Stream C: Multi-provider AI coaching backend + 20-provider registry

AI coaching service (backend/app/services/ai_provider.py):
- Two code paths: OpenAI-compatible (6 providers) + Anthropic (Claude)
- Streaming SSE responses via httpx async
- System prompt built from AGENT_GUIDE + live user context
- Graceful error handling for all provider failures
- Gemini adapter for Google's generateContent API

Chat endpoint (backend/app/routers/ai_chat.py):
- POST /api/ai/chat — SSE streaming response
- GET /api/ai/status — check configured provider
- History capped at 20 messages, content at 4K chars

Provider registry expanded to 20 providers:
- 9 device integrations (strava, polar, garmin, whoop, oura, coros, fitbit, withings, suunto)
- 8 AI providers (openai, openrouter, huggingface, groq, ollama, claude, gemini, custom_ai)
- 3 other (usda, nutritionix, telegram)
- Categorized: device, ai_provider, nutrition, notifications
- COROS: MCP bridge approach (no API integration needed)
- Strava: AI/ML warning per their ToS

Frontend ChatCoach.jsx to follow in next commit.

backend/app/main.py

@@ -96,6 +96,7 @@ from app.routers.catalog import router as catalog_router
 from app.routers.support import router as support_router
 from app.routers.nutrition import router as nutrition_router
 from app.routers.meal_plans import router as meal_plans_router
+from app.routers.ai_chat import router as ai_chat_router
 
 app.include_router(auth_router)
 app.include_router(onboarding_router)
@@ -109,6 +110,7 @@ app.include_router(support_router)
 app.include_router(programs_router)
 app.include_router(nutrition_router)
 app.include_router(meal_plans_router)
+app.include_router(ai_chat_router)
 
 
 @app.get("/api/health")