* 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>
* 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>
* 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>
* 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>
* 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>
* 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.
* 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>
* 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>
* 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>
* 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
* show thinking if last message is empty
* sql toggle copy and border fix
* add table and schema context
* add suggestions for policy
* Add snippet content to ai assistant if on sql editor and assistant is open
---------
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
* start
* added panels
* remove stuff
* fixes and refinements
* clean up
* remove old assistant panel
* resizable assistant kinda
* use icon
* Add missing package
* remove canvas
* add suggestions
* updated empty state if no tables exist
* fix table condition
* Implement diffing if using assistant in sql editor
* Reinstate old assistant in SQL editor if feature preview is off
* pane size adjustment
* assistant button corners
* Add SQL snippet content to assistant if opening assistant in sql editor
* Add the necessary checks for opt in and hipaa
* revert adding snippet to assistant when opening assistant in sql editor
* Add cmd i shortcut
* Add admonitions for when disablePrompt is toggled on, and if no api key is set. Add footer note RE rate limitation
* Bump ai package in packages
* some fixes for backwards compability depending on feature preview toggled
* Rename feature preview property for new assistant
* Smol fix
* Prevent SQL snippet from running until message is finished
* only loading last message
* fix z-index
* save chat state to global state
* add debug to failed ai queries
* Add basic contextual invalidation
* Add explain code action to SQL editor
* Add link to abort ongoing queries from SqlSnippet
* Update feature preview content
* Fix
* Fix
* Fix
* Te4st
* Fix tests
* ONly show ai button within a project
* Fix PH tracking
* Beef up a bit more event tracking
* Rough fix to padding when assistant is open
* A bit more telemetry stuff
* Update prompts
* fix rls editing via assistant
* Update generate-v3.ts
prompt to get auth schema too
* Add policy satement to assistant when editing
* Address all comments
* fixc
* Fix SqlSnippet not taking full width on larger viewports
* Adjust max width
---------
Co-authored-by: Saxon Fletcher <saxonafletcher@gmail.com>
* Hook up RLS to new assistant if feature flag is enabled
* Reset conversation if opening a different entity
* Add prompt to use alter policy if policy definition is provided
* Remove console log
* Add a message if openai_api_key not set
* Fix disabled state
* Some fixes
* Add same check in global assistant
* Remove check for api key for platform
---------
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
* Init AiAssistantPanel
* Temp
* Temp
* iterating on assistant ux
* More spiking
* Tweaking...
* Moar tweaking..
* Even more tweaking
* Tweek
* More tweaks
* Final tweaking...
* TWEAK
* Spelling
* Fix
* Assistant error handling and small bug fix in context for message
* Add feature flag
* Fix
* Address all feedback
* Minor
* Inital setup
* Add suggest feature to the RLS Assistant
* Add AI button
* Use existing policies in AI editor
* Remove old feature preview
* Cleanup
* Tooltip
* Update
* Change panel width
* Fix type
* Fix types again
* Flag cleanup
* Add tooltip
* Cleanup
* Add a clear history button
Missed some routes when restricting edge function regions in an earlier
PR. Any edge function that calls OpenAI needs to be called from an
OpenAI-supported region.
* chore: libpg-query types
* feat: improved rls ai tests
* feat: simplify assertitions for sql expressions
* refactor: split ai logic into separate files
* feat(rls-ai): test select, insert, update, delete policies
* feat: adds withMetadata wrapper for failed tests
* chore: remove custom libpg-query types
* feat(rls-ai): make tests concurrent
* fix(rls-ai): rules for 'using' and 'with check'
* feat(rls-ai): discourages restrictive policies
* feat(ai): makes withMetadata util sync or async
* refactor(ai): moves withMetadata to generic test utils
* feat(rls-ai): test joined table
* feat(rls-ai): test mfa
* chore(ai): make all tests concurrent
* fix(ai): chatSql function rename in studio
* refactor(ai): isolate logic into separate files
* chore(ai): remove trailing comma in tsconfig
* chore(ai): remove unused dep
* Reset some of the package versions to the versions from master.
* chore(ai): remove unused imports
---------
Co-authored-by: Ivan Vasilov <vasilov.ivan@gmail.com>
* Remove feature preview for the conversational AI for SQL editor.
* Remove all code related to the previous implementation of editor ai.
* Update the snapshots for the ai commands.
* Remove unneeded code from the ai panel.
* Show the diff bar when debugging.
* Convert the updateEditor function into a callback.
* Simplify the debugging functionality by using react state instead of react context.
* Erase the AI disclaimer when formatting code as modification.
* Add a button to clear the chat history.
