## Summary
This PR refactors the AI chat thread state management to use `null`
instead of a sentinel string value (`AGENT_CHAT_UNKNOWN_THREAD_ID`) to
represent an uninitialized or new chat thread. This improves type safety
and makes the code more idiomatic by using `null` to represent the
absence of a value.
## Key Changes
- **Removed sentinel constant**: Deleted `AGENT_CHAT_UNKNOWN_THREAD_ID`
constant and replaced all usages with `null`
- **Updated state types**: Changed `currentAIChatThreadState`,
`agentChatLastDiffSyncedThreadState`, and
`agentChatDisplayedThreadState` to use `string | null` type with `null`
as default value
- **Updated component family states**: Modified message-related state
families to accept `threadId: string | null` instead of `threadId:
string`
- **Refined null checks**: Added explicit `null` checks in:
- `AgentChatMessagesFetchEffect`: Updated `isNewThread` logic to check
for `null` first
- `useAIChatThreadClick` and `useSwitchToNewAIChat`: Added guards to
only save drafts when `currentAIChatThread !== null`
- `AgentChatThreadInitializationEffect`: Added null check before UUID
validation
- `useEnsureAgentChatThreadIdForSend`: Added null check before comparing
with draft key
- **Updated fallback logic**: Used nullish coalescing operator (`??`) in
`AIChatTab` and `useAIChatEditor` to default to
`AGENT_CHAT_NEW_THREAD_DRAFT_KEY` when thread is null
- **Enhanced refetch safety**: Added early return in
`handleRefetchMessages` to prevent refetching when in new thread state
## Implementation Details
- The change maintains backward compatibility by treating `null` the
same way the code previously treated `AGENT_CHAT_UNKNOWN_THREAD_ID`
- All draft saving operations now safely check for null before
attempting to store drafts
- The nullish coalescing pattern (`currentAIChatThread ??
AGENT_CHAT_NEW_THREAD_DRAFT_KEY`) ensures proper fallback behavior when
accessing draft storage
https://claude.ai/code/session_01Pz8KCygSNgBPYsndbMq8f7
---------
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
This PR adds support for attaching files to agent chat messages. Users
can now upload files when sending messages to the AI agent, and these
files are properly processed, stored, and made available to the agent
with signed URLs.
## Key Changes
- **File attachment input**: Added `fileIds` parameter to the
`sendChatMessage` GraphQL mutation to accept file IDs from the client
- **File processing**: Implemented `buildFilePartsFromIds()` method to
convert file IDs into file UI parts with signed URLs
- **Message composition**: Updated user messages to include both text
and file parts when files are attached
- **File URL signing**: Integrated `FileUrlService` to generate signed
URLs for files in the AgentChat folder, ensuring secure access
- **Message persistence**: Files are now included in the message parts
stored in the database and retrieved when loading conversation history
- **File metadata mapping**: Enhanced `mapDBPartToUIMessagePart()` to
properly extract MIME types from file entities and include file IDs
## Implementation Details
- Files are fetched from the database using the provided file IDs and
workspace context
- Each file is converted to an `ExtendedFileUIPart` with proper metadata
(filename, MIME type, signed URL, and file ID)
- When loading messages from the database, file parts are enhanced with
signed URLs to ensure they remain accessible
- The `loadMessagesFromDB()` method now requires the workspace ID to
properly sign file URLs
- File attachments are seamlessly integrated into the existing message
part system alongside text content
https://claude.ai/code/session_01TAdN1gBzeiYELX4XDrrYY1
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
## Summary
Refactored the `AgentChatMessageUIToolCallPart` output structure to
flatten the nested result object, simplifying the data model and
improving code clarity.
## Key Changes
- **Flattened output structure**: Moved `success`, `message`, and
`result` fields from `output.result` directly to `output`, eliminating
unnecessary nesting
- **Removed `toolName` field**: Deleted the unused `toolName` property
from the output object
- **Made fields optional**: Changed `error` and `result` to optional
fields to better represent cases where they may not be present
- **Updated hook logic**: Modified `useProcessUIToolCallMessage` to
access the flattened structure:
- Changed `toolExecutionPart.output.result.success` to
`toolExecutionPart.output.success`
- Changed `toolExecutionPart.output.result.result` to
`toolExecutionPart.output.result`
- Added null check for `navigateAppOutput` to handle cases where result
is undefined
## Implementation Details
The refactoring maintains backward compatibility in functionality while
simplifying the data structure. The optional `result` field now properly
reflects that navigation output may not always be present, with an
explicit guard clause added to handle this case gracefully.
https://claude.ai/code/session_01EnYKwVaCJyhgNPsi7p3YSq
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
- **Queue messages while streaming**: Messages sent during active AI
streaming are queued server-side and auto-flushed when the current
stream completes. Frontend renders queued messages optimistically in a
dedicated queue UI.
- **Drop `@ai-sdk/react` + `resumable-stream`**: Replace the dual HTTP
SSE + AI SDK client architecture with a single GraphQL SSE subscription
per thread. All events (token chunks, message persistence, queue
updates, errors) flow through Redis PubSub → GraphQL subscription.
- **Server-driven architecture**: The server decides whether to queue or
stream (via `POST /:threadId/message`). The frontend mirrors this
decision for optimistic rendering but defers to the server response.
- **Reuse AI SDK accumulation logic**: `readUIMessageStream` from the
`ai` package handles chunk-to-message accumulation on the frontend,
avoiding a custom 780-line accumulator.
## Key files
**Backend:**
- `agent-chat-event-publisher.service.ts` — publishes events to Redis
PubSub
- `agent-chat-subscription.resolver.ts` — GraphQL subscription resolver
- `stream-agent-chat.job.ts` — publishes chunks via PubSub instead of
resumable-stream
- `agent-chat.controller.ts` — unified `POST /:threadId/message`
endpoint
**Frontend:**
- `useAgentChatSubscription.ts` — subscribes to `onAgentChatEvent`,
bridges to `readUIMessageStream`
- `useAgentChat.ts` — send/stop/optimistic rendering (no more AI SDK)
- `AgentChatStreamSubscriptionEffect.tsx` — replaces
`AgentChatAiSdkStreamEffect.tsx`
## Test plan
- [ ] Send message on new thread → optimistic render, streaming response
appears
- [ ] Send message while streaming → queued instantly (no flash in main
thread)
- [ ] Queued message auto-flushes after current stream completes
- [ ] Remove queued message via queue UI
- [ ] Stop streaming mid-response
- [ ] Leave chat idle for several minutes → streaming still works after
(SSE client recycling)
- [ ] Token refresh during session → requests succeed (authenticated
fetch)
- [ ] Switch threads while streaming → clean subscription handoff
Made with [Cursor](https://cursor.com)
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
## Overview
Add resumable stream support for agent chat to allow clients to
reconnect and resume streaming responses if the connection is
interrupted (e.g., during page refresh).
## Changes
### Backend (Twenty Server)
- Add `activeStreamId` column to `AgentChatThreadEntity` to track
ongoing streams
- Create `AgentChatResumableStreamService` to manage Redis-backed
resumable streams using the `resumable-stream` library with ioredis
- Extend `AgentChatController` with:
- `GET /:threadId/stream` endpoint to resume an existing stream
- `DELETE /:threadId/stream` endpoint to stop an active stream
- Update `AgentChatStreamingService` to store streams in Redis and track
active stream IDs
- Add `resumable-stream@^2.2.12` dependency to package.json
### Frontend (Twenty Front)
- Update `useAgentChat` hook to:
- Use a persistent transport with `prepareReconnectToStreamRequest` for
resumable streams
- Export `resumeStream` function from useChat
- Add `handleStop` callback to clear active stream on DELETE endpoint
- Use thread ID as stable message ID instead of including message count
- Add stream resumption logic in `AgentChatAiSdkStreamEffect` component
to automatically call `resumeStream()` when switching threads
## Database Migration
New migration `1774003611071-add-active-stream-id-to-agent-chat-thread`
adds the `activeStreamId` column to store the current resumable stream
identifier.
---------
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
## Summary
- Removes two remaining direct `cookieStorage.setItem('tokenPair', ...)`
calls that were overwriting the Jotai-managed cookie (180-day expiry)
with a session cookie (no expiry) during **token renewal**
- Followup to #18795 which fixed the same issue in `handleSetAuthTokens`
but missed the renewal code paths
## Root cause
Two token renewal paths still had direct cookie writes without
`expires`:
1. **`apollo.factory.ts`** — `attemptTokenRenewal()` fires on every
`UNAUTHENTICATED` GraphQL error after a successful token refresh
2. **`useAgentChat.ts`** — `retryFetchWithRenewedToken()` fires on 401
from the AI chat endpoint
Both called `cookieStorage.setItem('tokenPair', JSON.stringify(tokens))`
without an `expires` attribute, creating a session cookie that overwrote
the Jotai-managed one. This is why the bug was **intermittent after
#18795**: it only appeared after a token renewal, not on fresh login.
The `onTokenPairChange` / `setTokenPair` calls already write through
Jotai's `atomWithStorage` → `createJotaiCookieStorage`, which always
sets `expires: 180 days`.
## Test plan
- Log in to the app
- Wait for a token renewal to occur (or force one by letting the access
token expire)
- Inspect the `tokenPair` cookie in DevTools → Application → Cookies
- Verify the cookie retains an expiration date ~180 days from now (not
"Session")
- Close and reopen the browser — confirm you remain logged in
Made with [Cursor](https://cursor.com)
## Summary
- Replaces per-provider TypeScript constant files
(`openai-models.const.ts`, `anthropic-models.const.ts`, etc.) with a
single `ai-providers.json` catalog as the source of truth
- Adds runtime model discovery via AI SDK for self-hosted providers,
with `models.dev` enrichment for pricing/capabilities
- Introduces composite model IDs (`provider/modelId`) for canonical,
conflict-free identification
- Simplifies provider configuration: API keys are injected from
environment variables (e.g., `OPENAI_API_KEY`)
- Adds admin panel UI for provider management (add/remove/test), model
discovery, recommended model configuration, and default fast/smart model
selection per workspace
- Removes deprecated config variables (`AI_DISABLED_MODEL_IDS`,
`AUTO_ENABLE_NEW_AI_MODELS`, etc.)
- Adds database migration for composite model ID format
## Test plan
- [ ] Server typecheck passes
- [ ] Frontend typecheck passes
- [ ] Server unit tests pass
- [ ] Frontend unit tests pass
- [ ] CI pipeline green
- [ ] Admin panel AI tab loads correctly
- [ ] Provider discovery works for configured providers
- [ ] Model recommendation toggles persist
- [ ] Default fast/smart model selection works
Made with [Cursor](https://cursor.com)
This PR:
- Breaks useAgentChatData into focused effect components (streaming,
fetch,
init, auto-scroll, diff sync)
- Splits message list into non-last (stable) + last (streaming/error) to
prevent full re-renders on each stream chunk
- Adds scroll-to-bottom button and MutationObserver-based auto-scroll on
thread switch
- Lifts loading state from context to atoms
- Adds areEqual to selector
factories
We could improve further but this sets up a robust architecture for
further refactoring.
## Messages flow
The flow of messages loading and streaming is now more solid.
Everything goes out from `AgentChatAiSdkStreamEffect`, whether loaded
from the DB or streaming directly, and every consumers is using only one
atom `agentChatMessagesComponentFamilyState`
## Data sync effect with callbacks new hook
See
`packages/twenty-front/src/modules/apollo/hooks/useQueryWithCallbacks.ts`
which allows to fix Apollo v4 migration leftovers and is an
implementation of the pattern we talked about with @charlesBochet
We could refine this pattern in another PR.
# Before
https://github.com/user-attachments/assets/84e7a96f-6790-405d-8a73-2dacbf783be5
# After
https://github.com/user-attachments/assets/4c692e3a-2413-4513-abcc-44d0da311203
Co-authored-by: Charles Bochet <charles@twenty.com>
## Summary
- **Delete 10 unused files**: 7 hooks (`useWorkflowRunUnsafe`,
`useGetViewById`, `useCreateViewFieldGroup`, `useDeleteViewFieldGroup`,
`useUpdateViewFieldGroup`, `useCreateManyViewFieldGroups`,
`useMoveViewColumns` + test), 1 component (`SettingsSummaryCard`), 1
utility (`createEventContext`)
- **Rename `objectMetadataItemsState` → `objectMetadataItemsSelector`**
across ~85 files to accurately reflect it is a derived selector (via
`createAtomSelector`), not a base Jotai atom
## Details
### Dead code removed
| Type | Name | Reason |
|------|------|--------|
| Hook | `useWorkflowRunUnsafe` | Never imported — duplicate of
`useWorkflowRun` without schema validation |
| Hook | `useGetViewById` | Never imported — `useViewById` is used
instead |
| Hook | `useCreateViewFieldGroup` | Never imported — CRUD done via
`usePerformViewFieldGroupAPIPersist` |
| Hook | `useDeleteViewFieldGroup` | Same as above |
| Hook | `useUpdateViewFieldGroup` | Same as above |
| Hook | `useCreateManyViewFieldGroups` | Same as above |
| Hook | `useMoveViewColumns` | Only imported by its own test — no
production usage |
| Component | `SettingsSummaryCard` | Never imported anywhere |
| Utility | `createEventContext` | Never imported anywhere |
### Rename
`objectMetadataItemsState` is created via `createAtomSelector` (it
derives from `objectMetadataItemsWithFieldsSelector`), so naming it
`*State` is misleading. Renamed to `objectMetadataItemsSelector` for
consistency with sibling selectors like
`objectMetadataItemsByNamePluralMapSelector`.
## Summary
- **Remove all "core" prefixes** from the views system — the
metadata-based storage migration is complete, so `CoreView`,
`coreViewsSelector`, `getCoreViews`, etc. are now just `View`,
`viewsSelector`, `getViews`
- **Eliminate the entire converter layer** (15 files, ~850 lines
deleted) — `convertCoreViewToView` and all sub-converters were either
no-ops or trivially adding `__typename` / mapping identical enum values.
Local enums now re-export from generated GraphQL types directly (single
source of truth)
- **Unify `View` and `ViewWithRelations`** into one type —
`ViewWithRelations` is now a type alias for `View`, selectors return
data directly without conversion
### Backend
- Rename `@ObjectType('CoreView')` → `@ObjectType('View')` (and all
sub-entities)
- Rename resolver methods: `getCoreViews` → `getViews`, `createCoreView`
→ `createView`, etc.
- Rename `FIND_ALL_CORE_VIEWS_GRAPHQL_OPERATION` →
`FIND_ALL_VIEWS_GRAPHQL_OPERATION`
### Frontend
- Delete 15 converter files (`convertGqlView*ToView*`,
`convertView*ToGql`, `convertViewWithRelationsToView`)
- Re-export `ViewType`, `ViewKey`, `ViewFilterGroupLogicalOperator` from
generated enums (no more duplicate enum definitions with different
casing)
- Replace `ViewOpenRecordInType` with `ViewOpenRecordIn` from generated
- Remove `__typename` from all local view sub-types
- Remove unused `variant` from `ViewFilter`, make `displayValue` and
`definition` optional
- Rename ~45 GraphQL query/mutation files and all selectors to drop
"core" prefix
- Delete unused `viewsWithRelationsSelector`
## Summary
This PR improves type safety across the codebase by replacing generic
`any` types with proper TypeScript types, removes unnecessary record
store operations, and adds TODO comments for future refactoring of
useEffect hooks.
## Key Changes
### Type Safety Improvements
- **SettingsAgentTurnDetail.tsx**: Replaced `any` type annotations with
proper `AgentMessage` type from generated GraphQL types
- **useCreateManyRecords.ts**: Added `RecordGqlNode` type for better
type safety when handling mutation responses
- **useLazyFindOneRecord.ts**: Replaced generic `Record<string, any>`
with `Record<string, RecordGqlNode>` for improved type checking
### Removed Unnecessary Operations
- **EventCardCalendarEvent.tsx**: Removed unused
`useUpsertRecordsInStore` hook and its associated useEffect that was
upserting calendar event records to the store
- **EventCardMessage.tsx**: Removed unused `useUpsertRecordsInStore`
hook and its associated useEffect that was upserting message records to
the store
### Conditional Query Execution
- **useLoadCurrentUser.ts**: Made the `FindAllCoreViewsDocument` query
conditional - only executes when `isOnAWorkspace` is true, preventing
unnecessary queries for users not on a workspace
### Documentation
- Added TODO comments in multiple files (`useAgentChatData.ts`,
`useWorkspaceFromInviteHash.ts`, `useGetPublicWorkspaceDataByDomain.ts`,
`useFindManyRecords.ts`, `useSingleRecordPickerPerformSearch.ts`)
referencing PR #18584 for future refactoring of useEffect hooks to avoid
unnecessary re-renders
## Implementation Details
- The removal of store upsert operations suggests these records are
already being managed elsewhere or the operations were redundant
- Type improvements maintain backward compatibility while providing
better IDE support and compile-time checking
- Conditional query execution reduces unnecessary network requests and
improves performance for non-workspace users
https://claude.ai/code/session_01YQErkoHotMvM6VL3JkWAqV
---------
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
This PR upgrades Apollo Client from v3.10.0 to v4 and refactors error
handling patterns across the codebase to use a new centralized
`useSnackBarOnQueryError` hook.
## Key Changes
- **Dependency Update**: Upgraded `@apollo/client` from `^3.10.0` to
`^3.11.0` in root package.json
- **New Hook**: Added `useSnackBarOnQueryError` hook for centralized
Apollo query error handling with snack bar notifications
- **Error Handling Refactor**: Updated 100+ files to use the new error
handling pattern:
- Removed direct `ApolloError` imports where no longer needed
- Replaced manual error handling logic with `useSnackBarOnQueryError`
hook
- Simplified error handling in hooks and components across multiple
modules
- **GraphQL Codegen**: Updated codegen configuration files to work with
Apollo Client v3.11.0
- **Type Definitions**: Added TypeScript declaration file for
`apollo-upload-client` module
- **Test Updates**: Updated test files to reflect new error handling
patterns
## Notable Implementation Details
- The new `useSnackBarOnQueryError` hook provides a consistent way to
handle Apollo query errors with automatic snack bar notifications
- Changes span across multiple feature areas: auth, object records,
settings, workflows, billing, and more
- All changes maintain backward compatibility while improving code
maintainability and reducing duplication
- Jest configuration updated to work with the new Apollo Client version
https://claude.ai/code/session_019WGZ6Rd7sEHuBg9sTrXRqJ
---------
Co-authored-by: Claude <noreply@anthropic.com>
This PR fixes what allows to have a working demo workspace skill.
- Skill updated many times into something that works
- Fixed infinite loop in AI chat by memoizing ai-sdk output
- Finished navigateToView implementation
- Increased MAX_STEPS to 300 so the chat don't quit in the middle of a
long running skill
- Added CreateManyRelationFields
This PR adds the necessary tool to create a demo workspace with :
relevant custom objects and fields, mock data and a real dashboard with
graph widgets.
It is still a bit under-optimized and slow but it works.
This PR also adds an AI tool that allows to see what happens in real
time, it navigates the app and waits when necessary.
---------
Co-authored-by: Félix Malfait <felix.malfait@gmail.com>
- Remove feature flag
- Remove legacy methods in file-upload and file-service
- Migrate AI Chat to new file management
---------
Co-authored-by: Charles Bochet <charles@twenty.com>
## Summary
Add Home/Chat tabs and a dedicated threads list in the navigation
drawer.
## Changes
- **Navbar tabs:** Tabs in the drawer to switch between Home and Chat
(with “New chat” button). Shown on desktop when expanded and on mobile
below the workspace selector.
- **Navbar threads list:** New `NavigationDrawerAIChatThreadsList` for
the Chat tab with date groups (Today / Yesterday / Older), thread rows
as `NavigationDrawerItem` (IconComment, title, timestamp). Shared
`useAIChatThreadClick` hook used by navbar and command menu; navbar
passes `resetNavigationStack: true`.
- **NavigationDrawerItem:** New `alwaysShowRightOptions` prop so the
timestamp is always visible (no hover-only).
---------
Co-authored-by: Etienne <45695613+etiennejouan@users.noreply.github.com>
Co-authored-by: Félix Malfait <felix@twenty.com>
Co-authored-by: Charles Bochet <charles@twenty.com>
## Summary
Removes the `recoil` dependency entirely from `package.json` and
`twenty-front/package.json`, completing the migration to Jotai as the
sole state management library.
Removes all Recoil infrastructure: `RecoilRoot` wrapper from `App.tsx`
and test decorators, `RecoilDebugObserver`, Recoil-specific ESLint rules
(`use-getLoadable-and-getValue-to-get-atoms`,
`useRecoilCallback-has-dependency-array`), and legacy Recoil utility
hooks/types (`useRecoilComponentState`, `useRecoilComponentValue`,
`createComponentState`, `createFamilyState`, `getSnapshotValue`,
`cookieStorageEffect`, `localStorageEffect`, etc.).
Renames all `V2`-suffixed Jotai state files and types to their canonical
names (e.g., `ComponentStateV2` -> `ComponentState`,
`agentChatInputStateV2` -> `agentChatInputState`, `SelectorCallbacksV2`
-> `SelectorCallbacks`), and removes the now-redundant V1 counterparts.
Updates ~433 files across the codebase to use the renamed Jotai imports,
remove Recoil imports, and clean up test wrappers (`RecoilRootDecorator`
-> `JotaiRootDecorator`).
## Summary
- **Admin-level filtering**: New AI tab in admin panel with server-wide
model availability controls (whitelist/blacklist via
`AI_AUTO_ENABLE_NEW_MODELS`, `AI_DISABLED_MODEL_IDS`,
`AI_ENABLED_MODEL_IDS` config variables). Dedicated
`setAdminAiModelEnabled` mutation replaces frontend config-variable
manipulation. Filter dropdown to show/hide unconfigured and deprecated
models.
- **Workspace-level filtering**: Per-workspace controls with "Use best
models only" mode (curated list backed by `isRecommended` flag), or
custom whitelist/blacklist. Separate Smart/Fast model selectors with
"Best (...)" virtual options.
- **Security enforcement**: Both layers enforced at every backend
execution point — workspace update, agent create/update, chat execution.
Model ID validated against known models before config mutation. All
admin endpoints protected by `AdminPanelGuard`.
## Changes
### Backend (`twenty-server`)
- New config variables for admin-level model filtering
- `AiModelRegistryService`: `getAllModelsWithStatus()`,
`setModelAdminEnabled()` with model ID validation,
`isModelAdminAllowed()`
- `AdminPanelResolver`: `getAdminAiModels` query,
`setAdminAiModelEnabled` mutation
- `WorkspaceEntity`: new fields (`autoEnableNewAiModels`,
`disabledAiModelIds`, `enabledAiModelIds`, `useRecommendedModels`)
- `WorkspaceService`: model validation on `smartModel`/`fastModel`
updates
- `AgentResolver`: model availability checks on create/update
- `isModelAllowedByWorkspace` centralized utility
- `isRecommended` flag on model definitions
- Two TypeORM migrations
### Frontend (`twenty-front`)
- New `SettingsAdminAI` component with search, filter dropdown
(unconfigured/deprecated), and model toggle cards
- AI tab added to admin panel navigation
- `useWorkspaceAiModelAvailability` hook for workspace-level filtering
- `SettingsAIModelsTab` redesigned: merged sections, "Use best models
only" toggle, conditional available models list
- `getModelIcon`/`getModelProviderLabel` shared utilities with GraphQL
enum casing normalization
- Updated generated GraphQL types and mock data
## Test plan
- [ ] Toggle models on/off in admin panel AI tab and verify they
appear/disappear in workspace settings
- [ ] Enable "Use best models only" in workspace settings and verify
only recommended models are selectable
- [ ] Disable recommended mode and verify whitelist/blacklist toggles
work correctly
- [ ] Verify deprecated models hidden by default, shown greyed out when
filter enabled
- [ ] Verify unconfigured models hidden by default, shown disabled when
filter enabled
- [ ] Try setting a disabled model as Smart/Fast model — should be
rejected
- [ ] Try creating an agent with a disabled model — should be rejected
- [ ] Verify admin panel AI tab requires admin access
Made with [Cursor](https://cursor.com)
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
## Summary
Fix file uploads in AI chat (Agent Chat) failing with "Failed to upload
file" for all file types.
## Root Cause
`useAIChatFileUpload.ts` was using `useApolloCoreClient()` which points
to the `/graphql` (workspace) endpoint. However, `FileUploadResolver` is
decorated with `@MetadataResolver()`, meaning `uploadFile` is only
registered on the `/metadata` endpoint.
## Fix
Replace `useApolloCoreClient()` with `useApolloClient()` from
`@apollo/client`, which is the default Apollo client pointing to the
`/metadata` endpoint. This is consistent with how
`useUploadAttachmentFile.tsx` handles file uploads.
## Changes
- Replaced `useApolloCoreClient` import with `useApolloClient` from
`@apollo/client`
- Updated the client variable to use the default Apollo client
- Removed unused `useApolloCoreClient` import
Fixes#18153
## Summary
- **Model pricing overhaul**: All model constants updated with accurate
pricing in dollars per 1M tokens, including cached input rates, cache
creation rates, and tiered >200k context pricing
- **New providers**: Added Google (Gemini 3.x), Mistral, and AWS Bedrock
as inference providers. Bedrock serves Claude Opus 4.6 and Sonnet 4.6
via AWS, with proper credential handling following the existing S3/SES
pattern
- **InferenceProvider/ModelFamily split**: Refactored `ModelProvider`
into two orthogonal enums — `InferenceProvider` (who serves the model:
auth, SDK, metadata format) and `ModelFamily` (who created it: token
counting semantics). This eliminates growing `||` chains for token
normalization checks like `excludesCachedTokens`
- **Billing improvements**: Reasoning tokens charged at output rate,
cache token discounts applied accurately, real errors thrown to Sentry
on billing failures
## Test plan
- [x] All existing unit tests updated and passing (23 tests across 3
test files)
- [x] Lint passes for both twenty-server and twenty-front
- [ ] CI checks pass
Made with [Cursor](https://cursor.com)
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
## Summary
Replaces the static "Ask AI" header in the command menu with the
conversation’s auto-generated title once it’s set after the first
message.
## Changes
- **Backend:** Title is generated after the first user message (existing
behavior).
- **Frontend:** After the first stream completes, we fetch the thread
title and sync it to:
- `currentAIChatThreadTitleState` (persists across command menu
close/reopen)
- Command menu page info and navigation stack (so the title survives
back navigation)
- **Entry points:** Opening Ask AI from the left nav or command center
uses the same title resolution (explicit `pageTitle` → current thread
title → "Ask AI" fallback).
- **Race fix:** Title sync only runs when the thread that finished
streaming is still the active thread, so switching threads mid-stream
doesn’t overwrite the current thread’s title.
---------
Co-authored-by: Félix Malfait <felix@twenty.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
## Summary
- update AI chat message typography and list line-height for readability
- apply richer markdown-section styling for headings, spacing,
separators, and inline code
- keep links non-underlined by default with underline on hover, using
accent11 for link color
- preserve previous AI chat table design while keeping other markdown
improvements
## Validation
- yarn eslint
packages/twenty-front/src/modules/ai/components/LazyMarkdownRenderer.tsx
packages/twenty-front/src/modules/ai/components/AIChatMessage.tsx
---------
Co-authored-by: Félix Malfait <felix.malfait@gmail.com>
## Summary
- Add `@mention` support to the AI Chat text input by replacing the
plain textarea with a minimal Tiptap editor and building a shared
`mention` module with reusable Tiptap extensions (`MentionTag`,
`MentionSuggestion`), search hook (`useMentionSearch`), and suggestion
menu — all shared with the existing BlockNote-based Notes mentions to
avoid code duplication
- Mentions are serialized as
`[[record:objectName:recordId:displayName]]` markdown (the format
already understood by the backend and rendered in chat messages), and
displayed using the existing `RecordLink` chip component for visual
consistency
- Fix images in chat messages overflowing their container by
constraining to `max-width: 100%`
- Fix web_search tool display showing literal `{query}` instead of the
actual query (ICU single-quote escaping issue in Lingui `t` tagged
templates)
## Test plan
- [ ] Open AI Chat, type `@` and verify the suggestion menu appears with
searchable records
- [ ] Select a mention from the dropdown (via click or keyboard
Enter/ArrowUp/Down) and verify the record chip renders inline
- [ ] Send a message containing a mention and verify it appears
correctly in the conversation as a clickable `RecordLink`
- [ ] Verify Enter sends the message when the suggestion menu is closed,
and selects a mention when the menu is open
- [ ] Verify images in AI chat responses are constrained to the
container width
- [ ] Verify the web_search tool step shows the actual search query
(e.g. "Searched the web for Salesforce") instead of `{query}`
- [ ] Verify Notes @mentions still work as before
Made with [Cursor](https://cursor.com)
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
## Summary
- **Fix token renewal endpoint**: Use `/metadata` instead of `/graphql`
for token renewal in agent chat, fixing auth issues
- **Improve tool display**: Add `load_skills` support, show formatted
tool names (underscores → spaces) with finish/loading states, display
tool icons during loading, and support custom loading messages from tool
input
- **Refactor workflow agent management**: Replace direct
`AgentRepository` access with `AgentService` for create/delete/find
operations in workflow steps, improving encapsulation and consistency
- **Simplify Apollo client usage**: Remove explicit Apollo client
override in `useGetToolIndex`, add `AgentChatProvider` to
`AppRouterProviders`
- **Fix load-skill tool**: Change parameter type from `string` to `json`
for proper schema parsing
- **Update agent-chat-streaming**: Use `AgentService` for agent
resolution and tool registration instead of direct repository queries
## Test plan
- [ ] Verify AI agent chat works end-to-end (send message, receive
response)
- [ ] Verify tool steps display correctly with icons and proper messages
during loading and after completion
- [ ] Verify workflow AI agent step creation and deletion works
correctly
- [ ] Verify workflow version cloning preserves agent configuration
- [ ] Verify token renewal works when tokens expire during agent chat
Made with [Cursor](https://cursor.com)
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
⚠️ **AI-generated PR — not ready for review** ⚠️
cc @FelixMalfait
---
## Changes
### System prompt improvements
- Explicit skill-before-tools workflow to prevent the model from calling
tools without loading the matching skill first
- Data efficiency guidance (default small limits, use filters)
- Pluralized `load_skill` → `load_skills` for consistency with
`load_tools`
### Token usage reduction
- Output serialization layer: strips null/undefined/empty values from
tool results
- Lowered default `find_*` limit from 100 → 10, max from 1000 → 100
### System object tool generation
- System objects (calendar events, messages, etc.) now generate AI tools
- Only workflow-related and favorite-related objects are excluded
### Context window display fix
- **Bug**: UI compared cumulative tokens (sum of all turns) against
single-request context window → showed 100% after a few turns
- **Fix**: Track `conversationSize` (last step's `inputTokens`) which
represents the actual conversation history size sent to the model
- New `conversationSize` column on thread entity with migration
### Workspace AI instructions
- Support for custom workspace-level AI instructions
---------
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
https://github.com/user-attachments/assets/c4e63edb-6e98-44bc-841f-ee110ae712d4
How it works
- `manifest.json` files are now committed when apps are published to our
repo
- to display available apps, from the server, we read into our github
repo, using a pod-scoped cache
- feature flagged
- app installation will be behind permission gate MARKETPLACE_APPS
Limitations and what is yet to develop
- content and settings tabs
- installed apps tab
- app installation
- test and potentially fix reading from .manifest.json once [Reshape
manifest
structure](https://github.com/twentyhq/core-team-issues/issues/2183) is
done. additional work is expected on assets notably. (couldnt properly
do it here as manifest.json will only be committed after this pr)
- we only read in community/ folder for now - we may want tochange that
- the cache is rather artisanal for now and scoped by pod - we may want
to change that
## Summary
Fixes an issue where the AI chat would show loading shimmers
indefinitely when opened on a workspace with no conversation history.
**Root cause:** The `isLoading` state in `useAgentChat` included
`!currentAIChatThread`. On workspaces with no chat threads,
`currentAIChatThread` remained `null`, causing `isLoading` to be
permanently `true`.
**Changes:**
- Remove `!currentAIChatThread` from `isLoading` calculation in
`useAgentChat` - this state should only reflect streaming/file selection
status
- Auto-create a chat thread in `useAgentChatData` when the threads query
returns empty, ensuring a valid thread exists for the `useChat` hook to
initialize properly
- Add primary font color to empty state title for better visibility
## Test plan
1. Create a new workspace or use a workspace with no AI chat history
2. Open the AI chat
3. Verify the empty state shows (not infinite loading shimmer)
4. Send a message and verify it works correctly
Made with [Cursor](https://cursor.com)
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
## Summary
This PR enables serverless functions to be exposed as AI tools, allowing
them to be used by AI agents.
### Changes
- Added new `SERVERLESS_FUNCTION` tool category
- Added `toolDescription`, `toolInputSchema`, and `toolOutputSchema`
fields to serverless functions
- Created database migration for the new schema columns
- Added tool index query and resolver for fetching available tools
- Added Settings AI page tabs (Skills, Tools, Settings) with new tools
table
- Added utility to convert tool schema to JSON schema format
- Updated frontend to display tools in the settings page
### Implementation Details
- Serverless functions can now define tool metadata (description,
input/output schemas)
- These functions are automatically registered in the tool registry
- The tool index endpoint allows querying available tools with their
schemas
- Settings page now has a dedicated Tools tab showing all available
tools
## Summary
This PR adds user-friendly error handling for AI chat features,
specifically for **billing credits exhausted** and **API key not
configured** errors.
## Changes
### Backend
- Added `BILLING_CREDITS_EXHAUSTED` exception code with 402 status
- Added `API_KEY_NOT_CONFIGURED` exception code with 503 status
- Added billing check before AI chat streaming in
`agent-chat.controller.ts`
- Added error code to HTTP exception response body for frontend error
type detection
- Created `AgentRestApiExceptionFilter` for agent-specific errors
### Frontend
- Created `AIChatBanner` - reusable banner component for error/warning
messages
- Created `AIChatCreditsExhaustedMessage` - shows upgrade prompts based
on user permissions
- Created `AIChatApiKeyNotConfiguredMessage` - shows configuration
guidance with docs link
- Created `AIChatErrorRenderer` - encapsulates error type switching
logic (fixes nested ternary)
- Created `AIChatStandaloneError` - displays errors when there are no
messages
- Split `aiChatErrorUtils.ts` into separate files (1 export per file):
- `AIChatErrorCode.ts`
- `extractErrorCode.ts`
- `isAIChatErrorOfType.ts`
- `isBillingCreditsExhaustedError.ts`
- `isApiKeyNotConfiguredError.ts`
- Added comprehensive test coverage (27 tests)
### Other
- Updated trial period banner messaging
## Testing
- All lint checks pass
- All 27 new tests pass
- TypeScript typecheck passes
## Summary
This PR enforces the use of `@/` alias for imports instead of relative
parent imports (`../`).
## Changes
### ESLint Configuration
- Added `no-restricted-imports` pattern in `eslint.config.react.mjs` to
block `../*` imports with the message "Relative parent imports are not
allowed. Use @/ alias instead."
- Removed the non-working `import/no-relative-parent-imports` rule
(doesn't work properly in ESLint flat config)
### VS Code Settings
- Added `javascript.preferences.importModuleSpecifier: non-relative` to
`.vscode/settings.json` (TypeScript setting was already there)
### Code Fixes
- Fixed **941 relative parent imports** across **706 files** in
`packages/twenty-front`
- All `../` imports converted to use `@/` alias
## Why
- Consistent import style across the codebase
- Easier to move files without breaking imports
- Better IDE support for auto-imports
- Clearer understanding of where imports come from
## Summary
This PR adds the `lingui/no-unlocalized-strings` ESLint rule to detect
untranslated strings and fixes translation issues across multiple
components.
## Changes
### ESLint Configuration (`eslint.config.react.mjs`)
- Added comprehensive `ignore` patterns for non-translatable strings
(CSS values, HTML attributes, technical identifiers)
- Added `ignoreNames` for props that don't need translation (className,
data-*, aria-*, etc.)
- Added `ignoreFunctions` for console methods, URL APIs, and other
non-user-facing functions
- Disabled rule for debug files, storybook, and test files
### Components Fixed (~19 files)
- Object record components (field inputs, pickers, merge dialogs)
- Settings components (accounts, admin panel)
- Serverless function components
- Record table and title cell components
## Status
🚧 **Work in Progress** - ~124 files remaining to fix
This PR is being submitted as draft to allow progressive fixing of
remaining translation issues.
## Testing
- Run `npx eslint "src/**/*.tsx"` in `packages/twenty-front` to check
remaining issues
Félix Malfait