A variety of fixes and improvements to the Cmd+K AI completions endpoint
in the [SQL Editor](https://supabase.com/dashboard/project/_/sql/new):
- Pre-load table definitions for the public schema and any other schemas
referenced in the editor, so the model has real column names without
needing to fetch them dynamically
- Replace the generic tool suite with a single streamlined
`getSchemaDefinitions` tool the model can still call to look up
additional schemas on demand without behavior differences across
platform & self-hosted
- Swap generic chat system prompt for a purpose-built
`COMPLETION_PROMPT`; fix role (`assistant` → `user`) for consistency
with other endpoints
- Validate and type the request body with `zod`, which was previously
untyped (`any`)
- Improve Cmd+K behavior when nothing is selected — use the full editor
content as context, return the complete query rather than just the
changed fragment, and switch to a generation mode when the editor is
blank
- Escape single quotes in schema names when fetching entity definitions
in `pg-meta` to prevent schema names from breaking out of the SQL string
and injecting arbitrary content into the prompt
## Before
Before, the SQL Editor would often hallucinate tables / columns that
don't exist in the user's database making it less helpful if you don't
know the exact table/column names. Even with maximum Assistant opt-in
level on the org, it would often fail to call the necessary tools to
gather database context.
<img width="5062" height="1522" alt="image"
src="https://github.com/user-attachments/assets/fbe1130f-6b5a-41a8-99d7-7268880af188"
/>
<img width="2540" height="658" alt="image"
src="https://github.com/user-attachments/assets/a31c2967-7751-4fce-a9b7-60bd77660b1a"
/>
Sometimes it also silently fails and generates empty queries:
<img width="1352" height="398" alt="CleanShot 2026-04-09 at 17 46 06@2x"
src="https://github.com/user-attachments/assets/e17c103a-d47d-47e6-8c2e-101f0fae5651"
/>
Or echos back the user's prompt:
<img width="1368" height="282" alt="CleanShot 2026-04-09 at 23 04 56@2x"
src="https://github.com/user-attachments/assets/7dff6e64-f54e-45b5-8e86-5399e5a2fe41"
/>
## After
In this example, the completion correctly interpreted my request for
"completed" todos as a query on the `completed_foo` column in my
`public` schema, instead of assuming existence of a `completed` column.
<img width="1452" height="838" alt="CleanShot 2026-04-09 at 17 43 13@2x"
src="https://github.com/user-attachments/assets/7a575589-78b4-448d-810a-0330ff08ef8b"
/>
In this example, the completion was correctly aware of an `other` schema
because it was detected in my existing query. I didn't have to select
the text, it included the full query in context when unselected. Notice
how it correctly used the `is_done` column when I asked for "completed"
cakes:
<img width="1372" height="534" alt="CleanShot 2026-04-09 at 17 39 07@2x"
src="https://github.com/user-attachments/assets/e6b7eb6f-f3e8-4fa1-90a3-b5e34ddc14e4"
/>
Supersedes #44151
Closes AI-544
**Changes**
- Extracted tracing conditional to an `isTracingAllowed` helper with
unit tests (the function is simple but sensitive hence the extra testing
precaution)
- Disables Braintrust tracing for projects in EU database regions
(region prefix `eu-`) to address GDPR data residency concerns
- Disables Braintrust tracing for orgs whose owners have signed the
previous DPA, as a stopgap during the 30-day notice period for the
updated DPA that adds Braintrust as a subprocessor
- Refactored `org-ai-details.ts` → `ai-details.ts`, splitting
`getOrgAIDetails` into separate org and project helpers to cleanly scope
the EU-region check at the project level
DPA check uses the newly added `/documents/dpa-signed` endpoint from
https://github.com/supabase/platform/pull/31060. This PR includes
regenerated `api.d.ts` and `platform.d.ts` from running `pnpm codegen`
in `packages/api-types` to get type safety on this new endpoint.
Note tracing is still yet to be activated in production, this is a
preparatory step.
**To verify**
Send a chat message and check for the `x-braintrust-span-id` response
header on `POST /api/ai/sql/generate-v4` — it should be absent for
DPA-signed orgs or EU-region projects, and present otherwise.
<img width="3594" height="1992" alt="CleanShot 2026-04-03 at 14 28
58@2x"
src="https://github.com/user-attachments/assets/4c91d7ad-2604-4531-a78e-dedf41632fa5"
/>
If you have access to the Braintrust dashboard, you can also verify
whether logs are produced or not in the Assistant project there.
Closes AI-570
Closes AI-569
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Tracks organization DPA signing and detects EU-region projects
* Assistant tracing now follows a combined compliance policy (HIPAA
addon, DPA, project sensitivity, region)
* Added helpers to fetch org and project AI details
* **Documentation**
* Expanded API docs with additional examples and clarified parameter
descriptions
* Added response schemas for subscription preview and document status
* **Tests**
* Added/updated tests covering DPA/region behavior and tracing policy
enforcement
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
We're exploring support for newer models like
[gpt-5.4-nano](https://openai.com/index/introducing-gpt-5-4-mini-and-nano/)
in Assistant. This model doesn't support the `'minimal'` reasoning
effort level we use for gpt-5-mini which leads to vague errors.
<img width="595" height="263" alt="CleanShot 2026-03-18 at 17 13 05@2x"
src="https://github.com/user-attachments/assets/cf7c2370-322d-4a8a-be55-23e680db0aa0"
/>
Also, we've [previously
discussed](https://supabase.slack.com/archives/C0161K73J1J/p1771544464850199?thread_ts=1771493920.775699&cid=C0161K73J1J)
that reasoning adds unnecessary latency to otherwise simple AI
completion endpoints like `title-v2`. We want more control of reasoning
level independent of model/endpoint.
This PR aims to solve both problems by:
- making reasoning effort configurable on a per-request basis
- adding compile-time guardrails to prevent selecting an incompatible
reasoning level for models
- adding a `DEFAULT_COMPLETION_MODEL` with minimal reasoning that we can
update with newer models that support disabling reasoning (independent
of Assistant chat model reasoning)
Other improvements to our model config logic:
- Fixes bug in `onboarding/design.ts` and `assistant.eval.ts` where
`providerOptions` was being dropped
- `getModel()` now returns a bundled `modelParams` object (spread into
AI SDK calls) so `providerOptions` can't be accidentally omitted (this
[has happened
before](https://supabase.slack.com/archives/C0161K73J1J/p1771518443534309?thread_ts=1771493920.775699&cid=C0161K73J1J))
- Introduces an `ASSISTANT_MODELS` registry as a single source of truth
for assistant model config, eliminating hardcoded model IDs across the
codebase
- Aligns free/pro model conditional logic with `assistant.advance_model`
entitlement naming conventions instead of the `isLimited` pattern
- Adds `console.error` logging of Assistant stream errors so we can
interpret reasoning effort compatibility errors in the future (instead
of just opaque "Sorry, I'm having trouble responding right now" card)
- Removes unnecessary type casts and generally making the model config
logic stricter
- Removes pre-existing dead code: `anthropic` provider variant in
`GetModelParams` / `PROVIDERS` registry that was never implemented in
`getModel()`
Now if you try to select an unsupported reasoning level you get a type
error:
<img width="1306" height="320" alt="CleanShot 2026-03-20 at 14 37 24@2x"
src="https://github.com/user-attachments/assets/a6ac234b-5ea5-4d81-8e01-ac4be34a0800"
/>
And if for some reason an invalid reasoning level slips through, you now
get a server-side error surfacing the issue:
<img width="1268" height="204" alt="CleanShot 2026-03-20 at 14 58 14@2x"
src="https://github.com/user-attachments/assets/aadc1b7a-9495-475f-9741-39979bd27cd7"
/>
I've tested gpt-5 and gpt-5-mini are still working on the staging
preview and verified the models were selected properly in Braintrust
logs. Both models are available on my Pro test account, and my Free test
account shows the Pro upgrade CTA.
Closes AI-446
Closes AI-551
`reasoningEffort: 'minimal'` was
[configured](https://github.com/supabase/supabase/blob/d5cc70560d/apps/studio/lib/ai/model.utils.ts#L55-L59)
in the provider registry but `getModel()` returns it as a separate value
that callers must destructure and forward — and 7 of 8 endpoints weren't
doing so. This meant `gpt-5-mini` (a reasoning model) was running at
default reasoning effort for every call.
This PR destructures `providerOptions` from `getModel()` and passes it
to `generateObject`/`generateText` in all affected endpoints.
## Benchmark (local, median of 5 runs)
| Endpoint | Before (s) | After (s) | Speedup |
|----------|-----------|----------|---------|
| title-v2 | 7.0 | 1.9 | 3.7x |
| cron-v2 | 2.3 | 0.9 | 2.6x |
| filter-v1 | 5.8 | 2.2 | 2.6x |
| feedback/classify | 3.5 | 0.9 | 3.9x |
| feedback/rate | 2.9 | 0.9 | 3.2x |
`code/complete` and `policy` also received the fix but aren't
benchmarked here as they require a live DB connection and use multi-step
tool calls (separate latency concern tracked in AI-419).
To test the SQL naming, visit the SQL Editor in sidebar, add some SQL
like:
```sql
create table todos (
id serial primary key,
task text not null,
completed boolean default false
);
```
Right click on the snippet, "Rename" and "Rename with Supabase AI"
Closes AI-443
* try a really long context window to maximize caching
* update examples
* attempt to update packages and useChat
* update endpoints
* update zod
* zod
* update to v5
* message update
* Revert "zod"
This reverts commit ec39bac6b6.
* revert zod
* zod i
* fix complete endpoints
* remove async
* change to content
* type cleanup
* Revert the package bumps to rebuild them.
* Bump zod to 2.25.76 in all packages.
* Bump openai in all packages.
* Bump ai and ai-related packages.
* Remove unneeded files.
* Fix the rest of the migration stuff.
* Prettier fixes.
* testing new gptoss models
* sonnet as pro
* back to 3.7
* revert test
* add policy list tool
* fix
* refactor
* ai sdk 5 fixes
* refactor complete endpoint
* edge function prompt
* remove example
* use limited model for completions
* remove duplicate
* Update bedrock.ts
Co-authored-by: divit <27228526+delgado3d@users.noreply.github.com>
* add default check
* only add prefix if more then one region
* temp use api
* refactor to use openai api
* test
* remove unused import
* Prettier lint
* Fix test
* revert back to bedrock
* Tiny style fix for spacing of code blocks from edit message button
* try generate text normally
* prompt adjust
* add list style to prompt
* prompt adjust
* prompt adjust emphasise display query
* update prompts
* prompt adjust
* remove package
* prompt adjust
---------
Co-authored-by: Jordi Enric <jordi.err@gmail.com>
Co-authored-by: Ivan Vasilov <vasilov.ivan@gmail.com>
Co-authored-by: divit <27228526+delgado3d@users.noreply.github.com>
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
* try a really long context window to maximize caching
* update examples
* attempt to update packages and useChat
* update endpoints
* update zod
* zod
* update to v5
* message update
* Revert "zod"
This reverts commit ec39bac6b6.
* revert zod
* zod i
* fix complete endpoints
* remove async
* change to content
* type cleanup
* Revert the package bumps to rebuild them.
* Bump zod to 2.25.76 in all packages.
* Bump openai in all packages.
* Bump ai and ai-related packages.
* Remove unneeded files.
* Fix the rest of the migration stuff.
* Prettier fixes.
* add policy list tool
* refactor
* ai sdk 5 fixes
* refactor complete endpoint
* edge function prompt
* remove example
* slight prompt change
* Minor clean up
* More clean up
---------
Co-authored-by: Jordi Enric <jordi.err@gmail.com>
Co-authored-by: Ivan Vasilov <vasilov.ivan@gmail.com>
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
Matt Rossman