379 lines
10 KiB
Python
379 lines
10 KiB
Python
|
"""
|
||
|
|
Redis cache layer for monitoring data.
|
||
|
|
[AC-AISVC-91, AC-AISVC-92] Redis-based caching for Dashboard statistics.
|
||
|
|
"""
|
||
|
|
|
||
|
|
import json
|
||
|
|
import logging
|
||
|
|
from datetime import datetime
|
||
|
|
from typing import Any
|
||
|
|
|
||
|
|
import redis.asyncio as redis
|
||
|
|
|
||
|
|
from app.core.config import get_settings
|
||
|
|
|
||
|
|
logger = logging.getLogger(__name__)
|
||
|
|
|
||
|
|
|
||
|
|
class MonitoringCache:
|
||
|
|
"""
|
||
|
|
[AC-AISVC-91, AC-AISVC-92] Redis cache layer for monitoring data.
|
||
|
|
|
||
|
|
Features:
|
||
|
|
- Dashboard stats caching (60s TTL)
|
||
|
|
- Incremental counters (90 days TTL)
|
||
|
|
- Top N leaderboards
|
||
|
|
"""
|
||
|
|
|
||
|
|
def __init__(self, redis_client: redis.Redis | None = None):
|
||
|
|
self._redis = redis_client
|
||
|
|
self._settings = get_settings()
|
||
|
|
self._enabled = self._settings.redis_enabled
|
||
|
|
|
||
|
|
async def _get_client(self) -> redis.Redis | None:
|
||
|
|
if not self._enabled:
|
||
|
|
return None
|
||
|
|
if self._redis is None:
|
||
|
|
try:
|
||
|
|
self._redis = redis.from_url(
|
||
|
|
self._settings.redis_url,
|
||
|
|
encoding="utf-8",
|
||
|
|
decode_responses=True,
|
||
|
|
)
|
||
|
|
except Exception as e:
|
||
|
|
logger.warning(f"[MonitoringCache] Failed to connect to Redis: {e}")
|
||
|
|
self._enabled = False
|
||
|
|
return None
|
||
|
|
return self._redis
|
||
|
|
|
||
|
|
async def incr_counter(
|
||
|
|
self,
|
||
|
|
tenant_id: str,
|
||
|
|
metric: str,
|
||
|
|
date: str | None = None,
|
||
|
|
) -> int:
|
||
|
|
"""
|
||
|
|
Increment a counter atomically.
|
||
|
|
|
||
|
|
Key format: stats:{tenant_id}:counter:{metric}:{date}
|
||
|
|
TTL: 90 days (7776000 seconds)
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tenant_id: Tenant ID for isolation
|
||
|
|
metric: Metric name (e.g., 'intent_hit', 'template_use', 'flow_activate', 'guardrail_block')
|
||
|
|
date: Date string (YYYY-MM-DD), defaults to today
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
New counter value
|
||
|
|
"""
|
||
|
|
client = await self._get_client()
|
||
|
|
if client is None:
|
||
|
|
return 0
|
||
|
|
|
||
|
|
if date is None:
|
||
|
|
date = datetime.utcnow().strftime("%Y-%m-%d")
|
||
|
|
|
||
|
|
key = f"stats:{tenant_id}:counter:{metric}:{date}"
|
||
|
|
|
||
|
|
try:
|
||
|
|
count = await client.incr(key)
|
||
|
|
await client.expire(key, self._settings.stats_counter_ttl)
|
||
|
|
return count
|
||
|
|
except Exception as e:
|
||
|
|
logger.warning(f"[MonitoringCache] Failed to increment counter: {e}")
|
||
|
|
return 0
|
||
|
|
|
||
|
|
async def incr_counter_by(
|
||
|
|
self,
|
||
|
|
tenant_id: str,
|
||
|
|
metric: str,
|
||
|
|
amount: int,
|
||
|
|
date: str | None = None,
|
||
|
|
) -> int:
|
||
|
|
"""
|
||
|
|
Increment a counter by a specific amount atomically.
|
||
|
|
|
||
|
|
Key format: stats:{tenant_id}:counter:{metric}:{date}
|
||
|
|
TTL: 90 days
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tenant_id: Tenant ID for isolation
|
||
|
|
metric: Metric name
|
||
|
|
amount: Amount to increment by
|
||
|
|
date: Date string (YYYY-MM-DD), defaults to today
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
New counter value
|
||
|
|
"""
|
||
|
|
client = await self._get_client()
|
||
|
|
if client is None:
|
||
|
|
return 0
|
||
|
|
|
||
|
|
if date is None:
|
||
|
|
date = datetime.utcnow().strftime("%Y-%m-%d")
|
||
|
|
|
||
|
|
key = f"stats:{tenant_id}:counter:{metric}:{date}"
|
||
|
|
|
||
|
|
try:
|
||
|
|
count = await client.incrby(key, amount)
|
||
|
|
await client.expire(key, self._settings.stats_counter_ttl)
|
||
|
|
return count
|
||
|
|
except Exception as e:
|
||
|
|
logger.warning(f"[MonitoringCache] Failed to increment counter: {e}")
|
||
|
|
return 0
|
||
|
|
|
||
|
|
async def get_counter(
|
||
|
|
self,
|
||
|
|
tenant_id: str,
|
||
|
|
metric: str,
|
||
|
|
date: str | None = None,
|
||
|
|
) -> int:
|
||
|
|
"""
|
||
|
|
Get counter value.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tenant_id: Tenant ID for isolation
|
||
|
|
metric: Metric name
|
||
|
|
date: Date string (YYYY-MM-DD), defaults to today
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
Counter value (0 if not found)
|
||
|
|
"""
|
||
|
|
client = await self._get_client()
|
||
|
|
if client is None:
|
||
|
|
return 0
|
||
|
|
|
||
|
|
if date is None:
|
||
|
|
date = datetime.utcnow().strftime("%Y-%m-%d")
|
||
|
|
|
||
|
|
key = f"stats:{tenant_id}:counter:{metric}:{date}"
|
||
|
|
|
||
|
|
try:
|
||
|
|
value = await client.get(key)
|
||
|
|
return int(value) if value else 0
|
||
|
|
except Exception as e:
|
||
|
|
logger.warning(f"[MonitoringCache] Failed to get counter: {e}")
|
||
|
|
return 0
|
||
|
|
|
||
|
|
async def get_dashboard_stats(
|
||
|
|
self,
|
||
|
|
tenant_id: str,
|
||
|
|
) -> dict[str, Any] | None:
|
||
|
|
"""
|
||
|
|
Get cached Dashboard statistics.
|
||
|
|
|
||
|
|
Key format: stats:{tenant_id}:dashboard
|
||
|
|
TTL: 60 seconds
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tenant_id: Tenant ID for isolation
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
Cached stats dict or None if not found
|
||
|
|
"""
|
||
|
|
client = await self._get_client()
|
||
|
|
if client is None:
|
||
|
|
return None
|
||
|
|
|
||
|
|
key = f"stats:{tenant_id}:dashboard"
|
||
|
|
|
||
|
|
try:
|
||
|
|
data = await client.get(key)
|
||
|
|
if data:
|
||
|
|
return json.loads(data)
|
||
|
|
return None
|
||
|
|
except Exception as e:
|
||
|
|
logger.warning(f"[MonitoringCache] Failed to get dashboard stats: {e}")
|
||
|
|
return None
|
||
|
|
|
||
|
|
async def set_dashboard_stats(
|
||
|
|
self,
|
||
|
|
tenant_id: str,
|
||
|
|
stats: dict[str, Any],
|
||
|
|
) -> bool:
|
||
|
|
"""
|
||
|
|
Set Dashboard statistics cache.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tenant_id: Tenant ID for isolation
|
||
|
|
stats: Stats dict to cache
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
True if successful, False otherwise
|
||
|
|
"""
|
||
|
|
client = await self._get_client()
|
||
|
|
if client is None:
|
||
|
|
return False
|
||
|
|
|
||
|
|
key = f"stats:{tenant_id}:dashboard"
|
||
|
|
|
||
|
|
try:
|
||
|
|
await client.setex(
|
||
|
|
key,
|
||
|
|
self._settings.dashboard_cache_ttl,
|
||
|
|
json.dumps(stats, default=str),
|
||
|
|
)
|
||
|
|
return True
|
||
|
|
except Exception as e:
|
||
|
|
logger.warning(f"[MonitoringCache] Failed to set dashboard stats: {e}")
|
||
|
|
return False
|
||
|
|
|
||
|
|
async def invalidate_dashboard_stats(
|
||
|
|
self,
|
||
|
|
tenant_id: str,
|
||
|
|
) -> bool:
|
||
|
|
"""
|
||
|
|
Invalidate Dashboard statistics cache.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tenant_id: Tenant ID for isolation
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
True if successful, False otherwise
|
||
|
|
"""
|
||
|
|
client = await self._get_client()
|
||
|
|
if client is None:
|
||
|
|
return False
|
||
|
|
|
||
|
|
key = f"stats:{tenant_id}:dashboard"
|
||
|
|
|
||
|
|
try:
|
||
|
|
await client.delete(key)
|
||
|
|
return True
|
||
|
|
except Exception as e:
|
||
|
|
logger.warning(f"[MonitoringCache] Failed to invalidate dashboard stats: {e}")
|
||
|
|
return False
|
||
|
|
|
||
|
|
async def add_to_leaderboard(
|
||
|
|
self,
|
||
|
|
tenant_id: str,
|
||
|
|
leaderboard: str,
|
||
|
|
member: str,
|
||
|
|
score: float,
|
||
|
|
) -> bool:
|
||
|
|
"""
|
||
|
|
Add/update a member in a leaderboard (sorted set).
|
||
|
|
|
||
|
|
Key format: stats:{tenant_id}:leaderboard:{name}
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tenant_id: Tenant ID for isolation
|
||
|
|
leaderboard: Leaderboard name (e.g., 'intent_rules', 'templates', 'flows')
|
||
|
|
member: Member identifier
|
||
|
|
score: Score value
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
True if successful
|
||
|
|
"""
|
||
|
|
client = await self._get_client()
|
||
|
|
if client is None:
|
||
|
|
return False
|
||
|
|
|
||
|
|
key = f"stats:{tenant_id}:leaderboard:{leaderboard}"
|
||
|
|
|
||
|
|
try:
|
||
|
|
await client.zadd(key, {member: score})
|
||
|
|
await client.expire(key, self._settings.stats_counter_ttl)
|
||
|
|
return True
|
||
|
|
except Exception as e:
|
||
|
|
logger.warning(f"[MonitoringCache] Failed to add to leaderboard: {e}")
|
||
|
|
return False
|
||
|
|
|
||
|
|
async def get_leaderboard(
|
||
|
|
self,
|
||
|
|
tenant_id: str,
|
||
|
|
leaderboard: str,
|
||
|
|
limit: int = 5,
|
||
|
|
desc: bool = True,
|
||
|
|
) -> list[tuple[str, float]]:
|
||
|
|
"""
|
||
|
|
Get top N members from a leaderboard.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tenant_id: Tenant ID for isolation
|
||
|
|
leaderboard: Leaderboard name
|
||
|
|
limit: Maximum number of results
|
||
|
|
desc: Sort descending (highest first)
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
List of (member, score) tuples
|
||
|
|
"""
|
||
|
|
client = await self._get_client()
|
||
|
|
if client is None:
|
||
|
|
return []
|
||
|
|
|
||
|
|
key = f"stats:{tenant_id}:leaderboard:{leaderboard}"
|
||
|
|
|
||
|
|
try:
|
||
|
|
if desc:
|
||
|
|
results = await client.zrevrangebyscore(
|
||
|
|
key,
|
||
|
|
min=0,
|
||
|
|
max=float("inf"),
|
||
|
|
start=0,
|
||
|
|
num=limit,
|
||
|
|
withscores=True,
|
||
|
|
)
|
||
|
|
else:
|
||
|
|
results = await client.zrangebyscore(
|
||
|
|
key,
|
||
|
|
min=0,
|
||
|
|
max=float("inf"),
|
||
|
|
start=0,
|
||
|
|
num=limit,
|
||
|
|
withscores=True,
|
||
|
|
)
|
||
|
|
return results
|
||
|
|
except Exception as e:
|
||
|
|
logger.warning(f"[MonitoringCache] Failed to get leaderboard: {e}")
|
||
|
|
return []
|
||
|
|
|
||
|
|
async def incr_leaderboard_member(
|
||
|
|
self,
|
||
|
|
tenant_id: str,
|
||
|
|
leaderboard: str,
|
||
|
|
member: str,
|
||
|
|
increment: float = 1.0,
|
||
|
|
) -> bool:
|
||
|
|
"""
|
||
|
|
Increment a member's score in a leaderboard.
|
||
|
|
|
||
|
|
Args:
|
||
|
|
tenant_id: Tenant ID for isolation
|
||
|
|
leaderboard: Leaderboard name
|
||
|
|
member: Member identifier
|
||
|
|
increment: Amount to increment
|
||
|
|
|
||
|
|
Returns:
|
||
|
|
True if successful
|
||
|
|
"""
|
||
|
|
client = await self._get_client()
|
||
|
|
if client is None:
|
||
|
|
return False
|
||
|
|
|
||
|
|
key = f"stats:{tenant_id}:leaderboard:{leaderboard}"
|
||
|
|
|
||
|
|
try:
|
||
|
|
await client.zincrby(key, increment, member)
|
||
|
|
await client.expire(key, self._settings.stats_counter_ttl)
|
||
|
|
return True
|
||
|
|
except Exception as e:
|
||
|
|
logger.warning(f"[MonitoringCache] Failed to incr leaderboard member: {e}")
|
||
|
|
return False
|
||
|
|
|
||
|
|
async def close(self) -> None:
|
||
|
|
"""Close Redis connection."""
|
||
|
|
if self._redis:
|
||
|
|
await self._redis.close()
|
||
|
|
|
||
|
|
|
||
|
|
_monitoring_cache: MonitoringCache | None = None
|
||
|
|
|
||
|
|
|
||
|
|
def get_monitoring_cache() -> MonitoringCache:
|
||
|
|
"""Get singleton MonitoringCache instance."""
|
||
|
|
global _monitoring_cache
|
||
|
|
if _monitoring_cache is None:
|
||
|
|
_monitoring_cache = MonitoringCache()
|
||
|
|
return _monitoring_cache
|