Merge pull request 'fix(CI): notify竞态修复 + 双倍触发去重 (PR #12 rebase, reviewed & approved)' (#14) from fix/ci-dedup-v2 into main

.gitea/workflows/ci.yml

@@ -1,9 +1,10 @@
 # CI 管道 — moziplus v2.0
 #
 # 触发条件：
-#   - push（非 main 分支）
 #   - pull_request（opened, synchronize）
 #
+# 注意：只保留 pull_request 触发，避免 push + pull_request 双倍触发
+#
 # Gitea v1.23.4 限制注意：
 #   - 不支持 failure() 表达式，用 always() + shell 条件判断替代
 #   - 不支持 concurrency / continue-on-error / timeout-minutes / permissions
@@ -13,10 +14,6 @@
 name: CI
 
 on:
-  push:
-    branches:
-      - '**'
-      - '!main'
   pull_request:
     types: [opened, synchronize]
 
@@ -53,7 +50,8 @@ jobs:
           /tmp/ci-venv-test/bin/pytest tests/ -m "not e2e" -x -q
 
   # ── Job 3: CI 失败通知 ───────────────────────────────
-  # v1.23 不支持 failure()，用 always() + shell 检查 commit status 替代
+  # 使用 needs.<job>.result 直接判断，不查询 commit status API
+  # 根因：notify 自身的 pending status 会污染 commit status 查询结果（竞态条件）
   notify-on-failure:
     runs-on: macos-arm64
     needs: [lint, test]
@@ -62,31 +60,34 @@ jobs:
       - name: Check results and notify
         env:
           GITEA_TOKEN: ${{ secrets.GITEA_TOKEN }}
+          LINT_RESULT: ${{ needs.lint.result }}
+          TEST_RESULT: ${{ needs.test.result }}
         run: |
-          # 查询当前 commit 的 status
-          STATUS=$(curl -sf \
-            -H "Authorization: token $GITEA_TOKEN" \
-            "${{ gitea.api_url }}/repos/${{ gitea.repository }}/commits/${{ gitea.sha }}/status" \
-            | python3 -c "import sys,json; print(json.load(sys.stdin).get('state',''))" 2>/dev/null || echo "")
+          echo "Lint result: $LINT_RESULT"
+          echo "Test result: $TEST_RESULT"
 
-          echo "Commit status: $STATUS"
-
-          if [ "$STATUS" != "success" ]; then
-            echo "CI failed or status unknown, sending notification..."
+          # 只有 lint 或 test 明确失败时才发通知
+          if [ "$LINT_RESULT" = "failure" ] || [ "$TEST_RESULT" = "failure" ]; then
+            echo "CI has failures, sending notification..."
 
             # 如果是 PR 事件，写评论通知
             PR_NUMBER="${{ gitea.event.pull_request.number }}"
             if [ -n "$PR_NUMBER" ]; then
+              # 构建失败摘要
+              FAILED_JOBS=""
+              [ "$LINT_RESULT" = "failure" ] && FAILED_JOBS="${FAILED_JOBS}lint "
+              [ "$TEST_RESULT" = "failure" ] && FAILED_JOBS="${FAILED_JOBS}test "
+
               curl -sf -X POST \
                 -H "Authorization: token $GITEA_TOKEN" \
                 -H "Content-Type: application/json" \
                 "${{ gitea.api_url }}/repos/${{ gitea.repository }}/issues/${PR_NUMBER}/comments" \
-                -d "{\"body\": \"[CI] 失败\\n\\n分支: ${{ gitea.ref_name }}\\n触发 commit: \`${{ gitea.sha }}\`\\n请检查 CI 日志并修复。\"}" \
+                -d "{\"body\": \"[CI] 失败\\n\\n分支: ${{ gitea.ref_name }}\\n触发 commit: \`${{ gitea.sha }}\`\\n失败 Job: ${FAILED_JOBS}\\n请检查 CI 日志并修复。\"}" \
                 || echo "Failed to post PR comment"
               echo "PR comment posted."
             else
               echo "Not a PR event, skipping PR comment."
             fi
           else
-            echo "CI passed, no notification needed."
+            echo "No explicit failures (results: lint=$LINT_RESULT, test=$TEST_RESULT), no notification needed."
           fi

src/daemon/spawner.py

@@ -15,7 +15,7 @@ from datetime import datetime
 from pathlib import Path
 from typing import Any, Dict, List, Optional
 
-from src.blackboard.db import get_connection
+from src.blackboard.db import get_connection, init_db
 
 logger = logging.getLogger("moziplus-v2.spawner")
 
@@ -163,7 +163,6 @@ class AgentBusyError(Exception):
 
     #07: reason 字段区分具体原因,便于 dispatcher 层区分处理。
     """
-
     def __init__(self, agent_id: str, reason: str = "busy", detail: Optional[dict] = None):
         self.agent_id = agent_id
         self.reason = reason   # counter_blocked / session_locked / session_running / session_compacting / session_stuck
@@ -300,7 +299,7 @@ class AgentSpawner:
             project_id, agent_id)
 
     def _build_minimal_fallback(self, task_id, title, description, must_haves,
-                                project_id, agent_id):
+                             project_id, agent_id):
         """最小 fallback:只有任务上下文 + API 指令"""
         task_section = f"""## 任务
 {title}
@@ -312,7 +311,7 @@ class AgentSpawner:
         return task_section + "\n\n---\n\n" + api_section
 
     def _build_api_section(self, project_id: str, task_id: str,
-                           agent_id: str) -> str:
+                            agent_id: str) -> str:
         """构建 API 回写操作指令(BootstrapBuilder 模式下补充)"""
         # mail 任务直接 done,不走 review
         success_status = '"done"' if project_id == "_mail" else '"review"'
@@ -338,8 +337,8 @@ curl -X POST http://{self.api_host}:{self.api_port}/api/projects/{project_id}/ta
 """
 
     def _build_discussion_prompt(self, task_id: str, title: str,
-                                 description: str, must_haves: str,
-                                 project_id: str, agent_id: str) -> str:
+                                  description: str, must_haves: str,
+                                  project_id: str, agent_id: str) -> str:
         """构建讨论类 spawn prompt(§3.3 框架 + Boids)"""
         goal_snapshot = description or title
         constraints = must_haves or "(无特殊约束)"
@@ -380,8 +379,9 @@ curl -X POST http://{self.api_host}:{self.api_port}/api/projects/{project_id}/ta
             return router.agent_profiles.get(agent_id)
         return None
 
+
     def _build_mail_prompt(self, task_id: str, title: str, description: str,
-                           must_haves: str, agent_id: str) -> str:
+                            must_haves: str, agent_id: str) -> str:
         """构建 Mail 专用精简模板"""
         # 解析 must_haves 获取 from 和 performative
         from_agent = agent_id
@@ -575,7 +575,7 @@ curl -X POST http://{self.api_host}:{self.api_port}/api/projects/{project_id}/ta
                 stderr=asyncio.subprocess.PIPE,
             )
             self._register_session(session_id, agent_id, task_id, proc.pid,
-                                   broadcast_task_ids=broadcast_task_ids)
+                                     broadcast_task_ids=broadcast_task_ids)
             logger.info("Spawned agent %s (session=%s, pid=%d)",
                         agent_id, session_id, proc.pid)
 
@@ -848,10 +848,13 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
             #      A8(gateway_unreachable), A11(lock_conflict),
             #      A10(compact_failed), A12(agent_error)
             # v2.8.1 Fix-3a: crash 类 outcome 设 cooldown,给 agent session 恢复时间
-            if outcome in ("crashed", "compact_failed", "process_crash", "session_stuck",
+            if outcome == "crashed" and self.counter:
+                self.counter.set_cooldown(agent_id, seconds=60)
+                logger.info("Crash cooldown set for %s: 60s (outcome=%s)", agent_id, outcome)
+            elif outcome in ("compact_failed", "process_crash", "session_stuck",
                            "compact_hanging", "agent_error", "compact_interrupted") and self.counter:
                 self.counter.set_cooldown(agent_id, seconds=300)  # 5 分钟
-                logger.info("Crash/error cooldown set for %s: 300s (outcome=%s)", agent_id, outcome)
+                logger.info("Error cooldown set for %s: 300s (outcome=%s)", agent_id, outcome)
             # F1: 不可恢复 outcome → 立刻标 failed + 写黑板
             if outcome in ("auth_failed", "agent_error") and db_path and task_id:
                 logger.error("Task %s: unrecoverable outcome=%s, marking failed immediately", task_id, outcome)
@@ -878,6 +881,9 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
         except Exception:
             pass
 
+        stderr_text = b"".join(stderr_chunks).decode("utf-8", errors="replace")
+
+        # 检查 session 状态
         state = self._check_session_state(agent_id)
 
         # B1: 假死 - 先复活,连续假死 ≥2 次再 failed
@@ -1213,7 +1219,7 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
         实测 50KB 在长对话中不够（compact 记录被推出窗口导致漏检）。
         正常扫描量不变：从尾部往前扫，遇到超过 15min 的 timestamp 即 break。
         """
-        if not session_file or not Path(session_file).exists():
+        if not session_file or not pathlib.Path(session_file).exists():
             return False
         try:
             from datetime import datetime, timezone
@@ -1422,7 +1428,7 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
         return defaults
 
     def _update_retry_counts(self, db_path: Optional[Path],
-                             task_id: Optional[str], counts: dict):
+                              task_id: Optional[str], counts: dict):
         """将 retry counts 写回最新 task_attempt 的 metadata"""
         if not db_path or not task_id:
             return
@@ -1482,8 +1488,8 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
                         from src.blackboard.operations import Blackboard
                         bb = Blackboard(db_path)
                         cid = bb.add_comment(task_id, "daemon",
-                                             f"@pangtong-fujunshi 任务执行失败: {reason}，请评估是否需要介入",
-                                             comment_type="system")
+                            f"@pangtong-fujunshi 任务执行失败: {reason}，请评估是否需要介入",
+                            comment_type="system")
                         bb.record_mentions(cid, task_id, ["pangtong-fujunshi"])
                         logger.info("Task %s: failure notified pangtong via comment+mention (reason=%s)", task_id, reason)
                 except Exception as e: