mirror of
https://github.com/supabase/supabase.git
synced 2026-10-05 17:35:10 +03:00
codex/fix-tanstack-e2e
58
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Charis
|
13de8189c9 |
feat(studio): assistant get_active_incidents on status page endpoint (#50994)
## Summary * Adds a second branch to the assistant's `get_active_incidents` tool (`apps/studio/lib/ai/tools/incident-tools.ts`) that reads `/api/status-page` when the global ConfigCat flag `incidentIoStatusPage` is on, instead of the legacy `/api/incident-status` endpoint. * Filters on `visible`, ignores `show_banner` (only the global banner respects it), and concatenates ongoing incidents + in-progress maintenances (not scheduled maintenances). * Adds `isServerFlagEnabled` to `lib/server/configcat.ts` for reading global, non-user-targeted ConfigCat flags server-side, and threads the flag through `getTools` from `pages/api/ai/sql/generate-v4.ts`. This is PR 3 of 6 in the [FE-4057](https://linear.app/supabase/issue/FE-4057/frontend-bannerbot-reconfigured) stack — stacked on `charis/fe-4057-pr2-support-form`. Behind the `incidentIoStatusPage` flag (default off), so this ships no user-visible change on its own. See Linear [FE-4057](https://linear.app/supabase/issue/FE-4057/frontend-bannerbot-reconfigured) for full context. ## Test plan - [X] `pnpm --filter studio run typecheck` - [X] `pnpm --filter studio run lint:ratchet` - [X] `pnpm knip --workspace apps/studio` - [X] `pnpm test:prettier` - [X] `pnpm --filter studio exec vitest run lib/ai/tools/incident-tools.test.ts` (19/19 passing, including 7 new tests for the status-page branch) |
||
|
Saxon FletcherandClaude Opus 5.5
|
5e59b6047e |
chore(studio): extend Assistant response time and handle timeouts (#50892)
## Problem
- Assistant responses were capped at 120 seconds and 10 steps, which is
too short for longer reasoning or multi-step tool work.
- When the hosting platform ended a request at that limit, the
connection just dropped. The user got no explanation, and "Thinking…"
and tool rows kept spinning.
- Studio's own tools ignored the request's abort signal, so a stop,
disconnect or deadline couldn't cancel their in-flight requests.
- Aborted responses never closed their Braintrust span. Under TanStack
Start, the remote MCP client was only released on `res.on('close')`,
which the adapter never emits.
## Solution
Uses AI SDK options instead of custom stream handling:
- `maxDuration` goes to 300s and the step limit to 20. `streamText({
timeout: { totalMs } })` stops the response at 270s, leaving time to
finish the stream before the platform cutoff.
- `toUIMessageStream({ messageMetadata })` marks an aborted response
`timedOut: true`. `Chat` ignores `abort` chunks, so the client reads
this flag instead and shows a timeout alert with Retry. The flag is
saved with the message, so the alert survives a reload.
- `toUIMessageStream({ onEnd })` aborts the request whenever the stream
ends, releasing the MCP client on both runtimes. `streamText({ onAbort
})` ends the Braintrust span.
- Studio tools pass the SDK's `abortSignal` to their fetches. MCP tools
already did.
- Reasoning and server-tool rows that never finished show "Response
interrupted" instead of a spinner or "Ran X ✓".
There's no per-tool timeout. Approved SQL and migrations can
legitimately run longer, and aborting the HTTP request doesn't stop the
query in Postgres.
## Review instructions
1. Run the unit tests: `cd apps/studio && pnpm vitest run
lib/api/generate-v4.test.ts lib/ai components/ui/AIAssistantPanel`
2. To see a timeout without waiting 4.5 minutes, temporarily set
`ASSISTANT_TIMEOUT_MS` in `apps/studio/lib/ai/assistant-timeout.ts` to
`15_000` and run `pnpm dev:studio`.
3. Ask the Assistant something that needs several tool calls or long
reasoning, for example "Audit my schema for missing indexes and RLS
gaps, then write the fixes."
4. After 15 seconds, check that:
- the response stops and a "Assistant response timed out" alert appears
with Retry
- any in-progress reasoning or tool row shows "Response interrupted"
instead of spinning
- Retry starts a new response
- reloading the page still shows the alert on that chat
5. Stop a response with the Stop button before the deadline. It should
stop without the timeout alert.
6. With the default 270s, confirm that a normal response completes as
before.
## Checklist
Check all before review:
- [ ] I have read
[CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md)
- [ ] If I wrote a new docs topic or edited an existing topic, I used
the `/write-the-docs` or `/edit-the-docs` skill, which references
[WORD_LIST](https://github.com/supabase/supabase/blob/master/apps/docs/WORD_LIST.md)
and the docs
[CONTRIBUTING](https://github.com/supabase/supabase/blob/master/apps/docs/CONTRIBUTING.md)
guide
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Improvements**
* AI assistant responses can now run for up to five minutes, supporting
longer requests.
* When a response times out, the assistant displays a message suggesting
you retry or ask for a smaller change.
* Incomplete responses now show a “Response interrupted” notice, and
loading indicators stop when generation ends.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>
|
||
|
|
ec574f3a51 |
fix(studio): pass Authorization header to assistant list_policies tool (#50756)
<!-- ccr-slack-attribution --> _Requested by **Saxon Fletcher** · [Slack thread](https://supabase.slack.com/archives/C051L8U2EJF/p1789995309253479?thread_ts=1789995309.253479&cid=C051L8U2EJF)_ Resolves AI-1246 ## Problem **Before:** The Assistant's `list_policies` tool fails in about 70% of traces. It only "succeeds" when the org has AI opt-in disabled, because then it returns the privacy stub and never makes a request. When opt-in is enabled, it runs the pg-meta query server-side with no `Authorization` header, so the request is unauthenticated and fails. The Assistant then falls back to `execute_sql`. **After:** `list_policies` sends the caller's `Authorization` header, the same way `execute_sql` in `studio-tools.ts` already does, so it returns the project's RLS policies. ## Solution `getTools` already receives `authorization` but didn't pass it to `getSchemaTools`. This PR passes it through. `list_policies` builds `{ Authorization }` from it, and `getDatabasePolicies` gets an optional `headersInit` argument that it forwards to `executeSql`, the same pattern `getDatabaseFunctions` uses. Existing client-side callers of `getDatabasePolicies` don't change. Files: `lib/ai/tools/index.ts`, `lib/ai/tools/schema-tools.ts`, `data/database-policies/database-policies-query.ts`, plus tests in `lib/ai/tools/schema-tools.test.ts` (new) and `lib/ai/tools/index.test.ts`. ## Review instructions 1. Read `schema-tools.ts` and compare it with the `authHeaders` handling in `studio-tools.ts` (`execute_sql`). 2. On the preview, use an org with AI opt-in set to at least "schema" and ask the Assistant to list the RLS policies on `public`. `list_policies` should return the policies without falling back to `execute_sql`. Local gates (all passed): - `pnpm typecheck` in `apps/studio` (next typegen + `tsc --noEmit`) - `npx eslint` on touched files: 0 errors. The 2 warnings are on lines this PR doesn't change. - `npx vitest run lib/ai/tools/schema-tools.test.ts lib/ai/tools/index.test.ts lib/ai/tool-filter.test.ts`: 24/24 passed. I also ran the new header test against the old `schema-tools.ts` and it failed, as expected. - `SORT_IMPORTS=false npx prettier --config prettier.config.mjs --check` on touched files Follow-up, not in this PR: `getRlsKnowledge` in `fallback-tools.ts` (self-hosted path) also calls `getDatabasePolicies` without headers, even though a `headers` object is already in scope there. ## AI disclosure Claude Code (agent) wrote this PR from the Slack request. @SaxonF (Saxon Fletcher) is the accountable human owner. A human needs to review it before merge. ## Checklist - [x] I have read [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) - [ ] If I wrote a new docs topic or edited an existing topic, I used the `/write-the-docs` or `/edit-the-docs` skill (N/A, no docs changes) 🤖 Generated with [Claude Code](https://claude.com/claude-code) https://claude.ai/code/session_0171Mk7SiKYLDDoAQvbDYfeK --- _Generated by [Claude Code](https://claude.ai/code/session_0171Mk7SiKYLDDoAQvbDYfeK)_ --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: Joshen Lim <joshenlimek@gmail.com> |
||
|
Matt RossmanandJoshen Lim
|
4bb36b944f |
feat(studio): let High Compliance projects opt-in to Assistant data access (#50548)
Orgs with the HIPAA add-on had the Assistant's opt-in level forced to `disabled` on any project marked High Compliance, regardless of what the org picked in its AI settings. The restriction predated our AI provider BAAs. The consequence is those users see the Assistant failing to answer questions about their data w/ no clear path how to fix it, even though the LLM provider supports this use case. This PR removes these Assistant restrictions on the server and client so those projects honor the org's chosen level. Braintrust conversation tracing is unchanged and still blocked for these projects, see [this test case](https://github.com/supabase/supabase/blob/b9800ccf16/apps/studio/lib/ai/braintrust-logger.test.ts#L16-L20). See [comments](https://linear.app/supabase/issue/AI-1153/allow-hipaa-orgs-to-opt-in-to-assistant-data-access-for-high#comment-485a0d46) for legal approval and conditions. The client-side changes enable features like "Debug with AI" on SQL query failures, “Generate/Rename with AI” for snippet titles, and generated Assistant chat titles for these customers. The AI opt-in copy now adds a reminder to obtain consent from data subjects, linking the [shared responsibility model](https://supabase.com/docs/guides/deployment/shared-responsibility-model) based also on [this comment](https://linear.app/supabase/issue/AI-1153/allow-hipaa-orgs-to-opt-in-to-assistant-data-access-for-high#comment-f81ee610). <img width="400" alt="CleanShot 2026-09-17 at 5 01 02 PM@2x" src="https://github.com/user-attachments/assets/d02123f2-3e32-4d83-9f98-7d15e59222ef" /> To test with a HIPAA-enabled project in staging, you can use this [Plan Change [Staging]](https://app.hex.tech/supabase/app/Plan-Change-Staging-032BD32jo1EaisCS85qunf/latest) Hex to add the HIPAA add-on. Once the add-on is present, you can turn on High Compliance from a project's settings. Also in org settings, crank up the Assistant data opt-in level and verify the Assistant is able to answer questions about the project's data. My results testing with opt-in level "Schema, Logs & Database Data": | High compliance setting | Data opt-in working | |--------|--------| | <img width="1302" height="422" alt="CleanShot 2026-09-17 at 5 03 36 PM@2x" src="https://github.com/user-attachments/assets/c416371b-2eb8-49df-9c07-6d8eababb443" /> | <img width="1566" height="1516" alt="CleanShot 2026-09-17 at 5 05 14 PM@2x" src="https://github.com/user-attachments/assets/39624355-7f8f-46ce-9f08-a8acfb9da830" /> | Closes AI-1153 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit ## New Features - AI-assisted query renaming, snippet title generation, debugging, and tools now follow organization AI opt-in settings rather than project HIPAA status. - Debugging assistance and AI actions remain available for eligible users without additional HIPAA-based blocking. - AI metadata warnings consistently show standard opt-in messaging and permission settings. - AI settings remind users to obtain consent before entering personal data and link to shared responsibility guidance. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Joshen Lim <joshenlimek@gmail.com> |
||
|
Matt Rossman
|
a133ef60a6 |
fix(studio): correct the Assistant's blocked-tool privacy message (#50411)
When the Assistant calls a tool that's blocked on permissions, the response had two problems. First, it told users their data goes to Amazon Bedrock when production inference [routes to OpenAI](https://github.com/supabase/supabase/blob/b824acdfd204071f931a0aee01bee953ef164b6b/apps/studio/pages/api/ai/sql/generate-v4.ts#L170-L172). It now says "third-party AI providers" like the [opt-in settings](https://github.com/supabase/supabase/blob/b824acdfd204071f931a0aee01bee953ef164b6b/apps/studio/components/interfaces/Organization/GeneralSettings/AIOptInLevelSelector.tsx#L84-L88) do. I verified that was the last user-facing Bedrock mention. Second, HIPAA-restricted projects got that same copy telling them to change data opt-in settings, but for those projects `getAIDetails` [forces their level to `disabled`](https://github.com/supabase/supabase/blob/b824acdfd204071f931a0aee01bee953ef164b6b/apps/studio/lib/ai/ai-details.ts#L70-L73). They get separate copy now to prevent confusion. Closes AI-1154 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Added HIPAA-aware AI controls for eligible projects. - AI opt-in is automatically disabled when HIPAA requirements apply. - Privacy messages now distinguish standard AI opt-in restrictions from HIPAA-related restrictions. - AI-assisted SQL and tool experiences consistently apply HIPAA restrictions when determining available capabilities. - **Bug Fixes** - Improved handling of AI settings for HIPAA-sensitive projects and invalid project or organization configurations. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Pedro RodriguesandClaude Sonnet 5
|
22d7bc0cfd |
feat(studio-evals): custom search_docs tool for the eval harness (no token / no PAT) (#50092)
- Eval harness's only live tool, `search_docs`, no longer needs the in-process MCP client or its dummy token — it now calls the public docs GraphQL API (`https://supabase.com/docs/api/graphql`) directly. Low risk as this is an eval-harness change only. Production assistant path (`mcp-tools.ts`) untouched. **Update:** per [@mattrossman's review](https://github.com/supabase/supabase/pull/50092#discussion_r3980396341), the eval tool's description embeds the Content API's own GraphQL schema (fetched via a `{ schema }` query and minified with `gqlmin`), mirroring how `@supabase/mcp-server-supabase`'s `docs-tools.ts`/`loadSchema` populates production's `search_docs` description. Without it, the model had no schema to work from and issued malformed queries, which caused the 218 `search_docs` errors and the -25pp Docs Faithfulness regression in the first eval run on this PR. Schema loading is required: `createSearchDocsTool()` rejects if the schema fetch fails, so preflight and the gated eval job fail loudly instead of producing untrustworthy fallback results. `createSearchDocsTool` is async because the `ai` package's `tool()` only accepts a plain string `description`, unlike the MCP SDK's async description support; both callers (`getMockTools`, `evals/preflight.ts`) await it. `gqlmin` is a direct `apps/studio` dependency and was already transitive via `@supabase/mcp-server-supabase`. ### Verification - `pnpm -C apps/studio exec -- tsc --noEmit` reaches the compiler; it reports only the pre-existing unrelated `packages/ui-patterns/src/McpUrlBuilder/components/InstructionBlocks.tsx` `StaticImageData` error. - `pnpm -C apps/studio exec -- vitest run lib/ai/tools/mock-tools.test.ts lib/ai/tools/mcp-tools.test.ts` — 21/21 passed. - `pnpm exec tsx evals/preflight.ts` — live docs API schema fetch and search_docs call passed. - `NEXT_PUBLIC_CONTENT_API_URL=http://127.0.0.1:1/graphql pnpm -C apps/studio exec -- tsx evals/preflight.ts` — failed fast as expected, proving schema/API failures gate evals. - Fresh `run-evals` pass: Docs Faithfulness 55.7% (0pp), with no systemic `search_docs` regression. Risk: eval-harness-only; schema/API outage now fails the eval job before scoring rather than allowing fallback descriptions. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added documentation search powered by the public Supabase documentation GraphQL API. * Documentation search results now include live schema information and clearer error handling for failed or invalid requests. * **Bug Fixes** * Improved evaluation tooling reliability by removing unnecessary connection-abort behavior. * Updated validation to detect missing search tools and malformed documentation responses. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com> |
||
|
Gildas GarciaandAlaister Young
|
737b8595f2 |
Update API types (#50234)
## Problem platform, v1 and v2 have been already completely migrated and introduced some changes. Some types have been renamed, some outputs and inputs updated. ## Solution - Update the API types - Fix the TS errors ## Update Taking this over to unblock #50134, which needs the new scoped token permission ids from the regenerated types. - Merged `master`. - Regenerated `api-v2.d.ts` from the production spec. The previous files came from a local API that exposed a webhook events endpoint production doesn't have yet. Production has since added standardized 400 error responses on the v2 organization endpoints. `api-v1.d.ts` and `platform.d.ts` already matched production. - Fixed `verify-production-types`. It formatted the regenerated files in a temp directory outside the repository, so Prettier fell back to its defaults and the comparison could never match the committed files. It now passes the repository config explicitly. `pnpm api:verify-types` passes on this branch. - Verified locally: `pnpm typecheck`, `pnpm api:verify-types`, Studio unit tests. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Preserved descriptions when saving, sharing, moving, or unsharing notebooks, reports, SQL snippets, and saved queries. * Improved handling of empty or null values across notebook descriptions, billing usage, pooler settings, and infrastructure fields. * Improved read-replica connection handling, including read-only connection strings. * Updated storage configuration and capability handling to match current settings. * **API and Compatibility** * Updated organization, project, storage, OAuth, billing, and infrastructure data handling to match current API responses. * OAuth app creation and updates now require scopes. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Alaister Young <10985857+alaister@users.noreply.github.com> |
||
|
|
1966209483 |
chore(deps): upgrade vitest to v5 (#49994)
Upgrades Vitest from 4.1.4 to 5.0.0 across the monorepo, fixes the handful of things v5 turned into hard errors, and drops the `vi.clearAllMocks()` boilerplate that v5's `clearMocks` default makes redundant. **Changed:** - `vitest`, `@vitest/ui`, `@vitest/coverage-v8` 4.1.4 → 5.0.0 (catalog) - `vi.mock` calls that lived inside `beforeAll`/`beforeEach`/test bodies moved to module scope (v5 throws on nested calls). Affects the Studio and docs setup files and four Studio tests. - `detectBrowser` test restores `navigator` via `vi.unstubAllGlobals()` instead of assigning `global.navigator`, which now reaches jsdom's getter-only property. - `RowEditor.utils.test.ts` restores its `JSON.stringify` spy. It used to leak a throwing mock for the rest of the file, which v5's coverage provider now trips over. A later test in the same file had been asserting the leak's side effect (valid JSON reported as invalid) and now asserts the correct behavior. - `@testing-library/jest-dom` 6.6 → 7.0.1. Its vitest type augmentation resolves through a peer now, so it lands on each package's own `vitest` instead of whichever copy pnpm hoisted. Fixes `toBeInTheDocument` type errors in dev-tools after the reshuffle. - `@testing-library/react` 16.0.0 → 16.3.3 for the React 19 peer range. - `vite: catalog:` added to dev-tools, www, and common. Without it they resolved a newer vite than the catalog pin, which forked a second vitest instance in the lockfile. There's now one. - ai-commands custom matcher types use v5's `Matchers<R, T>` form. - 110 test files: `vi.clearAllMocks()` removed from `beforeEach`/`afterEach` hooks, along with hooks that only did that and the imports they left unused. Calls that also reset/restore mocks are untouched. Second commit, mechanical. **Added:** - `.vitest/` to the root gitignore (v5 writes JSON/JUnit/HTML reporter output there) **Removed:** - `vite-tsconfig-paths` catalog entry and deps. Vitest 5 resolves tsconfig paths itself. Release-age note: this sat in draft with a temporary `minimumReleaseAgeExclude` entry for `vitest` and `@vitest/*` while 5.0.0 was inside the workspace's 3-day `minimumReleaseAge` window. That window has closed, so the exclusion is gone and nothing bypasses the release-age gate. **Perf** (local, medians of 3 runs, same machine): | Suite | v4.1.4 | v5.0.0 | |---|---|---| | studio | 144.1s | 141.7s (-2%) | | studio `--coverage` | 156.9s | 146.4s (-7%) | | ui-patterns | 6.27s | 5.07s (-19%) | | ui `--coverage` | 3.35s | 2.14s (-36%) | | www | 0.89s | 0.47s (-47%) | Studio is dominated by jsdom environment setup per file, which v5 doesn't change. `vitest doctor` recommends keeping the current pool config: the vm pools and `isolate: false` all break tests. ## To test - `pnpm install --frozen-lockfile` succeeds with no `minimumReleaseAgeExclude` entry for vitest. - CI: Studio unit tests, ui, ui-patterns, www, docs, and typecheck/lint should all be green. The lint ratchet was checked locally: warning counts on touched Studio files are identical to master. - `pnpm test:studio` locally passes with coverage (588 files, 6240 tests). - Open a Studio test that uses `toBeInTheDocument` in your editor and confirm no type errors on jest-dom matchers, in Studio and in `packages/dev-tools`. - Known pre-existing failures unrelated to this PR: one dev-tools test (`getEventCountBadge` capped pill) fails on master too. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit ## Tests - Improved test coverage for JSON validation and mobile navigation behavior. - Updated test setup, cleanup, environment configuration, and matcher support across application and shared package suites. - Removed obsolete coverage for alternate MCP transport selection. ## Chores - Streamlined TypeScript path resolution and Vitest reporter output handling. - Updated testing libraries and Vitest tooling across documentation, Studio, website, and shared packages. - Added Vitest reporter output to ignored files. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Alaister Young <10985857+alaister@users.noreply.github.com> Co-authored-by: Ivan Vasilov <vasilov.ivan@gmail.com> |
||
|
Pedro RodriguesandClaude Sonnet 5
|
e5f2b29625 |
refactor(studio): remove USE_REMOTE_MCP gate, always use remote MCP server (#50089)
## Summary - Removes the `USE_REMOTE_MCP` env-var gate from the dashboard assistant: `getMcpTools` now always connects to the remote MCP server (the rollout from #47479 has been stable ~2 months and is enabled in prod). - Drops the var from `apps/studio/turbo.jsonc` and deletes the now-obsolete transport-selection tests. - The legacy in-process client (`createInProcessSupabaseMCPClient`) stays, re-scoped to the hermetic eval harness (`mock-tools.ts`, `evals/preflight.ts`); removing it is tracked by AI-897. ## Verification - `pnpm exec tsc --noEmit` in apps/studio: no errors in any changed file (one pre-existing unrelated error in `packages/ui-patterns/.../InstructionBlocks.tsx`). - `mcp-tools.test.ts` (7), `mock-tools.test.ts` (15), `tools/index.test.ts` (6), `supabase-mcp.test.ts` (11) all pass. ## Risk Low. Remote failure already degrades to non-MCP tools in `getTools`; rollback = revert this PR (or re-add the gate). ## Follow-up After this lands in prod, `USE_REMOTE_MCP` can be removed from the Vercel env vars — nothing in the repo reads it anymore. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Improvements** * AI tools now consistently use the remote service when retrieving available tools. * If the remote service is unavailable, times out, or cannot authenticate, the assistant continues operating with the tools that remain available. * Evaluation and development behavior now more closely reflects the remote service experience. * **Maintenance** * Updated supporting documentation and automated coverage to reflect the streamlined tool connection behavior. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: Claude Sonnet 5 <noreply@anthropic.com> |
||
|
|
e0280cb650 |
docs: restructure observability navigation and overview (#49505)
<!-- CURSOR_AGENT_PR_BODY_BEGIN --> ## Stack Draft stack extracted from `docs/monitoring`. Merge bottom-up. The troubleshooting *catalog* rewrite (`content/troubleshooting` and the Diagnosing UI) stays out of scope. 1. #49503 move inspect and advisors 2. #49501 split Studio logs from ClickHouse queries 3. #49500 treat reports as signal dashboards 4. #49502 add Observe the data hub 5. #49506 add agent setup components 6. #49504 add hire-an-agent templates 7. **#49505** restructure observability nav, overview, Detecting, and flatten Observe the data ← **this PR** ## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Docs update. Top layer in the observability stack. ## What is the current behavior? The section is still titled Monitoring and Debugging, with a Debugging / Monitoring split that does not match the new pages. The debugging guide is still the master layer-isolation + symptom table. Observe the data is split into “what data” vs “where to observe it,” which duplicates the source pages. ## What is the new behavior? - Section title is Observability - Overview groups Observe the data, Detect and resolve, Hire an agent, and Export - **Observe the data is flattened by source.** Logs, Metrics API, Database, Advisors, and Reports each list where to read that source. There is no separate MCP/API/CLI/Studio nav group. - **Observe vs Detecting:** Observe is the catalog (what exists, how to access it). Detecting is how to *use* those sources to pick up a Health / Security / Performance / Usage signal. Named errors skip to Diagnosing. - Studio Logs sits under Logs. Reports sits beside the other sources. - Troubleshooting stays in the global menu and also appears as Diagnosing under Detect and resolve ## Additional context This is the last PR in the stack. Together the seven PRs reconstruct the `docs/monitoring` observability IA and guide content, without shipping the troubleshooting catalog overhaul. <!-- CURSOR_AGENT_PR_BODY_END --> <div><a href="https://cursor.com/agents/bc-a3cb5ece-925b-4046-b58a-5d69e9a9d794?cursor_ref=pr_footer&cursor_cta=open_in_web"><picture><source media="(prefers-color-scheme: dark)" srcset="https://cursor.com/assets/images/open-in-web-dark.png"><source media="(prefers-color-scheme: light)" srcset="https://cursor.com/assets/images/open-in-web-light.png"><img alt="Open in Web" width="114" height="28" src="https://cursor.com/assets/images/open-in-web-dark.png"></picture></a> <a href="https://cursor.com/background-agent?bcId=bc-a3cb5ece-925b-4046-b58a-5d69e9a9d794&cursor_ref=pr_footer&cursor_cta=open_in_cursor"><picture><source media="(prefers-color-scheme: dark)" srcset="https://cursor.com/assets/images/open-in-cursor-dark.png"><source media="(prefers-color-scheme: light)" srcset="https://cursor.com/assets/images/open-in-cursor-light.png"><img alt="Open in Cursor" width="131" height="28" src="https://cursor.com/assets/images/open-in-cursor-dark.png"></picture></a> </div> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Saxon Fletcher <SaxonF@users.noreply.github.com> Co-authored-by: Nik Richers <nik@validmind.ai> |
||
|
|
0bbd64743c |
docs: move inspect and advisors into observability (#49503)
<!-- CURSOR_AGENT_PR_BODY_BEGIN --> ## Stack Draft stack extracted from `docs/monitoring`. Merge bottom-up. Troubleshooting / debugging-guide rewrite is out of scope. 1. **#49503** move inspect and advisors ← **this PR** 2. #49501 split Studio logs from ClickHouse queries 3. #49500 treat reports as signal dashboards 4. #49502 add Observe the data hub 5. #49506 add agent setup components 6. #49504 add hire-an-agent templates 7. #49505 restructure observability nav and overview ## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Docs update. First layer in the observability stack. ## What is the current behavior? Inspect and advisors live under Database (`/guides/database/inspect`, `/guides/database/database-advisors`). Observability readers have to leave the monitoring section to find them. ## What is the new behavior? - Moves inspect into `/guides/monitoring-and-debugging/inspect` - Adds `/guides/monitoring-and-debugging/advisors` (replaces the Database Advisors page) - Adds redirects and updates Studio/docs links so old URLs keep working - Adds both pages to the existing Monitoring nav so they are discoverable before the later IA PR ## Additional context Inspect and advisors pages render as standard MDX. Redirects cover `/docs/guides/database/inspect`, `/docs/guides/database/database-advisors`, and `/docs/guides/database/database-linter`. Debugging-guide content is unchanged except the inspect URL. ## Self-review - No leftover `/guides/database/inspect` or `/guides/database/database-advisors` links in docs guides or Studio linter/AI surfaces (historical blog posts left as-is) - Smoke test path updated to `/docs/guides/monitoring-and-debugging/advisors` <!-- CURSOR_AGENT_PR_BODY_END --> <div><a href="https://cursor.com/agents/bc-a3cb5ece-925b-4046-b58a-5d69e9a9d794?cursor_ref=pr_footer&cursor_cta=open_in_web"><picture><source media="(prefers-color-scheme: dark)" srcset="https://cursor.com/assets/images/open-in-web-dark.png"><source media="(prefers-color-scheme: light)" srcset="https://cursor.com/assets/images/open-in-web-light.png"><img alt="Open in Web" width="114" height="28" src="https://cursor.com/assets/images/open-in-web-dark.png"></picture></a> <a href="https://cursor.com/background-agent?bcId=bc-a3cb5ece-925b-4046-b58a-5d69e9a9d794&cursor_ref=pr_footer&cursor_cta=open_in_cursor"><picture><source media="(prefers-color-scheme: dark)" srcset="https://cursor.com/assets/images/open-in-cursor-dark.png"><source media="(prefers-color-scheme: light)" srcset="https://cursor.com/assets/images/open-in-cursor-light.png"><img alt="Open in Cursor" width="131" height="28" src="https://cursor.com/assets/images/open-in-cursor-dark.png"></picture></a> </div> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Added a centralized Advisors guide for security and performance checks. - Updated database inspection guidance with live Postgres statistics, cache hit-rate context, and query-analysis resources. - **Documentation** - Reorganized Advisors and database inspection content under Monitoring and Debugging. - Updated navigation, cross-references, in-product help links, and CLI documentation links. - Added permanent redirects from previous documentation URLs to preserve access. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Saxon Fletcher <SaxonF@users.noreply.github.com> Co-authored-by: Nik Richers <nik@validmind.ai> |
||
|
|
dcac820571 |
feat(studio): add assistant notebook run tool (#49361)
## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Assistant feature and data-handling plumbing. ## Stack context This stack is based on #49352 (`chore/assistant-tool-outcomes`) and assumes #49350–#49352 merge first. Review bottom to top: 1. #49361 — assistant notebook run tool 2. #49362 — assistant notebook run UI 3. #49364 — terminal-state polish ## What is the current behavior? The Assistant can read and edit notebooks, but it cannot execute all saved query cells as one approved operation. ## What is the new behavior? - Adds a `run_notebook` tool with one approval gate for the complete notebook. - Executes database and log cells sequentially in notebook order. - Rejects stale runs when the notebook changed after the Assistant read it. - Resolves primary and read-replica connections and forwards authorization to log and replica requests. - Shares rows with the model only when the organization's AI data-sharing level permits it. - Strictly validates and sanitizes persisted notebook-run output before replaying message history. - Registers the tool in prompts, filtering, mocks, and tool construction. ## How to test manually This is the tool/data layer; use the top-of-stack preview from #49364 for the complete UI while checking these behaviors. 1. In Explorer, create and save a notebook named **Assistant run smoke test** with: - a markdown cell - a working database query - a working Logs query - a database query that returns no rows, such as `select 1 where false` 2. Open the AI Assistant and ask: **Read the “Assistant run smoke test” notebook and analyze it using its current results.** 3. Confirm the Assistant reads the notebook and requests one `run_notebook` approval for all query cells, rather than requesting one approval per cell. 4. Approve the run. Confirm database and Logs queries execute in notebook order, the markdown cell is not executed, and the Assistant responds only after the complete run finishes. 5. Start another run but do not approve it yet. In another tab, edit and save the notebook. Return to the pending approval and approve it. 6. Confirm the stale run is rejected, the Assistant reads the latest notebook version, and a new approval is required. 7. Optional privacy check: set the organization AI data-sharing level to schema-only, run a query containing a recognizable value, and confirm the value remains visible in the notebook result UI but is not repeated in the Assistant's answer. ## Automated test `mise exec node@22 -- pnpm --dir apps/studio exec vitest --run lib/ai/tool-filter.test.ts lib/ai/tools/index.test.ts lib/ai/tools/mock-tools.test.ts lib/ai/tools/notebook-tools.test.ts lib/ai/tools/tool-sanitizer.test.ts` 80 tests pass at this stack boundary. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Added AI-assisted notebook execution for database and log cells, with approval, freshness checks, replica support, and per-cell error handling. - Added notebook deletion and database discovery and validation for notebook management. - Added configurable privacy controls for notebook results. - Added request header support for analytics SQL execution. - **Bug Fixes** - Improved replica lookup handling so other notebook cells can continue when one lookup fails. - Prevented invalid, unauthorized, or overly detailed notebook execution results from being exposed. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Cursor Agent <cursoragent@cursor.com> Co-authored-by: Saxon Fletcher <SaxonF@users.noreply.github.com> |
||
|
CharisandJoshen Lim
|
89b4f1aca4 |
feat(studio): add delete_notebook tool to AI assistant (#49413)
## Summary * Adds a `delete_notebook` AI assistant tool (`needsApproval: true`) that lets the assistant delete a notebook with explicit user approval, mirroring the existing `create_notebook`/`update_notebook` tools. * Wires up a destructive-styled approval card in the AI Assistant Panel (fetches the notebook to show its name, warns the deletion is permanent) using the same `Confirm`/tool-approval plumbing as the other notebook tools. * Updates `tool-filter.ts` opt-in gating, the assistant system prompt, the eval-harness mock tools, and the eval dataset with `delete_notebook` coverage. * Adds test coverage in `notebook-tools.test.ts`, `mock-tools.test.ts`, and `NotebookProposalRenderer.test.tsx`. Closes [FE-4242](https://linear.app/supabase/issue/FE-4242/assistant-delete-notebook-tool). ## Test plan - [X] `pnpm typecheck --filter=studio` passes - [X] `pnpm --filter studio exec vitest run` for the touched files (notebook-tools, mock-tools, NotebookProposalRenderer, [Message.Parts](<http://Message.Parts>), and existing consumers of `content-delete-mutation`) — all passing - [X] `eslint` and `prettier --check` clean on all touched files - [X] Manual verification of the approval UI in a running Studio instance (not done in this session) ## Summary by CodeRabbit * **New Features** * Added AI-assisted notebook deletion with explicit confirmation and irreversible-action warnings. * Added safeguards to distinguish deleting an entire notebook from removing individual panels. * Completed deletions now display the deleted notebook’s name without an option to reopen it. * **Bug Fixes** * Improved handling of missing notebooks and invalid deletion requests. * **Tests** * Added coverage for deletion approval, denial, errors, and successful completion. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added AI-assisted notebook deletion with explicit approval and irreversible-action warnings. * Added confirmation, loading, error, and completion states for notebook deletion. * Prevented accidental full-notebook deletion when only a panel or section should be removed. * Improved notebook update results by showing applied changes when available. * **Bug Fixes** * Notebook deletion now uses the required API version. * Improved handling and validation of missing notebooks during deletion. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Joshen Lim <joshenlimek@gmail.com> |
||
|
Charis
|
8920439569 |
Expose previous notebook content in update_notebook (#49401)
## Summary - Plumb pre-update notebook snapshot through `update_notebook` tool response as `previous_content` - Add sanitizers in `tool-sanitizer.ts` to strip snapshot before model sees it - Add client-side stripping in `prepareMessagesForAPI` to avoid re-uploading snapshot on subsequent turns - This is PR 2 of 3 fixing Linear issue FE-4243 (notebook update proposal shows 'unapplyable' error for already-completed updates) - Ships no visible behavior change on its own; enables PR 3 to restore diff preview for completed updates ## Test plan - [x] Unit tests: 80/80 passing across notebook-tools.test.ts, tool-sanitizer.test.ts, generate-assistant-response.utils.test.ts, message-utils.test.ts, and mock-tools.test.ts - [x] Typecheck: clean for all changed files - [x] ESLint: zero errors, lint:ratchet passes (exit 0) - [x] Integration: previous_content is correctly populated with pre-update notebook, stripped before model context, and stripped on client-side re-upload <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **Bug Fixes** - Notebook updates now retain previous content for recovery and history. - AI responses expose only the notebook’s ID and name, keeping previous content out of model-visible data. - **Tests** - Added coverage for notebook update results, content sanitization, and message preparation, including cases where previous content is absent or preserved. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Charis
|
ee59d28240 |
fix(studio): reject unknown database_identifier before writing a notebook (#49333)
## Summary - `create_notebook`/`update_notebook` now validate every `database_cell`'s `database_identifier` against the project's real database list (`getReadReplicas`) before writing, throwing an assistant-actionable `NotebookToolError` (same pattern as the existing `expected_updated_at` mismatch check) when it doesn't match. - Only fetches the database list when a cell actually sets `database_identifier` — no added cost for the common case. - `update_notebook` validates only the cells its own operations introduce (`insert_cell`/`replace_cell`), not the whole resulting notebook — otherwise an unrelated, untouched pre-existing cell whose replica was removed after the fact would block updates that never touch it. Part 4/6 of the stack for FE-4225 (expose valid database identifiers to the notebook AI agent). Stacked on #49332. This closes the gap that PR 3 reopened: a model can no longer invent an identifier that silently breaks a cell — it now gets a retryable error naming `list_databases` (added in #49328) as the way to find a real one. ## Test plan - [x] `create_notebook`/`update_notebook` reject an unknown `database_identifier` with `NotebookToolError` + `exposeToAssistant: true` - [x] Both succeed when the identifier matches a real database - [x] `create_notebook` never calls the databases endpoint when no cell sets `database_identifier` - [x] `update_notebook` succeeds without validating or fetching databases when no operation introduces a database_cell, even if an untouched existing cell carries a now-invalid identifier - [x] `pnpm --filter studio exec tsc --noEmit` passes <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added a database-listing tool that provides database identifiers and metadata, including primary-database status. * Database results now return only the relevant fields. * **Bug Fixes** * Added validation to prevent notebooks from referencing unknown databases. * Create and update actions now provide clear errors for invalid database identifiers. * Updates validate newly added or replaced cells while preserving existing, untouched cells. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Charis
|
0f730de9e0 |
feat(studio): add list_databases tool for the AI assistant (#49328)
## Summary
- Adds a `list_databases` tool to the notebook AI tools
(`getNotebookTools`), returning `{ identifier, is_primary, region,
status }` for the project's primary and any read replicas, via
`getReadReplicas`.
- Registers `list_databases` in `tool-filter.ts` (opt-in validation
schema + SCHEMA category), and adds a mock fixture in `mock-tools.ts`
for evals.
Part 2/6 of the stack for FE-4225 (expose valid database identifiers to
the notebook AI agent). Stacked on #49327. A later PR in the stack
reinstates `database_identifier` on the agent-facing notebook schema and
requires the agent to call this tool first.
## Test plan
- [x] New test coverage in `notebook-tools.test.ts` for
`list_databases`, including `is_primary` computation
- [x] Existing exact-tool-set assertion updated
- [x] `pnpm --filter studio exec tsc --noEmit` passes
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added an AI notebook tool for listing a project’s databases.
* Results include each database’s identifier, region, status, and
whether it is the primary database.
* Supports projects with read replicas.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
|
||
|
Saxon Fletcher
|
aa2897f712 |
feat(studio): teach assistant to query ClickHouse logs (#49292)
## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Feature and bug fix. ## What is the current behavior? The assistant can call `query_logs`, but it is not given the ClickHouse schema and query-writing guidance it needs. It also lacks a current UTC reference for producing the absolute timestamps required by the tool, which can lead to valid queries being run against the wrong time range and reported as returning zero rows. ## What is the new behavior? - Adds a dedicated `logs` knowledge topic backed by the shared ClickHouse schema and query guidance. - Requires the assistant to load that knowledge before using `query_logs`. - Includes the current UTC time in project context so relative requests can be converted to correct absolute tool parameters. - Covers the new knowledge flow and context with focused tests and updates the assistant eval expectation. ## How to test 1. Check out this PR and run Studio against a project that has recent logs. Generate some project activity first, such as an API request, if needed. 2. Open the AI Assistant and ask: `Show log counts by minute for the last 15 minutes and summarize any spikes.` 3. Expand the assistant's tool activity and verify it loads the `logs` knowledge topic before calling `query_logs`. 4. Inspect the `query_logs` input and verify: - `iso_timestamp_start` and `iso_timestamp_end` are absolute UTC timestamps ending in `Z`. - The timestamps cover approximately the requested 15-minute window. - The SQL uses ClickHouse syntax, includes a `LIMIT`, and does not put the time range in the SQL `WHERE` clause. 5. Verify the assistant's summary reflects the rows returned by `query_logs` instead of reporting zero rows when results are present. ## Additional context This is the bottom PR in stack #49294. The front-end visualization is added separately in #49293. Verified with 59 focused tests across assistant context, Studio/MCP tools, query display, and logs result parsing. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Added AI-assisted project log querying through the `query_logs` tool. - Added logs knowledge guidance for time ranges, schema discovery, query limits, and concise result summaries. - Project context now includes the current UTC timestamp to improve relative time-range interpretation. - Improved notebook assistance with safer table verification and appropriate handling of log queries. - **Bug Fixes** - Prevented incorrect SQL timestamp filtering and enabled cross-service searches without requiring a source filter. - Added validation for supported knowledge topics. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Charis
|
ebd616fa90 |
fix(studio): auto-retry notebook updates on stale/invalid conflicts (#49323)
## Summary
- **Removed dead client-side refresh UI** in
`NotebookProposalRenderer.tsx` and its test — the diff preview is always
computed from live data, so the check was redundant with the tool's
server-side re-validation
- **Added typed `NotebookToolError`** in `notebook-tools.ts` with
structured metadata (`{ exposeToAssistant: boolean }`) validated by a
zod schema with a literal discriminant tag (`tag:
'notebook_tool_error'`) — tracks the two retryable failures: staleness
conflict and invalid operations (unknown cell id)
- **Encoded errors in `generate-v4.ts` onError** — the one place in the
pipeline that holds the live `Error` before it becomes a string in the
persisted message
- **Extracted and fixed message history filter** into new
`generate-assistant-response.utils.ts` — any tool-error whose
`errorText` decodes against the `NotebookToolError` schema is let
through (with `errorText` rewritten to plain prose so the model sees the
message, not JSON), while other errors stay filtered as before
Net effect: the assistant detects the specific, actionable rejection
reason and retries on its own with no dead button or human intervention
needed.
## Test plan
- Existing unit tests in `NotebookProposalRenderer.test.tsx` pass (dead
button test removed)
- New unit tests in `notebook-tools.test.ts` cover encode/decode
round-trips and error discrimination
- New unit tests in `generate-assistant-response.utils.test.ts` cover
message history filtering with all error states
- `pnpm typecheck` is clean
- `pnpm --filter studio run lint:ratchet` passes (no new ESLint
warnings)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Notebook update errors now provide clearer, structured explanations to
the AI assistant.
* Assistant responses preserve relevant notebook error details while
filtering invalid or temporary tool states.
* **Bug Fixes**
* Improved handling of stale notebook revisions and invalid notebook
update operations.
* Notebook proposal rendering proceeds without an unnecessary refresh
step.
* **Tests**
* Expanded coverage for notebook errors, message filtering,
serialization, and error handling.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
|
||
|
Joshen Lim
|
2893c783d5 |
Hook up APIs for Notebooks CRUD (#49254)
## Context API changes are ready so hooking up the endpoints for full CRUD UX E2E - Can create notebooks - Can load notebooks - Can delete notebooks - Can update notebooks |
||
|
CharisandJoshen Lim
|
8bdfe03fe7 |
refactor(studio): drop notebook type widening now that the API supports it (#49272)
## Summary - Regenerates `packages/api-types` for the content endpoints now that the Platform API's `notebook` content type has landed (list/get/upsert `type` enums, plus `UpsertContentBody`'s notebook cell shape with `_id`/`y_series`). Unrelated schema drift from the same regen (Warehouse, SSO, notification exceptions, etc.) is excluded — only the content-endpoint hunks are applied. - Removes every local widening cast added while the API support was pending (`content-query.ts`, `content-infinite-query.ts`, `notebook-query.ts`, `notebook-upsert-mutation.ts`, `sql-folders-query.ts`). - What remains is scoped and renamed to match: draft ids (`generateDraftId`/`isDraftId`), used only for cells created client-side in the editor before their first save, dropped before they'd ever reach the backend as a fake `_id`. ## Test plan - [x] `pnpm typecheck` — clean - [x] `pnpm --filter studio test` — full suite passes (518 files / 5471 tests) - [x] `pnpm --filter studio run lint:ratchet` — no new warnings - [x] `pnpm format` / prettier — clean <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Improved notebook cell tracking during editing, reordering, insertion, and deletion. * Preserved existing cell identifiers while removing temporary draft identifiers before saving. * Improved chart configuration for selecting and displaying multiple Y-axis series. * Strengthened notebook validation and content persistence behavior. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Joshen Lim <joshenlimek@gmail.com> |
||
|
Saxon Fletcher
|
c80f8ad78d |
chore(studio): upgrade AI SDK to v7 (#49167)
## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Chore / dependency upgrade. ## What is the current behavior? Studio is on AI SDK 6 (`ai` ^6.0.174, `@ai-sdk/react` ^3). Tool approvals still use the v6 `needsApproval` flag on individual tools. ## What is the new behavior? Upgrades Studio to AI SDK 7 (`ai` 7.0.59) and the matching `@ai-sdk/*` packages. Aligns call sites with v7 names (`instructions`, `isStepCount`, `onEnd`, `ToolExecutionOptions`). This is the bottom of stack #49171. Later layers add a shared Confirm card and AssistantQueryCell. ## Additional context - Stack: #49167 → #49168 → #49169 → #49170 - `needsApproval` on tools is left as-is in this PR so the upgrade can land independently. A follow-up can move those gates to `streamText({ toolApproval })` and `experimental_toolApprovalSecret`. - Independent of the notebook preview stack ([#49112](https://github.com/supabase/supabase/pull/49112), [#49159](https://github.com/supabase/supabase/pull/49159)), which should merge first before we wrap notebook proposals in Confirm. ## Test plan - [ ] `pnpm --filter studio test` for `lib/ai/tools/*` and assistant generate path - [ ] Assistant chat still streams and tool-approval SQL / Edge Function still pause for confirm - [ ] Evals still run with mock tools (`needsApproval: false` overrides) <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Improvements** * Updated AI-powered chat, onboarding, SQL, code completion, and recipe generation workflows for more reliable responses. * Streaming responses now better preserve reasoning and source information where available. * Improved tool privacy notices while preserving dynamically generated tool descriptions. * Refined AI response handling, including step limits and structured policy results. * **Bug Fixes** * Improved compatibility across AI-powered tool interactions and execution scenarios. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Charis
|
9be60cab63 |
refactor(studio): add optimistic locking to update_notebook (#49111)
## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Refactor / hardening ## What is the current behavior? The `update_notebook` AI tool re-fetches the notebook right before applying operations, but concurrent edits are last-write-wins: the model has no way to detect that the notebook changed since it planned the edit, so a stale diff can silently overwrite someone else's changes. ## What is the new behavior? - `get_notebook` now returns the notebook's `updated_at` timestamp. - `update_notebook` requires a new `expected_updated_at` input field (the `updated_at` the model got from `get_notebook`). - At execute time, after the existing re-fetch and before applying operations, `update_notebook` compares the fetched `updated_at` against `expected_updated_at` and throws a descriptive error if they don't match, telling the model to re-read the notebook and reissue the update. - The notebook system prompt and mock tools (used by the eval harness) are updated to match. ## Additional context <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Notebook retrieval now includes the latest update timestamp. * Notebook edits require confirmation that the content is current before saving. * **Bug Fixes** * Prevented stale edits from overwriting newer notebook changes. * Conflicting updates are rejected, allowing the latest content to be fetched before retrying. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Joshen Lim
|
2f89014f74 |
Add logs cells (#49064)
## Context Related to Explorer/Notebooks - adds the source selector for query cell within a notebook <img width="1108" height="648" alt="image" src="https://github.com/user-attachments/assets/d1434197-3738-41b0-a8ef-1919c91181d9" /> <img width="1103" height="633" alt="image" src="https://github.com/user-attachments/assets/97f8c6a3-629d-4a41-aab4-3fdc5e8b2c7e" /> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added support for displaying log cells in the query editor. * Added switching between database and log query sources. * Log and database cells can display results as tables or charts. * Log queries support optional row limits. * Improved reliability when changing query settings. * Notebook query views now default to table display when unspecified. * **Bug Fixes** * Log cells no longer appear blank or get omitted from notebook views. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Joshen Lim
|
d434c63bad |
joshen/fe 4150 explorer query cells result display settings (#49003)
## Context Related to Explorer / Notebooks - this adds chart functionality for the Query cells <img width="250" alt="image" src="https://github.com/user-attachments/assets/4ea37c14-87dc-4c43-ba7f-cb9436085c81" /> Query results can be rendered as either bar or line chart - using the chart packages from `ui-patterns` [NOTE]: For design team reviewers - am patching the chart packages to be agnostic to the `timestamp` property within the provided data set. Would love to use this component from a consistency POV instead of the old `BarChart` component we have. Have intentionally omitted log scale functionality from this PR - will have that separately 🙏 <img width="999" height="483" alt="image" src="https://github.com/user-attachments/assets/14356ee4-c658-4fd1-90e0-17c38dac4822" /> <img width="988" height="478" alt="image" src="https://github.com/user-attachments/assets/cd0ca088-9a03-4aa3-9884-17bc36d3cabf" /> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Added chart views for notebook query results, including bar and line charts. - Added display settings for selecting X/Y columns, chart type, scale, cumulative values, and label visibility. - Added configurable X-axis support for charts. - Display preferences are saved with each notebook cell. - **Improvements** - New database cells default to table view. - Chart results better handle varied data types. - Empty results and incomplete chart settings now display clear placeholders. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Charis
|
8baaa517d0 |
test(studio): add list_notebooks eval cases (FE-4086) (#49010)
## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Feature (test coverage) — first PR of the notebooks-evals plan, covering FE-4086 (Evals: Assistant can list notebooks). ## What is the current behavior? `dataset.ts` has zero notebook eval cases. Separately, two small gaps block writing them: `assistant.eval.ts` never sets `isExplorerEnabled`, so `NOTEBOOKS_PROMPT` never loads into the eval task's system prompt; and `list_notebooks`' `inputSchema` has no sort parameter, even though `getContent` already supports one, so "most recent" isn't answerable. ## What is the new behavior? - `assistant.eval.ts` passes `isExplorerEnabled: true` so `NOTEBOOKS_PROMPT` loads during evals. - `list_notebooks` gains a `sort_by: 'name' | 'inserted_at'` param, forwarded to `getContent`'s `sort`. Only creation order is exposed, since the underlying API has no `updated_at` sort key. - 3 new dataset cases: basic notebook enumeration, sorting by creation time (`sort_by`/`limit` args), and a nonexistent-notebook case guarding against hallucinated results. - A unit test covering `sort_by` forwarding to the content API's query param. ## Additional context <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added notebook sorting options when listing notebooks, including by name or insertion date. * Added evaluation coverage for listing notebooks, finding the newest notebook, and avoiding fabricated results for nonexistent notebooks. * **Bug Fixes** * Ensured selected notebook sorting preferences are correctly applied when retrieving content. * Improved assistant evaluation coverage with Explorer mode enabled. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Charis
|
b9835e419c |
test(studio): mock notebook tools (#48952)
## Summary - Adds deterministic `list_notebooks`/`get_notebook` fixtures (two seeded notebooks, each with markdown/database/log cells) and stateful in-memory `create_notebook`/`update_notebook` mocks to `apps/studio/lib/ai/tools/mock-tools.ts`, so Braintrust evals can exercise notebook tool calls without a real project. - Both write-tool mocks force `needsApproval: false`, matching the existing `execute_sql`/`deploy_edge_function` mock pattern — the eval harness filters out tool-parts in `'approval-requested'` state and can never answer an approval gate. - All four notebook tools are wrapped from the real `getNotebookTools()` definitions (only `execute`/`needsApproval` overridden), so evals validate the model's arguments against the exact production schemas. - Dedupes `describeOperationError` (previously duplicated between this new mock and `notebook-tools.ts`) into a single exported `describeNotebookOperationError` in `notebook-operations.ts`. **Stacked on #48949** (`feature/notebooks-update-tool`) — this PR's base branch is that PR, not `master`, because it reuses `update_notebook` and the shared error helper that only exist there. Merge #48949 first, then retarget/merge this one. ## Test plan - [x] \`pnpm --filter studio typecheck\` passes - [x] \`pnpm --filter studio test\` — all notebook-related suites pass (\`mock-tools.test.ts\`, \`notebook-tools.test.ts\`, \`data/content/notebooks/*\`) - [x] \`eslint\` / \`prettier --check\` clean on all touched files |
||
|
Charis
|
4da8bfe469 |
feat(studio): wire update_notebook tool (#48949)
## Summary - Adds `update_notebook`, an AI tool (`needsApproval: true`) that re-fetches a notebook, applies an ordered list of cell operations (insert/replace/delete/move, from `notebook-operations.ts`) via `applyNotebookOperations`, and PUTs the resolved content. Concurrent edits are last-write-wins, since re-fetching at execute time is the only mitigation per the RFC. - Registers `update_notebook` in `toolSetValidationSchema` / `TOOL_CATEGORY_MAP`, and documents it in the notebooks system prompt. - The untrusted→safe SQL promotion (`acceptUntrustedSql`/`acceptUntrustedLogsSql`) is inlined directly inside each `needsApproval: true` tool's own `execute` (both `create_notebook` and `update_notebook`), rather than behind a shared helper — kept auditable right next to the approval gate that authorizes it, and not reusable by an unrelated caller unaware it needs re-promotion. Resolves FE-4083 ## Test plan - [x] `notebook-tools.test.ts`: re-fetch → apply operations → PUT with promoted SQL; descriptive error (no PUT) when an operation targets an unknown cell id; `needsApproval` asserted for both create and update - [x] `pnpm vitest run` on `notebook-tools.test.ts`, `tools/index.test.ts`, `tool-filter.test.ts` — all pass - [x] `tsc --noEmit`, `eslint`, `prettier --check` — clean on all touched files <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * AI-assisted notebook editing now supports updating existing notebooks. * Notebook changes are refreshed before being applied to help preserve the latest content. * Updates report operation errors and return a summary of the modified notebook. * Notebook edits require user approval before being saved. * **Bug Fixes** * Invalid or unknown cell references are reported without applying a partial update. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Pedro RodriguesandClaude Opus 4.8
|
47595f8ac7 |
feat(self-hosted): implement queryLogs for the MCP debugging tools (#48900)
> [!IMPORTANT] > > Only merge this when (https://github.com/supabase/platform/pull/36804) is merged, as the AI assistant will not have access to the `query_logs` tool for the remote MCP server ## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Feature (self-hosted / CLI Studio MCP server). ## What is the current behavior? Self-hosted `getDebuggingOperations` (`apps/studio/lib/api/self-hosted/mcp.ts`) implements only `getLogs`, so the MCP `debugging` group exposes `get_logs` — a fixed per-service log dump built by `getLogQuery`. Logs are served by Logflare, which speaks BigQuery SQL. ## What is the new behavior? Bumps `@supabase/mcp-server-supabase` to `^0.10.0` (adds `query_logs` + `logsDialect`, and hides `get_logs` wherever a platform declares `queryLogs`) and moves logs over to it. - **Self-hosted `query_logs`:** declares `logsDialect: 'bigquery'` and implements `queryLogs`, passing the model's SQL straight through to the same Logflare `logs.all` endpoint (arbitrary `sql` param) — no new endpoint, no dialect translation. - **Drops `get_logs` from self-hosted:** `getLogs` throws (the server hides it once `queryLogs` exists) and the per-service `getLogQuery` builder is deleted; the model now writes its own BigQuery SQL, guided by the dialect schema hint. - **Honors no-logs mode:** `query_logs` throws when `logs:all` is disabled — the self-hosted default, enabled via the `docker-compose.logs.yml` override. - **Assistant:** switches the dashboard assistant from `get_logs` to `query_logs` (allowlist, drift guard, prompt, mocks, evals). Refs AI-1046 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * AI debugging can query recent project logs using read-only SQL. * Log queries support optional time-range filters, filtering, aggregation, and joins. * Self-hosted debugging checks whether logging is enabled before running queries. * **Bug Fixes** * Updated debugging workflows and validation to consistently use the new log-query capability. * Removed reliance on legacy service-specific log filtering and query behavior. * **Documentation** * Updated MCP debugging tool guidance to describe SQL-based log queries. * **Tests** * Expanded coverage for enabled, disabled, and unsupported logging scenarios. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Charis
|
ddb3e2c442 |
feat(studio): create_notebook AI tool (#48938)
## Summary - Adds a `create_notebook` AI assistant tool (`needsApproval: true`) that lets the assistant create a new notebook after explicit user approval. - Cell SQL is promoted from untrusted to safe via `acceptUntrustedSql`/`acceptUntrustedLogsSql` inside `execute`, using the approval gate as the confirming user gesture (same pattern as `execute_sql`). - Input is validated against the existing agent-writable notebook schema, which rejects any agent-supplied cell `id` at the schema level. - Threads an optional auth-headers param through `upsertContent`/`createNotebook`/`updateNotebook` so the tool can pass its own bearer token server-side. - Registers the tool in the tool-filter (`SCHEMA` category, alongside `list_notebooks`/`get_notebook`) and adds a `## Notebooks` prompt section guiding the assistant on when to use `create_notebook` vs. one-off `execute_sql`. Resolves FE-4082 ## Test plan - [x] `notebook-tools.test.ts` covers: tool registration, `needsApproval`, cell-id rejection, valid input, PUT body shape, and the returned id — all passing - [x] Typecheck clean - [x] Lint clean (no new warnings) <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added AI-assisted notebook creation for saving multi-step investigations. * Added support for database and log SQL cells in newly created notebooks. * Notebook creation requires approval before saving and returns the notebook’s name and identifier. * Added support for custom request headers during notebook and content operations. * Added guidance for choosing between one-time SQL execution and reusable notebooks when Explorer is enabled. * **Improvements** * Improved validation and normalization of notebook content before saving. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Charis
|
7798e42435 |
feat(studio): notebook read tools (#48908)
## Summary - Adds `list_notebooks` (cursor-paginated) and `get_notebook` AI tools in `lib/ai/tools/notebook-tools.ts`, modeled directly on `report-tools.ts`: server-side `getContent`/`getNotebook` with the `authorization` header forwarded, zod-validated input. - `get_notebook` resolves every cell and exposes `unchecked_sql` as a plain `sql` field for the agent to read — display only, per the `safe-sql-execution` skill; nothing here executes SQL. - Registers both tools in `lib/ai/tools/index.ts` (same platform branch as reports) and in `lib/ai/tool-filter.ts`'s `toolSetValidationSchema` + `TOOL_CATEGORY_MAP` (`SCHEMA` tier). - Adds an optional `headers` param to `content-infinite-query.ts`'s `getContent`, mirroring the sibling `content-query.ts`, so the cursor-paginated fetch can carry the `Authorization` header from a server context. - New tools are behind the Explorer feature flag. Stacked on #48907 (1.4 — notebook query and mutation hooks), per the Notebooks implementation plan (stack 2.1). Resolves FE-4081 Resolves FE-4080 ## Test plan - [x] `pnpm exec tsc --noEmit` — no new errors - [x] `pnpm exec vitest run lib/ai/tools/notebook-tools.test.ts lib/ai/tools/index.test.ts lib/ai/tools/report-tools.test.ts data/content/notebooks` — 36/36 passing - [x] `pnpm --filter studio run lint` — no new warnings - [x] `pnpm exec prettier --check` on changed files — clean <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added AI tools to list project notebooks with pagination. * Added AI support for retrieving notebook markdown and resolved SQL cell content. * Notebook tools now respect project and authorization context. * Notebook features are available only when Explorer access is enabled. * Content requests can forward custom request headers. * **Tests** * Added coverage for notebook tools, Explorer access, feature flags, authorization, pagination, and error handling. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Joshen Lim
|
2c53ca4a79 |
Support listing and reading custom reports from Assistant (#48530)
## Context This is pre-requisite work for adding support to managing custom reports from the Assistant. Planning to break this into a number of PRs, briefly - Adding read support for custom reports - Adding write support for custom reports - Adding run support for custom reports - Should be able to infer data from the results then This PR starts with adding support for listing and reading custom reports from the Assistant ## Other changes involved - Updates setting up of the home page report to have better title and description - Swaps the variant of the ToggleGroup in the SQL block for custom reports as the default variant blends into the background color of the PopoverContent ## To test - [ ] Assistant should be able to list custom reports + read its contents <img width="428" height="755" alt="image" src="https://github.com/user-attachments/assets/6a15b660-c0ee-4a06-984c-87eff3943eec" /> <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit - **New Features** - Added AI-assisted tools to list reports and retrieve report details, including chart counts, layouts, configurations, and SQL-backed chart information. - Added clearer empty-state messaging when no snippets are available. - **Improvements** - New homepage reports now use the name “Homepage Report” and include a descriptive project-home summary. - Updated query controls with refreshed visual styling. - Improved content requests to support additional request context. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Joshen Lim
|
4901f081e5 |
Migrate remaining requests to pg-meta API to use query endpoint (#47758)
## Context Migrates the remaining API requests to the pg-meta endpoint to use the query endpoint directly with the SQL from the pg-meta package. This touches the following: - policies - publications - triggers - views - materialized views - types ## To test Just need to verify that we're still fetching the data correctly on these pages - Database policies - Database publications - Database triggers - Database tables (views + materialized views) - Database types <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Bug Fixes** * Improved and stabilized loading of database metadata (views, triggers, RLS policies, publications, materialized views, and enum types), including more reliable schema-scoped filtering. * Updated policy loading behavior and related UI queries to consistently use schema arrays, improving cache correctness and consistency. * **Tests** * Updated end-to-end test synchronization to wait for the correct metadata responses using more specific request identifiers. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Carel de WaalandAlaister Young
|
0acc0eb8b3 |
feat: Support Form - Sync AI assistant conversation to Front (#46778)
# Sync AI assistant conversation to Front ## What & why When a user submits a support ticket, an AI assistant chat opens so they get help immediately while waiting for a human agent. This PR mirrors every turn of that chat into the Front conversation the support form already created, so the support team sees the full context and Front automations (routing, emails, CSAT) can act on it. Studio holds no Front credentials — it calls the platform endpoints (see the platform PR) to do the syncing. The assistant card is gated behind the `supportAssistantFollowUp` ConfigCat flag. ## How it works 1. **Submit** — `SupportFormV3` generates a stable `threadRef` (via the `uuid` package — `crypto.randomUUID()` is `undefined` in insecure contexts like non-localhost HTTP and would throw, silently aborting the submit) and sends it on `/platform/feedback/send`. The response returns the Front `conversationId`. Both are stored on `SubmittedSupportRequest`. 2. **Open chat** — `SupportAssistantSuccessCardContent` opens a chat seeded with `supportMetadata` (`threadRef`, `frontConversationId`, subject, category, severity, …). The first message is a `<support>…</support>` XML block. 3. **First user message** — the chat is tagged `isSupportChat = true`; the `onFinish` hook fires `syncSupportChatToFront`. 4. **Subsequent turns** — each `onFinish` slices the unsynced delta, strips the XML metadata block from the seed message, and posts to the platform messages endpoint. 5. **Escalation / resolve** — the `escalate_to_human` / `resolve_support_conversation` tools (and manual **Escalate**/**Resolve** buttons in the assistant input) flip lifecycle status via `setSupportLifecycleStatus` → `syncSupportLifecycleToFront`, which calls the escalation/resolve endpoints. Front rules act on `ai_support_status`. The assistant only resolves after the user explicitly confirms the issue is fixed. ## Key design decisions - **`threadRef` as the shared key** — one UUID travels as `threadRef` on submit and as `chatId` on every sync, so all messages thread into a single Front conversation. - **`conversationId` from the form response** — passed to all sync/lifecycle calls so the platform skips lazy derivation and PATCHes custom fields directly. - **Delta-only sync** — `lastSyncedMessageCount` tracks what's been sent; the boundary is snapshotted before the async call to avoid skipping messages that arrive mid-flight. - **Server-side de-dup** — stable `external_id` (`chatId:msg.id`) means retries don't duplicate in Front. - **Fire-and-forget** — sync failures log to Sentry, never break the chat; `isSyncing` resets on rehydration so the next `onFinish` retries the same delta. Message and lifecycle syncs use separate guards (`isSyncing` / `isLifecycleSyncing`) so an in-flight message sync can't drop an escalate/resolve. - **Lifecycle queued until the conversation exists** — if a lifecycle transition is requested before the initial message sync has returned a `frontConversationId`, it's stored as `pendingLifecycleStatus` and flushed once the id is assigned, rather than dropped. - **Tools return immediately** — the lifecycle tools return a stub to the AI SDK; the real Front call happens in `onFinish`, keeping async I/O out of the tool execute path. - **XML seed stripped before sync** — only the user's actual `<message>` is sent to Front (or dropped entirely if the form already created the conversation). ## Changes | Area | File(s) | | --- | --- | | Support form state | `SupportForm.state.ts` — `threadRef` / `frontConversationId` on `SubmittedSupportRequest` | | Support form submit | `support-ticket-send.ts` — sends `threadRef`, reads `conversationId` | | Support form UI | `SupportFormV3.tsx` — generates `threadRef`, stores `conversationId` | | AI assistant state | `ai-assistant-state.tsx` — `SupportChatMetadata`, `setSupportLifecycleStatus`, `onFinish` wiring, tool handling | | Message sync | `state/ai-chat-front-sync.ts` — delta tracking, message filtering, initial vs. incremental | | API data layer | `data/feedback/ai-chat-front-sync.ts` — typed platform-client wrappers for the three conversation endpoints | | Support tools | `lib/ai/tools/support-tools.ts` — `escalate_to_human`, `resolve_support_conversation` | | Tool integration | `lib/ai/tool-filter.ts`, `tools/index.ts`, `generate-assistant-response.ts` | | Success card | `SupportAssistantSuccessCardContent.tsx` — tags chat on first engagement | | Assistant panel UI | `AIAssistant.tsx` — Escalate/Resolve buttons, disabled input on closed chats, support placeholders | <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit ## Summary by CodeRabbit - **New Features** - Support chats now include “Escalate to human” and “Resolve” actions. - Support submissions can be associated with a stable Front thread via a generated `threadRef`, preserving linkage across follow-ups. - AI assistant responses and input hints adapt when support mode is active. - **Bug Fixes** - Improved support chat state management and lifecycle handling to keep conversation metadata and message history synchronized more reliably with Front. - **Chores** - Added/updated coverage to reflect the new support-chat state and syncing behavior. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Alaister Young <10985857+alaister@users.noreply.github.com> |
||
|
Pedro RodriguesandClaude Opus 4.8
|
c4c213ce3d |
feat(studio): switch dashboard assistant to remote MCP server (#47479)
## I have read the [CONTRIBUTING.md](<https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md>) file. YES ## What kind of change does this PR introduce? Feature / refactor. ## What is the current behavior? The dashboard assistant runs `@supabase/mcp-server-supabase` in-process over an in-memory transport (`lib/ai/supabase-mcp.ts`). ## What is the new behavior? The assistant connects to the **remote MCP server** over HTTP (`@ai-sdk/mcp`), forwarding the dashboard session token as a bearer. URL comes from `NEXT_PUBLIC_MCP_URL` with a local-dev fallback; platform-only, and Nimbus works via the same env var. * **Tool model unchanged:** UI-controlled `execute_sql` (with `needsApproval`) and `deploy_edge_function` still come from Studio; the allowlist (`TOOL_CATEGORY_MAP`) remains the gate keeping the remote's write tools away from the assistant (`read_only` is defense-in-depth). * **Attribution:** sends `x-source-name: supabase-studio` (+ `x-source-version`) → logged as `source_name`/`client_name`. * **Connection lifecycle:** the HTTP client is closed via the request's `AbortSignal` (tools execute later during streaming); `signal` is required on `getTools`/`getMcpTools`. * **Resilience:** a remote-MCP failure degrades to the remaining tools instead of failing the assistant. * **Drift protection:** relied-upon tools are typed against `keyof typeof supabaseMcpToolSchemas`, so a package bump that renames/removes one fails `pnpm typecheck`; a runtime check also warns if the deployed server returns fewer tools. * Adds unit tests for the above. ## Additional context * Verified end-to-end against a local remote MCP server with a dashboard token: `initialize` 200, tools listed, a tool executed, client closed cleanly. * The remote MCP (mgmt-api) already accepts dashboard session tokens (GoTrue-JWT auth path) — no backend change needed. `NEXT_PUBLIC_MCP_URL` must point at each env's `/mcp`. * `@supabase/mcp-server-supabase` is kept — still used by the self-hosted `/api/mcp` routes. Closes [AI-137](https://linear.app/supabase/issue/AI-137/switch-dashboard-assistant-to-remote-mcp) ## Rollout * **Rollout:** merges with `USE_REMOTE_MCP` off (in-process); flip it to `true` per environment (staging → prod → Nimbus) once each one's prerequisites land. * **Rollback:** unset `USE_REMOTE_MCP` and redeploy to fall back to the in-process client — no revert needed. ## Summary by CodeRabbit * **Bug Fixes** * Improved AI request handling so tool loading and generation clean up properly when a request is cancelled or the browser connection closes. * Added safer fallback behavior when remote tool loading fails, so AI features can continue with available tools instead of stopping entirely. * Updated remote tool access to use the current project reference and preserve the correct access headers. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * AI tools now connect more reliably to remote services and stop cleanly when requests end or are canceled. * Tool loading is more resilient, continuing with available tools if remote access is unavailable. * **Bug Fixes** * Improved cleanup to prevent lingering connections during SQL generation and policy workflows. * Added safer handling for remote tool changes and invalid responses. * **Tests** * Expanded automated coverage for remote tool setup, cancellation, and fallback behavior. <!-- end of auto-generated comment: release notes by coderabbit.ai --> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com> |
||
|
Gildas Garcia
|
0e3364bbad |
Chore/cleanup studio deps (#47399)
## Problem Knip reported some unused dependencies. Some are actually used in builds, etc but others are not. ## Solution Remove the really unused dependencies <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Chores** * Cleaned up unused dependencies and removed some obsolete test/support files. * Updated project ignore rules to better match current app structure and generated files. * **Bug Fixes** * No user-facing behavior changed; this release is focused on maintenance and cleanup. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Joshen Lim
|
1baaded0bb |
Consolidate execute-sql-query into execute-sql-mutation (#46944)
## Context Just some clean up as I was going through stuff - `useExecuteSqlQuery` is deprecated and not used at all - As such `execute-sql-query` is technically irrelevant, the more relevant file is `execute-sql-mutation` - Hence opting to consolidate `execute-sql-query` into `execute-sql-mutation` - Also removing `ExecuteSqlError` since its just re-exporting the `ResponseError` type There's a lot of file changes but its essentially just updating the importing statements across the files |
||
|
Matt Rossman
|
65fab30935 |
feat(ai): judge tool inputs, add storage guidance and permissive RLS evals (#46168)
Adding broad RLS policies to public buckets can cause users to expose more than they expected, like the ability to list all profile pictures on an app. This patches Assistant with knowledge to follow our latest guidance on restrictive RLS policies for storage buckets https://github.com/supabase/supabase/pull/46172 **Changes** - Adds Storage bucket evals for public website assets and avatar access patterns to distinguish public vs private bucket use cases - Adds eval for overly permissive table policies - Adds `storage` knowledge so Assistant distinguishes public buckets, private buckets, object reads, and object listing. - Adds `includeToolCallInputs` option for scorer transcripts so LLM judges can evaluate proposed SQL/tool actions. - Bumps max step count to 10 since storage knowledge may incur another tool call (also 10 is recommended [here](https://vercel.com/academy/ai-sdk/multi-step-and-generative-ui#why-multi-step-is-required) for complex multi-tool scenarios) **References** - https://supabase.com/docs/guides/storage/buckets/fundamentals#public-buckets - https://supabase.com/docs/guides/storage/security/access-control - https://github.com/supabase/supabase/pull/46172 **Notes:** - These prompt tweaks are not meant to be exhaustive fixes, they are mainly hotfixes intended to hold us out until these cases can be addressed more deeply in skills/docs and tracked in a central evals Closes AI-676 Closes AI-756 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added Storage knowledge resource for the assistant covering Supabase Storage access patterns and RLS guidance. * Added three evaluation cases: two for Storage (marketing assets, avatars) and one for RLS policy generation for user profiles. * **Improvements** * Evaluators now include tool call inputs when judging conversations. * Assistant prompts and generation enhanced with richer Storage/RLS guidance and extended streaming limits. * **Tests** * Added test ensuring tool call inputs are included in serialized thread context. <!-- review_stack_entry_start --> [](https://app.coderabbit.ai/change-stack/supabase/supabase/pull/46168?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack) <!-- review_stack_entry_end --> <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Saxon Fletcher
|
80da153450 |
Fix for AI Assistant query and deploy confirmation (#46052)
When Assistant requests confirmation to run a query or deploy an edge function if the user doesn't skip or run and instead sends a follow-up message it errors out. This allows follow-up messages and treats them as "skips" which means adjusting confirmation message state as part of the follow-up. This also uses toModelOutput to cleanse data based on permissions. <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit ## Release Notes * **New Features** * Enhanced tool approval workflow: pending approvals are now automatically resolved as denied when submitting new messages * Improved chat input state management with better handling of approval states * Customizable loading messages for tool operations * **Bug Fixes** * Fixed chat input availability during pending tool approval states * Improved tool execution feedback during approval workflows <!-- review_stack_entry_start --> [](https://app.coderabbit.ai/change-stack/supabase/supabase/pull/46052?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack) <!-- review_stack_entry_end --> <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Matt Rossman
|
212ccf8135 |
fix(ai): contextualize cron schedule as SQL writes, score in "Tool Usage" (#45997)
When Assistant tries to schedule crons in read-only mode, it succeeds but creates the jobs under the `supabase_read_only_user`. This causes permission errors when user try to delete or unschedule them from the Cron dashboard. The root fix will be to enforce read-only transactions for that user. In the meantime, this PR steers Assistant to avoid the mistake. **Changes** - Prompts `execute_sql` to treat side-effecting function calls such as `cron.schedule()` as write queries. - Adds tool input assertions for "Tool Usage" scorer and a focused cron regression eval. - Updates eval mocks to show pg_cron extension as installed so it can call `cron.schedule()` **Verification** See [this trace](https://www.braintrust.dev/app/supabase.io/p/Assistant/trace?object_type=experiment&object_id=4a9e8c0e-83b7-4555-8502-365662c3ec8e&r=e041e69b-b70f-41d1-b88c-e8f7888c3de5&s=e041e69b-b70f-41d1-b88c-e8f7888c3de5) from Braintrust where the new eval passes "Tool Usage", correctly using `isWriteQuery` for the `cron.schedule()` Closes AI-737 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Tool evaluation now validates tool inputs (including exact and substring matches) in addition to tool presence. * **Tests** * Added a test confirming cron-scheduling behavior and that SQL scheduling/enqueue calls are treated as write operations. * **Chores** * Added pg_cron to mock extension data. * Clarified description that SQL calls with side effects should be treated as writes. <!-- review_stack_entry_start --> [](https://app.coderabbit.ai/change-stack/supabase/supabase/pull/45997?utm_source=github_walkthrough&utm_medium=github&utm_campaign=change_stack) <!-- review_stack_entry_end --> <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Charis
|
12869fcd9f |
studio: flip executeSql signature to SafeSqlFragment (7/7) (#46007)
## Summary Final PR in the SafeSql migration stack. Stacked on top of #46006. Tightens `executeSql`'s `sql` parameter from `string` to `SafeSqlFragment`. Any future raw-string caller is now a compile error — the SafeSql safety property becomes structural rather than convention-based. Also adapts the AI `execute_sql` tool to promote AI-generated SQL via `acceptUntrustedSql(untrustedSql(sql))` inside the `execute` callback. The tool's existing \`needsApproval: true\` gate ensures `execute` only runs after the user has explicitly approved — that approval is the gesture that promotes untrusted to safe. ## Test plan - [x] `pnpm typecheck` passes - [x] Grep for any remaining raw-string `executeSql` calls in `apps/studio` returns nothing - [x] Dev-server smoke: AI tool approval flow executes SQL |
||
|
Charis
|
39ec777d22 |
studio: SafeSql stragglers + remaining tests (6/7) (#46006)
## Summary Part 6 of 7 in the SafeSql migration stack. Picks up the few remaining files that didn't fit cleanly into earlier batches: - `components/Docs/Description.tsx` — comment statements built via `safeSql`. - `components/Integrations/IntegrationOverviewTabV2/InstallIntegrationSheet.test.tsx` — test fixture updated to `SafeSqlFragment`. - `lib/ai/tools/studio-tools.test.ts` — test fixture updated. - `lib/api/generate-v4.test.ts` — test fixture updated. Sets up PR 7, which flips the `executeSql` signature itself. ## Test plan - [x] `pnpm typecheck` passes - [x] Specific Studio unit tests run on top of the stack (`Policies.utils.test.ts`, `SidePanelEditor.utils.createTable.test.ts`, `useQueryInsightsIssues.utils.test.ts`) - [x] Dev-server smoke: Docs panel renders / accepts edits <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Tests** * Updated test suites to reflect internal type definition changes. * **Refactor** * Internal code improvements to enhance type safety and consistency across the codebase. <!-- review_stack_entry_start --> [](https://app.coderabbit.ai/change-stack/supabase/supabase/pull/46006) <!-- review_stack_entry_end --> <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Matt Rossman
|
d143571586 |
feat(assistant): trace-level scorers + server-side tool execution with needsApproval (#45654)
## Motivation When Assistant runs a potentially destructive tool like `execute_sql`, it stops the LLM request and prompts for client-side approval and execution of the tool. After approval, a second request kicks off under a separate trace. This has made scoring and [Topics](https://www.braintrust.dev/blog/topics) classification challenging, as the generated `output` is split across stateless requests. The [span-level scoring](https://www.braintrust.dev/docs/evaluate/custom-code#score-spans) approach we've used thusfar (after the LLM call, we massage the result into an `output` payload that's stuck onto the root span) has been cumbersome and led to invalid scores / topics where only part of the assistant response is considered. It's also inefficient, as we're duplicating potentially large info (like the `search_docs` output) that already exists within the trace. An alternative to scoring spans is to [score traces](https://www.braintrust.dev/docs/evaluate/custom-code#score-traces). Braintrust [best practices](https://www.braintrust.dev/docs/evaluate/score-online#best-practices) advise: > Use span scope for evaluating individual operations or outputs. Use trace scope for evaluating multi-turn conversations, overall workflow completion, or when your scorer needs access to the full execution context. We've also received [direct guidance](https://supabase.slack.com/archives/C05QYJBLX89/p1777925770927149?thread_ts=1777905716.911979&cid=C05QYJBLX89) from their team to use this approach. ## Changes Migrates eval scorers from custom `AssistantEvalOutput` shape to trace-level scoring via `trace.getThread()` / `trace.getSpans()`, with thread parsing that scores the full latest Assistant turn and passes prior conversation separately where relevant. Moves `execute_sql` and `deploy_edge_function` from client-side execution after approval to AI SDK `needsApproval` + server-side `execute()`. SQL results returned to the model are gated by AI opt-in level, so row data is only included with `schema_and_log_and_data`; otherwise the tool returns the no-data-permissions sentinel. Adds `metadata.isFinalStep` to disambiguate multiple LLM requests within an "assistant" turn due to tool call requests/responses. For online evals, this means we should configure automations to only score traces with `metadata.isFinalStep = true` to ensure we're judging the complete generated response. Other minor kaizen changes: - Renamed `promptProviderOptions` to `systemProviderOptions` to clarify that this is associated with the "system" message and disambiguate from the root `providerOptions` - Adds `evals/trace-utils.ts` to handle Zod validation of the `unknown` span shapes from Braintrust, to more easily access typed inputs/output on tool spans. - Bumps AI SDK floor version `^6.0.116` → `^6.0.174` - Tweaked the "Conciseness" scorer to not unfairly dock points for the new `[called tool_name]` labels in serialized assistant response ## Verification In the studio staging build, I asked Assistant to create a todos table with 3 sample todos. I manually approved the `execute_sql` call and saw Assistant generate text before & after the call. In Braintrust I verified two traces were produced (see [filtered logs](https://www.braintrust.dev/app/supabase.io/p/Assistant/logs?v=Staging&tvt=trace&search={%22filter%22:[{%22text%22:%22metadata.environment%2520%253D%2520%27staging%27%22,%22label%22:%22metadata.environment%2520%253D%2520%27staging%27%22,%22originType%22:%22btql%22},{%22text%22:%22%2560Chat%2520ID%2560%2520%253D%2520%25221cb2ac45-e5e7-458c-9da4-3bf6863b8842%2522%22,%22label%22:%22Chat%2520ID%2520equals%25201cb2ac45-e5e7-458c-9da4-3bf6863b8842%22,%22originType%22:%22form%22}]})), the first with `metadata.isFinalStep = false` and the second with `metadata.isFinalStep = true`. In the Braintrust staging scorers, I ran the preview Completeness scorer on the second trace and verified it sees the complete Assistant response including markers for tool calls ([link to trace](https://www.braintrust.dev/app/supabase.io/p/Assistant%20(Staging%20Scorers)/trace?object_type=project_logs&object_id=b5214b62-ad1e-4929-9d5b-40b1daebe948&r=0ed0a4f8-8aff-4a34-bb1d-1df1d88a5070&s=ff9015f8-6bf7-4ab3-83a9-ca4e69e27e82)) <img width="1193" height="960" alt="CleanShot 2026-05-07 at 11 27 10@2x" src="https://github.com/user-attachments/assets/509d4858-c3a1-4068-986d-3aa4d5617d1a" /> I also tested the `deploy_edge_function` workflow and verified it still prompts for permission and warns on deployment of existing functions. **References** - https://www.braintrust.dev/docs/evaluate/custom-code#score-traces - https://ai-sdk.dev/docs/ai-sdk-core/tools-and-tool-calling#tool-execution-approval Supercedes https://github.com/supabase/supabase/pull/45556 and https://github.com/supabase/supabase/pull/45339 Closes AI-473 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Tool actions (SQL execution, edge-function deploy) now require explicit user Approve/Deny before proceeding. * **Improvements** * Assistant pauses for approval responses before sending follow-ups, giving clearer control over risky actions. * Deploy/replace flows show confirmation and clearer replace warnings. * Evaluation/scoring updated to use richer trace data for more accurate assistant performance signals. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Joshen Lim
|
7f5865872a |
Enforce noUnusedLocals and noUnusedParameters in tsconfig.json + fix all related issues (#45264)
## Context Enforce `noUnusedLocals` and `noUnusedParameters` in tsconfig.json + fix all related issues |
||
|
Manuel RubioandAndrey A.
|
667be50982 |
fix(self-hosted): local AI assistant unable to read schemas and interpret/execute SQL (#44757)
## I have read the [CONTRIBUTING.md](https://github.com/supabase/supabase/blob/master/CONTRIBUTING.md) file. YES ## What kind of change does this PR introduce? Bug fix for #42574 ## What is the current behavior? If you setup a self-hosted Supabase environment and ask local AI assistant it is unable to interpret the results for executed SQL queries. ## What is the new behavior? Local AI assistant can now read schemas and interpret the results for executed SQL queries. ## Additional context I tested it using ollama with a smaller model which does not support reasoning mode so It would be useful if someone can test it using an actual OpenAI API KEY. The main issue was that `executeSql` returns a wrapped `{ result: {...} }` on `fallback-tools.ts` making the model think there's no result. The solution is just to unwrap it like it's done at: `apps/studio/data/database-functions/database-functions-query.ts`: ``` export async function getDatabaseFunctions(...) { ... const { result } = await executeSql(...) ... return result as DatabaseFunction[] } ``` Also added a `false` default value in `execute_sql` tool schema so zod validation does not reject a valid LLM tool call if the model omits the field (which happened with the smaller model) <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **Refactor** * Optimized internal schema metadata query handling in AI tools. * **Chores** * Enhanced SQL execution tool robustness by providing a sensible default for query type specification when not explicitly provided. <!-- end of auto-generated comment: release notes by coderabbit.ai --> Co-authored-by: Andrey A. <56412611+aantti@users.noreply.github.com> |
||
|
Alaister YoungandAlaister Young
|
1b1d05ff96 |
chore: upgrade vite to v8 and vitest to v4 (#44833)
Upgrade vite and vitest to their latest major versions across the
monorepo, along with related packages.
**Changed:**
- `vite` catalog: `^7.3.2` → `^8.0.8` (Rolldown replaces esbuild/Rollup)
- `vitest` catalog: `^3.2.0` → `^4.1.4`
- `@vitejs/plugin-react`: `^4.3.4` → `^6.0.1`
- `@vitest/coverage-v8`: `^3.2.0` → `^4.1.4`
- `@vitest/ui`: `^3.2.0` → `^4.1.4`
- `vite-tsconfig-paths`: `^4.3.2` / `^5.1.4` → `^6.1.1`
**Pinned to vite 7:**
- `apps/lite-studio` — `@react-router/dev` hasn't declared vite 8
support yet
- `blocks/vue` — Nuxt plugins (`vite-plugin-inspect`, `vite-dev-rpc`,
`vite-hot-client`, `vite-plugin-vue-tracer`) haven't declared vite 8
support yet
**Test fixes for vitest 4 breaking changes:**
- **`apps/studio/lib/api/snippets.utils.test.ts`** — Replaced
`vi.mock('fs/promises')` automock with an explicit factory. Vitest 4's
automocking doesn't create mock functions for getter-based exports on
Node built-ins, so `mockedFS.access.mockResolvedValue` etc. were
`undefined`.
- **`apps/studio/lib/api/self-hosted/functions/index.test.ts`** —
Changed `mockReturnValue` to `mockImplementation(function() { ... })`
for a constructor mock. Vitest 4 no longer allows `mockReturnValue` when
the mock is called with `new`.
- **`apps/studio/tests/pages/api/mcp/index.test.ts`** — Changed arrow
function to regular `function` in `mockImplementation` for
`StreamableHTTPServerTransport`. Arrow functions can't be constructors,
and vitest 4 now enforces this.
- **`packages/ui-patterns/vitest.setup.ts`** — Changed `ResizeObserver`
mock from arrow function to regular `function` for the same constructor
enforcement reason. This was crashing Radix popover rendering in jsdom.
## To test
- `pnpm test:studio` — all 226 test files should pass
- `pnpm --filter ui-patterns vitest run` — all 183 tests should pass
- `pnpm --filter www test -- --run` — all 19 tests should pass
- `pnpm --filter ui vitest run` — all tests should pass
- `pnpm --filter dev-tools vitest run` — all tests should pass
- `pnpm --filter ai-commands vitest run` — all tests should pass
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Chores**
* Standardized and updated development tooling versions and version
sources for consistent installs across the repo (Vite, Vitest,
vite-tsconfig-paths and related plugins/catalog entries).
* **Tests**
* Improved test mocks and typings (updated mock
factories/implementations and tightened spy/type assertions) to increase
test reliability and compatibility with updated tooling.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: Alaister Young <10985857+alaister@users.noreply.github.com>
|
||
|
Charis
|
205cbe7d26 | chore(studio}: enforce import order, remove bare import specifiers (#44585) | ||
|
Matt Rossman
|
82deff37de |
feat(assistant): lazy load topic knowledge via load_knowledge tool (#44296)
Moves knowledge (RLS, Edge Functions, PostgreSQL best practices, Realtime) out of the static system prompt and into a `load_knowledge` tool the model calls on demand, reducing prompt bloat. This is a temporary stopgap until the [standard Supabase agent-skills](https://github.com/supabase/agent-skills) are ready for integration in Assistant. - New always-available `load_knowledge` tool added to `rendering-tools.ts` - Updated `Message.Parts.tsx` so the "Ran load_knowledge" chip renders in chat - System prompt replaces the four knowledge blobs with an `## Available Knowledge` block and is hardened to load knowledge for given topics - New "Knowledge Usage" scorer and `requiredKnowledge` assertions check that knowledge loads as expected in test scenarios - Filters GraphQL error responses out of `output.docs` before faithfulness scoring to reduce noise See "Knowledge Usage" scoring 100% in evals with no major regressions: https://github.com/supabase/supabase/pull/44296#issuecomment-4145760236 Sample trace showing the tool in action ([Braintrust](https://www.braintrust.dev/app/supabase.io/p/Assistant/trace?object_type=project_logs&object_id=5a8d02e5-b3b6-40cc-ba76-ecee286478f4&r=351a11c8-9cb7-4945-93ad-d11e8cc2e3e1&s=351a11c8-9cb7-4945-93ad-d11e8cc2e3e1)) <img width="2192" height="1730" alt="CleanShot 2026-03-30 at 13 53 59@2x" src="https://github.com/user-attachments/assets/f483767c-34e0-401c-8089-5b9834fe696a" /> **References** - https://ai-sdk.dev/cookbook/guides/agent-skills Closes AI-508 <!-- This is an auto-generated comment: release notes by coderabbit.ai --> ## Summary by CodeRabbit * **New Features** * Added dynamic knowledge loading capability enabling the AI assistant to retrieve on-demand information about PostgreSQL best practices, Row Level Security, Edge Functions, and Realtime. * **Bug Fixes** * Improved search results filtering to exclude error responses in tool outputs. * **Tests** * Enhanced evaluation metrics with knowledge usage scoring. * Expanded test dataset cases to validate knowledge requirement handling. <!-- end of auto-generated comment: release notes by coderabbit.ai --> |
||
|
Joshen Lim
|
be26feb9ba |
Chore/shift manual queries into pg meta 03 (#43951)
## Context Shifting more dashboard queries into pg-meta so that we centralize all manually written queries in one place Having them in packages/pg-meta also allows us to write tests for them ## To test Just needs a smoke test on - Table Editor - Fetching entities - Viewing definition - SQL Editor - View ongoing queries - Abort queries - Integrations - Queues - Database - Migrations -Triggers (Updating) |
||
|
Matt Rossman
|
25036af80e |
fix(assistant): sanitize backslash-escaped apostrophes in SQL (#43728)
Fix for the LLM occasionally generating MySQL-style `\'` escapes in SQL, which are invalid in PostgreSQL. Example trace where this happened in the wild: ([Braintrust](https://www.braintrust.dev/app/supabase.io/p/Assistant/review?tab=experiment&r=5fcf1b12-8584-455c-9e9a-bdc0fa3ed21c&s=5fcf1b12-8584-455c-9e9a-bdc0fa3ed21c&o=0627ada8-b567-4117-9fe8-49d847cb73a7&review=1)) **Changes** - Adds `fixSqlBackslashEscapes` to convert `\'` → `''` before SQL is executed - Unit tests + adversarial eval dataset case Compare the results of the adversarial test case: - `master`: 0% SQL Validity ([Braintrust](https://www.braintrust.dev/app/supabase.io/p/Dev%20(mattrossman%2FAssistant)/trace?object_type=experiment&object_id=b469cbf7-4d6f-429c-9819-6c4099294123&r=dce5a29b-2fde-44c3-80f8-4e14d1f657c0&s=dce5a29b-2fde-44c3-80f8-4e14d1f657c0)) - This branch: 100% SQL Validity ([Braintrust](https://www.braintrust.dev/app/supabase.io/p/Assistant/trace?object_type=experiment&object_id=160e9ce0-e320-4f6d-8aa7-c5ad7e01fbd2&r=d75ef0e3-90ed-42a7-9ef3-8bf69592f193&s=0eeca492-dbe6-451e-8d81-127caff30320)) Closes AI-400 |
||
|
Jordi Enric
|
ac64a902c1 | chore: adds tests (#42653) |
