⚠️ **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>
## 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 introduces a Skills system for AI agents, inspired by the [Agent
Skills specification](https://agentskills.io/specification).
## Changes
### Backend
- **SkillEntity**: New database entity with migration for storing skills
- **V2 Sync Mechanism**: Implemented FlatSkill, builders, validators,
and action handlers following the v2 flat entity pattern
- **Standard Skills**: Pre-defined skills (workflow-building,
data-manipulation, dashboard-building, metadata-building, research,
code-interpreter, xlsx, pdf, docx, pptx)
- **GraphQL API**: CRUD operations for skills with proper guards and
permissions
- **Workspace Cache**: Integrated skills into the workspace cache system
### Frontend
- **Skills Table**: Searchable table in AI settings showing all skills
- **Skill Form**: Create/edit page with Label (primary), Description,
and Content (markdown editor)
- **API Name**: Following existing patterns, name is derived from label
with advanced settings toggle for custom API names
- **Standard vs Custom**: Standard skills are read-only, custom skills
can be edited/deleted
## Key Design Decisions
- Skills are stored in the database (Salesforce-like approach) rather
than files
- Name is derived from Label by default (isLabelSyncedWithName pattern)
- Skills reference functions/files via @ mentions in markdown content
rather than explicit relations
- Standard skills are synced from code, custom skills are created via UI
## Screenshots
Skills table and form UI follow existing settings patterns.
## Testing
- [x] Lint passes
- [x] Typecheck passes
- [ ] CI tests
## 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
- Add a context usage indicator to the AI chat interface inspired by
Vercel's AI SDK Context component
- Display token consumption, context window utilization percentage, and
estimated cost in credits
- Show a circular progress ring with percentage, revealing detailed
breakdown on hover
## Changes
### Backend
- Stream usage metadata (tokens, model config) via `messageMetadata`
callback in `agent-chat-streaming.service.ts`
- Return model config from `chat-execution.service.ts`
- Add usage and model types to `ExtendedUIMessage` metadata
### Frontend
- New `ContextUsageProgressRing` component - circular SVG progress
indicator
- New `AIChatContextUsageButton` component with hover card showing:
- Progress bar with used/total tokens
- Input/output token counts with credit costs
- Total credits consumed
- Track cumulative usage in Recoil state (`agentChatUsageState`)
- Reset usage when creating new chat thread
- Integrate button into `AIChatTab`
## Test plan
- [ ] Open AI chat and send a message
- [ ] Verify the context usage button appears with percentage
- [ ] Hover over the button to see detailed breakdown
- [ ] Verify credits are calculated correctly
- [ ] Create a new chat thread and verify usage resets to 0
## 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 -->
## 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
Adds intelligent routing system that automatically selects the best
agent for user queries based on conversation context.
### Changes:
- Added `routerModel` column to workspace table for configurable router
LLM selection
- Implemented `RouterService` with conversation history analysis and
agent matching logic
- Created router settings UI in AI Settings page with model dropdown
- Removed agent-specific thread associations - threads are now
agent-agnostic
- Added real-time routing status notification in chat UI with shimmer
effect
- Removed automatic default assistant agent creation
- Renamed GraphQL operations from agent-specific to generic (e.g.,
`agentChatThreads` → `chatThreads`)
---------
Co-authored-by: Félix Malfait <felix.malfait@gmail.com>
Co-authored-by: Félix Malfait <felix@twenty.com>
Closes [#1583](https://github.com/twentyhq/core-team-issues/issues/1583)
- Removed `messageId` column from `File` table and its references in
code (unrelated to this PR)
- Updated AI chat to use React Context API with persistent provider in
`CommandMenuContainer`
- Converted all AI chat component states to regular Recoil atoms (no
instance context needed)
---------
Co-authored-by: Félix Malfait <felix@twenty.com>
## TODO
- [ ] add dropdown to use records from outside the context
- [x] add loader for files chip
- [x] add roleId where it's necessary
- [x] Split AvatarChip in two components. One with the icon that will
call the second with leftComponent.
- [ ] Fix tests
- [x] Fix UI regression on Search
Félix Malfait