feat: add OpenAI integration with dependency injection support

- Add OpenAIAdapter class using official OpenAI SDK with async support
- Create custom exception hierarchy for LLM errors (authentication,
  rate limit, connection, configuration, response errors)
- Refactor adapter factory to use FastAPI Depends() for dependency injection
- Update configuration to support 'openai' mode with API key and model settings
- Add proper HTTP error mapping for all LLM exception types
- Update Dockerfile with default OPENAI_MODEL environment variable
- Update .env.example with OpenAI configuration options

.env.example

@@ -1,6 +1,10 @@
-# LLM Mode: "local" or "remote"
+# LLM Mode: "local", "remote", or "openai"
 LLM_MODE=local
 
 # Remote LLM Configuration (required if LLM_MODE=remote)
 LLM_REMOTE_URL=https://your-llm-service.com/generate
 LLM_REMOTE_TOKEN=
+
+# OpenAI Configuration (required if LLM_MODE=openai)
+OPENAI_API_KEY=sk-your-api-key-here
+OPENAI_MODEL=gpt-4o-mini