## Summary
This PR introduces a comprehensive agent evaluation system and refactors
the AI module structure for better organization.
## Key Changes
### 🎯 Agent Evaluation System
- Added **Agent Turn Evaluation** entities, DTOs, and database schema
- New GraphQL mutations: `evaluateAgentTurn` and `runEvaluationInput`
- Added `evaluationInputs` field to Agent entity for storing test inputs
- New `AgentTurnGraderService` for automatic turn evaluation
- Added evaluation UI with new **Evals** and **Logs** tabs in agent
detail pages
### 🏗️ Entity & Module Refactoring
- Renamed `AgentChatMessage` → `AgentMessage` for clarity
- Consolidated chat entities: `AgentMessage`, `AgentTurn`, and
`AgentChatThread`
- Reorganized AI modules under `ai/` subdirectory structure
- Updated imports across codebase to reflect new module paths
### 🤖 New Agents & Roles
- Added **Dashboard Builder Agent** for dashboard creation and
management
- Added **Dashboard Manager Role** with appropriate permissions
- Updated role permissions to be more granular (users vs agents vs API
keys)
### 🔐 Permission System Updates
- Added `HTTP_REQUEST_TOOL` permission flag
- Updated Workflow Manager role permissions (restricted tool access)
- Enhanced permission flag types to differentiate between user/agent/API
key contexts
- Added `isRelevantForAgents`, `isRelevantForApiKeys`,
`isRelevantForUsers` to permission flags
### 📨 Message Role Enhancement
- Added `system` role to `AgentMessageRole` enum (alongside
user/assistant)
- Updated message handling to support system prompts
### 🎨 UI/UX Improvements
- New tabs in agent detail: **Evals** and **Logs**
- Added turn detail page: `/ai/agents/:agentId/turns/:turnId`
- Fixed text overflow in `SettingsListItemCardContent`
- Updated role applicability labels ("Assignable to Workspace Members")
### 🛠️ Technical Improvements
- Fixed Zod schema validation for UUID and Date fields (use string
validators)
- Updated `ToolRegistryService` to properly register HTTP tool with
permission flag
- Enhanced error handling in agent execution services
- Updated database migrations for new entity schema
## Database Migrations
- `1764210000000-add-system-role-to-agent-message.ts`
- `1764220000000-add-evaluation-inputs-to-agent.ts`
- `1764200000000-add-agent-turn-evaluation.ts`
- `1764100000000-refactor-agent-chat-entities.ts`
## Testing
- [ ] Agent evaluation flow tested
- [ ] Dashboard Builder agent tested
- [ ] Permission system validated
- [ ] UI tabs and navigation tested
- [ ] Database migrations run successfully
## Breaking Changes
⚠️ **Entity Rename**: `AgentChatMessage` renamed to `AgentMessage` -
GraphQL queries need updating
## Related Issues
<!-- Link any related issues here -->
## Screenshots
<!-- Add screenshots if applicable -->
## Description
Fixed the height of the options menu button in the side panel footer to
be 24px instead of 32px, matching the height of other buttons in the
footer.
## Changes
- Added `size="small"` prop to the `Button` component in
`OptionsDropdownMenu.tsx`
- This ensures consistent button sizing across the side panel footer
## Before
The options menu button was 32px high (medium size), making it larger
than other footer buttons.
<img width="543" height="421" alt="image"
src="https://github.com/user-attachments/assets/3c4fdfd0-73d1-4884-a639-3382090dfe15"
/>
## After
The options menu button is now 24px high (small size), consistent with
other side panel footer buttons.
<img width="1000" height="824" alt="CleanShot 2025-11-26 at 18 50 43@2x"
src="https://github.com/user-attachments/assets/798e7975-a7a8-4c00-b2e7-c0d1261249f8"
/>
Closes https://github.com/twentyhq/twenty/issues/15692, fixes
https://github.com/twentyhq/twenty/issues/14678
The issue was:
- When a user is signing up, they are asked for their first name and
last name with which we fulfill their workspaceMember entity for the
workspace they are signing up to (which is the one they are creating if
they are not joining an existing workspace). user.firstName and
user.lastName remain empty
- When we create a record, we are using user.firstName and user.lastName
to fulfill the text field "createdByName", which intends to save the
name of the creator at the moment of the creation. This field is then
use 1) when filtering on createdBy (as a trick to be able to filter by
this, since we don't have filters on nested fields, ie we dont have
filters on person.createdByWorkspaceMember) 2) to display the user
creator when a user has left a workspace - otherwise we rely on the
dynamic createdByWorkspaceMember.firstName and lastName
- So filtering on createdBy was not working as createdByName is empty.
We did not see that in dev mode because we have seeded users with names
The fix
- When we create a record, we use workspaceMember.firstName and
workspaceMember.lastName as we should.
- When an existing user joins a workspace, they are asked to give their
name again so that we set their workspaceMember name
- This will not fix the history of the records (they will still have
createdByName empty so the filter will not work properly), but a command
to fix it would be very long as it would iterate over all the records of
each active workspace
The long-term view is to get rid of user and to store the name in
userWorkspace
## Description
- Connect Pie Chart to the backend
- Update from the old design to the new design
- Switch seamlessly from/to other types of chart from the Pie Chart by
converting the configuration
Note: There are a couple things to implement before the pie chart is
ready to go live:
- Add a new setting on Bar, Line and Pie chart to hide and display
legends (toggle)
- Add data labels next to each slice
## Video QA
https://github.com/user-attachments/assets/b1561e32-0434-43ad-8855-d617b209ce27
## Overview
This PR replaces the dynamic agent handoff system with a more
predictable planning-based router that decides upfront how to handle
multi-agent coordination.
## Major Changes
### 🔄 Architecture Shift: Handoffs → Planning
**Removed:**
- `AgentHandoffEntity` and handoff tracking system
- `AgentHandoffService` and `AgentHandoffExecutorService`
- Dynamic agent-to-agent transfers during execution
- Handoff tool generation and description templates
**Added:**
- `AiRouterService` with two strategies: `simple` (single agent) and
`planned` (multi-agent)
- `AgentPlanExecutorService` for executing multi-step plans
- Plan validation (cycle detection, dependency resolution)
- `UnifiedRouterResult` type with discriminated union
### 🤖 New Standard Agents
Added two new specialized agents:
- **Researcher Agent**: Web search, fact-finding, competitive
intelligence
- **Code Agent**: TypeScript function generation for serverless
workflows
### 🏗️ Router Refactoring (Latest)
Split router responsibilities into focused services:
- `AiRouterStrategyDeciderService`: Decides simple vs planned strategy
- `AiRouterPlanGeneratorService`: Generates and validates execution
plans
- `AiRouterService`: Coordinates between services (reduced from 426→275
lines)
### ⚙️ Configuration Improvements
- Added `outputStrategy` to agent definitions (`direct` vs `synthesize`)
- Removed hardcoded special cases for workflow-builder
- Added `plannerModel` field to workspace entity
- Increased `MAX_STEPS` from 10 to 25 for complex workflows
### 📝 Agent Prompt Refinements
Significantly simplified prompts for better clarity:
- Workflow Builder: 51→36 lines
- Helper: 49→28 lines
- Data Manipulator: Enhanced with sorting guidance
### 🔍 Enhanced Debugging
- Plan reasoning and step count in data message parts
- Router debug info with token usage tracking
- Better logging throughout execution pipeline
## Benefits
1. **Simpler Mental Model**: Router decides upfront vs dynamic transfers
2. **Better Predictability**: Users see the plan before execution
3. **Cleaner Architecture**: SRP with focused services
4. **Configuration Over Code**: Agent behavior via config, not hardcoded
logic
5. **Plan Validation**: Catches invalid dependencies and cycles
## Migration Notes
- Database migration removes `agentHandoff` table
- Adds `plannerModel` column to workspace table
- No API breaking changes (agent endpoints unchanged)
## Testing
- Integration tests updated to remove handoff dependencies
- Agent tool test utilities simplified
- Plan validation covered by new logic
## Next Steps (Future PRs)
- Parallel execution of independent plan steps
- Dynamic re-planning based on results
- Plan caching for common routing patterns
- Error recovery strategies in plan executor
Closes#15957
The core problem: `handleChange` calls `setDraftValue`, but when blur
fires, `handleClickOutside` runs in the same event turn and uses
the `draftValue` captured in its closure from the last render. React
hasn’t re-rendered yet, so that captured `draftValue` is stale. Recoil
atom writes are synchronous, but the render that would update the
closure happens on the next turn.
I considered deferring `handleClickOutside` to the next tick
(setTimeout/Promise), but that’s a timing hack: it makes focus/blur
ordering unpredictable (inline cells, tables, other listeners), risks
double triggers, and can fire after unmount. Another option was to
duplicate the `handleChange` logic inside `handleClickOutside`
(screenshot), but that defeats having draft state in one place.
<p align="center">
<img width="496" height="332" alt="const nextSecondaryLinks =
updatedLinks slice (1);"
src="https://github.com/user-attachments/assets/638e2bcf-871b-4b53-9124-c8489c5db530"
/>
</p>
The clean solution is to read the current draft from a Recoil snapshot
at call time inside `handleClickOutside`. Snapshot reads pull the latest
atom value (including synchronous `setDraftValue` that just ran) even
before a re-render occurs, so they’re not subject to the stale closure.
That way, blur uses the up-to-date draft without timing hacks or
duplicated logic.
MultiItemFieldInput is used in four places. Each of them contains the
updated code.
Block users from creating NUMERIC, POSITION, and TS_VECTOR fields via
the API as these are system-only types. Users should use NUMBER instead
of NUMERIC.
/closes #16023
closes https://github.com/twentyhq/core-team-issues/issues/1629
To do before requesting review :
- filter update
Migration to come in an other PR
Strat :
1/ Null transformation
- [x] Transform NULL equivalent value to NULL in field validation in
common api - pre-query - with feature flag
- [ ] Same logic in ORM (Not done, complex to handle feature flag here)
- [x] Transform NULL value to equivalent in data formatting in ORM -
post-query
2/ Migration (in other PR) for fieldMetadata not nullable with default
defaultValue (empty string, ...)
- [ ] Remove NOT NULL db constraint
- [ ] Update record value to NULL
- [ ] Update field metadata : isNullable:true
- [ ] Update uniqueIndex whereClause (also for standard uniqueIndex)
- [ ] Activate feature flag
3/ Update metadata creation
- [x] No more default default value
- [x] Update standard field nullability
- [x] Remove index default whereClause for standard field
4/ Update filter
- [x] When filtering on NULL or empty string, be sure all records are
returned (the one with NULL + the one with "")
5/ Test
- [ ] Strat. to do
# Introduction
Two things:
- Enforcing non nullable workspace custom application Id for any
workspace
- Fixing front non editable data models following
https://github.com/twentyhq/twenty/pull/15911 that associate any custom
entities to an applicationId. The front was putting everything as
readonly when under an app ( we will have to handle the twenty standard
application in the future too )
## Fallback
### Migration
The non nullable migration will fail when released, that's why it's
being swallowed and re-run in an upgrade command post workspace custom
application creation for those that miss one. Allowing the migration to
pass in the end
The typeorm migration still need to exists for any new workspaces
### GetCurrentUser
In order to dynamically display isReadOnly in data model settings we're
fetching the workspaceCustomApplicationId through the `getCurrentUser`
If not fallback this endpoint would throw until we're handling existing
workspaces that do not have a custom workspace application
The fallback should be removed post release
## Widget duplication
- Created a shared component for the option menu shared by the record
page, the dashboards and the workflows
- Fix arrow selection in the option menu in workflows, which wasn't
working
- Scroll to the new widget after creation and open the new widget
settings
https://github.com/user-attachments/assets/47b8dade-44bd-4ba2-a81c-01b09e8718d3
[Figma
Design](https://www.figma.com/design/xt8O9mFeLl46C5InWwoMrN/Twenty?node-id=81380-344641&t=FpjWNOK2gZuDQQfr-0)
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Adds a side panel layout for the Command Menu, routes modals into a
local container, updates the top bar and context chips, and standardizes
small button sizes.
>
> - **Command Menu**:
> - **Side Panel Layout**: Introduces `CommandMenuSidePanelLayout` with
animated width, hosts `CommandMenuRouter`, and provides a modal
container via `ModalContainerContext`.
> - **Top Bar**: Redesign (`CommandMenuTopBar`) with back icon, optional
AI sparkles action, compact height
(`COMMAND_MENU_SEARCH_BAR_HEIGHT=40`), and updated placeholder.
> - **Context Chips**: Adds `CommandMenuLastContextChip` and
`CommandMenuRecordInfo`; extends `CommandMenuContextChip` with `page`
prop; updates `CommandMenuContextChipGroups` to render last chip as
record info when applicable.
> - **Container Simplification**: `CommandMenuContainer` simplified to
just provide contexts and `AgentChatProvider`.
> - **Modal System**:
> - Adds `ModalContainerContext` and updates `Modal` to portal into
provided container; `Modal.Backdrop` supports `isInContainer`.
> - Updates usages (e.g., `UserOrMetadataLoader`, `ActionModal`) to
align with new modal behavior.
> - **Page Integration**:
> - Replaces `PageBody` with `CommandMenuSidePanelLayout` in
`RecordShowPage` and `RecordIndexContainerGater`.
> - Removes global `CommandMenuRouter` from `DefaultLayout` (keeps
keyboard shortcuts).
> - **UI/Styling**:
> - Standardizes several buttons to `size="small"` (e.g., command
actions, open record, options, reply, workflow footer).
> - Adjusts `ShowPageSubContainer` styling when rendered inside command
menu.
> - Storybook tests updated for new placeholder text.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
81fcaa145618a2fa1c3e11e2dc88fe832c51374c. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Félix Malfait <felix.malfait@gmail.com>
Co-authored-by: Lucas Bordeau <bordeau.lucas@gmail.com>
Co-authored-by: Devessier <baptiste@devessier.fr>
Co-authored-by: Aman Raj <92664006+araj00@users.noreply.github.com>
Co-authored-by: Etienne <45695613+etiennejouan@users.noreply.github.com>
Co-authored-by: Paul Rastoin <45004772+prastoin@users.noreply.github.com>
Resolves [Dependabot Alert
74](https://github.com/twentyhq/twenty/security/dependabot/74).
Upgraded `graphql-upload` from `13.0.0` to `16.0.2`. Type exports
changed. API remains the same.
Tested the following upload flows:
- profile picture
- workspace logo
- rich text editor (image, video, file)
- record profile picture
- file associated to record.
They all work as intended, nothing breaks.
Closes https://github.com/twentyhq/core-team-issues/issues/1891
Create empty buckets according to the date granularity
Video QA:
https://github.com/user-attachments/assets/86c0f817-35b3-4bab-b093-d11491684b82
Note: We would also need to create empty buckets for cyclic
granularities (DAY_OF_THE_WEEK, MONTH_OF_THE_YEAR, QUARTER_OF_THE_YEAR).
TODO:
- Always order the cyclic granularities Monday -> Sunday (take
firstDayOfTheWeek into account), January -> December, Q1 -> Q4. For now
they are returned by the backend in alphabetical order, which doesn't
make much sense
- Remove the translation into the user's locale of these granularities
from the backend because otherwise we can't reconstruct the missing days
or month in the frontend since they will be translated
---------
Co-authored-by: Lucas Bordeau <bordeau.lucas@gmail.com>
## 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
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>
- 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
## 🐛 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>
nitin