fix(diagnostician): 相容 openclaw_nemo 回傳格式 → 解除全面 ABSTAIN

根因: AI Router DIAGNOSE→openclaw_nemo 回傳 ClawBot 格式：
     {"action_title":"...","risk_level":"...","confidence":0.85}
     Diagnostician 只解析 {"hypotheses":[...]} → 永遠 0 hypotheses → ABSTAIN

修復: _extract_hypotheses() 新增 openclaw_nemo 格式檢測與轉換
     action_title→description, confidence→confidence, risk_level→category

影響: 所有 critical alert 自 2026-04-15 收到後一律 ABSTAIN，無任何修復動作

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

apps/api/src/agents/diagnostician_agent.py

@@ -202,7 +202,35 @@ Phase 4 動態異常偵測（AI 主動巡檢結果，可作為高信心佐證）
 # ─────────────────────────────────────────────────────────────────────────────
 
 def _extract_hypotheses(parsed: dict[str, Any]) -> list[Hypothesis]:
-    """從 LLM 解析結果提取假設列表（按信心降序）。"""
+    """從 LLM 解析結果提取假設列表（按信心降序）。
+
+    支援兩種格式：
+    1. 標準格式：{"hypotheses": [{description, confidence, evidence_chain, category}]}
+    2. OpenClaw Nemo 格式：{"action_title": "...", "risk_level": "...", "confidence": 0.85}
+       （openclaw_nemo 呼叫 ClawBot /api/v1/analyze/incident 回傳）
+
+    2026-04-16 ogt + Claude Sonnet 4.6: 修復 openclaw_nemo 格式不相容
+        根因: ai_router DIAGNOSE→openclaw_nemo 回傳 action_title 格式，
+              diagnostician 只解析 hypotheses 格式 → 永遠 0 hypotheses → ABSTAIN
+    """
+    # OpenClaw Nemo 格式轉換（有 action_title 但無 hypotheses）
+    if "action_title" in parsed and "hypotheses" not in parsed:
+        action_title = str(parsed.get("action_title", ""))
+        confidence = float(parsed.get("confidence", 0.5))
+        risk_level = str(parsed.get("risk_level", "medium"))
+        # risk_level → category 映射
+        risk_to_cat = {"critical": "CriticalFailure", "high": "HighRisk",
+                       "medium": "ModerateIssue", "low": "LowRisk"}
+        category = risk_to_cat.get(risk_level.lower(), "Unknown")
+        if action_title and confidence > 0:
+            return [Hypothesis(
+                description=action_title[:500],
+                confidence=confidence,
+                evidence_chain=[],
+                category=category,
+            )]
+        return []
+
     raw = parsed.get("hypotheses", [])
     hypotheses = []
     for item in raw: