feat: add Qdrant local mode support with in-memory and persistent storage

Adds flexible Qdrant deployment modes to reduce infrastructure requirements
for local development and smaller deployments:

**Configuration Changes:**
- Add QDRANT_LOCATION environment variable (mutually exclusive with QDRANT_URL)
- Three modes: network (URL), in-memory (:memory:, default), persistent (file path)
- Settings dataclass validation via __post_init__ ensures mutual exclusivity
- API key warning when set in local mode (ignored, only for network mode)

**Client Initialization:**
- Auto-detect mode: network (url + api_key) vs local (:memory: or path=)
- In-memory: AsyncQdrantClient(":memory:") - zero config default
- Persistent: AsyncQdrantClient(path="/app/data/qdrant") - file storage
- Network: AsyncQdrantClient(url, api_key) - production mode

**Docker Compose Updates:**
- Qdrant service moved to optional profile (--profile qdrant)
- MCP service uses QDRANT_LOCATION=:memory: by default
- Added mcp-data volume for persistent storage (/app/data)
- No hard dependency on qdrant service

**Documentation:**
- Comprehensive configuration guide in docs/configuration.md
- All three modes documented with pros/cons
- Docker Compose examples for each mode
- Environment variable reference table

**Tests:**
- 13 new config validation tests (mutual exclusivity, defaults, warnings)
- Persistent mode integration test (create, close, reopen, verify persistence)
- All 82 unit tests + 5 smoke tests pass

**Breaking Change:**
- Default changed from QDRANT_URL=http://qdrant:6333 to QDRANT_LOCATION=:memory:
- Simplifies local development (no external service needed)
- Production deployments: explicitly set QDRANT_URL or QDRANT_LOCATION

Related: ADR-007 background vector sync implementation

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

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

nextcloud_mcp_server/config.py

@@ -1,3 +1,4 @@
+import logging
 import logging.config
 import os
 from dataclasses import dataclass
@@ -162,8 +163,9 @@ class Settings:
     vector_sync_processor_workers: int = 3
     vector_sync_queue_max_size: int = 10000
 
-    # Qdrant settings
-    qdrant_url: str = "http://qdrant:6333"
+    # Qdrant settings (mutually exclusive modes)
+    qdrant_url: Optional[str] = None  # Network mode: http://qdrant:6333
+    qdrant_location: Optional[str] = None  # Local mode: :memory: or /path/to/data
     qdrant_api_key: Optional[str] = None
     qdrant_collection: str = "nextcloud_content"
 
@@ -172,6 +174,29 @@ class Settings:
     ollama_embedding_model: str = "nomic-embed-text"
     ollama_verify_ssl: bool = True
 
+    def __post_init__(self):
+        """Validate Qdrant configuration and set defaults."""
+        logger = logging.getLogger(__name__)
+
+        # Ensure mutual exclusivity
+        if self.qdrant_url and self.qdrant_location:
+            raise ValueError(
+                "Cannot set both QDRANT_URL and QDRANT_LOCATION. "
+                "Use QDRANT_URL for network mode or QDRANT_LOCATION for local mode."
+            )
+
+        # Default to :memory: if neither set
+        if not self.qdrant_url and not self.qdrant_location:
+            self.qdrant_location = ":memory:"
+            logger.info("Using default Qdrant mode: in-memory (:memory:)")
+
+        # Warn if API key set in local mode
+        if self.qdrant_location and self.qdrant_api_key:
+            logger.warning(
+                "QDRANT_API_KEY is set but QDRANT_LOCATION is used (local mode). "
+                "API key is only relevant for network mode and will be ignored."
+            )
+
 
 def get_settings() -> Settings:
     """Get application settings from environment variables.
@@ -220,7 +245,8 @@ def get_settings() -> Settings:
             os.getenv("VECTOR_SYNC_QUEUE_MAX_SIZE", "10000")
         ),
         # Qdrant settings
-        qdrant_url=os.getenv("QDRANT_URL", "http://qdrant:6333"),
+        qdrant_url=os.getenv("QDRANT_URL"),
+        qdrant_location=os.getenv("QDRANT_LOCATION"),
         qdrant_api_key=os.getenv("QDRANT_API_KEY"),
         qdrant_collection=os.getenv("QDRANT_COLLECTION", "nextcloud_content"),
         # Ollama settings

nextcloud_mcp_server/vector/qdrant_client.py

@@ -1,11 +1,12 @@
 """Qdrant client wrapper."""
 
 import logging
-import os
 
 from qdrant_client import AsyncQdrantClient
 from qdrant_client.models import Distance, VectorParams
 
+from nextcloud_mcp_server.config import get_settings
+
 logger = logging.getLogger(__name__)
 
 
@@ -19,6 +20,11 @@ async def get_qdrant_client() -> AsyncQdrantClient:
 
     Automatically creates collection on first use if it doesn't exist.
 
+    Supports three Qdrant modes:
+    - Network mode: QDRANT_URL set (e.g., http://qdrant:6333)
+    - In-memory mode: QDRANT_LOCATION=:memory: (default if nothing configured)
+    - Persistent local mode: QDRANT_LOCATION=/path/to/data
+
     Returns:
         Configured AsyncQdrantClient instance
 
@@ -28,17 +34,33 @@ async def get_qdrant_client() -> AsyncQdrantClient:
     global _qdrant_client
 
     if _qdrant_client is None:
-        url = os.getenv("QDRANT_URL", "http://qdrant:6333")
-        api_key = os.getenv("QDRANT_API_KEY")
+        settings = get_settings()
 
-        _qdrant_client = AsyncQdrantClient(
-            url=url,
-            api_key=api_key,
-            timeout=30,
-        )
+        # Detect mode and initialize client accordingly
+        if settings.qdrant_url:
+            # Network mode
+            logger.info(f"Using Qdrant network mode: {settings.qdrant_url}")
+            _qdrant_client = AsyncQdrantClient(
+                url=settings.qdrant_url,
+                api_key=settings.qdrant_api_key,
+                timeout=30,
+            )
+        elif settings.qdrant_location:
+            # Local mode (either :memory: or persistent path)
+            if settings.qdrant_location == ":memory:":
+                logger.info("Using Qdrant in-memory mode: :memory:")
+                _qdrant_client = AsyncQdrantClient(":memory:")
+            else:
+                # Persistent local mode - use path parameter
+                logger.info(f"Using Qdrant persistent mode: {settings.qdrant_location}")
+                _qdrant_client = AsyncQdrantClient(path=settings.qdrant_location)
+        else:
+            # Should not happen due to __post_init__ validation, but handle gracefully
+            logger.warning("No Qdrant mode configured, defaulting to :memory:")
+            _qdrant_client = AsyncQdrantClient(":memory:")
 
         # Ensure collection exists
-        collection_name = os.getenv("QDRANT_COLLECTION", "nextcloud_content")
+        collection_name = settings.qdrant_collection
 
         # Import here to avoid circular dependency
         from nextcloud_mcp_server.embedding import get_embedding_service