docs(features/ai-services): add Mistral configuration setup instructions

- Add Configuration Setup section with appsettings.Development.json example
- Clarify where to add API key (local dev config, not version control)
- Add security note about not committing API keys
- Update Phase 0 deliverables with clarity

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

docs/features/ai-services.md

@@ -91,6 +91,29 @@ As a learner, I want AI-powered features like generated stories, speech recognit
   - Vosk Python library + German model
   - Coqui TTS Python library + German model
 
+### Configuration Setup
+
+Add the following to your local `appsettings.Development.json` file:
+
+```json
+{
+  "Mistral": {
+    "ApiKey": "YOUR_MISTRAL_API_KEY",
+    "BaseUrl": "https://api.mistral.ai/v1/",
+    "DefaultModel": "mistral-medium",
+    "TimeoutSeconds": 30,
+    "MaxRetries": 3,
+    "RateLimitPerMinute": 10,
+    "EnableCaching": true,
+    "CacheTTLMinutes": 60,
+    "CircuitBreakerFailureThreshold": 5,
+    "CircuitBreakerResetMinutes": 1
+  }
+}
+```
+
+**Note**: Do NOT commit your API key to version control. Use environment variables in production or keep it in local development configuration files only.
+
 ### Data Flow
 
 #### Story Generation Flow
@@ -148,8 +171,8 @@ As a learner, I want AI-powered features like generated stories, speech recognit
 
 **Deliverables:**
 - Standalone Mistral API connector component
-- Configurable via appsettings.json
+- Configurable via appsettings.json (add to local appsettings.Development.json)
-- Resilient to API failures
+- Resilient to API failures (retry, rate limiting, circuit breaker, caching)
 - Testable with mocked HTTP client
 
 ### Phase 1: Configuration & Interfaces (2 hours)