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>
2025-12-13 17:27:51 +01:00
parent c049c1e354
commit 4c6ac89808
11 changed files with 1465 additions and 24 deletions
@@ -0,0 +1,390 @@
+"""
+Redis-backed memory cache for session context.
+
+Provides short-term memory storage with TTL:
+- Session context (24h TTL)
+- Recent entities mentioned in conversation
+- User-scoped with conversation isolation
+
+Uses Redis DB 2 (separate from benchmarks in DB 1).
+"""
+import json
+from typing import Any
+
+import redis.asyncio as redis
+
+from .config import config
+from .logging_config import get_logger
+from .multi_tenancy import get_session_key, get_entities_key
+
+logger = get_logger(__name__)
+
+
+class MemoryCache:
+    """
+    Redis-backed cache for session memory.
+
+    Stores ephemeral context that doesn't need vector search:
+    - Session context (recent topics, user state)
+    - Recent entities (people, places, things mentioned)
+    - Conversation metadata
+
+    All data expires after REDIS_MEMORY_TTL_HOURS (default 24h).
+
+    Usage:
+        cache = MemoryCache()
+        await cache.set_session_context(
+            user="jpmschweitzer",
+            conversation_id="conv_123",
+            context={"topic": "docker", "mood": "curious"}
+        )
+        context = await cache.get_session_context("jpmschweitzer", "conv_123")
+    """
+
+    def __init__(
+        self,
+        redis_url: str | None = None,
+        ttl_hours: int | None = None,
+    ):
+        """
+        Initialize memory cache.
+
+        Args:
+            redis_url: Redis connection URL (defaults to config.redis_memory_url)
+            ttl_hours: TTL for cached data (defaults to config.REDIS_MEMORY_TTL_HOURS)
+        """
+        self._redis_url = redis_url or config.redis_memory_url
+        self._ttl_seconds = (ttl_hours or config.REDIS_MEMORY_TTL_HOURS) * 3600
+        self._client: redis.Redis | None = None
+
+        logger.info(
+            "memory_cache_initialized",
+            redis_url=self._redis_url,
+            ttl_hours=ttl_hours or config.REDIS_MEMORY_TTL_HOURS,
+        )
+
+    async def _get_client(self) -> redis.Redis:
+        """Get or create Redis client."""
+        if self._client is None:
+            self._client = redis.from_url(
+                self._redis_url,
+                encoding="utf-8",
+                decode_responses=True,
+                socket_timeout=config.REDIS_TIMEOUT,
+                socket_connect_timeout=config.REDIS_TIMEOUT,
+            )
+        return self._client
+
+    async def close(self) -> None:
+        """Close Redis connection."""
+        if self._client is not None:
+            await self._client.aclose()
+            self._client = None
+
+    # =========================================================================
+    # Session Context
+    # =========================================================================
+
+    async def get_session_context(
+        self,
+        user: str,
+        conversation_id: str,
+    ) -> dict[str, Any] | None:
+        """
+        Get session context for a conversation.
+
+        Args:
+            user: User identifier
+            conversation_id: Conversation identifier
+
+        Returns:
+            Session context dict or None if not found
+
+        Example:
+            >>> context = await cache.get_session_context("jpmschweitzer", "conv_123")
+            >>> context
+            {"topic": "docker", "mood": "curious", "last_tool": "librarian"}
+        """
+        try:
+            client = await self._get_client()
+            key = get_session_key(user, conversation_id)
+
+            data = await client.get(key)
+            if data is None:
+                return None
+
+            return json.loads(data)
+
+        except Exception as e:
+            logger.warning(
+                "memory_cache_get_session_failed",
+                user=user,
+                conversation_id=conversation_id,
+                error=str(e),
+            )
+            return None
+
+    async def set_session_context(
+        self,
+        user: str,
+        conversation_id: str,
+        context: dict[str, Any],
+    ) -> bool:
+        """
+        Set session context for a conversation.
+
+        Args:
+            user: User identifier
+            conversation_id: Conversation identifier
+            context: Context data to store
+
+        Returns:
+            True if successful, False otherwise
+
+        Example:
+            >>> await cache.set_session_context(
+            ...     "jpmschweitzer",
+            ...     "conv_123",
+            ...     {"topic": "docker", "mood": "curious"}
+            ... )
+            True
+        """
+        try:
+            client = await self._get_client()
+            key = get_session_key(user, conversation_id)
+
+            await client.setex(
+                key,
+                self._ttl_seconds,
+                json.dumps(context),
+            )
+
+            logger.debug(
+                "memory_cache_set_session",
+                user=user,
+                conversation_id=conversation_id,
+                context_keys=list(context.keys()),
+            )
+            return True
+
+        except Exception as e:
+            logger.warning(
+                "memory_cache_set_session_failed",
+                user=user,
+                conversation_id=conversation_id,
+                error=str(e),
+            )
+            return False
+
+    async def update_session_context(
+        self,
+        user: str,
+        conversation_id: str,
+        updates: dict[str, Any],
+    ) -> bool:
+        """
+        Update session context (merge with existing).
+
+        Args:
+            user: User identifier
+            conversation_id: Conversation identifier
+            updates: Fields to update/add
+
+        Returns:
+            True if successful, False otherwise
+        """
+        existing = await self.get_session_context(user, conversation_id) or {}
+        existing.update(updates)
+        return await self.set_session_context(user, conversation_id, existing)
+
+    async def delete_session_context(
+        self,
+        user: str,
+        conversation_id: str,
+    ) -> bool:
+        """
+        Delete session context for a conversation.
+
+        Args:
+            user: User identifier
+            conversation_id: Conversation identifier
+
+        Returns:
+            True if deleted, False otherwise
+        """
+        try:
+            client = await self._get_client()
+            key = get_session_key(user, conversation_id)
+            await client.delete(key)
+            return True
+
+        except Exception as e:
+            logger.warning(
+                "memory_cache_delete_session_failed",
+                user=user,
+                conversation_id=conversation_id,
+                error=str(e),
+            )
+            return False
+
+    # =========================================================================
+    # Recent Entities
+    # =========================================================================
+
+    async def get_recent_entities(
+        self,
+        user: str,
+        conversation_id: str,
+    ) -> list[str]:
+        """
+        Get recently mentioned entities in a conversation.
+
+        Args:
+            user: User identifier
+            conversation_id: Conversation identifier
+
+        Returns:
+            List of entity names/identifiers
+
+        Example:
+            >>> entities = await cache.get_recent_entities("jpmschweitzer", "conv_123")
+            >>> entities
+            ["Docker", "Kubernetes", "nginx"]
+        """
+        try:
+            client = await self._get_client()
+            key = get_entities_key(user, conversation_id)
+
+            # Get all members of the set
+            entities = await client.smembers(key)
+            return list(entities)
+
+        except Exception as e:
+            logger.warning(
+                "memory_cache_get_entities_failed",
+                user=user,
+                conversation_id=conversation_id,
+                error=str(e),
+            )
+            return []
+
+    async def add_recent_entities(
+        self,
+        user: str,
+        conversation_id: str,
+        entities: list[str],
+    ) -> bool:
+        """
+        Add entities to the recent entities set.
+
+        Args:
+            user: User identifier
+            conversation_id: Conversation identifier
+            entities: Entity names to add
+
+        Returns:
+            True if successful, False otherwise
+
+        Example:
+            >>> await cache.add_recent_entities(
+            ...     "jpmschweitzer",
+            ...     "conv_123",
+            ...     ["Docker", "Kubernetes"]
+            ... )
+            True
+        """
+        if not entities:
+            return True
+
+        try:
+            client = await self._get_client()
+            key = get_entities_key(user, conversation_id)
+
+            # Add to set
+            await client.sadd(key, *entities)
+
+            # Refresh TTL
+            await client.expire(key, self._ttl_seconds)
+
+            logger.debug(
+                "memory_cache_add_entities",
+                user=user,
+                conversation_id=conversation_id,
+                entities=entities,
+            )
+            return True
+
+        except Exception as e:
+            logger.warning(
+                "memory_cache_add_entities_failed",
+                user=user,
+                conversation_id=conversation_id,
+                error=str(e),
+            )
+            return False
+
+    async def clear_recent_entities(
+        self,
+        user: str,
+        conversation_id: str,
+    ) -> bool:
+        """
+        Clear all recent entities for a conversation.
+
+        Args:
+            user: User identifier
+            conversation_id: Conversation identifier
+
+        Returns:
+            True if cleared, False otherwise
+        """
+        try:
+            client = await self._get_client()
+            key = get_entities_key(user, conversation_id)
+            await client.delete(key)
+            return True
+
+        except Exception as e:
+            logger.warning(
+                "memory_cache_clear_entities_failed",
+                user=user,
+                conversation_id=conversation_id,
+                error=str(e),
+            )
+            return False
+
+    # =========================================================================
+    # Health Check
+    # =========================================================================
+
+    async def health_check(self) -> bool:
+        """
+        Check if Redis is reachable.
+
+        Returns:
+            True if healthy, False otherwise
+        """
+        try:
+            client = await self._get_client()
+            await client.ping()
+            return True
+        except Exception as e:
+            logger.error("memory_cache_health_check_failed", error=str(e))
+            return False
+
+
+# Global cache instance (lazy initialization)
+_memory_cache: MemoryCache | None = None
+
+
+def get_memory_cache() -> MemoryCache:
+    """
+    Get global memory cache instance.
+
+    Returns:
+        MemoryCache instance
+    """
+    global _memory_cache
+    if _memory_cache is None:
+        _memory_cache = MemoryCache()
+    return _memory_cache