feat: Add OpenAI provider support for embeddings and generation

Adds OpenAI provider to the unified provider architecture (ADR-015),
supporting:
- OpenAI API (api.openai.com)
- GitHub Models API (models.github.ai/inference)
- OpenAI-compatible endpoints (Fireworks, Together, etc.)

Features:
- Embedding support with text-embedding-3-small/large models
- Text generation via chat completions API
- Automatic retry with exponential backoff for rate limits
- Provider auto-detection in registry (priority after Bedrock)

Environment variables:
- OPENAI_API_KEY: API key (required)
- OPENAI_BASE_URL: Base URL override (optional)
- OPENAI_EMBEDDING_MODEL: Embedding model (default: text-embedding-3-small)
- OPENAI_GENERATION_MODEL: Generation model (default: gpt-4o-mini)

Also adds:
- Integration tests for RAG pipeline with MCP sampling
- MCP client sampling support for integration tests
- Ground truth Q&A pairs for Nextcloud User Manual

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

tests/conftest.py

@@ -114,6 +114,7 @@ async def create_mcp_client_session(
     token: str | None = None,
     client_name: str = "MCP",
     elicitation_callback: Any = None,
+    sampling_callback: Any = None,
 ) -> AsyncGenerator[ClientSession, Any]:
     """
     Factory function to create an MCP client session with proper lifecycle management.
@@ -133,6 +134,8 @@ async def create_mcp_client_session(
         client_name: Client name for logging (e.g., "OAuth MCP (Playwright)")
         elicitation_callback: Optional callback for handling elicitation requests.
             Should match signature: async def callback(context: RequestContext, params: ElicitRequestParams) -> ElicitResult | ErrorData
+        sampling_callback: Optional callback for handling sampling (LLM generation) requests.
+            Should match signature: async def callback(context: RequestContext, params: CreateMessageRequestParams) -> CreateMessageResult | ErrorData
 
     Yields:
         Initialized MCP ClientSession
@@ -156,7 +159,10 @@ async def create_mcp_client_session(
         _,
     ):
         async with ClientSession(
-            read_stream, write_stream, elicitation_callback=elicitation_callback
+            read_stream,
+            write_stream,
+            elicitation_callback=elicitation_callback,
+            sampling_callback=sampling_callback,
         ) as session:
             await session.initialize()
             logger.info(f"{client_name} client session initialized successfully")