ogt 7fbeaaf213
All checks were successful
CD Pipeline / deploy (push) Successful in 1m16s
fix(ai-ops): Hermes L1 移除過緊 timeout + keep_alive 常駐
問題盤點(2026-04-19 實地 SSH 111:11434):
- 我原本設 HERMES_TIMEOUT=30 是人為限制,AI 推理不該被綁
- 111 Ollama 實況:9 個模型共享,deepseek-r1:14b 會佔 VRAM
- hermes3 冷啟動 30+s(切換)/ warm 後 <1s(40x 差距)
- 30s timeout → 冷啟動必中 → 誤判 AI 掛 → 人為降級

修正:
- HERMES_TIMEOUT default 30 → 180(HERMES_TIMEOUT=0 代表無限制)
- 新增 keep_alive=24h payload,讓 hermes3 常駐 VRAM
  避免被其他客戶端(deepseek-r1 等)切換觸發冷啟動
- Memory reference_env_map.md 更新 111 實況(9 模型清單、切換陷阱、
  ADR-012 呼叫設定)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-19 14:25:28 +08:00
Description
EwoooC — 商品看板 + 業績報表 + AI KM (Flask + pgvector, Docker Compose on 188)
37 MiB
Languages
PostScript 59.7%
Python 30.9%
HTML 4.2%
CSS 2.1%
JavaScript 1.9%
Other 1.1%