## Summary
This PR adds configurable response format support for AI agents,
allowing them to return either plain text or structured JSON data based
on a defined schema.
## Key Features
### 1. Agent Response Format Configuration
- Added `AgentResponseFormat` type supporting:
- `text`: Returns plain text responses (default)
- `json`: Returns structured JSON based on defined schema
- New `AgentResponseSchema` type moved to `twenty-shared/ai` for sharing
between frontend/backend
### 2. Settings UI
- New `SettingsAgentResponseFormat` component for configuring response
format
- Visual schema builder for defining JSON output structure
- Real-time validation and preview
- Integrated into agent settings tab
### 3. Workflow Integration
- AI Agent workflow action automatically uses agent's configured
response format
- Output schema dynamically generated from agent's response format
- Workflow variable picker shows structured fields for JSON responses
- Backward compatible with existing text-only agents
### 4. Backend Implementation
- Added `convertAgentSchemaToZod` utility to validate JSON responses
- Agent executor service handles both text and JSON generation
- Automatic agent creation/cloning when adding AI agent steps to
workflows
- Unique agent naming with conflict resolution
### 5. Database Migration
- Migration `1763622159656-update-agent-response-format.ts`
- Sets default `responseFormat` to `{"type":"text"}` for existing agents
- Updated all standard agents with proper response format
## Changes by Module
### Frontend (`twenty-front`)
- 🆕 `AgentResponseFormat` type
- 🆕 `SettingsAgentResponseFormat` component
- ✏️ Updated `WorkflowEditActionAiAgent` to support response format
configuration
- 🗑️ Removed deprecated `useAiAgentOutputSchema` hook and
`AiAgentOutputSchema` type
### Backend (`twenty-server`)
- 🆕 `AgentResponseFormat` type in agent entity
- 🆕 `convertAgentSchemaToZod` utility for schema validation
- ✏️ Updated `AiAgentExecutorService` to handle both text and JSON
generation
- ✏️ Updated `WorkflowSchemaWorkspaceService` to generate output schema
from agent config
- ✏️ Enhanced `WorkflowVersionStepOperationsWorkspaceService` with agent
creation/cloning
- 🆕 Agent naming constants for conflict resolution
### Shared (`twenty-shared`)
- 🆕 `AgentResponseSchema` type
- 🆕 `ModelConfiguration` type moved to shared package
- Updated exports in `ai/index.ts`
## Code Quality
- Removed useless comments following code style guidelines
- All linter checks passed
- Type-safe implementation with proper TypeScript types
## Testing
- ✅ Database migration tested
- ✅ Agent creation/cloning in workflows verified
- ✅ Response format switching (text ↔ JSON) validated
- ✅ Backward compatibility with existing agents confirmed
## Migration Notes
- Existing agents will have `responseFormat: {type: 'text'}` set
automatically
- No breaking changes - all existing functionality preserved
- Agents can be updated to use JSON format through settings UI
# Introduction
Fixes https://github.com/twentyhq/private-issues/issues/371
We weren't strictly validating relation field collision on join column
name availability of the target field object
## Refactor
Extracted morph or relation specific condition out of the common flat
field metadata name validate availability to be located in the dedicated
morph or relation flat field validator
## Tests
Added two tests, ONE_TO_MANY and MANY_TO_ONE in order to cover the use
case
Fixes https://github.com/twentyhq/private-issues/issues/362
**How to reproduce**
Link a person that has a duplicate to an opportunity. (you can create a
duplicate by giving two people the same linkedin link).
Open the opportunity record from opportunity table.
Click on the related person (in "Point of contact").
In front of "Duplicates", click on the merge button (two arrows becoming
one).
You should here see an empty "Merge preview" and an error when clicking
"First" tab.
**Issue**
The issue is that CommandMenuMergeRecordPage is getting the referenced
objectMetadataItem from useContextStoreObjectMetadataItemOrThrow without
an instance id. contextStoreObjectMetadataItem is still "opportunity" as
it should be, being on an opportunity view.
So further down it attempts to display the record page according the
label identifier field from opportunity, which is a text field, "name",
and it breaks because the record is actually a person for who the "name"
field is not a text but a full_name type.
**Fix**
I suggested a fix that offers the possibility to find the referenced
objectMetadataItem from the MergeRecords instanceId. But I still gave
flexibility to avoid having to set that state everytime we open the
merge tab, by falling back to the default
contextStoreObjectMetadataItem. (this is used when we merge records from
ticking two records from a view and open the command menu).
Im not sure this is the best option. Open to suggestions !
---------
Co-authored-by: Charles Bochet <charles@twenty.com>
The `VITE_DISABLE_ESLINT_CHECKER` environment variable is removed from
the codebase. ESLint checker no longer runs during Vite builds
(equivalent to the previous `VITE_DISABLE_ESLINT_CHECKER=true`
behavior).
**Configuration**
- Removed from `.env.example` (active and commented lines)
- Removed from `vite.config.ts` destructuring and conditional logic
- Removed from build scripts in `package.json` and `nx.json`
**Code change in vite.config.ts:**
```diff
- if (VITE_DISABLE_ESLINT_CHECKER !== 'true') {
- checkers['eslint'] = {
- lintCommand: 'eslint ../../packages/twenty-front --max-warnings 0',
- useFlatConfig: true,
- };
- }
```
**Documentation**
- Updated main English troubleshooting guide to remove references to the
variable
- Translated documentation files are intentionally not modified and will
be handled by a separate workflow
> [!NOTE]
> ESLint will not run in the background via Vite's checker plugin.
Developers will need to run `npx nx lint twenty-front` manually or rely
on their IDE's ESLint extension for real-time feedback on open files.
Created from VS Code via the <a
href="https://marketplace.visualstudio.com/items?itemName=GitHub.vscode-pull-request-github">GitHub
Pull Request</a> extension.
<!-- START COPILOT CODING AGENT SUFFIX -->
<details>
<summary>Original prompt</summary>
> Your job is to delete everything related to
VITE_DISABLE_ESLINT_CHECKER in the codebase.
>
> We mention this env var in documentation: drop the content talking
about it.
>
> We use it in the vite config: drop the check and keep the code paths
that used to run when `VITE_DISABLE_ESLINT_CHECKER=true`.
>
> User has selected text in file packages/twenty-front/.env.example from
3:1 to 3:28
</details>
Created from VS Code via the [GitHub Pull
Request](https://marketplace.visualstudio.com/items?itemName=GitHub.vscode-pull-request-github)
extension.
<!-- START COPILOT CODING AGENT TIPS -->
---
✨ Let Copilot coding agent [set things up for
you](https://github.com/twentyhq/twenty/issues/new?title=✨+Set+up+Copilot+instructions&body=Configure%20instructions%20for%20this%20repository%20as%20documented%20in%20%5BBest%20practices%20for%20Copilot%20coding%20agent%20in%20your%20repository%5D%28https://gh.io/copilot-coding-agent-tips%29%2E%0A%0A%3COnboard%20this%20repo%3E&assignees=copilot)
— coding agent works faster and does higher quality work when set up for
your repo.
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: Devessier <29370468+Devessier@users.noreply.github.com>
- These actions are displayed in the accent color
- Added new context store state
`contextStoreIsPageInEditModeComponentState`
- Reverted the order in which the actions are displayed (the first
action should appear to the right of the top bar action menu)
https://github.com/user-attachments/assets/3a0769cf-61ed-4619-8c4d-e3a01765b63c
## Problem
When accessing file URLs like `/files/attachment/{token}/{filename}`,
the server was returning 500 errors with no logs. The issue was that the
route pattern `*path/:filename` was not properly extracting parameters,
causing `request.params[0]` to be undefined.
## Solution
- Changed route from `@Get('*path/:filename')` to
`@Get(':folder/:token/:filename')` for explicit parameter extraction
- Simplified `extractFileInfoFromRequest` to use named route parameters
directly instead of complex path parsing
- Removed unnecessary logging that was added during debugging
- Added test to verify route parameters are correctly extracted and
passed to FileService
## Testing
- Added unit test that verifies folder, token, and filename parameters
are correctly passed to the service
- Test will catch any future regressions where route parameters are not
properly extracted
## 🐛 Issues Fixed
### 1. Role Editing Not Working for New Agents
When creating a new agent and then creating a role for it, the role
permissions appeared as non-editable. This was caused by:
- In create mode, `agentId = ''` (empty string from `useParams`)
- Empty string is **falsy** but `isDefined('')` returns **true**
- This caused incorrect behavior in role exclusivity checks and API
calls
### 2. Missing Role Data Loading
The agent form wasn't loading role data needed for permission editing
because it was missing the `SettingsRolesQueryEffect` component.
### 3. Navigation Conflicts
The `useSaveDraftRoleToDB` hook contained navigation logic that caused
conflicts when used from different contexts (role detail page vs agent
form).
### 4. Linting Errors
Unused `useIcons` import in `SettingsAgentRoleTab.tsx`.
---
## 🔧 Changes Made
### Agent Role Tab (`SettingsAgentRoleTab.tsx`)
- ✅ Use `isNonEmptyString(agentId)` to validate agentId (follows
codebase patterns)
- ✅ Improved role exclusivity logic to handle both create and edit
modes:
- **Edit mode**: Role must be assigned exclusively to this agent
- **Create mode**: Role must not be assigned to anyone yet
- ✅ Only call `assignRoleToAgent` when a valid agentId exists
- ✅ Pass `undefined` instead of empty string for `fromAgentId` prop
### Role Hook (`useSaveDraftRoleToDB.ts`)
- ✅ Removed navigation logic from the hook (better separation of
concerns)
- ✅ Removed `useNavigateSettings` and `SettingsPath` dependencies
- ✅ Hook now only handles data persistence, not navigation
### Role Component (`SettingsRole.tsx`)
- ✅ Added navigation after successful role creation in create mode
- ✅ Navigation now handled by the component using the hook
### Agent Form (`SettingsAgentForm.tsx`)
- ✅ Added `SettingsRolesQueryEffect` to ensure role data is loaded
- ✅ Agent form handles its own navigation after save
---
## ✅ Testing Scenarios
All these scenarios now work correctly:
1. ✅ Create new agent → Create role → Edit permissions → Save agent
2. ✅ Edit existing agent → Create role → Edit permissions → Save
3. ✅ Edit existing agent → Try to edit shared role (shows warning
message)
4. ✅ Navigate to object-level permissions from agent form with proper
breadcrumbs
---
## 📝 Technical Details
### Root Cause Analysis
The main issue was that empty string was being treated differently in
different checks:
- `agentId &&` → evaluates to `false` (empty string is falsy)
- `isDefined(agentId)` → returns `true` (empty string is defined)
This inconsistency caused the role to appear as non-editable and
attempted invalid API calls.
### Solution
Used `isNonEmptyString()` from `@sniptt/guards` which properly checks
both that the value is defined AND not empty, following codebase
conventions.
---
## 🎯 Impact
- Fixes critical bug preventing role permission configuration for new
agents
- Improves code quality with better separation of concerns
- Makes navigation logic more predictable and maintainable
- Follows codebase patterns and guidelines
Previously, single-item fields `maxItemCount: 1` didn’t show updated
values after pressing `Enter` the UI only refreshed on click outside.
This happened because the items list was hidden while
`shouldAutoEditSingleItem` remained true.
This PR updates the render condition to also check `!isInputDisplayed`,
ensuring the items list re-renders immediately after editing.
**Result:** Instant UI updates on Enter with no impact on multi-item
fields.
Fixes#15792
Co-authored-by: Lucas Bordeau <bordeau.lucas@gmail.com>
I know you did this change in order to make the frontend faster and less
resource eating. However it broke this optimistic rendering part
@lucasbordeau.
I suggest this quick fix, but I am open to a sharper one as well
Fixes https://github.com/twentyhq/twenty/issues/15838
---------
Co-authored-by: Lucas Bordeau <bordeau.lucas@gmail.com>
Co-authored-by: Charles Bochet <charles@twenty.com>
## Overview
This PR refactors the `CalendarEventDetails` component to dynamically
display both standard and custom fields added via the metadata API,
instead of using a hardcoded field list.
## Changes
- Replaced hardcoded `fieldsToDisplay` array with dynamic field fetching
using `useFieldListFieldMetadataItems` hook
- Split fields into `standardFields` (maintaining original order) and
`customFields`
- Introduced `renderField` helper function to eliminate code duplication
- Custom fields now automatically appear at the bottom of the detail
panel after standard fields
- Maintained exact field order and all existing functionality including
participant response status display
## Technical Details
- Uses existing `useFieldListFieldMetadataItems` pattern already
established in the codebase
- Standard field order explicitly defined: startsAt, endsAt,
conferenceLink, location, description
- Participant response status (Yes/Maybe/No) correctly positioned
between first 2 and last 3 standard fields
- All fields respect permissions and visibility settings from metadata
## Testing
- ✅ Verified all standard fields display in correct order
- ✅ Added custom field `mycustomfieldtest` via metadata API - displays
correctly at bottom
- ✅ Participant responses (Yes/Maybe/No) render correctly with avatars
- ✅ Event title, creation date, and event chip display properly
- ✅ Canceled event styling (strikethrough) works
- ✅ No console errors or regressions detected
- ✅ Read-only behavior maintained (calendar events sync from external
sources)
## Screenshots
<img width="1401" height="746" alt="CleanShot 2025-11-17 at 11 23 57"
src="https://github.com/user-attachments/assets/3d967ec5-6d31-4fc3-b971-c73ea521c87d"
/>
## Related
This enables users to extend calendar events with custom metadata fields
that will automatically display in the UI without code changes.
---------
Co-authored-by: Charles Bochet <charles@twenty.com>
There was an extra definition of @nx/js inside twenty-server, which was
not recognized during upgrade by the CLI. This caused two versions of
@nx/js in the repo - 22.0.3 from root and 21.3.11 from the twenty-server
package.
Removed the one inside twenty-server to maintain a single source of
truth.
Closes https://github.com/twentyhq/core-team-issues/issues/1600.
Two remarks
- This `limit` variable does not reduce postgre's work at it still needs
to scan the whole table. It did not seem possible to me to optimize this
as we cannot foresee which dimensions will be used by the user, and an
optimization could only result from an index on the dimension(s) (e.g.:
group companies by addressCity limit 50 can be optimized if we have an
index on companies.addressCity + we had a default orderBy on
adressCity). But this will still optimize the FE which at the moment
receives all groups and truncates the result.
- I have not done the work on the FE as the addition of limit is a
breaking change, and will break until the workspaces' schema is rebuilt,
so we need to flush the cache. I think this could be acceptable as the
feature is in the lab but I preferred not doing it yet as it would have
no impact since in the BE I added a default limit to 50 groups, and I
expect more FE work will be done to allow the user to choose their own
limit
## Background
Team Comfortably Summed had submitted Activity Summary for Twenty's
Hacktoberfest. This is a follow-up PR post-Hacktoberfest.
## Changes
### Purpose
>_What is the objective?_
To improve the code based on human and bot comments from the initial
Hacktoberfest PR, and to improve the robustness of task completion
calculation.
>_Are we solving a problem or making necessary changes to support an
existing and / or a new feature?_
Making changes to improve existing features.
### Summary
> _Are there files we can ignore?_
None.
> _Please provide a high-level summary of the changes._
- Corrects `README.md` by removing irrelevant commands and unnecessary
configuration notes
- Updates `people-creation-summariser.ts`
- Replaces requesting of company for each person by including `depth=1`
as query parameter in GET /people request as suggested by Martin Muller
– link to comment:
[link](https://github.com/twentyhq/twenty/pull/15510#discussion_r2486019035)
- Updates `senders.ts`
- Renames `formattedMesage` to `formattedMessage`
- Updates `task-creation-summariser.ts`
- Improves calculation of completed task percentage by relying only on
list of completed tasks and total list of tasks
- The initial implementation includes relying on pending tasks and
pending overdue tasks which can result in undesired calculation outcome
Some Glob CLI related alerts were generated last night. I believe
they're safe to dismiss since I do not expect us to use the Glob CLI in
production environment, and those alerts do not impact the API, but
still updating the dependency version just in case.
Not sure if this would resolve all/any of the alerts since glob is a
dependency for many other dependencies, so a good number of dependency
variants are pulled in.
The alert that confirms it's just a CLI related vulnerability:
[Dependabot Alert
307](https://github.com/twentyhq/twenty/security/dependabot/307)
Resolves [Dependabot Alert
309](https://github.com/twentyhq/twenty/security/dependabot/309) and
maybe also a few others.
Bumped up the version for js-yaml to 4.1.1 and 3.14.2 across transitive
dependencies using `yarn up js-yaml --recursive`.
Context -
- refactoring v1 and v2 seeds to test v2 dashboard flag both on and off
Right now, the db reset command fails if the feature flag is off
- whenever there is a groupBy field -- we should add a default groupMode
- we already do that on the front -- but implementing the same on server
so that api users get the same response
This is also the reason why the second seed on dashboards lags a lot --
because on that particular dashboard's widget -- we set groupBy but no
groupMode (in seeding util) -- and the effect of limiting the bars to
fifty runs depending on the groupMode
