feat: add configurable response format for AI agents (text/JSON) (#15953)

## 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

packages/twenty-server/src/modules/workflow/workflow-executor/workflow-actions/ai-agent/ai-agent.workflow-action.ts

@@ -80,7 +80,6 @@ export class AiAgentWorkflowAction implements WorkflowAction {
       const { result, usage } = await this.aiAgentExecutionService.executeAgent(
         {
           agent,
-          schema: step.settings.outputSchema,
           userPrompt: resolveInput(prompt, context) as string,
           actorContext: executionContext.isActingOnBehalfOfUser
             ? executionContext.initiator

packages/twenty-server/src/modules/workflow/workflow-executor/workflow-actions/ai-agent/services/ai-agent-executor.service.ts

@@ -1,9 +1,15 @@
 import { Injectable, Logger } from '@nestjs/common';
 import { InjectRepository } from '@nestjs/typeorm';
 
-import { generateObject, generateText, stepCountIs, ToolSet } from 'ai';
-import { Repository } from 'typeorm';
+import {
+  generateObject,
+  generateText,
+  jsonSchema,
+  stepCountIs,
+  ToolSet,
+} from 'ai';
 import { type ActorMetadata } from 'twenty-shared/types';
+import { Repository } from 'typeorm';
 
 import { AI_TELEMETRY_CONFIG } from 'src/engine/core-modules/ai/constants/ai-telemetry.const';
 import { AiModelRegistryService } from 'src/engine/core-modules/ai/services/ai-model-registry.service';
@@ -17,10 +23,8 @@ import {
 } from 'src/engine/metadata-modules/agent/agent.exception';
 import { AGENT_CONFIG } from 'src/engine/metadata-modules/agent/constants/agent-config.const';
 import { AGENT_SYSTEM_PROMPTS } from 'src/engine/metadata-modules/agent/constants/agent-system-prompts.const';
-import { convertOutputSchemaToZod } from 'src/engine/metadata-modules/agent/utils/convert-output-schema-to-zod';
 import { RoleTargetsEntity } from 'src/engine/metadata-modules/role/role-targets.entity';
 import { type RolePermissionConfig } from 'src/engine/twenty-orm/types/role-permission-config';
-import { OutputSchema } from 'src/modules/workflow/workflow-builder/workflow-schema/types/output-schema.type';
 
 @Injectable()
 export class AiAgentExecutorService {
@@ -86,13 +90,11 @@ export class AiAgentExecutorService {
 
   async executeAgent({
     agent,
-    schema,
     userPrompt,
     actorContext,
     rolePermissionConfig,
   }: {
     agent: AgentEntity | null;
-    schema: OutputSchema;
     userPrompt: string;
     actorContext?: ActorMetadata;
     rolePermissionConfig?: RolePermissionConfig;
@@ -121,12 +123,18 @@ export class AiAgentExecutorService {
         experimental_telemetry: AI_TELEMETRY_CONFIG,
       });
 
-      if (Object.keys(schema).length === 0) {
+      const agentSchema =
+        agent?.responseFormat?.type === 'json'
+          ? agent.responseFormat.schema
+          : undefined;
+
+      if (!agentSchema) {
         return {
           result: { response: textResponse.text },
           usage: textResponse.usage,
         };
       }
+
       const output = await generateObject({
         system: AGENT_SYSTEM_PROMPTS.OUTPUT_GENERATOR,
         model: registeredModel.model,
@@ -135,12 +143,12 @@ export class AiAgentExecutorService {
                  Execution Results: ${textResponse.text}
 
                  Please generate the structured output based on the execution results and context above.`,
-        schema: convertOutputSchemaToZod(schema),
+        schema: jsonSchema(agentSchema),
         experimental_telemetry: AI_TELEMETRY_CONFIG,
       });
 
       return {
-        result: output.object,
+        result: output.object as object,
         usage: {
           inputTokens:
             (textResponse.usage?.inputTokens ?? 0) +