OG T
5f9a6a7e55
fix(ai): 移除假信心分數 + 顯示 AI 模型來源
問題: AI 仲裁顯示硬編碼信心分數 (0.75/0.88/0.92/0.70)
修復:
- decision_manager: 預設 confidence 0.75 → 0.0
- decision_manager: Expert System confidence=0.0 + is_rule_based
- openclaw: 所有 Mock Response confidence → 0.0
- telegram_gateway: 新增 ai_provider 欄位
- telegram_gateway: 動態來源標籤 (Ollama/Gemini/Claude/規則匹配)
Telegram 卡片顯示:
- confidence > 0 + provider=ollama → 🤖 Ollama 仲裁
- confidence > 0 + provider=gemini → 🤖 Gemini 仲裁
- confidence > 0 + provider=claude → 🤖 Claude 仲裁
- confidence == 0 → ⚙️ 規則匹配
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-03-29 15:19:51 +08:00
..
2026-03-26 16:06:20 +08:00
2026-03-26 16:06:20 +08:00
2026-03-29 01:48:59 +08:00
2026-03-29 15:19:51 +08:00
2026-03-29 11:28:33 +08:00
2026-03-22 18:57:44 +08:00
2026-03-22 18:57:44 +08:00
2026-03-23 18:40:36 +08:00
2026-03-22 18:57:44 +08:00
2026-03-29 01:24:17 +08:00
2026-03-26 19:13:03 +08:00
2026-03-22 18:57:44 +08:00
2026-03-26 00:32:19 +08:00