fix: rescue gcp ollama through proxy
All checks were successful
CD Pipeline / deploy (push) Successful in 1m9s
All checks were successful
CD Pipeline / deploy (push) Successful in 1m9s
This commit is contained in:
@@ -317,3 +317,10 @@
|
||||
- V10.625 將 GCP embedding failure circuit 狀態公開為 `is_embedding_gcp_circuit_open()` / `embedding_gcp_circuit_remaining_seconds()`,讓 worker 可用明確狀態判斷,不再猜測空向量原因。
|
||||
- `OpenClawLearningService` worker 在熔斷中不 claim 新任務;若處理中開啟熔斷,當筆與同批剩餘任務會退回 `pending` 並寫入延後原因,不扣 `attempts`、不刷成 `failed`。
|
||||
- 背景 embedding 仍維持 GCP-A → GCP-B,不落 111;111 不承接 `bge-m3` 背景批次的治理規則不變。
|
||||
|
||||
## 29. 2026-06-18 V10.626 GCP-A direct timeout 改走 110 proxy rescue
|
||||
|
||||
- 正式診斷腳本顯示:188 直連 GCP-A `34.143.170.20:11434` `/api/version` timeout,但 GCP-B direct、111、110 `11435` primary proxy、110 `11436` secondary proxy 都可用;GCP-B `bge-m3` embed 實測約 2.9 秒。
|
||||
- V10.626 新增 `OLLAMA_HOST_PRIMARY_PROXY` / `OLLAMA_HOST_SECONDARY_PROXY`,預設為 `http://192.168.0.110:11435` / `http://192.168.0.110:11436`。
|
||||
- `resolve_ollama_host()` 順序調整為 GCP-A direct → GCP-A via 110 proxy → GCP-B direct → GCP-B via 110 proxy → 111;proxy rescue 是同順位入口救援,不代表 direct GCP host 已恢復。
|
||||
- 近 24 小時 `ai_calls` 只有 `ollama_secondary=51`、`gcp_ollama=3`、`nim=1`,沒有 Gemini provider;Gemini hard disabled / fallback disabled 的紅線仍有效。
|
||||
|
||||
Reference in New Issue
Block a user