vincent/EnterpriseArchitect
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(sidecar-v2): implement multi-pool provider proxy with cooldown, rate limiting, WebUI

Browse Source 
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>
This commit is contained in:
bizwings
2026-06-25 16:39:01 +08:00
parent 4fd89b038d
commit 611ebd11a8
19 changed files with 3034 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
services/nvidia_sidecar/__init__.py
+1
View File
@@ -0,0 +1 @@
"""Sidecar V2 — Multi-pool provider proxy with cooldown, rate limiting, and WebUI management."""