Files
library-desk/src/services/volatile_service.py
T
jpmschweitzerandClaude Fable 5 8a1c9ba5f3 fix(security): scope every HybridRAG leg and ingestion path to the caller's tenant
A live /query/hybrid probe as user=llm_tester returned jpmschweitzer
pages. Audit of all legs (vector, graph, web-persistence, volatile,
documents) plus enrichment/persistence found and fixed these unscoped
paths:

- vector_service.update_from_page and graph_service.update_from_page now
  refuse pages outside users/{user}/ - previously any tenant could
  ingest any wiki page (incl. another tenant's) into its own collection
  and graph labels, which is how foreign content entered the vector leg.
- ingestion_service.ingest_all_pages clamps path_prefix to the caller's
  namespace (segment-exact, sanitized comparison) and defaults to
  users/{user}; /ingest/all returns 400 on cross-tenant prefixes.
- hybrid_rag_service._persist_search_for_librarian linked SearchQuery
  nodes to unscoped (d:Document {page_id}); now matches only
  User_{Tenant}_Document nodes.
- graph_service: _get_entity_mention_count, entity-stub mention/related
  queries, generate_entity_stubs, find/purge_orphan_entities matched
  unscoped Document nodes; cleanup_broken_relationships matched all
  tenants' SearchQuery nodes; _entity_has_wiki_page listed all wiki
  pages. All are now tenant-label / namespace scoped.
- volatile_service collection names now use the sanitized user id.
- is_path_in_user_namespace enforces a path-segment boundary
  (users/llm_tester2 is not llm_tester's namespace) and treats
  hyphen/underscore tenant spellings as the same sanitized tenant.
- New offline unit tests per leg (mocked clients) assert the
  tenant-scoped collection/label/path is used and cross-tenant access
  is refused.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-14 11:15:43 +02:00

572 lines
18 KiB
Python

"""
Volatile Cache service for Library Desk.
Provides ephemeral data storage with TTL using Qdrant vectors:
- Weather, news, financial data
- Transit schedules, traffic conditions
- System status, social notifications
Data is stored as embedded vectors for semantic search retrieval.
"""
import hashlib
import logging
import time
from datetime import datetime
from typing import List, Optional, Dict, Any
from src.clients.qdrant_client import QdrantClientWrapper
from src.clients.ollama_client import OllamaClient
from src.config import Settings
from src.models.volatile import (
VolatileRecordResponse,
VolatileNamespace,
NAMESPACE_DEFAULT_TTL,
)
logger = logging.getLogger(__name__)
class VolatileCacheService:
"""
Service for volatile data with TTL stored in Qdrant.
Stores ephemeral data as vectors for semantic search retrieval.
Each user has an isolated volatile collection.
"""
COLLECTION_PREFIX = "volatile_"
def __init__(
self,
qdrant_client: QdrantClientWrapper,
ollama_client: OllamaClient,
settings: Settings
):
"""
Initialize volatile cache service.
Args:
qdrant_client: Qdrant client for vector storage
ollama_client: Ollama client for embeddings
settings: Application settings
"""
self.qdrant = qdrant_client
self.ollama = ollama_client
self.settings = settings
logger.info("Initialized VolatileCacheService (Qdrant backend)")
def _collection_name(self, user: str) -> str:
"""
Get volatile collection name for user.
The user id is sanitized (same rules as the document collections)
so raw identifiers cannot alias or escape the per-tenant
collection naming scheme.
"""
from src.core.multi_tenancy import sanitize_user_id
return f"{self.COLLECTION_PREFIX}{sanitize_user_id(user)}"
def _make_vector_id(self, namespace: str, key: str) -> str:
"""
Generate deterministic vector ID for namespace/key.
Same namespace+key always produces same ID for upsert behavior.
"""
combined = f"{namespace}:{key}"
return hashlib.md5(combined.encode()).hexdigest()
def _get_default_ttl(self, namespace: str) -> int:
"""Get default TTL for a namespace."""
try:
ns = VolatileNamespace(namespace)
return NAMESPACE_DEFAULT_TTL.get(ns, self.settings.volatile_default_ttl)
except ValueError:
return self.settings.volatile_default_ttl
def _current_timestamp_ms(self) -> int:
"""Get current timestamp in milliseconds."""
return int(time.time() * 1000)
def _to_natural_language(
self,
namespace: str,
key: str,
data: Dict[str, Any]
) -> str:
"""
Convert structured data to natural language for embedding.
This creates a text representation that embeds well semantically.
"""
# Template-based conversion for known namespaces
if namespace == VolatileNamespace.WEATHER:
temp = data.get("temperature", data.get("temp", "unknown"))
conditions = data.get("conditions", data.get("weather", ""))
humidity = data.get("humidity", "")
text = f"Current weather in {key}: {temp}°C"
if conditions:
text += f", {conditions}"
if humidity:
text += f", humidity {humidity}%"
return text
elif namespace == VolatileNamespace.NEWS:
title = data.get("title", data.get("headline", ""))
summary = data.get("summary", data.get("description", ""))
source = data.get("source", "")
text = f"News: {title}"
if summary:
text += f". {summary}"
if source:
text += f" (Source: {source})"
return text
elif namespace == VolatileNamespace.FINANCIAL:
symbol = data.get("symbol", key)
price = data.get("price", "")
change = data.get("change", data.get("change_percent", ""))
text = f"Financial data for {symbol}"
if price:
text += f": price {price}"
if change:
text += f", change {change}%"
return text
elif namespace == VolatileNamespace.TRANSIT:
route = data.get("route", data.get("line", key))
status = data.get("status", "")
delay = data.get("delay", data.get("delay_minutes", ""))
text = f"Transit {route}"
if status:
text += f": {status}"
if delay:
text += f", delay {delay} minutes"
return text
elif namespace == VolatileNamespace.TRAFFIC:
location = data.get("location", key)
duration = data.get("duration", data.get("travel_time", ""))
congestion = data.get("congestion", "")
text = f"Traffic for {location}"
if duration:
text += f": {duration} minutes"
if congestion:
text += f", congestion level {congestion}"
return text
elif namespace == VolatileNamespace.AIR_QUALITY:
location = data.get("location", key)
aqi = data.get("aqi", data.get("index", ""))
quality = data.get("quality", "")
text = f"Air quality in {location}"
if aqi:
text += f": AQI {aqi}"
if quality:
text += f" ({quality})"
return text
elif namespace == VolatileNamespace.SPORTS:
event = data.get("event", data.get("match", key))
score = data.get("score", "")
status = data.get("status", "")
text = f"Sports: {event}"
if score:
text += f" - Score: {score}"
if status:
text += f" ({status})"
return text
elif namespace == VolatileNamespace.SYSTEM:
service = data.get("service", key)
status = data.get("status", "unknown")
message = data.get("message", "")
text = f"System status for {service}: {status}"
if message:
text += f". {message}"
return text
# Fallback: serialize key fields
text_parts = [f"{namespace} data for {key}:"]
for k, v in data.items():
if isinstance(v, (str, int, float, bool)):
text_parts.append(f"{k}: {v}")
return " ".join(text_parts)
async def store(
self,
user: str,
namespace: str,
key: str,
data: Dict[str, Any],
source: Optional[str] = None,
ttl: Optional[int] = None,
refresh_schedule: Optional[str] = None
) -> VolatileRecordResponse:
"""
Store volatile data as an embedded vector.
Args:
user: User identifier
namespace: Data namespace (from controlled list)
key: Record key (normalized slug)
data: Structured data to store
source: Origin API/service
ttl: TTL in seconds (uses namespace default if not set)
refresh_schedule: Optional cron expression for refresh
Returns:
The stored record
"""
collection = self._collection_name(user)
# Ensure collection exists
await self.qdrant.ensure_collection(collection)
# Calculate TTL and expiry
effective_ttl = ttl if ttl is not None else self._get_default_ttl(namespace)
now_ms = self._current_timestamp_ms()
expiry_ms = now_ms + (effective_ttl * 1000)
# Convert to natural language for embedding
text = self._to_natural_language(namespace, key, data)
# Generate embedding
embedding = await self.ollama.embed(text)
if not embedding:
raise ValueError("Failed to generate embedding for volatile data")
# Build payload
now = datetime.utcnow()
payload = {
"doc_type": "volatile",
"namespace": namespace,
"key": key,
"text": text,
"raw_data": data,
"source": source,
"created_at": now.isoformat(),
"updated_at": now.isoformat(),
"ttl": effective_ttl,
"ttl_expiry": expiry_ms,
"refresh_schedule": refresh_schedule,
"user": user,
}
# Upsert vector (same namespace+key = same ID = update)
vector_id = self._make_vector_id(namespace, key)
success = await self.qdrant.upsert_vector(
collection_name=collection,
vector_id=vector_id,
vector=embedding,
payload=payload
)
if not success:
raise ValueError("Failed to store volatile vector")
logger.debug(f"Stored volatile {namespace}:{key} with TTL {effective_ttl}s")
return VolatileRecordResponse(
key=key,
namespace=namespace,
data=data,
source=source,
created_at=now,
updated_at=now,
ttl=effective_ttl,
ttl_remaining=effective_ttl,
refresh_schedule=refresh_schedule,
user=user,
)
async def search(
self,
user: str,
query: str,
limit: int = 5,
score_threshold: float = 0.75
) -> List[VolatileRecordResponse]:
"""
Semantic search across volatile data.
Args:
user: User identifier
query: Search query
limit: Maximum results
score_threshold: Minimum similarity score (higher = stricter)
Returns:
List of matching volatile records
"""
collection = self._collection_name(user)
# Check if collection exists
if not await self.qdrant.collection_exists(collection):
return []
# Generate query embedding
query_embedding = await self.ollama.embed(query)
if not query_embedding:
logger.error("Failed to embed query for volatile search")
return []
# Search with expiry filter
now_ms = self._current_timestamp_ms()
results = await self.qdrant.search_with_expiry_filter(
collection_name=collection,
query_vector=query_embedding,
current_timestamp=now_ms,
limit=limit,
score_threshold=score_threshold
)
# Convert to response models
responses = []
for result in results:
payload = result["payload"]
ttl_expiry = payload.get("ttl_expiry", 0)
ttl_remaining = max(0, (ttl_expiry - now_ms) // 1000)
responses.append(VolatileRecordResponse(
key=payload["key"],
namespace=payload["namespace"],
data=payload.get("raw_data", {}),
source=payload.get("source"),
created_at=datetime.fromisoformat(payload["created_at"]),
updated_at=datetime.fromisoformat(payload["updated_at"]),
ttl=payload.get("ttl", 0),
ttl_remaining=ttl_remaining,
refresh_schedule=payload.get("refresh_schedule"),
user=payload["user"],
))
return responses
async def get(
self,
user: str,
namespace: str,
key: str
) -> Optional[VolatileRecordResponse]:
"""
Get a specific volatile record by namespace and key.
Args:
user: User identifier
namespace: Data namespace
key: Record key
Returns:
Record if found and not expired, None otherwise
"""
# Use search with high threshold to find exact match
query = self._to_natural_language(namespace, key, {"key": key})
results = await self.search(user, query, limit=10, score_threshold=0.5)
# Find exact namespace+key match
for result in results:
if result.namespace == namespace and result.key == key:
return result
return None
async def delete(
self,
user: str,
namespace: str,
key: str
) -> bool:
"""
Delete a specific volatile record.
Args:
user: User identifier
namespace: Data namespace
key: Record key
Returns:
True if deleted, False if not found
"""
collection = self._collection_name(user)
if not await self.qdrant.collection_exists(collection):
return False
vector_id = self._make_vector_id(namespace, key)
try:
deleted = await self.qdrant.delete_by_ids(
collection_name=collection,
point_ids=[vector_id]
)
return deleted > 0
except Exception as e:
logger.error(f"Failed to delete volatile {namespace}:{key}: {e}")
return False
async def get_scheduled(
self,
user: str
) -> List[VolatileRecordResponse]:
"""
Get all records with refresh schedules.
Used by scheduler to determine what needs refreshing.
Args:
user: User identifier
Returns:
List of records with refresh_schedule set
"""
collection = self._collection_name(user)
if not await self.qdrant.collection_exists(collection):
return []
now_ms = self._current_timestamp_ms()
scheduled = []
# Scroll through all non-expired records
try:
all_points = await self.qdrant.scroll_all_points(
collection_name=collection,
with_payload=True
)
for point in all_points:
payload = point.get("payload", {})
ttl_expiry = payload.get("ttl_expiry", 0)
# Skip expired
if ttl_expiry <= now_ms:
continue
# Only include if has refresh schedule
if payload.get("refresh_schedule"):
ttl_remaining = max(0, (ttl_expiry - now_ms) // 1000)
scheduled.append(VolatileRecordResponse(
key=payload["key"],
namespace=payload["namespace"],
data=payload.get("raw_data", {}),
source=payload.get("source"),
created_at=datetime.fromisoformat(payload["created_at"]),
updated_at=datetime.fromisoformat(payload["updated_at"]),
ttl=payload.get("ttl", 0),
ttl_remaining=ttl_remaining,
refresh_schedule=payload["refresh_schedule"],
user=payload["user"],
))
return scheduled
except Exception as e:
logger.error(f"Failed to get scheduled volatile records: {e}")
return []
async def get_stats(
self,
user: str
) -> Dict[str, Any]:
"""
Get cache statistics for user.
Args:
user: User identifier
Returns:
Statistics dict
"""
collection = self._collection_name(user)
if not await self.qdrant.collection_exists(collection):
return {
"total_records": 0,
"by_namespace": {},
"scheduled_count": 0,
"expired_count": 0,
}
now_ms = self._current_timestamp_ms()
by_namespace: Dict[str, int] = {}
total = 0
scheduled = 0
expired = 0
try:
all_points = await self.qdrant.scroll_all_points(
collection_name=collection,
with_payload=True
)
for point in all_points:
payload = point.get("payload", {})
namespace = payload.get("namespace", "unknown")
ttl_expiry = payload.get("ttl_expiry", 0)
if ttl_expiry <= now_ms:
expired += 1
else:
total += 1
by_namespace[namespace] = by_namespace.get(namespace, 0) + 1
if payload.get("refresh_schedule"):
scheduled += 1
return {
"total_records": total,
"by_namespace": by_namespace,
"scheduled_count": scheduled,
"expired_count": expired,
}
except Exception as e:
logger.error(f"Failed to get volatile stats: {e}")
return {
"total_records": 0,
"by_namespace": {},
"scheduled_count": 0,
"expired_count": 0,
}
async def purge_expired(
self,
user: str
) -> int:
"""
Purge all expired volatile records for user.
Args:
user: User identifier
Returns:
Number of records purged
"""
collection = self._collection_name(user)
if not await self.qdrant.collection_exists(collection):
return 0
now_ms = self._current_timestamp_ms()
return await self.qdrant.delete_expired_vectors(collection, now_ms)
async def purge_all_expired(self) -> Dict[str, int]:
"""
Purge expired records from all volatile collections.
Returns:
Dict of collection -> purged count
"""
collections = await self.qdrant.get_volatile_collections()
results = {}
now_ms = self._current_timestamp_ms()
for collection in collections:
purged = await self.qdrant.delete_expired_vectors(collection, now_ms)
if purged > 0:
results[collection] = purged
logger.info(f"Purged {purged} expired from {collection}")
return results