wooo/awoooi
1
1
Fork 0
Code Issues 2 Pull Requests 1 Actions 3 Packages Projects Releases Wiki Activity

fix(chat+nim): 修復首席架構師 Review I1-I4 + S3 四項重要問題
All checks were successful
CD Pipeline / build-and-deploy (push) Successful in 7m9s
Details

Browse Source 
I1: chat_manager._call_openclaw timeout=30.0 → 讀 settings.OPENCLAW_TIMEOUT
I2: nvidia_provider.py stale comment "45" → "55" 對齊 ConfigMap
I3: asyncio.shield 移除 — shield 超時後 task 繼續跑但無人等待 (silent leak)
I4: ChatManager.__init__ 移除 repo 實例 (leWOOOgo 禁 Service 持有 repository)
S3: _check_nemotron_health probe 10s → 25s + /v1/models 輕量端點

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
OG T
2026-04-03 16:36:16 +08:00
parent be247d6c5c
commit 15aabd6ac5
4 changed files with 51 additions and 16 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
apps/api/src/services/nvidia_provider.py
View File

@@ -119,7 +119,7 @@ NVIDIA_DEFAULT_MODEL = "nvidia/nemotron-mini-4b-instruct"
# 請求超時 (秒)
# 2026-04-01 ogt: 設為 30s (平衡點)
# 2026-04-03 ogt: 改從 config 讀取，與 NEMOTRON_TIMEOUT_SECONDS=45 對齊
# 2026-04-03 ogt: 改從 config 讀取，與 NEMOTRON_TIMEOUT_SECONDS=55 對齊
# Memory 記載 NIM 免費 tier 延遲 11-45s，30s 硬編碼導致慢請求全超時
def _get_nvidia_timeout() -> float:
try: