feat: Add Agent Evaluation System and Refactor AI Modules (#16111)
## 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 -->
This commit is contained in:
+2
-2
@@ -2,11 +2,11 @@ import { Test, type TestingModule } from '@nestjs/testing';
|
||||
|
||||
import { SupportDriver } from 'src/engine/core-modules/twenty-config/interfaces/support.interface';
|
||||
|
||||
import { ClientConfigService } from 'src/engine/core-modules/client-config/services/client-config.service';
|
||||
import {
|
||||
type ModelId,
|
||||
ModelProvider,
|
||||
} from 'src/engine/metadata-modules/ai-models/constants/ai-models.const';
|
||||
import { ClientConfigService } from 'src/engine/core-modules/client-config/services/client-config.service';
|
||||
} from 'src/engine/metadata-modules/ai/ai-models/constants/ai-models.const';
|
||||
|
||||
import { ClientConfigController } from './client-config.controller';
|
||||
|
||||
|
||||
+4
-4
@@ -2,14 +2,14 @@ import { Field, ObjectType, registerEnumType } from '@nestjs/graphql';
|
||||
|
||||
import { SupportDriver } from 'src/engine/core-modules/twenty-config/interfaces/support.interface';
|
||||
|
||||
import {
|
||||
ModelId,
|
||||
ModelProvider,
|
||||
} from 'src/engine/metadata-modules/ai-models/constants/ai-models.const';
|
||||
import { BillingTrialPeriodDTO } from 'src/engine/core-modules/billing/dtos/billing-trial-period.dto';
|
||||
import { CaptchaDriverType } from 'src/engine/core-modules/captcha/interfaces';
|
||||
import { FeatureFlagKey } from 'src/engine/core-modules/feature-flag/enums/feature-flag-key.enum';
|
||||
import { AuthProvidersDTO } from 'src/engine/core-modules/workspace/dtos/public-workspace-data-output';
|
||||
import {
|
||||
ModelId,
|
||||
ModelProvider,
|
||||
} from 'src/engine/metadata-modules/ai/ai-models/constants/ai-models.const';
|
||||
|
||||
registerEnumType(FeatureFlagKey, {
|
||||
name: 'FeatureFlagKey',
|
||||
|
||||
+1
-1
@@ -3,12 +3,12 @@ import { Test, type TestingModule } from '@nestjs/testing';
|
||||
import { NodeEnvironment } from 'src/engine/core-modules/twenty-config/interfaces/node-environment.interface';
|
||||
import { SupportDriver } from 'src/engine/core-modules/twenty-config/interfaces/support.interface';
|
||||
|
||||
import { AiModelRegistryService } from 'src/engine/metadata-modules/ai-models/services/ai-model-registry.service';
|
||||
import { CaptchaDriverType } from 'src/engine/core-modules/captcha/interfaces';
|
||||
import { ClientConfigService } from 'src/engine/core-modules/client-config/services/client-config.service';
|
||||
import { DomainServerConfigService } from 'src/engine/core-modules/domain/domain-server-config/services/domain-server-config.service';
|
||||
import { PUBLIC_FEATURE_FLAGS } from 'src/engine/core-modules/feature-flag/constants/public-feature-flag.const';
|
||||
import { TwentyConfigService } from 'src/engine/core-modules/twenty-config/twenty-config.service';
|
||||
import { AiModelRegistryService } from 'src/engine/metadata-modules/ai/ai-models/services/ai-model-registry.service';
|
||||
|
||||
describe('ClientConfigService', () => {
|
||||
let service: ClientConfigService;
|
||||
|
||||
+3
-3
@@ -12,14 +12,14 @@ import {
|
||||
import { DomainServerConfigService } from 'src/engine/core-modules/domain/domain-server-config/services/domain-server-config.service';
|
||||
import { PUBLIC_FEATURE_FLAGS } from 'src/engine/core-modules/feature-flag/constants/public-feature-flag.const';
|
||||
import { TwentyConfigService } from 'src/engine/core-modules/twenty-config/twenty-config.service';
|
||||
import { convertCentsToBillingCredits } from 'src/engine/metadata-modules/ai-billing/utils/convert-cents-to-billing-credits.util';
|
||||
import { convertCentsToBillingCredits } from 'src/engine/metadata-modules/ai/ai-billing/utils/convert-cents-to-billing-credits.util';
|
||||
import {
|
||||
AI_MODELS,
|
||||
DEFAULT_FAST_MODEL,
|
||||
DEFAULT_SMART_MODEL,
|
||||
ModelProvider,
|
||||
} from 'src/engine/metadata-modules/ai-models/constants/ai-models.const';
|
||||
import { AiModelRegistryService } from 'src/engine/metadata-modules/ai-models/services/ai-model-registry.service';
|
||||
} from 'src/engine/metadata-modules/ai/ai-models/constants/ai-models.const';
|
||||
import { AiModelRegistryService } from 'src/engine/metadata-modules/ai/ai-models/services/ai-model-registry.service';
|
||||
|
||||
@Injectable()
|
||||
export class ClientConfigService {
|
||||
|
||||
Reference in New Issue
Block a user