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 -->
## Summary
Resolves 13 findings (2 HIGH, 5 MEDIUM, 6 LOW) from the frontend
telemetry audit: 1 action-string collision, 1 camelCase experiment name,
9 dead events removed, 4 missing org groups attached, 1 ambiguous
property renamed, 1 raw-string property narrowed, plus consolidations
and a structural tightening on TABLE_EVENT_ACTIONS.
## Changes
### HIGH
- Rename `EventPageCtaClickedEvent.action` to
`www_event_page_cta_clicked` so it no longer collides with the pricing
CTA event (which had a different schema sharing the same action string)
- Snake_case the header-upgrade experiment exposure name
(`headerUpgradeCta_experiment_exposed` →
`header_upgrade_cta_experiment_exposed`); PostHog flag key and
`?source=` URL param unchanged
### MEDIUM
- Remove 4 dead `ProjectCreation*Step*` events (referenced a v2 route
that doesn't exist; 0 emissions)
- Remove 4 dead experiment exposure events:
`ProjectCreationRlsOptionExperimentExposed`, `HomeNewExperimentExposed`,
`TableCreateGeneratePoliciesExperimentExposed`,
`TableCreateGeneratePoliciesExperimentConverted` (0 emissions)
- Attach org group to `dpa_request_button_clicked` (0% had `$group_0`
per Hex)
- Delete `RegisterStateOfStartups2025NewsletterClicked` (interface
naming outlier, 0 emissions, page renamed to 2026)
- Rename `AssistantSuggestionRunQueryClickedEvent.category` to
`mutationType` with tightened literal union (`'functions' |
'rls-policies' | 'unknown'`)
- Attach org group to `project_creation_default_privileges_exposed` on
Vercel surface via explicit `groupOverrides` (auto-injection misses
because `useSelectedOrganizationQuery` is undefined on that page)
### LOW
- Consolidate `IndexAdvisorBannerEnableButtonClickedEvent` +
`IndexAdvisorDialogEnableButtonClickedEvent` into one event with
`origin: 'banner' | 'dialog'`
- Rename `ImportDataFileDroppedEvent` → `ImportDataFileAddedEvent` so
the interface name matches the action and the verb is on the approved
list
- Rename `LogDrainConfirmButtonSubmittedEvent` → `LogDrainRemovedEvent`
and action to `log_drain_removed` (fires on delete-confirm modal,
matches `CronJobRemovedEvent` pattern)
- Add `type` property to `CronJobRemovedEvent` (parsed from the job's
command), matching the create/update event shape
- Tighten `TABLE_EVENT_ACTIONS` values with `satisfies` against the
event union so renames in the union fail typecheck here too
- Attach org group to `www_pricing_plan_cta_clicked` at 5 emission sites
when an org is available in the page context
- Narrow `unified_logs_row_clicked.logType` from raw `string` to the
5-literal `LOG_TYPES` union (zod already validates server values)
### Bundled refactor
Migrated 5 emission sites from deprecated `useSendEventMutation` to
`useTrack` while their containing files were being edited: `DPA.tsx`,
`DisplayBlockRenderer.tsx`, `Grid.tsx` (2 events), `DeleteCronJob.tsx`.
Full sweep of the remaining ~79 files is a separate follow-up.
## Testing
Mostly just renaming of events
## Linear
- fixes GROWTH-798
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **Refactor**
* Standardized telemetry to a unified tracking system for more
consistent analytics.
* Simplified experiment exposure reporting for upgrade prompts.
* **New Features**
* More granular tracking for CSV import, cron job deletions, log drain
removals, DPA downloads/requests, and pricing CTAs.
* Assistant now classifies mutation queries more precisely.
* **Bug Fixes**
* Improved default-privileges exposure logic on Vercel deployments
(skips when org missing).
<!-- review_stack_entry_start -->
[](https://app.coderabbit.ai/change-stack/supabase/supabase/pull/45964)
<!-- review_stack_entry_end -->
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
## 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 -->
This PR fixes some prettier issues:
- Bump and unify all prettier versions to 3.7.3 across teh whole repo
- Bump the SQL prettier plugin
- When running `test:prettier`, check `mdx` files also
- Run the new prettier format on all files
---------
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
The queries used for the Table Editor menu aren't invalidated when the
Assistant executes SQL, so newly created views/tables and fresh lints
aren't shown. Now adds invalidations whenever a write query is run from
the Assistant interface.
* update onboarding
* update model and fix part issue
* action orientated assistant
* fix tool
* lock
* remove unused filter
* fix tests
* fix again
* update package
* update container
* fix tests
* refactor(ai assistant): break out message markdown and profile picture
* wip
* refactor(ai assistant): break up message component
* refactor: break ai assistant message down into multiple files
* refactor: simplify ReportBlock state
* fix: styling of draggable report block header
When the drag handle is showing, it overlaps with the block header.
Decrease the opacity of the header so the handle can be seen and the two
can be distinguished.
* fix: minor tweaks to tool ui
* refactor: simplify DisplayBlockRenderer state
* fix: remove double deploy button in edge function block
When the confirm footer is shown, the deploy button on the top right should be
hidden (not just disabled) to avoid confusion.
* refactor, test: message sanitization by opt-in level
Refactor the message sanitization to have more type safety and be more testable.
Add tests to ensure:
- Message sanitization always runs on generate-v4
- Message sanitization correctly works by opt-in level
* Fix conflicts in pnpm lock
* Couple of nits and refactors
* Revert casing for report block snippet
* adjust sanitised prompt
* Fix tests
---------
Co-authored-by: Charis Lam <26616127+charislam@users.noreply.github.com>
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
* Update perms checking in audit logs
* Deprecate useCheckPermissions, useIsPermissionsLoaded and useCheckProjectPermissions as they're no longer used
* Rename useAsyncCheckProjectPermissions to useAsyncCheckPermissions
* Fix TS
* Replace all usage of useProjectContext with useSelectedProjectQuery
* Replace all usage of useSelectedProject with useSelectedProjectQuery
* Replace all usage of useProjectByRef with useProjectByRefQuery
* Replace all usage of useSelectedOrganization with useSelectedOrganizationQuery
* Deprecate useSelectedProject, useSelectedOrganization, and useProjectByRef hooks
* Deprecate ProjecContext
* step 1
* use mcp
* system prompt
* clean up
* space
* clean up
* add three state opt in toggle
* clean up
* todo
* hooks
* refactor opt in form and modal
* refinements
* add bedrock
* remove console
* update mcp util
* use bedrock
* remove openai sdk package
* re-add tools
* update complete endpoints
* fix: ai assistant markdown formatting (#35541)
* fix: mcp types and project ref (#35540)
* feat: more flexible aws credential provider (#35538)
* feat: more flexible aws credential provider
* fix: add AWS_REGION to turbo env vars
* change to allowed
* update complete endpoints
* add an additional permission
* refinements
* use claud 4
* legal copy changes
* update other ai functions to use bedrock
* update generate v3 copy
* remove generate sql modal
* fixes for query block
* re-add dragging to reports
* clean up
* add open ai edge function example
* use handle error from fetchers
* remove schema and lean on tools
* copy
* Assistant MCP tests (#36049)
* feat: refactor and test mcp and model logic
* fix: remove get_project tool
* fix: remove additional get_project tool references
* update copy
* Clean up, fixes, refactors
* oops
* Float errors from AI endpoionts as toasts
* Use a env var AWS_BEDROCK_PROFILE for bedrock.
* Rename the env var for AWS bedrock profile.
* feat: support custom aws bedrock env vars
* chore: add comments explaining aws credential chain
* MCP Self Hosted Check (#36185)
support self hosted
* feat: bedrock auth via vercel oidc
* Fix broken unit test
* Feeeex
* Refactor useOrgOptedIntoAi
* Remove useDisallowHipaa hook
* small system prompt change
* readd vercel packages
* fix self hosted
* increase max duration
* try more direct prompt
* max duration 90
* reduce max steps and add loading
* mono font
* backwards compat styling
* Chore/limit number of messages sent to assistant (#36388)
* Limit number of historical messages that get sent to assistant
* Update max chat history to 5
* alignment
* bump mcp server version
* Add feature flag for opt in tags (#36466)
* Add feature flag for opt in tags
* Add one more check
* security section system prompt
* rely on default link and replace image markdown
* Add custom link component to assistant message block (#36527)
* Add custom link component to assistant message block
* Update based on feedback
* Render plain text if URL is deemed unsafe
* fix mcp tools and parse data (#36593)
* Update Admonition for AI Assistant for when opt in is re-enabled (#36663)
* Update Admonition for AI Assistant for when opt in is re-enabled
* Update
* Smol fix
* Fix TS
* Tiny
---------
Co-authored-by: Greg Richardson <greg.nmr@gmail.com>
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
Co-authored-by: Ivan Vasilov <vasilov.ivan@gmail.com>
Saxon Fletcher
