed/Open/Half-Open)
-- Estado de rate limit y lockouts activos
-- Estadísticas de caché de firma
-- Telemetría de latencia (p50/p95/p99) + caché de prompt
-- Reset de salud con un clic
-
-### 🔧 Playground del Traductor
-
-- Debug, prueba y visualiza traducciones de formato de API
-- Envía solicitudes y ve cómo OmniRoute traduce entre formatos de proveedores
-- Invaluable para troubleshooting de problemas de integración
-
-### 💾 Cloud Sync
-
-- Sincroniza proveedores, combos y configuraciones entre dispositivos
-- Sincronización automática en segundo plano
-- Almacenamiento cifrado seguro
-
-</details>
-
----
-
-## 📖 Guía de Configuración
-
-<details>
-<summary><b>💳 Proveedores por Suscripción</b></summary>
-
-### Claude Code (Pro/Max)
-
-```bash
-Dashboard → Proveedores → Conectar Claude Code
-→ Login OAuth → Renovación automática de token
-→ Rastreo de cuota 5h + semanal
-
-Modelos:
-  cc/claude-opus-4-6
-  cc/claude-sonnet-4-5-20250929
-  cc/claude-haiku-4-5-20251001
-```
-
-**Consejo Pro:** Usa Opus para tareas complejas, Sonnet para velocidad. ¡OmniRoute rastrea cuota por modelo!
-
-### OpenAI Codex (Plus/Pro)
-
-```bash
-Dashboard → Proveedores → Conectar Codex
-→ Login OAuth (puerto 1455)
-→ Reset 5h + semanal
-
-Modelos:
-  cx/gpt-5.2-codex
-  cx/gpt-5.1-codex-max
-```
-
-### Gemini CLI (¡GRATUITO 180K/mes!)
-
-```bash
-Dashboard → Proveedores → Conectar Gemini CLI
-→ Google OAuth
-→ 180K completions/mes + 1K/día
-
-Modelos:
-  gc/gemini-3-flash-preview
-  gc/gemini-2.5-pro
-```
-
-**Mejor Valor:** ¡Tier gratuito enorme! Úsalo antes de los tiers pagos.
-
-### GitHub Copilot
-
-```bash
-Dashboard → Proveedores → Conectar GitHub
-→ OAuth vía GitHub
-→ Reset mensual (1ro del mes)
-
-Modelos:
-  gh/gpt-5
-  gh/claude-4.5-sonnet
-  gh/gemini-3-pro
-```
-
-</details>
-
-<details>
-<summary><b>🔑 Proveedores por API Key</b></summary>
-
-### NVIDIA NIM (¡GRATUITO 1000 créditos!)
-
-1. Regístrate: [build.nvidia.com](https://build.nvidia.com)
-2. Obtén API key gratuita (1000 créditos de inferencia incluidos)
-3. Dashboard → Agregar Proveedor → NVIDIA NIM:
-   - API Key: `nvapi-your-key`
-
-**Modelos:** `nvidia/llama-3.3-70b-instruct`, `nvidia/mistral-7b-instruct`, y 50+ más
-
-**Consejo Pro:** ¡API compatible con OpenAI — funciona perfectamente con la traducción de formato de OmniRoute!
-
-### DeepSeek
-
-1. Regístrate: [platform.deepseek.com](https://platform.deepseek.com)
-2. Obtén API key
-3. Dashboard → Agregar Proveedor → DeepSeek
-
-**Modelos:** `deepseek/deepseek-chat`, `deepseek/deepseek-coder`
-
-### Groq (¡Tier Gratuito Disponible!)
-
-1. Regístrate: [console.groq.com](https://console.groq.com)
-2. Obtén API key (tier gratuito incluido)
-3. Dashboard → Agregar Proveedor → Groq
-
-**Modelos:** `groq/llama-3.3-70b`, `groq/mixtral-8x7b`
-
-**Consejo Pro:** ¡Inferencia ultra-rápida — mejor para programación en tiempo real!
-
-### OpenRouter (100+ Modelos)
-
-1. Regístrate: [openrouter.ai](https://openrouter.ai)
-2. Obtén API key
-3. Dashboard → Agregar Proveedor → OpenRouter
-
-**Modelos:** Accede a 100+ modelos de todos los principales proveedores a través de una única API key.
-
-</details>
-
-<details>
-<summary><b>💰 Proveedores Baratos (Respaldo)</b></summary>
-
-### GLM-4.7 (Reset diario, $0.6/1M)
-
-1. Regístrate: [Zhipu AI](https://open.bigmodel.cn/)
-2. Obtén API key del Plan Coding
-3. Dashboard → Agregar API Key:
-   - Proveedor: `glm`
-   - API Key: `your-key`
-
-**Usa:** `glm/glm-4.7`
-
-**Consejo Pro:** ¡El Plan Coding ofrece 3× cuota a 1/7 del costo! Reset diario 10:00 AM.
-
-### MiniMax M2.1 (Reset 5h, $0.20/1M)
-
-1. Regístrate: [MiniMax](https://www.minimax.io/)
-2. Obtén API key
-3. Dashboard → Agregar API Key
-
-**Usa:** `minimax/MiniMax-M2.1`
-
-**Consejo Pro:** ¡Opción más barata para contexto largo (1M tokens)!
-
-### Kimi K2 ($9/mes fijo)
-
-1. Suscríbete: [Moonshot AI](https://platform.moonshot.ai/)
-2. Obtén API key
-3. Dashboard → Agregar API Key
-
-**Usa:** `kimi/kimi-latest`
-
-**Consejo Pro:** ¡$9/mes fijo por 10M tokens = $0.90/1M de costo efectivo!
-
-</details>
-
-<details>
-<summary><b>🆓 Proveedores GRATUITOS (Respaldo de Emergencia)</b></summary>
-
-### iFlow (8 modelos GRATUITOS)
-
-```bash
-Dashboard → Conectar iFlow
-→ Login OAuth iFlow
-→ Uso ilimitado
-
-Modelos:
-  if/kimi-k2-thinking
-  if/qwen3-coder-plus
-  if/glm-4.7
-  if/minimax-m2
-  if/deepseek-r1
-```
-
-### Qwen (3 modelos GRATUITOS)
-
-```bash
-Dashboard → Conectar Qwen
-→ Autorización por código de dispositivo
-→ Uso ilimitado
-
-Modelos:
-  qw/qwen3-coder-plus
-  qw/qwen3-coder-flash
-```
-
-### Kiro (Claude GRATUITO)
-
-```bash
-Dashboard → Conectar Kiro
-→ AWS Builder ID o Google/GitHub
-→ Uso ilimitado
-
-Modelos:
-  kr/claude-sonnet-4.5
-  kr/claude-haiku-4.5
-```
-
-</details>
-
-<details>
-<summary><b>🎨 Crear Combos</b></summary>
-
-### Ejemplo 1: Maximizar Suscripción → Respaldo Barato
-
-```
-Dashboard → Combos → Crear Nuevo
-
-Nombre: premium-coding
-Modelos:
-  1. cc/claude-opus-4-6 (Suscripción primaria)
-  2. glm/glm-4.7 (Respaldo barato, $0.6/1M)
-  3. minimax/MiniMax-M2.1 (Fallback más barato, $0.20/1M)
-
-Usa en CLI: premium-coding
-```
-
-### Ejemplo 2: Solo Gratuito (Costo Cero)
-
-```
-Nombre: free-combo
-Modelos:
-  1. gc/gemini-3-flash-preview (180K gratis/mes)
-  2. if/kimi-k2-thinking (ilimitado)
-  3. qw/qwen3-coder-plus (ilimitado)
-
-Costo: ¡$0 para siempre!
-```
-
-</details>
-
-<details>
-<summary><b>🔧 Integración CLI</b></summary>
-
-### Cursor IDE
-
-```
-Configuración → Modelos → Avanzado:
-  OpenAI API Base URL: http://localhost:20128/v1
-  OpenAI API Key: [del dashboard OmniRoute]
-  Model: cc/claude-opus-4-6
-```
-
-### Claude Code
-
-Usa la página **CLI Tools** en el dashboard para configuración en un clic, o edita `~/.claude/settings.json` manualmente.
-
-### Codex CLI
-
-```bash
-export OPENAI_BASE_URL="http://localhost:20128"
-export OPENAI_API_KEY="your-omniroute-api-key"
-
-codex "your prompt"
-```
-
-### OpenClaw
-
-**Opción 1 — Dashboard (recomendado):**
-
-```
-Dashboard → CLI Tools → OpenClaw → Seleccionar Modelo → Aplicar
-```
-
-**Opción 2 — Manual:** Edita `~/.openclaw/openclaw.json`:
-
-```json
-{
-  "models": {
-    "providers": {
-      "omniroute": {
-        "baseUrl": "http://127.0.0.1:20128/v1",
-        "apiKey": "sk_omniroute",
-        "api": "openai-completions"
-      }
-    }
-  }
-}
-```
-
-> **Nota:** OpenClaw solo funciona con OmniRoute local. Usa `127.0.0.1` en lugar de `localhost` para evitar problemas de resolución IPv6.
-
-### Cline / Continue / RooCode
-
-```
-Configuración → Configuración de API:
-  Proveedor: OpenAI Compatible
-  Base URL: http://localhost:20128/v1
-  API Key: [del dashboard OmniRoute]
-  Model: if/kimi-k2-thinking
-```
-
-</details>
-
----
-
-## 📊 Modelos Disponibles
-
-<details>
-<summary><b>Ver todos los modelos disponibles</b></summary>
-
-**Claude Code (`cc/`)** - Pro/Max:
-
-- `cc/claude-opus-4-6`
-- `cc/claude-sonnet-4-5-20250929`
-- `cc/claude-haiku-4-5-20251001`
-
-**Codex (`cx/`)** - Plus/Pro:
-
-- `cx/gpt-5.2-codex`
-- `cx/gpt-5.1-codex-max`
-
-**Gemini CLI (`gc/`)** - GRATUITO:
-
-- `gc/gemini-3-flash-preview`
-- `gc/gemini-2.5-pro`
-
-**GitHub Copilot (`gh/`)**:
-
-- `gh/gpt-5`
-- `gh/claude-4.5-sonnet`
-
-**NVIDIA NIM (`nvidia/`)** - Créditos GRATUITOS:
-
-- `nvidia/llama-3.3-70b-instruct`
-- `nvidia/mistral-7b-instruct`
-- 50+ más modelos en [build.nvidia.com](https://build.nvidia.com)
-
-**GLM (`glm/`)** - $0.6/1M:
-
-- `glm/glm-4.7`
-
-**MiniMax (`minimax/`)** - $0.2/1M:
-
-- `minimax/MiniMax-M2.1`
-
-**iFlow (`if/`)** - GRATUITO:
-
-- `if/kimi-k2-thinking`
-- `if/qwen3-coder-plus`
-- `if/deepseek-r1`
-- `if/glm-4.7`
-- `if/minimax-m2`
-
-**Qwen (`qw/`)** - GRATUITO:
-
-- `qw/qwen3-coder-plus`
-- `qw/qwen3-coder-flash`
-
-**Kiro (`kr/`)** - GRATUITO:
-
-- `kr/claude-sonnet-4.5`
-- `kr/claude-haiku-4.5`
-
-**OpenRouter (`or/`)** - 100+ modelos:
-
-- `or/anthropic/claude-4-sonnet`
-- `or/google/gemini-2.5-pro`
-- Cualquier modelo de [openrouter.ai/models](https://openrouter.ai/models)
-
-</details>
-
----
-
-## 🧪 Evaluaciones (Evals)
-
-OmniRoute incluye un framework de evaluación integrado para probar la calidad de respuestas de LLM contra un conjunto golden. Accede vía **Analytics → Evals** en el dashboard.
-
-### Conjunto Golden Integrado
-
-El "OmniRoute Golden Set" precargado contiene 10 casos de prueba que cubren:
-
-- Saludos, matemáticas, geografía, generación de código
-- Conformidad de formato JSON, traducción, markdown
-- Rechazo de seguridad (contenido dañino), conteo, lógica booleana
-
-### Estrategias de Evaluación
-
-| Estrategia | Descripción                                          | Ejemplo                          |
-| ---------- | ---------------------------------------------------- | -------------------------------- |
-| `exact`    | La salida debe coincidir exactamente                 | `"4"`                            |
-| `contains` | La salida debe contener subcadena (case-insensitive) | `"Paris"`                        |
-| `regex`    | La salida debe coincidir con el patrón regex         | `"1.*2.*3"`                      |
-| `custom`   | Función JS personalizada retorna true/false          | `(output) => output.length > 10` |
-
----
-
-## 🐛 Solución de Problemas
-
-<details>
-<summary><b>Haz clic para expandir la guía de solución de problemas</b></summary>
-
-**"Language model did not provide messages"**
-
-- Cuota del proveedor agotada → Verifica el rastreador de cuota en el dashboard
-- Solución: Usa combo con fallback o cambia a tier más barato
-
-**Rate limiting**
-
-- Cuota de suscripción agotada → Fallback a GLM/MiniMax
-- Agrega combo: `cc/claude-opus-4-6 → glm/glm-4.7 → if/kimi-k2-thinking`
-
-**Token OAuth expirado**
-
-- Renovado automáticamente por OmniRoute
-- Si persiste: Dashboard → Proveedor → Reconectar
-
-**Costos altos**
-
-- Verifica estadísticas de uso en Dashboard → Costos
-- Cambia modelo primario a GLM/MiniMax
-- Usa tier gratuito (Gemini CLI, iFlow) para tareas no críticas
-
-**Dashboard se abre en el puerto equivocado**
-
-- Establece `PORT=20128` y `NEXT_PUBLIC_BASE_URL=http://localhost:20128`
-
-**Errores de cloud sync**
-
-- Verifica que `BASE_URL` apunte a tu instancia en ejecución
-- Verifica que `CLOUD_URL` apunte a tu endpoint cloud esperado
-- Mantén los valores `NEXT_PUBLIC_*` alineados con los valores del servidor
-
-**Primer login no funciona**
-
-- Verifica `INITIAL_PASSWORD` en `.env`
-- Si no está definido, la contraseña predeterminada es `123456`
-
-**Sin logs de solicitud**
-
-- Establece `ENABLE_REQUEST_LOGS=true` en `.env`
-
-**Prueba de conexión muestra "Invalid" para proveedores compatibles con OpenAI**
-
-- Muchos proveedores no exponen el endpoint `/models`
-- OmniRoute v1.0.6+ incluye validación vía chat completions como fallback
-- Asegúrate de que la URL base incluya el sufijo `/v1`
-
-</details>
-
----
-
-## 🛠️ Stack Tecnológico
-
-- **Runtime**: Node.js 20+
-- **Lenguaje**: TypeScript 5.9 — **100% TypeScript** en `src/` y `open-sse/` (v1.0.6)
-- **Framework**: Next.js 16 + React 19 + Tailwind CSS 4
-- **Base de Datos**: LowDB (JSON) + SQLite (estado del dominio + logs de proxy)
-- **Streaming**: Server-Sent Events (SSE)
-- **Auth**: OAuth 2.0 (PKCE) + JWT + API Keys
-- **Testing**: Node.js test runner (368+ tests unitarios)
-- **CI/CD**: GitHub Actions (publicación automática npm + Docker Hub en release)
-- **Website**: [omniroute.online](https://omniroute.online)
-- **Paquete**: [npmjs.com/package/omniroute](https://www.npmjs.com/package/omniroute)
-- **Docker**: [hub.docker.com/r/diegosouzapw/omniroute](https://hub.docker.com/r/diegosouzapw/omniroute)
-- **Resiliencia**: Circuit breaker, backoff exponencial, anti-thundering herd, spoofing TLS
-
----
-
-## 📖 Documentación
-
-| Documento                                        | Descripción                                        |
-| ------------------------------------------------ | -------------------------------------------------- |
-| [Guía del Usuario](docs/USER_GUIDE.md)           | Proveedores, combos, integración CLI, deploy       |
-| [Referencia de API](docs/API_REFERENCE.md)       | Todos los endpoints con ejemplos                   |
-| [Solución de Problemas](docs/TROUBLESHOOTING.md) | Problemas comunes y soluciones                     |
-| [Arquitectura](docs/ARCHITECTURE.md)             | Arquitectura del sistema e internos                |
-| [Contribuir](CONTRIBUTING.md)                    | Setup de desarrollo y directrices                  |
-| [Spec OpenAPI](docs/openapi.yaml)                | Especificación OpenAPI 3.0                         |
-| [Política de Seguridad](SECURITY.md)             | Reportar vulnerabilidades y prácticas de seguridad |
-
----
-
-## 📧 Soporte
-
-> 💬 **¡Únete a la comunidad!** [Grupo WhatsApp](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) — Obtén ayuda, comparte consejos y mantente al día.
-
-- **Website**: [omniroute.online](https://omniroute.online)
-- **GitHub**: [github.com/diegosouzapw/OmniRoute](https://github.com/diegosouzapw/OmniRoute)
-- **Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
-- **WhatsApp**: [Grupo de la Comunidad](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-- **Proyecto Original**: [9router por decolua](https://github.com/decolua/9router)
-
----
-
-## 👥 Contribuidores
-
-[![Contributors](https://contrib.rocks/image?repo=diegosouzapw/OmniRoute&max=100&columns=20&anon=1)](https://github.com/diegosouzapw/OmniRoute/graphs/contributors)
-
-### Cómo Contribuir
-
-1. Haz fork del repositorio
-2. Crea tu rama de funcionalidad (`git checkout -b feature/amazing-feature`)
-3. Haz commit de tus cambios (`git commit -m 'Add amazing feature'`)
-4. Haz push a la rama (`git push origin feature/amazing-feature`)
-5. Abre un Pull Request
-
-Consulta [CONTRIBUTING.md](CONTRIBUTING.md) para directrices detalladas.
-
-### Lanzar una Nueva Versión
-
-```bash
-# Crea un release — la publicación en npm ocurre automáticamente
-gh release create v1.0.6 --title "v1.0.6" --generate-notes
-```
-
----
-
-## 📊 Historial de Stars
-
-<a href="https://star-history.com/#diegosouzapw/OmniRoute&Date">
- <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date&theme=dark" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date" />
- </picture>
-</a>
-
----
-
-## 🙏 Agradecimientos
-
-Agradecimiento especial a **[9router](https://github.com/decolua/9router)** por **[decolua](https://github.com/decolua)** — el proyecto original que inspiró este fork. OmniRoute se construye sobre esa increíble base con características adicionales, APIs multi-modal y una reescritura completa en TypeScript.
-
-Agradecimiento especial a **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** — la implementación original en Go que inspiró esta adaptación a JavaScript.
-
----
-
-## 📄 Licencia
-
-Licencia MIT - consulta [LICENSE](LICENSE) para detalles.
-
----
-
-<div align="center">
-  <sub>Hecho con ❤️ para desarrolladores que programan 24/7</sub>
-  <br/>
-  <sub><a href="https://omniroute.online">omniroute.online</a></sub>
-</div>

README.fr.md

@@ -1,999 +0,0 @@
-<div align="center">
-  <img src="./docs/screenshots/MainOmniRoute.png" alt="OmniRoute Dashboard" width="800"/>
-  
-  # 🚀 OmniRoute — La Passerelle IA Gratuite
-
-### N'arrêtez jamais de coder. Routage intelligent vers des **modèles IA GRATUITS et économiques** avec fallback automatique.
-
-_Votre proxy API universel — un endpoint, 36+ fournisseurs, zéro temps d'arrêt._
-
-**Chat Completions • Embeddings • Génération d'images • Audio • Reranking • 100% TypeScript**
-
----
-
-### 🤖 Fournisseur IA gratuit pour vos agents de programmation préférés
-
-_Connectez n'importe quel IDE ou outil CLI alimenté par l'IA via OmniRoute — passerelle API gratuite pour un codage illimité._
-
-  <table>
-    <tr>
-      <td align="center" width="110">
-        <a href="https://github.com/cline/cline">
-          <img src="./public/providers/openclaw.png" alt="OpenClaw" width="48"/><br/>
-          <b>OpenClaw</b>
-        </a><br/>
-        <sub>⭐ 205K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/HKUDS/nanobot">
-          <img src="./public/providers/nanobot.png" alt="NanoBot" width="48"/><br/>
-          <b>NanoBot</b>
-        </a><br/>
-        <sub>⭐ 20.9K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/sipeed/picoclaw">
-          <img src="./public/providers/picoclaw.jpg" alt="PicoClaw" width="48"/><br/>
-          <b>PicoClaw</b>
-        </a><br/>
-        <sub>⭐ 14.6K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/zeroclaw-labs/zeroclaw">
-          <img src="./public/providers/zeroclaw.png" alt="ZeroClaw" width="48"/><br/>
-          <b>ZeroClaw</b>
-        </a><br/>
-        <sub>⭐ 9.9K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/nearai/ironclaw">
-          <img src="./public/providers/ironclaw.png" alt="IronClaw" width="48"/><br/>
-          <b>IronClaw</b>
-        </a><br/>
-        <sub>⭐ 2.1K</sub>
-      </td>
-    </tr>
-    <tr>
-      <td align="center" width="110">
-        <a href="https://github.com/anomalyco/opencode">
-          <img src="./public/providers/opencode.svg" alt="OpenCode" width="48"/><br/>
-          <b>OpenCode</b>
-        </a><br/>
-        <sub>⭐ 106K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/openai/codex">
-          <img src="./public/providers/codex.png" alt="Codex CLI" width="48"/><br/>
-          <b>Codex CLI</b>
-        </a><br/>
-        <sub>⭐ 60.8K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/anthropics/claude-code">
-          <img src="./public/providers/claude.png" alt="Claude Code" width="48"/><br/>
-          <b>Claude Code</b>
-        </a><br/>
-        <sub>⭐ 67.3K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/google-gemini/gemini-cli">
-          <img src="./public/providers/gemini-cli.png" alt="Gemini CLI" width="48"/><br/>
-          <b>Gemini CLI</b>
-        </a><br/>
-        <sub>⭐ 94.7K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/Kilo-Org/kilocode">
-          <img src="./public/providers/kilocode.png" alt="Kilo Code" width="48"/><br/>
-          <b>Kilo Code</b>
-        </a><br/>
-        <sub>⭐ 15.5K</sub>
-      </td>
-    </tr>
-  </table>
-
-<sub>📡 Tous les agents se connectent via <code>http://localhost:20128/v1</code> ou <code>http://cloud.omniroute.online/v1</code> — une configuration, modèles et quota illimités</sub>
-
----
-
-[![npm version](https://img.shields.io/npm/v/omniroute?color=cb3837&logo=npm)](https://www.npmjs.com/package/omniroute)
-[![Docker Hub](https://img.shields.io/docker/v/diegosouzapw/omniroute?label=Docker%20Hub&logo=docker&color=2496ED)](https://hub.docker.com/r/diegosouzapw/omniroute)
-[![License](https://img.shields.io/github/license/diegosouzapw/OmniRoute)](https://github.com/diegosouzapw/OmniRoute/blob/main/LICENSE)
-[![Website](https://img.shields.io/badge/Website-omniroute.online-blue?logo=google-chrome&logoColor=white)](https://omniroute.online)
-[![WhatsApp](https://img.shields.io/badge/WhatsApp-Community-25D366?logo=whatsapp&logoColor=white)](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-
-[🌐 Site web](https://omniroute.online) • [🚀 Démarrage rapide](#-démarrage-rapide) • [💡 Fonctionnalités](#-fonctionnalités-principales) • [📖 Docs](#-documentation) • [💰 Tarifs](#-aperçu-des-tarifs)
-
-🌐 **Disponible en :** [English](README.md) | [Português](README.pt-BR.md) | [Español](README.es.md) | [Русский](README.ru.md) | [中文](README.zh-CN.md) | [Deutsch](README.de.md) | [Français](README.fr.md) | [Italiano](README.it.md)
-
-</div>
-
----
-
-## 🤔 Pourquoi OmniRoute ?
-
-**Arrêtez de gaspiller de l'argent et de vous heurter aux limites :**
-
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Le quota d'abonnement expire inutilisé chaque mois
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Les limites de débit vous arrêtent en plein codage
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> APIs coûteuses (20-50 $/mois par fournisseur)
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Changement manuel entre fournisseurs
-
-**OmniRoute résout ces problèmes :**
-
-- ✅ **Maximisez les abonnements** — Suivez les quotas, utilisez chaque bit avant la réinitialisation
-- ✅ **Fallback automatique** — Abonnement → Clé API → Économique → Gratuit, zéro temps d'arrêt
-- ✅ **Multi-comptes** — Round-robin entre les comptes par fournisseur
-- ✅ **Universel** — Fonctionne avec Claude Code, Codex, Gemini CLI, Cursor, Cline, OpenClaw, tout outil CLI
-
----
-
-## 🔄 Comment ça fonctionne
-
-```
-┌─────────────┐
-│  Votre CLI  │  (Claude Code, Codex, Gemini CLI, OpenClaw, Cursor, Cline...)
-│   Tool      │
-└──────┬──────┘
-       │ http://localhost:20128/v1
-       ↓
-┌─────────────────────────────────────────┐
-│        OmniRoute (Routeur intelligent)   │
-│  • Traduction de format (OpenAI ↔ Claude) │
-│  • Suivi des quotas + Embeddings + Images │
-│  • Renouvellement automatique des tokens   │
-└──────┬──────────────────────────────────┘
-       │
-       ├─→ [Tier 1: ABONNEMENT] Claude Code, Codex, Gemini CLI
-       │   ↓ quota épuisé
-       ├─→ [Tier 2: CLÉ API] DeepSeek, Groq, xAI, Mistral, NVIDIA NIM, etc.
-       │   ↓ limite de budget
-       ├─→ [Tier 3: ÉCONOMIQUE] GLM ($0.6/1M), MiniMax ($0.2/1M)
-       │   ↓ limite de budget
-       └─→ [Tier 4: GRATUIT] iFlow, Qwen, Kiro (illimité)
-
-Résultat : Ne jamais arrêter de coder, coût minimal
-```
-
----
-
-## ⚡ Démarrage rapide
-
-**1. Installer globalement :**
-
-```bash
-npm install -g omniroute
-omniroute
-```
-
-🎉 Le tableau de bord s'ouvre sur `http://localhost:20128`
-
-| Commande                | Description                                 |
-| ----------------------- | ------------------------------------------- |
-| `omniroute`             | Démarrer le serveur (port par défaut 20128) |
-| `omniroute --port 3000` | Utiliser un port personnalisé               |
-| `omniroute --no-open`   | Ne pas ouvrir le navigateur automatiquement |
-| `omniroute --help`      | Afficher l'aide                             |
-
-**2. Connecter un fournisseur GRATUIT :**
-
-Tableau de bord → Fournisseurs → Connecter **Claude Code** ou **Antigravity** → Connexion OAuth → Terminé !
-
-**3. Utiliser dans votre outil CLI :**
-
-```
-Claude Code/Codex/Gemini CLI/OpenClaw/Cursor/Cline Paramètres :
-  Endpoint : http://localhost:20128/v1
-  API Key : [copier depuis le tableau de bord]
-  Model : if/kimi-k2-thinking
-```
-
-**C'est tout !** Commencez à coder avec des modèles IA GRATUITS.
-
-**Alternative — exécuter depuis le code source :**
-
-```bash
-cp .env.example .env
-npm install
-PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev
-```
-
----
-
-## 🐳 Docker
-
-OmniRoute est disponible en tant qu'image Docker publique sur [Docker Hub](https://hub.docker.com/r/diegosouzapw/omniroute).
-
-**Démarrage rapide :**
-
-```bash
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-**Avec fichier d'environnement :**
-
-```bash
-# Copier et modifier le .env d'abord
-cp .env.example .env
-
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  --env-file .env \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-**Avec Docker Compose :**
-
-```bash
-# Profil de base (sans outils CLI)
-docker compose --profile base up -d
-
-# Profil CLI (Claude Code, Codex, OpenClaw intégrés)
-docker compose --profile cli up -d
-```
-
-| Image                    | Tag      | Taille | Description             |
-| ------------------------ | -------- | ------ | ----------------------- |
-| `diegosouzapw/omniroute` | `latest` | ~250MB | Dernière version stable |
-| `diegosouzapw/omniroute` | `1.0.6`  | ~250MB | Version actuelle        |
-
----
-
-## 💰 Aperçu des tarifs
-
-| Tier              | Fournisseur       | Coût                       | Réinitialisation    | Idéal pour                    |
-| ----------------- | ----------------- | -------------------------- | ------------------- | ----------------------------- |
-| **💳 ABONNEMENT** | Claude Code (Pro) | 20 $/mois                  | 5h + hebdomadaire   | Déjà abonné                   |
-|                   | Codex (Plus/Pro)  | 20-200 $/mois              | 5h + hebdomadaire   | Utilisateurs OpenAI           |
-|                   | Gemini CLI        | **GRATUIT**                | 180K/mois + 1K/jour | Tout le monde !               |
-|                   | GitHub Copilot    | 10-19 $/mois               | Mensuel             | Utilisateurs GitHub           |
-| **🔑 CLÉ API**    | NVIDIA NIM        | **GRATUIT** (1000 crédits) | Unique              | Tests gratuits                |
-|                   | DeepSeek          | À l'usage                  | Aucune              | Meilleur rapport qualité-prix |
-|                   | Groq              | Niveau gratuit + payant    | Limité              | Inférence ultra-rapide        |
-|                   | xAI (Grok)        | À l'usage                  | Aucune              | Modèles Grok                  |
-|                   | Mistral           | Niveau gratuit + payant    | Limité              | IA européenne                 |
-|                   | OpenRouter        | À l'usage                  | Aucune              | 100+ modèles                  |
-| **💰 ÉCONOMIQUE** | GLM-4.7           | 0,6 $/1M                   | Quotidien 10h       | Backup économique             |
-|                   | MiniMax M2.1      | 0,2 $/1M                   | Rotatif 5h          | Option la moins chère         |
-|                   | Kimi K2           | 9 $/mois fixe              | 10M tokens/mois     | Coût prévisible               |
-| **🆓 GRATUIT**    | iFlow             | 0 $                        | Illimité            | 8 modèles gratuits            |
-|                   | Qwen              | 0 $                        | Illimité            | 3 modèles gratuits            |
-|                   | Kiro              | 0 $                        | Illimité            | Claude gratuit                |
-
-**💡 Conseil Pro :** Commencez avec Gemini CLI (180K gratuits/mois) + iFlow (illimité gratuit) = 0 $ de coût !
-
----
-
-## 🎯 Cas d'utilisation
-
-### Cas 1 : « J'ai un abonnement Claude Pro »
-
-**Problème :** Le quota expire inutilisé, limites de débit pendant le codage intensif
-
-```
-Combo : "maximize-claude"
-  1. cc/claude-opus-4-6        (utiliser l'abonnement au maximum)
-  2. glm/glm-4.7               (backup économique quand le quota est épuisé)
-  3. if/kimi-k2-thinking       (fallback d'urgence gratuit)
-
-Coût mensuel : 20 $ (abonnement) + ~5 $ (backup) = 25 $ au total
-vs. 20 $ + atteindre les limites = frustration
-```
-
-### Cas 2 : « Je veux zéro coût »
-
-**Problème :** Impossible de payer des abonnements, besoin d'IA fiable pour coder
-
-```
-Combo : "free-forever"
-  1. gc/gemini-3-flash         (180K gratuits/mois)
-  2. if/kimi-k2-thinking       (illimité gratuit)
-  3. qw/qwen3-coder-plus       (illimité gratuit)
-
-Coût mensuel : 0 $
-Qualité : Modèles prêts pour la production
-```
-
-### Cas 3 : « Je dois coder 24/7, sans interruption »
-
-**Problème :** Délais serrés, ne peut pas se permettre de temps d'arrêt
-
-```
-Combo : "always-on"
-  1. cc/claude-opus-4-6        (meilleure qualité)
-  2. cx/gpt-5.2-codex          (deuxième abonnement)
-  3. glm/glm-4.7               (économique, reset quotidien)
-  4. minimax/MiniMax-M2.1      (le moins cher, reset 5h)
-  5. if/kimi-k2-thinking       (gratuit illimité)
-
-Résultat : 5 niveaux de fallback = zéro temps d'arrêt
-```
-
-### Cas 4 : « Je veux l'IA GRATUITE dans OpenClaw »
-
-**Problème :** Besoin d'assistant IA dans les apps de messagerie, entièrement gratuit
-
-```
-Combo : "openclaw-free"
-  1. if/glm-4.7                (illimité gratuit)
-  2. if/minimax-m2.1           (illimité gratuit)
-  3. if/kimi-k2-thinking       (illimité gratuit)
-
-Coût mensuel : 0 $
-Accès via : WhatsApp, Telegram, Slack, Discord, iMessage, Signal...
-```
-
----
-
-## 💡 Fonctionnalités principales
-
-### 🧠 Routage & Intelligence
-
-| Fonctionnalité                        | Ce qu'elle fait                                                                 |
-| ------------------------------------- | ------------------------------------------------------------------------------- |
-| 🎯 **Fallback intelligent 4 niveaux** | Auto-routage : Abonnement → Clé API → Économique → Gratuit                      |
-| 📊 **Suivi des quotas en temps réel** | Comptage de tokens en direct + compte à rebours de réinitialisation             |
-| 🔄 **Traduction de format**           | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro transparent                            |
-| 👥 **Support multi-comptes**          | Plusieurs comptes par fournisseur avec sélection intelligente                   |
-| 🔄 **Renouvellement auto des tokens** | Les tokens OAuth se renouvellent automatiquement avec retry                     |
-| 🎨 **Combos personnalisés**           | 6 stratégies : fill-first, round-robin, p2c, random, least-used, cost-optimized |
-| 🧩 **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    |
-| 💬 **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        |
-
-### 🎵 APIs multi-modales
-
-| Fonctionnalité             | Ce qu'elle fait                                         |
-| -------------------------- | ------------------------------------------------------- |
-| 🖼️ **Génération d'images** | `/v1/images/generations` — 4 fournisseurs, 9+ modèles   |
-| 📐 **Embeddings**          | `/v1/embeddings` — 6 fournisseurs, 9+ modèles           |
-| 🎤 **Transcription audio** | `/v1/audio/transcriptions` — compatible Whisper         |
-| 🔊 **Texte vers parole**   | `/v1/audio/speech` — synthèse audio multi-fournisseur   |
-| 🛡️ **Modérations**         | `/v1/moderations` — vérifications de sécurité           |
-| 🔀 **Reranking**           | `/v1/rerank` — reclassement de pertinence des documents |
-
-### 🛡️ 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                |
-
-### 📊 Observabilité & Analytique
-
-| Fonctionnalité                    | Ce qu'elle fait                                                           |
-| --------------------------------- | ------------------------------------------------------------------------- |
-| 📝 **Logs de requêtes**           | Mode debug avec logs complets requête/réponse                             |
-| 💾 **Logs SQLite**                | Logs proxy persistants survivant aux redémarrages                         |
-| 📊 **Tableau de bord analytique** | Recharts : cartes de stats, graphique d'utilisation, tableau fournisseurs |
-| 📈 **Suivi de progression**       | Événements SSE de progression opt-in pour le streaming                    |
-| 🧪 **Évaluations LLM**            | Tests avec golden set et 4 stratégies de correspondance                   |
-| 🔍 **Télémétrie des requêtes**    | Agrégation de latence p50/p95/p99 + traçage X-Request-Id                  |
-| 📋 **Logs + Quotas**              | Pages dédiées pour navigation des logs et suivi des quotas                |
-| 🏥 **Tableau de bord santé**      | Uptime, états circuit breaker, lockouts, stats cache                      |
-| 💰 **Suivi des coûts**            | Gestion de budget + configuration des prix par modèle                     |
-
-### ☁️ Déploiement & Synchronisation
-
-| Fonctionnalité                    | Ce qu'elle fait                                                                 |
-| --------------------------------- | ------------------------------------------------------------------------------- |
-| 💾 **Cloud Sync**                 | Synchroniser les paramètres entre appareils via Cloudflare Workers              |
-| 🌐 **Déployer partout**           | Localhost, VPS, Docker, Cloudflare Workers                                      |
-| 🔑 **Gestion des clés API**       | Générer, faire tourner et limiter les clés API par fournisseur                  |
-| 🧙 **Assistant de configuration** | Setup guidé en 4 étapes pour les nouveaux utilisateurs                          |
-| 🔧 **Tableau de bord CLI Tools**  | Configuration en un clic pour Claude, Codex, Cline, OpenClaw, Kilo, Antigravity |
-| 🔄 **Sauvegardes DB**             | Sauvegarde et restauration automatiques de tous les paramètres                  |
-
-<details>
-<summary><b>📖 Détails des fonctionnalités</b></summary>
-
-### 🎯 Fallback intelligent 4 niveaux
-
-Créez des combos avec fallback automatique :
-
-```
-Combo : "my-coding-stack"
-  1. cc/claude-opus-4-6        (votre abonnement)
-  2. nvidia/llama-3.3-70b      (API NVIDIA gratuite)
-  3. glm/glm-4.7               (backup économique, $0.6/1M)
-  4. if/kimi-k2-thinking       (fallback gratuit)
-
-→ Bascule automatiquement lorsque le quota est épuisé ou en cas d'erreurs
-```
-
-### 📊 Suivi des quotas en temps réel
-
-- Consommation de tokens par fournisseur
-- Compte à rebours de réinitialisation (5 heures, quotidien, hebdomadaire)
-- Estimation des coûts pour les niveaux payants
-- Rapports de dépenses mensuels
-
-### 🔄 Traduction de format
-
-Traduction transparente entre les formats :
-
-- **OpenAI** ↔ **Claude** ↔ **Gemini** ↔ **OpenAI Responses**
-- Votre CLI envoie le format OpenAI → OmniRoute traduit → Le fournisseur reçoit le format natif
-- Fonctionne avec tout outil supportant les endpoints OpenAI personnalisés
-
-### 👥 Support multi-comptes
-
-- Ajouter plusieurs comptes par fournisseur
-- Round-robin automatique ou routage par priorité
-- Basculement vers le compte suivant lorsqu'un quota est atteint
-
-### 🔄 Renouvellement automatique des tokens
-
-- Les tokens OAuth se renouvellent automatiquement avant expiration
-- Pas de réauthentification manuelle nécessaire
-- Expérience transparente sur tous les fournisseurs
-
-### 🎨 Combos personnalisés
-
-- Créer des combinaisons de modèles illimitées
-- 6 stratégies : fill-first, round-robin, power-of-two-choices, random, least-used, cost-optimized
-- Partager les combos entre appareils avec Cloud Sync
-
-### 🏥 Tableau de bord santé
-
-- Statut du système (uptime, version, utilisation mémoire)
-- États des circuit breakers par fournisseur (Closed/Open/Half-Open)
-- Statut des rate limits et lockouts actifs
-- Statistiques du cache de signatures
-- Télémétrie de latence (p50/p95/p99) + cache de prompt
-- Réinitialisation de la santé en un clic
-
-### 🔧 Playground du traducteur
-
-- Déboguer, tester et visualiser les traductions de format d'API
-- Envoyer des requêtes et voir comment OmniRoute traduit entre les formats des fournisseurs
-- Inestimable pour résoudre les problèmes d'intégration
-
-### 💾 Cloud Sync
-
-- Synchroniser fournisseurs, combos et paramètres entre appareils
-- Synchronisation en arrière-plan automatique
-- Stockage chiffré sécurisé
-
-</details>
-
----
-
-## 📖 Guide de configuration
-
-<details>
-<summary><b>💳 Fournisseurs par abonnement</b></summary>
-
-### Claude Code (Pro/Max)
-
-```bash
-Tableau de bord → Fournisseurs → Connecter Claude Code
-→ Connexion OAuth → Renouvellement auto des tokens
-→ Suivi de quota 5h + hebdomadaire
-
-Modèles :
-  cc/claude-opus-4-6
-  cc/claude-sonnet-4-5-20250929
-  cc/claude-haiku-4-5-20251001
-```
-
-**Conseil Pro :** Utilisez Opus pour les tâches complexes, Sonnet pour la vitesse. OmniRoute suit les quotas par modèle !
-
-### OpenAI Codex (Plus/Pro)
-
-```bash
-Tableau de bord → Fournisseurs → Connecter Codex
-→ Connexion OAuth (port 1455)
-→ Reset 5h + hebdomadaire
-
-Modèles :
-  cx/gpt-5.2-codex
-  cx/gpt-5.1-codex-max
-```
-
-### Gemini CLI (GRATUIT 180K/mois !)
-
-```bash
-Tableau de bord → Fournisseurs → Connecter Gemini CLI
-→ Google OAuth
-→ 180K completions/mois + 1K/jour
-
-Modèles :
-  gc/gemini-3-flash-preview
-  gc/gemini-2.5-pro
-```
-
-**Meilleure valeur :** Niveau gratuit énorme ! Utilisez avant les niveaux payants.
-
-### GitHub Copilot
-
-```bash
-Tableau de bord → Fournisseurs → Connecter GitHub
-→ OAuth via GitHub
-→ Reset mensuel (1er du mois)
-
-Modèles :
-  gh/gpt-5
-  gh/claude-4.5-sonnet
-  gh/gemini-3-pro
-```
-
-</details>
-
-<details>
-<summary><b>🔑 Fournisseurs par clé API</b></summary>
-
-### NVIDIA NIM (GRATUIT 1000 crédits !)
-
-1. S'inscrire : [build.nvidia.com](https://build.nvidia.com)
-2. Obtenir une clé API gratuite (1000 crédits d'inférence inclus)
-3. Tableau de bord → Ajouter fournisseur → NVIDIA NIM :
-   - API Key : `nvapi-your-key`
-
-**Modèles :** `nvidia/llama-3.3-70b-instruct`, `nvidia/mistral-7b-instruct` et 50+ autres
-
-**Conseil Pro :** API compatible OpenAI — fonctionne parfaitement avec la traduction de format d'OmniRoute !
-
-### DeepSeek
-
-1. S'inscrire : [platform.deepseek.com](https://platform.deepseek.com)
-2. Obtenir une clé API
-3. Tableau de bord → Ajouter fournisseur → DeepSeek
-
-**Modèles :** `deepseek/deepseek-chat`, `deepseek/deepseek-coder`
-
-### Groq (Niveau gratuit disponible !)
-
-1. S'inscrire : [console.groq.com](https://console.groq.com)
-2. Obtenir une clé API (niveau gratuit inclus)
-3. Tableau de bord → Ajouter fournisseur → Groq
-
-**Modèles :** `groq/llama-3.3-70b`, `groq/mixtral-8x7b`
-
-**Conseil Pro :** Inférence ultra-rapide — idéal pour le codage en temps réel !
-
-### OpenRouter (100+ modèles)
-
-1. S'inscrire : [openrouter.ai](https://openrouter.ai)
-2. Obtenir une clé API
-3. Tableau de bord → Ajouter fournisseur → OpenRouter
-
-**Modèles :** Accès à 100+ modèles de tous les grands fournisseurs via une seule clé API.
-
-</details>
-
-<details>
-<summary><b>💰 Fournisseurs économiques (Backup)</b></summary>
-
-### GLM-4.7 (Reset quotidien, $0.6/1M)
-
-1. S'inscrire : [Zhipu AI](https://open.bigmodel.cn/)
-2. Obtenir une clé API du Coding Plan
-3. Tableau de bord → Ajouter clé API :
-   - Fournisseur : `glm`
-   - API Key : `your-key`
-
-**Utilisez :** `glm/glm-4.7`
-
-**Conseil Pro :** Le Coding Plan offre 3× le quota à 1/7 du coût ! Reset quotidien à 10h.
-
-### MiniMax M2.1 (Reset 5h, $0.20/1M)
-
-1. S'inscrire : [MiniMax](https://www.minimax.io/)
-2. Obtenir une clé API
-3. Tableau de bord → Ajouter clé API
-
-**Utilisez :** `minimax/MiniMax-M2.1`
-
-**Conseil Pro :** L'option la moins chère pour le contexte long (1M tokens) !
-
-### Kimi K2 (9 $/mois fixe)
-
-1. S'abonner : [Moonshot AI](https://platform.moonshot.ai/)
-2. Obtenir une clé API
-3. Tableau de bord → Ajouter clé API
-
-**Utilisez :** `kimi/kimi-latest`
-
-**Conseil Pro :** 9 $/mois fixe pour 10M tokens = 0,90 $/1M de coût effectif !
-
-</details>
-
-<details>
-<summary><b>🆓 Fournisseurs GRATUITS (Backup d'urgence)</b></summary>
-
-### iFlow (8 modèles GRATUITS)
-
-```bash
-Tableau de bord → Connecter iFlow
-→ Connexion OAuth iFlow
-→ Utilisation illimitée
-
-Modèles :
-  if/kimi-k2-thinking
-  if/qwen3-coder-plus
-  if/glm-4.7
-  if/minimax-m2
-  if/deepseek-r1
-```
-
-### Qwen (3 modèles GRATUITS)
-
-```bash
-Tableau de bord → Connecter Qwen
-→ Autorisation par code d'appareil
-→ Utilisation illimitée
-
-Modèles :
-  qw/qwen3-coder-plus
-  qw/qwen3-coder-flash
-```
-
-### Kiro (Claude GRATUIT)
-
-```bash
-Tableau de bord → Connecter Kiro
-→ AWS Builder ID ou Google/GitHub
-→ Utilisation illimitée
-
-Modèles :
-  kr/claude-sonnet-4.5
-  kr/claude-haiku-4.5
-```
-
-</details>
-
-<details>
-<summary><b>🎨 Créer des combos</b></summary>
-
-### Exemple 1 : Maximiser l'abonnement → Backup économique
-
-```
-Tableau de bord → Combos → Créer nouveau
-
-Nom : premium-coding
-Modèles :
-  1. cc/claude-opus-4-6 (Abonnement principal)
-  2. glm/glm-4.7 (Backup économique, $0.6/1M)
-  3. minimax/MiniMax-M2.1 (Fallback le moins cher, $0.20/1M)
-
-Utilisez en CLI : premium-coding
-```
-
-### Exemple 2 : Gratuit uniquement (Zéro coût)
-
-```
-Nom : free-combo
-Modèles :
-  1. gc/gemini-3-flash-preview (180K gratuits/mois)
-  2. if/kimi-k2-thinking (illimité)
-  3. qw/qwen3-coder-plus (illimité)
-
-Coût : 0 $ pour toujours !
-```
-
-</details>
-
-<details>
-<summary><b>🔧 Intégration CLI</b></summary>
-
-### Cursor IDE
-
-```
-Paramètres → Modèles → Avancé :
-  OpenAI API Base URL : http://localhost:20128/v1
-  OpenAI API Key : [du tableau de bord OmniRoute]
-  Model : cc/claude-opus-4-6
-```
-
-### Claude Code
-
-Utilisez la page **CLI Tools** dans le tableau de bord pour la configuration en un clic, ou modifiez `~/.claude/settings.json` manuellement.
-
-### Codex CLI
-
-```bash
-export OPENAI_BASE_URL="http://localhost:20128"
-export OPENAI_API_KEY="your-omniroute-api-key"
-
-codex "your prompt"
-```
-
-### OpenClaw
-
-**Option 1 — Tableau de bord (recommandé) :**
-
-```
-Tableau de bord → CLI Tools → OpenClaw → Sélectionner modèle → Appliquer
-```
-
-**Option 2 — Manuel :** Modifier `~/.openclaw/openclaw.json` :
-
-```json
-{
-  "models": {
-    "providers": {
-      "omniroute": {
-        "baseUrl": "http://127.0.0.1:20128/v1",
-        "apiKey": "sk_omniroute",
-        "api": "openai-completions"
-      }
-    }
-  }
-}
-```
-
-> **Note :** OpenClaw fonctionne uniquement avec OmniRoute local. Utilisez `127.0.0.1` au lieu de `localhost` pour éviter les problèmes de résolution IPv6.
-
-### Cline / Continue / RooCode
-
-```
-Paramètres → Configuration API :
-  Fournisseur : OpenAI Compatible
-  Base URL : http://localhost:20128/v1
-  API Key : [du tableau de bord OmniRoute]
-  Model : if/kimi-k2-thinking
-```
-
-</details>
-
----
-
-## 📊 Modèles disponibles
-
-<details>
-<summary><b>Voir tous les modèles disponibles</b></summary>
-
-**Claude Code (`cc/`)** - Pro/Max :
-
-- `cc/claude-opus-4-6`
-- `cc/claude-sonnet-4-5-20250929`
-- `cc/claude-haiku-4-5-20251001`
-
-**Codex (`cx/`)** - Plus/Pro :
-
-- `cx/gpt-5.2-codex`
-- `cx/gpt-5.1-codex-max`
-
-**Gemini CLI (`gc/`)** - GRATUIT :
-
-- `gc/gemini-3-flash-preview`
-- `gc/gemini-2.5-pro`
-
-**GitHub Copilot (`gh/`)** :
-
-- `gh/gpt-5`
-- `gh/claude-4.5-sonnet`
-
-**NVIDIA NIM (`nvidia/`)** - Crédits GRATUITS :
-
-- `nvidia/llama-3.3-70b-instruct`
-- `nvidia/mistral-7b-instruct`
-- 50+ modèles sur [build.nvidia.com](https://build.nvidia.com)
-
-**GLM (`glm/`)** - $0.6/1M :
-
-- `glm/glm-4.7`
-
-**MiniMax (`minimax/`)** - $0.2/1M :
-
-- `minimax/MiniMax-M2.1`
-
-**iFlow (`if/`)** - GRATUIT :
-
-- `if/kimi-k2-thinking`
-- `if/qwen3-coder-plus`
-- `if/deepseek-r1`
-- `if/glm-4.7`
-- `if/minimax-m2`
-
-**Qwen (`qw/`)** - GRATUIT :
-
-- `qw/qwen3-coder-plus`
-- `qw/qwen3-coder-flash`
-
-**Kiro (`kr/`)** - GRATUIT :
-
-- `kr/claude-sonnet-4.5`
-- `kr/claude-haiku-4.5`
-
-**OpenRouter (`or/`)** - 100+ modèles :
-
-- `or/anthropic/claude-4-sonnet`
-- `or/google/gemini-2.5-pro`
-- Tout modèle de [openrouter.ai/models](https://openrouter.ai/models)
-
-</details>
-
----
-
-## 🧪 Évaluations (Evals)
-
-OmniRoute inclut un framework d'évaluation intégré pour tester la qualité des réponses LLM contre un golden set. Accès via **Analytics → Evals** dans le tableau de bord.
-
-### Golden Set intégré
-
-Le « OmniRoute Golden Set » préchargé contient 10 cas de test :
-
-- Salutations, mathématiques, géographie, génération de code
-- Conformité format JSON, traduction, markdown
-- Rejet de sécurité (contenu nocif), comptage, logique booléenne
-
-### Stratégies d'évaluation
-
-| Stratégie  | Description                                                    | Exemple                          |
-| ---------- | -------------------------------------------------------------- | -------------------------------- |
-| `exact`    | La sortie doit correspondre exactement                         | `"4"`                            |
-| `contains` | La sortie doit contenir la sous-chaîne (insensible à la casse) | `"Paris"`                        |
-| `regex`    | La sortie doit correspondre au motif regex                     | `"1.*2.*3"`                      |
-| `custom`   | Fonction JS personnalisée retourne true/false                  | `(output) => output.length > 10` |
-
----
-
-## 🐛 Dépannage
-
-<details>
-<summary><b>Cliquez pour développer le guide de dépannage</b></summary>
-
-**« Language model did not provide messages »**
-
-- Quota du fournisseur épuisé → Vérifiez le suivi de quota dans le tableau de bord
-- Solution : Utilisez un combo avec fallback ou passez à un niveau moins cher
-
-**Rate limiting**
-
-- Quota d'abonnement épuisé → Fallback vers GLM/MiniMax
-- Ajoutez un combo : `cc/claude-opus-4-6 → glm/glm-4.7 → if/kimi-k2-thinking`
-
-**Token OAuth expiré**
-
-- Renouvelé automatiquement par OmniRoute
-- Si le problème persiste : Tableau de bord → Fournisseur → Reconnecter
-
-**Coûts élevés**
-
-- Vérifiez les statistiques d'utilisation dans Tableau de bord → Coûts
-- Changez le modèle principal pour GLM/MiniMax
-- Utilisez le niveau gratuit (Gemini CLI, iFlow) pour les tâches non critiques
-
-**Le tableau de bord s'ouvre sur le mauvais port**
-
-- Définissez `PORT=20128` et `NEXT_PUBLIC_BASE_URL=http://localhost:20128`
-
-**Erreurs de cloud sync**
-
-- Vérifiez que `BASE_URL` pointe vers votre instance en cours d'exécution
-- Vérifiez que `CLOUD_URL` pointe vers le point de terminaison cloud attendu
-- Gardez les valeurs `NEXT_PUBLIC_*` alignées avec les valeurs du serveur
-
-**Le premier login ne fonctionne pas**
-
-- Vérifiez `INITIAL_PASSWORD` dans `.env`
-- Si non défini, le mot de passe par défaut est `123456`
-
-**Pas de logs de requêtes**
-
-- Définissez `ENABLE_REQUEST_LOGS=true` dans `.env`
-
-**Le test de connexion affiche « Invalid » pour les fournisseurs compatibles OpenAI**
-
-- Beaucoup de fournisseurs n'exposent pas le point de terminaison `/models`
-- OmniRoute v1.0.6+ inclut une validation de secours via chat completions
-- Assurez-vous que l'URL de base inclut le suffixe `/v1`
-
-</details>
-
----
-
-## 🛠️ Stack technologique
-
-- **Runtime** : Node.js 20+
-- **Langage** : TypeScript 5.9 — **100% TypeScript** dans `src/` et `open-sse/` (v1.0.6)
-- **Framework** : Next.js 16 + React 19 + Tailwind CSS 4
-- **Base de données** : LowDB (JSON) + SQLite (état du domaine + logs proxy)
-- **Streaming** : Server-Sent Events (SSE)
-- **Auth** : OAuth 2.0 (PKCE) + JWT + API Keys
-- **Tests** : Node.js test runner (368+ tests unitaires)
-- **CI/CD** : GitHub Actions (publication automatique npm + Docker Hub lors du release)
-- **Site web** : [omniroute.online](https://omniroute.online)
-- **Package** : [npmjs.com/package/omniroute](https://www.npmjs.com/package/omniroute)
-- **Docker** : [hub.docker.com/r/diegosouzapw/omniroute](https://hub.docker.com/r/diegosouzapw/omniroute)
-- **Résilience** : Circuit breaker, backoff exponentiel, anti-thundering herd, spoofing TLS
-
----
-
-## 📖 Documentation
-
-| Document                                   | Description                                         |
-| ------------------------------------------ | --------------------------------------------------- |
-| [Guide utilisateur](docs/USER_GUIDE.md)    | Fournisseurs, combos, intégration CLI, déploiement  |
-| [Référence API](docs/API_REFERENCE.md)     | Tous les endpoints avec exemples                    |
-| [Dépannage](docs/TROUBLESHOOTING.md)       | Problèmes courants et solutions                     |
-| [Architecture](docs/ARCHITECTURE.md)       | Architecture système et détails internes            |
-| [Contribuer](CONTRIBUTING.md)              | Configuration de développement et directives        |
-| [Spécification OpenAPI](docs/openapi.yaml) | Spécification OpenAPI 3.0                           |
-| [Politique de sécurité](SECURITY.md)       | Signalement de vulnérabilités et pratiques sécurité |
-
----
-
-## 📧 Support
-
-> 💬 **Rejoignez notre communauté !** [Groupe WhatsApp](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) — Obtenez de l'aide, partagez des astuces et restez informé.
-
-- **Site web** : [omniroute.online](https://omniroute.online)
-- **GitHub** : [github.com/diegosouzapw/OmniRoute](https://github.com/diegosouzapw/OmniRoute)
-- **Issues** : [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
-- **WhatsApp** : [Groupe communautaire](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-- **Projet original** : [9router par decolua](https://github.com/decolua/9router)
-
----
-
-## 👥 Contributeurs
-
-[![Contributors](https://contrib.rocks/image?repo=diegosouzapw/OmniRoute&max=100&columns=20&anon=1)](https://github.com/diegosouzapw/OmniRoute/graphs/contributors)
-
-### Comment contribuer
-
-1. Forkez le dépôt
-2. Créez votre branche de fonctionnalité (`git checkout -b feature/amazing-feature`)
-3. Committez vos changements (`git commit -m 'Add amazing feature'`)
-4. Poussez vers la branche (`git push origin feature/amazing-feature`)
-5. Ouvrez une Pull Request
-
-Consultez [CONTRIBUTING.md](CONTRIBUTING.md) pour les directives détaillées.
-
-### Publier une nouvelle version
-
-```bash
-# Créer un release — la publication npm est automatique
-gh release create v1.0.6 --title "v1.0.6" --generate-notes
-```
-
----
-
-## 📊 Historique des Stars
-
-<a href="https://star-history.com/#diegosouzapw/OmniRoute&Date">
- <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date&theme=dark" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date" />
- </picture>
-</a>
-
----
-
-## 🙏 Remerciements
-
-Remerciements spéciaux à **[9router](https://github.com/decolua/9router)** par **[decolua](https://github.com/decolua)** — le projet original qui a inspiré ce fork. OmniRoute construit sur cette base incroyable avec des fonctionnalités supplémentaires, des APIs multi-modales et une réécriture complète en TypeScript.
-
-Remerciements spéciaux à **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** — l'implémentation originale en Go qui a inspiré ce portage en JavaScript.
-
----
-
-## 📄 Licence
-
-Licence MIT — voir [LICENSE](LICENSE) pour les détails.
-
----
-
-<div align="center">
-  <sub>Fait avec ❤️ pour les développeurs qui codent 24/7</sub>
-  <br/>
-  <sub><a href="https://omniroute.online">omniroute.online</a></sub>
-</div>

README.ru.md

@@ -1,999 +0,0 @@
-<div align="center">
-  <img src="./docs/screenshots/MainOmniRoute.png" alt="OmniRoute Dashboard" width="800"/>
-  
-  # 🚀 OmniRoute — Бесплатный AI Gateway
-
-### Никогда не прекращайте программировать. Умная маршрутизация к **БЕСПЛАТНЫМ и дешёвым AI-моделям** с автоматическим fallback.
-
-_Ваш универсальный API-прокси — одна точка доступа, 36+ провайдеров, нулевой простой._
-
-**Chat Completions • Embeddings • Генерация изображений • Аудио • Reranking • 100% TypeScript**
-
----
-
-### 🤖 Бесплатный AI-провайдер для ваших любимых агентов программирования
-
-_Подключайте любую IDE или CLI-инструмент с AI через OmniRoute — бесплатный API gateway для неограниченного программирования._
-
-  <table>
-    <tr>
-      <td align="center" width="110">
-        <a href="https://github.com/cline/cline">
-          <img src="./public/providers/openclaw.png" alt="OpenClaw" width="48"/><br/>
-          <b>OpenClaw</b>
-        </a><br/>
-        <sub>⭐ 205K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/HKUDS/nanobot">
-          <img src="./public/providers/nanobot.png" alt="NanoBot" width="48"/><br/>
-          <b>NanoBot</b>
-        </a><br/>
-        <sub>⭐ 20.9K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/sipeed/picoclaw">
-          <img src="./public/providers/picoclaw.jpg" alt="PicoClaw" width="48"/><br/>
-          <b>PicoClaw</b>
-        </a><br/>
-        <sub>⭐ 14.6K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/zeroclaw-labs/zeroclaw">
-          <img src="./public/providers/zeroclaw.png" alt="ZeroClaw" width="48"/><br/>
-          <b>ZeroClaw</b>
-        </a><br/>
-        <sub>⭐ 9.9K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/nearai/ironclaw">
-          <img src="./public/providers/ironclaw.png" alt="IronClaw" width="48"/><br/>
-          <b>IronClaw</b>
-        </a><br/>
-        <sub>⭐ 2.1K</sub>
-      </td>
-    </tr>
-    <tr>
-      <td align="center" width="110">
-        <a href="https://github.com/anomalyco/opencode">
-          <img src="./public/providers/opencode.svg" alt="OpenCode" width="48"/><br/>
-          <b>OpenCode</b>
-        </a><br/>
-        <sub>⭐ 106K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/openai/codex">
-          <img src="./public/providers/codex.png" alt="Codex CLI" width="48"/><br/>
-          <b>Codex CLI</b>
-        </a><br/>
-        <sub>⭐ 60.8K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/anthropics/claude-code">
-          <img src="./public/providers/claude.png" alt="Claude Code" width="48"/><br/>
-          <b>Claude Code</b>
-        </a><br/>
-        <sub>⭐ 67.3K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/google-gemini/gemini-cli">
-          <img src="./public/providers/gemini-cli.png" alt="Gemini CLI" width="48"/><br/>
-          <b>Gemini CLI</b>
-        </a><br/>
-        <sub>⭐ 94.7K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/Kilo-Org/kilocode">
-          <img src="./public/providers/kilocode.png" alt="Kilo Code" width="48"/><br/>
-          <b>Kilo Code</b>
-        </a><br/>
-        <sub>⭐ 15.5K</sub>
-      </td>
-    </tr>
-  </table>
-
-<sub>📡 Все агенты подключаются через <code>http://localhost:20128/v1</code> или <code>http://cloud.omniroute.online/v1</code> — одна конфигурация, неограниченные модели и квота</sub>
-
----
-
-[![npm version](https://img.shields.io/npm/v/omniroute?color=cb3837&logo=npm)](https://www.npmjs.com/package/omniroute)
-[![Docker Hub](https://img.shields.io/docker/v/diegosouzapw/omniroute?label=Docker%20Hub&logo=docker&color=2496ED)](https://hub.docker.com/r/diegosouzapw/omniroute)
-[![License](https://img.shields.io/github/license/diegosouzapw/OmniRoute)](https://github.com/diegosouzapw/OmniRoute/blob/main/LICENSE)
-[![Website](https://img.shields.io/badge/Website-omniroute.online-blue?logo=google-chrome&logoColor=white)](https://omniroute.online)
-[![WhatsApp](https://img.shields.io/badge/WhatsApp-Community-25D366?logo=whatsapp&logoColor=white)](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-
-[🌐 Сайт](https://omniroute.online) • [🚀 Быстрый старт](#-быстрый-старт) • [💡 Функции](#-основные-функции) • [📖 Документация](#-документация) • [💰 Цены](#-обзор-цен)
-
-🌐 **Доступно на:** [English](README.md) | [Português](README.pt-BR.md) | [Español](README.es.md) | [Русский](README.ru.md) | [中文](README.zh-CN.md) | [Deutsch](README.de.md) | [Français](README.fr.md) | [Italiano](README.it.md)
-
-</div>
-
----
-
-## 🤔 Почему OmniRoute?
-
-**Перестаньте тратить деньги и упираться в лимиты:**
-
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Квота подписки истекает неиспользованной каждый месяц
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Лимиты скорости останавливают вас посреди программирования
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Дорогие API ($20-50/месяц за провайдера)
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> Ручное переключение между провайдерами
-
-**OmniRoute решает это:**
-
-- ✅ **Максимизируйте подписки** — Отслеживайте квоты, используйте всё до сброса
-- ✅ **Автоматический fallback** — Подписка → API Key → Дешёвый → Бесплатный, нулевой простой
-- ✅ **Мульти-аккаунт** — Round-robin между аккаунтами каждого провайдера
-- ✅ **Универсальный** — Работает с Claude Code, Codex, Gemini CLI, Cursor, Cline, OpenClaw, любым CLI-инструментом
-
----
-
-## 🔄 Как это работает
-
-```
-┌─────────────┐
-│  Ваш CLI    │  (Claude Code, Codex, Gemini CLI, OpenClaw, Cursor, Cline...)
-│   Tool      │
-└──────┬──────┘
-       │ http://localhost:20128/v1
-       ↓
-┌─────────────────────────────────────────┐
-│        OmniRoute (Умный маршрутизатор)   │
-│  • Трансляция формата (OpenAI ↔ Claude) │
-│  • Отслеживание квот + Embeddings + Изображения │
-│  • Автообновление токенов               │
-└──────┬──────────────────────────────────┘
-       │
-       ├─→ [Tier 1: ПОДПИСКА] Claude Code, Codex, Gemini CLI
-       │   ↓ квота исчерпана
-       ├─→ [Tier 2: API KEY] DeepSeek, Groq, xAI, Mistral, NVIDIA NIM и др.
-       │   ↓ лимит бюджета
-       ├─→ [Tier 3: ДЕШЁВЫЙ] GLM ($0.6/1M), MiniMax ($0.2/1M)
-       │   ↓ лимит бюджета
-       └─→ [Tier 4: БЕСПЛАТНЫЙ] iFlow, Qwen, Kiro (неограниченно)
-
-Результат: Никогда не прекращайте программировать, минимальные затраты
-```
-
----
-
-## ⚡ Быстрый старт
-
-**1. Установите глобально:**
-
-```bash
-npm install -g omniroute
-omniroute
-```
-
-🎉 Dashboard открывается на `http://localhost:20128`
-
-| Команда                 | Описание                                   |
-| ----------------------- | ------------------------------------------ |
-| `omniroute`             | Запустить сервер (порт по умолчанию 20128) |
-| `omniroute --port 3000` | Использовать другой порт                   |
-| `omniroute --no-open`   | Не открывать браузер автоматически         |
-| `omniroute --help`      | Показать справку                           |
-
-**2. Подключите БЕСПЛАТНОГО провайдера:**
-
-Dashboard → Провайдеры → Подключить **Claude Code** или **Antigravity** → OAuth вход → Готово!
-
-**3. Используйте в CLI-инструменте:**
-
-```
-Claude Code/Codex/Gemini CLI/OpenClaw/Cursor/Cline Настройки:
-  Endpoint: http://localhost:20128/v1
-  API Key: [скопируйте из dashboard]
-  Model: if/kimi-k2-thinking
-```
-
-**Готово!** Начните программировать с БЕСПЛАТНЫМИ AI-моделями.
-
-**Альтернатива — запуск из исходного кода:**
-
-```bash
-cp .env.example .env
-npm install
-PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev
-```
-
----
-
-## 🐳 Docker
-
-OmniRoute доступен как публичный Docker-образ на [Docker Hub](https://hub.docker.com/r/diegosouzapw/omniroute).
-
-**Быстрый запуск:**
-
-```bash
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-**С файлом окружения:**
-
-```bash
-# Скопируйте и отредактируйте .env
-cp .env.example .env
-
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  --env-file .env \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-**Используя Docker Compose:**
-
-```bash
-# Базовый профиль (без CLI-инструментов)
-docker compose --profile base up -d
-
-# CLI-профиль (Claude Code, Codex, OpenClaw встроены)
-docker compose --profile cli up -d
-```
-
-| Образ                    | Тег      | Размер | Описание                   |
-| ------------------------ | -------- | ------ | -------------------------- |
-| `diegosouzapw/omniroute` | `latest` | ~250MB | Последний стабильный релиз |
-| `diegosouzapw/omniroute` | `1.0.6`  | ~250MB | Текущая версия             |
-
----
-
-## 💰 Обзор цен
-
-| Tier              | Провайдер         | Стоимость                     | Сброс квоты        | Лучше всего для                  |
-| ----------------- | ----------------- | ----------------------------- | ------------------ | -------------------------------- |
-| **💳 ПОДПИСКА**   | Claude Code (Pro) | $20/мес                       | 5ч + еженедельно   | Уже подписан                     |
-|                   | Codex (Plus/Pro)  | $20-200/мес                   | 5ч + еженедельно   | Пользователи OpenAI              |
-|                   | Gemini CLI        | **БЕСПЛАТНО**                 | 180K/мес + 1K/день | Все!                             |
-|                   | GitHub Copilot    | $10-19/мес                    | Ежемесячно         | Пользователи GitHub              |
-| **🔑 API KEY**    | NVIDIA NIM        | **БЕСПЛАТНО** (1000 кредитов) | Одноразово         | Бесплатное тестирование          |
-|                   | DeepSeek          | По использованию              | Нет                | Лучшее соотношение цена/качество |
-|                   | Groq              | Беспл. уровень + платный      | Ограничено         | Сверхбыстрый вывод               |
-|                   | xAI (Grok)        | По использованию              | Нет                | Модели Grok                      |
-|                   | Mistral           | Беспл. уровень + платный      | Ограничено         | Европейский AI                   |
-|                   | OpenRouter        | По использованию              | Нет                | 100+ моделей                     |
-| **💰 ДЕШЁВЫЙ**    | GLM-4.7           | $0.6/1M                       | Ежедневно 10ч      | Бюджетный бэкап                  |
-|                   | MiniMax M2.1      | $0.2/1M                       | 5ч ротация         | Самый дешёвый вариант            |
-|                   | Kimi K2           | $9/мес фикс                   | 10M токенов/мес    | Предсказуемая цена               |
-| **🆓 БЕСПЛАТНЫЙ** | iFlow             | $0                            | Неограниченно      | 8 бесплатных моделей             |
-|                   | Qwen              | $0                            | Неограниченно      | 3 бесплатные модели              |
-|                   | Kiro              | $0                            | Неограниченно      | Claude бесплатно                 |
-
-**💡 Совет:** Начните с Gemini CLI (180K бесплатно/мес) + iFlow (неограниченно бесплатно) = $0!
-
----
-
-## 🎯 Сценарии использования
-
-### Сценарий 1: «У меня подписка Claude Pro»
-
-**Проблема:** Квота истекает неиспользованной, лимиты скорости во время интенсивного программирования
-
-```
-Combo: "maximize-claude"
-  1. cc/claude-opus-4-6        (используйте подписку полностью)
-  2. glm/glm-4.7               (дешёвый бэкап при исчерпании квоты)
-  3. if/kimi-k2-thinking       (бесплатный аварийный fallback)
-
-Месячная стоимость: $20 (подписка) + ~$5 (бэкап) = $25 итого
-vs. $20 + упирание в лимиты = разочарование
-```
-
-### Сценарий 2: «Хочу нулевую стоимость»
-
-**Проблема:** Не может позволить подписки, нужен надёжный AI для программирования
-
-```
-Combo: "free-forever"
-  1. gc/gemini-3-flash         (180K бесплатно/мес)
-  2. if/kimi-k2-thinking       (неограниченно бесплатно)
-  3. qw/qwen3-coder-plus       (неограниченно бесплатно)
-
-Месячная стоимость: $0
-Качество: Модели готовые к продакшену
-```
-
-### Сценарий 3: «Мне нужно программировать 24/7, без перерывов»
-
-**Проблема:** Дедлайны, не может позволить простой
-
-```
-Combo: "always-on"
-  1. cc/claude-opus-4-6        (лучшее качество)
-  2. cx/gpt-5.2-codex          (вторая подписка)
-  3. glm/glm-4.7               (дешёвый, ежедневный сброс)
-  4. minimax/MiniMax-M2.1      (самый дешёвый, сброс 5ч)
-  5. if/kimi-k2-thinking       (бесплатно неограниченно)
-
-Результат: 5 уровней fallback = нулевой простой
-```
-
-### Сценарий 4: «Хочу БЕСПЛАТНЫЙ AI в OpenClaw»
-
-**Проблема:** Нужен AI-ассистент в мессенджерах, полностью бесплатно
-
-```
-Combo: "openclaw-free"
-  1. if/glm-4.7                (неограниченно бесплатно)
-  2. if/minimax-m2.1           (неограниченно бесплатно)
-  3. if/kimi-k2-thinking       (неограниченно бесплатно)
-
-Месячная стоимость: $0
-Доступ через: WhatsApp, Telegram, Slack, Discord, iMessage, Signal...
-```
-
----
-
-## 💡 Основные функции
-
-### 🧠 Маршрутизация и интеллект
-
-| Функция                                     | Что делает                                                                    |
-| ------------------------------------------- | ----------------------------------------------------------------------------- |
-| 🎯 **Умный 4-уровневый Fallback**           | Авто-маршрутизация: Подписка → API Key → Дешёвый → Бесплатный                 |
-| 📊 **Отслеживание квот в реальном времени** | Счётчик токенов в реальном времени + обратный отсчёт до сброса                |
-| 🔄 **Трансляция формата**                   | OpenAI ↔ Claude ↔ Gemini ↔ Cursor ↔ Kiro бесшовно                             |
-| 👥 **Мульти-аккаунт**                       | Несколько аккаунтов на провайдера с интеллектуальным выбором                  |
-| 🔄 **Автообновление токенов**               | OAuth-токены обновляются автоматически с повторами                            |
-| 🎨 **Пользовательские комбо**               | 6 стратегий: fill-first, round-robin, p2c, random, least-used, cost-optimized |
-| 🧩 **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           |
-| 💬 **Инъекция System Prompt**               | Глобальный system prompt для всех запросов                                    |
-| 📄 **API Responses**                        | Полная поддержка OpenAI Responses API (`/v1/responses`) для Codex             |
-
-### 🎵 Мультимодальные API
-
-| Функция                      | Что делает                                          |
-| ---------------------------- | --------------------------------------------------- |
-| 🖼️ **Генерация изображений** | `/v1/images/generations` — 4 провайдера, 9+ моделей |
-| 📐 **Embeddings**            | `/v1/embeddings` — 6 провайдеров, 9+ моделей        |
-| 🎤 **Транскрипция аудио**    | `/v1/audio/transcriptions` — Совместимо с Whisper   |
-| 🔊 **Текст в речь**          | `/v1/audio/speech` — Мульти-провайдерный синтез     |
-| 🛡️ **Модерация**             | `/v1/moderations` — Проверки безопасности контента  |
-| 🔀 **Reranking**             | `/v1/rerank` — Переранжирование релевантности       |
-
-### 🛡️ 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 |
-
-### 📊 Наблюдаемость и аналитика
-
-| Функция                       | Что делает                                                               |
-| ----------------------------- | ------------------------------------------------------------------------ |
-| 📝 **Логи запросов**          | Режим debug с полными логами запросов/ответов                            |
-| 💾 **Логи SQLite**            | Постоянные proxy-логи переживают перезапуски                             |
-| 📊 **Dashboard аналитики**    | Recharts: карточки статистики, график использования, таблица провайдеров |
-| 📈 **Отслеживание прогресса** | Opt-in SSE-события прогресса для стриминга                               |
-| 🧪 **Оценки LLM**             | Тестирование с golden set и 4 стратегиями сравнения                      |
-| 🔍 **Телеметрия запросов**    | Агрегация латентности p50/p95/p99 + трекинг X-Request-Id                 |
-| 📋 **Логи + Квоты**           | Отдельные страницы для просмотра логов и отслеживания квот               |
-| 🏥 **Dashboard здоровья**     | Uptime, состояния circuit breaker, блокировки, статистика кеша           |
-| 💰 **Отслеживание стоимости** | Управление бюджетом + настройка цен по моделям                           |
-
-### ☁️ Деплой и синхронизация
-
-| Функция                    | Что делает                                                                  |
-| -------------------------- | --------------------------------------------------------------------------- |
-| 💾 **Cloud Sync**          | Синхронизация настроек между устройствами через Cloudflare Workers          |
-| 🌐 **Деплой куда угодно**  | Localhost, VPS, Docker, Cloudflare Workers                                  |
-| 🔑 **Управление API Keys** | Генерация, ротация и настройка scope API keys по провайдерам                |
-| 🧙 **Мастер настройки**    | 4-шаговая настройка для новых пользователей                                 |
-| 🔧 **Dashboard CLI Tools** | Настройка в один клик для Claude, Codex, Cline, OpenClaw, Kilo, Antigravity |
-| 🔄 **Бэкапы БД**           | Автоматическое резервное копирование и восстановление всех настроек         |
-
-<details>
-<summary><b>📖 Подробности функций</b></summary>
-
-### 🎯 Умный 4-уровневый Fallback
-
-Создавайте комбо с автоматическим fallback:
-
-```
-Combo: "my-coding-stack"
-  1. cc/claude-opus-4-6        (ваша подписка)
-  2. nvidia/llama-3.3-70b      (бесплатный NVIDIA API)
-  3. glm/glm-4.7               (дешёвый бэкап, $0.6/1M)
-  4. if/kimi-k2-thinking       (бесплатный fallback)
-
-→ Автоматически переключается при исчерпании квоты или ошибках
-```
-
-### 📊 Отслеживание квот в реальном времени
-
-- Потребление токенов по провайдерам
-- Обратный отсчёт до сброса (5 часов, ежедневно, еженедельно)
-- Оценка стоимости для платных уровней
-- Ежемесячные отчёты о расходах
-
-### 🔄 Трансляция формата
-
-Бесшовная трансляция между форматами:
-
-- **OpenAI** ↔ **Claude** ↔ **Gemini** ↔ **OpenAI Responses**
-- Ваш CLI отправляет формат OpenAI → OmniRoute транслирует → Провайдер получает нативный формат
-- Работает с любым инструментом, поддерживающим пользовательские OpenAI endpoints
-
-### 👥 Мульти-аккаунт
-
-- Добавляйте несколько аккаунтов на провайдера
-- Автоматический round-robin или маршрутизация по приоритету
-- Fallback на следующий аккаунт при исчерпании квоты
-
-### 🔄 Автообновление токенов
-
-- OAuth-токены обновляются автоматически до истечения
-- Без необходимости ручной повторной аутентификации
-- Бесшовный опыт по всем провайдерам
-
-### 🎨 Пользовательские комбо
-
-- Создавайте неограниченные комбинации моделей
-- 6 стратегий: fill-first, round-robin, power-of-two-choices, random, least-used, cost-optimized
-- Делитесь комбо между устройствами с Cloud Sync
-
-### 🏥 Dashboard здоровья
-
-- Статус системы (uptime, версия, использование памяти)
-- Состояния circuit breaker по провайдерам (Closed/Open/Half-Open)
-- Статус rate limit и активные блокировки
-- Статистика кеша сигнатур
-- Телеметрия латентности (p50/p95/p99) + кеш промптов
-- Сброс состояния здоровья одним кликом
-
-### 🔧 Playground транслятора
-
-- Отладка, тестирование и визуализация трансляции форматов API
-- Отправляйте запросы и смотрите, как OmniRoute транслирует между форматами провайдеров
-- Бесценно для устранения проблем интеграции
-
-### 💾 Cloud Sync
-
-- Синхронизация провайдеров, комбо и настроек между устройствами
-- Автоматическая фоновая синхронизация
-- Безопасное шифрованное хранилище
-
-</details>
-
----
-
-## 📖 Руководство по настройке
-
-<details>
-<summary><b>💳 Провайдеры по подписке</b></summary>
-
-### Claude Code (Pro/Max)
-
-```bash
-Dashboard → Провайдеры → Подключить Claude Code
-→ OAuth вход → Автообновление токенов
-→ Отслеживание квоты 5ч + еженедельно
-
-Модели:
-  cc/claude-opus-4-6
-  cc/claude-sonnet-4-5-20250929
-  cc/claude-haiku-4-5-20251001
-```
-
-**Совет:** Используйте Opus для сложных задач, Sonnet для скорости. OmniRoute отслеживает квоту по моделям!
-
-### OpenAI Codex (Plus/Pro)
-
-```bash
-Dashboard → Провайдеры → Подключить Codex
-→ OAuth вход (порт 1455)
-→ Сброс 5ч + еженедельно
-
-Модели:
-  cx/gpt-5.2-codex
-  cx/gpt-5.1-codex-max
-```
-
-### Gemini CLI (БЕСПЛАТНО 180K/мес!)
-
-```bash
-Dashboard → Провайдеры → Подключить Gemini CLI
-→ Google OAuth
-→ 180K completions/мес + 1K/день
-
-Модели:
-  gc/gemini-3-flash-preview
-  gc/gemini-2.5-pro
-```
-
-**Лучшая ценность:** Огромный бесплатный уровень! Используйте перед платными.
-
-### GitHub Copilot
-
-```bash
-Dashboard → Провайдеры → Подключить GitHub
-→ OAuth через GitHub
-→ Ежемесячный сброс (1-е число)
-
-Модели:
-  gh/gpt-5
-  gh/claude-4.5-sonnet
-  gh/gemini-3-pro
-```
-
-</details>
-
-<details>
-<summary><b>🔑 Провайдеры по API Key</b></summary>
-
-### NVIDIA NIM (БЕСПЛАТНО 1000 кредитов!)
-
-1. Регистрация: [build.nvidia.com](https://build.nvidia.com)
-2. Получите бесплатный API key (1000 кредитов включены)
-3. Dashboard → Добавить провайдера → NVIDIA NIM:
-   - API Key: `nvapi-your-key`
-
-**Модели:** `nvidia/llama-3.3-70b-instruct`, `nvidia/mistral-7b-instruct` и 50+ других
-
-**Совет:** OpenAI-совместимый API — работает идеально с трансляцией форматов OmniRoute!
-
-### DeepSeek
-
-1. Регистрация: [platform.deepseek.com](https://platform.deepseek.com)
-2. Получите API key
-3. Dashboard → Добавить провайдера → DeepSeek
-
-**Модели:** `deepseek/deepseek-chat`, `deepseek/deepseek-coder`
-
-### Groq (Бесплатный уровень доступен!)
-
-1. Регистрация: [console.groq.com](https://console.groq.com)
-2. Получите API key (бесплатный уровень включён)
-3. Dashboard → Добавить провайдера → Groq
-
-**Модели:** `groq/llama-3.3-70b`, `groq/mixtral-8x7b`
-
-**Совет:** Сверхбыстрый вывод — лучший для программирования в реальном времени!
-
-### OpenRouter (100+ моделей)
-
-1. Регистрация: [openrouter.ai](https://openrouter.ai)
-2. Получите API key
-3. Dashboard → Добавить провайдера → OpenRouter
-
-**Модели:** Доступ к 100+ моделям от всех основных провайдеров через один API key.
-
-</details>
-
-<details>
-<summary><b>💰 Дешёвые провайдеры (Бэкап)</b></summary>
-
-### GLM-4.7 (Ежедневный сброс, $0.6/1M)
-
-1. Регистрация: [Zhipu AI](https://open.bigmodel.cn/)
-2. Получите API key из Coding Plan
-3. Dashboard → Добавить API Key:
-   - Провайдер: `glm`
-   - API Key: `your-key`
-
-**Используйте:** `glm/glm-4.7`
-
-**Совет:** Coding Plan предлагает 3× квоту по цене 1/7! Ежедневный сброс в 10:00.
-
-### MiniMax M2.1 (Сброс 5ч, $0.20/1M)
-
-1. Регистрация: [MiniMax](https://www.minimax.io/)
-2. Получите API key
-3. Dashboard → Добавить API Key
-
-**Используйте:** `minimax/MiniMax-M2.1`
-
-**Совет:** Самый дешёвый вариант для длинного контекста (1M токенов)!
-
-### Kimi K2 ($9/мес фикс)
-
-1. Подпишитесь: [Moonshot AI](https://platform.moonshot.ai/)
-2. Получите API key
-3. Dashboard → Добавить API Key
-
-**Используйте:** `kimi/kimi-latest`
-
-**Совет:** Фикс $9/мес за 10M токенов = $0.90/1M эффективная стоимость!
-
-</details>
-
-<details>
-<summary><b>🆓 БЕСПЛАТНЫЕ провайдеры (Аварийный бэкап)</b></summary>
-
-### iFlow (8 БЕСПЛАТНЫХ моделей)
-
-```bash
-Dashboard → Подключить iFlow
-→ OAuth вход iFlow
-→ Неограниченное использование
-
-Модели:
-  if/kimi-k2-thinking
-  if/qwen3-coder-plus
-  if/glm-4.7
-  if/minimax-m2
-  if/deepseek-r1
-```
-
-### Qwen (3 БЕСПЛАТНЫЕ модели)
-
-```bash
-Dashboard → Подключить Qwen
-→ Авторизация по коду устройства
-→ Неограниченное использование
-
-Модели:
-  qw/qwen3-coder-plus
-  qw/qwen3-coder-flash
-```
-
-### Kiro (Claude БЕСПЛАТНО)
-
-```bash
-Dashboard → Подключить Kiro
-→ AWS Builder ID или Google/GitHub
-→ Неограниченное использование
-
-Модели:
-  kr/claude-sonnet-4.5
-  kr/claude-haiku-4.5
-```
-
-</details>
-
-<details>
-<summary><b>🎨 Создание комбо</b></summary>
-
-### Пример 1: Максимизация подписки → Дешёвый бэкап
-
-```
-Dashboard → Комбо → Создать новое
-
-Название: premium-coding
-Модели:
-  1. cc/claude-opus-4-6 (Основная подписка)
-  2. glm/glm-4.7 (Дешёвый бэкап, $0.6/1M)
-  3. minimax/MiniMax-M2.1 (Самый дешёвый fallback, $0.20/1M)
-
-Используйте в CLI: premium-coding
-```
-
-### Пример 2: Только бесплатные (Нулевая стоимость)
-
-```
-Название: free-combo
-Модели:
-  1. gc/gemini-3-flash-preview (180K бесплатно/мес)
-  2. if/kimi-k2-thinking (неограниченно)
-  3. qw/qwen3-coder-plus (неограниченно)
-
-Стоимость: $0 навсегда!
-```
-
-</details>
-
-<details>
-<summary><b>🔧 Интеграция с CLI</b></summary>
-
-### Cursor IDE
-
-```
-Настройки → Модели → Расширенные:
-  OpenAI API Base URL: http://localhost:20128/v1
-  OpenAI API Key: [из dashboard OmniRoute]
-  Model: cc/claude-opus-4-6
-```
-
-### Claude Code
-
-Используйте страницу **CLI Tools** в dashboard для настройки в один клик, или редактируйте `~/.claude/settings.json` вручную.
-
-### Codex CLI
-
-```bash
-export OPENAI_BASE_URL="http://localhost:20128"
-export OPENAI_API_KEY="your-omniroute-api-key"
-
-codex "your prompt"
-```
-
-### OpenClaw
-
-**Вариант 1 — Dashboard (рекомендуется):**
-
-```
-Dashboard → CLI Tools → OpenClaw → Выбрать модель → Применить
-```
-
-**Вариант 2 — Вручную:** Редактируйте `~/.openclaw/openclaw.json`:
-
-```json
-{
-  "models": {
-    "providers": {
-      "omniroute": {
-        "baseUrl": "http://127.0.0.1:20128/v1",
-        "apiKey": "sk_omniroute",
-        "api": "openai-completions"
-      }
-    }
-  }
-}
-```
-
-> **Примечание:** OpenClaw работает только с локальным OmniRoute. Используйте `127.0.0.1` вместо `localhost` для избежания проблем с IPv6.
-
-### Cline / Continue / RooCode
-
-```
-Настройки → Конфигурация API:
-  Провайдер: OpenAI Compatible
-  Base URL: http://localhost:20128/v1
-  API Key: [из dashboard OmniRoute]
-  Model: if/kimi-k2-thinking
-```
-
-</details>
-
----
-
-## 📊 Доступные модели
-
-<details>
-<summary><b>Посмотреть все доступные модели</b></summary>
-
-**Claude Code (`cc/`)** - Pro/Max:
-
-- `cc/claude-opus-4-6`
-- `cc/claude-sonnet-4-5-20250929`
-- `cc/claude-haiku-4-5-20251001`
-
-**Codex (`cx/`)** - Plus/Pro:
-
-- `cx/gpt-5.2-codex`
-- `cx/gpt-5.1-codex-max`
-
-**Gemini CLI (`gc/`)** - БЕСПЛАТНО:
-
-- `gc/gemini-3-flash-preview`
-- `gc/gemini-2.5-pro`
-
-**GitHub Copilot (`gh/`)**:
-
-- `gh/gpt-5`
-- `gh/claude-4.5-sonnet`
-
-**NVIDIA NIM (`nvidia/`)** - БЕСПЛАТНЫЕ кредиты:
-
-- `nvidia/llama-3.3-70b-instruct`
-- `nvidia/mistral-7b-instruct`
-- 50+ моделей на [build.nvidia.com](https://build.nvidia.com)
-
-**GLM (`glm/`)** - $0.6/1M:
-
-- `glm/glm-4.7`
-
-**MiniMax (`minimax/`)** - $0.2/1M:
-
-- `minimax/MiniMax-M2.1`
-
-**iFlow (`if/`)** - БЕСПЛАТНО:
-
-- `if/kimi-k2-thinking`
-- `if/qwen3-coder-plus`
-- `if/deepseek-r1`
-- `if/glm-4.7`
-- `if/minimax-m2`
-
-**Qwen (`qw/`)** - БЕСПЛАТНО:
-
-- `qw/qwen3-coder-plus`
-- `qw/qwen3-coder-flash`
-
-**Kiro (`kr/`)** - БЕСПЛАТНО:
-
-- `kr/claude-sonnet-4.5`
-- `kr/claude-haiku-4.5`
-
-**OpenRouter (`or/`)** - 100+ моделей:
-
-- `or/anthropic/claude-4-sonnet`
-- `or/google/gemini-2.5-pro`
-- Любая модель с [openrouter.ai/models](https://openrouter.ai/models)
-
-</details>
-
----
-
-## 🧪 Оценки (Evals)
-
-OmniRoute включает встроенный фреймворк оценки для тестирования качества ответов LLM по golden set. Доступ через **Analytics → Evals** в dashboard.
-
-### Встроенный Golden Set
-
-Предзагруженный «OmniRoute Golden Set» содержит 10 тестов:
-
-- Приветствия, математика, география, генерация кода
-- Соответствие формату JSON, перевод, markdown
-- Отказ от небезопасного контента, подсчёт, булева логика
-
-### Стратегии оценки
-
-| Стратегия  | Описание                                              | Пример                           |
-| ---------- | ----------------------------------------------------- | -------------------------------- |
-| `exact`    | Вывод должен совпадать точно                          | `"4"`                            |
-| `contains` | Вывод должен содержать подстроку (без учёта регистра) | `"Paris"`                        |
-| `regex`    | Вывод должен соответствовать regex-паттерну           | `"1.*2.*3"`                      |
-| `custom`   | Пользовательская JS-функция возвращает true/false     | `(output) => output.length > 10` |
-
----
-
-## 🐛 Устранение неполадок
-
-<details>
-<summary><b>Нажмите для раскрытия руководства</b></summary>
-
-**«Language model did not provide messages»**
-
-- Квота провайдера исчерпана → Проверьте трекер квот в dashboard
-- Решение: Используйте комбо с fallback или переключитесь на более дешёвый уровень
-
-**Rate limiting**
-
-- Квота подписки исчерпана → Fallback на GLM/MiniMax
-- Добавьте комбо: `cc/claude-opus-4-6 → glm/glm-4.7 → if/kimi-k2-thinking`
-
-**OAuth-токен истёк**
-
-- Обновляется автоматически OmniRoute
-- Если проблема сохраняется: Dashboard → Провайдер → Переподключить
-
-**Высокие расходы**
-
-- Проверьте статистику в Dashboard → Расходы
-- Переключите основную модель на GLM/MiniMax
-- Используйте бесплатный уровень (Gemini CLI, iFlow) для некритичных задач
-
-**Dashboard открывается на неправильном порту**
-
-- Установите `PORT=20128` и `NEXT_PUBLIC_BASE_URL=http://localhost:20128`
-
-**Ошибки cloud sync**
-
-- Проверьте что `BASE_URL` указывает на ваш запущенный экземпляр
-- Проверьте что `CLOUD_URL` указывает на правильный облачный endpoint
-- Держите значения `NEXT_PUBLIC_*` синхронизированными с серверными значениями
-
-**Первый вход не работает**
-
-- Проверьте `INITIAL_PASSWORD` в `.env`
-- Если не задан, пароль по умолчанию `123456`
-
-**Нет логов запросов**
-
-- Установите `ENABLE_REQUEST_LOGS=true` в `.env`
-
-**Тест подключения показывает «Invalid» для OpenAI-совместимых провайдеров**
-
-- Многие провайдеры не предоставляют endpoint `/models`
-- OmniRoute v1.0.6+ включает fallback-валидацию через chat completions
-- Убедитесь что base URL содержит суффикс `/v1`
-
-</details>
-
----
-
-## 🛠️ Технологический стек
-
-- **Runtime**: Node.js 20+
-- **Язык**: TypeScript 5.9 — **100% TypeScript** в `src/` и `open-sse/` (v1.0.6)
-- **Framework**: Next.js 16 + React 19 + Tailwind CSS 4
-- **База данных**: LowDB (JSON) + SQLite (состояние домена + proxy-логи)
-- **Стриминг**: Server-Sent Events (SSE)
-- **Аутентификация**: OAuth 2.0 (PKCE) + JWT + API Keys
-- **Тестирование**: Node.js test runner (368+ юнит-тестов)
-- **CI/CD**: GitHub Actions (авто-публикация npm + Docker Hub при релизе)
-- **Сайт**: [omniroute.online](https://omniroute.online)
-- **Пакет**: [npmjs.com/package/omniroute](https://www.npmjs.com/package/omniroute)
-- **Docker**: [hub.docker.com/r/diegosouzapw/omniroute](https://hub.docker.com/r/diegosouzapw/omniroute)
-- **Устойчивость**: Circuit breaker, экспоненциальный backoff, anti-thundering herd, TLS-спуфинг
-
----
-
-## 📖 Документация
-
-| Документ                                        | Описание                                         |
-| ----------------------------------------------- | ------------------------------------------------ |
-| [Руководство пользователя](docs/USER_GUIDE.md)  | Провайдеры, комбо, интеграция CLI, деплой        |
-| [Справка API](docs/API_REFERENCE.md)            | Все endpoints с примерами                        |
-| [Устранение неполадок](docs/TROUBLESHOOTING.md) | Частые проблемы и решения                        |
-| [Архитектура](docs/ARCHITECTURE.md)             | Архитектура системы и внутреннее устройство      |
-| [Как внести вклад](CONTRIBUTING.md)             | Настройка разработки и руководящие принципы      |
-| [Спецификация OpenAPI](docs/openapi.yaml)       | Спецификация OpenAPI 3.0                         |
-| [Политика безопасности](SECURITY.md)            | Сообщение об уязвимостях и практики безопасности |
-
----
-
-## 📧 Поддержка
-
-> 💬 **Присоединяйтесь к сообществу!** [Группа WhatsApp](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) — Получайте помощь, делитесь советами и оставайтесь в курсе.
-
-- **Сайт**: [omniroute.online](https://omniroute.online)
-- **GitHub**: [github.com/diegosouzapw/OmniRoute](https://github.com/diegosouzapw/OmniRoute)
-- **Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
-- **WhatsApp**: [Группа сообщества](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-- **Оригинальный проект**: [9router от decolua](https://github.com/decolua/9router)
-
----
-
-## 👥 Участники
-
-[![Contributors](https://contrib.rocks/image?repo=diegosouzapw/OmniRoute&max=100&columns=20&anon=1)](https://github.com/diegosouzapw/OmniRoute/graphs/contributors)
-
-### Как внести вклад
-
-1. Сделайте fork репозитория
-2. Создайте ветку функции (`git checkout -b feature/amazing-feature`)
-3. Зафиксируйте изменения (`git commit -m 'Add amazing feature'`)
-4. Отправьте в ветку (`git push origin feature/amazing-feature`)
-5. Откройте Pull Request
-
-См. [CONTRIBUTING.md](CONTRIBUTING.md) для подробных рекомендаций.
-
-### Выпуск новой версии
-
-```bash
-# Создайте релиз — публикация в npm происходит автоматически
-gh release create v1.0.6 --title "v1.0.6" --generate-notes
-```
-
----
-
-## 📊 История звёзд
-
-<a href="https://star-history.com/#diegosouzapw/OmniRoute&Date">
- <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date&theme=dark" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date" />
- </picture>
-</a>
-
----
-
-## 🙏 Благодарности
-
-Особая благодарность **[9router](https://github.com/decolua/9router)** от **[decolua](https://github.com/decolua)** — оригинальному проекту, вдохновившему этот форк. OmniRoute строится на этом невероятном фундаменте с дополнительными функциями, мультимодальными API и полной переписью на TypeScript.
-
-Особая благодарность **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** — оригинальной реализации на Go, вдохновившей этот порт на JavaScript.
-
----
-
-## 📄 Лицензия
-
-Лицензия MIT — см. [LICENSE](LICENSE) для подробностей.
-
----
-
-<div align="center">
-  <sub>Сделано с ❤️ для разработчиков, которые программируют 24/7</sub>
-  <br/>
-  <sub><a href="https://omniroute.online">omniroute.online</a></sub>
-</div>

README.zh-CN.md

@@ -1,999 +0,0 @@
-<div align="center">
-  <img src="./docs/screenshots/MainOmniRoute.png" alt="OmniRoute Dashboard" width="800"/>
-  
-  # 🚀 OmniRoute — 免费 AI 网关
-
-### 永不停止编程。智能路由至**免费和低成本 AI 模型**，自动故障转移。
-
-_您的通用 API 代理 — 一个端点，36+ 提供商，零停机时间。_
-
-**Chat Completions • Embeddings • 图像生成 • 音频 • Reranking • 100% TypeScript**
-
----
-
-### 🤖 为您最爱的编程代理提供免费 AI
-
-_通过 OmniRoute 连接任何 AI 驱动的 IDE 或 CLI 工具 — 免费 API 网关，无限编程。_
-
-  <table>
-    <tr>
-      <td align="center" width="110">
-        <a href="https://github.com/cline/cline">
-          <img src="./public/providers/openclaw.png" alt="OpenClaw" width="48"/><br/>
-          <b>OpenClaw</b>
-        </a><br/>
-        <sub>⭐ 205K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/HKUDS/nanobot">
-          <img src="./public/providers/nanobot.png" alt="NanoBot" width="48"/><br/>
-          <b>NanoBot</b>
-        </a><br/>
-        <sub>⭐ 20.9K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/sipeed/picoclaw">
-          <img src="./public/providers/picoclaw.jpg" alt="PicoClaw" width="48"/><br/>
-          <b>PicoClaw</b>
-        </a><br/>
-        <sub>⭐ 14.6K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/zeroclaw-labs/zeroclaw">
-          <img src="./public/providers/zeroclaw.png" alt="ZeroClaw" width="48"/><br/>
-          <b>ZeroClaw</b>
-        </a><br/>
-        <sub>⭐ 9.9K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/nearai/ironclaw">
-          <img src="./public/providers/ironclaw.png" alt="IronClaw" width="48"/><br/>
-          <b>IronClaw</b>
-        </a><br/>
-        <sub>⭐ 2.1K</sub>
-      </td>
-    </tr>
-    <tr>
-      <td align="center" width="110">
-        <a href="https://github.com/anomalyco/opencode">
-          <img src="./public/providers/opencode.svg" alt="OpenCode" width="48"/><br/>
-          <b>OpenCode</b>
-        </a><br/>
-        <sub>⭐ 106K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/openai/codex">
-          <img src="./public/providers/codex.png" alt="Codex CLI" width="48"/><br/>
-          <b>Codex CLI</b>
-        </a><br/>
-        <sub>⭐ 60.8K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/anthropics/claude-code">
-          <img src="./public/providers/claude.png" alt="Claude Code" width="48"/><br/>
-          <b>Claude Code</b>
-        </a><br/>
-        <sub>⭐ 67.3K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/google-gemini/gemini-cli">
-          <img src="./public/providers/gemini-cli.png" alt="Gemini CLI" width="48"/><br/>
-          <b>Gemini CLI</b>
-        </a><br/>
-        <sub>⭐ 94.7K</sub>
-      </td>
-      <td align="center" width="110">
-        <a href="https://github.com/Kilo-Org/kilocode">
-          <img src="./public/providers/kilocode.png" alt="Kilo Code" width="48"/><br/>
-          <b>Kilo Code</b>
-        </a><br/>
-        <sub>⭐ 15.5K</sub>
-      </td>
-    </tr>
-  </table>
-
-<sub>📡 所有代理通过 <code>http://localhost:20128/v1</code> 或 <code>http://cloud.omniroute.online/v1</code> 连接 — 一个配置，无限模型和配额</sub>
-
----
-
-[![npm version](https://img.shields.io/npm/v/omniroute?color=cb3837&logo=npm)](https://www.npmjs.com/package/omniroute)
-[![Docker Hub](https://img.shields.io/docker/v/diegosouzapw/omniroute?label=Docker%20Hub&logo=docker&color=2496ED)](https://hub.docker.com/r/diegosouzapw/omniroute)
-[![License](https://img.shields.io/github/license/diegosouzapw/OmniRoute)](https://github.com/diegosouzapw/OmniRoute/blob/main/LICENSE)
-[![Website](https://img.shields.io/badge/Website-omniroute.online-blue?logo=google-chrome&logoColor=white)](https://omniroute.online)
-[![WhatsApp](https://img.shields.io/badge/WhatsApp-Community-25D366?logo=whatsapp&logoColor=white)](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-
-[🌐 网站](https://omniroute.online) • [🚀 快速开始](#-快速开始) • [💡 功能特性](#-核心功能) • [📖 文档](#-文档) • [💰 定价](#-定价概览)
-
-🌐 **多语言版本：** [English](README.md) | [Português](README.pt-BR.md) | [Español](README.es.md) | [Русский](README.ru.md) | [中文](README.zh-CN.md) | [Deutsch](README.de.md) | [Français](README.fr.md) | [Italiano](README.it.md)
-
-</div>
-
----
-
-## 🤔 为什么选择 OmniRoute？
-
-**停止浪费金钱和遭遇限制：**
-
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> 订阅配额每月未使用就过期
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> 速率限制在编程中途停止你
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> 昂贵的 API（每个提供商 $20-50/月）
-- <img src="https://img.shields.io/badge/✗-e74c3c?style=flat-square" height="16"/> 手动在提供商间切换
-
-**OmniRoute 解决这些问题：**
-
-- ✅ **最大化订阅** — 追踪配额，在重置前用完每一点
-- ✅ **自动故障转移** — 订阅 → API Key → 低价 → 免费，零停机
-- ✅ **多账号** — 每个提供商的账号轮询
-- ✅ **通用** — 适用于 Claude Code、Codex、Gemini CLI、Cursor、Cline、OpenClaw、任何 CLI 工具
-
----
-
-## 🔄 工作原理
-
-```
-┌─────────────┐
-│  您的 CLI   │  (Claude Code, Codex, Gemini CLI, OpenClaw, Cursor, Cline...)
-│   工具      │
-└──────┬──────┘
-       │ http://localhost:20128/v1
-       ↓
-┌─────────────────────────────────────────┐
-│         OmniRoute（智能路由器）           │
-│  • 格式转换（OpenAI ↔ Claude）          │
-│  • 配额追踪 + Embeddings + 图像         │
-│  • 自动令牌刷新                         │
-└──────┬──────────────────────────────────┘
-       │
-       ├─→ [第1层: 订阅] Claude Code, Codex, Gemini CLI
-       │   ↓ 配额用完
-       ├─→ [第2层: API KEY] DeepSeek, Groq, xAI, Mistral, NVIDIA NIM 等
-       │   ↓ 预算限制
-       ├─→ [第3层: 低价] GLM ($0.6/1M), MiniMax ($0.2/1M)
-       │   ↓ 预算限制
-       └─→ [第4层: 免费] iFlow, Qwen, Kiro（无限制）
-
-结果：永不停止编程，成本最低
-```
-
----
-
-## ⚡ 快速开始
-
-**1. 全局安装：**
-
-```bash
-npm install -g omniroute
-omniroute
-```
-
-🎉 仪表板在 `http://localhost:20128` 打开
-
-| 命令                    | 描述                         |
-| ----------------------- | ---------------------------- |
-| `omniroute`             | 启动服务器（默认端口 20128） |
-| `omniroute --port 3000` | 使用自定义端口               |
-| `omniroute --no-open`   | 不自动打开浏览器             |
-| `omniroute --help`      | 显示帮助                     |
-
-**2. 连接免费提供商：**
-
-仪表板 → 提供商 → 连接 **Claude Code** 或 **Antigravity** → OAuth 登录 → 完成！
-
-**3. 在 CLI 工具中使用：**
-
-```
-Claude Code/Codex/Gemini CLI/OpenClaw/Cursor/Cline 设置：
-  Endpoint: http://localhost:20128/v1
-  API Key: [从仪表板复制]
-  Model: if/kimi-k2-thinking
-```
-
-**完成！** 开始使用免费 AI 模型编程。
-
-**替代方案 — 从源代码运行：**
-
-```bash
-cp .env.example .env
-npm install
-PORT=20128 NEXT_PUBLIC_BASE_URL=http://localhost:20128 npm run dev
-```
-
----
-
-## 🐳 Docker
-
-OmniRoute 作为公共 Docker 镜像在 [Docker Hub](https://hub.docker.com/r/diegosouzapw/omniroute) 上可用。
-
-**快速运行：**
-
-```bash
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-**使用环境文件：**
-
-```bash
-# 先复制并编辑 .env
-cp .env.example .env
-
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  --env-file .env \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-**使用 Docker Compose：**
-
-```bash
-# 基础配置（无 CLI 工具）
-docker compose --profile base up -d
-
-# CLI 配置（内置 Claude Code、Codex、OpenClaw）
-docker compose --profile cli up -d
-```
-
-| 镜像                     | 标签     | 大小   | 描述       |
-| ------------------------ | -------- | ------ | ---------- |
-| `diegosouzapw/omniroute` | `latest` | ~250MB | 最新稳定版 |
-| `diegosouzapw/omniroute` | `1.0.6`  | ~250MB | 当前版本   |
-
----
-
-## 💰 定价概览
-
-| 层级           | 提供商            | 费用                  | 配额重置        | 最适合       |
-| -------------- | ----------------- | --------------------- | --------------- | ------------ |
-| **💳 订阅**    | Claude Code (Pro) | $20/月                | 5小时 + 每周    | 已订阅用户   |
-|                | Codex (Plus/Pro)  | $20-200/月            | 5小时 + 每周    | OpenAI 用户  |
-|                | Gemini CLI        | **免费**              | 180K/月 + 1K/天 | 所有人！     |
-|                | GitHub Copilot    | $10-19/月             | 每月            | GitHub 用户  |
-| **🔑 API KEY** | NVIDIA NIM        | **免费**（1000 积分） | 一次性          | 免费测试     |
-|                | DeepSeek          | 按使用量              | 无              | 最佳性价比   |
-|                | Groq              | 免费层 + 付费         | 限速            | 超快推理     |
-|                | xAI (Grok)        | 按使用量              | 无              | Grok 模型    |
-|                | Mistral           | 免费层 + 付费         | 限速            | 欧洲 AI      |
-|                | OpenRouter        | 按使用量              | 无              | 100+ 模型    |
-| **💰 低价**    | GLM-4.7           | $0.6/1M               | 每日 10时       | 经济备用     |
-|                | MiniMax M2.1      | $0.2/1M               | 5小时滚动       | 最便宜选项   |
-|                | Kimi K2           | $9/月固定             | 每月 10M Token  | 可预测成本   |
-| **🆓 免费**    | iFlow             | $0                    | 无限制          | 8 个免费模型 |
-|                | Qwen              | $0                    | 无限制          | 3 个免费模型 |
-|                | Kiro              | $0                    | 无限制          | 免费 Claude  |
-
-**💡 专业建议：** 从 Gemini CLI（每月 180K 免费）+ iFlow（无限免费）开始 = $0 成本！
-
----
-
-## 🎯 使用场景
-
-### 场景 1："我有 Claude Pro 订阅"
-
-**问题：** 配额未使用就过期，编程高峰期遇到速率限制
-
-```
-Combo: "maximize-claude"
-  1. cc/claude-opus-4-6        （充分使用订阅）
-  2. glm/glm-4.7               （配额用完时的便宜备用）
-  3. if/kimi-k2-thinking       （免费应急后备）
-
-每月成本：$20（订阅）+ ~$5（备用）= $25 总计
-对比：$20 + 遇到限制 = 受挫
-```
-
-### 场景 2："我想要零成本"
-
-**问题：** 无法承担订阅费用，需要可靠的 AI 编程
-
-```
-Combo: "free-forever"
-  1. gc/gemini-3-flash         （每月 180K 免费）
-  2. if/kimi-k2-thinking       （无限免费）
-  3. qw/qwen3-coder-plus       （无限免费）
-
-每月成本：$0
-质量：生产级模型
-```
-
-### 场景 3："我需要 24/7 编程，不中断"
-
-**问题：** 截止日期紧迫，不能有停机时间
-
-```
-Combo: "always-on"
-  1. cc/claude-opus-4-6        （最佳质量）
-  2. cx/gpt-5.2-codex          （第二个订阅）
-  3. glm/glm-4.7               （便宜，每日重置）
-  4. minimax/MiniMax-M2.1      （最便宜，5小时重置）
-  5. if/kimi-k2-thinking       （免费无限制）
-
-结果：5 层故障转移 = 零停机
-```
-
-### 场景 4："我想在 OpenClaw 中使用免费 AI"
-
-**问题：** 需要在消息应用中使用 AI 助手，完全免费
-
-```
-Combo: "openclaw-free"
-  1. if/glm-4.7                （无限免费）
-  2. if/minimax-m2.1           （无限免费）
-  3. if/kimi-k2-thinking       （无限免费）
-
-每月成本：$0
-访问方式：WhatsApp、Telegram、Slack、Discord、iMessage、Signal...
-```
-
----
-
-## 💡 核心功能
-
-### 🧠 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                 |
-
-### 🎵 多模态 API
-
-| 功能              | 功能描述                                       |
-| ----------------- | ---------------------------------------------- |
-| 🖼️ **图像生成**   | `/v1/images/generations` — 4 个提供商，9+ 模型 |
-| 📐 **Embeddings** | `/v1/embeddings` — 6 个提供商，9+ 模型         |
-| 🎤 **音频转录**   | `/v1/audio/transcriptions` — Whisper 兼容      |
-| 🔊 **文字转语音** | `/v1/audio/speech` — 多提供商音频合成          |
-| 🛡️ **内容审核**   | `/v1/moderations` — 内容安全检查               |
-| 🔀 **重排序**     | `/v1/rerank` — 文档相关性重排序                |
-
-### 🛡️ 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       |
-
-### 📊 可观察性与分析
-
-| 功能               | 功能描述                                   |
-| ------------------ | ------------------------------------------ |
-| 📝 **请求日志**    | 调试模式，完整的请求/响应日志              |
-| 💾 **SQLite 日志** | 持久化代理日志，服务器重启后仍然保留       |
-| 📊 **分析仪表板**  | Recharts：统计卡片、使用量图表、提供商表格 |
-| 📈 **进度追踪**    | 流式传输的 SSE 进度事件（可选）            |
-| 🧪 **LLM 评估**    | 黄金集测试，4 种匹配策略                   |
-| 🔍 **请求遥测**    | p50/p95/p99 延迟聚合 + X-Request-Id 追踪   |
-| 📋 **日志 + 配额** | 专用页面用于日志浏览和配额追踪             |
-| 🏥 **健康仪表板**  | 运行时间、断路器状态、锁定、缓存统计       |
-| 💰 **成本追踪**    | 预算管理 + 每模型定价配置                  |
-
-### ☁️ 部署与同步
-
-| 功能                  | 功能描述                                                   |
-| --------------------- | ---------------------------------------------------------- |
-| 💾 **Cloud Sync**     | 通过 Cloudflare Workers 在设备间同步配置                   |
-| 🌐 **随处部署**       | Localhost、VPS、Docker、Cloudflare Workers                 |
-| 🔑 **API Key 管理**   | 按提供商生成、轮换和设定 API Key 范围                      |
-| 🧙 **配置向导**       | 4 步引导式设置，面向新用户                                 |
-| 🔧 **CLI 工具仪表板** | 一键配置 Claude、Codex、Cline、OpenClaw、Kilo、Antigravity |
-| 🔄 **数据库备份**     | 自动备份和恢复所有设置                                     |
-
-<details>
-<summary><b>📖 功能详情</b></summary>
-
-### 🎯 智能 4 层故障转移
-
-创建带自动故障转移的组合：
-
-```
-Combo: "my-coding-stack"
-  1. cc/claude-opus-4-6        （您的订阅）
-  2. nvidia/llama-3.3-70b      （免费 NVIDIA API）
-  3. glm/glm-4.7               （便宜备用，$0.6/1M）
-  4. if/kimi-k2-thinking       （免费后备）
-
-→ 配额用完或出错时自动切换
-```
-
-### 📊 实时配额追踪
-
-- 每个提供商的 Token 消耗
-- 重置倒计时（5 小时、每日、每周）
-- 付费层级的成本估算
-- 月度支出报告
-
-### 🔄 格式转换
-
-格式间的无缝转换：
-
-- **OpenAI** ↔ **Claude** ↔ **Gemini** ↔ **OpenAI Responses**
-- 您的 CLI 发送 OpenAI 格式 → OmniRoute 转换 → 提供商接收原生格式
-- 适用于任何支持自定义 OpenAI 端点的工具
-
-### 👥 多账号支持
-
-- 每个提供商添加多个账号
-- 自动轮询或基于优先级的路由
-- 当一个账号达到配额时自动切换到下一个
-
-### 🔄 自动令牌刷新
-
-- OAuth 令牌在过期前自动刷新
-- 无需手动重新认证
-- 所有提供商的无缝体验
-
-### 🎨 自定义组合
-
-- 创建无限模型组合
-- 6 种策略：fill-first、round-robin、power-of-two-choices、random、least-used、cost-optimized
-- 通过 Cloud Sync 在设备间共享组合
-
-### 🏥 健康仪表板
-
-- 系统状态（运行时间、版本、内存使用）
-- 每个提供商的断路器状态（Closed/Open/Half-Open）
-- 速率限制状态和活动锁定
-- 签名缓存统计
-- 延迟遥测（p50/p95/p99）+ 提示缓存
-- 一键重置健康状态
-
-### 🔧 翻译器 Playground
-
-- 调试、测试和可视化 API 格式转换
-- 发送请求并查看 OmniRoute 如何在提供商格式间转换
-- 对排查集成问题非常有价值
-
-### 💾 Cloud Sync
-
-- 在设备间同步提供商、组合和设置
-- 自动后台同步
-- 安全加密存储
-
-</details>
-
----
-
-## 📖 设置指南
-
-<details>
-<summary><b>💳 订阅提供商</b></summary>
-
-### Claude Code (Pro/Max)
-
-```bash
-仪表板 → 提供商 → 连接 Claude Code
-→ OAuth 登录 → 自动令牌刷新
-→ 5 小时 + 每周配额追踪
-
-模型：
-  cc/claude-opus-4-6
-  cc/claude-sonnet-4-5-20250929
-  cc/claude-haiku-4-5-20251001
-```
-
-**专业建议：** 复杂任务用 Opus，追求速度用 Sonnet。OmniRoute 按模型追踪配额！
-
-### OpenAI Codex (Plus/Pro)
-
-```bash
-仪表板 → 提供商 → 连接 Codex
-→ OAuth 登录（端口 1455）
-→ 5 小时 + 每周重置
-
-模型：
-  cx/gpt-5.2-codex
-  cx/gpt-5.1-codex-max
-```
-
-### Gemini CLI（免费 180K/月！）
-
-```bash
-仪表板 → 提供商 → 连接 Gemini CLI
-→ Google OAuth
-→ 每月 180K completions + 每天 1K
-
-模型：
-  gc/gemini-3-flash-preview
-  gc/gemini-2.5-pro
-```
-
-**最佳价值：** 巨大的免费额度！在付费层级之前使用。
-
-### GitHub Copilot
-
-```bash
-仪表板 → 提供商 → 连接 GitHub
-→ 通过 GitHub OAuth
-→ 每月重置（每月 1 日）
-
-模型：
-  gh/gpt-5
-  gh/claude-4.5-sonnet
-  gh/gemini-3-pro
-```
-
-</details>
-
-<details>
-<summary><b>🔑 API Key 提供商</b></summary>
-
-### NVIDIA NIM（免费 1000 积分！）
-
-1. 注册：[build.nvidia.com](https://build.nvidia.com)
-2. 获取免费 API key（包含 1000 推理积分）
-3. 仪表板 → 添加提供商 → NVIDIA NIM：
-   - API Key：`nvapi-your-key`
-
-**模型：** `nvidia/llama-3.3-70b-instruct`、`nvidia/mistral-7b-instruct` 及 50+ 更多
-
-**专业建议：** OpenAI 兼容的 API — 与 OmniRoute 的格式转换完美配合！
-
-### DeepSeek
-
-1. 注册：[platform.deepseek.com](https://platform.deepseek.com)
-2. 获取 API key
-3. 仪表板 → 添加提供商 → DeepSeek
-
-**模型：** `deepseek/deepseek-chat`、`deepseek/deepseek-coder`
-
-### Groq（免费层可用！）
-
-1. 注册：[console.groq.com](https://console.groq.com)
-2. 获取 API key（包含免费层）
-3. 仪表板 → 添加提供商 → Groq
-
-**模型：** `groq/llama-3.3-70b`、`groq/mixtral-8x7b`
-
-**专业建议：** 超快推理 — 最适合实时编程！
-
-### OpenRouter（100+ 模型）
-
-1. 注册：[openrouter.ai](https://openrouter.ai)
-2. 获取 API key
-3. 仪表板 → 添加提供商 → OpenRouter
-
-**模型：** 通过一个 API key 访问所有主要提供商的 100+ 模型。
-
-</details>
-
-<details>
-<summary><b>💰 低价提供商（备用）</b></summary>
-
-### GLM-4.7（每日重置，$0.6/1M）
-
-1. 注册：[Zhipu AI](https://open.bigmodel.cn/)
-2. 从 Coding Plan 获取 API key
-3. 仪表板 → 添加 API Key：
-   - 提供商：`glm`
-   - API Key：`your-key`
-
-**使用：** `glm/glm-4.7`
-
-**专业建议：** Coding Plan 以 1/7 的价格提供 3 倍配额！每日 10:00 AM 重置。
-
-### MiniMax M2.1（5 小时重置，$0.20/1M）
-
-1. 注册：[MiniMax](https://www.minimax.io/)
-2. 获取 API key
-3. 仪表板 → 添加 API Key
-
-**使用：** `minimax/MiniMax-M2.1`
-
-**专业建议：** 长上下文（1M Token）最便宜的选项！
-
-### Kimi K2（$9/月固定）
-
-1. 订阅：[Moonshot AI](https://platform.moonshot.ai/)
-2. 获取 API key
-3. 仪表板 → 添加 API Key
-
-**使用：** `kimi/kimi-latest`
-
-**专业建议：** 固定 $9/月 10M Token = $0.90/1M 有效成本！
-
-</details>
-
-<details>
-<summary><b>🆓 免费提供商（应急备用）</b></summary>
-
-### iFlow（8 个免费模型）
-
-```bash
-仪表板 → 连接 iFlow
-→ iFlow OAuth 登录
-→ 无限使用
-
-模型：
-  if/kimi-k2-thinking
-  if/qwen3-coder-plus
-  if/glm-4.7
-  if/minimax-m2
-  if/deepseek-r1
-```
-
-### Qwen（3 个免费模型）
-
-```bash
-仪表板 → 连接 Qwen
-→ 设备码授权
-→ 无限使用
-
-模型：
-  qw/qwen3-coder-plus
-  qw/qwen3-coder-flash
-```
-
-### Kiro（免费 Claude）
-
-```bash
-仪表板 → 连接 Kiro
-→ AWS Builder ID 或 Google/GitHub
-→ 无限使用
-
-模型：
-  kr/claude-sonnet-4.5
-  kr/claude-haiku-4.5
-```
-
-</details>
-
-<details>
-<summary><b>🎨 创建组合</b></summary>
-
-### 示例 1：最大化订阅 → 便宜备用
-
-```
-仪表板 → 组合 → 创建新的
-
-名称：premium-coding
-模型：
-  1. cc/claude-opus-4-6（订阅主力）
-  2. glm/glm-4.7（便宜备用，$0.6/1M）
-  3. minimax/MiniMax-M2.1（最便宜的后备，$0.20/1M）
-
-在 CLI 中使用：premium-coding
-```
-
-### 示例 2：仅免费（零成本）
-
-```
-名称：free-combo
-模型：
-  1. gc/gemini-3-flash-preview（每月 180K 免费）
-  2. if/kimi-k2-thinking（无限制）
-  3. qw/qwen3-coder-plus（无限制）
-
-成本：永远 $0！
-```
-
-</details>
-
-<details>
-<summary><b>🔧 CLI 集成</b></summary>
-
-### Cursor IDE
-
-```
-设置 → 模型 → 高级：
-  OpenAI API Base URL: http://localhost:20128/v1
-  OpenAI API Key: [从 OmniRoute 仪表板获取]
-  Model: cc/claude-opus-4-6
-```
-
-### Claude Code
-
-使用仪表板中的 **CLI Tools** 页面一键配置，或手动编辑 `~/.claude/settings.json`。
-
-### Codex CLI
-
-```bash
-export OPENAI_BASE_URL="http://localhost:20128"
-export OPENAI_API_KEY="your-omniroute-api-key"
-
-codex "your prompt"
-```
-
-### OpenClaw
-
-**选项 1 — 仪表板（推荐）：**
-
-```
-仪表板 → CLI Tools → OpenClaw → 选择模型 → 应用
-```
-
-**选项 2 — 手动：** 编辑 `~/.openclaw/openclaw.json`：
-
-```json
-{
-  "models": {
-    "providers": {
-      "omniroute": {
-        "baseUrl": "http://127.0.0.1:20128/v1",
-        "apiKey": "sk_omniroute",
-        "api": "openai-completions"
-      }
-    }
-  }
-}
-```
-
-> **注意：** OpenClaw 仅支持本地 OmniRoute。使用 `127.0.0.1` 而非 `localhost` 以避免 IPv6 解析问题。
-
-### Cline / Continue / RooCode
-
-```
-设置 → API 配置：
-  提供商：OpenAI Compatible
-  Base URL: http://localhost:20128/v1
-  API Key: [从 OmniRoute 仪表板获取]
-  Model: if/kimi-k2-thinking
-```
-
-</details>
-
----
-
-## 📊 可用模型
-
-<details>
-<summary><b>查看所有可用模型</b></summary>
-
-**Claude Code (`cc/`)** - Pro/Max:
-
-- `cc/claude-opus-4-6`
-- `cc/claude-sonnet-4-5-20250929`
-- `cc/claude-haiku-4-5-20251001`
-
-**Codex (`cx/`)** - Plus/Pro:
-
-- `cx/gpt-5.2-codex`
-- `cx/gpt-5.1-codex-max`
-
-**Gemini CLI (`gc/`)** - 免费:
-
-- `gc/gemini-3-flash-preview`
-- `gc/gemini-2.5-pro`
-
-**GitHub Copilot (`gh/`)**:
-
-- `gh/gpt-5`
-- `gh/claude-4.5-sonnet`
-
-**NVIDIA NIM (`nvidia/`)** - 免费积分:
-
-- `nvidia/llama-3.3-70b-instruct`
-- `nvidia/mistral-7b-instruct`
-- 50+ 更多模型在 [build.nvidia.com](https://build.nvidia.com)
-
-**GLM (`glm/`)** - $0.6/1M:
-
-- `glm/glm-4.7`
-
-**MiniMax (`minimax/`)** - $0.2/1M:
-
-- `minimax/MiniMax-M2.1`
-
-**iFlow (`if/`)** - 免费:
-
-- `if/kimi-k2-thinking`
-- `if/qwen3-coder-plus`
-- `if/deepseek-r1`
-- `if/glm-4.7`
-- `if/minimax-m2`
-
-**Qwen (`qw/`)** - 免费:
-
-- `qw/qwen3-coder-plus`
-- `qw/qwen3-coder-flash`
-
-**Kiro (`kr/`)** - 免费:
-
-- `kr/claude-sonnet-4.5`
-- `kr/claude-haiku-4.5`
-
-**OpenRouter (`or/`)** - 100+ 模型:
-
-- `or/anthropic/claude-4-sonnet`
-- `or/google/gemini-2.5-pro`
-- [openrouter.ai/models](https://openrouter.ai/models) 上的任何模型
-
-</details>
-
----
-
-## 🧪 评估 (Evals)
-
-OmniRoute 包含内置评估框架，用于针对黄金集测试 LLM 响应质量。通过仪表板中的 **Analytics → Evals** 访问。
-
-### 内置黄金集
-
-预加载的「OmniRoute Golden Set」包含 10 个测试用例：
-
-- 问候、数学、地理、代码生成
-- JSON 格式合规性、翻译、markdown
-- 安全拒绝（有害内容）、计数、布尔逻辑
-
-### 评估策略
-
-| 策略       | 描述                             | 示例                             |
-| ---------- | -------------------------------- | -------------------------------- |
-| `exact`    | 输出必须完全匹配                 | `"4"`                            |
-| `contains` | 输出必须包含子串（不区分大小写） | `"Paris"`                        |
-| `regex`    | 输出必须匹配正则表达式模式       | `"1.*2.*3"`                      |
-| `custom`   | 自定义 JS 函数返回 true/false    | `(output) => output.length > 10` |
-
----
-
-## 🐛 故障排除
-
-<details>
-<summary><b>点击展开故障排除指南</b></summary>
-
-**"Language model did not provide messages"**
-
-- 提供商配额已耗尽 → 检查仪表板配额追踪器
-- 解决方案：使用组合故障转移或切换到更便宜的层级
-
-**速率限制**
-
-- 订阅配额耗尽 → 回退到 GLM/MiniMax
-- 添加组合：`cc/claude-opus-4-6 → glm/glm-4.7 → if/kimi-k2-thinking`
-
-**OAuth 令牌过期**
-
-- OmniRoute 自动刷新
-- 如果问题持续：仪表板 → 提供商 → 重新连接
-
-**高成本**
-
-- 在仪表板 → 成本中检查使用统计
-- 将主要模型切换为 GLM/MiniMax
-- 对非关键任务使用免费层（Gemini CLI、iFlow）
-
-**仪表板在错误端口打开**
-
-- 设置 `PORT=20128` 和 `NEXT_PUBLIC_BASE_URL=http://localhost:20128`
-
-**Cloud sync 错误**
-
-- 验证 `BASE_URL` 指向您正在运行的实例
-- 验证 `CLOUD_URL` 指向预期的云端点
-- 保持 `NEXT_PUBLIC_*` 值与服务器端值一致
-
-**首次登录不工作**
-
-- 检查 `.env` 中的 `INITIAL_PASSWORD`
-- 如未设置，默认密码为 `123456`
-
-**没有请求日志**
-
-- 在 `.env` 中设置 `ENABLE_REQUEST_LOGS=true`
-
-**兼容 OpenAI 的提供商连接测试显示 "Invalid"**
-
-- 许多提供商不暴露 `/models` 端点
-- OmniRoute v1.0.6+ 包含通过 chat completions 的回退验证
-- 确保 base URL 包含 `/v1` 后缀
-
-</details>
-
----
-
-## 🛠️ 技术栈
-
-- **运行时**: Node.js 20+
-- **语言**: TypeScript 5.9 — `src/` 和 `open-sse/` 中 **100% TypeScript**（v1.0.6）
-- **框架**: Next.js 16 + React 19 + Tailwind CSS 4
-- **数据库**: LowDB (JSON) + SQLite（领域状态 + 代理日志）
-- **流式传输**: Server-Sent Events (SSE)
-- **认证**: OAuth 2.0 (PKCE) + JWT + API Keys
-- **测试**: Node.js test runner（368+ 单元测试）
-- **CI/CD**: GitHub Actions（发布时自动 npm 发布 + Docker Hub）
-- **网站**: [omniroute.online](https://omniroute.online)
-- **包**: [npmjs.com/package/omniroute](https://www.npmjs.com/package/omniroute)
-- **Docker**: [hub.docker.com/r/diegosouzapw/omniroute](https://hub.docker.com/r/diegosouzapw/omniroute)
-- **弹性**: 断路器、指数退避、反惊群、TLS 伪装
-
----
-
-## 📖 文档
-
-| 文档                                | 描述                         |
-| ----------------------------------- | ---------------------------- |
-| [用户指南](docs/USER_GUIDE.md)      | 提供商、组合、CLI 集成、部署 |
-| [API 参考](docs/API_REFERENCE.md)   | 所有端点及示例               |
-| [故障排除](docs/TROUBLESHOOTING.md) | 常见问题和解决方案           |
-| [架构](docs/ARCHITECTURE.md)        | 系统架构和内部机制           |
-| [贡献指南](CONTRIBUTING.md)         | 开发设置和指南               |
-| [OpenAPI 规范](docs/openapi.yaml)   | OpenAPI 3.0 规范             |
-| [安全策略](SECURITY.md)             | 漏洞报告和安全实践           |
-
----
-
-## 📧 支持
-
-> 💬 **加入我们的社区！** [WhatsApp 群组](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t) — 获取帮助、分享技巧、了解最新动态。
-
-- **网站**: [omniroute.online](https://omniroute.online)
-- **GitHub**: [github.com/diegosouzapw/OmniRoute](https://github.com/diegosouzapw/OmniRoute)
-- **Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
-- **WhatsApp**: [社区群组](https://chat.whatsapp.com/JI7cDQ1GyaiDHhVBpLxf8b?mode=gi_t)
-- **原始项目**: [decolua 的 9router](https://github.com/decolua/9router)
-
----
-
-## 👥 贡献者
-
-[![Contributors](https://contrib.rocks/image?repo=diegosouzapw/OmniRoute&max=100&columns=20&anon=1)](https://github.com/diegosouzapw/OmniRoute/graphs/contributors)
-
-### 如何贡献
-
-1. Fork 仓库
-2. 创建功能分支（`git checkout -b feature/amazing-feature`）
-3. 提交更改（`git commit -m 'Add amazing feature'`）
-4. 推送到分支（`git push origin feature/amazing-feature`）
-5. 打开 Pull Request
-
-详细指南请参阅 [CONTRIBUTING.md](CONTRIBUTING.md)。
-
-### 发布新版本
-
-```bash
-# 创建发布 — npm 发布自动完成
-gh release create v1.0.6 --title "v1.0.6" --generate-notes
-```
-
----
-
-## 📊 Star 历史
-
-<a href="https://star-history.com/#diegosouzapw/OmniRoute&Date">
- <picture>
-   <source media="(prefers-color-scheme: dark)" srcset="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date&theme=dark" />
-   <source media="(prefers-color-scheme: light)" srcset="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date" />
-   <img alt="Star History Chart" src="https://api.star-history.com/svg?repos=diegosouzapw/OmniRoute&type=Date" />
- </picture>
-</a>
-
----
-
-## 🙏 致谢
-
-特别感谢 **[decolua](https://github.com/decolua)** 的 **[9router](https://github.com/decolua/9router)** — 启发了本 fork 的原始项目。OmniRoute 在这个令人难以置信的基础上添加了额外功能、多模态 API 和完整的 TypeScript 重写。
-
-特别感谢 **[CLIProxyAPI](https://github.com/router-for-me/CLIProxyAPI)** — 启发了本 JavaScript 移植的原始 Go 实现。
-
----
-
-## 📄 许可证
-
-MIT 许可证 — 详见 [LICENSE](LICENSE)。
-
----
-
-<div align="center">
-  <sub>用 ❤️ 为 24/7 编程的开发者打造</sub>
-  <br/>
-  <sub><a href="https://omniroute.online">omniroute.online</a></sub>
-</div>

SECURITY.md

@@ -1,169 +1,21 @@
 # Security Policy
 
-## Reporting Vulnerabilities
-
-If you discover a security vulnerability in OmniRoute, please report it responsibly:
-
-1. **DO NOT** open a public GitHub issue
-2. Use [GitHub Security Advisories](https://github.com/diegosouzapw/OmniRoute/security/advisories/new)
-3. Include: description, reproduction steps, and potential impact
-
-## Response Timeline
-
-| Stage               | Target                      |
-| ------------------- | --------------------------- |
-| Acknowledgment      | 48 hours                    |
-| Triage & Assessment | 5 business days             |
-| Patch Release       | 14 business days (critical) |
-
 ## Supported Versions
 
-| Version | Support Status |
-| ------- | -------------- |
-| 1.0.x   | ✅ Active      |
-| 0.8.x   | ✅ Security    |
-| < 0.8.0 | ❌ Unsupported |
+Use this section to tell people about which versions of your project are
+currently being supported with security updates.
 
----
+| Version | Supported          |
+| ------- | ------------------ |
+| 5.1.x   | :white_check_mark: |
+| 5.0.x   | :x:                |
+| 4.0.x   | :white_check_mark: |
+| < 4.0   | :x:                |
 
-## Security Architecture
+## Reporting a Vulnerability
 
-OmniRoute implements a multi-layered security model:
+Use this section to tell people how to report a vulnerability.
 
-```
-Request → CORS → API Key Auth → Prompt Injection Guard → Input Sanitizer → Rate Limiter → Circuit Breaker → Provider
-```
-
-### 🔐 Authentication & Authorization
-
-| Feature              | Implementation                                             |
-| -------------------- | ---------------------------------------------------------- |
-| **Dashboard Login**  | Password-based auth with JWT tokens (HttpOnly cookies)     |
-| **API Key Auth**     | HMAC-signed keys with CRC validation                       |
-| **OAuth 2.0 + PKCE** | Secure provider auth (Claude, Codex, Gemini, Cursor, etc.) |
-| **Token Refresh**    | Automatic OAuth token refresh before expiry                |
-| **Secure Cookies**   | `AUTH_COOKIE_SECURE=true` for HTTPS environments           |
-
-### 🛡️ Encryption at Rest
-
-All sensitive data stored in SQLite is encrypted using **AES-256-GCM** with scrypt key derivation:
-
-- API keys, access tokens, refresh tokens, and ID tokens
-- Versioned format: `enc:v1:<iv>:<ciphertext>:<authTag>`
-- Passthrough mode (plaintext) when `STORAGE_ENCRYPTION_KEY` is not set
-
-```bash
-# Generate encryption key:
-STORAGE_ENCRYPTION_KEY=$(openssl rand -hex 32)
-```
-
-### 🧠 Prompt Injection Guard
-
-Middleware that detects and blocks prompt injection attacks in LLM requests:
-
-| Pattern Type        | Severity | Example                                        |
-| ------------------- | -------- | ---------------------------------------------- |
-| System Override     | High     | "ignore all previous instructions"             |
-| Role Hijack         | High     | "you are now DAN, you can do anything"         |
-| Delimiter Injection | Medium   | Encoded separators to break context boundaries |
-| DAN/Jailbreak       | High     | Known jailbreak prompt patterns                |
-| Instruction Leak    | Medium   | "show me your system prompt"                   |
-
-Configure via dashboard (Settings → Security) or `.env`:
-
-```env
-INPUT_SANITIZER_ENABLED=true
-INPUT_SANITIZER_MODE=block    # warn | block | redact
-```
-
-### 🔒 PII Redaction
-
-Automatic detection and optional redaction of personally identifiable information:
-
-| PII Type      | Pattern               | Replacement        |
-| ------------- | --------------------- | ------------------ |
-| Email         | `user@domain.com`     | `[EMAIL_REDACTED]` |
-| CPF (Brazil)  | `123.456.789-00`      | `[CPF_REDACTED]`   |
-| CNPJ (Brazil) | `12.345.678/0001-00`  | `[CNPJ_REDACTED]`  |
-| Credit Card   | `4111-1111-1111-1111` | `[CC_REDACTED]`    |
-| Phone         | `+55 11 99999-9999`   | `[PHONE_REDACTED]` |
-| SSN (US)      | `123-45-6789`         | `[SSN_REDACTED]`   |
-
-```env
-PII_REDACTION_ENABLED=true
-```
-
-### 🌐 Network Security
-
-| Feature                  | Description                                                      |
-| ------------------------ | ---------------------------------------------------------------- |
-| **CORS**                 | Configurable origin control (`CORS_ORIGIN` env var, default `*`) |
-| **IP Filtering**         | Whitelist/blacklist IP ranges in dashboard                       |
-| **Rate Limiting**        | Per-provider rate limits with automatic backoff                  |
-| **Anti-Thundering Herd** | Mutex + per-connection locking prevents cascading 502s           |
-
-### 🔌 Resilience & Availability
-
-| Feature                 | Description                                                        |
-| ----------------------- | ------------------------------------------------------------------ |
-| **Circuit Breaker**     | 3-state (Closed → Open → Half-Open) per provider, SQLite-persisted |
-| **Request Idempotency** | 5-second dedup window for duplicate requests                       |
-| **Exponential Backoff** | Automatic retry with increasing delays                             |
-| **Health Dashboard**    | Real-time provider health monitoring                               |
-
-### 📋 Compliance
-
-| Feature            | Description                                         |
-| ------------------ | --------------------------------------------------- |
-| **Log Retention**  | Automatic cleanup after `LOG_RETENTION_DAYS`        |
-| **No-Log Opt-out** | Per API key `noLog` flag disables request logging   |
-| **Audit Log**      | Administrative actions tracked in `audit_log` table |
-
----
-
-## Required Environment Variables
-
-All secrets must be set before starting the server. The server will **fail fast** if they are missing or weak.
-
-```bash
-# REQUIRED — server will not start without these:
-JWT_SECRET=$(openssl rand -base64 48)     # min 32 chars
-API_KEY_SECRET=$(openssl rand -hex 32)    # min 16 chars
-
-# RECOMMENDED — enables encryption at rest:
-STORAGE_ENCRYPTION_KEY=$(openssl rand -hex 32)
-```
-
-The server actively rejects known-weak values like `changeme`, `secret`, or `password`.
-
----
-
-## Docker Security
-
-- Use non-root user in production
-- Mount secrets as read-only volumes
-- Never copy `.env` files into Docker images
-- Use `.dockerignore` to exclude sensitive files
-- Set `AUTH_COOKIE_SECURE=true` when behind HTTPS
-
-```bash
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  --read-only \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  -e JWT_SECRET="$(openssl rand -base64 48)" \
-  -e API_KEY_SECRET="$(openssl rand -hex 32)" \
-  -e STORAGE_ENCRYPTION_KEY="$(openssl rand -hex 32)" \
-  diegosouzapw/omniroute:latest
-```
-
----
-
-## Dependencies
-
-- Run `npm audit` regularly
-- Keep dependencies updated
-- The project uses `husky` + `lint-staged` for pre-commit checks
-- CI pipeline runs ESLint security rules on every push
+Tell them where to go, how often they can expect to get an update on a
+reported vulnerability, what to expect if the vulnerability is accepted or
+declined, etc.

bin/reset-password.mjs

@@ -1,116 +0,0 @@
-#!/usr/bin/env node
-
-/**
- * Password Reset CLI — T-38
- *
- * Usage:
- *   node bin/reset-password.mjs
- *   npx omniroute reset-password
- *
- * Resets the admin password for OmniRoute.
- * Prompts for a new password and updates the database directly.
- *
- * @module bin/reset-password
- */
-
-import { createInterface } from "node:readline";
-import { resolve, dirname } from "node:path";
-import { fileURLToPath } from "node:url";
-import { existsSync } from "node:fs";
-import { createHash } from "node:crypto";
-
-const __dirname = dirname(fileURLToPath(import.meta.url));
-
-// Resolve data directory — same logic as the server
-const DATA_DIR = process.env.DATA_DIR || resolve(__dirname, "..", "data");
-const DB_PATH = resolve(DATA_DIR, "settings.db");
-
-const rl = createInterface({
-  input: process.stdin,
-  output: process.stdout,
-});
-
-function ask(question) {
-  return new Promise((resolve) => rl.question(question, resolve));
-}
-
-function hashPassword(password) {
-  return createHash("sha256").update(password).digest("hex");
-}
-
-console.log("\n🔑 OmniRoute — Password Reset\n");
-
-async function main() {
-  // Check if database exists
-  if (!existsSync(DB_PATH)) {
-    console.error(`❌ Database not found at: ${DB_PATH}`);
-    console.error(`   Make sure OmniRoute has been started at least once.`);
-    console.error(`   Or set DATA_DIR env var to your data directory.\n`);
-    process.exit(1);
-  }
-
-  let Database;
-  try {
-    Database = (await import("better-sqlite3")).default;
-  } catch {
-    console.error("❌ better-sqlite3 not installed. Run: npm install");
-    process.exit(1);
-  }
-
-  const db = new Database(DB_PATH);
-
-  // Check current settings
-  const row = db.prepare("SELECT value FROM settings WHERE key = 'password'").get();
-
-  if (row) {
-    console.log("ℹ️  A password is currently set.");
-  } else {
-    console.log("ℹ️  No password is currently set.");
-  }
-
-  const password = await ask("Enter new password (min 4 chars): ");
-
-  if (!password || password.length < 4) {
-    console.error("\n❌ Password must be at least 4 characters.\n");
-    db.close();
-    rl.close();
-    process.exit(1);
-  }
-
-  const confirm = await ask("Confirm new password: ");
-
-  if (password !== confirm) {
-    console.error("\n❌ Passwords do not match.\n");
-    db.close();
-    rl.close();
-    process.exit(1);
-  }
-
-  const hashed = hashPassword(password);
-
-  // Upsert the password
-  const stmt = db.prepare(`
-    INSERT INTO settings (key, value) VALUES ('password', ?)
-    ON CONFLICT(key) DO UPDATE SET value = excluded.value
-  `);
-  stmt.run(hashed);
-
-  // Also ensure requireLogin is true
-  const loginStmt = db.prepare(`
-    INSERT INTO settings (key, value) VALUES ('requireLogin', 'true')
-    ON CONFLICT(key) DO UPDATE SET value = excluded.value
-  `);
-  loginStmt.run();
-
-  db.close();
-  rl.close();
-
-  console.log("\n✅ Password reset successfully!");
-  console.log("   Restart OmniRoute for changes to take effect.\n");
-}
-
-main().catch((err) => {
-  console.error(`\n❌ Error: ${err.message}\n`);
-  rl.close();
-  process.exit(1);
-});

docker-compose.yml

@@ -18,8 +18,6 @@
 x-common: &common
   restart: unless-stopped
   env_file: .env
-  environment:
-    - DATA_DIR=/app/data # Must match the volume mount below
   volumes:
     - omniroute-data:/app/data
   healthcheck:

docs/API_REFERENCE.md

@@ -1,439 +0,0 @@
-# API Reference
-
-Complete reference for all OmniRoute API endpoints.
-
----
-
-## Table of Contents
-
-- [Chat Completions](#chat-completions)
-- [Embeddings](#embeddings)
-- [Image Generation](#image-generation)
-- [List Models](#list-models)
-- [Compatibility Endpoints](#compatibility-endpoints)
-- [Semantic Cache](#semantic-cache)
-- [Dashboard & Management](#dashboard--management)
-- [Request Processing](#request-processing)
-- [Authentication](#authentication)
-
----
-
-## Chat Completions
-
-```bash
-POST /v1/chat/completions
-Authorization: Bearer your-api-key
-Content-Type: application/json
-
-{
-  "model": "cc/claude-opus-4-6",
-  "messages": [
-    {"role": "user", "content": "Write a function to..."}
-  ],
-  "stream": true
-}
-```
-
-### Custom Headers
-
-| Header                   | Direction | Description                       |
-| ------------------------ | --------- | --------------------------------- |
-| `X-OmniRoute-No-Cache`   | Request   | Set to `true` to bypass cache     |
-| `X-OmniRoute-Progress`   | Request   | Set to `true` for progress events |
-| `Idempotency-Key`        | Request   | Dedup key (5s window)             |
-| `X-Request-Id`           | Request   | Alternative dedup key             |
-| `X-OmniRoute-Cache`      | Response  | `HIT` or `MISS` (non-streaming)   |
-| `X-OmniRoute-Idempotent` | Response  | `true` if deduplicated            |
-| `X-OmniRoute-Progress`   | Response  | `enabled` if progress tracking on |
-
----
-
-## Embeddings
-
-```bash
-POST /v1/embeddings
-Authorization: Bearer your-api-key
-Content-Type: application/json
-
-{
-  "model": "nebius/Qwen/Qwen3-Embedding-8B",
-  "input": "The food was delicious"
-}
-```
-
-Available providers: Nebius, OpenAI, Mistral, Together AI, Fireworks, NVIDIA.
-
-```bash
-# List all embedding models
-GET /v1/embeddings
-```
-
----
-
-## Image Generation
-
-```bash
-POST /v1/images/generations
-Authorization: Bearer your-api-key
-Content-Type: application/json
-
-{
-  "model": "openai/dall-e-3",
-  "prompt": "A beautiful sunset over mountains",
-  "size": "1024x1024"
-}
-```
-
-Available providers: OpenAI (DALL-E), xAI (Grok Image), Together AI (FLUX), Fireworks AI.
-
-```bash
-# List all image models
-GET /v1/images/generations
-```
-
----
-
-## List Models
-
-```bash
-GET /v1/models
-Authorization: Bearer your-api-key
-
-→ Returns all chat, embedding, and image models + combos in OpenAI format
-```
-
----
-
-## Compatibility Endpoints
-
-| Method | Path                        | Format                 |
-| ------ | --------------------------- | ---------------------- |
-| POST   | `/v1/chat/completions`      | OpenAI                 |
-| POST   | `/v1/messages`              | Anthropic              |
-| POST   | `/v1/responses`             | OpenAI Responses       |
-| POST   | `/v1/embeddings`            | OpenAI                 |
-| POST   | `/v1/images/generations`    | OpenAI                 |
-| GET    | `/v1/models`                | OpenAI                 |
-| POST   | `/v1/messages/count_tokens` | Anthropic              |
-| GET    | `/v1beta/models`            | Gemini                 |
-| POST   | `/v1beta/models/{...path}`  | Gemini generateContent |
-| POST   | `/v1/api/chat`              | Ollama                 |
-
-### Dedicated Provider Routes
-
-```bash
-POST /v1/providers/{provider}/chat/completions
-POST /v1/providers/{provider}/embeddings
-POST /v1/providers/{provider}/images/generations
-```
-
-The provider prefix is auto-added if missing. Mismatched models return `400`.
-
----
-
-## Semantic Cache
-
-```bash
-# Get cache stats
-GET /api/cache
-
-# Clear all caches
-DELETE /api/cache
-```
-
-Response example:
-
-```json
-{
-  "semanticCache": {
-    "memorySize": 42,
-    "memoryMaxSize": 500,
-    "dbSize": 128,
-    "hitRate": 0.65
-  },
-  "idempotency": {
-    "activeKeys": 3,
-    "windowMs": 5000
-  }
-}
-```
-
----
-
-## Dashboard & Management
-
-### Authentication
-
-| Endpoint                      | Method  | Description           |
-| ----------------------------- | ------- | --------------------- |
-| `/api/auth/login`             | POST    | Login                 |
-| `/api/auth/logout`            | POST    | Logout                |
-| `/api/settings/require-login` | GET/PUT | Toggle login required |
-
-### Provider Management
-
-| Endpoint                     | Method          | Description              |
-| ---------------------------- | --------------- | ------------------------ |
-| `/api/providers`             | GET/POST        | List / create providers  |
-| `/api/providers/[id]`        | GET/PUT/DELETE  | Manage a provider        |
-| `/api/providers/[id]/test`   | POST            | Test provider connection |
-| `/api/providers/[id]/models` | GET             | List provider models     |
-| `/api/providers/validate`    | POST            | Validate provider config |
-| `/api/provider-nodes*`       | Various         | Provider node management |
-| `/api/provider-models`       | GET/POST/DELETE | Custom models            |
-
-### OAuth Flows
-
-| Endpoint                         | Method  | Description             |
-| -------------------------------- | ------- | ----------------------- |
-| `/api/oauth/[provider]/[action]` | Various | Provider-specific OAuth |
-
-### Routing & Config
-
-| Endpoint              | Method   | Description                   |
-| --------------------- | -------- | ----------------------------- |
-| `/api/models/alias`   | GET/POST | Model aliases                 |
-| `/api/models/catalog` | GET      | All models by provider + type |
-| `/api/combos*`        | Various  | Combo management              |
-| `/api/keys*`          | Various  | API key management            |
-| `/api/pricing`        | GET      | Model pricing                 |
-
-### Usage & Analytics
-
-| Endpoint                    | Method | Description          |
-| --------------------------- | ------ | -------------------- |
-| `/api/usage/history`        | GET    | Usage history        |
-| `/api/usage/logs`           | GET    | Usage logs           |
-| `/api/usage/request-logs`   | GET    | Request-level logs   |
-| `/api/usage/[connectionId]` | GET    | Per-connection usage |
-
-### Settings
-
-| Endpoint                        | Method  | Description            |
-| ------------------------------- | ------- | ---------------------- |
-| `/api/settings`                 | GET/PUT | General settings       |
-| `/api/settings/proxy`           | GET/PUT | Network proxy config   |
-| `/api/settings/proxy/test`      | POST    | Test proxy connection  |
-| `/api/settings/ip-filter`       | GET/PUT | IP allowlist/blocklist |
-| `/api/settings/thinking-budget` | GET/PUT | Reasoning token budget |
-| `/api/settings/system-prompt`   | GET/PUT | Global system prompt   |
-
-### Monitoring
-
-| Endpoint                 | Method     | Description             |
-| ------------------------ | ---------- | ----------------------- |
-| `/api/sessions`          | GET        | Active session tracking |
-| `/api/rate-limits`       | GET        | Per-account rate limits |
-| `/api/monitoring/health` | GET        | Health check            |
-| `/api/cache`             | GET/DELETE | Cache stats / clear     |
-
-### Backup & Export/Import
-
-| Endpoint                    | Method | Description                             |
-| --------------------------- | ------ | --------------------------------------- |
-| `/api/db-backups`           | GET    | List available backups                  |
-| `/api/db-backups`           | PUT    | Create a manual backup                  |
-| `/api/db-backups`           | POST   | Restore from a specific backup          |
-| `/api/db-backups/export`    | GET    | Download database as .sqlite file       |
-| `/api/db-backups/import`    | POST   | Upload .sqlite file to replace database |
-| `/api/db-backups/exportAll` | GET    | Download full backup as .tar.gz archive |
-
-### Cloud Sync
-
-| Endpoint               | Method  | Description           |
-| ---------------------- | ------- | --------------------- |
-| `/api/sync/cloud`      | Various | Cloud sync operations |
-| `/api/sync/initialize` | POST    | Initialize sync       |
-| `/api/cloud/*`         | Various | Cloud management      |
-
-### CLI Tools
-
-| Endpoint                           | Method | Description         |
-| ---------------------------------- | ------ | ------------------- |
-| `/api/cli-tools/claude-settings`   | GET    | Claude CLI status   |
-| `/api/cli-tools/codex-settings`    | GET    | Codex CLI status    |
-| `/api/cli-tools/droid-settings`    | GET    | Droid CLI status    |
-| `/api/cli-tools/openclaw-settings` | GET    | OpenClaw CLI status |
-| `/api/cli-tools/runtime/[toolId]`  | GET    | Generic CLI runtime |
-
-CLI responses include: `installed`, `runnable`, `command`, `commandPath`, `runtimeMode`, `reason`.
-
-### Resilience & Rate Limits
-
-| Endpoint                | Method  | Description                     |
-| ----------------------- | ------- | ------------------------------- |
-| `/api/resilience`       | GET/PUT | Get/update resilience profiles  |
-| `/api/resilience/reset` | POST    | Reset circuit breakers          |
-| `/api/rate-limits`      | GET     | Per-account rate limit status   |
-| `/api/rate-limit`       | GET     | Global rate limit configuration |
-
-### Evals
-
-| Endpoint     | Method   | Description                       |
-| ------------ | -------- | --------------------------------- |
-| `/api/evals` | GET/POST | List eval suites / run evaluation |
-
-### Policies
-
-| Endpoint        | Method          | Description             |
-| --------------- | --------------- | ----------------------- |
-| `/api/policies` | GET/POST/DELETE | Manage routing policies |
-
-### Compliance
-
-| Endpoint                    | Method | Description                   |
-| --------------------------- | ------ | ----------------------------- |
-| `/api/compliance/audit-log` | GET    | Compliance audit log (last N) |
-
-### v1beta (Gemini-Compatible)
-
-| Endpoint                   | Method | Description                       |
-| -------------------------- | ------ | --------------------------------- |
-| `/v1beta/models`           | GET    | List models in Gemini format      |
-| `/v1beta/models/{...path}` | POST   | Gemini `generateContent` endpoint |
-
-These endpoints mirror Gemini's API format for clients that expect native Gemini SDK compatibility.
-
-### Internal / System APIs
-
-| Endpoint        | Method | Description                                          |
-| --------------- | ------ | ---------------------------------------------------- |
-| `/api/init`     | GET    | Application initialization check (used on first run) |
-| `/api/tags`     | GET    | Ollama-compatible model tags (for Ollama clients)    |
-| `/api/restart`  | POST   | Trigger graceful server restart                      |
-| `/api/shutdown` | POST   | Trigger graceful server shutdown                     |
-
-> **Note:** These endpoints are used internally by the system or for Ollama client compatibility. They are not typically called by end users.
-
----
-
-## Audio Transcription
-
-```bash
-POST /v1/audio/transcriptions
-Authorization: Bearer your-api-key
-Content-Type: multipart/form-data
-```
-
-Transcribe audio files using Deepgram or AssemblyAI.
-
-**Request:**
-
-```bash
-curl -X POST http://localhost:20128/v1/audio/transcriptions \
-  -H "Authorization: Bearer your-api-key" \
-  -F "file=@recording.mp3" \
-  -F "model=deepgram/nova-3"
-```
-
-**Response:**
-
-```json
-{
-  "text": "Hello, this is the transcribed audio content.",
-  "task": "transcribe",
-  "language": "en",
-  "duration": 12.5
-}
-```
-
-**Supported providers:** `deepgram/nova-3`, `assemblyai/best`.
-
-**Supported formats:** `mp3`, `wav`, `m4a`, `flac`, `ogg`, `webm`.
-
----
-
-## Ollama Compatibility
-
-For clients that use Ollama's API format:
-
-```bash
-# Chat endpoint (Ollama format)
-POST /v1/api/chat
-
-# Model listing (Ollama format)
-GET /api/tags
-```
-
-Requests are automatically translated between Ollama and internal formats.
-
----
-
-## Telemetry
-
-```bash
-# Get latency telemetry summary (p50/p95/p99 per provider)
-GET /api/telemetry/summary
-```
-
-**Response:**
-
-```json
-{
-  "providers": {
-    "claudeCode": { "p50": 245, "p95": 890, "p99": 1200, "count": 150 },
-    "github": { "p50": 180, "p95": 620, "p99": 950, "count": 320 }
-  }
-}
-```
-
----
-
-## Budget
-
-```bash
-# Get budget status for all API keys
-GET /api/usage/budget
-
-# Set or update a budget
-POST /api/usage/budget
-Content-Type: application/json
-
-{
-  "keyId": "key-123",
-  "limit": 50.00,
-  "period": "monthly"
-}
-```
-
----
-
-## Model Availability
-
-```bash
-# Get real-time model availability across all providers
-GET /api/models/availability
-
-# Check availability for a specific model
-POST /api/models/availability
-Content-Type: application/json
-
-{
-  "model": "claude-sonnet-4-5-20250929"
-}
-```
-
----
-
-## Request Processing
-
-1. Client sends request to `/v1/*`
-2. Route handler calls `handleChat`, `handleEmbedding`, `handleAudioTranscription`, or `handleImageGeneration`
-3. Model is resolved (direct provider/model or alias/combo)
-4. Credentials selected from local DB with account availability filtering
-5. For chat: `handleChatCore` — format detection, translation, cache check, idempotency check
-6. Provider executor sends upstream request
-7. Response translated back to client format (chat) or returned as-is (embeddings/images/audio)
-8. Usage/logging recorded
-9. Fallback applies on errors according to combo rules
-
-Full architecture reference: [`ARCHITECTURE.md`](ARCHITECTURE.md)
-
----
-
-## Authentication
-
-- Dashboard routes (`/dashboard/*`) use `auth_token` cookie
-- Login uses saved password hash; fallback to `INITIAL_PASSWORD`
-- `requireLogin` toggleable via `/api/settings/require-login`
-- `/v1/*` routes optionally require Bearer API key when `REQUIRE_API_KEY=true`

docs/ARCHITECTURE.md

@@ -1,6 +1,6 @@
 # OmniRoute Architecture
 
-_Last updated: 2026-02-18_
+_Last updated: 2026-02-09_
 
 ## Executive Summary
 
@@ -17,29 +17,9 @@ Core capabilities:
 - Embedding generation via `/v1/embeddings` (6 providers, 9 models)
 - Image generation via `/v1/images/generations` (4 providers, 9 models)
 - Think tag parsing (`<think>...</think>`) for reasoning models
-- Response sanitization for strict OpenAI SDK compatibility
-- Role normalization (developer→system, system→user) for cross-provider compatibility
-- Structured output conversion (json_schema → Gemini responseSchema)
 - Local persistence for providers, keys, aliases, combos, settings, pricing
 - Usage/cost tracking and request logging
 - Optional cloud sync for multi-device/state sync
-- IP allowlist/blocklist for API access control
-- Thinking budget management (passthrough/auto/custom/adaptive)
-- Global system prompt injection
-- Session tracking and fingerprinting
-- Per-account enhanced rate limiting with provider-specific profiles
-- Circuit breaker pattern for provider resilience
-- Anti-thundering herd protection with mutex locking
-- Signature-based request deduplication cache
-- Domain layer: model availability, cost rules, fallback policy, lockout policy
-- Domain state persistence (SQLite write-through cache for fallbacks, budgets, lockouts, circuit breakers)
-- Policy engine for centralized request evaluation (lockout → budget → fallback)
-- Request telemetry with p50/p95/p99 latency aggregation
-- Correlation ID (X-Request-Id) for end-to-end tracing
-- Compliance audit logging with opt-out per API key
-- Eval framework for LLM quality assurance
-- Resilience UI dashboard with real-time circuit breaker status
-- Modular OAuth providers (12 individual modules under `src/lib/oauth/providers/`)
 
 Primary runtime model:
 
@@ -123,18 +103,18 @@ Main directories:
 
 Important compatibility routes:
 
-- `src/app/api/v1/chat/completions/route.ts`
-- `src/app/api/v1/messages/route.ts`
-- `src/app/api/v1/responses/route.ts`
-- `src/app/api/v1/models/route.ts` — includes custom models with `custom: true`
-- `src/app/api/v1/embeddings/route.ts` — embedding generation (6 providers)
-- `src/app/api/v1/images/generations/route.ts` — image generation (4+ providers incl. Antigravity/Nebius)
-- `src/app/api/v1/messages/count_tokens/route.ts`
-- `src/app/api/v1/providers/[provider]/chat/completions/route.ts` — dedicated per-provider chat
-- `src/app/api/v1/providers/[provider]/embeddings/route.ts` — dedicated per-provider embeddings
-- `src/app/api/v1/providers/[provider]/images/generations/route.ts` — dedicated per-provider images
-- `src/app/api/v1beta/models/route.ts`
-- `src/app/api/v1beta/models/[...path]/route.ts`
+- `src/app/api/v1/chat/completions/route.js`
+- `src/app/api/v1/messages/route.js`
+- `src/app/api/v1/responses/route.js`
+- `src/app/api/v1/models/route.js` — includes custom models with `custom: true`
+- `src/app/api/v1/embeddings/route.js` — embedding generation (6 providers)
+- `src/app/api/v1/images/generations/route.js` — image generation (4+ providers incl. Antigravity/Nebius)
+- `src/app/api/v1/messages/count_tokens/route.js`
+- `src/app/api/v1/providers/[provider]/chat/completions/route.js` — dedicated per-provider chat
+- `src/app/api/v1/providers/[provider]/embeddings/route.js` — dedicated per-provider embeddings
+- `src/app/api/v1/providers/[provider]/images/generations/route.js` — dedicated per-provider images
+- `src/app/api/v1beta/models/route.js`
+- `src/app/api/v1beta/models/[...path]/route.js`
 
 Management domains:
 
@@ -149,111 +129,52 @@ Management domains:
 - Usage: `src/app/api/usage/*`
 - Sync/cloud: `src/app/api/sync/*`, `src/app/api/cloud/*`
 - CLI tooling helpers: `src/app/api/cli-tools/*`
-- IP filter: `src/app/api/settings/ip-filter` (GET/PUT)
-- Thinking budget: `src/app/api/settings/thinking-budget` (GET/PUT)
-- System prompt: `src/app/api/settings/system-prompt` (GET/PUT)
-- Sessions: `src/app/api/sessions` (GET)
-- Rate limits: `src/app/api/rate-limits` (GET)
-- Resilience: `src/app/api/resilience` (GET/PATCH) — provider profiles, circuit breaker, rate limit state
-- Resilience reset: `src/app/api/resilience/reset` (POST) — reset breakers + cooldowns
-- Cache stats: `src/app/api/cache/stats` (GET/DELETE)
-- Model availability: `src/app/api/models/availability` (GET/POST)
-- Telemetry: `src/app/api/telemetry/summary` (GET)
-- Budget: `src/app/api/usage/budget` (GET/POST)
-- Fallback chains: `src/app/api/fallback/chains` (GET/POST/DELETE)
-- Compliance audit: `src/app/api/compliance/audit-log` (GET)
-- Evals: `src/app/api/evals` (GET/POST), `src/app/api/evals/[suiteId]` (GET)
-- Policies: `src/app/api/policies` (GET/POST)
 
 ## 2) SSE + Translation Core
 
 Main flow modules:
 
-- Entry: `src/sse/handlers/chat.ts`
-- Core orchestration: `open-sse/handlers/chatCore.ts`
+- Entry: `src/sse/handlers/chat.js`
+- Core orchestration: `open-sse/handlers/chatCore.js`
 - Provider execution adapters: `open-sse/executors/*`
-- Format detection/provider config: `open-sse/services/provider.ts`
-- Model parse/resolve: `src/sse/services/model.ts`, `open-sse/services/model.ts`
-- Account fallback logic: `open-sse/services/accountFallback.ts`
-- Translation registry: `open-sse/translator/index.ts`
-- Stream transformations: `open-sse/utils/stream.ts`, `open-sse/utils/streamHandler.ts`
-- Usage extraction/normalization: `open-sse/utils/usageTracking.ts`
-- Think tag parser: `open-sse/utils/thinkTagParser.ts`
-- Embedding handler: `open-sse/handlers/embeddings.ts`
-- Embedding provider registry: `open-sse/config/embeddingRegistry.ts`
-- Image generation handler: `open-sse/handlers/imageGeneration.ts`
-- Image provider registry: `open-sse/config/imageRegistry.ts`
-- Response sanitization: `open-sse/handlers/responseSanitizer.ts`
-- Role normalization: `open-sse/services/roleNormalizer.ts`
-
-Services (business logic):
-
-- Account selection/scoring: `open-sse/services/accountSelector.ts`
-- Context lifecycle management: `open-sse/services/contextManager.ts`
-- IP filter enforcement: `open-sse/services/ipFilter.ts`
-- Session tracking: `open-sse/services/sessionManager.ts`
-- Request deduplication: `open-sse/services/signatureCache.ts`
-- System prompt injection: `open-sse/services/systemPrompt.ts`
-- Thinking budget management: `open-sse/services/thinkingBudget.ts`
-- Wildcard model routing: `open-sse/services/wildcardRouter.ts`
-- Rate limit management: `open-sse/services/rateLimitManager.ts`
-- Circuit breaker: `open-sse/services/circuitBreaker.ts`
-
-Domain layer modules:
-
-- Model availability: `src/lib/domain/modelAvailability.ts`
-- Cost rules/budgets: `src/lib/domain/costRules.ts`
-- Fallback policy: `src/lib/domain/fallbackPolicy.ts`
-- Combo resolver: `src/lib/domain/comboResolver.ts`
-- Lockout policy: `src/lib/domain/lockoutPolicy.ts`
-- Policy engine: `src/domain/policyEngine.ts` — centralized lockout → budget → fallback evaluation
-- Error codes catalog: `src/lib/domain/errorCodes.ts`
-- Request ID: `src/lib/domain/requestId.ts`
-- Fetch timeout: `src/lib/domain/fetchTimeout.ts`
-- Request telemetry: `src/lib/domain/requestTelemetry.ts`
-- Compliance/audit: `src/lib/domain/compliance/index.ts`
-- Eval runner: `src/lib/domain/evalRunner.ts`
-- Domain state persistence: `src/lib/db/domainState.ts` — SQLite CRUD for fallback chains, budgets, cost history, lockout state, circuit breakers
-
-OAuth provider modules (12 individual files under `src/lib/oauth/providers/`):
-
-- Registry index: `src/lib/oauth/providers/index.ts`
-- Individual providers: `claude.ts`, `codex.ts`, `gemini.ts`, `antigravity.ts`, `iflow.ts`, `qwen.ts`, `kimi-coding.ts`, `github.ts`, `kiro.ts`, `cursor.ts`, `kilocode.ts`, `cline.ts`
-- Thin wrapper: `src/lib/oauth/providers.ts` — re-exports from individual modules
+- Format detection/provider config: `open-sse/services/provider.js`
+- Model parse/resolve: `src/sse/services/model.js`, `open-sse/services/model.js`
+- Account fallback logic: `open-sse/services/accountFallback.js`
+- Translation registry: `open-sse/translator/index.js`
+- Stream transformations: `open-sse/utils/stream.js`, `open-sse/utils/streamHandler.js`
+- Usage extraction/normalization: `open-sse/utils/usageTracking.js`
+- Think tag parser: `open-sse/utils/thinkTagParser.js`
+- Embedding handler: `open-sse/handlers/embeddings.js`
+- Embedding provider registry: `open-sse/config/embeddingRegistry.js`
+- Image generation handler: `open-sse/handlers/imageGeneration.js`
+- Image provider registry: `open-sse/config/imageRegistry.js`
 
 ## 3) Persistence Layer
 
 Primary state DB:
 
-- `src/lib/localDb.ts`
+- `src/lib/localDb.js`
 - file: `${DATA_DIR}/db.json` (or `$XDG_CONFIG_HOME/omniroute/db.json` when set, else `~/.omniroute/db.json`)
-- entities: providerConnections, providerNodes, modelAliases, combos, apiKeys, settings, pricing, **customModels**, **proxyConfig**, **ipFilter**, **thinkingBudget**, **systemPrompt**
+- entities: providerConnections, providerNodes, modelAliases, combos, apiKeys, settings, pricing, **customModels**, **proxyConfig**
 
 Usage DB:
 
-- `src/lib/usageDb.ts`
+- `src/lib/usageDb.js`
 - files: `${DATA_DIR}/usage.json`, `${DATA_DIR}/log.txt`, `${DATA_DIR}/call_logs/`
 - follows same base directory policy as `localDb` (`DATA_DIR`, then `XDG_CONFIG_HOME/omniroute` when set)
-- decomposed into focused sub-modules: `migrations.ts`, `usageHistory.ts`, `costCalculator.ts`, `usageStats.ts`, `callLogs.ts`
-
-Domain State DB (SQLite):
-
-- `src/lib/db/domainState.ts` — CRUD operations for domain state
-- Tables (created in `src/lib/db/core.ts`): `domain_fallback_chains`, `domain_budgets`, `domain_cost_history`, `domain_lockout_state`, `domain_circuit_breakers`
-- Write-through cache pattern: in-memory Maps are authoritative at runtime; mutations are written synchronously to SQLite; state is restored from DB on cold start
 
 ## 4) Auth + Security Surfaces
 
-- Dashboard cookie auth: `src/proxy.ts`, `src/app/api/auth/login/route.ts`
-- API key generation/verification: `src/shared/utils/apiKey.ts`
+- Dashboard cookie auth: `src/proxy.js`, `src/app/api/auth/login/route.js`
+- API key generation/verification: `src/shared/utils/apiKey.js`
 - Provider secrets persisted in `providerConnections` entries
-- Outbound proxy support via `open-sse/utils/proxyFetch.ts` (env vars) and `open-sse/utils/networkProxy.ts` (configurable per-provider or global)
+- Outbound proxy support via `open-sse/utils/proxyFetch.js` (env vars) and `open-sse/utils/networkProxy.js` (configurable per-provider or global)
 
 ## 5) Cloud Sync
 
-- Scheduler init: `src/lib/initCloudSync.ts`, `src/shared/services/initializeCloudSync.ts`
-- Periodic task: `src/shared/services/cloudSyncScheduler.ts`
-- Control route: `src/app/api/sync/cloud/route.ts`
+- Scheduler init: `src/lib/initCloudSync.js`, `src/shared/services/initializeCloudSync.js`
+- Periodic task: `src/shared/services/cloudSyncScheduler.js`
+- Control route: `src/app/api/sync/cloud/route.js`
 
 ## Request Lifecycle (`/v1/chat/completions`)
 
@@ -332,7 +253,7 @@ flowchart TD
     Q -- No --> R[Return all unavailable]
 ```
 
-Fallback decisions are driven by `open-sse/services/accountFallback.ts` using status codes and error-message heuristics.
+Fallback decisions are driven by `open-sse/services/accountFallback.js` using status codes and error-message heuristics.
 
 ## OAuth Onboarding and Token Refresh Lifecycle
 
@@ -364,7 +285,7 @@ sequenceDiagram
     Test-->>UI: validation result
 ```
 
-Refresh during live traffic is executed inside `open-sse/handlers/chatCore.ts` via executor `refreshCredentials()`.
+Refresh during live traffic is executed inside `open-sse/handlers/chatCore.js` via executor `refreshCredentials()`.
 
 ## Cloud Sync Lifecycle (Enable / Sync / Disable)
 
@@ -413,9 +334,6 @@ erDiagram
       number stickyRoundRobinLimit
       boolean requireLogin
       string password_hash
-      string fallbackStrategy
-      json rateLimitDefaults
-      json providerProfiles
     }
 
     PROVIDER_CONNECTION {
@@ -481,24 +399,6 @@ erDiagram
       string global
       json providers
     }
-
-    IP_FILTER {
-      string mode
-      string[] allowlist
-      string[] blocklist
-    }
-
-    THINKING_BUDGET {
-      string mode
-      number customBudget
-      string effortLevel
-    }
-
-    SYSTEM_PROMPT {
-      boolean enabled
-      string prompt
-      string position
-    }
 ```
 
 Physical storage files:
@@ -559,33 +459,28 @@ flowchart LR
 - `src/app/api/usage/*`: usage and logs APIs
 - `src/app/api/sync/*` + `src/app/api/cloud/*`: cloud sync and cloud-facing helpers
 - `src/app/api/cli-tools/*`: local CLI config writers/checkers
-- `src/app/api/settings/ip-filter`: IP allowlist/blocklist (GET/PUT)
-- `src/app/api/settings/thinking-budget`: thinking token budget config (GET/PUT)
-- `src/app/api/settings/system-prompt`: global system prompt (GET/PUT)
-- `src/app/api/sessions`: active session listing (GET)
-- `src/app/api/rate-limits`: per-account rate limit status (GET)
 
 ### Routing and Execution Core
 
-- `src/sse/handlers/chat.ts`: request parse, combo handling, account selection loop
-- `open-sse/handlers/chatCore.ts`: translation, executor dispatch, retry/refresh handling, stream setup
+- `src/sse/handlers/chat.js`: request parse, combo handling, account selection loop
+- `open-sse/handlers/chatCore.js`: translation, executor dispatch, retry/refresh handling, stream setup
 - `open-sse/executors/*`: provider-specific network and format behavior
 
 ### Translation Registry and Format Converters
 
-- `open-sse/translator/index.ts`: translator registry and orchestration
+- `open-sse/translator/index.js`: translator registry and orchestration
 - Request translators: `open-sse/translator/request/*`
 - Response translators: `open-sse/translator/response/*`
-- Format constants: `open-sse/translator/formats.ts`
+- Format constants: `open-sse/translator/formats.js`
 
 ### Persistence
 
-- `src/lib/localDb.ts`: persistent config/state
-- `src/lib/usageDb.ts`: usage history and rolling request logs
+- `src/lib/localDb.js`: persistent config/state
+- `src/lib/usageDb.js`: usage history and rolling request logs
 
 ## Provider Executor Coverage (Strategy Pattern)
 
-Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/executors/base.ts`), which provides URL building, header construction, retry with exponential backoff, credential refresh hooks, and the `execute()` orchestration method.
+Each provider has a specialized executor extending `BaseExecutor` (in `open-sse/executors/base.js`), which provides URL building, header construction, retry with exponential backoff, credential refresh hooks, and the `execute()` orchestration method.
 
 | Executor              | Provider(s)                                                                                                                                                  | Special Handling                                                     |
 | --------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ | -------------------------------------------------------------------- |
@@ -652,23 +547,16 @@ Source Format → OpenAI (hub) → Target Format
 
 Translations are selected dynamically based on source payload shape and provider target format.
 
-Additional processing layers in the translation pipeline:
-
-- **Response sanitization** — Strips non-standard fields from OpenAI-format responses (both streaming and non-streaming) to ensure strict SDK compliance
-- **Role normalization** — Converts `developer` → `system` for non-OpenAI targets; merges `system` → `user` for models that reject the system role (GLM, ERNIE)
-- **Think tag extraction** — Parses `<think>...</think>` blocks from content into `reasoning_content` field
-- **Structured output** — Converts OpenAI `response_format.json_schema` to Gemini's `responseMimeType` + `responseSchema`
-
 ## Supported API Endpoints
 
 | Endpoint                                           | Format             | Handler                                              |
 | -------------------------------------------------- | ------------------ | ---------------------------------------------------- |
-| `POST /v1/chat/completions`                        | OpenAI Chat        | `src/sse/handlers/chat.ts`                           |
+| `POST /v1/chat/completions`                        | OpenAI Chat        | `src/sse/handlers/chat.js`                           |
 | `POST /v1/messages`                                | Claude Messages    | Same handler (auto-detected)                         |
-| `POST /v1/responses`                               | OpenAI Responses   | `open-sse/handlers/responsesHandler.ts`              |
-| `POST /v1/embeddings`                              | OpenAI Embeddings  | `open-sse/handlers/embeddings.ts`                    |
+| `POST /v1/responses`                               | OpenAI Responses   | `open-sse/handlers/responsesHandler.js`              |
+| `POST /v1/embeddings`                              | OpenAI Embeddings  | `open-sse/handlers/embeddings.js`                    |
 | `GET /v1/embeddings`                               | Model listing      | API route                                            |
-| `POST /v1/images/generations`                      | OpenAI Images      | `open-sse/handlers/imageGeneration.ts`               |
+| `POST /v1/images/generations`                      | OpenAI Images      | `open-sse/handlers/imageGeneration.js`               |
 | `GET /v1/images/generations`                       | Model listing      | API route                                            |
 | `POST /v1/providers/{provider}/chat/completions`   | OpenAI Chat        | Dedicated per-provider with model validation         |
 | `POST /v1/providers/{provider}/embeddings`         | OpenAI Embeddings  | Dedicated per-provider with model validation         |
@@ -683,11 +571,11 @@ Additional processing layers in the translation pipeline:
 
 ## Bypass Handler
 
-The bypass handler (`open-sse/utils/bypassHandler.ts`) intercepts known "throwaway" requests from Claude CLI — warmup pings, title extractions, and token counts — and returns a **fake response** without consuming upstream provider tokens. This is triggered only when `User-Agent` contains `claude-cli`.
+The bypass handler (`open-sse/utils/bypassHandler.js`) intercepts known "throwaway" requests from Claude CLI — warmup pings, title extractions, and token counts — and returns a **fake response** without consuming upstream provider tokens. This is triggered only when `User-Agent` contains `claude-cli`.
 
 ## Request Logger Pipeline
 
-The request logger (`open-sse/utils/requestLogger.ts`) provides a 7-stage debug logging pipeline, disabled by default, enabled via `ENABLE_REQUEST_LOGS=true`:
+The request logger (`open-sse/utils/requestLogger.js`) provides a 7-stage debug logging pipeline, disabled by default, enabled via `ENABLE_REQUEST_LOGS=true`:
 
 ```
 1_req_client.json → 2_req_source.json → 3_req_openai.json → 4_req_target.json
@@ -729,7 +617,7 @@ Files are written to `<repo>/logs/<session>/` for each request session.
 
 Runtime visibility sources:
 
-- console logs from `src/sse/utils/logger.ts`
+- console logs from `src/sse/utils/logger.js`
 - per-request usage aggregates in `usage.json`
 - textual request status log in `log.txt`
 - optional deep request/translation logs under `logs/` when `ENABLE_REQUEST_LOGS=true`
@@ -761,18 +649,17 @@ Environment variables actively used by code:
 ## Known Architectural Notes
 
 1. `usageDb` and `localDb` now share the same base directory policy (`DATA_DIR` -> `XDG_CONFIG_HOME/omniroute` -> `~/.omniroute`) with legacy file migration.
-2. `/api/v1/route.ts` returns a static model list and is not the main models source used by `/v1/models`.
+2. `/api/v1/route.js` returns a static model list and is not the main models source used by `/v1/models`.
 3. Request logger writes full headers/body when enabled; treat log directory as sensitive.
 4. Cloud behavior depends on correct `NEXT_PUBLIC_BASE_URL` and cloud endpoint reachability.
 5. The `open-sse/` directory is published as the `@omniroute/open-sse` **npm workspace package**. Source code imports it via `@omniroute/open-sse/...` (resolved by Next.js `transpilePackages`). File paths in this document still use the directory name `open-sse/` for consistency.
-6. Charts in the dashboard use **Recharts** (SVG-based) for accessible, interactive analytics visualizations (model usage bar charts, provider breakdown tables with success rates).
-7. E2E tests use **Playwright** (`tests/e2e/`), run via `npm run test:e2e`. Unit tests use **Node.js test runner** (`tests/unit/`), run via `npm run test:plan3`. Source code under `src/` is **TypeScript** (`.ts`/`.tsx`); the `open-sse/` workspace remains JavaScript (`.js`).
-8. Settings page is organized into 5 tabs: Security, Routing (6 global strategies: fill-first, round-robin, p2c, random, least-used, cost-optimized), Resilience (editable rate limits, circuit breaker, policies), AI (thinking budget, system prompt, prompt cache), Advanced (proxy).
+6. Charts in the dashboard use **Recharts** (SVG-based) for accessible, interactive visualizations (bar charts, donut charts).
+7. E2E tests use **Playwright** (`tests/e2e/`), run via `npm run test:e2e`. Unit tests use **Node.js test runner** (`tests/unit/`), run via `npm run test:plan3`.
 
 ## Operational Verification Checklist
 
-- Build from source: `npm run build`
-- Build Docker image: `docker build -t omniroute .`
+- Build from source: `cd /root/dev/omniroute && npm run build`
+- Build Docker image: `cd /root/dev/omniroute && docker build -t omniroute .`
 - Start service and verify:
 - `GET /api/settings`
 - `GET /api/v1/models`

docs/CODEBASE_DOCUMENTATION.md

@@ -110,18 +110,18 @@ The **single source of truth** for all provider configuration.
 
 | File                          | Purpose                                                                                                                                                                                                                   |
 | ----------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `constants.ts`                | `PROVIDERS` object with base URLs, OAuth credentials (defaults), headers, and default system prompts for every provider. Also defines `HTTP_STATUS`, `ERROR_TYPES`, `COOLDOWN_MS`, `BACKOFF_CONFIG`, and `SKIP_PATTERNS`. |
-| `credentialLoader.ts`         | Loads external credentials from `data/provider-credentials.json` and merges them over the hardcoded defaults in `PROVIDERS`. Keeps secrets out of source control while maintaining backwards compatibility.               |
-| `providerModels.ts`           | Central model registry: maps provider aliases → model IDs. Functions like `getModels()`, `getProviderByAlias()`.                                                                                                          |
-| `codexInstructions.ts`        | System instructions injected into Codex requests (editing constraints, sandbox rules, approval policies).                                                                                                                 |
-| `defaultThinkingSignature.ts` | Default "thinking" signatures for Claude and Gemini models.                                                                                                                                                               |
-| `ollamaModels.ts`             | Schema definition for local Ollama models (name, size, family, quantization).                                                                                                                                             |
+| `constants.js`                | `PROVIDERS` object with base URLs, OAuth credentials (defaults), headers, and default system prompts for every provider. Also defines `HTTP_STATUS`, `ERROR_TYPES`, `COOLDOWN_MS`, `BACKOFF_CONFIG`, and `SKIP_PATTERNS`. |
+| `credentialLoader.js`         | Loads external credentials from `data/provider-credentials.json` and merges them over the hardcoded defaults in `PROVIDERS`. Keeps secrets out of source control while maintaining backwards compatibility.               |
+| `providerModels.js`           | Central model registry: maps provider aliases → model IDs. Functions like `getModels()`, `getProviderByAlias()`.                                                                                                          |
+| `codexInstructions.js`        | System instructions injected into Codex requests (editing constraints, sandbox rules, approval policies).                                                                                                                 |
+| `defaultThinkingSignature.js` | Default "thinking" signatures for Claude and Gemini models.                                                                                                                                                               |
+| `ollamaModels.js`             | Schema definition for local Ollama models (name, size, family, quantization).                                                                                                                                             |
 
 #### Credential Loading Flow
 
 ```mermaid
 flowchart TD
-    A["App starts"] --> B["constants.ts defines PROVIDERS\nwith hardcoded defaults"]
+    A["App starts"] --> B["constants.js defines PROVIDERS\nwith hardcoded defaults"]
     B --> C{"data/provider-credentials.json\nexists?"}
     C -->|Yes| D["credentialLoader reads JSON"]
     C -->|No| E["Use hardcoded defaults"]
@@ -194,15 +194,15 @@ classDiagram
 
 | Executor         | Provider                                   | Key Specializations                                                                                                 |
 | ---------------- | ------------------------------------------ | ------------------------------------------------------------------------------------------------------------------- |
-| `base.ts`        | —                                          | Abstract base: URL building, headers, retry logic, credential refresh                                               |
-| `default.ts`     | Claude, Gemini, OpenAI, GLM, Kimi, MiniMax | Generic OAuth token refresh for standard providers                                                                  |
-| `antigravity.ts` | Google Cloud Code                          | Project/session ID generation, multi-URL fallback, custom retry parsing from error messages ("reset after 2h7m23s") |
-| `cursor.ts`      | Cursor IDE                                 | **Most complex**: SHA-256 checksum auth, Protobuf request encoding, binary EventStream → SSE response parsing       |
-| `codex.ts`       | OpenAI Codex                               | Injects system instructions, manages thinking levels, removes unsupported parameters                                |
-| `gemini-cli.ts`  | Google Gemini CLI                          | Custom URL building (`streamGenerateContent`), Google OAuth token refresh                                           |
-| `github.ts`      | GitHub Copilot                             | Dual token system (GitHub OAuth + Copilot token), VSCode header mimicking                                           |
-| `kiro.ts`        | AWS CodeWhisperer                          | AWS EventStream binary parsing, AMZN event frames, token estimation                                                 |
-| `index.ts`       | —                                          | Factory: maps provider name → executor class, with default fallback                                                 |
+| `base.js`        | —                                          | Abstract base: URL building, headers, retry logic, credential refresh                                               |
+| `default.js`     | Claude, Gemini, OpenAI, GLM, Kimi, MiniMax | Generic OAuth token refresh for standard providers                                                                  |
+| `antigravity.js` | Google Cloud Code                          | Project/session ID generation, multi-URL fallback, custom retry parsing from error messages ("reset after 2h7m23s") |
+| `cursor.js`      | Cursor IDE                                 | **Most complex**: SHA-256 checksum auth, Protobuf request encoding, binary EventStream → SSE response parsing       |
+| `codex.js`       | OpenAI Codex                               | Injects system instructions, manages thinking levels, removes unsupported parameters                                |
+| `gemini-cli.js`  | Google Gemini CLI                          | Custom URL building (`streamGenerateContent`), Google OAuth token refresh                                           |
+| `github.js`      | GitHub Copilot                             | Dual token system (GitHub OAuth + Copilot token), VSCode header mimicking                                           |
+| `kiro.js`        | AWS CodeWhisperer                          | AWS EventStream binary parsing, AMZN event frames, token estimation                                                 |
+| `index.js`       | —                                          | Factory: maps provider name → executor class, with default fallback                                                 |
 
 ---
 
@@ -212,12 +212,12 @@ The **orchestration layer** — coordinates translation, execution, streaming, a
 
 | File                  | Purpose                                                                                                                                                                                                                |
 | --------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `chatCore.ts`         | **Central orchestrator** (~600 lines). Handles the complete request lifecycle: format detection → translation → executor dispatch → streaming/non-streaming response → token refresh → error handling → usage logging. |
-| `responsesHandler.ts` | Adapter for OpenAI's Responses API: converts Responses format → Chat Completions → sends to `chatCore` → converts SSE back to Responses format.                                                                        |
-| `embeddings.ts`       | Embedding generation handler: resolves embedding model → provider, dispatches to provider API, returns OpenAI-compatible embedding response. Supports 6+ providers.                                                    |
-| `imageGeneration.ts`  | Image generation handler: resolves image model → provider, supports OpenAI-compatible, Gemini-image (Antigravity), and fallback (Nebius) modes. Returns base64 or URL images.                                          |
+| `chatCore.js`         | **Central orchestrator** (~600 lines). Handles the complete request lifecycle: format detection → translation → executor dispatch → streaming/non-streaming response → token refresh → error handling → usage logging. |
+| `responsesHandler.js` | Adapter for OpenAI's Responses API: converts Responses format → Chat Completions → sends to `chatCore` → converts SSE back to Responses format.                                                                        |
+| `embeddings.js`       | Embedding generation handler: resolves embedding model → provider, dispatches to provider API, returns OpenAI-compatible embedding response. Supports 6+ providers.                                                    |
+| `imageGeneration.js`  | Image generation handler: resolves image model → provider, supports OpenAI-compatible, Gemini-image (Antigravity), and fallback (Nebius) modes. Returns base64 or URL images.                                          |
 
-#### Request Lifecycle (chatCore.ts)
+#### Request Lifecycle (chatCore.js)
 
 ```mermaid
 sequenceDiagram
@@ -262,20 +262,12 @@ Business logic that supports the handlers and executors.
 
 | File                 | Purpose                                                                                                                                                                                                                                                                                                                                |
 | -------------------- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| `provider.ts`        | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
-| `model.ts`           | Model string parsing (`claude/model-name` → `{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support.                                                                             |
-| `accountFallback.ts` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not).                                                                                                                                                                         |
-| `tokenRefresh.ts`    | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff.                                                                       |
-| `combo.ts`           | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes.                                                                                                                                                                          |
-| `usage.ts`           | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings).                                                                                                                                                                              |
-| `accountSelector.ts` | Smart account selection with scoring algorithm: considers priority, health status, round-robin position, and cooldown state to pick the optimal account for each request.                                                                                                                                                              |
-| `contextManager.ts`  | Request context lifecycle management: creates and tracks per-request context objects with metadata (request ID, timestamps, provider info) for debugging and logging.                                                                                                                                                                  |
-| `ipFilter.ts`        | IP-based access control: supports allowlist and blocklist modes. Validates client IP against configured rules before processing API requests.                                                                                                                                                                                          |
-| `sessionManager.ts`  | Session tracking with client fingerprinting: tracks active sessions using hashed client identifiers, monitors request counts, and provides session metrics.                                                                                                                                                                            |
-| `signatureCache.ts`  | Request signature-based deduplication cache: prevents duplicate requests by caching recent request signatures and returning cached responses for identical requests within a time window.                                                                                                                                              |
-| `systemPrompt.ts`    | Global system prompt injection: prepends or appends a configurable system prompt to all requests, with per-provider compatibility handling.                                                                                                                                                                                            |
-| `thinkingBudget.ts`  | Reasoning token budget management: supports passthrough, auto (strip thinking config), custom (fixed budget), and adaptive (complexity-scaled) modes for controlling thinking/reasoning tokens.                                                                                                                                        |
-| `wildcardRouter.ts`  | Wildcard model pattern routing: resolves wildcard patterns (e.g., `*/claude-*`) to concrete provider/model pairs based on availability and priority.                                                                                                                                                                                   |
+| `provider.js`        | **Format detection** (`detectFormat`): analyzes request body structure to identify Claude/OpenAI/Gemini/Antigravity/Responses formats (includes `max_tokens` heuristic for Claude). Also: URL building, header building, thinking config normalization. Supports `openai-compatible-*` and `anthropic-compatible-*` dynamic providers. |
+| `model.js`           | Model string parsing (`claude/model-name` → `{provider: "claude", model: "model-name"}`), alias resolution with collision detection, input sanitization (rejects path traversal/control chars), and model info resolution with async alias getter support.                                                                             |
+| `accountFallback.js` | Rate-limit handling: exponential backoff (1s → 2s → 4s → max 2min), account cooldown management, error classification (which errors trigger fallback vs. not).                                                                                                                                                                         |
+| `tokenRefresh.js`    | OAuth token refresh for **every provider**: Google (Gemini, Antigravity), Claude, Codex, Qwen, iFlow, GitHub (OAuth + Copilot dual-token), Kiro (AWS SSO OIDC + Social Auth). Includes in-flight promise deduplication cache and retry with exponential backoff.                                                                       |
+| `combo.js`           | **Combo models**: chains of fallback models. If model A fails with a fallback-eligible error, try model B, then C, etc. Returns actual upstream status codes.                                                                                                                                                                          |
+| `usage.js`           | Fetches quota/usage data from provider APIs (GitHub Copilot quotas, Antigravity model quotas, Codex rate limits, Kiro usage breakdowns, Claude settings).                                                                                                                                                                              |
 
 #### Token Refresh Deduplication
 
@@ -377,8 +369,8 @@ graph TD
 | `request/`   | 8 translators | Convert request bodies between formats. Each file self-registers via `register(from, to, fn)` on import.                                                                                                                                                         |
 | `response/`  | 7 translators | Convert streaming response chunks between formats. Handles SSE event types, thinking blocks, tool calls.                                                                                                                                                         |
 | `helpers/`   | 6 helpers     | Shared utilities: `claudeHelper` (system prompt extraction, thinking config), `geminiHelper` (parts/contents mapping), `openaiHelper` (format filtering), `toolCallHelper` (ID generation, missing response injection), `maxTokensHelper`, `responsesApiHelper`. |
-| `index.ts`   | —             | Translation engine: `translateRequest()`, `translateResponse()`, state management, registry.                                                                                                                                                                     |
-| `formats.ts` | —             | Format constants: `OPENAI`, `CLAUDE`, `GEMINI`, `ANTIGRAVITY`, `KIRO`, `CURSOR`, `OPENAI_RESPONSES`.                                                                                                                                                             |
+| `index.js`   | —             | Translation engine: `translateRequest()`, `translateResponse()`, state management, registry.                                                                                                                                                                     |
+| `formats.js` | —             | Format constants: `OPENAI`, `CLAUDE`, `GEMINI`, `ANTIGRAVITY`, `KIRO`, `CURSOR`, `OPENAI_RESPONSES`.                                                                                                                                                             |
 
 #### Key Design: Self-Registering Plugins
 
@@ -397,13 +389,13 @@ import "./request/claude-to-openai.js"; // ← self-registers
 
 | File               | Purpose                                                                                                                                                                                                                                                                              |
 | ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
-| `error.ts`         | Error response building (OpenAI-compatible format), upstream error parsing, Antigravity retry-time extraction from error messages, SSE error streaming.                                                                                                                              |
-| `stream.ts`        | **SSE Transform Stream** — the core streaming pipeline. Two modes: `TRANSLATE` (full format translation) and `PASSTHROUGH` (normalize + extract usage). Handles chunk buffering, usage estimation, content length tracking. Per-stream encoder/decoder instances avoid shared state. |
-| `streamHelpers.ts` | Low-level SSE utilities: `parseSSELine` (whitespace-tolerant), `hasValuableContent` (filters empty chunks for OpenAI/Claude/Gemini), `fixInvalidId`, `formatSSE` (format-aware SSE serialization with `perf_metrics` cleanup).                                                       |
-| `usageTracking.ts` | Token usage extraction from any format (Claude/OpenAI/Gemini/Responses), estimation with separate tool/message char-per-token ratios, buffer addition (2000 tokens safety margin), format-specific field filtering, console logging with ANSI colors.                                |
-| `requestLogger.ts` | File-based request logging (opt-in via `ENABLE_REQUEST_LOGS=true`). Creates session folders with numbered files: `1_req_client.json` → `7_res_client.txt`. All I/O is async (fire-and-forget). Masks sensitive headers.                                                              |
-| `bypassHandler.ts` | Intercepts specific patterns from Claude CLI (title extraction, warmup, count) and returns fake responses without calling any provider. Supports both streaming and non-streaming. Intentionally limited to Claude CLI scope.                                                        |
-| `networkProxy.ts`  | Resolves outbound proxy URL for a given provider with precedence: provider-specific config → global config → environment variables (`HTTPS_PROXY`/`HTTP_PROXY`/`ALL_PROXY`). Supports `NO_PROXY` exclusions. Caches config for 30s.                                                  |
+| `error.js`         | Error response building (OpenAI-compatible format), upstream error parsing, Antigravity retry-time extraction from error messages, SSE error streaming.                                                                                                                              |
+| `stream.js`        | **SSE Transform Stream** — the core streaming pipeline. Two modes: `TRANSLATE` (full format translation) and `PASSTHROUGH` (normalize + extract usage). Handles chunk buffering, usage estimation, content length tracking. Per-stream encoder/decoder instances avoid shared state. |
+| `streamHelpers.js` | Low-level SSE utilities: `parseSSELine` (whitespace-tolerant), `hasValuableContent` (filters empty chunks for OpenAI/Claude/Gemini), `fixInvalidId`, `formatSSE` (format-aware SSE serialization with `perf_metrics` cleanup).                                                       |
+| `usageTracking.js` | Token usage extraction from any format (Claude/OpenAI/Gemini/Responses), estimation with separate tool/message char-per-token ratios, buffer addition (2000 tokens safety margin), format-specific field filtering, console logging with ANSI colors.                                |
+| `requestLogger.js` | File-based request logging (opt-in via `ENABLE_REQUEST_LOGS=true`). Creates session folders with numbered files: `1_req_client.json` → `7_res_client.txt`. All I/O is async (fire-and-forget). Masks sensitive headers.                                                              |
+| `bypassHandler.js` | Intercepts specific patterns from Claude CLI (title extraction, warmup, count) and returns fake responses without calling any provider. Supports both streaming and non-streaming. Intentionally limited to Claude CLI scope.                                                        |
+| `networkProxy.js`  | Resolves outbound proxy URL for a given provider with precedence: provider-specific config → global config → environment variables (`HTTPS_PROXY`/`HTTP_PROXY`/`ALL_PROXY`). Supports `NO_PROXY` exclusions. Caches config for 30s.                                                  |
 
 #### SSE Streaming Pipeline
 
@@ -450,7 +442,7 @@ logs/
 | Directory     | Purpose                                                                |
 | ------------- | ---------------------------------------------------------------------- |
 | `src/app/`    | Web UI, API routes, Express middleware, OAuth callback handlers        |
-| `src/lib/`    | Database access (`localDb.ts`, `usageDb.ts`), authentication, shared   |
+| `src/lib/`    | Database access (`localDb.js`, `usageDb.js`), authentication, shared   |
 | `src/mitm/`   | Man-in-the-middle proxy utilities for intercepting provider traffic    |
 | `src/models/` | Database model definitions                                             |
 | `src/shared/` | Wrappers around open-sse functions (provider, stream, error, etc.)     |
@@ -468,11 +460,6 @@ logs/
 | `/v1/providers/[provider]/chat/completions`   | POST            | Dedicated per-provider chat completions with model validation                         |
 | `/v1/providers/[provider]/embeddings`         | POST            | Dedicated per-provider embeddings with model validation                               |
 | `/v1/providers/[provider]/images/generations` | POST            | Dedicated per-provider image generation with model validation                         |
-| `/api/settings/ip-filter`                     | GET/PUT         | IP allowlist/blocklist management                                                     |
-| `/api/settings/thinking-budget`               | GET/PUT         | Reasoning token budget configuration (passthrough/auto/custom/adaptive)               |
-| `/api/settings/system-prompt`                 | GET/PUT         | Global system prompt injection for all requests                                       |
-| `/api/sessions`                               | GET             | Active session tracking and metrics                                                   |
-| `/api/rate-limits`                            | GET             | Per-account rate limit status                                                         |
 
 ---
 
@@ -484,7 +471,7 @@ All formats translate through **OpenAI format as the hub**. Adding a new provide
 
 ### 5.2 Executor Strategy Pattern
 
-Each provider has a dedicated executor class inheriting from `BaseExecutor`. The factory in `executors/index.ts` selects the right one at runtime.
+Each provider has a dedicated executor class inheriting from `BaseExecutor`. The factory in `executors/index.js` selects the right one at runtime.
 
 ### 5.3 Self-Registering Plugin System
 

docs/FEATURES.md

@@ -1,75 +0,0 @@
-# OmniRoute — Dashboard Features Gallery
-
-Visual guide to every section of the OmniRoute dashboard.
-
----
-
-## 🔌 Providers
-
-Manage AI provider connections: OAuth providers (Claude Code, Codex, Gemini CLI), API key providers (Groq, DeepSeek, OpenRouter), and free providers (iFlow, Qwen, Kiro).
-
-![Providers Dashboard](screenshots/01-providers.png)
-
----
-
-## 🎨 Combos
-
-Create model routing combos with 6 strategies: fill-first, round-robin, power-of-two-choices, random, least-used, and cost-optimized. Each combo chains multiple models with automatic fallback.
-
-![Combos Dashboard](screenshots/02-combos.png)
-
----
-
-## 📊 Analytics
-
-Comprehensive usage analytics with token consumption, cost estimates, activity heatmaps, weekly distribution charts, and per-provider breakdowns.
-
-![Analytics Dashboard](screenshots/03-analytics.png)
-
----
-
-## 🏥 System Health
-
-Real-time monitoring: uptime, memory, version, latency percentiles (p50/p95/p99), cache statistics, and provider circuit breaker states.
-
-![Health Dashboard](screenshots/04-health.png)
-
----
-
-## 🔧 Translator Playground
-
-Four modes for debugging API translations: **Playground** (format converter), **Chat Tester** (live requests), **Test Bench** (batch tests), and **Live Monitor** (real-time stream).
-
-![Translator Playground](screenshots/05-translator.png)
-
----
-
-## ⚙️ 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.
-
-![Settings Dashboard](screenshots/06-settings.png)
-
----
-
-## 🔧 CLI Tools
-
-One-click configuration for AI coding tools: Claude Code, Codex CLI, Gemini CLI, OpenClaw, Kilo Code, and Antigravity.
-
-![CLI Tools Dashboard](screenshots/07-cli-tools.png)
-
----
-
-## 📝 Request Logs
-
-Real-time request logging with filtering by provider, model, account, and API key. Shows status codes, token usage, latency, and response details.
-
-![Usage Logs](screenshots/08-usage.png)
-
----
-
-## 🌐 API Endpoint
-
-Your unified API endpoint with capability breakdown: Chat Completions, Embeddings, Image Generation, Reranking, Audio Transcription, and registered API keys.
-
-![Endpoint Dashboard](screenshots/09-endpoint.png)

docs/TASKS.md

@@ -1,113 +0,0 @@
-# Rate Limiting & Flow Control Overhaul — Tasks
-
-> Referência: [Relatório de Análise](../walkthrough.md) · Fase docs em `/docs/phases/`
-
----
-
-## Fase 1 — Error Classification & Provider Profiles
-
-### Backend Core
-
-- [x] `constants.ts` — Substituir `COOLDOWN_MS.transient` por `transientInitial` (5s) + `transientMax` (60s)
-- [x] `constants.ts` — Adicionar `PROVIDER_PROFILES` (oauth / apikey) com cooldowns diferenciados
-- [x] `constants.ts` — Adicionar `DEFAULT_API_LIMITS` (100 RPM, 200ms minTime)
-- [x] `providerRegistry.ts` — Criar helper `getProviderCategory(providerId)` → `"oauth"` | `"apikey"`
-- [x] `accountFallback.ts` — Aceitar `provider` como parâmetro em `checkFallbackError`
-- [x] `accountFallback.ts` — Implementar backoff exponencial para 502/503/504 transientes
-- [x] `accountFallback.ts` — Calcular cooldown baseado no perfil do provedor
-- [x] `accountFallback.ts` — Adicionar helper `getProviderProfile(provider)`
-
-### Callers (propagar `provider`)
-
-- [x] `auth.ts` → `markAccountUnavailable` — Passar `provider` para `checkFallbackError`
-- [x] `combo.ts` → `handleComboChat` / `handleRoundRobinCombo` — Passar `provider` nos erros
-
-### Testes
-
-- [x] Atualizar `rate-limit-enhanced.test.mjs` — Teste "transient errors don't increase backoff" → `newBackoffLevel = 1`
-- [x] Criar `error-classification.test.mjs` — Cooldown exponencial 502, perfis OAuth/API, helper `getProviderCategory`
-
----
-
-## Fase 2 — Circuit Breaker no Combo Pipeline
-
-### Backend
-
-- [x] `combo.ts` — Importar `getCircuitBreaker` e `CircuitBreakerOpenError`
-- [x] `combo.ts` — `handleComboChat` — Verificar `breaker.canExecute()` antes de cada modelo
-- [x] `combo.ts` — `handleRoundRobinCombo` — Integrar breaker per-model
-- [x] `combo.ts` — Marcar `semaphore.markRateLimited` para 502/503/504 (não só 429)
-- [x] `combo.ts` — Implementar early exit quando todos os modelos têm breaker OPEN
-
-### Testes
-
-- [x] Criar `combo-circuit-breaker.test.mjs` — Combo skip breaker OPEN, early exit, semáforo 502
-
----
-
-## Fase 3 — Anti-Thundering Herd & Auto Rate Limit
-
-### Backend
-
-- [x] `rateLimitManager.ts` — Auto-enable para `apikey` providers com limites elevados
-- [x] `rateLimitManager.ts` — Criar limiter com defaults (100 RPM) quando não configurado
-- [x] `auth.ts` — Adicionar mutex na `markAccountUnavailable` para evitar marcação paralela
-
-### Testes
-
-- [x] Criar `thundering-herd.test.mjs` — Mutex, auto-enable, limites não restritivos
-
----
-
-## Fase 4 — Frontend Resilience UI
-
-### Settings Page
-
-- [x] `settings/page.tsx` — Adicionar tab "Resilience" (icon: `health_and_safety`) entre Routing e Pricing
-
-### Novos Componentes
-
-- [x] Criar `ResilienceTab.tsx` — Layout com 4 cards (Provider Profiles → Rate Limiting → Circuit Breakers → Policies)
-- [x] Criar `ProviderProfilesCard.tsx` — Toggle OAuth/API Key, inputs para cooldowns
-- [x] Criar `CircuitBreakerCard.tsx` — Status real-time per-provider, auto-refresh 5s, botão reset
-- [x] Criar `RateLimitOverviewCard.tsx` — Tabela providers × accounts × cooldown — **agora editável com RPM, Min Gap, Max Concurrent**
-
-### API Routes
-
-- [x] Criar `api/resilience/route.ts` — GET (estado completo + defaults mesclados) + PATCH (salvar perfis + defaults)
-- [x] Criar `api/resilience/reset/route.ts` — POST (resetar breakers + cooldowns)
-
-### Migração
-
-- [x] `PoliciesPanel.tsx` movido de Security para Resilience tab
-
----
-
-## Fase 5 — Settings Page Restructure (v0.9.0)
-
-### Tab Reorganization
-
-- [x] **Security** — Simplificado para Login/Password + IP Access Control
-- [x] **Routing** — Expandido para 6 estratégias globais com descrições
-- [x] **Resilience** — Reordenado: Provider Profiles → Rate Limiting (editável) → Circuit Breakers → Policies
-- [x] **AI** — Thinking Budget + System Prompt + Prompt Cache (movido do Advanced)
-- [x] **Advanced** — Simplificado para apenas Global Proxy
-
-### Backend Routing Strategies
-
-- [x] `auth.ts` — Implementar `random` (Fisher-Yates shuffle)
-- [x] `auth.ts` — Implementar `least-used` (sorted by lastUsedAt)
-- [x] `auth.ts` — Implementar `cost-optimized` (sorted by priority)
-- [x] `auth.ts` — Corrigir `p2c` (power-of-two-choices com health scoring)
-- [x] `settings.ts` — Expandir tipo `fallbackStrategy` para 6 valores
-
----
-
-## Verificação Final
-
-- [x] Rodar todos os testes unitários: `node --test tests/unit/*.test.mjs`
-- [x] Build do Next.js: `npm run build`
-- [x] Verificar aba Resilience no browser
-- [x] Testar persistência dos perfis (salvar → reload)
-- [x] Testar Reset All Breakers
-- [x] Verificar todas as 5 tabs reestruturadas

docs/TROUBLESHOOTING.md

@@ -1,215 +0,0 @@
-# Troubleshooting
-
-Common problems and solutions for OmniRoute.
-
----
-
-## Quick Fixes
-
-| Problem                       | Solution                                                           |
-| ----------------------------- | ------------------------------------------------------------------ |
-| First login not working       | Check `INITIAL_PASSWORD` in `.env` (default: `123456`)             |
-| Dashboard opens on wrong port | Set `PORT=20128` and `NEXT_PUBLIC_BASE_URL=http://localhost:20128` |
-| No request logs under `logs/` | Set `ENABLE_REQUEST_LOGS=true`                                     |
-
----
-
-## Provider Issues
-
-### "Language model did not provide messages"
-
-**Cause:** Provider quota exhausted.
-
-**Fix:**
-
-1. Check dashboard quota tracker
-2. Use a combo with fallback tiers
-3. Switch to cheaper/free tier
-
-### Rate Limiting
-
-**Cause:** Subscription quota exhausted.
-
-**Fix:**
-
-- Add fallback: `cc/claude-opus-4-6 → glm/glm-4.7 → if/kimi-k2-thinking`
-- Use GLM/MiniMax as cheap backup
-
-### OAuth Token Expired
-
-OmniRoute auto-refreshes tokens. If issues persist:
-
-1. Dashboard → Provider → Reconnect
-2. Delete and re-add the provider connection
-
----
-
-## Cloud Issues
-
-### Cloud Sync Errors
-
-1. Verify `BASE_URL` points to your running instance (e.g., `http://localhost:20128`)
-2. Verify `CLOUD_URL` points to your cloud endpoint (e.g., `https://omniroute.dev`)
-3. Keep `NEXT_PUBLIC_*` values aligned with server-side values
-
-### Cloud `stream=false` Returns 500
-
-**Symptom:** `Unexpected token 'd'...` on cloud endpoint for non-streaming calls.
-
-**Cause:** Upstream returns SSE payload while client expects JSON.
-
-**Workaround:** Use `stream=true` for cloud direct calls. Local runtime includes SSE→JSON fallback.
-
-### Cloud Says Connected but "Invalid API key"
-
-1. Create a fresh key from local dashboard (`/api/keys`)
-2. Run cloud sync: Enable Cloud → Sync Now
-3. Old/non-synced keys can still return `401` on cloud
-
----
-
-## Docker Issues
-
-### CLI Tool Shows Not Installed
-
-1. Check runtime fields: `curl http://localhost:20128/api/cli-tools/runtime/codex | jq`
-2. For portable mode: use image target `runner-cli` (bundled CLIs)
-3. For host mount mode: set `CLI_EXTRA_PATHS` and mount host bin directory as read-only
-4. If `installed=true` and `runnable=false`: binary was found but failed healthcheck
-
-### Quick Runtime Validation
-
-```bash
-curl -s http://localhost:20128/api/cli-tools/codex-settings | jq '{installed,runnable,commandPath,runtimeMode,reason}'
-curl -s http://localhost:20128/api/cli-tools/claude-settings | jq '{installed,runnable,commandPath,runtimeMode,reason}'
-curl -s http://localhost:20128/api/cli-tools/openclaw-settings | jq '{installed,runnable,commandPath,runtimeMode,reason}'
-```
-
----
-
-## Cost Issues
-
-### High Costs
-
-1. Check usage stats in Dashboard → Usage
-2. Switch primary model to GLM/MiniMax
-3. Use free tier (Gemini CLI, iFlow) for non-critical tasks
-4. Set cost budgets per API key: Dashboard → API Keys → Budget
-
----
-
-## Debugging
-
-### Enable Request Logs
-
-Set `ENABLE_REQUEST_LOGS=true` in your `.env` file. Logs appear under `logs/` directory.
-
-### Check Provider Health
-
-```bash
-# Health dashboard
-http://localhost:20128/dashboard/health
-
-# API health check
-curl http://localhost:20128/api/monitoring/health
-```
-
-### Runtime Storage
-
-- Main state: `${DATA_DIR}/db.json` (providers, combos, aliases, keys, settings)
-- Usage: `${DATA_DIR}/usage.json`, `${DATA_DIR}/log.txt`, `${DATA_DIR}/call_logs/`
-- Request logs: `<repo>/logs/...` (when `ENABLE_REQUEST_LOGS=true`)
-
----
-
-## Circuit Breaker Issues
-
-### Provider stuck in OPEN state
-
-When a provider's circuit breaker is OPEN, requests are blocked until the cooldown expires.
-
-**Fix:**
-
-1. Go to **Dashboard → Settings → Resilience**
-2. Check the circuit breaker card for the affected provider
-3. Click **Reset All** to clear all breakers, or wait for the cooldown to expire
-4. Verify the provider is actually available before resetting
-
-### Provider keeps tripping the circuit breaker
-
-If a provider repeatedly enters OPEN state:
-
-1. Check **Dashboard → Health → Provider Health** for the failure pattern
-2. Go to **Settings → Resilience → Provider Profiles** and increase the failure threshold
-3. Check if the provider has changed API limits or requires re-authentication
-4. Review latency telemetry — high latency may cause timeout-based failures
-
----
-
-## Audio Transcription Issues
-
-### "Unsupported model" error
-
-- Ensure you're using the correct prefix: `deepgram/nova-3` or `assemblyai/best`
-- Verify the provider is connected in **Dashboard → Providers**
-
-### Transcription returns empty or fails
-
-- Check supported audio formats: `mp3`, `wav`, `m4a`, `flac`, `ogg`, `webm`
-- Verify file size is within provider limits (typically < 25MB)
-- Check provider API key validity in the provider card
-
----
-
-## Translator Debugging
-
-Use **Dashboard → Translator** to debug format translation issues:
-
-| Mode             | When to Use                                                                                  |
-| ---------------- | -------------------------------------------------------------------------------------------- |
-| **Playground**   | Compare input/output formats side by side — paste a failing request to see how it translates |
-| **Chat Tester**  | Send live messages and inspect the full request/response payload including headers           |
-| **Test Bench**   | Run batch tests across format combinations to find which translations are broken             |
-| **Live Monitor** | Watch real-time request flow to catch intermittent translation issues                        |
-
-### Common format issues
-
-- **Thinking tags not appearing** — Check if the target provider supports thinking and the thinking budget setting
-- **Tool calls dropping** — Some format translations may strip unsupported fields; verify in Playground mode
-- **System prompt missing** — Claude and Gemini handle system prompts differently; check translation output
-- **SDK returns raw string instead of object** — Fixed in v1.1.0: response sanitizer now strips non-standard fields (`x_groq`, `usage_breakdown`, etc.) that cause OpenAI SDK Pydantic validation failures
-- **GLM/ERNIE rejects `system` role** — Fixed in v1.1.0: role normalizer automatically merges system messages into user messages for incompatible models
-- **`developer` role not recognized** — Fixed in v1.1.0: automatically converted to `system` for non-OpenAI providers
-- **`json_schema` not working with Gemini** — Fixed in v1.1.0: `response_format` is now converted to Gemini's `responseMimeType` + `responseSchema`
-
----
-
-## Resilience Settings
-
-### Auto rate-limit not triggering
-
-- Auto rate-limit only applies to API key providers (not OAuth/subscription)
-- Verify **Settings → Resilience → Provider Profiles** has auto-rate-limit enabled
-- Check if the provider returns `429` status codes or `Retry-After` headers
-
-### Tuning exponential backoff
-
-Provider profiles support these settings:
-
-- **Base delay** — Initial wait time after first failure (default: 1s)
-- **Max delay** — Maximum wait time cap (default: 30s)
-- **Multiplier** — How much to increase delay per consecutive failure (default: 2x)
-
-### Anti-thundering herd
-
-When many concurrent requests hit a rate-limited provider, OmniRoute uses mutex + auto rate-limiting to serialize requests and prevent cascading failures. This is automatic for API key providers.
-
----
-
-## Still Stuck?
-
-- **GitHub Issues**: [github.com/diegosouzapw/OmniRoute/issues](https://github.com/diegosouzapw/OmniRoute/issues)
-- **Architecture**: See [`docs/ARCHITECTURE.md`](ARCHITECTURE.md) for internal details
-- **API Reference**: See [`docs/API_REFERENCE.md`](API_REFERENCE.md) for all endpoints
-- **Health Dashboard**: Check **Dashboard → Health** for real-time system status
-- **Translator**: Use **Dashboard → Translator** to debug format issues

docs/USER_GUIDE.md

@@ -1,696 +0,0 @@
-# User Guide
-
-Complete guide for configuring providers, creating combos, integrating CLI tools, and deploying OmniRoute.
-
----
-
-## Table of Contents
-
-- [Pricing at a Glance](#-pricing-at-a-glance)
-- [Use Cases](#-use-cases)
-- [Provider Setup](#-provider-setup)
-- [CLI Integration](#-cli-integration)
-- [Deployment](#-deployment)
-- [Available Models](#-available-models)
-- [Advanced Features](#-advanced-features)
-
----
-
-## 💰 Pricing at a Glance
-
-| Tier                | Provider          | Cost        | Quota Reset      | Best For             |
-| ------------------- | ----------------- | ----------- | ---------------- | -------------------- |
-| **💳 SUBSCRIPTION** | Claude Code (Pro) | $20/mo      | 5h + weekly      | Already subscribed   |
-|                     | Codex (Plus/Pro)  | $20-200/mo  | 5h + weekly      | OpenAI users         |
-|                     | Gemini CLI        | **FREE**    | 180K/mo + 1K/day | Everyone!            |
-|                     | GitHub Copilot    | $10-19/mo   | Monthly          | GitHub users         |
-| **🔑 API KEY**      | DeepSeek          | Pay per use | None             | Cheap reasoning      |
-|                     | Groq              | Pay per use | None             | Ultra-fast inference |
-|                     | xAI (Grok)        | Pay per use | None             | Grok 4 reasoning     |
-|                     | Mistral           | Pay per use | None             | EU-hosted models     |
-|                     | Perplexity        | Pay per use | None             | Search-augmented     |
-|                     | Together AI       | Pay per use | None             | Open-source models   |
-|                     | Fireworks AI      | Pay per use | None             | Fast FLUX images     |
-|                     | Cerebras          | Pay per use | None             | Wafer-scale speed    |
-|                     | Cohere            | Pay per use | None             | Command R+ RAG       |
-|                     | NVIDIA NIM        | Pay per use | None             | Enterprise models    |
-| **💰 CHEAP**        | GLM-4.7           | $0.6/1M     | Daily 10AM       | Budget backup        |
-|                     | MiniMax M2.1      | $0.2/1M     | 5-hour rolling   | Cheapest option      |
-|                     | Kimi K2           | $9/mo flat  | 10M tokens/mo    | Predictable cost     |
-| **🆓 FREE**         | iFlow             | $0          | Unlimited        | 8 models free        |
-|                     | Qwen              | $0          | Unlimited        | 3 models free        |
-|                     | Kiro              | $0          | Unlimited        | Claude free          |
-
-**💡 Pro Tip:** Start with Gemini CLI (180K free/month) + iFlow (unlimited free) combo = $0 cost!
-
----
-
-## 🎯 Use Cases
-
-### Case 1: "I have Claude Pro subscription"
-
-**Problem:** Quota expires unused, rate limits during heavy coding
-
-```
-Combo: "maximize-claude"
-  1. cc/claude-opus-4-6        (use subscription fully)
-  2. glm/glm-4.7               (cheap backup when quota out)
-  3. if/kimi-k2-thinking       (free emergency fallback)
-
-Monthly cost: $20 (subscription) + ~$5 (backup) = $25 total
-vs. $20 + hitting limits = frustration
-```
-
-### Case 2: "I want zero cost"
-
-**Problem:** Can't afford subscriptions, need reliable AI coding
-
-```
-Combo: "free-forever"
-  1. gc/gemini-3-flash         (180K free/month)
-  2. if/kimi-k2-thinking       (unlimited free)
-  3. qw/qwen3-coder-plus       (unlimited free)
-
-Monthly cost: $0
-Quality: Production-ready models
-```
-
-### Case 3: "I need 24/7 coding, no interruptions"
-
-**Problem:** Deadlines, can't afford downtime
-
-```
-Combo: "always-on"
-  1. cc/claude-opus-4-6        (best quality)
-  2. cx/gpt-5.2-codex          (second subscription)
-  3. glm/glm-4.7               (cheap, resets daily)
-  4. minimax/MiniMax-M2.1      (cheapest, 5h reset)
-  5. if/kimi-k2-thinking       (free unlimited)
-
-Result: 5 layers of fallback = zero downtime
-Monthly cost: $20-200 (subscriptions) + $10-20 (backup)
-```
-
-### Case 4: "I want FREE AI in OpenClaw"
-
-**Problem:** Need AI assistant in messaging apps, completely free
-
-```
-Combo: "openclaw-free"
-  1. if/glm-4.7                (unlimited free)
-  2. if/minimax-m2.1           (unlimited free)
-  3. if/kimi-k2-thinking       (unlimited free)
-
-Monthly cost: $0
-Access via: WhatsApp, Telegram, Slack, Discord, iMessage, Signal...
-```
-
----
-
-## 📖 Provider Setup
-
-### 🔐 Subscription Providers
-
-#### Claude Code (Pro/Max)
-
-```bash
-Dashboard → Providers → Connect Claude Code
-→ OAuth login → Auto token refresh
-→ 5-hour + weekly quota tracking
-
-Models:
-  cc/claude-opus-4-6
-  cc/claude-sonnet-4-5-20250929
-  cc/claude-haiku-4-5-20251001
-```
-
-**Pro Tip:** Use Opus for complex tasks, Sonnet for speed. OmniRoute tracks quota per model!
-
-#### OpenAI Codex (Plus/Pro)
-
-```bash
-Dashboard → Providers → Connect Codex
-→ OAuth login (port 1455)
-→ 5-hour + weekly reset
-
-Models:
-  cx/gpt-5.2-codex
-  cx/gpt-5.1-codex-max
-```
-
-#### Gemini CLI (FREE 180K/month!)
-
-```bash
-Dashboard → Providers → Connect Gemini CLI
-→ Google OAuth
-→ 180K completions/month + 1K/day
-
-Models:
-  gc/gemini-3-flash-preview
-  gc/gemini-2.5-pro
-```
-
-**Best Value:** Huge free tier! Use this before paid tiers.
-
-#### GitHub Copilot
-
-```bash
-Dashboard → Providers → Connect GitHub
-→ OAuth via GitHub
-→ Monthly reset (1st of month)
-
-Models:
-  gh/gpt-5
-  gh/claude-4.5-sonnet
-  gh/gemini-3-pro
-```
-
-### 💰 Cheap Providers
-
-#### GLM-4.7 (Daily reset, $0.6/1M)
-
-1. Sign up: [Zhipu AI](https://open.bigmodel.cn/)
-2. Get API key from Coding Plan
-3. Dashboard → Add API Key: Provider: `glm`, API Key: `your-key`
-
-**Use:** `glm/glm-4.7` — **Pro Tip:** Coding Plan offers 3× quota at 1/7 cost! Reset daily 10:00 AM.
-
-#### MiniMax M2.1 (5h reset, $0.20/1M)
-
-1. Sign up: [MiniMax](https://www.minimax.io/)
-2. Get API key → Dashboard → Add API Key
-
-**Use:** `minimax/MiniMax-M2.1` — **Pro Tip:** Cheapest option for long context (1M tokens)!
-
-#### Kimi K2 ($9/month flat)
-
-1. Subscribe: [Moonshot AI](https://platform.moonshot.ai/)
-2. Get API key → Dashboard → Add API Key
-
-**Use:** `kimi/kimi-latest` — **Pro Tip:** Fixed $9/month for 10M tokens = $0.90/1M effective cost!
-
-### 🆓 FREE Providers
-
-#### iFlow (8 FREE models)
-
-```bash
-Dashboard → Connect iFlow → OAuth login → Unlimited usage
-
-Models: if/kimi-k2-thinking, if/qwen3-coder-plus, if/glm-4.7, if/minimax-m2, if/deepseek-r1
-```
-
-#### Qwen (3 FREE models)
-
-```bash
-Dashboard → Connect Qwen → Device code auth → Unlimited usage
-
-Models: qw/qwen3-coder-plus, qw/qwen3-coder-flash
-```
-
-#### Kiro (Claude FREE)
-
-```bash
-Dashboard → Connect Kiro → AWS Builder ID or Google/GitHub → Unlimited
-
-Models: kr/claude-sonnet-4.5, kr/claude-haiku-4.5
-```
-
----
-
-## 🎨 Combos
-
-### Example 1: Maximize Subscription → Cheap Backup
-
-```
-Dashboard → Combos → Create New
-
-Name: premium-coding
-Models:
-  1. cc/claude-opus-4-6 (Subscription primary)
-  2. glm/glm-4.7 (Cheap backup, $0.6/1M)
-  3. minimax/MiniMax-M2.1 (Cheapest fallback, $0.20/1M)
-
-Use in CLI: premium-coding
-```
-
-### Example 2: Free-Only (Zero Cost)
-
-```
-Name: free-combo
-Models:
-  1. gc/gemini-3-flash-preview (180K free/month)
-  2. if/kimi-k2-thinking (unlimited)
-  3. qw/qwen3-coder-plus (unlimited)
-
-Cost: $0 forever!
-```
-
----
-
-## 🔧 CLI Integration
-
-### Cursor IDE
-
-```
-Settings → Models → Advanced:
-  OpenAI API Base URL: http://localhost:20128/v1
-  OpenAI API Key: [from omniroute dashboard]
-  Model: cc/claude-opus-4-6
-```
-
-### Claude Code
-
-Edit `~/.claude/config.json`:
-
-```json
-{
-  "anthropic_api_base": "http://localhost:20128/v1",
-  "anthropic_api_key": "your-omniroute-api-key"
-}
-```
-
-### Codex CLI
-
-```bash
-export OPENAI_BASE_URL="http://localhost:20128"
-export OPENAI_API_KEY="your-omniroute-api-key"
-codex "your prompt"
-```
-
-### OpenClaw
-
-Edit `~/.openclaw/openclaw.json`:
-
-```json
-{
-  "agents": {
-    "defaults": {
-      "model": { "primary": "omniroute/if/glm-4.7" }
-    }
-  },
-  "models": {
-    "providers": {
-      "omniroute": {
-        "baseUrl": "http://localhost:20128/v1",
-        "apiKey": "your-omniroute-api-key",
-        "api": "openai-completions",
-        "models": [{ "id": "if/glm-4.7", "name": "glm-4.7" }]
-      }
-    }
-  }
-}
-```
-
-**Or use Dashboard:** CLI Tools → OpenClaw → Auto-config
-
-### Cline / Continue / RooCode
-
-```
-Provider: OpenAI Compatible
-Base URL: http://localhost:20128/v1
-API Key: [from dashboard]
-Model: cc/claude-opus-4-6
-```
-
----
-
-## 🚀 Deployment
-
-### VPS Deployment
-
-```bash
-git clone https://github.com/diegosouzapw/OmniRoute.git
-cd OmniRoute && npm install && npm run build
-
-export JWT_SECRET="your-secure-secret-change-this"
-export INITIAL_PASSWORD="your-password"
-export DATA_DIR="/var/lib/omniroute"
-export PORT="20128"
-export HOSTNAME="0.0.0.0"
-export NODE_ENV="production"
-export NEXT_PUBLIC_BASE_URL="http://localhost:20128"
-export API_KEY_SECRET="endpoint-proxy-api-key-secret"
-
-npm run start
-# Or: pm2 start npm --name omniroute -- start
-```
-
-### Docker
-
-```bash
-# Build image (default = runner-cli with codex/claude/droid preinstalled)
-docker build -t omniroute:cli .
-
-# Portable mode (recommended)
-docker run -d --name omniroute -p 20128:20128 --env-file ./.env -v omniroute-data:/app/data omniroute:cli
-```
-
-For host-integrated mode with CLI binaries, see the Docker section in the main docs.
-
-### Environment Variables
-
-| Variable              | Default                              | Description                                             |
-| --------------------- | ------------------------------------ | ------------------------------------------------------- |
-| `JWT_SECRET`          | `omniroute-default-secret-change-me` | JWT signing secret (**change in production**)           |
-| `INITIAL_PASSWORD`    | `123456`                             | First login password                                    |
-| `DATA_DIR`            | `~/.omniroute`                       | Data directory (db, usage, logs)                        |
-| `PORT`                | framework default                    | Service port (`20128` in examples)                      |
-| `HOSTNAME`            | framework default                    | Bind host (Docker defaults to `0.0.0.0`)                |
-| `NODE_ENV`            | runtime default                      | Set `production` for deploy                             |
-| `BASE_URL`            | `http://localhost:20128`             | Server-side internal base URL                           |
-| `CLOUD_URL`           | `https://omniroute.dev`              | Cloud sync endpoint base URL                            |
-| `API_KEY_SECRET`      | `endpoint-proxy-api-key-secret`      | HMAC secret for generated API keys                      |
-| `REQUIRE_API_KEY`     | `false`                              | Enforce Bearer API key on `/v1/*`                       |
-| `ENABLE_REQUEST_LOGS` | `false`                              | Enables request/response logs                           |
-| `AUTH_COOKIE_SECURE`  | `false`                              | Force `Secure` auth cookie (behind HTTPS reverse proxy) |
-
-For the full environment variable reference, see the [README](../README.md).
-
----
-
-## 📊 Available Models
-
-<details>
-<summary><b>View all available models</b></summary>
-
-**Claude Code (`cc/`)** — Pro/Max: `cc/claude-opus-4-6`, `cc/claude-sonnet-4-5-20250929`, `cc/claude-haiku-4-5-20251001`
-
-**Codex (`cx/`)** — Plus/Pro: `cx/gpt-5.2-codex`, `cx/gpt-5.1-codex-max`
-
-**Gemini CLI (`gc/`)** — FREE: `gc/gemini-3-flash-preview`, `gc/gemini-2.5-pro`
-
-**GitHub Copilot (`gh/`)**: `gh/gpt-5`, `gh/claude-4.5-sonnet`
-
-**GLM (`glm/`)** — $0.6/1M: `glm/glm-4.7`
-
-**MiniMax (`minimax/`)** — $0.2/1M: `minimax/MiniMax-M2.1`
-
-**iFlow (`if/`)** — FREE: `if/kimi-k2-thinking`, `if/qwen3-coder-plus`, `if/deepseek-r1`
-
-**Qwen (`qw/`)** — FREE: `qw/qwen3-coder-plus`, `qw/qwen3-coder-flash`
-
-**Kiro (`kr/`)** — FREE: `kr/claude-sonnet-4.5`, `kr/claude-haiku-4.5`
-
-**DeepSeek (`ds/`)**: `ds/deepseek-chat`, `ds/deepseek-reasoner`
-
-**Groq (`groq/`)**: `groq/llama-3.3-70b-versatile`, `groq/llama-4-maverick-17b-128e-instruct`
-
-**xAI (`xai/`)**: `xai/grok-4`, `xai/grok-4-0709-fast-reasoning`, `xai/grok-code-mini`
-
-**Mistral (`mistral/`)**: `mistral/mistral-large-2501`, `mistral/codestral-2501`
-
-**Perplexity (`pplx/`)**: `pplx/sonar-pro`, `pplx/sonar`
-
-**Together AI (`together/`)**: `together/meta-llama/Llama-3.3-70B-Instruct-Turbo`
-
-**Fireworks AI (`fireworks/`)**: `fireworks/accounts/fireworks/models/deepseek-v3p1`
-
-**Cerebras (`cerebras/`)**: `cerebras/llama-3.3-70b`
-
-**Cohere (`cohere/`)**: `cohere/command-r-plus-08-2024`
-
-**NVIDIA NIM (`nvidia/`)**: `nvidia/nvidia/llama-3.3-70b-instruct`
-
-</details>
-
----
-
-## 🧩 Advanced Features
-
-### Custom Models
-
-Add any model ID to any provider without waiting for an app update:
-
-```bash
-# Via API
-curl -X POST http://localhost:20128/api/provider-models \
-  -H "Content-Type: application/json" \
-  -d '{"provider": "openai", "modelId": "gpt-4.5-preview", "modelName": "GPT-4.5 Preview"}'
-
-# List: curl http://localhost:20128/api/provider-models?provider=openai
-# Remove: curl -X DELETE "http://localhost:20128/api/provider-models?provider=openai&model=gpt-4.5-preview"
-```
-
-Or use Dashboard: **Providers → [Provider] → Custom Models**.
-
-### Dedicated Provider Routes
-
-Route requests directly to a specific provider with model validation:
-
-```bash
-POST http://localhost:20128/v1/providers/openai/chat/completions
-POST http://localhost:20128/v1/providers/openai/embeddings
-POST http://localhost:20128/v1/providers/fireworks/images/generations
-```
-
-The provider prefix is auto-added if missing. Mismatched models return `400`.
-
-### Network Proxy Configuration
-
-```bash
-# Set global proxy
-curl -X PUT http://localhost:20128/api/settings/proxy \
-  -d '{"global": {"type":"http","host":"proxy.example.com","port":"8080"}}'
-
-# Per-provider proxy
-curl -X PUT http://localhost:20128/api/settings/proxy \
-  -d '{"providers": {"openai": {"type":"socks5","host":"proxy.example.com","port":"1080"}}}'
-
-# Test proxy
-curl -X POST http://localhost:20128/api/settings/proxy/test \
-  -d '{"proxy":{"type":"socks5","host":"proxy.example.com","port":"1080"}}'
-```
-
-**Precedence:** Key-specific → Combo-specific → Provider-specific → Global → Environment.
-
-### Model Catalog API
-
-```bash
-curl http://localhost:20128/api/models/catalog
-```
-
-Returns models grouped by provider with types (`chat`, `embedding`, `image`).
-
-### Cloud Sync
-
-- Sync providers, combos, and settings across devices
-- Automatic background sync with timeout + fail-fast
-- Prefer server-side `BASE_URL`/`CLOUD_URL` in production
-
-### LLM Gateway Intelligence (Phase 9)
-
-- **Semantic Cache** — Auto-caches non-streaming, temperature=0 responses (bypass with `X-OmniRoute-No-Cache: true`)
-- **Request Idempotency** — Deduplicates requests within 5s via `Idempotency-Key` or `X-Request-Id` header
-- **Progress Tracking** — Opt-in SSE `event: progress` events via `X-OmniRoute-Progress: true` header
-
----
-
-### Translator Playground
-
-Access via **Dashboard → Translator**. Debug and visualize how OmniRoute translates API requests between providers.
-
-| Mode             | Purpose                                                                                |
-| ---------------- | -------------------------------------------------------------------------------------- |
-| **Playground**   | Select source/target formats, paste a request, and see the translated output instantly |
-| **Chat Tester**  | Send live chat messages through the proxy and inspect the full request/response cycle  |
-| **Test Bench**   | Run batch tests across multiple format combinations to verify translation correctness  |
-| **Live Monitor** | Watch real-time translations as requests flow through the proxy                        |
-
-**Use cases:**
-
-- Debug why a specific client/provider combination fails
-- Verify that thinking tags, tool calls, and system prompts translate correctly
-- Compare format differences between OpenAI, Claude, Gemini, and Responses API formats
-
----
-
-### Routing Strategies
-
-Configure via **Dashboard → Settings → Routing**.
-
-| Strategy                       | Description                                                                                      |
-| ------------------------------ | ------------------------------------------------------------------------------------------------ |
-| **Fill First**                 | Uses accounts in priority order — primary account handles all requests until unavailable         |
-| **Round Robin**                | Cycles through all accounts with a configurable sticky limit (default: 3 calls per account)      |
-| **P2C (Power of Two Choices)** | Picks 2 random accounts and routes to the healthier one — balances load with awareness of health |
-| **Random**                     | Randomly selects an account for each request using Fisher-Yates shuffle                          |
-| **Least Used**                 | Routes to the account with the oldest `lastUsedAt` timestamp, distributing traffic evenly        |
-| **Cost Optimized**             | Routes to the account with the lowest priority value, optimizing for lowest-cost providers       |
-
-#### Wildcard Model Aliases
-
-Create wildcard patterns to remap model names:
-
-```
-Pattern: claude-sonnet-*     →  Target: cc/claude-sonnet-4-5-20250929
-Pattern: gpt-*               →  Target: gh/gpt-5.1-codex
-```
-
-Wildcards support `*` (any characters) and `?` (single character).
-
-#### Fallback Chains
-
-Define global fallback chains that apply across all requests:
-
-```
-Chain: production-fallback
-  1. cc/claude-opus-4-6
-  2. gh/gpt-5.1-codex
-  3. glm/glm-4.7
-```
-
----
-
-### Resilience & Circuit Breakers
-
-Configure via **Dashboard → Settings → Resilience**.
-
-OmniRoute implements provider-level resilience with four components:
-
-1. **Provider Profiles** — Per-provider configuration for:
-   - Failure threshold (how many failures before opening)
-   - Cooldown duration
-   - Rate limit detection sensitivity
-   - Exponential backoff parameters
-
-2. **Editable Rate Limits** — System-level defaults configurable in the dashboard:
-   - **Requests Per Minute (RPM)** — Maximum requests per minute per account
-   - **Min Time Between Requests** — Minimum gap in milliseconds between requests
-   - **Max Concurrent Requests** — Maximum simultaneous requests per account
-   - Click **Edit** to modify, then **Save** or **Cancel**. Values persist via the resilience API.
-
-3. **Circuit Breaker** — Tracks failures per provider and automatically opens the circuit when a threshold is reached:
-   - **CLOSED** (Healthy) — Requests flow normally
-   - **OPEN** — Provider is temporarily blocked after repeated failures
-   - **HALF_OPEN** — Testing if provider has recovered
-
-4. **Policies & Locked Identifiers** — Shows circuit breaker status and locked identifiers with force-unlock capability.
-
-5. **Rate Limit Auto-Detection** — Monitors `429` and `Retry-After` headers to proactively avoid hitting provider rate limits.
-
-**Pro Tip:** Use **Reset All** button to clear all circuit breakers and cooldowns when a provider recovers from an outage.
-
----
-
-### Database Export / Import
-
-Manage database backups in **Dashboard → Settings → System & Storage**.
-
-| Action                   | Description                                                                                                                    |
-| ------------------------ | ------------------------------------------------------------------------------------------------------------------------------ |
-| **Export Database**      | Downloads the current SQLite database as a `.sqlite` file                                                                      |
-| **Export All (.tar.gz)** | Downloads a full backup archive including: database, settings, combos, provider connections (no credentials), API key metadata |
-| **Import Database**      | Upload a `.sqlite` file to replace the current database. A pre-import backup is automatically created                          |
-
-```bash
-# API: Export database
-curl -o backup.sqlite http://localhost:20128/api/db-backups/export
-
-# API: Export all (full archive)
-curl -o backup.tar.gz http://localhost:20128/api/db-backups/exportAll
-
-# API: Import database
-curl -X POST http://localhost:20128/api/db-backups/import \
-  -F "file=@backup.sqlite"
-```
-
-**Import Validation:** The imported file is validated for integrity (SQLite pragma check), required tables (`provider_connections`, `provider_nodes`, `combos`, `api_keys`), and size (max 100MB).
-
-**Use Cases:**
-
-- Migrate OmniRoute between machines
-- Create external backups for disaster recovery
-- Share configurations between team members (export all → share archive)
-
----
-
-### Settings Dashboard
-
-The settings page is organized into 5 tabs for easy navigation:
-
-| Tab            | Contents                                                                                       |
-| -------------- | ---------------------------------------------------------------------------------------------- |
-| **Security**   | Login/Password settings, IP Access Control, API auth for `/models`, and Provider Blocking      |
-| **Routing**    | Global routing strategy (6 options), wildcard model aliases, fallback chains, combo defaults   |
-| **Resilience** | Provider profiles, editable rate limits, circuit breaker status, policies & locked identifiers |
-| **AI**         | Thinking budget configuration, global system prompt injection, prompt cache stats              |
-| **Advanced**   | Global proxy configuration (HTTP/SOCKS5)                                                       |
-
----
-
-### Costs & Budget Management
-
-Access via **Dashboard → Costs**.
-
-| Tab         | Purpose                                                                                  |
-| ----------- | ---------------------------------------------------------------------------------------- |
-| **Budget**  | Set spending limits per API key with daily/weekly/monthly budgets and real-time tracking |
-| **Pricing** | View and edit model pricing entries — cost per 1K input/output tokens per provider       |
-
-```bash
-# API: Set a budget
-curl -X POST http://localhost:20128/api/usage/budget \
-  -H "Content-Type: application/json" \
-  -d '{"keyId": "key-123", "limit": 50.00, "period": "monthly"}'
-
-# API: Get current budget status
-curl http://localhost:20128/api/usage/budget
-```
-
-**Cost Tracking:** Every request logs token usage and calculates cost using the pricing table. View breakdowns in **Dashboard → Usage** by provider, model, and API key.
-
----
-
-### Audio Transcription
-
-OmniRoute supports audio transcription via the OpenAI-compatible endpoint:
-
-```bash
-POST /v1/audio/transcriptions
-Authorization: Bearer your-api-key
-Content-Type: multipart/form-data
-
-# Example with curl
-curl -X POST http://localhost:20128/v1/audio/transcriptions \
-  -H "Authorization: Bearer your-api-key" \
-  -F "file=@audio.mp3" \
-  -F "model=deepgram/nova-3"
-```
-
-Available providers: **Deepgram** (`deepgram/`), **AssemblyAI** (`assemblyai/`).
-
-Supported audio formats: `mp3`, `wav`, `m4a`, `flac`, `ogg`, `webm`.
-
----
-
-### Combo Balancing Strategies
-
-Configure per-combo balancing in **Dashboard → Combos → Create/Edit → Strategy**.
-
-| Strategy           | Description                                                              |
-| ------------------ | ------------------------------------------------------------------------ |
-| **Round-Robin**    | Rotates through models sequentially                                      |
-| **Priority**       | Always tries the first model; falls back only on error                   |
-| **Random**         | Picks a random model from the combo for each request                     |
-| **Weighted**       | Routes proportionally based on assigned weights per model                |
-| **Least-Used**     | Routes to the model with the fewest recent requests (uses combo metrics) |
-| **Cost-Optimized** | Routes to the cheapest available model (uses pricing table)              |
-
-Global combo defaults can be set in **Dashboard → Settings → Routing → Combo Defaults**.
-
----
-
-### Health Dashboard
-
-Access via **Dashboard → Health**. Real-time system health overview with 6 cards:
-
-| Card                  | What It Shows                                               |
-| --------------------- | ----------------------------------------------------------- |
-| **System Status**     | Uptime, version, memory usage, data directory               |
-| **Provider Health**   | Per-provider circuit breaker state (Closed/Open/Half-Open)  |
-| **Rate Limits**       | Active rate limit cooldowns per account with remaining time |
-| **Active Lockouts**   | Providers temporarily blocked by the lockout policy         |
-| **Signature Cache**   | Deduplication cache stats (active keys, hit rate)           |
-| **Latency Telemetry** | p50/p95/p99 latency aggregation per provider                |
-
-**Pro Tip:** The Health page auto-refreshes every 10 seconds. Use the circuit breaker card to identify which providers are experiencing issues.

docs/VM_DEPLOYMENT_GUIDE.md

@@ -1,399 +0,0 @@
-# OmniRoute — Guia de Deploy em VM com Cloudflare
-
-Guia completo para instalar e configurar o OmniRoute em uma VM (VPS) com domínio gerenciado via Cloudflare.
-
----
-
-## Pré-Requisitos
-
-| Item        | Mínimo                   | Recomendado      |
-| ----------- | ------------------------ | ---------------- |
-| **CPU**     | 1 vCPU                   | 2 vCPU           |
-| **RAM**     | 1 GB                     | 2 GB             |
-| **Disco**   | 10 GB SSD                | 25 GB SSD        |
-| **SO**      | Ubuntu 22.04 LTS         | Ubuntu 24.04 LTS |
-| **Domínio** | Registrado no Cloudflare | —                |
-| **Docker**  | Docker Engine 24+        | Docker 27+       |
-
-**Providers testados**: Akamai (Linode), DigitalOcean, Vultr, Hetzner, AWS Lightsail.
-
----
-
-## 1. Configurar a VM
-
-### 1.1 Criar a instância
-
-No seu provider de VPS preferido:
-
-- Escolha Ubuntu 24.04 LTS
-- Selecione o plano mínimo (1 vCPU / 1 GB RAM)
-- Defina uma senha forte para root ou configure SSH key
-- Anote o **IP público** (ex: `203.0.113.10`)
-
-### 1.2 Conectar via SSH
-
-```bash
-ssh root@203.0.113.10
-```
-
-### 1.3 Atualizar o sistema
-
-```bash
-apt update && apt upgrade -y
-```
-
-### 1.4 Instalar Docker
-
-```bash
-# Instalar dependências
-apt install -y ca-certificates curl gnupg
-
-# Adicionar repositório oficial do Docker
-install -m 0755 -d /etc/apt/keyrings
-curl -fsSL https://download.docker.com/linux/ubuntu/gpg | gpg --dearmor -o /etc/apt/keyrings/docker.gpg
-chmod a+r /etc/apt/keyrings/docker.gpg
-echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.gpg] https://download.docker.com/linux/ubuntu $(. /etc/os-release && echo "$VERSION_CODENAME") stable" | tee /etc/apt/sources.list.d/docker.list > /dev/null
-apt update
-apt install -y docker-ce docker-ce-cli containerd.io docker-compose-plugin
-```
-
-### 1.5 Instalar nginx
-
-```bash
-apt install -y nginx
-```
-
-### 1.6 Configurar Firewall (UFW)
-
-```bash
-ufw default deny incoming
-ufw default allow outgoing
-ufw allow 22/tcp    # SSH
-ufw allow 80/tcp    # HTTP (redirect)
-ufw allow 443/tcp   # HTTPS
-ufw enable
-```
-
-> **Dica**: Para segurança máxima, restrinja as portas 80 e 443 apenas para IPs da Cloudflare. Veja a seção [Segurança Avançada](#segurança-avançada).
-
----
-
-## 2. Instalar o OmniRoute
-
-### 2.1 Criar diretório de configuração
-
-```bash
-mkdir -p /opt/omniroute
-```
-
-### 2.2 Criar arquivo de variáveis de ambiente
-
-```bash
-cat > /opt/omniroute/.env << 'EOF'
-# === Segurança ===
-JWT_SECRET=ALTERE-PARA-CHAVE-SECRETA-UNICA-64-CHARS
-INITIAL_PASSWORD=SuaSenhaSegura123!
-API_KEY_SECRET=ALTERE-PARA-OUTRA-CHAVE-SECRETA
-STORAGE_ENCRYPTION_KEY=ALTERE-PARA-TERCEIRA-CHAVE-SECRETA
-STORAGE_ENCRYPTION_KEY_VERSION=v1
-MACHINE_ID_SALT=ALTERE-PARA-SALT-UNICO
-
-# === App ===
-PORT=20128
-NODE_ENV=production
-HOSTNAME=0.0.0.0
-DATA_DIR=/app/data
-STORAGE_DRIVER=sqlite
-ENABLE_REQUEST_LOGS=true
-AUTH_COOKIE_SECURE=false
-REQUIRE_API_KEY=false
-
-# === Domain (altere para seu domínio) ===
-BASE_URL=https://llms.seudominio.com
-NEXT_PUBLIC_BASE_URL=https://llms.seudominio.com
-
-# === Cloud Sync (opcional) ===
-# CLOUD_URL=https://cloud.omniroute.online
-# NEXT_PUBLIC_CLOUD_URL=https://cloud.omniroute.online
-EOF
-```
-
-> ⚠️ **IMPORTANTE**: Gere chaves secretas únicas! Use `openssl rand -hex 32` para cada chave.
-
-### 2.3 Iniciar o container
-
-```bash
-docker pull diegosouzapw/omniroute:latest
-
-docker run -d \
-  --name omniroute \
-  --restart unless-stopped \
-  --env-file /opt/omniroute/.env \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-### 2.4 Verificar se está rodando
-
-```bash
-docker ps | grep omniroute
-docker logs omniroute --tail 20
-```
-
-Deve exibir: `[DB] SQLite database ready` e `listening on port 20128`.
-
----
-
-## 3. Configurar nginx (Reverse Proxy)
-
-### 3.1 Gerar certificado SSL (Cloudflare Origin)
-
-No painel da Cloudflare:
-
-1. Vá em **SSL/TLS → Origin Server**
-2. Clique **Create Certificate**
-3. Deixe os padrões (15 anos, \*.seudominio.com)
-4. Copie o **Origin Certificate** e a **Private Key**
-
-```bash
-mkdir -p /etc/nginx/ssl
-
-# Colar o certificado
-nano /etc/nginx/ssl/origin.crt
-
-# Colar a chave privada
-nano /etc/nginx/ssl/origin.key
-
-chmod 600 /etc/nginx/ssl/origin.key
-```
-
-### 3.2 Configuração do nginx
-
-```bash
-cat > /etc/nginx/sites-available/omniroute << 'NGINX'
-# Default server — bloqueia acesso direto por IP
-server {
-    listen 80 default_server;
-    listen [::]:80 default_server;
-    listen 443 ssl default_server;
-    listen [::]:443 ssl default_server;
-    ssl_certificate     /etc/nginx/ssl/origin.crt;
-    ssl_certificate_key /etc/nginx/ssl/origin.key;
-    server_name _;
-    return 444;
-}
-
-# OmniRoute — HTTPS
-server {
-    listen 443 ssl;
-    listen [::]:443 ssl;
-    server_name llms.seudominio.com;  # Altere para seu domínio
-
-    ssl_certificate     /etc/nginx/ssl/origin.crt;
-    ssl_certificate_key /etc/nginx/ssl/origin.key;
-    ssl_protocols TLSv1.2 TLSv1.3;
-
-    client_max_body_size 100M;
-
-    location / {
-        proxy_pass http://127.0.0.1:20128;
-        proxy_set_header Host $host;
-        proxy_set_header X-Real-IP $remote_addr;
-        proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
-        proxy_set_header X-Forwarded-Proto $scheme;
-
-        # WebSocket support
-        proxy_http_version 1.1;
-        proxy_set_header Upgrade $http_upgrade;
-        proxy_set_header Connection "upgrade";
-
-        # SSE (Server-Sent Events) — streaming AI responses
-        proxy_buffering off;
-        proxy_cache off;
-        proxy_read_timeout 300s;
-        proxy_send_timeout 300s;
-    }
-}
-
-# HTTP → HTTPS redirect
-server {
-    listen 80;
-    listen [::]:80;
-    server_name llms.seudominio.com;
-    return 301 https://$server_name$request_uri;
-}
-NGINX
-```
-
-### 3.3 Ativar e testar
-
-```bash
-# Remover config padrão
-rm -f /etc/nginx/sites-enabled/default
-
-# Ativar OmniRoute
-ln -sf /etc/nginx/sites-available/omniroute /etc/nginx/sites-enabled/omniroute
-
-# Testar e recarregar
-nginx -t && systemctl reload nginx
-```
-
----
-
-## 4. Configurar Cloudflare DNS
-
-### 4.1 Adicionar registro DNS
-
-No painel da Cloudflare → DNS:
-
-| Type | Name   | Content                   | Proxy      |
-| ---- | ------ | ------------------------- | ---------- |
-| A    | `llms` | `203.0.113.10` (IP da VM) | ✅ Proxied |
-
-### 4.2 Configurar SSL
-
-Em **SSL/TLS → Overview**:
-
-- Modo: **Full (Strict)**
-
-Em **SSL/TLS → Edge Certificates**:
-
-- Always Use HTTPS: ✅ On
-- Minimum TLS Version: TLS 1.2
-- Automatic HTTPS Rewrites: ✅ On
-
-### 4.3 Testar
-
-```bash
-curl -sI https://llms.seudominio.com/health
-# Deve retornar HTTP/2 200
-```
-
----
-
-## 5. Operações e Manutenção
-
-### Atualizar para nova versão
-
-```bash
-docker pull diegosouzapw/omniroute:latest
-docker stop omniroute && docker rm omniroute
-docker run -d --name omniroute --restart unless-stopped \
-  --env-file /opt/omniroute/.env \
-  -p 20128:20128 \
-  -v omniroute-data:/app/data \
-  diegosouzapw/omniroute:latest
-```
-
-### Ver logs
-
-```bash
-docker logs -f omniroute          # Stream em tempo real
-docker logs omniroute --tail 50   # Últimas 50 linhas
-```
-
-### Backup manual do banco
-
-```bash
-# Copiar dados do volume para o host
-docker cp omniroute:/app/data ./backup-$(date +%F)
-
-# Ou comprimir todo o volume
-docker run --rm -v omniroute-data:/data -v $(pwd):/backup \
-  alpine tar czf /backup/omniroute-data-$(date +%F).tar.gz /data
-```
-
-### Restaurar de backup
-
-```bash
-docker stop omniroute
-docker run --rm -v omniroute-data:/data -v $(pwd):/backup \
-  alpine sh -c "rm -rf /data/* && tar xzf /backup/omniroute-data-YYYY-MM-DD.tar.gz -C /"
-docker start omniroute
-```
-
----
-
-## 6. Segurança Avançada
-
-### Restringir nginx para Cloudflare IPs
-
-```bash
-cat > /etc/nginx/cloudflare-ips.conf << 'CF'
-# Cloudflare IPv4 ranges — atualizar periodicamente
-# https://www.cloudflare.com/ips-v4/
-set_real_ip_from 173.245.48.0/20;
-set_real_ip_from 103.21.244.0/22;
-set_real_ip_from 103.22.200.0/22;
-set_real_ip_from 103.31.4.0/22;
-set_real_ip_from 141.101.64.0/18;
-set_real_ip_from 108.162.192.0/18;
-set_real_ip_from 190.93.240.0/20;
-set_real_ip_from 188.114.96.0/20;
-set_real_ip_from 197.234.240.0/22;
-set_real_ip_from 198.41.128.0/17;
-set_real_ip_from 162.158.0.0/15;
-set_real_ip_from 104.16.0.0/13;
-set_real_ip_from 104.24.0.0/14;
-set_real_ip_from 172.64.0.0/13;
-set_real_ip_from 131.0.72.0/22;
-real_ip_header CF-Connecting-IP;
-CF
-```
-
-Adicionar no `nginx.conf` dentro do bloco `http {}`:
-
-```nginx
-include /etc/nginx/cloudflare-ips.conf;
-```
-
-### Install fail2ban
-
-```bash
-apt install -y fail2ban
-systemctl enable fail2ban
-systemctl start fail2ban
-
-# Verificar status
-fail2ban-client status sshd
-```
-
-### Bloquear acesso direto na porta do Docker
-
-```bash
-# Impedir acesso externo direto à porta 20128
-iptables -I DOCKER-USER -p tcp --dport 20128 -j DROP
-iptables -I DOCKER-USER -i lo -p tcp --dport 20128 -j ACCEPT
-
-# Persistir as regras
-apt install -y iptables-persistent
-netfilter-persistent save
-```
-
----
-
-## 7. Deploy do Cloud Worker (Opcional)
-
-Para acesso remoto via Cloudflare Workers (sem expor a VM diretamente):
-
-```bash
-# No repositório local
-cd omnirouteCloud
-npm install
-npx wrangler login
-npx wrangler deploy
-```
-
-Ver documentação completa em [omnirouteCloud/README.md](../omnirouteCloud/README.md).
-
----
-
-## Resumo de Portas
-
-| Porta | Serviço     | Acesso                        |
-| ----- | ----------- | ----------------------------- |
-| 22    | SSH         | Público (com fail2ban)        |
-| 80    | nginx HTTP  | Redirect → HTTPS              |
-| 443   | nginx HTTPS | Via Cloudflare Proxy          |
-| 20128 | OmniRoute   | Somente localhost (via nginx) |

docs/adr/ADR-001-nextjs-foundation.md

@@ -1,37 +0,0 @@
-# ADR-001: Next.js as the Foundation for an AI Gateway
-
-## Status: Accepted
-
-## Context
-
-OmniRoute is an AI routing gateway that translates, forwards, and manages requests across 20+ LLM providers. We needed a framework that could serve both the API proxy layer and a management dashboard from a single codebase.
-
-**Alternatives considered:**
-
-- **Express.js only** — Simpler proxy, but requires separate frontend tooling
-- **Fastify** — Fast, but no built-in SSR/dashboard support
-- **Next.js** — Unified full-stack framework with API routes, SSR, and static pages
-
-## Decision
-
-We chose Next.js because:
-
-1. **Single deployment** — API routes (`/api/*`) and dashboard UI in one process
-2. **Middleware layer** — Native request interception for auth guards and request tracing
-3. **File-based routing** — Easy to map provider endpoints to handlers
-4. **Built-in TypeScript** — Type safety across the entire codebase
-
-## Consequences
-
-**Positive:**
-
-- One `npm run build` produces both API and UI
-- Middleware provides centralized auth and request tracing
-- Dashboard gets automatic code splitting and optimization
-
-**Negative:**
-
-- Next.js middleware has limitations (no heavy imports, edge runtime constraints)
-- Serverless deployment model doesn't align with persistent WebSocket/SSE connections
-- Build times are longer than Express-only setups
-- The SSE proxy layer (`open-sse/`) operates outside Next.js conventions

docs/adr/ADR-002-hub-spoke-translation.md

@@ -1,37 +0,0 @@
-# ADR-002: Hub-and-Spoke Translation with OpenAI as Intermediate Format
-
-## Status: Accepted
-
-## Context
-
-OmniRoute routes requests across 20+ providers, each with its own API format (OpenAI, Anthropic Messages, Google Gemini, AWS Bedrock, etc.). Direct provider-to-provider translation would require O(n²) translators.
-
-**Alternatives considered:**
-
-- **Direct translation** — Each pair needs a dedicated translator (n² complexity)
-- **Common intermediate format** — Translate to/from a canonical format (2n complexity)
-- **Protocol buffers** — Strong typing but heavy overhead for a proxy
-
-## Decision
-
-We use the **OpenAI Chat Completions format** as the canonical intermediate representation. All incoming requests are normalized to OpenAI format, processed, then translated to the target provider's format.
-
-```
-Client → [any format] → OpenAI canonical → [target format] → Provider
-Provider → [response] → OpenAI canonical → [original format] → Client
-```
-
-## Consequences
-
-**Positive:**
-
-- Only 2 translators per provider (inbound + outbound) instead of n² pairs
-- OpenAI format is the de facto standard — most clients already use it
-- Adding a new provider requires only implementing one translator pair
-- Streaming (SSE) works consistently through the canonical format
-
-**Negative:**
-
-- Some provider-specific features may be lost in translation
-- The double translation adds latency (typically < 5ms)
-- OpenAI format changes require updating the canonical representation

docs/adr/ADR-003-dual-storage-sqlite.md

@@ -1,39 +0,0 @@
-# ADR-003: Dual Storage — SQLite Primary with JSON Migration Path
-
-## Status: Accepted
-
-## Context
-
-OmniRoute originally used LowDB (JSON file) for all persistence. As the project grew, JSON-based storage became a bottleneck for concurrent access, querying, and data integrity.
-
-**Alternatives considered:**
-
-- **LowDB only** — Simple but no concurrent access, no ACID, no querying
-- **SQLite only** — Fast, ACID-compliant, but breaks existing deployments
-- **PostgreSQL** — Production-grade but requires external dependency
-- **Dual storage with migration** — SQLite primary + automatic JSON migration
-
-## Decision
-
-We migrated to **SQLite as the primary store** with an automatic one-time migration from `db.json`:
-
-1. On startup, if `db.json` exists and SQLite is empty, auto-migrate all data
-2. All new reads/writes go through SQLite
-3. The `db.json` file is preserved but no longer written to
-
-Settings remain in a hybrid model where LowDB handles simple key-value configuration for backward compatibility.
-
-## Consequences
-
-**Positive:**
-
-- ACID transactions for provider connections, API keys, and usage data
-- Proper SQL queries for analytics and log filtering
-- Concurrent read/write safety via WAL mode
-- Zero-downtime migration from JSON — users upgrade transparently
-
-**Negative:**
-
-- Two storage engines to maintain (SQLite + LowDB for settings)
-- Migration code must handle edge cases and partial data
-- SQLite binary dependency needed in deployment environments

eslint.config.mjs

@@ -1,41 +1,16 @@
+import { defineConfig, globalIgnores } from "eslint/config";
 import nextVitals from "eslint-config-next/core-web-vitals";
-import tseslint from "typescript-eslint";
 
-/** @type {import("eslint").Linter.Config[]} */
-const eslintConfig = [
+const eslintConfig = defineConfig([
   ...nextVitals,
-  // FASE-02: Security rules (strict everywhere)
-  {
-    rules: {
-      "no-eval": "error",
-      "no-implied-eval": "error",
-      "no-new-func": "error",
-    },
-  },
-  // Relaxed rules for open-sse and tests (incremental adoption)
-  {
-    files: ["open-sse/**/*.ts", "tests/**/*.mjs", "tests/**/*.ts"],
-    plugins: {
-      "@typescript-eslint": tseslint.plugin,
-    },
-    rules: {
-      "@typescript-eslint/no-explicit-any": "warn",
-      "@next/next/no-assign-module-variable": "off",
-      "react-hooks/rules-of-hooks": "off",
-    },
-  },
-  // Global ignores (open-sse and tests REMOVED — now linted)
-  {
-    ignores: [
-      ".next/**",
-      "out/**",
-      "build/**",
-      "next-env.d.ts",
-      "scripts/**",
-      "bin/**",
-      "node_modules/**",
-    ],
-  },
-];
+  // Override default ignores of eslint-config-next.
+  globalIgnores([
+    // Default ignores of eslint-config-next:
+    ".next/**",
+    "out/**",
+    "build/**",
+    "next-env.d.ts",
+  ]),
+]);
 
 export default eslintConfig;

llm.txt

@@ -1,134 +0,0 @@
-# OmniRoute
-
-> OmniRoute is a free, open-source AI Gateway that acts as a universal API proxy for multi-provider LLMs. It provides smart routing, automatic fallback, load balancing, and format translation across 36+ AI providers — all through a single OpenAI-compatible endpoint.
-
-## Overview
-
-OmniRoute solves the problem of managing multiple AI provider subscriptions, quotas, and rate limits. It sits between your AI-powered tools (IDE agents, CLI tools) and AI providers, routing requests intelligently through a 4-tier fallback system: Subscription → API Key → Cheap → Free.
-
-**Key value:** One endpoint (`http://localhost:20128/v1`), unlimited models, zero downtime, minimal cost.
-
-## Tech Stack
-
-- **Runtime:** Node.js >= 18
-- **Framework:** Next.js 16 (App Router) with TypeScript
-- **Database:** SQLite via better-sqlite3 (local, zero-config)
-- **State management:** Zustand (client), lowdb (server JSON persistence)
-- **UI:** React 19, Tailwind CSS 4, Recharts for analytics
-- **Auth:** OAuth 2.0 (PKCE) for providers, bcrypt for local user auth
-- **Background jobs:** Custom token health check scheduler
-- **Streaming:** Server-Sent Events (SSE) for real-time proxy responses
-- **Proxy engine:** Custom pipeline with format translation, circuit breaker, rate limiting
-- **Package:** Published on npm (`omniroute`) and Docker Hub (`diegosouzapw/omniroute`)
-
-## Project Structure
-
-```
-/
-├── src/                          # Main application source
-│   ├── app/                      # Next.js App Router pages and API routes
-│   │   ├── (dashboard)/          # Dashboard UI pages (providers, combos, analytics, logs, etc.)
-│   │   ├── api/                  # REST API endpoints
-│   │   │   ├── v1/               # OpenAI-compatible API (chat, models, embeddings, images, audio)
-│   │   │   ├── oauth/            # OAuth flows per provider (authorize, exchange, callback)
-│   │   │   ├── providers/        # Provider CRUD and batch testing
-│   │   │   ├── models/           # Dashboard model listing and aliases
-│   │   │   ├── combos/           # Combo CRUD (multi-model fallback chains)
-│   │   │   └── ...               # Other endpoints (usage, logs, health, settings, etc.)
-│   │   └── login/                # Login page
-│   ├── domain/                   # Domain types and business logic interfaces
-│   ├── lib/                      # Core libraries
-│   │   ├── db/                   # SQLite database layer (providers, combos, prompts, logs)
-│   │   ├── oauth/                # OAuth providers, services, and utilities
-│   │   │   ├── providers/        # Provider-specific OAuth configs (GitHub, Google, Claude, etc.)
-│   │   │   ├── services/         # Provider-specific token exchange logic
-│   │   │   └── utils/            # PKCE, callback server, token helpers
-│   │   ├── cloudSync.ts          # Cloud sync via Cloudflare Workers
-│   │   ├── tokenHealthCheck.ts   # Background OAuth token refresh scheduler
-│   │   └── localDb.ts            # Unified database access layer
-│   ├── shared/                   # Shared utilities, components, and constants
-│   │   ├── components/           # Reusable UI components (Card, Badge, Button, Modal, etc.)
-│   │   ├── constants/            # Provider definitions, model lists, pricing
-│   │   └── utils/                # Helpers (auth, CORS, error codes, machine ID)
-│   ├── sse/                      # SSE proxy pipeline
-│   │   ├── services/             # Auth resolution, format translation, response handling
-│   │   └── middleware/           # Rate limiting, circuit breaker, caching, idempotency
-│   ├── store/                    # Zustand client-side stores
-│   ├── types/                    # TypeScript type definitions
-│   ├── proxy.ts                  # Main proxy request handler
-│   └── server-init.ts            # Server initialization (DB, health checks)
-├── open-sse/                     # Standalone SSE server (npm workspace)
-│   ├── config/                   # Model registries (embedding, image, audio, rerank, moderation)
-│   ├── handlers/                 # Request handlers per API type
-│   └── translators/              # Format translators (OpenAI ↔ Claude ↔ Gemini ↔ Responses)
-├── tests/                        # Test suites
-│   ├── unit/                     # Unit tests (32+ test files)
-│   └── integration/              # Integration tests
-├── docs/                         # Documentation and screenshots
-├── bin/                          # CLI entry points (omniroute, reset-password)
-└── .env.example                  # Environment variable template
-```
-
-## Key Architectural Decisions
-
-1. **OpenAI-compatible API surface:** All incoming requests follow the OpenAI API format (`/v1/chat/completions`, `/v1/models`, etc.). This makes OmniRoute a drop-in replacement for any tool that supports custom OpenAI endpoints.
-
-2. **Provider abstraction via format translators:** Each AI provider (Claude, Gemini, etc.) has a translator in `open-sse/translators/` that converts between the OpenAI format and the provider's native format. This happens transparently.
-
-3. **Connection-based provider model:** Providers are stored as "connections" in SQLite. Each connection has an `id`, `provider`, `authType` (oauth/apikey/free), `isActive` flag, and credentials. Multiple connections per provider are supported for multi-account rotation.
-
-4. **Combo system for fallback:** Users create "combos" — ordered lists of `provider/model` pairs. The proxy tries each in order until one succeeds. Supports 6 strategies: fill-first, round-robin, power-of-two-choices, random, least-used, cost-optimized.
-
-5. **SSE proxy pipeline (`src/sse/`):** The proxy pipeline is middleware-based: request → auth resolution → rate limiting → circuit breaker → format translation → upstream call → response translation → SSE streaming back to client.
-
-6. **SQLite for persistence:** All state (providers, combos, logs, settings) is stored in a single SQLite database file at `data/omniroute.db`. This keeps the app self-contained and zero-config.
-
-7. **OAuth with PKCE:** OAuth flows use PKCE for security. A local callback server (`src/lib/oauth/utils/server.ts`) handles the redirect. Token refresh is handled by a background job (`tokenHealthCheck.ts`).
-
-## Main Flows
-
-### Proxy Request Flow
-1. Client sends OpenAI-format request to `/v1/chat/completions`
-2. API key validation (`src/shared/utils/apiAuth.ts`)
-3. Model resolution: direct model or combo lookup
-4. For combos: iterate through models in fallback order
-5. Auth resolution: get credentials for the target provider
-6. Format translation: OpenAI → provider native format
-7. Upstream request with circuit breaker and rate limiting
-8. Response translation: provider → OpenAI format
-9. SSE streaming back to client
-
-### OAuth Flow
-1. Dashboard initiates `/api/oauth/[provider]/authorize`
-2. User completes OAuth login in browser
-3. Callback hits `/api/oauth/[provider]/exchange`
-4. Tokens stored as a provider connection in SQLite
-5. Background job refreshes tokens before expiry
-
-### Model Listing
-- `/api/models` — Dashboard endpoint, lists all defined models with aliases
-- `/v1/models` — OpenAI-compatible endpoint, lists only models from active providers
-
-## Important Notes for LLMs
-
-1. **Two model endpoints exist:** `/api/models` (dashboard, all models) and `/v1/models` (OpenAI-compatible, active only). Don't confuse them.
-
-2. **Provider IDs vs aliases:** Providers have both an ID (`claude`, `github`) and a short alias (`cc`, `gh`). Models are referenced as `alias/model-name` (e.g., `cc/claude-opus-4-6`).
-
-3. **The `open-sse/` directory is a separate npm workspace** with its own config, handlers, and translators. It handles the actual SSE streaming and format translation.
-
-4. **Environment variables:** All configuration is in `.env` (from `.env.example`). Key vars: `PORT`, `NEXT_PUBLIC_BASE_URL`, `API_KEY`, `ADMIN_PASSWORD`.
-
-5. **Database migrations:** SQLite schema is managed inline in `src/lib/db/core.ts` and `src/lib/db/providers.ts`. No migration framework — schema changes are applied on startup.
-
-6. **Tests use Node.js built-in test runner:** Run `npm test` or `node --test tests/unit/*.test.mjs`. Playwright is used for E2E tests.
-
-7. **The proxy pipeline is in `src/sse/`**, not in `src/app/api/v1/`. The API routes in `src/app/api/v1/` delegate to the SSE server running on a separate Express instance.
-
-## Links
-
-- Repository: https://github.com/diegosouzapw/OmniRoute
-- Website: https://omniroute.online
-- npm: https://www.npmjs.com/package/omniroute
-- Docker Hub: https://hub.docker.com/r/diegosouzapw/omniroute
-- Documentation: See `/docs/` directory

next.config.mjs

@@ -1,18 +1,11 @@
 /** @type {import('next').NextConfig} */
 const nextConfig = {
-  turbopack: {},
   output: "standalone",
-  serverExternalPackages: ["better-sqlite3"],
   transpilePackages: ["@omniroute/open-sse"],
   allowedDevOrigins: ["192.168.*"],
-  typescript: {
-    // All TS errors resolved — strict checking enforced
-    ignoreBuildErrors: false,
-  },
   images: {
     unoptimized: true,
   },
-
   // NEXT_PUBLIC_CLOUD_URL is set in .env — do NOT hardcode here (it overrides .env)
   webpack: (config, { isServer }) => {
     // Ignore fs/path modules in browser bundle

open-sse/config/audioRegistry.js

@@ -6,22 +6,7 @@
  * - /v1/audio/speech (TTS API)
  */
 
-interface AudioModel {
-  id: string;
-  name: string;
-}
-
-interface AudioProvider {
-  id: string;
-  baseUrl: string;
-  authType: string;
-  authHeader: string;
-  format?: string;
-  async?: boolean;
-  models: AudioModel[];
-}
-
-export const AUDIO_TRANSCRIPTION_PROVIDERS: Record<string, AudioProvider> = {
+export const AUDIO_TRANSCRIPTION_PROVIDERS = {
   openai: {
     id: "openai",
     baseUrl: "https://api.openai.com/v1/audio/transcriptions",
@@ -72,7 +57,7 @@ export const AUDIO_TRANSCRIPTION_PROVIDERS: Record<string, AudioProvider> = {
   },
 };
 
-export const AUDIO_SPEECH_PROVIDERS: Record<string, AudioProvider> = {
+export const AUDIO_SPEECH_PROVIDERS = {
   openai: {
     id: "openai",
     baseUrl: "https://api.openai.com/v1/audio/speech",
@@ -111,21 +96,21 @@ export const AUDIO_SPEECH_PROVIDERS: Record<string, AudioProvider> = {
 /**
  * Get transcription provider config by ID
  */
-export function getTranscriptionProvider(providerId: string): AudioProvider | null {
+export function getTranscriptionProvider(providerId) {
   return AUDIO_TRANSCRIPTION_PROVIDERS[providerId] || null;
 }
 
 /**
  * Get speech provider config by ID
  */
-export function getSpeechProvider(providerId: string): AudioProvider | null {
+export function getSpeechProvider(providerId) {
   return AUDIO_SPEECH_PROVIDERS[providerId] || null;
 }
 
 /**
  * Parse audio model string (format: "provider/model" or just "model")
  */
-function parseAudioModel(modelStr: string | null, registry: Record<string, AudioProvider>): { provider: string | null; model: string | null } {
+function parseAudioModel(modelStr, registry) {
   if (!modelStr) return { provider: null, model: null };
 
   for (const [providerId, config] of Object.entries(registry)) {
@@ -143,11 +128,11 @@ function parseAudioModel(modelStr: string | null, registry: Record<string, Audio
   return { provider: null, model: modelStr };
 }
 
-export function parseTranscriptionModel(modelStr: string | null) {
+export function parseTranscriptionModel(modelStr) {
   return parseAudioModel(modelStr, AUDIO_TRANSCRIPTION_PROVIDERS);
 }
 
-export function parseSpeechModel(modelStr: string | null) {
+export function parseSpeechModel(modelStr) {
   return parseAudioModel(modelStr, AUDIO_SPEECH_PROVIDERS);
 }
 

open-sse/config/constants.js

@@ -1,4 +1,4 @@
-import { loadProviderCredentials } from "./credentialLoader.ts";
+import { loadProviderCredentials } from "./credentialLoader.js";
 
 // Timeout for non-streaming fetch requests (ms). Prevents stalled connections.
 export const FETCH_TIMEOUT_MS = parseInt(process.env.FETCH_TIMEOUT_MS || "120000", 10);
@@ -9,7 +9,7 @@ export const STREAM_IDLE_TIMEOUT_MS = parseInt(process.env.STREAM_IDLE_TIMEOUT_M
 // Provider configurations
 // OAuth credentials read from env vars with hardcoded fallbacks for backward compatibility.
 // Use provider-credentials.json or env vars to override in production.
-import { generateLegacyProviders } from "./providerRegistry.ts";
+import { generateLegacyProviders } from "./providerRegistry.js";
 
 export const PROVIDERS = generateLegacyProviders();
 
@@ -113,29 +113,12 @@ export const BACKOFF_CONFIG = {
   maxLevel: 15, // Cap backoff level
 };
 
-// Configurable backoff steps for rate limits (Phase 1 — enhanced rate limiting)
-// Used for per-model lockouts with increasing severity
-export const BACKOFF_STEPS_MS = [60_000, 120_000, 300_000, 600_000, 1_200_000];
-// 1min → 2min → 5min → 10min → 20min
-
-// Structured error classification for rate limiting decisions
-export const RateLimitReason = {
-  QUOTA_EXHAUSTED: "quota_exhausted", // Daily/monthly quota depleted
-  RATE_LIMIT_EXCEEDED: "rate_limit_exceeded", // RPM/RPD limits hit
-  MODEL_CAPACITY: "model_capacity", // Model overloaded (529, 503)
-  SERVER_ERROR: "server_error", // 5xx errors
-  AUTH_ERROR: "auth_error", // 401, 403
-  UNKNOWN: "unknown",
-};
-
 // Error-based cooldown times (aligned with CLIProxyAPI)
 export const COOLDOWN_MS = {
-  unauthorized: 2 * 60 * 1000, // 401 → 2 min
-  paymentRequired: 2 * 60 * 1000, // 402/403 → 2 min
+  unauthorized: 2 * 60 * 1000, // 401 → 30 min
+  paymentRequired: 2 * 60 * 1000, // 402/403 → 30 min
   notFound: 2 * 60 * 1000, // 404 → 2 minutes
-  transientInitial: 5 * 1000, // 408/500/502/503/504 first hit → 5s (backoff from here)
-  transientMax: 60 * 1000, // 502/503/504 backoff ceiling → 60s
-  transient: 5 * 1000, // Legacy alias → points to transientInitial
+  transient: 30 * 1000, // 408/500/502/503/504 → 1 min
   requestNotAllowed: 5 * 1000, // "Request not allowed" → 5 sec
   // Legacy aliases for backward compatibility
   rateLimit: 2 * 60 * 1000,
@@ -143,33 +126,5 @@ export const COOLDOWN_MS = {
   authExpired: 2 * 60 * 1000,
 };
 
-// ─── Provider Resilience Profiles ───────────────────────────────────────────
-// Separate behavior for OAuth (low-limit, session-based) vs API Key (high-limit, metered)
-export const PROVIDER_PROFILES = {
-  oauth: {
-    transientCooldown: 5000, // 5s (session tokens — short recovery)
-    rateLimitCooldown: 60000, // 60s default when no retry-after header
-    maxBackoffLevel: 8, // Higher ceiling (sessions may stay bad longer)
-    circuitBreakerThreshold: 3, // Opens fast (low limit providers)
-    circuitBreakerReset: 60000, // 1min reset
-  },
-  apikey: {
-    transientCooldown: 3000, // 3s (API providers recover faster)
-    rateLimitCooldown: 0, // 0 = respect retry-after header from provider
-    maxBackoffLevel: 5, // Lower ceiling (API quotas reset at known intervals)
-    circuitBreakerThreshold: 5, // More tolerant (occasional 502 is normal)
-    circuitBreakerReset: 30000, // 30s reset
-  },
-};
-
-// Default rate limit values for API Key providers (auto-enabled safety net)
-// These are intentionally HIGH — they won't restrict normal usage.
-// Real limits are learned from provider response headers.
-export const DEFAULT_API_LIMITS = {
-  requestsPerMinute: 100, // 100 RPM (most APIs allow 60-600 RPM)
-  minTimeBetweenRequests: 200, // 200ms minimum gap
-  concurrentRequests: 10, // Max 10 parallel per provider
-};
-
 // Skip patterns - requests containing these texts will bypass provider
 export const SKIP_PATTERNS = ["Please write a 5-10 word title for the following conversation:"];

open-sse/config/providerModels.js

@@ -1,4 +1,4 @@
-import { generateModels, generateAliasMap } from "./providerRegistry.ts";
+import { generateModels, generateAliasMap } from "./providerRegistry.js";
 
 // Provider models - Generated from providerRegistry.js (single source of truth)
 export const PROVIDER_MODELS = generateModels();

open-sse/config/providerRegistry.js

@@ -6,51 +6,9 @@
  * is auto-generated from this registry.
  */
 
-// ── Types ─────────────────────────────────────────────────────────────────
-
-export interface RegistryModel {
-  id: string;
-  name: string;
-  targetFormat?: string;
-}
-
-export interface RegistryOAuth {
-  clientIdEnv?: string;
-  clientIdDefault?: string;
-  clientSecretEnv?: string;
-  clientSecretDefault?: string;
-  tokenUrl?: string;
-  refreshUrl?: string;
-  authUrl?: string;
-  initiateUrl?: string;
-  pollUrlBase?: string;
-}
-
-export interface RegistryEntry {
-  id: string;
-  alias: string;
-  format: string;
-  executor: string;
-  baseUrl?: string;
-  baseUrls?: string[];
-  responsesBaseUrl?: string;
-  urlSuffix?: string;
-  urlBuilder?: (base: string, model: string, stream: boolean) => string;
-  authType: string;
-  authHeader: string;
-  authPrefix?: string;
-  headers?: Record<string, string>;
-  extraHeaders?: Record<string, string>;
-  oauth?: RegistryOAuth;
-  models: RegistryModel[];
-  chatPath?: string;
-  clientVersion?: string;
-  passthroughModels?: boolean;
-}
-
 // ── Registry ──────────────────────────────────────────────────────────────
 
-export const REGISTRY: Record<string, RegistryEntry> = {
+export const REGISTRY = {
   // ─── OAuth Providers ───────────────────────────────────────────────────
   claude: {
     id: "claude",
@@ -802,10 +760,10 @@ export const REGISTRY: Record<string, RegistryEntry> = {
 // ── Generator Functions ───────────────────────────────────────────────────
 
 /** Generate legacy PROVIDERS object shape for constants.js backward compatibility */
-export function generateLegacyProviders(): Record<string, any> {
-  const providers: Record<string, any> = {};
+export function generateLegacyProviders() {
+  const providers = {};
   for (const [id, entry] of Object.entries(REGISTRY)) {
-    const p: Record<string, any> = { format: entry.format };
+    const p = { format: entry.format };
 
     // URL(s)
     if (entry.baseUrls) {
@@ -850,8 +808,8 @@ export function generateLegacyProviders(): Record<string, any> {
 }
 
 /** Generate PROVIDER_MODELS map (alias → model list) */
-export function generateModels(): Record<string, RegistryModel[]> {
-  const models: Record<string, RegistryModel[]> = {};
+export function generateModels() {
+  const models = {};
   for (const entry of Object.values(REGISTRY)) {
     if (entry.models && entry.models.length > 0) {
       const key = entry.alias || entry.id;
@@ -865,8 +823,8 @@ export function generateModels(): Record<string, RegistryModel[]> {
 }
 
 /** Generate PROVIDER_ID_TO_ALIAS map */
-export function generateAliasMap(): Record<string, string> {
-  const map: Record<string, string> = {};
+export function generateAliasMap() {
+  const map = {};
   for (const entry of Object.values(REGISTRY)) {
     map[entry.id] = entry.alias || entry.id;
   }
@@ -883,23 +841,11 @@ for (const entry of Object.values(REGISTRY)) {
 }
 
 /** Get registry entry by provider ID or alias */
-export function getRegistryEntry(provider: string): RegistryEntry | null {
+export function getRegistryEntry(provider) {
   return REGISTRY[provider] || _byAlias.get(provider) || null;
 }
 
 /** Get all registered provider IDs */
-export function getRegisteredProviders(): string[] {
+export function getRegisteredProviders() {
   return Object.keys(REGISTRY);
 }
-
-/**
- * Get provider category: "oauth" or "apikey"
- * Used by the resilience layer to apply different cooldown/backoff profiles.
- * @param {string} provider - Provider ID or alias
- * @returns {"oauth"|"apikey"}
- */
-export function getProviderCategory(provider: string): "oauth" | "apikey" {
-  const entry = getRegistryEntry(provider);
-  if (!entry) return "apikey"; // Safe default for unknown providers
-  return entry.authType === "apikey" ? "apikey" : "oauth";
-}

open-sse/executors/antigravity.js

@@ -1,6 +1,6 @@
 import crypto from "crypto";
-import { BaseExecutor } from "./base.ts";
-import { PROVIDERS, OAUTH_ENDPOINTS, HTTP_STATUS } from "../config/constants.ts";
+import { BaseExecutor } from "./base.js";
+import { PROVIDERS, OAUTH_ENDPOINTS, HTTP_STATUS } from "../config/constants.js";
 
 const MAX_RETRY_AFTER_MS = 10000;
 

open-sse/executors/base.js

@@ -1,4 +1,4 @@
-import { HTTP_STATUS, FETCH_TIMEOUT_MS } from "../config/constants.ts";
+import { HTTP_STATUS, FETCH_TIMEOUT_MS } from "../config/constants.js";
 
 /**
  * BaseExecutor - Base class for provider executors.
@@ -6,10 +6,7 @@ import { HTTP_STATUS, FETCH_TIMEOUT_MS } from "../config/constants.ts";
  * (buildUrl, buildHeaders, transformRequest, etc.) for each provider.
  */
 export class BaseExecutor {
-  provider: any;
-  config: any;
-
-  constructor(provider: any, config: any) {
+  constructor(provider, config) {
     this.provider = provider;
     this.config = config;
   }
@@ -99,7 +96,7 @@ export class BaseExecutor {
             ? AbortSignal.any([signal, timeoutSignal])
             : signal || timeoutSignal;
 
-        const fetchOptions: Record<string, any> = {
+        const fetchOptions = {
           method: "POST",
           headers,
           body: JSON.stringify(transformedBody),

open-sse/executors/codex.js

@@ -1,6 +1,6 @@
-import { BaseExecutor } from "./base.ts";
-import { CODEX_DEFAULT_INSTRUCTIONS } from "../config/codexInstructions.ts";
-import { PROVIDERS } from "../config/constants.ts";
+import { BaseExecutor } from "./base.js";
+import { CODEX_DEFAULT_INSTRUCTIONS } from "../config/codexInstructions.js";
+import { PROVIDERS } from "../config/constants.js";
 
 /**
  * Codex Executor - handles OpenAI Codex API (Responses API format)

open-sse/executors/cursor.js

@@ -1,4 +1,3 @@
-declare var EdgeRuntime: any;
 /**
  * CursorExecutor — Handles communication with the Cursor IDE API.
  *
@@ -20,16 +19,16 @@ declare var EdgeRuntime: any;
  * @see cursorProtobuf.js for Protobuf encoding/decoding utilities
  */
 
-import { BaseExecutor } from "./base.ts";
-import { PROVIDERS, HTTP_STATUS } from "../config/constants.ts";
+import { BaseExecutor } from "./base.js";
+import { PROVIDERS, HTTP_STATUS } from "../config/constants.js";
 import {
   generateCursorBody,
   parseConnectRPCFrame,
   extractTextFromResponse,
-} from "../utils/cursorProtobuf.ts";
-import { estimateUsage } from "../utils/usageTracking.ts";
-import { FORMATS } from "../translator/formats.ts";
-import { buildCursorRequest } from "../translator/request/openai-to-cursor.ts";
+} from "../utils/cursorProtobuf.js";
+import { estimateUsage } from "../utils/usageTracking.js";
+import { FORMATS } from "../translator/formats.js";
+import { buildCursorRequest } from "../translator/request/openai-to-cursor.js";
 import crypto from "crypto";
 import { v5 as uuidv5 } from "uuid";
 import zlib from "zlib";
@@ -227,7 +226,7 @@ export class CursorExecutor extends BaseExecutor {
 
     return {
       status: response.status,
-      headers: Object.fromEntries((response.headers as any).entries()),
+      headers: Object.fromEntries(response.headers.entries()),
       body: Buffer.from(await response.arrayBuffer()),
     };
   }
@@ -291,7 +290,7 @@ export class CursorExecutor extends BaseExecutor {
     const transformedBody = this.transformRequest(model, body, stream, credentials);
 
     try {
-      const response: any = http2
+      const response = http2
         ? await this.makeHttp2Request(url, headers, transformedBody, signal)
         : await this.makeFetchRequest(url, headers, transformedBody, signal);
 
@@ -459,7 +458,8 @@ export class CursorExecutor extends BaseExecutor {
 
     console.log(`[CURSOR BUFFER] Final toolCalls count: ${toolCalls.length}`);
 
-    const message: Record<string, any> = { role: "assistant",
+    const message = {
+      role: "assistant",
       content: totalContent || null,
     };
 

open-sse/executors/default.js

@@ -1,6 +1,6 @@
-import { BaseExecutor } from "./base.ts";
-import { PROVIDERS, OAUTH_ENDPOINTS } from "../config/constants.ts";
-import { getAccessToken } from "../services/tokenRefresh.ts";
+import { BaseExecutor } from "./base.js";
+import { PROVIDERS, OAUTH_ENDPOINTS } from "../config/constants.js";
+import { getAccessToken } from "../services/tokenRefresh.js";
 
 export class DefaultExecutor extends BaseExecutor {
   constructor(provider) {

open-sse/executors/gemini-cli.js

@@ -1,5 +1,5 @@
-import { BaseExecutor } from "./base.ts";
-import { PROVIDERS, OAUTH_ENDPOINTS } from "../config/constants.ts";
+import { BaseExecutor } from "./base.js";
+import { PROVIDERS, OAUTH_ENDPOINTS } from "../config/constants.js";
 
 export class GeminiCLIExecutor extends BaseExecutor {
   constructor() {

open-sse/executors/github.js

@@ -1,6 +1,6 @@
-import { BaseExecutor } from "./base.ts";
-import { PROVIDERS, OAUTH_ENDPOINTS } from "../config/constants.ts";
-import { getModelTargetFormat } from "../config/providerModels.ts";
+import { BaseExecutor } from "./base.js";
+import { PROVIDERS, OAUTH_ENDPOINTS } from "../config/constants.js";
+import { getModelTargetFormat } from "../config/providerModels.js";
 
 export class GithubExecutor extends BaseExecutor {
   constructor() {

open-sse/executors/index.js

@@ -0,0 +1,38 @@
+import { AntigravityExecutor } from "./antigravity.js";
+import { GeminiCLIExecutor } from "./gemini-cli.js";
+import { GithubExecutor } from "./github.js";
+import { KiroExecutor } from "./kiro.js";
+import { CodexExecutor } from "./codex.js";
+import { CursorExecutor } from "./cursor.js";
+import { DefaultExecutor } from "./default.js";
+
+const executors = {
+  antigravity: new AntigravityExecutor(),
+  "gemini-cli": new GeminiCLIExecutor(),
+  github: new GithubExecutor(),
+  kiro: new KiroExecutor(),
+  codex: new CodexExecutor(),
+  cursor: new CursorExecutor(),
+  cu: new CursorExecutor(), // Alias for cursor
+};
+
+const defaultCache = new Map();
+
+export function getExecutor(provider) {
+  if (executors[provider]) return executors[provider];
+  if (!defaultCache.has(provider)) defaultCache.set(provider, new DefaultExecutor(provider));
+  return defaultCache.get(provider);
+}
+
+export function hasSpecializedExecutor(provider) {
+  return !!executors[provider];
+}
+
+export { BaseExecutor } from "./base.js";
+export { AntigravityExecutor } from "./antigravity.js";
+export { GeminiCLIExecutor } from "./gemini-cli.js";
+export { GithubExecutor } from "./github.js";
+export { KiroExecutor } from "./kiro.js";
+export { CodexExecutor } from "./codex.js";
+export { CursorExecutor } from "./cursor.js";
+export { DefaultExecutor } from "./default.js";

open-sse/executors/index.ts

@@ -1,38 +0,0 @@
-import { AntigravityExecutor } from "./antigravity.ts";
-import { GeminiCLIExecutor } from "./gemini-cli.ts";
-import { GithubExecutor } from "./github.ts";
-import { KiroExecutor } from "./kiro.ts";
-import { CodexExecutor } from "./codex.ts";
-import { CursorExecutor } from "./cursor.ts";
-import { DefaultExecutor } from "./default.ts";
-
-const executors = {
-  antigravity: new AntigravityExecutor(),
-  "gemini-cli": new GeminiCLIExecutor(),
-  github: new GithubExecutor(),
-  kiro: new KiroExecutor(),
-  codex: new CodexExecutor(),
-  cursor: new CursorExecutor(),
-  cu: new CursorExecutor(), // Alias for cursor
-};
-
-const defaultCache = new Map();
-
-export function getExecutor(provider) {
-  if (executors[provider]) return executors[provider];
-  if (!defaultCache.has(provider)) defaultCache.set(provider, new DefaultExecutor(provider));
-  return defaultCache.get(provider);
-}
-
-export function hasSpecializedExecutor(provider) {
-  return !!executors[provider];
-}
-
-export { BaseExecutor } from "./base.ts";
-export { AntigravityExecutor } from "./antigravity.ts";
-export { GeminiCLIExecutor } from "./gemini-cli.ts";
-export { GithubExecutor } from "./github.ts";
-export { KiroExecutor } from "./kiro.ts";
-export { CodexExecutor } from "./codex.ts";
-export { CursorExecutor } from "./cursor.ts";
-export { DefaultExecutor } from "./default.ts";

open-sse/executors/kiro.js

@@ -1,7 +1,7 @@
-import { BaseExecutor } from "./base.ts";
-import { PROVIDERS } from "../config/constants.ts";
+import { BaseExecutor } from "./base.js";
+import { PROVIDERS } from "../config/constants.js";
 import { v4 as uuidv4 } from "uuid";
-import { refreshKiroToken } from "../services/tokenRefresh.ts";
+import { refreshKiroToken } from "../services/tokenRefresh.js";
 
 // ── CRC32 lookup table (IEEE polynomial, no dependency) ──
 const CRC32_TABLE = new Uint32Array(256);
@@ -83,7 +83,8 @@ export class KiroExecutor extends BaseExecutor {
     let chunkIndex = 0;
     const responseId = `chatcmpl-${Date.now()}`;
     const created = Math.floor(Date.now() / 1000);
-    const state: Record<string, any> = { endDetected: false,
+    const state = {
+      endDetected: false,
       finishEmitted: false,
       hasToolCalls: false,
       toolCallIndex: 0,
@@ -125,7 +126,7 @@ export class KiroExecutor extends BaseExecutor {
             const content = event.payload.content;
             state.totalContentLength += content.length;
 
-            const chunk: Record<string, any> = {
+            const chunk = {
               id: responseId,
               object: "chat.completion.chunk",
               created,
@@ -144,7 +145,7 @@ export class KiroExecutor extends BaseExecutor {
 
           // Handle codeEvent
           if (eventType === "codeEvent" && event.payload?.content) {
-            const chunk: Record<string, any> = {
+            const chunk = {
               id: responseId,
               object: "chat.completion.chunk",
               created,
@@ -256,7 +257,7 @@ export class KiroExecutor extends BaseExecutor {
 
           // Handle messageStopEvent
           if (eventType === "messageStopEvent") {
-            const chunk: Record<string, any> = {
+            const chunk = {
               id: responseId,
               object: "chat.completion.chunk",
               created,
@@ -329,7 +330,7 @@ export class KiroExecutor extends BaseExecutor {
               };
             }
 
-            const finishChunk: Record<string, any> = {
+            const finishChunk = {
               id: responseId,
               object: "chat.completion.chunk",
               created,

open-sse/handlers/audioSpeech.js

@@ -1,4 +1,3 @@
-import { getCorsOrigin } from "../utils/cors.ts";
 /**
  * Audio Speech Handler (TTS)
  *
@@ -11,8 +10,8 @@ import { getCorsOrigin } from "../utils/cors.ts";
  * - Deepgram: POST { text } with model via query param, Token auth
  */
 
-import { getSpeechProvider, parseSpeechModel } from "../config/audioRegistry.ts";
-import { errorResponse } from "../utils/error.ts";
+import { getSpeechProvider, parseSpeechModel } from "../config/audioRegistry.js";
+import { errorResponse } from "../utils/error.js";
 
 /**
  * Build auth header for a speech provider
@@ -41,10 +40,7 @@ async function handleHyperbolicSpeech(providerConfig, body, token) {
     const errText = await res.text();
     return new Response(errText, {
       status: res.status,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-      },
+      headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" },
     });
   }
 
@@ -56,7 +52,7 @@ async function handleHyperbolicSpeech(providerConfig, body, token) {
     status: 200,
     headers: {
       "Content-Type": "audio/mpeg",
-      "Access-Control-Allow-Origin": getCorsOrigin(),
+      "Access-Control-Allow-Origin": "*",
     },
   });
 }
@@ -81,10 +77,7 @@ async function handleDeepgramSpeech(providerConfig, body, modelId, token) {
     const errText = await res.text();
     return new Response(errText, {
       status: res.status,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-      },
+      headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" },
     });
   }
 
@@ -93,7 +86,7 @@ async function handleDeepgramSpeech(providerConfig, body, modelId, token) {
     status: 200,
     headers: {
       "Content-Type": contentType,
-      "Access-Control-Allow-Origin": getCorsOrigin(),
+      "Access-Control-Allow-Origin": "*",
       "Transfer-Encoding": "chunked",
     },
   });
@@ -107,13 +100,12 @@ async function handleDeepgramSpeech(providerConfig, body, modelId, token) {
  * @param {Object} options.credentials - Provider credentials { apiKey }
  * @returns {Response}
  */
-/** @returns {Promise<any>} */
 export async function handleAudioSpeech({ body, credentials }) {
   if (!body.model) {
-    return errorResponse(400, "model is required");
+    return errorResponse("model is required", 400);
   }
   if (!body.input) {
-    return errorResponse(400, "input is required");
+    return errorResponse("input is required", 400);
   }
 
   const { provider: providerId, model: modelId } = parseSpeechModel(body.model);
@@ -121,14 +113,14 @@ 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`,
+      400
     );
   }
 
   const token = credentials?.apiKey || credentials?.accessToken;
   if (!token) {
-    return errorResponse(401, `No credentials for speech provider: ${providerId}`);
+    return errorResponse(`No credentials for speech provider: ${providerId}`, 401);
   }
 
   try {
@@ -161,10 +153,7 @@ export async function handleAudioSpeech({ body, credentials }) {
       const errText = await res.text();
       return new Response(errText, {
         status: res.status,
-        headers: {
-          "Content-Type": "application/json",
-          "Access-Control-Allow-Origin": getCorsOrigin(),
-        },
+        headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" },
       });
     }
 
@@ -174,11 +163,11 @@ export async function handleAudioSpeech({ body, credentials }) {
       status: 200,
       headers: {
         "Content-Type": contentType,
-        "Access-Control-Allow-Origin": getCorsOrigin(),
+        "Access-Control-Allow-Origin": "*",
         "Transfer-Encoding": "chunked",
       },
     });
   } catch (err) {
-    return errorResponse(500, `Speech request failed: ${err.message}`);
+    return errorResponse(`Speech request failed: ${err.message}`, 500);
   }
 }

open-sse/handlers/audioTranscription.js

@@ -1,4 +1,3 @@
-import { getCorsOrigin } from "../utils/cors.ts";
 /**
  * Audio Transcription Handler
  *
@@ -11,8 +10,8 @@ import { getCorsOrigin } from "../utils/cors.ts";
  * - AssemblyAI: async workflow (upload → submit → poll)
  */
 
-import { getTranscriptionProvider, parseTranscriptionModel } from "../config/audioRegistry.ts";
-import { errorResponse } from "../utils/error.ts";
+import { getTranscriptionProvider, parseTranscriptionModel } from "../config/audioRegistry.js";
+import { errorResponse } from "../utils/error.js";
 
 /**
  * Build auth header for a transcription provider
@@ -47,10 +46,7 @@ async function handleDeepgramTranscription(providerConfig, file, modelId, token)
     const errText = await res.text();
     return new Response(errText, {
       status: res.status,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-      },
+      headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" },
     });
   }
 
@@ -58,7 +54,7 @@ async function handleDeepgramTranscription(providerConfig, file, modelId, token)
   // Transform Deepgram response to OpenAI Whisper format
   const text = data.results?.channels?.[0]?.alternatives?.[0]?.transcript || "";
 
-  return Response.json({ text }, { headers: { "Access-Control-Allow-Origin": getCorsOrigin() } });
+  return Response.json({ text }, { headers: { "Access-Control-Allow-Origin": "*" } });
 }
 
 /**
@@ -82,10 +78,7 @@ async function handleAssemblyAITranscription(providerConfig, file, modelId, toke
     const errText = await uploadRes.text();
     return new Response(errText, {
       status: uploadRes.status,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-      },
+      headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" },
     });
   }
 
@@ -109,10 +102,7 @@ async function handleAssemblyAITranscription(providerConfig, file, modelId, toke
     const errText = await submitRes.text();
     return new Response(errText, {
       status: submitRes.status,
-      headers: {
-        "Content-Type": "application/json",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
-      },
+      headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" },
     });
   }
 
@@ -134,16 +124,16 @@ async function handleAssemblyAITranscription(providerConfig, file, modelId, toke
     if (result.status === "completed") {
       return Response.json(
         { text: result.text || "" },
-        { headers: { "Access-Control-Allow-Origin": getCorsOrigin() } }
+        { headers: { "Access-Control-Allow-Origin": "*" } }
       );
     }
 
     if (result.status === "error") {
-      return errorResponse(500, result.error || "AssemblyAI transcription failed");
+      return errorResponse(result.error || "AssemblyAI transcription failed", 500);
     }
   }
 
-  return errorResponse(504, "AssemblyAI transcription timed out after 120s");
+  return errorResponse("AssemblyAI transcription timed out after 120s", 504);
 }
 
 /**
@@ -154,16 +144,15 @@ async function handleAssemblyAITranscription(providerConfig, file, modelId, toke
  * @param {Object} options.credentials - Provider credentials { apiKey }
  * @returns {Response}
  */
-/** @returns {Promise<any>} */
 export async function handleAudioTranscription({ formData, credentials }) {
   const model = formData.get("model");
   if (!model) {
-    return errorResponse(400, "model is required");
+    return errorResponse("model is required", 400);
   }
 
   const file = formData.get("file");
   if (!file) {
-    return errorResponse(400, "file is required");
+    return errorResponse("file is required", 400);
   }
 
   const { provider: providerId, model: modelId } = parseTranscriptionModel(model);
@@ -171,14 +160,14 @@ 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`,
+      400
     );
   }
 
   const token = credentials?.apiKey || credentials?.accessToken;
   if (!token) {
-    return errorResponse(401, `No credentials for transcription provider: ${providerId}`);
+    return errorResponse(`No credentials for transcription provider: ${providerId}`, 401);
   }
 
   // Route to provider-specific handler
@@ -192,11 +181,7 @@ export async function handleAudioTranscription({ formData, credentials }) {
 
   // Default: OpenAI/Groq-compatible multipart proxy
   const upstreamForm = new FormData();
-  upstreamForm.append(
-    "file",
-    /** @type {Blob} */ file,
-    /** @type {any} */ file.name || "audio.wav"
-  );
+  upstreamForm.append("file", file, file.name || "audio.wav");
   upstreamForm.append("model", modelId);
 
   // Forward optional parameters
@@ -209,7 +194,7 @@ export async function handleAudioTranscription({ formData, credentials }) {
   ]) {
     const val = formData.get(key);
     if (val !== null && val !== undefined) {
-      upstreamForm.append(key, /** @type {string} */ val);
+      upstreamForm.append(key, val);
     }
   }
 
@@ -224,10 +209,7 @@ export async function handleAudioTranscription({ formData, credentials }) {
       const errText = await res.text();
       return new Response(errText, {
         status: res.status,
-        headers: {
-          "Content-Type": "application/json",
-          "Access-Control-Allow-Origin": getCorsOrigin(),
-        },
+        headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" },
       });
     }
 
@@ -236,9 +218,9 @@ export async function handleAudioTranscription({ formData, credentials }) {
 
     return new Response(data, {
       status: 200,
-      headers: { "Content-Type": contentType, "Access-Control-Allow-Origin": getCorsOrigin() },
+      headers: { "Content-Type": contentType, "Access-Control-Allow-Origin": "*" },
     });
   } catch (err) {
-    return errorResponse(500, `Transcription request failed: ${err.message}`);
+    return errorResponse(`Transcription request failed: ${err.message}`, 500);
   }
 }

open-sse/handlers/chatCore.js

@@ -1,44 +1,34 @@
-import { getCorsOrigin } from "../utils/cors.ts";
-import { detectFormat, getTargetFormat } from "../services/provider.ts";
-import { translateRequest, needsTranslation } from "../translator/index.ts";
-import { FORMATS } from "../translator/formats.ts";
+import { detectFormat, getTargetFormat } from "../services/provider.js";
+import { translateRequest, needsTranslation } from "../translator/index.js";
+import { FORMATS } from "../translator/formats.js";
 import {
   createSSETransformStreamWithLogger,
   createPassthroughStreamWithLogger,
   COLORS,
-} from "../utils/stream.ts";
-import { createStreamController, pipeWithDisconnect } from "../utils/streamHandler.ts";
-import { addBufferToUsage, filterUsageForFormat, estimateUsage } from "../utils/usageTracking.ts";
-import { refreshWithRetry } from "../services/tokenRefresh.ts";
-import { createRequestLogger } from "../utils/requestLogger.ts";
-import { getModelTargetFormat, PROVIDER_ID_TO_ALIAS } from "../config/providerModels.ts";
-import { createErrorResult, parseUpstreamError, formatProviderError } from "../utils/error.ts";
-import { HTTP_STATUS } from "../config/constants.ts";
-import { handleBypassRequest } from "../utils/bypassHandler.ts";
+} from "../utils/stream.js";
+import { createStreamController, pipeWithDisconnect } from "../utils/streamHandler.js";
+import { addBufferToUsage, filterUsageForFormat, estimateUsage } from "../utils/usageTracking.js";
+import { refreshWithRetry } from "../services/tokenRefresh.js";
+import { createRequestLogger } from "../utils/requestLogger.js";
+import { getModelTargetFormat, PROVIDER_ID_TO_ALIAS } from "../config/providerModels.js";
+import { createErrorResult, parseUpstreamError, formatProviderError } from "../utils/error.js";
+import { HTTP_STATUS } from "../config/constants.js";
+import { handleBypassRequest } from "../utils/bypassHandler.js";
 import {
   saveRequestUsage,
   trackPendingRequest,
   appendRequestLog,
   saveCallLog,
-} from "@/lib/usageDb";
-import { getExecutor } from "../executors/index.ts";
-import { translateNonStreamingResponse } from "./responseTranslator.ts";
-import { extractUsageFromResponse } from "./usageExtractor.ts";
-import { parseSSEToOpenAIResponse, parseSSEToResponsesOutput } from "./sseParser.ts";
-import { sanitizeOpenAIResponse } from "./responseSanitizer.ts";
+} from "@/lib/usageDb.js";
+import { getExecutor } from "../executors/index.js";
+import { translateNonStreamingResponse } from "./responseTranslator.js";
+import { extractUsageFromResponse } from "./usageExtractor.js";
+import { parseSSEToOpenAIResponse, parseSSEToResponsesOutput } from "./sseParser.js";
 import {
   withRateLimit,
   updateFromHeaders,
   initializeRateLimits,
-} from "../services/rateLimitManager.ts";
-import {
-  generateSignature,
-  getCachedResponse,
-  setCachedResponse,
-  isCacheable,
-} from "@/lib/semanticCache";
-import { getIdempotencyKey, checkIdempotency, saveIdempotency } from "@/lib/idempotencyLayer";
-import { createProgressTransform, wantsProgress } from "../utils/progressTracker.ts";
+} from "../services/rateLimitManager.js";
 
 /**
  * Core chat handler - shared between SSE and Worker
@@ -54,7 +44,6 @@ import { createProgressTransform, wantsProgress } from "../utils/progressTracker
  * @param {string} options.connectionId - Connection ID for usage tracking
  * @param {object} options.apiKeyInfo - API key metadata for usage attribution
  */
-/** @param {any} options */
 export async function handleChatCore({
   body,
   modelInfo,
@@ -72,24 +61,6 @@ export async function handleChatCore({
   const { provider, model } = modelInfo;
   const startTime = Date.now();
 
-  // ── Phase 9.2: Idempotency check ──
-  const idempotencyKey = getIdempotencyKey(clientRawRequest?.headers);
-  const cachedIdemp = checkIdempotency(idempotencyKey);
-  if (cachedIdemp) {
-    log?.debug?.("IDEMPOTENCY", `Hit for key=${idempotencyKey?.slice(0, 12)}...`);
-    return {
-      success: true,
-      response: new Response(JSON.stringify(cachedIdemp.response), {
-        status: cachedIdemp.status,
-        headers: {
-          "Content-Type": "application/json",
-          "Access-Control-Allow-Origin": getCorsOrigin(),
-          "X-OmniRoute-Idempotent": "true",
-        },
-      }),
-    };
-  }
-
   // Initialize rate limit settings from persisted DB (once, lazy)
   await initializeRateLimits();
 
@@ -110,27 +81,8 @@ export async function handleChatCore({
   const modelTargetFormat = getModelTargetFormat(alias, model);
   const targetFormat = modelTargetFormat || getTargetFormat(provider);
 
-  // Default to false unless client explicitly sets stream: true (OpenAI spec compliant)
-  const stream = body.stream === true;
-
-  // ── Phase 9.1: Semantic cache check (non-streaming, temp=0 only) ──
-  if (isCacheable(body, clientRawRequest?.headers)) {
-    const signature = generateSignature(model, body.messages, body.temperature, body.top_p);
-    const cached = getCachedResponse(signature);
-    if (cached) {
-      log?.debug?.("CACHE", `Semantic cache HIT for ${model}`);
-      return {
-        success: true,
-        response: new Response(JSON.stringify(cached), {
-          headers: {
-            "Content-Type": "application/json",
-            "Access-Control-Allow-Origin": getCorsOrigin(),
-            "X-OmniRoute-Cache": "HIT",
-          },
-        }),
-      };
-    }
-  }
+  // Default to streaming unless client explicitly sets stream: false
+  const stream = body.stream !== false;
 
   // Create request logger for this session: sourceFormat_targetFormat_model
   const reqLogger = await createRequestLogger(sourceFormat, targetFormat, model);
@@ -190,7 +142,7 @@ export async function handleChatCore({
             status: statusCode,
             headers: {
               "Content-Type": "application/json",
-              "Access-Control-Allow-Origin": getCorsOrigin(),
+              "Access-Control-Allow-Origin": "*",
             },
           }
         ),
@@ -473,17 +425,10 @@ export async function handleChatCore({
     }
 
     // Translate response to client's expected format (usually OpenAI)
-    let translatedResponse = needsTranslation(targetFormat, sourceFormat)
+    const translatedResponse = needsTranslation(targetFormat, sourceFormat)
       ? translateNonStreamingResponse(responseBody, targetFormat, sourceFormat)
       : responseBody;
 
-    // Sanitize response for OpenAI SDK compatibility
-    // Strips non-standard fields (x_groq, usage_breakdown, service_tier, etc.)
-    // Extracts <think> tags into reasoning_content
-    if (sourceFormat === FORMATS.OPENAI) {
-      translatedResponse = sanitizeOpenAIResponse(translatedResponse);
-    }
-
     // Add buffer and filter usage for client (to prevent CLI context errors)
     if (translatedResponse?.usage) {
       const buffered = addBufferToUsage(translatedResponse.usage);
@@ -499,24 +444,12 @@ export async function handleChatCore({
       }
     }
 
-    // ── Phase 9.1: Cache store (non-streaming, temp=0) ──
-    if (isCacheable(body, clientRawRequest?.headers)) {
-      const signature = generateSignature(model, body.messages, body.temperature, body.top_p);
-      const tokensSaved = usage?.prompt_tokens + usage?.completion_tokens || 0;
-      setCachedResponse(signature, model, translatedResponse, tokensSaved);
-      log?.debug?.("CACHE", `Stored response for ${model} (${tokensSaved} tokens)`);
-    }
-
-    // ── Phase 9.2: Save for idempotency ──
-    saveIdempotency(idempotencyKey, translatedResponse, 200);
-
     return {
       success: true,
       response: new Response(JSON.stringify(translatedResponse), {
         headers: {
           "Content-Type": "application/json",
-          "Access-Control-Allow-Origin": getCorsOrigin(),
-          "X-OmniRoute-Cache": "MISS",
+          "Access-Control-Allow-Origin": "*",
         },
       }),
     };
@@ -533,7 +466,7 @@ export async function handleChatCore({
     "Content-Type": "text/event-stream",
     "Cache-Control": "no-cache",
     Connection: "keep-alive",
-    "Access-Control-Allow-Origin": getCorsOrigin(),
+    "Access-Control-Allow-Origin": "*",
   };
 
   // Create transform stream with logger for streaming response
@@ -613,22 +546,12 @@ export async function handleChatCore({
     );
   }
 
-  // ── Phase 9.3: Progress tracking (opt-in) ──
-  const progressEnabled = wantsProgress(clientRawRequest?.headers);
-  let finalStream;
-  if (progressEnabled) {
-    const progressTransform = createProgressTransform({ signal: streamController.signal });
-    // Chain: provider → transform → progress → client
-    const transformedBody = pipeWithDisconnect(providerResponse, transformStream, streamController);
-    finalStream = transformedBody.pipeThrough(progressTransform);
-    responseHeaders["X-OmniRoute-Progress"] = "enabled";
-  } else {
-    finalStream = pipeWithDisconnect(providerResponse, transformStream, streamController);
-  }
+  // Pipe response through transform with disconnect detection
+  const transformedBody = pipeWithDisconnect(providerResponse, transformStream, streamController);
 
   return {
     success: true,
-    response: new Response(finalStream, {
+    response: new Response(transformedBody, {
       headers: responseHeaders,
     }),
   };

open-sse/handlers/embeddings.js

@@ -13,8 +13,8 @@
  * }
  */
 
-import { getEmbeddingProvider, parseEmbeddingModel } from "../config/embeddingRegistry.ts";
-import { saveCallLog } from "@/lib/usageDb";
+import { getEmbeddingProvider, parseEmbeddingModel } from "../config/embeddingRegistry.js";
+import { saveCallLog } from "@/lib/usageDb.js";
 
 /**
  * Handle embedding request
@@ -52,7 +52,7 @@ export async function handleEmbedding({ body, credentials, log }) {
   }
 
   // Build upstream request
-  const upstreamBody: Record<string, any> = {
+  const upstreamBody = {
     model: model,
     input: body.input,
   };

open-sse/handlers/imageGeneration.js

@@ -15,8 +15,8 @@
  * }
  */
 
-import { getImageProvider, parseImageModel } from "../config/imageRegistry.ts";
-import { saveCallLog } from "@/lib/usageDb";
+import { getImageProvider, parseImageModel } from "../config/imageRegistry.js";
+import { saveCallLog } from "@/lib/usageDb.js";
 
 /**
  * Handle image generation request
@@ -232,7 +232,7 @@ async function handleOpenAIImageGeneration({
   };
 
   // Build upstream request (OpenAI-compatible format)
-  const upstreamBody: Record<string, any> = {
+  const upstreamBody = {
     model: model,
     prompt: body.prompt,
   };

open-sse/handlers/moderations.js

@@ -1,12 +1,11 @@
-import { getCorsOrigin } from "../utils/cors.ts";
 /**
  * Moderation Handler
  *
  * Handles POST /v1/moderations (OpenAI Moderations API format).
  */
 
-import { getModerationProvider, parseModerationModel } from "../config/moderationRegistry.ts";
-import { errorResponse } from "../utils/error.ts";
+import { getModerationProvider, parseModerationModel } from "../config/moderationRegistry.js";
+import { errorResponse } from "../utils/error.js";
 
 /**
  * Handle moderation request
@@ -16,10 +15,9 @@ import { errorResponse } from "../utils/error.ts";
  * @param {Object} options.credentials - Provider credentials { apiKey }
  * @returns {Response}
  */
-/** @returns {Promise<any>} */
 export async function handleModeration({ body, credentials }) {
   if (!body.input) {
-    return errorResponse(400, "input is required");
+    return errorResponse("input is required", 400);
   }
 
   // Default to latest moderation model
@@ -29,14 +27,14 @@ export async function handleModeration({ body, credentials }) {
 
   if (!providerConfig) {
     return errorResponse(
-      400,
-      `No moderation provider found for model "${model}". Available: openai`
+      `No moderation provider found for model "${model}". Available: openai`,
+      400
     );
   }
 
   const token = credentials?.apiKey || credentials?.accessToken;
   if (!token) {
-    return errorResponse(401, `No credentials for moderation provider: ${providerId}`);
+    return errorResponse(`No credentials for moderation provider: ${providerId}`, 401);
   }
 
   try {
@@ -56,18 +54,15 @@ export async function handleModeration({ body, credentials }) {
       const errText = await res.text();
       return new Response(errText, {
         status: res.status,
-        headers: {
-          "Content-Type": "application/json",
-          "Access-Control-Allow-Origin": getCorsOrigin(),
-        },
+        headers: { "Content-Type": "application/json", "Access-Control-Allow-Origin": "*" },
       });
     }
 
     const data = await res.json();
     return Response.json(data, {
-      headers: { "Access-Control-Allow-Origin": getCorsOrigin() },
+      headers: { "Access-Control-Allow-Origin": "*" },
     });
   } catch (err) {
-    return errorResponse(500, `Moderation request failed: ${err.message}`);
+    return errorResponse(`Moderation request failed: ${err.message}`, 500);
   }
 }

open-sse/handlers/rerank.js

@@ -1,4 +1,3 @@
-import { getCorsOrigin } from "../utils/cors.ts";
 /**
  * Rerank Handler
  *
@@ -6,8 +5,8 @@ import { getCorsOrigin } from "../utils/cors.ts";
  * Routes to the appropriate provider based on the model prefix or lookup.
  */
 
-import { getRerankProvider, parseRerankModel } from "../config/rerankRegistry.ts";
-import { errorResponse } from "../utils/error.ts";
+import { getRerankProvider, parseRerankModel } from "../config/rerankRegistry.js";
+import { errorResponse } from "../utils/error.js";
 
 /**
  * Build authorization header for a rerank provider
@@ -70,7 +69,6 @@ function transformResponseFromProvider(providerConfig, data) {
  * @param {Object} options.credentials - Provider credentials { apiKey, accessToken }
  * @returns {Response}
  */
-/** @returns {Promise<any>} */
 export async function handleRerank({
   model,
   query,
@@ -79,10 +77,10 @@ export async function handleRerank({
   return_documents,
   credentials,
 }) {
-  if (!model) return errorResponse(400, "model is required");
-  if (!query) return errorResponse(400, "query is required");
+  if (!model) return errorResponse("model is required", 400);
+  if (!query) return errorResponse("query is required", 400);
   if (!documents || !Array.isArray(documents) || documents.length === 0) {
-    return errorResponse(400, "documents must be a non-empty array");
+    return errorResponse("documents must be a non-empty array", 400);
   }
 
   const { provider: providerId, model: modelId } = parseRerankModel(model);
@@ -90,14 +88,14 @@ export async function handleRerank({
 
   if (!providerConfig) {
     return errorResponse(
-      400,
-      `No rerank provider found for model "${model}". Available: cohere, together, nvidia, fireworks`
+      `No rerank provider found for model "${model}". Available: cohere, together, nvidia, fireworks`,
+      400
     );
   }
 
   const token = credentials?.apiKey || credentials?.accessToken;
   if (!token) {
-    return errorResponse(401, `No credentials for rerank provider: ${providerId}`);
+    return errorResponse(`No credentials for rerank provider: ${providerId}`, 401);
   }
 
   const requestBody = transformRequestForProvider(providerConfig, {
@@ -121,8 +119,8 @@ export async function handleRerank({
     if (!res.ok) {
       const errData = await res.json().catch(() => ({}));
       return errorResponse(
-        res.status,
-        errData.message || errData.error?.message || `Provider returned HTTP ${res.status}`
+        errData.message || errData.error?.message || `Provider returned HTTP ${res.status}`,
+        res.status
       );
     }
 
@@ -130,9 +128,9 @@ export async function handleRerank({
     const result = transformResponseFromProvider(providerConfig, data);
 
     return Response.json(result, {
-      headers: { "Access-Control-Allow-Origin": getCorsOrigin() },
+      headers: { "Access-Control-Allow-Origin": "*" },
     });
   } catch (err) {
-    return errorResponse(500, `Rerank request failed: ${err.message}`);
+    return errorResponse(`Rerank request failed: ${err.message}`, 500);
   }
 }

open-sse/handlers/responseSanitizer.ts

@@ -1,269 +0,0 @@
-/**
- * Response Sanitizer — Normalizes LLM responses to strict OpenAI SDK format.
- *
- * Fixes Issues:
- * 1. Strips non-standard fields (x_groq, usage_breakdown, service_tier) that
- *    break OpenAI Python SDK v1.83+ Pydantic validation (returns str instead of object)
- * 2. Extracts <think> tags from thinking models into reasoning_content
- * 3. Normalizes response id, object, and usage fields
- * 4. Converts developer role → system for non-OpenAI providers
- */
-
-// ── Standard OpenAI ChatCompletion fields ──────────────────────────────────
-const ALLOWED_TOP_LEVEL_FIELDS = new Set([
-  "id",
-  "object",
-  "created",
-  "model",
-  "choices",
-  "usage",
-  "system_fingerprint",
-]);
-
-const ALLOWED_USAGE_FIELDS = new Set([
-  "prompt_tokens",
-  "completion_tokens",
-  "total_tokens",
-  "prompt_tokens_details",
-  "completion_tokens_details",
-]);
-
-const ALLOWED_MESSAGE_FIELDS = new Set([
-  "role",
-  "content",
-  "tool_calls",
-  "function_call",
-  "refusal",
-  "reasoning_content",
-]);
-
-const ALLOWED_CHOICE_FIELDS = new Set(["index", "message", "delta", "finish_reason", "logprobs"]);
-
-// ── Think tag regex ────────────────────────────────────────────────────────
-// Matches <think>...</think> blocks (greedy, dotAll)
-const THINK_TAG_REGEX = /<think>([\s\S]*?)<\/think>/gi;
-
-/**
- * Extract <think> blocks from text content and return separated parts.
- * @returns {{ content: string, thinking: string | null }}
- */
-export function extractThinkingFromContent(text: string): {
-  content: string;
-  thinking: string | null;
-} {
-  if (!text || typeof text !== "string") {
-    return { content: text || "", thinking: null };
-  }
-
-  const thinkingParts: string[] = [];
-  let hasThinkTags = false;
-
-  const cleaned = text.replace(THINK_TAG_REGEX, (_, thinkContent) => {
-    hasThinkTags = true;
-    const trimmed = thinkContent.trim();
-    if (trimmed) {
-      thinkingParts.push(trimmed);
-    }
-    return "";
-  });
-
-  if (!hasThinkTags) {
-    return { content: text, thinking: null };
-  }
-
-  return {
-    content: cleaned.trim(),
-    thinking: thinkingParts.length > 0 ? thinkingParts.join("\n\n") : null,
-  };
-}
-
-/**
- * Sanitize a non-streaming OpenAI ChatCompletion response.
- * Strips non-standard fields and normalizes required fields.
- */
-export function sanitizeOpenAIResponse(body: any): any {
-  if (!body || typeof body !== "object") return body;
-
-  // Build sanitized response with only allowed top-level fields
-  const sanitized: Record<string, any> = {};
-
-  // Ensure required fields exist
-  sanitized.id = normalizeResponseId(body.id);
-  sanitized.object = body.object || "chat.completion";
-  sanitized.created = body.created || Math.floor(Date.now() / 1000);
-  sanitized.model = body.model || "unknown";
-
-  // Sanitize choices
-  if (Array.isArray(body.choices)) {
-    sanitized.choices = body.choices.map((choice: any, idx: number) => sanitizeChoice(choice, idx));
-  } else {
-    sanitized.choices = [];
-  }
-
-  // Sanitize usage
-  if (body.usage && typeof body.usage === "object") {
-    sanitized.usage = sanitizeUsage(body.usage);
-  }
-
-  // Keep system_fingerprint if present (it's a valid OpenAI field)
-  if (body.system_fingerprint) {
-    sanitized.system_fingerprint = body.system_fingerprint;
-  }
-
-  return sanitized;
-}
-
-/**
- * Sanitize a single choice object.
- */
-function sanitizeChoice(choice: any, defaultIndex: number): any {
-  const sanitized: Record<string, any> = {
-    index: choice.index ?? defaultIndex,
-    finish_reason: choice.finish_reason || null,
-  };
-
-  // Sanitize message (non-streaming) or delta (streaming)
-  if (choice.message) {
-    sanitized.message = sanitizeMessage(choice.message);
-  }
-  if (choice.delta) {
-    sanitized.delta = sanitizeMessage(choice.delta);
-  }
-
-  // Keep logprobs if present
-  if (choice.logprobs !== undefined) {
-    sanitized.logprobs = choice.logprobs;
-  }
-
-  return sanitized;
-}
-
-/**
- * Sanitize a message object, extracting <think> tags if present.
- */
-function sanitizeMessage(msg: any): any {
-  if (!msg || typeof msg !== "object") return msg;
-
-  const sanitized: Record<string, any> = {};
-
-  // Copy only allowed fields
-  if (msg.role) sanitized.role = msg.role;
-  if (msg.refusal !== undefined) sanitized.refusal = msg.refusal;
-
-  // Handle content — extract <think> tags
-  if (typeof msg.content === "string") {
-    const { content, thinking } = extractThinkingFromContent(msg.content);
-    sanitized.content = content;
-
-    // Set reasoning_content from <think> tags (if not already set)
-    if (thinking && !msg.reasoning_content) {
-      sanitized.reasoning_content = thinking;
-    }
-  } else if (msg.content !== undefined) {
-    sanitized.content = msg.content;
-  }
-
-  // Preserve existing reasoning_content (from providers that natively support it)
-  if (msg.reasoning_content && !sanitized.reasoning_content) {
-    sanitized.reasoning_content = msg.reasoning_content;
-  }
-
-  // Preserve tool_calls
-  if (msg.tool_calls) {
-    sanitized.tool_calls = msg.tool_calls;
-  }
-
-  // Preserve function_call (legacy)
-  if (msg.function_call) {
-    sanitized.function_call = msg.function_call;
-  }
-
-  return sanitized;
-}
-
-/**
- * Sanitize usage object — keep only standard fields.
- */
-function sanitizeUsage(usage: any): any {
-  if (!usage || typeof usage !== "object") return usage;
-
-  const sanitized: Record<string, any> = {};
-  for (const key of ALLOWED_USAGE_FIELDS) {
-    if (usage[key] !== undefined) {
-      sanitized[key] = usage[key];
-    }
-  }
-
-  // Ensure required fields
-  if (sanitized.prompt_tokens === undefined) sanitized.prompt_tokens = 0;
-  if (sanitized.completion_tokens === undefined) sanitized.completion_tokens = 0;
-  if (sanitized.total_tokens === undefined) {
-    sanitized.total_tokens = sanitized.prompt_tokens + sanitized.completion_tokens;
-  }
-
-  return sanitized;
-}
-
-/**
- * Normalize response ID to use chatcmpl- prefix.
- */
-function normalizeResponseId(id: any): string {
-  if (!id || typeof id !== "string") {
-    return `chatcmpl-${crypto.randomUUID().replace(/-/g, "").slice(0, 29)}`;
-  }
-  // Already correct format
-  if (id.startsWith("chatcmpl-")) return id;
-  // Keep custom IDs but don't break them
-  return id;
-}
-
-/**
- * Sanitize a streaming SSE chunk for passthrough mode.
- * Lighter than full sanitization — only strips problematic extra fields.
- */
-export function sanitizeStreamingChunk(parsed: any): any {
-  if (!parsed || typeof parsed !== "object") return parsed;
-
-  // Build sanitized chunk
-  const sanitized: Record<string, any> = {};
-
-  // Keep only standard fields
-  if (parsed.id !== undefined) sanitized.id = parsed.id;
-  sanitized.object = parsed.object || "chat.completion.chunk";
-  if (parsed.created !== undefined) sanitized.created = parsed.created;
-  if (parsed.model !== undefined) sanitized.model = parsed.model;
-
-  // Sanitize choices with delta
-  if (Array.isArray(parsed.choices)) {
-    sanitized.choices = parsed.choices.map((choice: any) => {
-      const c: Record<string, any> = {
-        index: choice.index ?? 0,
-      };
-      if (choice.delta !== undefined) {
-        c.delta = {};
-        const delta = choice.delta;
-        if (delta.role !== undefined) c.delta.role = delta.role;
-        if (delta.content !== undefined) c.delta.content = delta.content;
-        if (delta.reasoning_content !== undefined)
-          c.delta.reasoning_content = delta.reasoning_content;
-        if (delta.tool_calls !== undefined) c.delta.tool_calls = delta.tool_calls;
-        if (delta.function_call !== undefined) c.delta.function_call = delta.function_call;
-      }
-      if (choice.finish_reason !== undefined) c.finish_reason = choice.finish_reason;
-      if (choice.logprobs !== undefined) c.logprobs = choice.logprobs;
-      return c;
-    });
-  }
-
-  // Sanitize usage if present
-  if (parsed.usage && typeof parsed.usage === "object") {
-    sanitized.usage = sanitizeUsage(parsed.usage);
-  }
-
-  // Keep system_fingerprint if present
-  if (parsed.system_fingerprint) {
-    sanitized.system_fingerprint = parsed.system_fingerprint;
-  }
-
-  return sanitized;
-}

open-sse/handlers/responseTranslator.js

@@ -1,4 +1,4 @@
-import { FORMATS } from "../translator/formats.ts";
+import { FORMATS } from "../translator/formats.js";
 
 /**
  * Translate non-streaming response to OpenAI format
@@ -56,7 +56,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
       }
     }
 
-    const message: Record<string, any> = { role: "assistant" };
+    const message = { role: "assistant" };
     if (textContent) {
       message.content = textContent;
     }
@@ -74,7 +74,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
     const model = response?.model || responseBody?.model || "openai-responses";
     const finishReason = toolCalls.length > 0 ? "tool_calls" : "stop";
 
-    const result: Record<string, any> = {
+    const result = {
       id: `chatcmpl-${response?.id || Date.now()}`,
       object: "chat.completion",
       created: createdAt,
@@ -162,7 +162,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
     }
 
     // Build OpenAI format message
-    const message: Record<string, any> = { role: "assistant" };
+    const message = { role: "assistant" };
     if (textContent) {
       message.content = textContent;
     }
@@ -183,7 +183,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
       finishReason = "tool_calls";
     }
 
-    const result: Record<string, any> = {
+    const result = {
       id: `chatcmpl-${response.responseId || Date.now()}`,
       object: "chat.completion",
       created: Math.floor(new Date(response.createTime || Date.now()).getTime() / 1000),
@@ -241,7 +241,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
       }
     }
 
-    const message: Record<string, any> = { role: "assistant" };
+    const message = { role: "assistant" };
     if (textContent) {
       message.content = textContent;
     }
@@ -259,7 +259,7 @@ export function translateNonStreamingResponse(responseBody, targetFormat, source
     if (finishReason === "end_turn") finishReason = "stop";
     if (finishReason === "tool_use") finishReason = "tool_calls";
 
-    const result: Record<string, any> = {
+    const result = {
       id: `chatcmpl-${responseBody.id || Date.now()}`,
       object: "chat.completion",
       created: Math.floor(Date.now() / 1000),

open-sse/handlers/responsesHandler.js

@@ -1,12 +1,11 @@
-import { getCorsOrigin } from "../utils/cors.ts";
 /**
  * Responses API Handler for Workers
  * Converts Chat Completions to Codex Responses API format
  */
 
-import { handleChatCore } from "./chatCore.ts";
-import { convertResponsesApiFormat } from "../translator/helpers/responsesApiHelper.ts";
-import { createResponsesApiTransformStream } from "../transformer/responsesTransformer.ts";
+import { handleChatCore } from "./chatCore.js";
+import { convertResponsesApiFormat } from "../translator/helpers/responsesApiHelper.js";
+import { createResponsesApiTransformStream } from "../transformer/responsesTransformer.js";
 
 /**
  * Handle /v1/responses request
@@ -46,11 +45,8 @@ export async function handleResponsesCore({
     onCredentialsRefreshed,
     onRequestSuccess,
     onDisconnect,
-    clientRawRequest: null,
     connectionId,
-    userAgent: null,
-    comboName: null,
-  } as any);
+  });
 
   if (!result.success || !result.response) {
     return result;
@@ -76,7 +72,7 @@ export async function handleResponsesCore({
         "Content-Type": "text/event-stream",
         "Cache-Control": "no-cache",
         Connection: "keep-alive",
-        "Access-Control-Allow-Origin": getCorsOrigin(),
+        "Access-Control-Allow-Origin": "*",
       },
     }),
   };

open-sse/handlers/sseParser.js

@@ -44,14 +44,15 @@ export function parseSSEToOpenAIResponse(rawSSE, fallbackModel) {
     }
   }
 
-  const message: Record<string, any> = { role: "assistant",
+  const message = {
+    role: "assistant",
     content: contentParts.join(""),
   };
   if (reasoningParts.length > 0) {
     message.reasoning_content = reasoningParts.join("");
   }
 
-  const result: Record<string, any> = {
+  const result = {
     id: first.id || `chatcmpl-${Date.now()}`,
     object: "chat.completion",
     created: first.created || Math.floor(Date.now() / 1000),

open-sse/index.js

@@ -1,5 +1,5 @@
 // Patch global fetch with proxy support (must be first)
-import "./utils/proxyFetch.ts";
+import "./utils/proxyFetch.js";
 
 // Config
 export {
@@ -10,7 +10,7 @@ export {
   CLAUDE_SYSTEM_PROMPT,
   COOLDOWN_MS,
   BACKOFF_CONFIG,
-} from "./config/constants.ts";
+} from "./config/constants.js";
 export {
   PROVIDER_MODELS,
   getProviderModels,
@@ -20,10 +20,10 @@ export {
   getModelTargetFormat,
   PROVIDER_ID_TO_ALIAS,
   getModelsByProviderId,
-} from "./config/providerModels.ts";
+} from "./config/providerModels.js";
 
 // Translator
-export { FORMATS } from "./translator/formats.ts";
+export { FORMATS } from "./translator/formats.js";
 export {
   register,
   translateRequest,
@@ -31,7 +31,7 @@ export {
   needsTranslation,
   initState,
   initTranslators,
-} from "./translator/index.ts";
+} from "./translator/index.js";
 
 // Services
 export {
@@ -40,16 +40,16 @@ export {
   buildProviderUrl,
   buildProviderHeaders,
   getTargetFormat,
-} from "./services/provider.ts";
+} from "./services/provider.js";
 
-export { parseModel, resolveModelAliasFromMap, getModelInfoCore } from "./services/model.ts";
+export { parseModel, resolveModelAliasFromMap, getModelInfoCore } from "./services/model.js";
 
 export {
   checkFallbackError,
   isAccountUnavailable,
   getUnavailableUntil,
   filterAvailableAccounts,
-} from "./services/accountFallback.ts";
+} from "./services/accountFallback.js";
 
 export {
   TOKEN_EXPIRY_BUFFER_MS,
@@ -63,43 +63,43 @@ export {
   refreshCopilotToken,
   getAccessToken,
   refreshTokenByProvider,
-} from "./services/tokenRefresh.ts";
+} from "./services/tokenRefresh.js";
 
 // Handlers
-export { handleChatCore, isTokenExpiringSoon } from "./handlers/chatCore.ts";
+export { handleChatCore, isTokenExpiringSoon } from "./handlers/chatCore.js";
 export {
   createStreamController,
   pipeWithDisconnect,
   createDisconnectAwareStream,
-} from "./utils/streamHandler.ts";
+} from "./utils/streamHandler.js";
 
 // Executors
-export { getExecutor, hasSpecializedExecutor } from "./executors/index.ts";
+export { getExecutor, hasSpecializedExecutor } from "./executors/index.js";
 
 // Utils
-export { errorResponse, formatProviderError } from "./utils/error.ts";
+export { errorResponse, formatProviderError } from "./utils/error.js";
 export {
   createSSETransformStreamWithLogger,
   createPassthroughStreamWithLogger,
-} from "./utils/stream.ts";
+} from "./utils/stream.js";
 
 // Embeddings
-export { handleEmbedding } from "./handlers/embeddings.ts";
+export { handleEmbedding } from "./handlers/embeddings.js";
 export {
   EMBEDDING_PROVIDERS,
   getEmbeddingProvider,
   parseEmbeddingModel,
   getAllEmbeddingModels,
-} from "./config/embeddingRegistry.ts";
+} from "./config/embeddingRegistry.js";
 
 // Image Generation
-export { handleImageGeneration } from "./handlers/imageGeneration.ts";
+export { handleImageGeneration } from "./handlers/imageGeneration.js";
 export {
   IMAGE_PROVIDERS,
   getImageProvider,
   parseImageModel,
   getAllImageModels,
-} from "./config/imageRegistry.ts";
+} from "./config/imageRegistry.js";
 
 // Think Tag Parser
 export {
@@ -107,20 +107,20 @@ export {
   extractThinkTags,
   processStreamingThinkDelta,
   flushThinkBuffer,
-} from "./utils/thinkTagParser.ts";
+} from "./utils/thinkTagParser.js";
 
 // Rerank
-export { handleRerank } from "./handlers/rerank.ts";
+export { handleRerank } from "./handlers/rerank.js";
 export {
   RERANK_PROVIDERS,
   getRerankProvider,
   parseRerankModel,
   getAllRerankModels,
-} from "./config/rerankRegistry.ts";
+} from "./config/rerankRegistry.js";
 
 // Audio (Transcription + Speech)
-export { handleAudioTranscription } from "./handlers/audioTranscription.ts";
-export { handleAudioSpeech } from "./handlers/audioSpeech.ts";
+export { handleAudioTranscription } from "./handlers/audioTranscription.js";
+export { handleAudioSpeech } from "./handlers/audioSpeech.js";
 export {
   AUDIO_TRANSCRIPTION_PROVIDERS,
   AUDIO_SPEECH_PROVIDERS,
@@ -129,13 +129,13 @@ export {
   parseTranscriptionModel,
   parseSpeechModel,
   getAllAudioModels,
-} from "./config/audioRegistry.ts";
+} from "./config/audioRegistry.js";
 
 // Moderations
-export { handleModeration } from "./handlers/moderations.ts";
+export { handleModeration } from "./handlers/moderations.js";
 export {
   MODERATION_PROVIDERS,
   getModerationProvider,
   parseModerationModel,
   getAllModerationModels,
-} from "./config/moderationRegistry.ts";
+} from "./config/moderationRegistry.js";

open-sse/services/accountFallback.js

@@ -0,0 +1,201 @@
+import { COOLDOWN_MS, BACKOFF_CONFIG, HTTP_STATUS } from "../config/constants.js";
+
+/**
+ * Calculate exponential backoff cooldown for rate limits (429)
+ * Level 0: 1s, Level 1: 2s, Level 2: 4s... → max 2 min
+ * @param {number} backoffLevel - Current backoff level
+ * @returns {number} Cooldown in milliseconds
+ */
+export function getQuotaCooldown(backoffLevel = 0) {
+  const cooldown = BACKOFF_CONFIG.base * Math.pow(2, backoffLevel);
+  return Math.min(cooldown, BACKOFF_CONFIG.max);
+}
+
+/**
+ * Check if error should trigger account fallback (switch to next account)
+ * @param {number} status - HTTP status code
+ * @param {string} errorText - Error message text
+ * @param {number} backoffLevel - Current backoff level for exponential backoff
+ * @returns {{ shouldFallback: boolean, cooldownMs: number, newBackoffLevel?: number }}
+ */
+export function checkFallbackError(status, errorText, backoffLevel = 0) {
+  // Check error message FIRST - specific patterns take priority over status codes
+  if (errorText) {
+    const errorStr = typeof errorText === "string" ? errorText : JSON.stringify(errorText);
+    const lowerError = errorStr.toLowerCase();
+
+    if (lowerError.includes("no credentials")) {
+      return { shouldFallback: true, cooldownMs: COOLDOWN_MS.notFound };
+    }
+
+    if (lowerError.includes("request not allowed")) {
+      return { shouldFallback: true, cooldownMs: COOLDOWN_MS.requestNotAllowed };
+    }
+
+    // Rate limit keywords - exponential backoff
+    if (
+      lowerError.includes("rate limit") ||
+      lowerError.includes("too many requests") ||
+      lowerError.includes("quota exceeded") ||
+      lowerError.includes("capacity") ||
+      lowerError.includes("overloaded")
+    ) {
+      const newLevel = Math.min(backoffLevel + 1, BACKOFF_CONFIG.maxLevel);
+      return {
+        shouldFallback: true,
+        cooldownMs: getQuotaCooldown(backoffLevel),
+        newBackoffLevel: newLevel,
+      };
+    }
+  }
+
+  if (status === HTTP_STATUS.UNAUTHORIZED) {
+    return { shouldFallback: true, cooldownMs: COOLDOWN_MS.unauthorized };
+  }
+
+  if (status === HTTP_STATUS.PAYMENT_REQUIRED || status === HTTP_STATUS.FORBIDDEN) {
+    return { shouldFallback: true, cooldownMs: COOLDOWN_MS.paymentRequired };
+  }
+
+  if (status === HTTP_STATUS.NOT_FOUND) {
+    return { shouldFallback: true, cooldownMs: COOLDOWN_MS.notFound };
+  }
+
+  // 429 - Rate limit with exponential backoff
+  if (status === HTTP_STATUS.RATE_LIMITED) {
+    const newLevel = Math.min(backoffLevel + 1, BACKOFF_CONFIG.maxLevel);
+    return {
+      shouldFallback: true,
+      cooldownMs: getQuotaCooldown(backoffLevel),
+      newBackoffLevel: newLevel,
+    };
+  }
+
+  // Transient errors
+  const transientStatuses = [
+    HTTP_STATUS.NOT_ACCEPTABLE,
+    HTTP_STATUS.REQUEST_TIMEOUT,
+    HTTP_STATUS.SERVER_ERROR,
+    HTTP_STATUS.BAD_GATEWAY,
+    HTTP_STATUS.SERVICE_UNAVAILABLE,
+    HTTP_STATUS.GATEWAY_TIMEOUT,
+  ];
+  if (transientStatuses.includes(status)) {
+    return { shouldFallback: true, cooldownMs: COOLDOWN_MS.transient };
+  }
+
+  // 400 Bad Request - don't fallback (same request will fail on all accounts)
+  if (status === HTTP_STATUS.BAD_REQUEST) {
+    return { shouldFallback: false, cooldownMs: 0 };
+  }
+
+  // All other errors - fallback with transient cooldown
+  return { shouldFallback: true, cooldownMs: COOLDOWN_MS.transient };
+}
+
+/**
+ * Check if account is currently unavailable (cooldown not expired)
+ */
+export function isAccountUnavailable(unavailableUntil) {
+  if (!unavailableUntil) return false;
+  return new Date(unavailableUntil).getTime() > Date.now();
+}
+
+/**
+ * Calculate unavailable until timestamp
+ */
+export function getUnavailableUntil(cooldownMs) {
+  return new Date(Date.now() + cooldownMs).toISOString();
+}
+
+/**
+ * Get the earliest rateLimitedUntil from a list of accounts
+ * @param {Array} accounts - Array of account objects with rateLimitedUntil
+ * @returns {string|null} Earliest rateLimitedUntil ISO string, or null
+ */
+export function getEarliestRateLimitedUntil(accounts) {
+  let earliest = null;
+  const now = Date.now();
+  for (const acc of accounts) {
+    if (!acc.rateLimitedUntil) continue;
+    const until = new Date(acc.rateLimitedUntil).getTime();
+    if (until <= now) continue;
+    if (!earliest || until < earliest) earliest = until;
+  }
+  if (!earliest) return null;
+  return new Date(earliest).toISOString();
+}
+
+/**
+ * Format rateLimitedUntil to human-readable "reset after Xm Ys"
+ * @param {string} rateLimitedUntil - ISO timestamp
+ * @returns {string} e.g. "reset after 2m 30s"
+ */
+export function formatRetryAfter(rateLimitedUntil) {
+  if (!rateLimitedUntil) return "";
+  const diffMs = new Date(rateLimitedUntil).getTime() - Date.now();
+  if (diffMs <= 0) return "reset after 0s";
+  const totalSec = Math.ceil(diffMs / 1000);
+  const h = Math.floor(totalSec / 3600);
+  const m = Math.floor((totalSec % 3600) / 60);
+  const s = totalSec % 60;
+  const parts = [];
+  if (h > 0) parts.push(`${h}h`);
+  if (m > 0) parts.push(`${m}m`);
+  if (s > 0 || parts.length === 0) parts.push(`${s}s`);
+  return `reset after ${parts.join(" ")}`;
+}
+
+/**
+ * Filter available accounts (not in cooldown)
+ */
+export function filterAvailableAccounts(accounts, excludeId = null) {
+  const now = Date.now();
+  return accounts.filter((acc) => {
+    if (excludeId && acc.id === excludeId) return false;
+    if (acc.rateLimitedUntil) {
+      const until = new Date(acc.rateLimitedUntil).getTime();
+      if (until > now) return false;
+    }
+    return true;
+  });
+}
+
+/**
+ * Reset account state when request succeeds
+ * Clears cooldown and resets backoff level to 0
+ * @param {object} account - Account object
+ * @returns {object} Updated account with reset state
+ */
+export function resetAccountState(account) {
+  if (!account) return account;
+  return {
+    ...account,
+    rateLimitedUntil: null,
+    backoffLevel: 0,
+    lastError: null,
+    status: "active",
+  };
+}
+
+/**
+ * Apply error state to account
+ * @param {object} account - Account object
+ * @param {number} status - HTTP status code
+ * @param {string} errorText - Error message
+ * @returns {object} Updated account with error state
+ */
+export function applyErrorState(account, status, errorText) {
+  if (!account) return account;
+
+  const backoffLevel = account.backoffLevel || 0;
+  const { cooldownMs, newBackoffLevel } = checkFallbackError(status, errorText, backoffLevel);
+
+  return {
+    ...account,
+    rateLimitedUntil: cooldownMs > 0 ? getUnavailableUntil(cooldownMs) : null,
+    backoffLevel: newBackoffLevel ?? backoffLevel,
+    lastError: { status, message: errorText, timestamp: new Date().toISOString() },
+    status: "error",
+  };
+}

open-sse/services/accountFallback.ts

@@ -1,514 +0,0 @@
-import {
-  COOLDOWN_MS,
-  BACKOFF_CONFIG,
-  BACKOFF_STEPS_MS,
-  RateLimitReason,
-  HTTP_STATUS,
-  PROVIDER_PROFILES,
-} from "../config/constants.ts";
-import { getProviderCategory } from "../config/providerRegistry.ts";
-
-// ─── Provider Profile Helper ────────────────────────────────────────────────
-
-/**
- * Get the resilience profile for a provider (oauth or apikey).
- * @param {string} provider - Provider ID or alias
- * @returns {import('../config/constants.js').PROVIDER_PROFILES['oauth']}
- */
-export function getProviderProfile(provider) {
-  const category = getProviderCategory(provider);
-  return PROVIDER_PROFILES[category] ?? PROVIDER_PROFILES.apikey;
-}
-
-// ─── Per-Model Lockout Tracking ─────────────────────────────────────────────
-// 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);
-  }
-}, 15_000);
-_cleanupTimer.unref(); // Don't prevent process exit
-
-/**
- * Lock a specific model on a specific account
- * @param {string} provider
- * @param {string} connectionId
- * @param {string} model
- * @param {string} reason - from RateLimitReason
- * @param {number} cooldownMs
- */
-export function lockModel(provider, connectionId, model, reason, cooldownMs) {
-  if (!model) return; // No model → skip model-level locking
-  const key = `${provider}:${connectionId}:${model}`;
-  modelLockouts.set(key, {
-    reason,
-    until: Date.now() + cooldownMs,
-    lockedAt: Date.now(),
-  });
-}
-
-/**
- * Check if a specific model on a specific account is locked
- * @returns {boolean}
- */
-export function isModelLocked(provider, connectionId, model) {
-  if (!model) return false;
-  const key = `${provider}:${connectionId}:${model}`;
-  const entry = modelLockouts.get(key);
-  if (!entry) return false;
-  if (Date.now() > entry.until) {
-    modelLockouts.delete(key);
-    return false;
-  }
-  return true;
-}
-
-/**
- * Get model lockout info (for debugging/dashboard)
- */
-export function getModelLockoutInfo(provider, connectionId, model) {
-  if (!model) return null;
-  const key = `${provider}:${connectionId}:${model}`;
-  const entry = modelLockouts.get(key);
-  if (!entry || Date.now() > entry.until) return null;
-  return {
-    reason: entry.reason,
-    remainingMs: entry.until - Date.now(),
-    lockedAt: new Date(entry.lockedAt).toISOString(),
-  };
-}
-
-/**
- * Get all active model lockouts (for dashboard)
- */
-export function getAllModelLockouts() {
-  const now = Date.now();
-  const active = [];
-  for (const [key, entry] of modelLockouts) {
-    if (now <= entry.until) {
-      const [provider, connectionId, model] = key.split(":");
-      active.push({
-        provider,
-        connectionId,
-        model,
-        reason: entry.reason,
-        remainingMs: entry.until - now,
-      });
-    }
-  }
-  return active;
-}
-
-// ─── Retry-After Parsing ────────────────────────────────────────────────────
-
-/**
- * Parse retry-after information from JSON error response bodies.
- * Providers embed retry info in different formats.
- *
- * @param {string|object} responseBody - Raw response body or parsed JSON
- * @returns {{ retryAfterMs: number|null, reason: string }}
- */
-export function parseRetryAfterFromBody(responseBody) {
-  let body;
-  try {
-    body = typeof responseBody === "string" ? JSON.parse(responseBody) : responseBody;
-  } catch {
-    return { retryAfterMs: null, reason: RateLimitReason.UNKNOWN };
-  }
-
-  if (!body) return { retryAfterMs: null, reason: RateLimitReason.UNKNOWN };
-
-  // Gemini: { error: { details: [{ retryDelay: "33s" }] } }
-  const details = body.error?.details || body.details || [];
-  for (const detail of Array.isArray(details) ? details : []) {
-    if (detail.retryDelay) {
-      return {
-        retryAfterMs: parseDelayString(detail.retryDelay),
-        reason: RateLimitReason.RATE_LIMIT_EXCEEDED,
-      };
-    }
-  }
-
-  // OpenAI: "Please retry after 20s" in message
-  const msg = body.error?.message || body.message || "";
-  const retryMatch = msg.match(/retry\s+after\s+(\d+)\s*s/i);
-  if (retryMatch) {
-    return {
-      retryAfterMs: parseInt(retryMatch[1], 10) * 1000,
-      reason: RateLimitReason.RATE_LIMIT_EXCEEDED,
-    };
-  }
-
-  // Anthropic: error type classification
-  const errorType = body.error?.type || body.type || "";
-  if (errorType === "rate_limit_error") {
-    return { retryAfterMs: null, reason: RateLimitReason.RATE_LIMIT_EXCEEDED };
-  }
-
-  // Classify by error message keywords
-  const reason = classifyErrorText(msg || errorType);
-  return { retryAfterMs: null, reason };
-}
-
-/**
- * Parse delay strings like "33s", "2m", "1h", "1500ms"
- */
-function parseDelayString(value) {
-  if (!value) return null;
-  const str = String(value).trim();
-  const msMatch = str.match(/^(\d+)\s*ms$/i);
-  if (msMatch) return parseInt(msMatch[1], 10);
-  const secMatch = str.match(/^(\d+)\s*s$/i);
-  if (secMatch) return parseInt(secMatch[1], 10) * 1000;
-  const minMatch = str.match(/^(\d+)\s*m$/i);
-  if (minMatch) return parseInt(minMatch[1], 10) * 60 * 1000;
-  const hrMatch = str.match(/^(\d+)\s*h$/i);
-  if (hrMatch) return parseInt(hrMatch[1], 10) * 3600 * 1000;
-  // Bare number → seconds
-  const num = parseInt(str, 10);
-  return isNaN(num) ? null : num * 1000;
-}
-
-// ─── Error Classification ───────────────────────────────────────────────────
-
-/**
- * Classify error text into RateLimitReason
- */
-export function classifyErrorText(errorText) {
-  if (!errorText) return RateLimitReason.UNKNOWN;
-  const lower = String(errorText).toLowerCase();
-
-  if (
-    lower.includes("quota exceeded") ||
-    lower.includes("quota depleted") ||
-    lower.includes("billing")
-  ) {
-    return RateLimitReason.QUOTA_EXHAUSTED;
-  }
-  if (
-    lower.includes("rate limit") ||
-    lower.includes("too many requests") ||
-    lower.includes("rate_limit")
-  ) {
-    return RateLimitReason.RATE_LIMIT_EXCEEDED;
-  }
-  if (
-    lower.includes("capacity") ||
-    lower.includes("overloaded") ||
-    lower.includes("resource exhausted")
-  ) {
-    return RateLimitReason.MODEL_CAPACITY;
-  }
-  if (
-    lower.includes("unauthorized") ||
-    lower.includes("invalid api key") ||
-    lower.includes("authentication")
-  ) {
-    return RateLimitReason.AUTH_ERROR;
-  }
-  if (lower.includes("server error") || lower.includes("internal error")) {
-    return RateLimitReason.SERVER_ERROR;
-  }
-  return RateLimitReason.UNKNOWN;
-}
-
-/**
- * Classify HTTP status + error text into RateLimitReason
- */
-export function classifyError(status, errorText) {
-  // Text classification takes priority (more specific)
-  const textReason = classifyErrorText(errorText);
-  if (textReason !== RateLimitReason.UNKNOWN) return textReason;
-
-  // Fall back to status code
-  if (status === HTTP_STATUS.UNAUTHORIZED || status === HTTP_STATUS.FORBIDDEN) {
-    return RateLimitReason.AUTH_ERROR;
-  }
-  if (status === HTTP_STATUS.PAYMENT_REQUIRED) {
-    return RateLimitReason.QUOTA_EXHAUSTED;
-  }
-  if (status === HTTP_STATUS.RATE_LIMITED) {
-    return RateLimitReason.RATE_LIMIT_EXCEEDED;
-  }
-  if (status === HTTP_STATUS.SERVICE_UNAVAILABLE || status === 529) {
-    return RateLimitReason.MODEL_CAPACITY;
-  }
-  if (status >= 500) {
-    return RateLimitReason.SERVER_ERROR;
-  }
-  return RateLimitReason.UNKNOWN;
-}
-
-// ─── Configurable Backoff ───────────────────────────────────────────────────
-
-/**
- * Get backoff duration from configurable steps.
- * @param {number} failureCount - Number of consecutive failures
- * @returns {number} Duration in ms
- */
-export function getBackoffDuration(failureCount) {
-  const idx = Math.min(failureCount, BACKOFF_STEPS_MS.length - 1);
-  return BACKOFF_STEPS_MS[idx];
-}
-
-// ─── Original API (Backward Compatible) ────────────────────────────────────
-
-/**
- * Calculate exponential backoff cooldown for rate limits (429)
- * Level 0: 1s, Level 1: 2s, Level 2: 4s... → max 2 min
- * @param {number} backoffLevel - Current backoff level
- * @returns {number} Cooldown in milliseconds
- */
-export function getQuotaCooldown(backoffLevel = 0) {
-  const cooldown = BACKOFF_CONFIG.base * Math.pow(2, backoffLevel);
-  return Math.min(cooldown, BACKOFF_CONFIG.max);
-}
-
-/**
- * Check if error should trigger account fallback (switch to next account)
- * @param {number} status - HTTP status code
- * @param {string} errorText - Error message text
- * @param {number} backoffLevel - Current backoff level for exponential backoff
- * @param {string} [model] - Optional model name for model-level lockout
- * @param {string} [provider] - Provider ID for profile-aware cooldowns
- * @returns {{ shouldFallback: boolean, cooldownMs: number, newBackoffLevel?: number, reason?: string }}
- */
-export function checkFallbackError(
-  status,
-  errorText,
-  backoffLevel = 0,
-  model = null,
-  provider = null
-) {
-  // Check error message FIRST - specific patterns take priority over status codes
-  if (errorText) {
-    const errorStr = typeof errorText === "string" ? errorText : JSON.stringify(errorText);
-    const lowerError = errorStr.toLowerCase();
-
-    if (lowerError.includes("no credentials")) {
-      return {
-        shouldFallback: true,
-        cooldownMs: COOLDOWN_MS.notFound,
-        reason: RateLimitReason.AUTH_ERROR,
-      };
-    }
-
-    if (lowerError.includes("request not allowed")) {
-      return {
-        shouldFallback: true,
-        cooldownMs: COOLDOWN_MS.requestNotAllowed,
-        reason: RateLimitReason.RATE_LIMIT_EXCEEDED,
-      };
-    }
-
-    // Rate limit keywords - exponential backoff
-    if (
-      lowerError.includes("rate limit") ||
-      lowerError.includes("too many requests") ||
-      lowerError.includes("quota exceeded") ||
-      lowerError.includes("capacity") ||
-      lowerError.includes("overloaded")
-    ) {
-      const newLevel = Math.min(backoffLevel + 1, BACKOFF_CONFIG.maxLevel);
-      const reason = classifyErrorText(errorStr);
-      return {
-        shouldFallback: true,
-        cooldownMs: getQuotaCooldown(backoffLevel),
-        newBackoffLevel: newLevel,
-        reason,
-      };
-    }
-  }
-
-  if (status === HTTP_STATUS.UNAUTHORIZED) {
-    return {
-      shouldFallback: true,
-      cooldownMs: COOLDOWN_MS.unauthorized,
-      reason: RateLimitReason.AUTH_ERROR,
-    };
-  }
-
-  if (status === HTTP_STATUS.PAYMENT_REQUIRED || status === HTTP_STATUS.FORBIDDEN) {
-    return {
-      shouldFallback: true,
-      cooldownMs: COOLDOWN_MS.paymentRequired,
-      reason: RateLimitReason.QUOTA_EXHAUSTED,
-    };
-  }
-
-  if (status === HTTP_STATUS.NOT_FOUND) {
-    return {
-      shouldFallback: true,
-      cooldownMs: COOLDOWN_MS.notFound,
-      reason: RateLimitReason.UNKNOWN,
-    };
-  }
-
-  // 429 - Rate limit with exponential backoff
-  if (status === HTTP_STATUS.RATE_LIMITED) {
-    const newLevel = Math.min(backoffLevel + 1, BACKOFF_CONFIG.maxLevel);
-    return {
-      shouldFallback: true,
-      cooldownMs: getQuotaCooldown(backoffLevel),
-      newBackoffLevel: newLevel,
-      reason: RateLimitReason.RATE_LIMIT_EXCEEDED,
-    };
-  }
-
-  // Transient / server errors — exponential backoff with provider profile
-  const transientStatuses = [
-    HTTP_STATUS.NOT_ACCEPTABLE,
-    HTTP_STATUS.REQUEST_TIMEOUT,
-    HTTP_STATUS.SERVER_ERROR,
-    HTTP_STATUS.BAD_GATEWAY,
-    HTTP_STATUS.SERVICE_UNAVAILABLE,
-    HTTP_STATUS.GATEWAY_TIMEOUT,
-  ];
-  if (transientStatuses.includes(status)) {
-    const profile = provider ? getProviderProfile(provider) : null;
-    const baseCooldown = profile?.transientCooldown ?? COOLDOWN_MS.transientInitial;
-    const maxLevel = profile?.maxBackoffLevel ?? BACKOFF_CONFIG.maxLevel;
-    const cooldownMs = Math.min(baseCooldown * Math.pow(2, backoffLevel), COOLDOWN_MS.transientMax);
-    const newLevel = Math.min(backoffLevel + 1, maxLevel);
-    return {
-      shouldFallback: true,
-      cooldownMs,
-      newBackoffLevel: newLevel,
-      reason: RateLimitReason.SERVER_ERROR,
-    };
-  }
-
-  // 400 Bad Request - don't fallback (same request will fail on all accounts)
-  if (status === HTTP_STATUS.BAD_REQUEST) {
-    return { shouldFallback: false, cooldownMs: 0, reason: RateLimitReason.UNKNOWN };
-  }
-
-  // All other errors - fallback with transient cooldown
-  return {
-    shouldFallback: true,
-    cooldownMs: COOLDOWN_MS.transient,
-    reason: RateLimitReason.UNKNOWN,
-  };
-}
-
-// ─── Account State Management ───────────────────────────────────────────────
-
-/**
- * Check if account is currently unavailable (cooldown not expired)
- */
-export function isAccountUnavailable(unavailableUntil) {
-  if (!unavailableUntil) return false;
-  return new Date(unavailableUntil).getTime() > Date.now();
-}
-
-/**
- * Calculate unavailable until timestamp
- */
-export function getUnavailableUntil(cooldownMs) {
-  return new Date(Date.now() + cooldownMs).toISOString();
-}
-
-/**
- * Get the earliest rateLimitedUntil from a list of accounts
- */
-export function getEarliestRateLimitedUntil(accounts) {
-  let earliest = null;
-  const now = Date.now();
-  for (const acc of accounts) {
-    if (!acc.rateLimitedUntil) continue;
-    const until = new Date(acc.rateLimitedUntil).getTime();
-    if (until <= now) continue;
-    if (!earliest || until < earliest) earliest = until;
-  }
-  if (!earliest) return null;
-  return new Date(earliest).toISOString();
-}
-
-/**
- * Format rateLimitedUntil to human-readable "reset after Xm Ys"
- */
-export function formatRetryAfter(rateLimitedUntil) {
-  if (!rateLimitedUntil) return "";
-  const diffMs = new Date(rateLimitedUntil).getTime() - Date.now();
-  if (diffMs <= 0) return "reset after 0s";
-  const totalSec = Math.ceil(diffMs / 1000);
-  const h = Math.floor(totalSec / 3600);
-  const m = Math.floor((totalSec % 3600) / 60);
-  const s = totalSec % 60;
-  const parts = [];
-  if (h > 0) parts.push(`${h}h`);
-  if (m > 0) parts.push(`${m}m`);
-  if (s > 0 || parts.length === 0) parts.push(`${s}s`);
-  return `reset after ${parts.join(" ")}`;
-}
-
-/**
- * Filter available accounts (not in cooldown)
- */
-export function filterAvailableAccounts(accounts, excludeId = null) {
-  const now = Date.now();
-  return accounts.filter((acc) => {
-    if (excludeId && acc.id === excludeId) return false;
-    if (acc.rateLimitedUntil) {
-      const until = new Date(acc.rateLimitedUntil).getTime();
-      if (until > now) return false;
-    }
-    return true;
-  });
-}
-
-/**
- * Reset account state when request succeeds
- */
-export function resetAccountState(account) {
-  if (!account) return account;
-  return {
-    ...account,
-    rateLimitedUntil: null,
-    backoffLevel: 0,
-    lastError: null,
-    status: "active",
-  };
-}
-
-/**
- * Apply error state to account
- */
-export function applyErrorState(account, status, errorText, provider = null) {
-  if (!account) return account;
-
-  const backoffLevel = account.backoffLevel || 0;
-  const { cooldownMs, newBackoffLevel, reason } = checkFallbackError(
-    status,
-    errorText,
-    backoffLevel,
-    null,
-    provider
-  );
-
-  return {
-    ...account,
-    rateLimitedUntil: cooldownMs > 0 ? getUnavailableUntil(cooldownMs) : null,
-    backoffLevel: newBackoffLevel ?? backoffLevel,
-    lastError: { status, message: errorText, timestamp: new Date().toISOString(), reason },
-    status: "error",
-  };
-}
-
-/**
- * Get account health score (0-100) for P2C selection (Phase 9)
- * @param {object} account
- * @returns {number} score 0 = unhealthy, 100 = perfectly healthy
- */
-export function getAccountHealth(account, model?: any) {
-  if (!account) return 0;
-  let score = 100;
-  score -= (account.backoffLevel || 0) * 10;
-  if (account.lastError) score -= 20;
-  if (account.rateLimitedUntil && isAccountUnavailable(account.rateLimitedUntil)) score -= 30;
-  return Math.max(0, score);
-}

open-sse/services/accountSelector.ts

@@ -1,74 +0,0 @@
-/**
- * Quota-Aware Account Selection (P2C) — Phase 9
- *
- * Power of Two Choices: pick 2 random accounts, select the healthier one.
- * Uses account health scores from accountFallback.js.
- */
-
-import { getAccountHealth } from "./accountFallback.ts";
-
-/**
- * P2C selection: pick 2 random candidates, return the healthier one.
- * Falls back to random if only 1 candidate.
- *
- * @param {Array} accounts - Available account objects
- * @param {string} [model] - Model name (for model-specific health check)
- * @returns {object|null} Selected account
- */
-export function selectAccountP2C(accounts, model = null) {
-  if (!accounts || accounts.length === 0) return null;
-  if (accounts.length === 1) return accounts[0];
-
-  // Pick 2 random distinct indices
-  const i = Math.floor(Math.random() * accounts.length);
-  let j = Math.floor(Math.random() * (accounts.length - 1));
-  if (j >= i) j++; // Ensure distinct
-
-  const a = accounts[i];
-  const b = accounts[j];
-
-  const healthA = getAccountHealth(a, model);
-  const healthB = getAccountHealth(b, model);
-
-  return healthA >= healthB ? a : b;
-}
-
-/**
- * Select account with strategy support.
- * Integrates P2C as a new strategy alongside existing fill-first and round-robin.
- *
- * @param {Array} accounts - Available accounts
- * @param {string} strategy - "fill-first" | "round-robin" | "p2c" | "random"
- * @param {object} [state] - Strategy state (e.g., lastIndex for round-robin)
- * @param {string} [model] - Model name
- * @returns {{ account: object|null, state: object }}
- */
-export function selectAccount(accounts, strategy = "fill-first", state: any = {}, model = null) {
-  if (!accounts || accounts.length === 0) {
-    return { account: null, state };
-  }
-
-  switch (strategy) {
-    case "p2c":
-      return { account: selectAccountP2C(accounts, model), state };
-
-    case "random":
-      return {
-        account: accounts[Math.floor(Math.random() * accounts.length)],
-        state,
-      };
-
-    case "round-robin": {
-      const lastIndex = state.lastIndex ?? -1;
-      const nextIndex = (lastIndex + 1) % accounts.length;
-      return {
-        account: accounts[nextIndex],
-        state: { ...state, lastIndex: nextIndex },
-      };
-    }
-
-    case "fill-first":
-    default:
-      return { account: accounts[0], state };
-  }
-}

open-sse/services/combo.js

@@ -1,18 +1,13 @@
 /**
  * Shared combo (model combo) handling with fallback support
- * Supports: priority, weighted, round-robin, random, least-used, and cost-optimized strategies
+ * Supports: priority (sequential), weighted (probabilistic), and round-robin (circular) strategies
  */
 
-import { checkFallbackError, formatRetryAfter, getProviderProfile } from "./accountFallback.ts";
-import { unavailableResponse } from "../utils/error.ts";
-import { recordComboRequest, getComboMetrics } from "./comboMetrics.ts";
-import { resolveComboConfig, getDefaultComboConfig } from "./comboConfig.ts";
-import * as semaphore from "./rateLimitSemaphore.ts";
-import { getCircuitBreaker } from "../../src/shared/utils/circuitBreaker";
-import { parseModel } from "./model.ts";
-
-// Status codes that should mark semaphore + record circuit breaker failures
-const TRANSIENT_FOR_BREAKER = [429, 502, 503, 504];
+import { checkFallbackError, formatRetryAfter } from "./accountFallback.js";
+import { unavailableResponse } from "../utils/error.js";
+import { recordComboRequest } from "./comboMetrics.js";
+import { resolveComboConfig, getDefaultComboConfig } from "./comboConfig.js";
+import * as semaphore from "./rateLimitSemaphore.js";
 
 const MAX_COMBO_DEPTH = 3;
 
@@ -150,69 +145,9 @@ function orderModelsForWeightedFallback(models, selectedModel) {
   return [selected, ...rest].filter(Boolean).map((e) => e.model);
 }
 
-/**
- * Fisher-Yates shuffle (in-place)
- * @param {Array} arr
- * @returns {Array} The shuffled array
- */
-function shuffleArray(arr) {
-  for (let i = arr.length - 1; i > 0; i--) {
-    const j = Math.floor(Math.random() * (i + 1));
-    [arr[i], arr[j]] = [arr[j], arr[i]];
-  }
-  return arr;
-}
-
-/**
- * Sort models by pricing (cheapest first) for cost-optimized strategy
- * @param {Array<string>} models - Model strings in "provider/model" format
- * @returns {Promise<Array<string>>} Sorted model strings
- */
-async function sortModelsByCost(models) {
-  try {
-    const { getPricingForModel } = await import("../../src/lib/localDb");
-    const withCost = await Promise.all(
-      models.map(async (modelStr) => {
-        const parsed = parseModel(modelStr);
-        const provider = parsed.provider || parsed.providerAlias || "unknown";
-        const model = parsed.model || modelStr;
-        try {
-          const pricing = await getPricingForModel(provider, model);
-          return { modelStr, cost: pricing?.input ?? Infinity };
-        } catch {
-          return { modelStr, cost: Infinity };
-        }
-      })
-    );
-    withCost.sort((a, b) => a.cost - b.cost);
-    return withCost.map((e) => e.modelStr);
-  } catch {
-    // If pricing lookup fails entirely, return original order
-    return models;
-  }
-}
-
-/**
- * Sort models by usage count (least-used first) for least-used strategy
- * @param {Array<string>} models - Model strings
- * @param {string} comboName - Combo name for metrics lookup
- * @returns {Array<string>} Sorted model strings
- */
-function sortModelsByUsage(models, comboName) {
-  const metrics = getComboMetrics(comboName);
-  if (!metrics || !metrics.byModel) return models;
-
-  const withUsage = models.map((modelStr) => ({
-    modelStr,
-    requests: metrics.byModel[modelStr]?.requests ?? 0,
-  }));
-  withUsage.sort((a, b) => a.requests - b.requests);
-  return withUsage.map((e) => e.modelStr);
-}
-
 /**
  * Handle combo chat with fallback
- * Supports all 6 strategies: priority, weighted, round-robin, random, least-used, cost-optimized
+ * Supports priority (sequential) and weighted (probabilistic) strategies
  * @param {Object} options
  * @param {Object} options.body - Request body
  * @param {Object} options.combo - Full combo object { name, models, strategy, config }
@@ -221,7 +156,6 @@ function sortModelsByUsage(models, comboName) {
  * @param {Object} options.log - Logger object
  * @returns {Promise<Response>}
  */
-/** @param {any} options */
 export async function handleComboChat({
   body,
   combo,
@@ -276,7 +210,7 @@ export async function handleComboChat({
       );
     } else {
       orderedModels = flatModels;
-      log.info("COMBO", `${strategy} with nested resolution: ${orderedModels.length} total models`);
+      log.info("COMBO", `Priority with nested resolution: ${orderedModels.length} total models`);
     }
   } else if (strategy === "weighted") {
     const selected = selectWeightedModel(models);
@@ -286,18 +220,6 @@ export async function handleComboChat({
     orderedModels = models.map((m) => normalizeModelEntry(m).model);
   }
 
-  // Apply strategy-specific ordering
-  if (strategy === "random") {
-    orderedModels = shuffleArray([...orderedModels]);
-    log.info("COMBO", `Random shuffle: ${orderedModels.length} models`);
-  } else if (strategy === "least-used") {
-    orderedModels = sortModelsByUsage(orderedModels, combo.name);
-    log.info("COMBO", `Least-used ordering: ${orderedModels[0]} has fewest requests`);
-  } else if (strategy === "cost-optimized") {
-    orderedModels = await sortModelsByCost(orderedModels);
-    log.info("COMBO", `Cost-optimized ordering: cheapest first (${orderedModels[0]})`);
-  }
-
   let lastError = null;
   let earliestRetryAfter = null;
   let lastStatus = null;
@@ -307,20 +229,6 @@ export async function handleComboChat({
 
   for (let i = 0; i < orderedModels.length; i++) {
     const modelStr = orderedModels[i];
-    const parsed = parseModel(modelStr);
-    const provider = parsed.provider || parsed.providerAlias || "unknown";
-    const profile = getProviderProfile(provider);
-    const breaker = getCircuitBreaker(`combo:${provider}`, {
-      failureThreshold: profile.circuitBreakerThreshold,
-      resetTimeout: profile.circuitBreakerReset,
-    });
-
-    // Skip model if circuit breaker is OPEN
-    if (!breaker.canExecute()) {
-      log.info("COMBO", `Skipping ${modelStr}: circuit breaker OPEN for ${provider}`);
-      if (i > 0) fallbackCount++;
-      continue;
-    }
 
     // Pre-check: skip models where all accounts are in cooldown
     if (isModelAvailable) {
@@ -405,18 +313,7 @@ export async function handleComboChat({
         }
       }
 
-      const { shouldFallback, cooldownMs } = checkFallbackError(
-        result.status,
-        errorText,
-        0,
-        null,
-        provider
-      );
-
-      // Record failure in circuit breaker for transient errors
-      if (TRANSIENT_FOR_BREAKER.includes(result.status)) {
-        breaker._onFailure();
-      }
+      const { shouldFallback } = checkFallbackError(result.status, errorText);
 
       if (!shouldFallback) {
         log.warn("COMBO", `Model ${modelStr} failed (no fallback)`, { status: result.status });
@@ -438,24 +335,10 @@ export async function handleComboChat({
     }
   }
 
-  // Early exit: check if all models have breaker OPEN
-  const allBreakersOpen = orderedModels.every((m) => {
-    const p = parseModel(m).provider || parseModel(m).providerAlias || "unknown";
-    return !getCircuitBreaker(`combo:${p}`).canExecute();
-  });
-
   // All models failed
   const latencyMs = Date.now() - startTime;
   recordComboRequest(combo.name, null, { success: false, latencyMs, fallbackCount, strategy });
 
-  if (allBreakersOpen) {
-    log.warn("COMBO", "All models have circuit breaker OPEN — aborting");
-    return unavailableResponse(
-      503,
-      "All providers temporarily unavailable (circuit breakers open)"
-    );
-  }
-
   const status = lastStatus || 406;
   const msg = lastError || "All combo models unavailable";
 
@@ -529,20 +412,6 @@ async function handleRoundRobinCombo({
   for (let offset = 0; offset < modelCount; offset++) {
     const modelIndex = (startIndex + offset) % modelCount;
     const modelStr = orderedModels[modelIndex];
-    const parsed = parseModel(modelStr);
-    const provider = parsed.provider || parsed.providerAlias || "unknown";
-    const profile = getProviderProfile(provider);
-    const breaker = getCircuitBreaker(`combo:${provider}`, {
-      failureThreshold: profile.circuitBreakerThreshold,
-      resetTimeout: profile.circuitBreakerReset,
-    });
-
-    // Skip model if circuit breaker is OPEN
-    if (!breaker.canExecute()) {
-      log.info("COMBO-RR", `Skipping ${modelStr}: circuit breaker OPEN for ${provider}`);
-      if (offset > 0) fallbackCount++;
-      continue;
-    }
 
     // Pre-check availability
     if (isModelAvailable) {
@@ -641,22 +510,12 @@ async function handleRoundRobinCombo({
           }
         }
 
-        const { shouldFallback, cooldownMs } = checkFallbackError(
-          result.status,
-          errorText,
-          0,
-          null,
-          provider
-        );
+        const { shouldFallback, cooldownMs } = checkFallbackError(result.status, errorText);
 
-        // Transient errors → mark in semaphore AND record circuit breaker failure
-        if (TRANSIENT_FOR_BREAKER.includes(result.status) && cooldownMs > 0) {
+        // Rate-limited → mark in semaphore so queue pauses
+        if (result.status === 429 && cooldownMs > 0) {
           semaphore.markRateLimited(modelStr, cooldownMs);
-          breaker._onFailure();
-          log.warn(
-            "COMBO-RR",
-            `${modelStr} error ${result.status}, cooldown ${cooldownMs}ms (breaker: ${breaker.getStatus().failureCount}/${profile.circuitBreakerThreshold})`
-          );
+          log.warn("COMBO-RR", `${modelStr} rate-limited, cooldown ${cooldownMs}ms`);
         }
 
         if (!shouldFallback) {
@@ -692,20 +551,6 @@ async function handleRoundRobinCombo({
     strategy: "round-robin",
   });
 
-  // Early exit: check if all models have breaker OPEN
-  const allBreakersOpen = orderedModels.every((m) => {
-    const p = parseModel(m).provider || parseModel(m).providerAlias || "unknown";
-    return !getCircuitBreaker(`combo:${p}`).canExecute();
-  });
-
-  if (allBreakersOpen) {
-    log.warn("COMBO-RR", "All models have circuit breaker OPEN — aborting");
-    return unavailableResponse(
-      503,
-      "All providers temporarily unavailable (circuit breakers open)"
-    );
-  }
-
   const status = lastStatus || 406;
   const msg = lastError || "All round-robin combo models unavailable";
 

open-sse/services/comboConfig.js

@@ -27,7 +27,7 @@ const DEFAULT_COMBO_CONFIG = {
  * @param {string} [provider] - Optional provider to apply provider-level overrides
  * @returns {Object} Resolved config
  */
-export function resolveComboConfig(combo, settings, provider?: any) {
+export function resolveComboConfig(combo, settings, provider) {
   const global = settings?.comboDefaults || {};
   const providerOverride = provider ? settings?.providerOverrides?.[provider] || {} : {};
   const comboConfig = combo?.config || {};

open-sse/services/comboMetrics.js

@@ -35,7 +35,7 @@ export function recordComboRequest(
     });
   }
 
-  const combo: any = metrics.get(comboName);
+  const combo = metrics.get(comboName);
   combo.totalRequests++;
   combo.totalLatencyMs += latencyMs;
   combo.totalFallbacks += fallbackCount;
@@ -81,7 +81,7 @@ export function recordComboRequest(
  * @returns {Object|null}
  */
 export function getComboMetrics(comboName) {
-  const combo: any = metrics.get(comboName);
+  const combo = metrics.get(comboName);
   if (!combo) return null;
 
   return {
@@ -93,7 +93,7 @@ export function getComboMetrics(comboName) {
     fallbackRate:
       combo.totalRequests > 0 ? Math.round((combo.totalFallbacks / combo.totalRequests) * 100) : 0,
     byModel: Object.fromEntries(
-      Object.entries(combo.byModel).map(([model, m]: [string, any]) => [
+      Object.entries(combo.byModel).map(([model, m]) => [
         model,
         {
           ...m,
@@ -110,7 +110,7 @@ export function getComboMetrics(comboName) {
  * @returns {Object} Map of comboName → metrics
  */
 export function getAllComboMetrics() {
-  const result: Record<string, any> = {};
+  const result = {};
   for (const [name] of metrics) {
     result[name] = getComboMetrics(name);
   }

open-sse/services/contextManager.ts

@@ -1,203 +0,0 @@
-/**
- * Context Manager — Phase 4
- *
- * Pre-flight context compression to prevent "prompt too long" errors.
- * 3 layers: trim tool messages, compress thinking, aggressive purification.
- */
-
-// Default token limits per provider (rough estimates based on model context windows)
-const DEFAULT_LIMITS = {
-  claude: 200000,
-  openai: 128000,
-  gemini: 1000000,
-  default: 128000,
-};
-
-// Rough chars-per-token ratio for quick estimation
-const CHARS_PER_TOKEN = 4;
-
-/**
- * Estimate token count from text length
- */
-export function estimateTokens(text) {
-  if (!text) return 0;
-  const str = typeof text === "string" ? text : JSON.stringify(text);
-  return Math.ceil(str.length / CHARS_PER_TOKEN);
-}
-
-/**
- * Get token limit for a provider/model combination
- */
-export function getTokenLimit(provider, model = null) {
-  // Check if model has a known limit
-  if (model) {
-    const lower = model.toLowerCase();
-    if (lower.includes("claude")) return DEFAULT_LIMITS.claude;
-    if (lower.includes("gemini")) return DEFAULT_LIMITS.gemini;
-    if (lower.includes("gpt") || lower.includes("o1") || lower.includes("o3") || lower.includes("o4")) return DEFAULT_LIMITS.openai;
-  }
-  return DEFAULT_LIMITS[provider] || DEFAULT_LIMITS.default;
-}
-
-/**
- * Apply context compression to request body.
- * Operates in 3 layers of increasing aggressiveness:
- *
- * Layer 1: Trim tool_result messages (truncate long outputs)
- * Layer 2: Compress thinking blocks (remove from history, keep last)
- * Layer 3: Aggressive purification (drop old messages until fitting)
- *
- * @param {object} body - Request body with messages[]
- * @param {object} options - { provider?, model?, maxTokens?, reserveTokens? }
- * @returns {{ body: object, compressed: boolean, stats: object }}
- */
-export function compressContext(body, options: any = {}) {
-  if (!body || !body.messages || !Array.isArray(body.messages)) {
-    return { body, compressed: false, stats: {} };
-  }
-
-  const provider = options.provider || "default";
-  const maxTokens = options.maxTokens || getTokenLimit(provider, body.model || options.model);
-  const reserveTokens = options.reserveTokens || 16000; // Reserve for response
-  const targetTokens = maxTokens - reserveTokens;
-
-  let messages = [...body.messages];
-  let currentTokens = estimateTokens(JSON.stringify(messages));
-  const stats = { original: currentTokens, layers: [] };
-
-  // Already fits
-  if (currentTokens <= targetTokens) {
-    return { body, compressed: false, stats: { original: currentTokens, final: currentTokens } };
-  }
-
-  // Layer 1: Trim tool_result/tool messages
-  messages = trimToolMessages(messages, 2000); // Max 2000 chars per tool result
-  currentTokens = estimateTokens(JSON.stringify(messages));
-  stats.layers.push({ name: "trim_tools", tokens: currentTokens });
-
-  if (currentTokens <= targetTokens) {
-    return {
-      body: { ...body, messages },
-      compressed: true,
-      stats: { ...stats, final: currentTokens },
-    };
-  }
-
-  // Layer 2: Compress thinking blocks (remove from non-last assistant messages)
-  messages = compressThinking(messages);
-  currentTokens = estimateTokens(JSON.stringify(messages));
-  stats.layers.push({ name: "compress_thinking", tokens: currentTokens });
-
-  if (currentTokens <= targetTokens) {
-    return {
-      body: { ...body, messages },
-      compressed: true,
-      stats: { ...stats, final: currentTokens },
-    };
-  }
-
-  // Layer 3: Aggressive purification — drop oldest messages keeping system + last N pairs
-  messages = purifyHistory(messages, targetTokens);
-  currentTokens = estimateTokens(JSON.stringify(messages));
-  stats.layers.push({ name: "purify_history", tokens: currentTokens });
-
-  return {
-    body: { ...body, messages },
-    compressed: true,
-    stats: { ...stats, final: currentTokens },
-  };
-}
-
-// ─── Layer 1: Trim Tool Messages ────────────────────────────────────────────
-
-function trimToolMessages(messages, maxChars) {
-  return messages.map((msg) => {
-    if (msg.role === "tool" && typeof msg.content === "string" && msg.content.length > maxChars) {
-      return {
-        ...msg,
-        content: msg.content.slice(0, maxChars) + "\n... [truncated]",
-      };
-    }
-    // Handle array content (Claude format with tool_result blocks)
-    if (msg.role === "user" && Array.isArray(msg.content)) {
-      return {
-        ...msg,
-        content: msg.content.map((block) => {
-          if (block.type === "tool_result" && typeof block.content === "string" && block.content.length > maxChars) {
-            return { ...block, content: block.content.slice(0, maxChars) + "\n... [truncated]" };
-          }
-          return block;
-        }),
-      };
-    }
-    return msg;
-  });
-}
-
-// ─── Layer 2: Compress Thinking Blocks ──────────────────────────────────────
-
-function compressThinking(messages) {
-  // Find last assistant message index
-  let lastAssistantIdx = -1;
-  for (let i = messages.length - 1; i >= 0; i--) {
-    if (messages[i].role === "assistant") {
-      lastAssistantIdx = i;
-      break;
-    }
-  }
-
-  return messages.map((msg, i) => {
-    if (msg.role !== "assistant") return msg;
-    if (i === lastAssistantIdx) return msg; // Keep thinking in last assistant msg
-
-    // Remove thinking blocks from content array
-    if (Array.isArray(msg.content)) {
-      const filtered = msg.content.filter((block) => block.type !== "thinking");
-      if (filtered.length === 0) {
-        return { ...msg, content: "[thinking compressed]" };
-      }
-      return { ...msg, content: filtered };
-    }
-
-    // Remove thinking XML tags from string content
-    if (typeof msg.content === "string") {
-      const cleaned = msg.content
-        .replace(/<thinking>[\s\S]*?<\/thinking>/g, "")
-        .replace(/<antThinking>[\s\S]*?<\/antThinking>/g, "")
-        .trim();
-      return { ...msg, content: cleaned || "[thinking compressed]" };
-    }
-
-    return msg;
-  });
-}
-
-// ─── Layer 3: Aggressive Purification ───────────────────────────────────────
-
-function purifyHistory(messages, targetTokens) {
-  // Keep system message(s) and the last N message pairs
-  const system = messages.filter((m) => m.role === "system" || m.role === "developer");
-  const nonSystem = messages.filter((m) => m.role !== "system" && m.role !== "developer");
-
-  // Binary search for how many messages to keep from the end
-  let keep = nonSystem.length;
-  while (keep > 2) {
-    const candidate = [...system, ...nonSystem.slice(-keep)];
-    const tokens = estimateTokens(JSON.stringify(candidate));
-    if (tokens <= targetTokens) break;
-    keep = Math.max(2, Math.floor(keep * 0.7)); // Drop 30% each iteration
-  }
-
-  const result = [...system, ...nonSystem.slice(-keep)];
-
-  // Add summary of dropped messages
-  if (keep < nonSystem.length) {
-    const dropped = nonSystem.length - keep;
-    result.splice(system.length, 0, {
-      role: "system",
-      content: `[Context compressed: ${dropped} earlier messages removed to fit context window]`,
-    });
-  }
-
-  return result;
-}

open-sse/services/ipFilter.ts

@@ -1,249 +0,0 @@
-/**
- * IP Filter Middleware — Phase 6
- *
- * IP-based access control with blacklist, whitelist, priority modes, and temporary bans.
- */
-
-// In-memory IP lists
-let _config = {
-  enabled: false,
-  mode: "blacklist", // "blacklist" | "whitelist" | "whitelist-priority"
-  blacklist: new Set(),
-  whitelist: new Set(),
-  tempBans: new Map(), // IP → { until: timestamp, reason: string }
-};
-
-/**
- * Configure the IP filter
- */
-export function configureIPFilter(config) {
-  if (config.enabled !== undefined) _config.enabled = config.enabled;
-  if (config.mode) _config.mode = config.mode;
-  if (config.blacklist) _config.blacklist = new Set(config.blacklist);
-  if (config.whitelist) _config.whitelist = new Set(config.whitelist);
-}
-
-/**
- * Get current IP filter config (for API)
- */
-export function getIPFilterConfig() {
-  return {
-    enabled: _config.enabled,
-    mode: _config.mode,
-    blacklist: Array.from(_config.blacklist),
-    whitelist: Array.from(_config.whitelist),
-    tempBans: Array.from(_config.tempBans.entries()).map(([ip, info]) => ({
-      ip,
-      until: new Date(info.until).toISOString(),
-      reason: info.reason,
-      remainingMs: Math.max(0, info.until - Date.now()),
-    })),
-  };
-}
-
-/**
- * Check if an IP is allowed
- * @param {string} ip
- * @returns {{ allowed: boolean, reason?: string }}
- */
-export function checkIP(ip) {
-  if (!_config.enabled) return { allowed: true };
-  if (!ip) return { allowed: true };
-
-  const normalizedIP = normalizeIP(ip);
-
-  // Check temp bans first (highest priority)
-  const ban = _config.tempBans.get(normalizedIP);
-  if (ban) {
-    if (Date.now() < ban.until) {
-      return { allowed: false, reason: `Temporarily banned: ${ban.reason}` };
-    }
-    _config.tempBans.delete(normalizedIP); // Expired
-  }
-
-  switch (_config.mode) {
-    case "whitelist":
-      // Only whitelisted IPs allowed
-      if (!matchesAny(normalizedIP, _config.whitelist)) {
-        return { allowed: false, reason: "IP not in whitelist" };
-      }
-      return { allowed: true };
-
-    case "whitelist-priority":
-      // Whitelist overrides blacklist
-      if (matchesAny(normalizedIP, _config.whitelist)) {
-        return { allowed: true };
-      }
-      if (matchesAny(normalizedIP, _config.blacklist)) {
-        return { allowed: false, reason: "IP blacklisted" };
-      }
-      return { allowed: true };
-
-    case "blacklist":
-    default:
-      // Blacklisted IPs blocked
-      if (matchesAny(normalizedIP, _config.blacklist)) {
-        return { allowed: false, reason: "IP blacklisted" };
-      }
-      return { allowed: true };
-  }
-}
-
-/**
- * Temporarily ban an IP
- */
-export function tempBanIP(ip, durationMs, reason = "Automated ban") {
-  const normalizedIP = normalizeIP(ip);
-  _config.tempBans.set(normalizedIP, {
-    until: Date.now() + durationMs,
-    reason,
-  });
-}
-
-/**
- * Remove a temporary ban
- */
-export function removeTempBan(ip) {
-  _config.tempBans.delete(normalizeIP(ip));
-}
-
-/**
- * Add IP to blacklist
- */
-export function addToBlacklist(ip) {
-  _config.blacklist.add(normalizeIP(ip));
-}
-
-/**
- * Remove IP from blacklist
- */
-export function removeFromBlacklist(ip) {
-  _config.blacklist.delete(normalizeIP(ip));
-}
-
-/**
- * Add IP to whitelist
- */
-export function addToWhitelist(ip) {
-  _config.whitelist.add(normalizeIP(ip));
-}
-
-/**
- * Remove IP from whitelist
- */
-export function removeFromWhitelist(ip) {
-  _config.whitelist.delete(normalizeIP(ip));
-}
-
-/**
- * Express/Next.js middleware factory
- */
-export function createIPFilterMiddleware() {
-  return (req, res, next) => {
-    const ip = extractClientIP(req);
-    const { allowed, reason } = checkIP(ip);
-    if (!allowed) {
-      const statusCode = 403;
-      if (res.status) {
-        // Express
-        return res.status(statusCode).json({ error: reason || "Access denied" });
-      }
-      // Raw response
-      res.writeHead(statusCode, { "Content-Type": "application/json" });
-      return res.end(JSON.stringify({ error: reason || "Access denied" }));
-    }
-    if (next) next();
-  };
-}
-
-/**
- * For Next.js App Router — check IP from request object
- */
-export function checkRequestIP(request) {
-  const ip =
-    request.headers?.get?.("x-forwarded-for")?.split(",")[0].trim() ||
-    request.headers?.get?.("x-real-ip") ||
-    request.headers?.get?.("cf-connecting-ip") ||
-    request.ip ||
-    "unknown";
-  return checkIP(ip);
-}
-
-// ─── Internal Helpers ───────────────────────────────────────────────────────
-
-function normalizeIP(ip) {
-  if (!ip) return "";
-  // Remove IPv6 prefix from IPv4-mapped addresses
-  return ip.replace(/^::ffff:/, "").trim();
-}
-
-function matchesAny(ip, ipSet) {
-  // Direct match
-  if (ipSet.has(ip)) return true;
-
-  // CIDR match
-  for (const entry of ipSet) {
-    if (entry.includes("/") && matchesCIDR(ip, entry)) return true;
-    // Wildcard match (e.g., "192.168.*.*")
-    if (entry.includes("*") && matchesWildcard(ip, entry)) return true;
-  }
-  return false;
-}
-
-function matchesCIDR(ip, cidr) {
-  try {
-    const [range, bits] = cidr.split("/");
-    const mask = parseInt(bits, 10);
-    if (isNaN(mask) || mask < 0 || mask > 32) return false;
-    const ipNum = ipToNum(ip);
-    const rangeNum = ipToNum(range);
-    if (ipNum === null || rangeNum === null) return false;
-    const maskBits = (-1 << (32 - mask)) >>> 0;
-    return (ipNum & maskBits) === (rangeNum & maskBits);
-  } catch {
-    return false;
-  }
-}
-
-function ipToNum(ip) {
-  const parts = ip.split(".");
-  if (parts.length !== 4) return null;
-  let num = 0;
-  for (const p of parts) {
-    const n = parseInt(p, 10);
-    if (isNaN(n) || n < 0 || n > 255) return null;
-    num = (num << 8) | n;
-  }
-  return num >>> 0;
-}
-
-function matchesWildcard(ip, pattern) {
-  const ipParts = ip.split(".");
-  const patParts = pattern.split(".");
-  if (ipParts.length !== 4 || patParts.length !== 4) return false;
-  return ipParts.every((part, i) => patParts[i] === "*" || part === patParts[i]);
-}
-
-function extractClientIP(req) {
-  return (
-    req.headers?.["x-forwarded-for"]?.split(",")[0].trim() ||
-    req.headers?.["x-real-ip"] ||
-    req.headers?.["cf-connecting-ip"] ||
-    req.socket?.remoteAddress ||
-    req.ip ||
-    "unknown"
-  );
-}
-
-/**
- * Reset config (for testing)
- */
-export function resetIPFilter() {
-  _config = {
-    enabled: false,
-    mode: "blacklist",
-    blacklist: new Set(),
-    whitelist: new Set(),
-    tempBans: new Map(),
-  };
-}

open-sse/services/model.js

@@ -1,4 +1,4 @@
-import { PROVIDER_ID_TO_ALIAS, PROVIDER_MODELS } from "../config/providerModels.ts";
+import { PROVIDER_ID_TO_ALIAS, PROVIDER_MODELS } from "../config/providerModels.js";
 
 // Derive alias→provider mapping from the single source of truth (PROVIDER_ID_TO_ALIAS)
 // This prevents the two maps from drifting out of sync

open-sse/services/provider.js

@@ -1,5 +1,5 @@
-import { PROVIDERS } from "../config/constants.ts";
-import { getRegistryEntry } from "../config/providerRegistry.ts";
+import { PROVIDERS } from "../config/constants.js";
+import { getRegistryEntry } from "../config/providerRegistry.js";
 
 const OPENAI_COMPATIBLE_PREFIX = "openai-compatible-";
 const OPENAI_COMPATIBLE_DEFAULTS = {
@@ -156,7 +156,7 @@ export function getProviderFallbackCount(provider) {
 }
 
 // Build provider URL
-export function buildProviderUrl(provider, model, stream = true, options: any = {}) {
+export function buildProviderUrl(provider, model, stream = true, options = {}) {
   if (isOpenAICompatible(provider)) {
     const apiType = getOpenAICompatibleType(provider);
     const baseUrl = options?.baseUrl || OPENAI_COMPATIBLE_DEFAULTS.baseUrl;

open-sse/services/rateLimitManager.js

@@ -4,14 +4,10 @@
  * Creates per-provider+connection limiters that auto-learn rate limits
  * from API response headers (x-ratelimit-*, retry-after, anthropic-ratelimit-*).
  *
- * Default: ENABLED for API key providers (safety net), DISABLED for OAuth.
- * Can be toggled per provider connection via dashboard.
+ * Default: DISABLED. Must be enabled per provider connection via dashboard toggle.
  */
 
 import Bottleneck from "bottleneck";
-import { parseRetryAfterFromBody, lockModel } from "./accountFallback.ts";
-import { getProviderCategory } from "../config/providerRegistry.ts";
-import { DEFAULT_API_LIMITS } from "../config/constants.ts";
 
 // Store limiters keyed by "provider:connectionId" (and optionally ":model")
 const limiters = new Map();
@@ -40,47 +36,17 @@ export async function initializeRateLimits() {
   initialized = true;
 
   try {
-    const { getProviderConnections } = await import("@/lib/localDb");
+    const { getProviderConnections } = await import("@/lib/localDb.js");
     const connections = await getProviderConnections();
-    let explicitCount = 0;
-    let autoCount = 0;
-
+    let count = 0;
     for (const conn of connections) {
       if (conn.rateLimitProtection) {
-        // Explicitly enabled by user
         enabledConnections.add(conn.id);
-        explicitCount++;
-      } else if (
-        conn.provider &&
-        getProviderCategory(conn.provider) === "apikey" &&
-        conn.isActive
-      ) {
-        // Auto-enable for API key providers (safety net)
-        enabledConnections.add(conn.id);
-        autoCount++;
-
-        // Create a pre-configured limiter with conservative defaults
-        const key = `${conn.provider}:${conn.id}`;
-        if (!limiters.has(key)) {
-          limiters.set(
-            key,
-            new Bottleneck({
-              maxConcurrent: DEFAULT_API_LIMITS.concurrentRequests,
-              minTime: DEFAULT_API_LIMITS.minTimeBetweenRequests,
-              reservoir: DEFAULT_API_LIMITS.requestsPerMinute,
-              reservoirRefreshAmount: DEFAULT_API_LIMITS.requestsPerMinute,
-              reservoirRefreshInterval: 60 * 1000, // Refresh every minute
-              id: key,
-            })
-          );
-        }
+        count++;
       }
     }
-
-    if (explicitCount > 0 || autoCount > 0) {
-      console.log(
-        `🛡️ [RATE-LIMIT] Loaded ${explicitCount} explicit + ${autoCount} auto-enabled (API key) protection(s)`
-      );
+    if (count > 0) {
+      console.log(`🛡️ [RATE-LIMIT] Loaded ${count} connection(s) with rate limit protection`);
     }
   } catch (err) {
     console.error("[RATE-LIMIT] Failed to load settings:", err.message);
@@ -293,7 +259,7 @@ export function updateFromHeaders(provider, connectionId, headers, status, model
     // Calculate optimal minTime from RPM limit
     const minTime = Math.max(0, Math.floor(60000 / limit) - 10); // Small buffer
 
-    const updates: Record<string, any> = { minTime };
+    const updates = { minTime };
 
     // If remaining is low (< 10% of limit), set reservoir to throttle immediately
     if (!isNaN(remaining)) {
@@ -348,7 +314,7 @@ export function getRateLimitStatus(provider, connectionId) {
  * Get all active limiters status (for dashboard overview)
  */
 export function getAllRateLimitStatus() {
-  const result: Record<string, any> = {};
+  const result = {};
   for (const [key, limiter] of limiters) {
     const counts = limiter.counts();
     result[key] = {
@@ -359,38 +325,3 @@ export function getAllRateLimitStatus() {
   }
   return result;
 }
-
-/**
- * Update rate limiter based on API response body (JSON error responses).
- * Providers embed retry info in JSON payloads in different formats.
- * Should be called alongside updateFromHeaders for 4xx/5xx responses.
- *
- * @param {string} provider - Provider ID
- * @param {string} connectionId - Connection ID
- * @param {string|object} responseBody - Response body (string or parsed JSON)
- * @param {number} status - HTTP status code
- * @param {string} model - Model name (for per-model lockouts)
- */
-export function updateFromResponseBody(provider, connectionId, responseBody, status, model = null) {
-  if (!enabledConnections.has(connectionId)) return;
-
-  const { retryAfterMs, reason } = parseRetryAfterFromBody(responseBody);
-
-  if (retryAfterMs && retryAfterMs > 0) {
-    const limiter = getLimiter(provider, connectionId, null);
-    console.log(
-      `🚫 [RATE-LIMIT] ${provider}:${connectionId.slice(0, 8)} — body-parsed retry: ${Math.ceil(retryAfterMs / 1000)}s (${reason})`
-    );
-
-    limiter.updateSettings({
-      reservoir: 0,
-      reservoirRefreshAmount: 60,
-      reservoirRefreshInterval: retryAfterMs,
-    });
-
-    // Also apply model-level lockout if model is known
-    if (model) {
-      lockModel(provider, connectionId, model, reason, retryAfterMs);
-    }
-  }
-}

open-sse/services/rateLimitSemaphore.js

@@ -117,7 +117,7 @@ export function acquire(modelStr, { maxConcurrency = 3, timeoutMs = 30000 } = {}
       const idx = gate.queue.findIndex((item) => item.timer === timer);
       if (idx !== -1) gate.queue.splice(idx, 1);
       const err = new Error(`Semaphore timeout after ${timeoutMs}ms for ${modelStr}`);
-      (err as any).code = "SEMAPHORE_TIMEOUT";
+      err.code = "SEMAPHORE_TIMEOUT";
       reject(err);
     }, timeoutMs);
 

open-sse/services/roleNormalizer.ts

@@ -1,169 +0,0 @@
-/**
- * Role Normalizer — Converts message roles for provider compatibility.
- *
- * Fixes Issues:
- * 1. GLM/ZhipuAI rejects `system` role → merged into first `user` message
- * 2. OpenAI `developer` role not understood by non-OpenAI providers → normalized to `system`
- * 3. Some providers don't support `system` role at all → prepended to user message
- *
- * Provider capability matrix is defined here rather than in the registry to
- * avoid breaking changes to the existing RegistryEntry interface.
- */
-
-// ── Provider capabilities ──────────────────────────────────────────────────
-
-/**
- * Providers that do NOT support the `system` role in messages.
- * For these, system messages are merged into the first user message.
- *
- * Note: This applies only to OpenAI-format passthrough providers.
- * Claude and Gemini have their own system message handling in dedicated translators.
- */
-const PROVIDERS_WITHOUT_SYSTEM_ROLE = new Set([
-  // Known to reject system role (from troubleshooting report)
-  // GLM uses Claude format, so this is handled through claude translator
-  // But if accessed through OpenAI-format providers like nvidia, it needs this:
-]);
-
-/**
- * Models that are known to reject the `system` role regardless of provider.
- * Uses prefix matching (e.g., "glm-" matches "glm-4.7", "glm-4.5", etc.)
- */
-const MODELS_WITHOUT_SYSTEM_ROLE = [
-  "glm-", // ZhipuAI GLM models
-  "ernie-", // Baidu ERNIE models
-];
-
-/**
- * Check if a provider+model combo supports the system role.
- */
-function supportsSystemRole(provider: string, model: string): boolean {
-  if (PROVIDERS_WITHOUT_SYSTEM_ROLE.has(provider)) return false;
-
-  const modelLower = (model || "").toLowerCase();
-  for (const prefix of MODELS_WITHOUT_SYSTEM_ROLE) {
-    if (modelLower.startsWith(prefix)) return false;
-  }
-
-  return true;
-}
-
-/**
- * Normalize the `developer` role to `system` for non-OpenAI providers.
- * OpenAI introduced `developer` as a replacement for `system` in newer models,
- * but most other providers still expect `system`.
- *
- * @param messages - Array of messages
- * @param targetFormat - The target format (e.g., "openai", "claude", "gemini")
- * @returns Modified messages array
- */
-export function normalizeDeveloperRole(messages: any[], targetFormat: string): any[] {
-  if (!Array.isArray(messages)) return messages;
-
-  // For OpenAI format, keep developer role as-is (it's valid)
-  // For all other formats, convert developer → system
-  if (targetFormat === "openai") return messages;
-
-  return messages.map((msg) => {
-    if (msg.role === "developer") {
-      return { ...msg, role: "system" };
-    }
-    return msg;
-  });
-}
-
-/**
- * Convert `system` messages to user messages for providers that don't support
- * the system role. The system content is prepended to the first user message
- * with a clear delimiter.
- *
- * @param messages - Array of messages
- * @param provider - Provider name
- * @param model - Model name
- * @returns Modified messages array
- */
-export function normalizeSystemRole(messages: any[], provider: string, model: string): any[] {
-  if (!Array.isArray(messages) || messages.length === 0) return messages;
-  if (supportsSystemRole(provider, model)) return messages;
-
-  // Extract system messages
-  const systemMessages = messages.filter((m) => m.role === "system" || m.role === "developer");
-  if (systemMessages.length === 0) return messages;
-
-  // Build system content string
-  const systemContent = systemMessages
-    .map((m) => {
-      if (typeof m.content === "string") return m.content;
-      if (Array.isArray(m.content)) {
-        return m.content
-          .filter((c: any) => c.type === "text")
-          .map((c: any) => c.text)
-          .join("\n");
-      }
-      return "";
-    })
-    .filter(Boolean)
-    .join("\n\n");
-
-  if (!systemContent) {
-    return messages.filter((m) => m.role !== "system" && m.role !== "developer");
-  }
-
-  // Remove system messages and merge into first user message
-  const nonSystemMessages = messages.filter((m) => m.role !== "system" && m.role !== "developer");
-
-  // Find first user message and prepend system content
-  const firstUserIdx = nonSystemMessages.findIndex((m) => m.role === "user");
-  if (firstUserIdx >= 0) {
-    const userMsg = nonSystemMessages[firstUserIdx];
-    const userContent =
-      typeof userMsg.content === "string"
-        ? userMsg.content
-        : Array.isArray(userMsg.content)
-          ? userMsg.content
-              .filter((c: any) => c.type === "text")
-              .map((c: any) => c.text)
-              .join("\n")
-          : "";
-
-    nonSystemMessages[firstUserIdx] = {
-      ...userMsg,
-      content: `[System Instructions]\n${systemContent}\n\n[User Message]\n${userContent}`,
-    };
-  } else {
-    // No user message found — insert as a user message at the beginning
-    nonSystemMessages.unshift({
-      role: "user",
-      content: `[System Instructions]\n${systemContent}`,
-    });
-  }
-
-  return nonSystemMessages;
-}
-
-/**
- * Full role normalization pipeline.
- * Call this before sending the request to the provider.
- *
- * @param messages - Array of messages
- * @param provider - Provider name/id
- * @param model - Model name
- * @param targetFormat - Target API format
- * @returns Normalized messages array
- */
-export function normalizeRoles(
-  messages: any[],
-  provider: string,
-  model: string,
-  targetFormat: string
-): any[] {
-  if (!Array.isArray(messages)) return messages;
-
-  // Step 1: Normalize developer → system (for non-OpenAI formats)
-  let result = normalizeDeveloperRole(messages, targetFormat);
-
-  // Step 2: Normalize system → user (for providers that don't support system role)
-  result = normalizeSystemRole(result, provider, model);
-
-  return result;
-}

open-sse/services/sessionManager.ts

@@ -1,179 +0,0 @@
-/**
- * Session Fingerprinting — Phase 5
- *
- * Generates stable session IDs for sticky routing,
- * prompt caching, and per-session tracking.
- */
-
-import { createHash } from "node:crypto";
-
-// In-memory session store with metadata
-// key: sessionId → { createdAt, lastActive, requestCount, connectionId? }
-const sessions = new Map();
-
-// Auto-cleanup sessions older than 30 minutes
-const SESSION_TTL_MS = 30 * 60 * 1000;
-const _cleanupTimer = setInterval(() => {
-  const now = Date.now();
-  for (const [key, entry] of sessions) {
-    if (now - entry.lastActive > SESSION_TTL_MS) sessions.delete(key);
-  }
-}, 60_000);
-_cleanupTimer.unref();
-
-/**
- * Generate a stable session fingerprint from request characteristics.
- * Same client + same conversation → same session ID.
- *
- * Fingerprint factors:
- * - System prompt hash (stable per conversation/tool)
- * - First user message hash (stable per conversation)
- * - Model name
- * - Provider (optional)
- * - Tools signature (sorted tool names)
- *
- * @param {object} body - Request body
- * @param {object} [options] - Extra context
- * @returns {string} Session ID (hex hash)
- */
-export function generateSessionId(body, options: any = {}) {
-  const parts = [];
-
-  // Model contributes to fingerprint
-  if (body.model) parts.push(`model:${body.model}`);
-
-  // Provider binding
-  if (options.provider) parts.push(`provider:${options.provider}`);
-
-  // System prompt hash (first 32 chars of system content)
-  const systemPrompt = extractSystemPrompt(body);
-  if (systemPrompt) {
-    parts.push(`sys:${hashShort(systemPrompt)}`);
-  }
-
-  // First user message hash (identifies the conversation)
-  const firstUser = extractFirstUserMessage(body);
-  if (firstUser) {
-    parts.push(`user0:${hashShort(firstUser)}`);
-  }
-
-  // Tools signature (sorted names)
-  if (body.tools && Array.isArray(body.tools) && body.tools.length > 0) {
-    const toolNames = body.tools
-      .map((t) => t.name || t.function?.name || "")
-      .filter(Boolean)
-      .sort()
-      .join(",");
-    if (toolNames) parts.push(`tools:${hashShort(toolNames)}`);
-  }
-
-  // Connection ID for sticky routing
-  if (options.connectionId) parts.push(`conn:${options.connectionId}`);
-
-  if (parts.length === 0) return null;
-
-  const fingerprint = parts.join("|");
-  return createHash("sha256").update(fingerprint).digest("hex").slice(0, 16);
-}
-
-/**
- * Touch or create a session
- */
-export function touchSession(sessionId, connectionId = null) {
-  if (!sessionId) return;
-  const existing = sessions.get(sessionId);
-  if (existing) {
-    existing.lastActive = Date.now();
-    existing.requestCount++;
-    if (connectionId) existing.connectionId = connectionId;
-  } else {
-    sessions.set(sessionId, {
-      createdAt: Date.now(),
-      lastActive: Date.now(),
-      requestCount: 1,
-      connectionId,
-    });
-  }
-}
-
-/**
- * Get session info (for sticky routing decisions)
- */
-export function getSessionInfo(sessionId) {
-  if (!sessionId) return null;
-  const entry = sessions.get(sessionId);
-  if (!entry) return null;
-  if (Date.now() - entry.lastActive > SESSION_TTL_MS) {
-    sessions.delete(sessionId);
-    return null;
-  }
-  return { ...entry };
-}
-
-/**
- * Get the bound connection for a session (sticky routing)
- */
-export function getSessionConnection(sessionId) {
-  const info = getSessionInfo(sessionId);
-  return info?.connectionId || null;
-}
-
-/**
- * Get session count (for dashboard)
- */
-export function getActiveSessionCount() {
-  return sessions.size;
-}
-
-/**
- * Get all active sessions (for dashboard)
- */
-export function getActiveSessions() {
-  const now = Date.now();
-  const result = [];
-  for (const [id, entry] of sessions) {
-    if (now - entry.lastActive <= SESSION_TTL_MS) {
-      result.push({ sessionId: id, ...entry, ageMs: now - entry.createdAt });
-    }
-  }
-  return result;
-}
-
-/**
- * Clear all sessions (for testing)
- */
-export function clearSessions() {
-  sessions.clear();
-}
-
-// ─── Internal Helpers ───────────────────────────────────────────────────────
-
-function hashShort(text) {
-  return createHash("sha256").update(text).digest("hex").slice(0, 8);
-}
-
-function extractSystemPrompt(body) {
-  // Claude format: body.system
-  if (body.system) {
-    return typeof body.system === "string" ? body.system : JSON.stringify(body.system);
-  }
-  // OpenAI format: messages[0].role === "system"
-  if (body.messages && Array.isArray(body.messages)) {
-    const sys = body.messages.find((m) => m.role === "system" || m.role === "developer");
-    if (sys) {
-      return typeof sys.content === "string" ? sys.content : JSON.stringify(sys.content);
-    }
-  }
-  return null;
-}
-
-function extractFirstUserMessage(body) {
-  const messages = body.messages || body.input || [];
-  if (!Array.isArray(messages)) return null;
-  for (const msg of messages) {
-    if (msg.role === "user") {
-      return typeof msg.content === "string" ? msg.content : JSON.stringify(msg.content);
-    }
-  }
-  return null;
-}

open-sse/services/signatureCache.ts

@@ -1,171 +0,0 @@
-/**
- * Signature Cache — Phase 3
- *
- * Dynamic 3-layer cache for thinking signatures (tool, model family, session).
- * Replaces hardcoded thinking signature patterns with adaptive detection.
- */
-
-// 3-layer cache: tool → model family → session
-// Each layer stores patterns detected from responses
-const layers = {
-  tool: new Map(),      // e.g. "cursor" → Set of signature patterns
-  family: new Map(),    // e.g. "claude-sonnet" → Set of signature patterns
-  session: new Map(),   // e.g. sessionId → Set of signature patterns
-};
-
-// Known default signatures (bootstrap — will be supplemented by learning)
-const DEFAULT_SIGNATURES = [
-  "<antThinking>",
-  "</antThinking>",
-  "<thinking>",
-  "</thinking>",
-  "<internal_thought>",
-  "</internal_thought>",
-];
-
-// Max entries per cache layer to prevent unbounded growth
-const MAX_ENTRIES_PER_LAYER = 500;
-const MAX_PATTERNS_PER_KEY = 50;
-
-/**
- * Get all matching signatures for a given context.
- * Checks all 3 layers and merges results with defaults.
- *
- * @param {object} context - { tool?, modelFamily?, sessionId? }
- * @returns {string[]} Array of unique signature patterns
- */
-export function getSignatures(context: any = {}) {
-  const patterns = new Set(DEFAULT_SIGNATURES);
-
-  // Layer 1: Tool (e.g., "cursor", "cline", "antigravity")
-  if (context.tool && layers.tool.has(context.tool)) {
-    for (const p of layers.tool.get(context.tool)) patterns.add(p);
-  }
-
-  // Layer 2: Model family (e.g., "claude-sonnet", "claude-opus")
-  if (context.modelFamily && layers.family.has(context.modelFamily)) {
-    for (const p of layers.family.get(context.modelFamily)) patterns.add(p);
-  }
-
-  // Layer 3: Session-specific
-  if (context.sessionId && layers.session.has(context.sessionId)) {
-    for (const p of layers.session.get(context.sessionId)) patterns.add(p);
-  }
-
-  return Array.from(patterns);
-}
-
-/**
- * Add a discovered signature pattern to the cache.
- *
- * @param {string} pattern - The signature pattern (e.g., "<antThinking>")
- * @param {object} context - { tool?, modelFamily?, sessionId? }
- */
-export function addSignature(pattern: any, context: any = {}) {
-  if (!pattern || typeof pattern !== "string") return;
-
-  const addToLayer = (layer, key) => {
-    if (!key) return;
-    if (!layer.has(key)) {
-      if (layer.size >= MAX_ENTRIES_PER_LAYER) {
-        // Evict oldest entry
-        const firstKey = layer.keys().next().value;
-        layer.delete(firstKey);
-      }
-      layer.set(key, new Set());
-    }
-    const set = layer.get(key);
-    if (set.size < MAX_PATTERNS_PER_KEY) {
-      set.add(pattern);
-    }
-  };
-
-  addToLayer(layers.tool, context.tool);
-  addToLayer(layers.family, context.modelFamily);
-  addToLayer(layers.session, context.sessionId);
-}
-
-/**
- * Detect signatures in a text chunk from streaming response.
- * Auto-learns new patterns and adds them to cache.
- *
- * @param {string} text - Streaming text to scan
- * @param {object} context - { tool?, modelFamily?, sessionId? }
- * @returns {{ found: string[], cleaned: string }} Detected tags and cleaned text
- */
-export function detectAndLearn(text: any, context: any = {}) {
-  if (!text || typeof text !== "string") return { found: [], cleaned: text };
-
-  const found = [];
-  let cleaned = text;
-
-  // Check all known signatures
-  const known = getSignatures(context);
-  for (const sig of known) {
-    if (cleaned.includes(sig)) {
-      found.push(sig);
-      cleaned = cleaned.split(sig).join("");
-    }
-  }
-
-  // Auto-detect new XML-like thinking tags
-  const tagRegex = /<\/?([a-zA-Z_][a-zA-Z0-9_]*(?:Thinking|thinking|thought|Thought|internal_thought))>/g;
-  let match;
-  while ((match = tagRegex.exec(text)) !== null) {
-    const tag = match[0];
-    if (!known.includes(tag)) {
-      found.push(tag);
-      addSignature(tag, context);
-      cleaned = cleaned.split(tag).join("");
-    }
-  }
-
-  return { found, cleaned: cleaned.trim() || cleaned };
-}
-
-/**
- * Extract model family from model name
- * "claude-sonnet-4-20250514" → "claude-sonnet"
- * "gpt-4o-2024-08-06" → "gpt-4o"
- */
-export function getModelFamily(model) {
-  if (!model) return null;
-  // Remove date suffixes and version numbers
-  const cleaned = model
-    .replace(/-\d{4}-\d{2}-\d{2}$/, "") // Remove YYYY-MM-DD suffix
-    .replace(/-\d{8,}$/, "")            // Remove YYYYMMDD suffix
-    .replace(/-\d+(\.\d+)*$/, "")       // Remove version suffix like -4
-    .replace(/@.*$/, "");               // Remove @latest etc.
-  // Keep meaningful prefix
-  return cleaned || model;
-}
-
-/**
- * Get cache stats (for dashboard)
- */
-export function getCacheStats() {
-  return {
-    tool: {
-      entries: layers.tool.size,
-      patterns: Array.from(layers.tool.values()).reduce((sum, s) => sum + s.size, 0),
-    },
-    family: {
-      entries: layers.family.size,
-      patterns: Array.from(layers.family.values()).reduce((sum, s) => sum + s.size, 0),
-    },
-    session: {
-      entries: layers.session.size,
-      patterns: Array.from(layers.session.values()).reduce((sum, s) => sum + s.size, 0),
-    },
-    defaultCount: DEFAULT_SIGNATURES.length,
-  };
-}
-
-/**
- * Clear all cache layers (for testing)
- */
-export function clearCache() {
-  layers.tool.clear();
-  layers.family.clear();
-  layers.session.clear();
-}

open-sse/services/systemPrompt.ts

@@ -1,66 +0,0 @@
-/**
- * System Prompt Injection — Phase 10
- *
- * Injects a global system prompt into all requests at proxy level.
- */
-
-// In-memory config
-let _config = {
-  enabled: false,
-  prompt: "",
-};
-
-/**
- * Set system prompt config
- */
-export function setSystemPromptConfig(config) {
-  _config = { ..._config, ...config };
-}
-
-/**
- * Get system prompt config
- */
-export function getSystemPromptConfig() {
-  return { ..._config };
-}
-
-/**
- * Inject system prompt into request body.
- *
- * @param {object} body - Request body
- * @param {string} [promptText] - Override prompt text
- * @returns {object} Modified body
- */
-export function injectSystemPrompt(body, promptText = null) {
-  const text = promptText || _config.prompt;
-  if (!text || !_config.enabled) return body;
-  if (!body || typeof body !== "object") return body;
-  if (body._skipSystemPrompt) return body;
-
-  const result = { ...body };
-
-  // OpenAI/Claude format (messages[])
-  if (result.messages && Array.isArray(result.messages)) {
-    const sysIdx = result.messages.findIndex((m) => m.role === "system" || m.role === "developer");
-    result.messages = [...result.messages];
-    if (sysIdx >= 0) {
-      // Prepend to existing system message
-      const msg = { ...result.messages[sysIdx] };
-      msg.content = text + "\n\n" + (msg.content || "");
-      result.messages[sysIdx] = msg;
-    } else {
-      result.messages = [{ role: "system", content: text }, ...result.messages];
-    }
-  }
-
-  // Claude format (system field)
-  if (result.system !== undefined) {
-    if (typeof result.system === "string") {
-      result.system = text + "\n\n" + result.system;
-    } else if (Array.isArray(result.system)) {
-      result.system = [{ type: "text", text }, ...result.system];
-    }
-  }
-
-  return result;
-}