OG T
|
5ad403b287
|
fix(p0): v4.3 — 實測確認 Ollama CPU-only 不可用,DIAGNOSE 統一走 NIM
實測依據 (2026-04-05):
- Ollama llama3.2:3b CPU-only: 238s 回 {"ok":true},生產不可用
- Nemotron NIM: 2.2s~27.3s,avg 10.6s,一直是主力(Phase 22 起)
- NIM 從未有隱私問題,Incident 資料一直送雲端 GPU
變更:
- ai_router.py: _local_fallback_chain 廢棄(空 list)
- ai_router.py: DIAGNOSE route/route_sync 改回 _full_fallback_chain
- config.py: 更新 timeout 說明反映實測結果
- test_p0_diagnose_routing.py: 更新 docstring
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-04-05 01:49:06 +08:00 |
|
OG T
|
8056be5847
|
feat(ai-router): DIAGNOSE intent override 升級至 Nemotron (P0)
|
2026-04-04 17:41:45 +08:00 |
|
OG T
|
671974dedb
|
test(ai-router): TestLocalFallbackChain — require_local 隱私邊界驗證 (P0)
CD Pipeline / build-and-deploy (push) Failing after 43s
新增兩個測試:cloud provider 被跳過 + 全失敗回傳 local_providers_unavailable。
實作邏輯已存在於 AIRouterExecutor.execute()(2026-04-04 ogt Phase 25 P0)。
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-04-04 17:32:32 +08:00 |
|
OG T
|
ffd679f5d3
|
feat(nemotron): per-task timeout,DIAGNOSE 使用獨立 timeout 設定 (P0)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-04-04 16:58:23 +08:00 |
|