fix(ai): remove 188 ollama provider
All checks were successful
Code Review / ai-code-review (push) Successful in 12s
CD Pipeline / tests (push) Successful in 1m13s
CD Pipeline / build-and-deploy (push) Successful in 3m36s
CD Pipeline / post-deploy-checks (push) Successful in 1m20s

This commit is contained in:
Your Name
2026-05-06 14:33:16 +08:00
parent 578bf3bc7c
commit 4111ea4f9f
33 changed files with 193 additions and 233 deletions

View File

@@ -637,7 +637,7 @@ async def _nemoclaw_second_opinion(incident: "Incident", primary_result: dict) -
"""
MCP Phase 4a: NemoClaw second opinion — 信心 < 0.7 時觸發
============================================================
用 deepseek-r1:14b (Ollama 188) 對同一份資料做獨立推理,
用 deepseek-r1:14b (設定的 Ollama primary) 對同一份資料做獨立推理,
輸出純文字 advisory_note不執行任何操作。
2026-04-11 Claude Sonnet 4.6 Asia/Taipei
@@ -696,7 +696,7 @@ async def _generate_playbook_draft_if_new(incident: "Incident") -> None:
MCP Phase 4c: Playbook 無命中時,自動生成 AI 草稿 Playbook 寫入 KM
=====================================================================
- 僅在 KM 中不存在同 alertname 的 Playbook 時觸發(避免重複)
- 用 qwen2.5:7b-instruct (Ollama 188) 生成結構化 Playbook 草稿
- 用 qwen2.5:7b-instruct (設定的 Ollama primary) 生成結構化 Playbook 草稿
- 寫入 KnowledgeEntrystatus=DRAFT需人工審核後升為 APPROVED
- 寫入 AlertOperationLog PLAYBOOK_DRAFT_CREATED 事件