feat: add Phase F.1 memory infrastructure

Add multi-tenancy support and memory storage infrastructure:

- Add ContextVar-based request context (src/core/context.py)
  - Async-safe user/conversation tracking via contextvars
  - RequestContext manager for clean setup/teardown
  - get_user(), get_conversation_id() helpers

- Add multi-tenancy utilities (src/core/multi_tenancy.py)
  - User ID sanitization for collection/key names
  - get_memory_collection_name(), get_session_key() helpers

- Add Ollama embedding client (src/core/embeddings.py)
  - nomic-embed-text model (768 dimensions)
  - embed(), embed_batch(), health_check() methods

- Add Qdrant client wrapper (src/core/qdrant.py)
  - Per-user collection pattern: memories_{user}
  - upsert_memory(), search_memories(), delete_memory()
  - Type-based filtering support

- Add Redis memory cache (src/core/memory_cache.py)
  - Session context with 24h TTL
  - Recent entities tracking
  - Separate from benchmarks (db=2)

- Update config with memory settings
  - QDRANT_HOST, QDRANT_PORT, QDRANT_EMBEDDING_DIM
  - OLLAMA_EMBEDDING_MODEL
  - REDIS_MEMORY_DB, REDIS_MEMORY_TTL_HOURS

- Add user field to ResponseRequest (OpenAI standard)
- Set context in router, reset in finally block
- Update librarian client to use get_user() (12 methods)

All 333 unit tests pass.

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/core/embeddings.py

@@ -0,0 +1,269 @@
+"""
+Ollama client for embeddings generation.
+
+Provides async embedding operations via Ollama API:
+- Text embedding generation
+- Batch embedding support
+- Health checks
+
+Adapted from library-desk patterns.
+"""
+from typing import Optional
+
+import httpx
+
+from .config import config
+from .logging_config import get_logger
+
+logger = get_logger(__name__)
+
+
+class OllamaEmbeddingClient:
+    """
+    Ollama API client for embeddings.
+
+    Uses the Ollama embeddings endpoint to generate vector representations
+    of text using the nomic-embed-text model (768 dimensions).
+
+    Usage:
+        client = OllamaEmbeddingClient()
+        embedding = await client.embed("Hello world")
+        await client.close()
+
+    Or with context manager:
+        async with OllamaEmbeddingClient() as client:
+            embedding = await client.embed("Hello world")
+    """
+
+    def __init__(
+        self,
+        base_url: str | None = None,
+        model: str | None = None,
+        timeout: float = 120.0,
+    ):
+        """
+        Initialize Ollama embedding client.
+
+        Args:
+            base_url: Ollama server URL (defaults to config.OLLAMA_HOST)
+            model: Embedding model name (defaults to config.OLLAMA_EMBEDDING_MODEL)
+            timeout: Request timeout in seconds (embeddings can be slow)
+        """
+        self.base_url = (base_url or str(config.OLLAMA_HOST)).rstrip("/")
+        self.model = model or config.OLLAMA_EMBEDDING_MODEL
+        self.embeddings_url = f"{self.base_url}/api/embeddings"
+        self.tags_url = f"{self.base_url}/api/tags"
+        self._client: httpx.AsyncClient | None = None
+        self._timeout = timeout
+
+        logger.info(
+            "ollama_embedding_client_initialized",
+            base_url=self.base_url,
+            model=self.model,
+        )
+
+    async def _get_client(self) -> httpx.AsyncClient:
+        """Get or create HTTP client."""
+        if self._client is None:
+            self._client = httpx.AsyncClient(timeout=self._timeout)
+        return self._client
+
+    async def __aenter__(self) -> "OllamaEmbeddingClient":
+        """Async context manager entry."""
+        await self._get_client()
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb) -> None:
+        """Async context manager exit."""
+        await self.close()
+
+    async def close(self) -> None:
+        """Close HTTP client."""
+        if self._client is not None:
+            await self._client.aclose()
+            self._client = None
+
+    async def embed(self, text: str) -> list[float] | None:
+        """
+        Generate embedding for single text.
+
+        Args:
+            text: Text to embed
+
+        Returns:
+            Embedding vector (768-dimensional for nomic-embed-text) or None on failure
+
+        Example:
+            >>> embedding = await client.embed("Hello world")
+            >>> len(embedding)
+            768
+        """
+        try:
+            client = await self._get_client()
+
+            payload = {
+                "model": self.model,
+                "prompt": text,
+            }
+
+            response = await client.post(self.embeddings_url, json=payload)
+            response.raise_for_status()
+            data = response.json()
+
+            embedding = data.get("embedding")
+            if not embedding:
+                logger.error("ollama_embed_no_embedding", response_data=data)
+                return None
+
+            return embedding
+
+        except httpx.HTTPStatusError as e:
+            logger.error(
+                "ollama_embed_http_error",
+                status_code=e.response.status_code,
+                detail=e.response.text,
+            )
+            return None
+        except Exception as e:
+            logger.error("ollama_embed_failed", error=str(e), exc_info=True)
+            return None
+
+    async def embed_batch(
+        self,
+        texts: list[str],
+        show_progress: bool = False,
+    ) -> list[list[float] | None]:
+        """
+        Generate embeddings for multiple texts.
+
+        Note: Ollama doesn't support native batch embeddings, so this
+        sequentially calls embed() for each text.
+
+        Args:
+            texts: List of texts to embed
+            show_progress: Log progress for large batches
+
+        Returns:
+            List of embedding vectors (same order as input)
+            None entries for texts that failed to embed
+
+        Example:
+            >>> texts = ["Hello", "World", "Test"]
+            >>> embeddings = await client.embed_batch(texts)
+            >>> len(embeddings)
+            3
+        """
+        embeddings = []
+
+        for i, text in enumerate(texts):
+            if show_progress and i % 10 == 0:
+                logger.info(
+                    "ollama_embed_batch_progress",
+                    current=i,
+                    total=len(texts),
+                )
+
+            embedding = await self.embed(text)
+            embeddings.append(embedding)
+
+        if show_progress:
+            logger.info(
+                "ollama_embed_batch_complete",
+                successful=sum(1 for e in embeddings if e is not None),
+                total=len(texts),
+            )
+
+        return embeddings
+
+    async def embed_batch_filtered(
+        self,
+        texts: list[str],
+        show_progress: bool = False,
+    ) -> list[list[float]]:
+        """
+        Generate embeddings for multiple texts, filtering out failures.
+
+        Args:
+            texts: List of texts to embed
+            show_progress: Log progress for large batches
+
+        Returns:
+            List of successful embedding vectors (may be shorter than input)
+
+        Example:
+            >>> embeddings = await client.embed_batch_filtered(texts)
+            >>> all(e is not None for e in embeddings)
+            True
+        """
+        all_embeddings = await self.embed_batch(texts, show_progress)
+        return [e for e in all_embeddings if e is not None]
+
+    async def get_embedding_dimension(self) -> int | None:
+        """
+        Get embedding dimension for current model.
+
+        Returns:
+            Embedding dimension (e.g., 768 for nomic-embed-text) or None on failure
+
+        Example:
+            >>> dim = await client.get_embedding_dimension()
+            >>> dim
+            768
+        """
+        test_embedding = await self.embed("test")
+        if test_embedding:
+            return len(test_embedding)
+        return None
+
+    async def health_check(self) -> bool:
+        """
+        Check if Ollama server is reachable and model is available.
+
+        Returns:
+            True if healthy, False otherwise
+        """
+        try:
+            client = await self._get_client()
+            response = await client.get(self.tags_url, timeout=5.0)
+            response.raise_for_status()
+            data = response.json()
+            models = data.get("models", [])
+
+            # Check if our embedding model is available
+            model_found = False
+            for m in models:
+                name = m.get("name", "")
+                if name == self.model or name.startswith(f"{self.model}:"):
+                    model_found = True
+                    break
+
+            if not model_found:
+                logger.warning(
+                    "ollama_embedding_model_not_found",
+                    model=self.model,
+                    available=[m.get("name") for m in models],
+                )
+                return False
+
+            return True
+
+        except Exception as e:
+            logger.error("ollama_embedding_health_check_failed", error=str(e))
+            return False
+
+
+# Global client instance (lazy initialization)
+_embedding_client: OllamaEmbeddingClient | None = None
+
+
+def get_embedding_client() -> OllamaEmbeddingClient:
+    """
+    Get global embedding client instance.
+
+    Returns:
+        OllamaEmbeddingClient instance
+    """
+    global _embedding_client
+    if _embedding_client is None:
+        _embedding_client = OllamaEmbeddingClient()
+    return _embedding_client