Commit Graph
73 Commits
Author SHA1 Message Date
Greg Richardson d94f1f9b3a fix(ai): increase request body size limit (#39330)
* fix(ai): increase request body size limit

* fix: remove incorrect config type
2025-10-07 11:31:54 -06:00
54ad0b7495 Chore/ai realtime (#39145)
* 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

* ai realtime

* ai realtime

* 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

* add limitations prompt

* limitations prompt

* link prompt

* 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

* empty states

* prompt otpimise

* refine prompt

* prompt optimizer

* remove realtime for now

* Update apps/studio/lib/ai/prompts.ts

Co-authored-by: Charis <26616127+charislam@users.noreply.github.com>

* Update apps/studio/lib/ai/prompts.ts

Co-authored-by: Charis <26616127+charislam@users.noreply.github.com>

* updates

* feature flag

* use flag and additional check

* remove sort

* messages copy

---------

Co-authored-by: Charis Lam <26616127+charislam@users.noreply.github.com>
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
2025-10-06 10:31:40 +10:00
1973615a42 Prompt GPT-5 Optimizations (#39031)
* 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

* add limitations prompt

* limitations prompt

* link prompt

* 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

* prompt optimizer

* remove realtime for now

* Update apps/studio/lib/ai/prompts.ts

Co-authored-by: Charis <26616127+charislam@users.noreply.github.com>

* Update apps/studio/lib/ai/prompts.ts

Co-authored-by: Charis <26616127+charislam@users.noreply.github.com>

---------

Co-authored-by: Charis Lam <26616127+charislam@users.noreply.github.com>
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
2025-09-29 14:07:53 +10:00
626eb30e77 Assistant action orientated approach (#38806)
* 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>
2025-09-29 03:57:36 +00:00
Greg Richardson 9820707d71 feat: local mcp server (#38797)
* feat: local mcp server

* feat(local-mcp): implement migrations

* fix: remove unsupported mcp args

* feat(local-mcp): tests

* fix(local-mcp): packages to adhere to minimumReleaseAge

* fix(mcp): import path for createSupabaseApiPlatform

* fix(local-mcp): move tests out of pages/api dir

* refactor: self-hosted execute sql logic

* fix: deps
2025-09-23 12:00:08 -06:00
Saxon Fletcher d276aca6cb Chore/ai flow model (#38805)
* update onboarding

* update model and fix part issue

* lock

* remove unused filter

* fix tests

* fix again

* update package

* fix merge issue
2025-09-23 12:46:20 +10:00
Saxon FletcherandJoshen Lim bf004b8a1d Choose provider and model (#38267)
* choose provider and model

* fix test

* Fix lint

* Nit clean up

* add provider options and remove anthropic

* remove package

* use chat model and update prompt

* prompt rendering

* default to pro

* fix test

* low

* remove log

* remove redundant part.text

---------

Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
2025-09-09 10:05:39 +00:00
cddc472705 Test GPT-OSS (#37710)
* 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>
2025-08-27 11:34:44 +07:00
Saxon Fletcher adfc138450 Remove error display temporarily (#37804) 2025-08-09 14:56:05 +10:00
TaishiandJoshen Lim 81e1acc2d8 Add ability to stop AI Assistant responses mid-stream (#37628)
* get `stop()` from useChat and use it

* Implement abort signal in `generate-v4` API

* Enhance `onStop` functionality in AIAssistant to store partial message when aborted

* Update dependencies in AIAssistant to include `updateMessage` in effect hook (lint warning fix)

* change onStop prop to be required in AssistantChatForm

* add comment for saving partial AI responses

* remove redundant text size class

* Make onStop prop optional in AssistantChatForm and conditionally render stop button

* Add loading spinner to stop button in AssistantChatForm

* simplify opacity handling for submit button

* Add tooltips

* Improve UI error handler for assistant panel

* Small tweak

* Filter out any tool calls that are streaming in generate-v4, happens when aborting the assistant while a tool is being called

---------

Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
2025-08-08 17:47:46 +07:00
d60aceb562 Prompt and tool refactoring (#37500)
* 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>
2025-08-08 15:25:57 +07:00
d52e2c252b Update AI SDK 5 (#37656)
* 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.

* zod

* v4 again

---------

Co-authored-by: Jordi Enric <jordi.err@gmail.com>
Co-authored-by: Ivan Vasilov <vasilov.ivan@gmail.com>
2025-08-08 14:15:39 +07:00
Joshen LimandAlaister Young e70242f822 Chore/clean up assistant mcp feature flags (#36772)
* Clean up usage of newOrgAiOptIn and useBedrockAssistant feature flags

* Remove all OpenAI endpoints

* Fix for self-hosted

* Default isLimited to false

* Update PG meta tests

* Fix unit tests for model

* Revert pg meta tests

* Fix test

---------

Co-authored-by: Alaister Young <alaister@users.noreply.github.com>
2025-07-22 16:05:16 +08:00
Saxon Fletcher 8375880f9d remove dynamic chat name from prompt for caching (#37281) 2025-07-18 00:43:25 +00:00
Greg Richardson 2afd0c92ab fix(ai): temporarily remove log tools (#37274)
* fix(ai): temporarily remove log tools

* fix: temp remove log tools from tool filter logic

* fix: temp remove log tools from tests

* fix: remove references to get_logs in system prompt
2025-07-17 21:27:54 +00:00
Saxon FletcherandGreg Richardson 09c1c95d7e Upgrades pro users and above (#37183)
* feat: bedrock prompt caching

* fix: prompt cache point not sending to bedrock

* upgrade paid orgs to higher model

---------

Co-authored-by: Greg Richardson <greg.nmr@gmail.com>
2025-07-16 14:58:33 +10:00
Greg Richardson 283826cbd9 feat: bedrock prompt caching (#37140)
* feat: bedrock prompt caching

* fix: prompt cache point not sending to bedrock
2025-07-15 20:08:31 -05:00
Saxon Fletcher fd670667ab Context reduction (#37032)
* context saving

* fix model name

* add results comment

* fix errors
2025-07-11 16:03:37 +10:00
Saxon Fletcher e3125e59c2 Limit tools based on extensions (#37006)
* limit tools based on extensions

* if failed, fall back to disabled
2025-07-10 15:54:19 +10:00
Saxon Fletcher 0419d45b6f Add search docs, advisors, and custom logging tools (#36852)
* ui refinements

* rename chat

* copy

* prose message styles

* add icon back

* fix message save

* simplify empty state

* update suggestions

* pass through props

* button styles

* onboarding icons

* name button

* remove results

* current chat name

* use type

* add advisor and search

* fix down arrow

* logging tools

* more general filter tools

* fixes

* pageparam fix

* move search docs
2025-07-10 09:43:38 +10:00
Saxon Fletcher 216b235877 Review branch diff with AI (#36915) 2025-07-10 09:11:34 +10:00
Saxon Fletcher 94c45c2863 AI UI refine and renaming (#36819)
* ui refinements

* rename chat

* copy

* prose message styles

* add icon back

* fix message save

* simplify empty state

* update suggestions

* pass through props

* button styles

* onboarding icons

* name button

* remove results

* current chat name

* use type

* fix down arrow

* re-add chat name
2025-07-08 12:09:11 +10:00
Terry SuttonandIvan Vasilov 4d15119c29 opt in tags (#36885)
* Validate the aiOptInLevel on the server

* Fix another issue when the project and mismatched org.

* Fix a type error.

---------

Co-authored-by: Ivan Vasilov <vasilov.ivan@gmail.com>
2025-07-04 14:17:42 -02:30
Greg Richardsonanddelgado3d ea91bf4739 Distributes bedrock requests evenly across regions (#36837)
* wip

* feat: distribute bedrock requests across regions

* fix: tests and type errors

* chore: remove AWS_BEDROCK_REGION from turbo.json

* fix: vercel oidc provider to fallback in credential chain

---------

Co-authored-by: delgado3d <27228526+delgado3d@users.noreply.github.com>
2025-07-02 17:35:37 +00:00
Alaister Young f1b67c3f24 chore: generate-v4 expose error message (#36702) 2025-06-26 20:07:12 +08:00
Alaister Young a6b88de5f9 fix: generate-v3 safe parse body (#36700) 2025-06-26 11:51:39 +00:00
Joshen LimandSaxon Fletcher 256dbb7f38 Feature flag MCP changes (#36689)
* Feature flag assistant endpoint + opt in UI

* Feature flag bedrock stuff for the other endpoints like title, cron, complete

* add edge function complete v2

* revert to old complete

* Revert hardcode

* fix chart colour

---------

Co-authored-by: Saxon Fletcher <saxonafletcher@gmail.com>
2025-06-26 18:41:31 +08:00
Joshen Lim 63164fe165 Revert "Revert "Feature/assistant mcp"" (#36687)
* Revert "Revert "Feature/assistant mcp" (#36684)"

This reverts commit 2bff117cde.

* Attempt
2025-06-26 15:02:49 +08:00
Joshen Lim 2bff117cde Revert "Feature/assistant mcp" (#36684)
Revert "Feature/assistant mcp (#35318)"

This reverts commit 3a50dd1f72.
2025-06-26 13:06:50 +08:00
3a50dd1f72 Feature/assistant mcp (#35318)
* 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>
2025-06-26 12:13:27 +08:00
Alaister Young c0c3710bde fix(studio): bypass pg meta route on self-hosted for ai endpoints (#35812)
* fix(studio): bypass pg meta route on self-hosted for ai endpoints

* fix hosted

* wrong way round
2025-05-29 20:16:49 +08:00
Alaister Young 6c83f97478 fix: local api route fixes (#35642)
* fix: local api route fixes

* fix build

* fix tests

* address feedback

* remove unused debug
2025-05-14 15:26:50 +00:00
Ivan Vasilov 21f6f1bb16 fix: Disable the convertSqlToSupabaseJs AI tool (#35280)
* Disable the convertSqlToSupabaseJs tool because it relies on sql-to-rest which expects binaries of libpg-query.

* Comment out the code instead of deleting it.
2025-04-25 22:30:39 +07:00
Joshen LimandAlaister Young 8239e2f27b Cache results in assistant panel (#34509)
* Cache results in assistant panel

* Small fixes

* fix

* disable switching chats while new messages are streaming in

* small comment

* Fix Create new snippet CTA in query block

* Add useCallbacks

* Update

* Remove console log

---------

Co-authored-by: Alaister Young <a@alaisteryoung.com>
2025-03-31 19:24:21 +08:00
Joshen Lim 497ef6159b Just to trigger redeploy (#34326) 2025-03-21 21:19:16 +08:00
Joshen Lim 6f765da829 Fix openai api key empty state not showing in local (#34120) 2025-03-13 15:15:35 +01:00
Saxon FletcherandJoshen Lim 1cefb95a73 Create edge function (#33726)
* page components

* page component changes

* settings but broken saving

* rvert

* use sheet for provider

* styling

* remove things

* Some refactoring and fixing, added JSDocs to layouts

* Smol refactor

* Fix

* Update JSDocs

* updated scaffolding

* update edge functions layout

* remove params

* Clean up

* Spelling

* Clean up FormFieldWrappers

* One last clean up

* create edge functon

* use component

* flag

* fix merge errors

* fix imports

* fix merge issues

* fix import

* fix flag

* remove unused

* move templates

* re-add flag

* Small refactors

* Smol refactors

* Refactor

* add rename and delete via context

* create function fixes

* moved function name

* Smol update

* Small fix for selected state in edge functions side menu when on /new

---------

Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
2025-02-27 20:04:46 +08:00
Saxon FletcherandJoshen Lim 28fe5811de Inline editor feature preview (#33541)
* add edge function knowledge

* deploy edge function mutaton

* add edge function block with deploy

* update function url

* update tools

* editor sql

* add templates

* use monaco editor

* hook up templates

* fixes

* add behind feature flag

* preview docs

* move editor

* initialPrompt

* consolidate widgets

* remove generic editor

* move logic

* fix ts

* include schema metadata

* Fix width of save snippet button

* Set tooltip position

* Use inlineLink component

* Remove unnecessary z index

* Lint

* Lint import statements in EditorPanel

* fixes

* fix keyboard shortcut

* show/hide results and invalidation

* fix focus issues in widget

* fixes

* fix ts

* Support cmd enter shortcut to run query in InlineEditor

* Update InlineEditorPreview to use admonition

* prompt updates

* add discussion url to preview

* schemas array

* One last clean up

---------

Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
2025-02-19 14:58:58 +10:00
dff6c817ae Chore/assistant in self hosted (#33422)
* Add layoutheader to self-hosted to allow showing assistant

* Fix layout

* Remove debug checks

* Check for key

* Dont load tables

* Fix assistant error handling

* Yeet

* Update turbo.json

* Another one

* god

* Fix

* Add fallback

* last attempt to fix

* Clean up

* take the wheel

* Tiny fix

* Skip enrich query for local, to match prod

---------

Co-authored-by: Alaister Young <alaister@users.noreply.github.com>
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
2025-02-18 17:37:53 +08:00
f58b594ee8 Deploy edge function from Assistant (#33293)
* add edge function knowledge

* deploy edge function mutaton

* add edge function block with deploy

* update function url

* update tools

* Update apps/studio/pages/api/ai/sql/tools.ts

Co-authored-by: Greg Richardson <greg.nmr@gmail.com>

* edge function tool fixes

* copy

* prompt changes and verify jwt

* Very minor refactors

---------

Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
Co-authored-by: Greg Richardson <greg.nmr@gmail.com>
2025-02-07 14:11:23 +10:00
Greg Richardson 1106bfea32 fix: ai prompt to discourage security_invoker=on for table creations (#33207) 2025-01-30 17:08:15 -07:00
8b90d416ec Add inline completions to SQL Editor (#30706)
* monaco complete

* progress

* just add panel to sqleditor

* update panel and prompt

* adjust prompt

* clean up

* clean up and improve prompt

* update prompt

* refine prompt

* remove package

* use constants file

* revert v3 prompt

* combine diff action bars

* use widget

* refactor

* Some updates

* fix: useCompletion base path

* fix: typo on monaco action label

* feat: use entire selected line(s) for inline completions

* fix widget consistency

* widget styling

* Fix TS

* feat: lock llm model version

* fix enter key issue

* move complete endpoint

* update complete prompt

* remove file

* placeholder text

---------

Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
Co-authored-by: Greg Richardson <greg.nmr@gmail.com>
2024-12-17 15:02:06 +10:00
Joshen Lim 464f9aa5dd Chore/update rules in generate v3 (#31113)
* Add rules for RLS policies when using functions from auth schema

* Add rules to never expose auth.users through a public view

* Add rule for ensuring all tables have a PK

* Add rule to create a DB index when a foreign key is created

* Add rule to enable RLS on tables by default

* Add rule to use security invoker for views

* Add rules for materialized view, foreign table, and extensions
2024-12-13 17:15:11 +08:00
Saxon Fletcher 9f718e904f Feat/assistant scroll (#31042) 2024-12-11 07:00:29 +10:00
Saxon Fletcher ba372c349d Feat/assistant refinements 3 (#31015)
* limit local storage messages

* add tool for getting database functions

* reduce loading jitter in assistant
2024-12-09 17:02:39 +10:00
Joshen Lim 7ca43d8919 Chore/fix error handling in generate v3 (#30913)
* Fix error handling in generate-v3 endpoint

* Lint
2024-12-05 15:40:23 +08:00
Saxon Fletcher a92e34d7a4 dont send current table or schema if not opted in (#30793) 2024-12-02 20:51:29 +08:00
Saxon Fletcher ccb26246f4 let the assistant decide when to run (#30789)
* let the assistant decide when to run

* remove log
2024-12-02 21:47:46 +10:00
Saxon FletcherandJoshen Lim fcfc1cf38f Assistant refinements (#30759)
* message enter

* auth prompt

* style changes to message

* header assistant button

* more auth prompt

* prompt

* prompt user refine

* iteration of read only

* Add basic tests for AIAssistant.utils

---------

Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
2024-12-02 14:46:11 +08:00
Saxon FletcherandJoshen Lim 8c3da2ed95 More assistant refinements (#30730)
* ai refinements

* ui fixes

* space

* reduce dot height

* Fix prop type issue

* Assign allowHoverEffect to ai assistant button and panel

* Lint

* Some lints

---------

Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
2024-11-29 20:31:02 +10:00