* 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>
* refactor: ai sql logic to common package
* feat: ai sql tests
* feat: test rls policy ai chat assistant
* refactor: jest env loading
* feat(ai): improve sql title and description quality
* fix: ai message role type
* Move the new files to a separate package.
* Remove a forgotten console.log.
* Migrate the tests to use snapshots and commit the snapshots.
* Separate the functions which require edge runtime to be exported via /edge subpath.
* Bust the turbo cache when one of the deps has been rebuilt.
* chore: fix package main/type references
* fix: package lock out of sync
* fix: ai sql debugging to fix typos
---------
Co-authored-by: Ivan Vasilov <vasilov.ivan@gmail.com>
* Migrate all apps and packages to use OpenAI v4 lib.
* Minor fix.
* refactor: improve types for completion chunks
---------
Co-authored-by: Greg Richardson <greg.nmr@gmail.com>
* Add two more sizes to the Panel component.
* Add alias for the older openai-api library. The new one is added under the openai name.
* Add API routes
* Add components for the new AI RLS panel.
* Bunch of changes to the AI Policy Editor.
* Add a button for opening the new Policy Editor.
* Add a feature flag for the new editor.
* Add a confirmation modal when closing the panel.
* Fix leftover data when closing the panel.
* Make the copy button work.
* Add the next/swc packages to package-lock.json.
* Merge master
* Scaffold debug sql in rls editor
* Small improvements to policy chat
* Hook up debug to ai assistant panel
* Improve debug UX
* Add debug request badge
* Some styling fix
* Small styling fix
* Another small styling fix
* Shift create new policy ai button + fix error stylign with code editor height
* Add tooltips to apply changes and copy code from assistant message
* Hide assistant button is not platform
* Small lint
* Add default error handlers to all AI RQ mutations
* Small fix
* Remove IS PLATFORM check for rls assistant
* Add placeholder to RLS code editor
* Fix diff + rls code editor
* Add placeholder message after sending prompt
* Small style
* RLSCodeEditor hit tab if empty to populate placeholder text
* Light mode nudeges
* Update logic for when confirmation close modal should show
* Set render overview ruler as false for rls diff editor
* improve chat UX to make it smoother (thank you alaister for your help 🙏)
* Dynamically do keepPreviousData
* Gracefully handle errors for add prompt
* Use animated ai icon while message is loading
* using Sheet component
* Address commernts
* Bit more improvements
---------
Co-authored-by: Joshen Lim <joshenlimek@gmail.com>
Co-authored-by: Jonathan Summers-Muir <MildTomato@users.noreply.github.com>
* Move all studio files from /studio to /apps/studio.
* Move studio specific prettier ignores.
* Fix the ui references from studio.
* Fix the css imports.
* Fix all package.json issues.
* Fix the prettier setup for the studio app.
* Add .turbo folder to prettierignore.
* Fix the github workflows.
