Files
EnterpriseArchitect/services/nvidia_sidecar/pool_manager.py
T
vincent 611ebd11a8 feat(sidecar-v2): implement multi-pool provider proxy with cooldown, rate limiting, WebUI
BIZ-52 Step3 开发实现:
- storage: backend/usage/cooldown/config CRUD with SQLite WAL
- crypto: AES-256-GCM API key encryption
- pool_manager: primary/fallback pool routing
- cooldown_manager: 429 exponential backoff cooldown
- rate_limiter: per-backend token bucket RPM control
- router: model → backend routing with pool priority
- proxy: multi-pool request forwarding with retry
- server: FastAPI admin API + OpenAI-compatible proxy + SSE
- dashboard: WebUI with provider CRUD, stats, charts

Co-authored-by: multica-agent <github@multica.ai>
2026-06-25 16:39:01 +08:00

83 lines
3.0 KiB
Python

"""Provider pool management: primary / fallback pool routing."""
import structlog
from typing import Optional
from storage.backend_store import list_backends, get_pool_stats
from storage.models import Backend
logger = structlog.get_logger("sidecar_v2.pool_manager")
class PoolManager:
"""Manages provider pools and selects healthy backends for a given model.
Priority: primary pool → fallback pool.
Within a pool: healthy backends only, sorted by availability.
"""
def __init__(self):
self._pool_order = ["primary", "fallback"]
def get_available_backends(
self, canonical_model: str, pool: Optional[str] = None
) -> list[Backend]:
"""Get all healthy, enabled backends that serve a model, in pool order.
Args:
canonical_model: Canonical model name to match.
pool: Optional pool filter (primary/fallback). None = all pools.
Returns:
List of ready backends sorted by pool priority, then RPM utilization.
"""
backends: list[Backend] = []
pools_to_check = [pool] if pool else self._pool_order
for p in pools_to_check:
pool_backends = list_backends(pool=p, enabled_only=True, decrypt_key=True)
for b in pool_backends:
if b.status == "healthy" and b.has_model(canonical_model):
backends.append(b)
if pool:
break
return backends
def get_any_healthy_backends(self, pool: Optional[str] = None) -> list[Backend]:
"""Get all healthy, enabled backends regardless of model."""
backends: list[Backend] = []
pools_to_check = [pool] if pool else self._pool_order
for p in pools_to_check:
pool_backends = list_backends(pool=p, enabled_only=True, decrypt_key=True)
for b in pool_backends:
if b.status == "healthy":
backends.append(b)
if pool:
break
return backends
def get_pool_status(self) -> dict:
"""Get pool summary for dashboard."""
stats = get_pool_stats()
result = {}
for pool in self._pool_order:
s = stats.get(pool, {"total": 0, "enabled": 0, "healthy": 0, "cooling": 0, "error": 0})
result[pool] = s
# Also include any other pools
for pool, s in stats.items():
if pool not in result:
result[pool] = s
return result
def is_pool_available(self, canonical_model: str, pool: str = "primary") -> bool:
"""Check if a pool has any healthy backends for a model."""
backends = self.get_available_backends(canonical_model, pool=pool)
return len(backends) > 0
def is_any_pool_available(self, canonical_model: str) -> bool:
"""Check if any pool has healthy backends for a model."""
for pool in self._pool_order:
if self.is_pool_available(canonical_model, pool):
return True
return False