- Create llm_client.py with 5 provider implementations (Anthropic, OpenAI, Ollama, OpenRouter, Google)
- Add build_prompt() helper to construct system/user prompts from templates
- Wire up POST /transcribe/sessions/{id}/summaries endpoint to call LLM client
- Return generated content + token counts (input_tokens, output_tokens)
- API keys passed per-request, never stored or logged
- Uses prompt templates from prompts.py based on summary_type
- Updated ANON_KEY and SERVICE_ROLE_KEY from supabase container
- Changed SUPABASE_URL to local dev instance (192.168.0.155:8000)
- Synced .env.local with .env for consistency
