fix(solver): 傳遞 hypothesis 作為 alert_context 給 OPENCLAW_NEMO

根因：solver 呼叫 openclaw.call(prompt) 不傳 context
→ nemo fallback 把 prompt[:500]（系統說明「軍師 Agent」）
   當 signal description → LLM 回傳垃圾方案描述

修復：把 top.description 放進 alert_context.signals
      讓 nemo 看到真實根因假設（與 diagnostician 同模式 7eb8375）

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

apps/api/src/agents/solver_agent.py

@@ -111,9 +111,21 @@ class SolverAgent(BaseAgent):
             "confidence": top.confidence,
         })
 
+        # 2026-04-16 ogt + Claude Sonnet 4.6: 傳遞 hypothesis 結構化資料給 OPENCLAW_NEMO
+        # 根因：原本 call(prompt) 不傳 context → nemo fallback 把 prompt[:500]（系統說明）
+        #       當 signal description → LLM 回傳「設計修復方案的軍師 Agent」垃圾
+        # 修復：把 top hypothesis description 放進 alert_context.signals 讓 nemo 看到真實診斷
+        _hypothesis_text = (top.description or "（待診斷）")[:800]
+        alert_context = {
+            "incident_id": diagnosis.evidence_snapshot_id or "UNKNOWN",
+            "severity": "P3",
+            "signals": [{"alert_name": "diagnosis_hypothesis", "description": _hypothesis_text}],
+            "affected_services": [],
+        }
+
         from src.services.openclaw import get_openclaw
         openclaw = get_openclaw()
-        response_text, _provider, success = await openclaw.call(prompt)
+        response_text, _provider, success = await openclaw.call(prompt, alert_context=alert_context)
 
         if not success or not response_text:
             return self._degraded_plan(diagnosis, 0, "llm_failed")