docs(features): update AI Services plan with Mistral API Connector as Phase 0

- Add Phase 0: Mistral API Connector (2-3 hours) as first step
- Update status to In Progress
- Add MistralConnector to architecture diagram and components
- Add connector-specific tasks to implementation plan
- Add Mistral connector configuration examples
- Add progress history entry
- Update estimate from 10-16h to 12-18h

Generated by Mistral Vibe.
Co-Authored-By: Mistral Vibe <vibe@mistral.ai>

docs/features/ai-services.md

@@ -1,9 +1,9 @@
 # Feature: AI Services Integration
 
-> **Status**: ⏳ Planned  
+> **Status**: 🚀 In Progress  
 > **Priority**: High  
 > **Complexity**: High  
-> **Estimate**: 10-16 hours  
+> **Estimate**: 12-18 hours  
 > **Assignee**: -  
 > **Created**: May 31, 2025  
 > **Target Completion**: -  
@@ -68,7 +68,8 @@ As a learner, I want AI-powered features like generated stories, speech recognit
 │           │                     │                    │         │
 │           ▼                     ▼                    ▼         │
 │  ┌─────────────────────────────────────────────────────────┐  │
-│  │              Application Services                         │  │
+│  │              Connectors & Services                        │  │
+│  │  - MistralConnector (HTTP Client)                        │  │
 │  │  - StoryGenerationService                                │  │
 │  │  - WritingFeedbackService                                 │  │
 │  │  - VoskService (Speech Recognition)                      │  │
@@ -78,8 +79,10 @@ As a learner, I want AI-powered features like generated stories, speech recognit
 ```
 
 ### Components Involved
+- **Backend Connectors**:
+  - `IMistralConnector` / `MistralConnector` - HTTP client for Mistral API
 - **Backend Services**:
-  - `IMistralService` / `MistralService` - Text generation
+  - `IMistralService` / `MistralService` - Text generation (uses MistralConnector)
   - `IVoskService` / `VoskService` - Speech recognition
   - `ITtsService` / `TtsService` - Text-to-speech
 - **Configuration**: appsettings.json with AI settings
@@ -123,6 +126,25 @@ As a learner, I want AI-powered features like generated stories, speech recognit
 
 ## 🚀 Implementation Plan
 
+### Phase 0: Mistral API Connector (2-3 hours)
+**Objective**: Create a reusable, testable connector for Mistral API that can be used by all Mistral-based services.
+
+- [ ] Create `Domain/Interfaces/IMistralConnector.cs` - Interface for Mistral API connector
+- [ ] Create `Infrastructure/Services/MistralConnector.cs` - HTTP client implementation
+- [ ] Implement request/response models (`MistralRequest.cs`, `MistralResponse.cs`)
+- [ ] Add HTTP client configuration with base URL and timeout
+- [ ] Implement retry logic with exponential backoff
+- [ ] Add rate limiting at the connector level
+- [ ] Add response caching mechanism
+- [ ] Implement circuit breaker pattern for failure handling
+- [ ] Create unit tests for MistralConnector
+
+**Deliverables:**
+- Standalone Mistral API connector component
+- Configurable via appsettings.json
+- Resilient to API failures
+- Testable with mocked HTTP client
+
 ### Phase 1: Configuration & Interfaces (2 hours)
 - [ ] Add AI configuration section to appsettings.json
 - [ ] Create configuration classes (MistralConfig, VoskConfig, CoquiConfig)
@@ -178,6 +200,19 @@ As a learner, I want AI-powered features like generated stories, speech recognit
 
 ## ✅ Tasks
 
+### Backend - Mistral API Connector
+- [ ] Create `Domain/Interfaces/IMistralConnector.cs`
+- [ ] Create `Infrastructure/Services/MistralConnector.cs`
+- [ ] Create `Application/Models/MistralRequest.cs`
+- [ ] Create `Application/Models/MistralResponse.cs`
+- [ ] Create `Application/Models/MistralErrorResponse.cs`
+- [ ] Add HTTP client configuration in Program.cs
+- [ ] Implement retry logic with exponential backoff
+- [ ] Add rate limiting to connector
+- [ ] Add response caching mechanism
+- [ ] Implement circuit breaker pattern
+- [ ] Create unit tests for MistralConnector
+
 ### Backend - Configuration
 - [ ] Add Mistral settings to appsettings.json
 - [ ] Add Vosk settings to appsettings.json
@@ -189,15 +224,12 @@ As a learner, I want AI-powered features like generated stories, speech recognit
 - [ ] Add health checks for AI services
 
 ### Backend - Mistral Service
-- [ ] Create Domain/Interfaces/IMistralService.cs
+- [ ] Create `Domain/Interfaces/IMistralService.cs`
-- [ ] Create Infrastructure/Services/MistralService.cs
+- [ ] Create `Application/Services/MistralService.cs` (uses MistralConnector)
-- [ ] Implement Mistral API client
+- [ ] Implement prompt templates for different use cases
-- [ ] Create Models/MistralRequest.cs
+- [ ] Add story generation functionality
-- [ ] Create Models/MistralResponse.cs
+- [ ] Add writing feedback functionality
-- [ ] Add retry logic
+- [ ] Write unit tests (with mocked MistralConnector)
-- [ ] Add rate limiting
-- [ ] Add response caching
-- [ ] Write unit tests
 
 ### Backend - Vosk Service
 - [ ] Create Domain/Interfaces/IVoskService.cs
@@ -785,9 +817,20 @@ public async Task<IActionResult> RecognizeSpeech([FromBody] AudioRequest request
 | May 31, 2025 | Use Coqui TTS | Open-source, good quality, supports German |
 | May 31, 2025 | Self-host AI services | More control, no external API dependencies (except Mistral) |
 | May 31, 2025 | Use Python CLI wrappers | Easier integration with .NET, well-supported libraries |
+| June 9, 2025 | Add Mistral API Connector | Create reusable connector before service implementation |
 
 ### Technical Notes
 
+#### Mistral API Connector
+The Mistral Connector is a standalone component that handles all HTTP communication with the Mistral API. It provides:
+- HTTP client configuration with base URL and timeout
+- Retry logic with exponential backoff
+- Rate limiting at the connector level
+- Response caching mechanism
+- Circuit breaker pattern for failure handling
+
+This follows Clean Architecture: interface (`IMistralConnector`) in Domain layer, implementation (`MistralConnector`) in Infrastructure layer.
+
 #### Vosk Configuration
 ```json
 {
@@ -819,7 +862,21 @@ public async Task<IActionResult> RecognizeSpeech([FromBody] AudioRequest request
     "BaseUrl": "https://api.mistral.ai/v1/",
     "DefaultModel": "mistral-medium",
     "TimeoutSeconds": 30,
-    "MaxRetries": 3
+    "MaxRetries": 3,
+    "RateLimitPerMinute": 10,
+    "EnableCaching": true,
+    "CacheTTLMinutes": 60
+  }
+}
+```
+
+#### Mistral Connector Configuration
+```json
+{
+  "MistralConnector": {
+    "HttpClientTimeoutSeconds": 60,
+    "CircuitBreakerFailureThreshold": 5,
+    "CircuitBreakerResetMinutes": 1
   }
 }
 ```
@@ -875,6 +932,7 @@ public async Task<IActionResult> RecognizeSpeech([FromBody] AudioRequest request
 | Date | Status Change | Notes |
 |------|---------------|-------|
 | May 31, 2025 | Created | Initial plan based on application-plan.md |
+| June 9, 2025 | Updated | Added Phase 0: Mistral API Connector as first step |
 
 ---