## 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>
Gmail 429/403 rate-limit responses include an explicit retry-after
timestamp, usually ~15 minutes out.
The exponential backoff starts at 1 minute, so the channel burns through
all 5 retry attempts before the window actually closes and gets marked
as permanently failed.
Adds throttleRetryAfter to the message channel and uses max(backoff,
retryAfter) in isThrottled().
## Context
Creating a new object should now also create its record page layout,
tabs and widgets, including fields widget with its associated views/view
fields.
Custom objects record page layout fields widgets don't have section per
default
Note: I had to enable some widget creation through the custom API but we
should now implement proper validation (which should be minimal since
there is usually only the configuration type in the configuration
(except for FIELDS widget which contains a viewId)
Next step: Create view field should also create a viewField for the
FIELDS_WIDGET view (we should also add in the FIELDS widget
configuration a newFieldDefaults which will contain default visibility
and position to apply to the new view field)
The feature is still gated behind an env variable (this was necessary
for workspace creation, not so much here in this case but I prefer to
keep the same path for consistence)
This PR addresses TODO comments and improves code quality:
### 1. PullRequestItem.tsx
- Replaced `react-tooltip` with `twenty-ui` `AppTooltip` component
- Removed TODO comment
- Uses internal component library for consistency
### 2. MenuItemAvatar.tsx
- Refactored to use `MenuItem` internally, eliminating code duplication
- Removed about 63 lines of duplicate code
- Removed TODO comment as the merge is now complete
---------
Co-authored-by: cubic-dev-ai[bot] <191113872+cubic-dev-ai[bot]@users.noreply.github.com>
- moves workspace:* dependencies to dev-dependencies to avoid spreading
them in npm releases
- remove fix on rollup.external
- remove prepublishOnly and postpublish scripts
- set bundle packages to private
- add release-dump-version that update package.json version before
releasing to npm
- add release-verify-build that check no externalized twenty package
exists in `dist` before releasing to npm
- works with new release github action here ->
https://github.com/twentyhq/twenty-infra/pull/397
## Split twenty-sdk build into separate Node and browser targets
The SDK was bundling Node.js code (CLI, SDK API) and browser code (UI
components, front-component renderer) through a single Vite config. This
caused incorrect externalization — Node builtins leaked into browser
bundles and browser-specific chunking logic applied to CLI output.
This PR splits the build into `vite.config.node.ts` and
`vite.config.browser.ts` so each target gets the right externals and
output format.
Also includes a few housekeeping renames:
- `front-component` export path → `front-component-renderer` (matches
what it actually is)
- `front-component-common` merged into `front-component-api` (was a
needless extra module)
Fixes issue where tabs were synchronized when opening two records of the
same type in show page and side panel.
The root cause was that tab instance IDs were only based on
`pageLayoutId`, causing all records using the same page layout to share
the same tab state.
This change includes the record ID in the tab instance ID, making tabs
unique per record while maintaining backward compatibility for cases
where no record ID is available.
Fixes#17522
---------
Co-authored-by: Eruis <github@eruis.example>
## Summary
- Removed `vite-plugin-dts` (which used `tsc` internally) from the Vite
build and replaced DTS generation with `tsgo` as a sequential post-build
step — **~0.7s vs 1-10s**.
- Disabled `reportCompressedSize` to skip gzip computation for 64 output
files.
- Converted the build target to an explicit `nx:run-commands` executor
with sequential `vite build` → `tsgo` commands.
The `twenty-emails:build` step goes from ~22s to ~7s under load.
## Test plan
- [x] `nx build twenty-emails` produces both JS (64 files) and DTS (74
files) correctly
- [x] `dist/index.d.ts` exports match the source `src/index.ts`
- [x] Full `nx build twenty-server` succeeds end-to-end
- [ ] CI build passes
Made with [Cursor](https://cursor.com)
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
# Introduction
Avoid sending flat entity that contains server specific properties such
as foreignKey aggregators and universal properties by transpiling from
flat entity to scalar flat entity
A scalar flat entity is the exact match with the entities columns
Following https://github.com/twentyhq/twenty/pull/17622
## 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>
This PR aims to fix: #17408
Main modification includes adding a new column for dropdown in the
object permission rule table (containing options for editing and
removal). Removal logic is implemented using existing pattern with hook
```useResetObjectPermission``` (relies on existing hooks
```useUpsertFieldPermissionInDraftRole``` and
```useUpsertObjectPermissionInDraftRole```).
Feel free to suggest any necessary changes. Functionality (unrestricted
access is allowed when permission removal is applied) is already tested.
Demo video:
https://drive.google.com/file/d/1M4RYHw-JEhDdJksKkL3MY_VyXAV3aS9I/view?usp=sharing
---------
Co-authored-by: Etienne <45695613+etiennejouan@users.noreply.github.com>
As attachment files have migrated from fullPath to file files field,
need to migrate richText logic to fit to new attachment file handling +
data migration
In this PR
- Content tab for marketplace apps and installed apps: complies with
[figma](https://www.figma.com/design/xt8O9mFeLl46C5InWwoMrN/Twenty?node-id=34845-126856);
addition of field section showing fields added to standard objects;
initiative: arrow opens a sub-table of fields rows. (suggested because
1/ for marketplace apps we cannot redirect to the actual object page in
settings since the object does not exist yet in the workspace 2/ since
we dont have an quick "go back to application page" option, it can be
annoying to be redirected to a different setting page when we just want
to look at the content of the app objects)
- Permission tab for marketplace apps and installed apps
- left to do - settings tab (in another PR)
There are breaking changes but it's behind a feature flag not exposed
(access to marketplace) so not problematic
marketplace apps
https://github.com/user-attachments/assets/4c660101-50fc-47ce-b90a-8d6f17db5e74
installed apps
https://github.com/user-attachments/assets/c9229ee1-e75f-4cad-8766-758b2c5b37b4
## Summary
This PR adds **metadata eventing**: when schema metadata
(objectMetadata, fieldMetadata, view, viewField, etc.) is created,
updated, or deleted, we now emit events that can trigger webhooks and
future audit logs. It also adds **actor context** (`userId`,
`workspaceMemberId`) to those events so subscribers can attribute
changes to a user or API key.
## What changed
### 1. Metadata eventing (first commit)
- **MetadataEventEmitter**
New service that emits batch events after successful workspace
migrations. Event names follow `metadata.{entity}.{action}` (e.g.
`metadata.objectMetadata.created`, `metadata.fieldMetadata.updated`).
- **MetadataEventsToDbListener**
Listens for metadata events and enqueues webhook delivery via
`CallWebhookJobsForMetadataJob`.
- **Event types** (twenty-shared)
`MetadataEventAction`, `MetadataEventBatch`, and record event types for
create/update/delete.
- **WorkspaceMigrationValidateBuildAndRunService**
Calls the metadata event emitter after running migrations so all
metadata changes (from any module) emit events from a single place.
- **Create events**
Sourced from the create action payload (`flatEntity` /
`flatFieldMetadatas`) because `fromToAllFlatEntityMaps` does not provide
a before/after diff for creates. Update/delete events still use the
fromToAllFlatEntityMaps comparison.
### 2. Actor context (second commit)
- **MetadataEventEmitter**
Accepts optional `actorContext` (`userId`, `workspaceMemberId`) and
includes it on emitted batch events.
- **WorkspaceMigrationValidateBuildAndRunService**
Passes `actorContext` from the request into the metadata event emitter.
- **Metadata resolvers & services**
All metadata modules resolve `@AuthUser({ allowUndefined: true })` and
`@AuthUserWorkspaceId()` and pass `userId` and `workspaceMemberId`
through to the migration/event pipeline. Both are optional so
API-key–authenticated requests (no user) still emit events without a
user identity.
Shared some questions on Discord about the PR.
---------
Co-authored-by: Félix Malfait <felix.malfait@gmail.com>
Co-authored-by: prastoin <paul@twenty.com>
# Introduction
## Use `flatEntityTranspilers.toScalarFlatEntity` in create action
handler
**Changes:**
- Modified
`BaseWorkspaceMigrationRunnerActionHandlerService.insertFlatEntitiesInRepository()`
to transform flat entities using `toScalarFlatEntity()` before database
insertion
**What it does:**
Strips out TypeORM relation objects and metadata-only properties,
ensuring only scalar values (primitives, IDs, dates) are inserted into
the database.
**Benefits:**
- **Type Safety:** Prevents accidental insertion of nested objects that
TypeORM can't persist
- **Consistency:** All 17+ create action handlers automatically benefit
from proper data transformation
- **Single Source of Truth:** Centralized logic for what constitutes a
database-insertable entity
- **Prevents Errors:** Uses entity configuration schema to ensure only
valid properties are included
## Usage
```ts
protected async insertFlatEntitiesInRepository({
flatEntities,
queryRunner,
}: {
queryRunner: QueryRunner;
flatEntities: MetadataFlatEntity<TMetadataName>[];
}) {
const metadataEntity =
ALL_METADATA_ENTITY_BY_METADATA_NAME[this.metadataName];
const repository = queryRunner.manager.getRepository(metadataEntity);
const scalarFlatEntities = flatEntities.map((flatEntity) =>
flatEntityTranspilers.toScalarFlatEntity({
flatEntity,
metadataName: this.metadataName,
}),
);
await repository.insert(scalarFlatEntities);
}
```
## Upcoming refactor
About to completely split the
`packages/twenty-server/src/engine/workspace-manager/workspace-migration/workspace-migration-runner/interfaces/workspace-migration-runner-action-handler-service.interface.ts`
into three dedicated boilerplate one for each action type `create`
`delete` `update` will provide a better interfacing and typing + will
allow not requiring the user to provide the metadata execute handler as
required
## Context
Prefill the FIELDS widget configuration in standard page layouts during
workspace creation, linking each widget to a dedicated view with
positioned fields organized into sections (via view field groups)
We wanted something very declarative (by manually setting position and
visibility of each field per standard object).
In this PR I've generated all the compute- utils via AI (😨) for
position/visibility, we'll probably want to confirm with the product
which ordering/visibility we want for each standard object but I feel
like this can be merged as it is since it's behind a feature flag and
this will unblock the work on the frontend
## Summary
Fixes `EMFILE: too many open files, watch` crash that most of the team
is hitting on macOS when running `yarn start` or `npx nx start
twenty-server`.
Adds `rimraf dist` before `nest start --watch` in the `start` and
`start:debug` targets, so the watcher starts with a clean output
directory.
## Root cause
The NestJS SWC compiler (`@nestjs/cli@11`) creates **three overlapping
chokidar watchers** when `nest start --watch` runs:
| Watcher | Watches | Purpose | Handles |
|---|---|---|---|
| SWC CLI (`@swc/cli`) | `src/` | Detects file changes → recompiles |
~1,730 |
| NestJS `watchFilesInSrcDir` | `src/` | Workaround: SWC misses new
files | shared with above |
| NestJS `watchFilesInOutDir` | **`dist/`** | Detects compiled `.js` →
restarts server | **~3,548** |
`@nestjs/cli@11` ships with **chokidar v4**, which dropped macOS
`fsevents` support and uses `fs.watch()` instead — creating **one file
descriptor per directory**. Chokidar v3 used a single `fsevents` kernel
subscription per directory tree.
Total: **~5,000+ `fs.watch()` handles**, far exceeding the default macOS
`ulimit -n` of ~2,560.
### Why it broke now
PR #17851 (`15fc850212`) changed the `start` target from `dependsOn:
["build"]` to `dependsOn: ["^build"]`, removing the `rimraf dist && nest
build` pre-step. Without that cleanup, `dist/` accumulated stale
directories from code reorganizations (e.g. `application-layer/` →
`application/` rename), growing to ~3,548 directories vs ~1,730 in a
clean build.
## What this PR does
Adds `rimraf dist &&` before `nest start --watch` in the `start` and
`start:debug` commands. This ensures `dist/` starts empty and only
contains directories matching the current `src/` structure (~1,730),
keeping watcher count in the ~3,400 range.
We still get the startup speed improvement from #17851 (no redundant
full SWC build), since `rimraf dist` is ~instant while the removed `nest
build` step took 30-60s.
## Future considerations
As the codebase grows, even a clean `dist/` will eventually approach the
macOS default `ulimit -n` (~2,560). Options to consider if that happens:
1. **Yarn resolution to force chokidar 3.6.0** — restores `fsevents`,
reducing watcher count from ~5,000 to ~3-5. This is what Vite 7 does
internally. Simple and effective, but pins to an older major version.
2. **Patch `@nestjs/cli`** to skip the `dist/` watcher — the
`watchFilesInOutDir` watcher accounts for ~65% of all handles and only
exists because NestJS doesn't have a direct hook into SWC's
compilation-complete event. Could be removed via `yarn patch`.
3. **Replace `nest start --watch` entirely** — use `node
--watch-path=src` (Node 22+) with `@swc-node/register` for on-the-fly
compilation. Uses a single native watcher regardless of directory count.
Requires rethinking asset copying (`watchAssets` in `nest-cli.json`).
4. **Wait for upstream fix** — NestJS CLI should either re-add
`fsevents` support or use Node's recursive `fs.watch()` option
(available since Node 20) instead of per-directory watchers.
## Test plan
- [ ] Run `npx nx start twenty-server` on macOS — server starts without
EMFILE error
- [ ] Run `npx nx start:debug twenty-server` — debug mode starts without
EMFILE error
- [ ] Edit a `.ts` file while server is running — hot reload still works
- [ ] Run `yarn start` (frontend + backend + worker) — no crashes
Made with [Cursor](https://cursor.com)
Co-authored-by: Cursor <cursoragent@cursor.com>
## Remove Recoil from twenty-ui
Completely removes the `recoil` dependency from `twenty-ui` by
converting all atoms, hooks, and providers to Jotai equivalents.
### twenty-ui
- `createState` now returns a Jotai `PrimitiveAtom` instead of a Recoil
atom
- `iconsState`, `IconsProvider`, `useIcons` converted to Jotai
(`useSetAtom`, `useAtomValue`)
- `RecoilRootDecorator` now uses Jotai `Provider` (name kept for compat)
- Deleted unused `invalidAvatarUrlsState` (Avatar already uses
`invalidAvatarUrlsAtomV2`)
- Removed `recoil` from `package.json`
### twenty-front
- Created local Recoil `createState` at
`@/ui/utilities/state/utils/createState` for ~112 state files still on
Recoil
- Updated all imports accordingly
- Removed `iconsState` from Recoil snapshot preservation in `useAuth`
(lives in Jotai store now)
# Introduction
Related https://github.com/twentyhq/core-team-issues/issues/2227
On a field name update side effect leading to an index field mutation it
wouldn't get caught by the builder leading to an index field desync
We should land on a standard pattern regarding the field index either
jsonb or syncableEntity so this would not occur anymore as it would have
been strictly typed
## Recoil → Jotai progressive migration: infrastructure +
ChipFieldDisplay
### Benchmark
In the beginning, there was no hope:
<img width="1180" height="948" alt="image"
src="https://github.com/user-attachments/assets/f8635991-52e6-4958-8240-6ba7214132b2"
/>
Then the hope was reborn
<img width="2070" height="948" alt="image"
src="https://github.com/user-attachments/assets/be1182b9-1c8d-4fdc-ab4c-1484ad74449d"
/>
### Approach
We introduce a **V2 state management layer** backed by Jotai that
mirrors the existing Recoil API, enabling component-by-component
migration without a big-bang rewrite.
#### V2 API (Jotai-backed, Recoil-ergonomic)
- `createStateV2` / `createFamilyStateV2` — drop-in replacements for
`createState` / `createFamilyState`, returning wrapper types over Jotai
atoms
- `useRecoilValueV2`, `useRecoilStateV2`, `useFamilyRecoilValueV2`, etc.
— thin wrappers around Jotai's `useAtomValue` / `useAtom` / `useSetAtom`
- A shared `jotaiStore` (via `createStore()`) passed to a
`<JotaiProvider>` wrapping `<RecoilRoot>`, also accessible imperatively
for dual-writes
#### Dual-write bridge for progressive migration
For state shared between migrated and non-migrated components, we use
**dual-write**: writers update both the Recoil atom and the Jotai V2
atom (via `jotaiStore.set()`). This avoids sync components or extra
subscriptions.
Write sites updated: `useUpsertRecordsInStore`, `useSetRecordTableData`,
`ListenRecordUpdatesEffect`, `RecordShowEffect`,
`useLoadRecordIndexStates`, `useUpdateObjectViewOptions`.
#### First migration: ChipFieldDisplay render path
- `useChipFieldDisplay` → reads `recordStoreFamilyStateV2` via
`useFamilyRecoilValueV2` (was `useRecoilValue(recordStoreFamilyState)`)
- `RecordChip` → reads `recordIndexOpenRecordInStateV2` via
`useRecoilValueV2` (was `useRecoilValue(recordIndexOpenRecordInState)`)
- `Avatar` (twenty-ui) and event handlers (`useOpenRecordInCommandMenu`)
left on Recoil — not on the render path / in a different package
#### Pattern for migrating additional state
1. Create V2 atom: `createStateV2` or `createFamilyStateV2`
2. Add `jotaiStore.set(v2Atom, value)` at each write site
3. Switch readers to `useRecoilValueV2(v2Atom)`
4. Once all readers are migrated, remove the Recoil atom and dual-writes
#### Why not jotai-recoil-adapter?
Evaluated
[jotai-recoil-adapter](https://github.com/clockelliptic/jotai-recoil-adapter)
— not production-ready (21 open issues, no React 19, forces providerless
mode, missing types). We built a purpose-built thin layer instead.
Bumps
[@types/bytes](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/bytes)
from 3.1.4 to 3.1.5.
<details>
<summary>Commits</summary>
<ul>
<li>See full diff in <a
href="https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/bytes">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
---------
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Abdullah <125115953+mabdullahabaid@users.noreply.github.com>
## PR description
This PR:
- Creates a TypeScript-based extractor that discovers all exported
twenty-ui components by scanning barrel files, extracting
props/slots/events via ts-morph type analysis, and generating the remote
DOM bindings automatically.
- Adds a new ESLint rule which enforces all *Props types in twenty-ui
components to be exported, which is required for the extractor to
discover component prop types. Existing twenty-ui components are updated
to comply with this rule.
- Extends the remote DOM generation to support slots, per-component
events, forwardRef wrappers, and richer property types (array, object,
function)
## Edge cases to fix in another PR
- Icons cannot be rendered inside buttons
- IconButtons throw an error when mounted
- MenuItems are not displayed correctly
- MenuItemNavigate throws on click
## Video Demo
https://github.com/user-attachments/assets/c2ed67cf-6a15-4896-9fec-e83fac0e862b
