mirror of
https://github.com/supabase/supabase.git
synced 2026-10-08 10:55:06 +03:00
chore/function-recent-errors
11
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 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>
|
||
|
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 --> |
||
|
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 |
||
|
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 --> |
||
|
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> |
||
|
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 --> |
