fix(openclaw): Nemotron 重試邏輯 + exhausted log key (未提交的修改)

- generate_incident_proposal_with_tools: 單次 try/except → 2次重試迴圈
- 失敗 log key: nemotron_collaboration_failed → nemotron_collaboration_exhausted
- 失敗時 nemotron_enabled=True (讓統帥看到失敗狀態)
- _call_nemotron_tools: timeout 超時改為拋出異常(讓外層重試)
- 這是之前 Session 的本地修改，修正測試與實際實作不一致問題

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

apps/api/src/services/openclaw.py

@@ -1635,45 +1635,66 @@ Focus on:
             )
             return proposal, provider, True
 
-        # Step 3: 呼叫 Nemotron Tool Calling
+        # Step 3: 呼叫 Nemotron Tool Calling — 🔴 必須等到有結果，不可跳過
+        # 2026-04-07 ogt: 統帥指示 Nemotron 不能跳過，必須等到處理完成
         logger.info(
             "nemotron_collaboration_start",
             incident_id=incident_id,
             risk_level=risk_level,
         )
 
-        try:
-            nemotron_result = await self._call_nemotron_tools(
-                incident_id=incident_id,
-                reasoning=proposal.get("reasoning", ""),
-                target_resource=proposal.get("target_resource", ""),
-                suggested_action=proposal.get("action", ""),
-                namespace=proposal.get("namespace", "awoooi-prod"),
-            )
+        max_retries = 2
+        last_error = None
+        for attempt in range(1, max_retries + 1):
+            try:
+                nemotron_result = await self._call_nemotron_tools(
+                    incident_id=incident_id,
+                    reasoning=proposal.get("reasoning", ""),
+                    target_resource=proposal.get("target_resource", ""),
+                    suggested_action=proposal.get("action", ""),
+                    namespace=proposal.get("namespace", "awoooi-prod"),
+                )
 
-            proposal["nemotron_enabled"] = True
-            proposal["nemotron_tools"] = nemotron_result.get("tools", [])
-            proposal["nemotron_validation"] = nemotron_result.get("validation", "⏳ 驗證中")
-            proposal["nemotron_latency_ms"] = nemotron_result.get("latency_ms", 0.0)
+                proposal["nemotron_enabled"] = True
+                proposal["nemotron_tools"] = nemotron_result.get("tools", [])
+                proposal["nemotron_validation"] = nemotron_result.get("validation", "⏳ 驗證中")
+                proposal["nemotron_latency_ms"] = nemotron_result.get("latency_ms", 0.0)
 
-            logger.info(
-                "nemotron_collaboration_complete",
-                incident_id=incident_id,
-                tools_count=len(proposal["nemotron_tools"]),
-                validation=proposal["nemotron_validation"],
-                latency_ms=proposal["nemotron_latency_ms"],
-            )
+                logger.info(
+                    "nemotron_collaboration_complete",
+                    incident_id=incident_id,
+                    tools_count=len(proposal["nemotron_tools"]),
+                    validation=proposal["nemotron_validation"],
+                    latency_ms=proposal["nemotron_latency_ms"],
+                    attempt=attempt,
+                )
+                last_error = None
+                break  # 成功，跳出重試迴圈
 
-        except Exception as e:
-            # Nemotron 失敗不阻塞主流程，降級為純 OpenClaw
-            logger.warning(
-                "nemotron_collaboration_failed",
+            except Exception as e:
+                last_error = e
+                logger.warning(
+                    "nemotron_collaboration_retry",
+                    incident_id=incident_id,
+                    error=str(e),
+                    attempt=attempt,
+                    max_retries=max_retries,
+                )
+                if attempt < max_retries:
+                    import asyncio
+                    await asyncio.sleep(2)  # 重試前等 2 秒
+
+        # 重試全部失敗 — 仍然標記 enabled 並顯示失敗狀態（不隱藏）
+        if last_error is not None:
+            logger.error(
+                "nemotron_collaboration_exhausted",
                 incident_id=incident_id,
-                error=str(e),
+                error=str(last_error),
+                retries=max_retries,
             )
-            proposal["nemotron_enabled"] = False
-            proposal["nemotron_tools"] = None
-            proposal["nemotron_validation"] = "❌ 呼叫失敗"
+            proposal["nemotron_enabled"] = True  # 🔴 仍然顯示區塊，讓統帥知道失敗了
+            proposal["nemotron_tools"] = []
+            proposal["nemotron_validation"] = f"❌ {max_retries}次重試均失敗"
             proposal["nemotron_latency_ms"] = 0.0
 
         return proposal, provider, True
@@ -1776,8 +1797,8 @@ Focus on:
         ]
 
         try:
-            # 設置超時
-            timeout = settings.NEMOTRON_TIMEOUT_SECONDS
+            # 2026-04-07 ogt: 統帥指示不可跳過 Nemotron，用 120 秒寬裕超時
+            timeout = 120
 
             result = await asyncio.wait_for(
                 nvidia.tool_call(
@@ -1822,16 +1843,13 @@ Focus on:
 
         except asyncio.TimeoutError:
             latency_ms = (time.time() - start_time) * 1000
-            logger.warning(
+            logger.error(
                 "nemotron_tool_call_timeout",
                 incident_id=incident_id,
-                timeout_seconds=settings.NEMOTRON_TIMEOUT_SECONDS,
+                timeout_seconds=timeout,
             )
-            return {
-                "tools": [],
-                "validation": "⏳ 呼叫超時",
-                "latency_ms": latency_ms,
-            }
+            # 超時也拋出，讓外層重試
+            raise
 
         except Exception as e:
             latency_ms = (time.time() - start_time) * 1000