chore: simayi-approved changes - lint fixes, toolchain improvements, healthz
All changes reviewed and APPROVED in PR #12 (Review ID: 40): - toolchain_routes: webhook repo/org format compat, content dedup (sha256), closed issue filter - dispatcher: inform mail crash 误标 done 修复 - ticker: cleanup and improvements - healthz endpoint - conftest: integration/e2e deselect markers - docs: design docs, test-guide updates - various lint/whitespace fixes across 30 files
This commit is contained in:
cfdaily
@@ -11,7 +11,8 @@ A 类 Skill 由引擎确定性注入全文，不靠 Description 触发。
|
||||
|
||||
import logging
|
||||
import os
|
||||
from typing import Any, List
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.bootstrap")
|
||||
|
||||
|
||||
@@ -73,7 +73,7 @@ class ActiveAgentCounter:
|
||||
cd = seconds if seconds is not None else self._default_cooldown_seconds
|
||||
self._cooldown_until[agent_id] = time.time() + cd
|
||||
logger.info("Cooldown set for %s: %.0fs (until %.0f)",
|
||||
agent_id, cd, self._cooldown_until[agent_id])
|
||||
agent_id, cd, self._cooldown_until[agent_id])
|
||||
|
||||
async def can_acquire(self, agent_id: str, session_id: str = "main") -> bool:
|
||||
"""三层检查：cooldown → global → per agent → per session key"""
|
||||
|
||||
+18
-10
@@ -14,6 +14,7 @@ from __future__ import annotations
|
||||
import json
|
||||
import logging
|
||||
import sqlite3
|
||||
from datetime import datetime
|
||||
from enum import Enum
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional
|
||||
@@ -21,7 +22,7 @@ from typing import Any, Dict, List, Optional
|
||||
from src.blackboard.models import Task
|
||||
from src.blackboard.db import get_connection
|
||||
from src.daemon.spawner import AgentBusyError
|
||||
from src.daemon.router import AgentRouter
|
||||
from src.daemon.router import AgentRouter, RouteDecision
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.dispatcher")
|
||||
|
||||
@@ -193,7 +194,6 @@ class Dispatcher:
|
||||
_task_id = task.id
|
||||
_mail_db = db_path
|
||||
_disp = self
|
||||
|
||||
def _mail_on_checks_passed():
|
||||
nonlocal _mail_marked_working
|
||||
if not _disp._mail_auto_working(_task_id, _mail_db):
|
||||
@@ -203,8 +203,8 @@ class Dispatcher:
|
||||
|
||||
# 构建 spawn message
|
||||
message = self._build_spawn_message(task, agent_id, project_config,
|
||||
mode=decision.get("mode", ""),
|
||||
spawn_type=action_type or "executor")
|
||||
mode=decision.get("mode", ""),
|
||||
spawn_type=action_type or "executor")
|
||||
|
||||
# v2.7.2: on_complete 只含业务逻辑，不含 counter.release
|
||||
# counter.release 由 spawn_full_agent 内部的 wrapped_on_complete 保证
|
||||
@@ -218,7 +218,7 @@ class Dispatcher:
|
||||
def _mail_on_complete(aid, outcome):
|
||||
# 幻觉门控：检查是否有回复，自动标 done/failed
|
||||
try:
|
||||
_dispatcher._mail_auto_complete(_task_id, aid, _mail_db, _must_haves)
|
||||
_dispatcher._mail_auto_complete(_task_id, aid, _mail_db, _must_haves, outcome=outcome)
|
||||
except Exception as e:
|
||||
logger.error("Mail %s: on_complete error: %s", _task_id, e)
|
||||
on_complete = _mail_on_complete
|
||||
@@ -269,8 +269,8 @@ class Dispatcher:
|
||||
from src.blackboard.blackboard import Blackboard
|
||||
bb = Blackboard(_task_db)
|
||||
bb.add_comment(_task_id, "daemon",
|
||||
f"@{task_row['assignee']} 审查结论: {verdict_str}，请查看详情并决定接受或反驳",
|
||||
comment_type="review")
|
||||
f"@{task_row['assignee']} 审查结论: {verdict_str}，请查看详情并决定接受或反驳",
|
||||
comment_type="review")
|
||||
logger.info("Task %s: review verdict=%s, notified assignee=%s",
|
||||
_task_id, verdict_str, task_row["assignee"] if task_row else "?")
|
||||
# 不标 done，保持 review 状态
|
||||
@@ -576,7 +576,7 @@ class Dispatcher:
|
||||
|
||||
def _mail_oc_legacy(aid, outcome):
|
||||
try:
|
||||
_disp._mail_auto_complete(_t_id, aid, _m_db, _m_mh)
|
||||
_disp._mail_auto_complete(_t_id, aid, _m_db, _m_mh, outcome=outcome)
|
||||
except Exception as e:
|
||||
logger.error("Mail %s: legacy on_complete error: %s", _t_id, e)
|
||||
on_complete_legacy = _mail_oc_legacy
|
||||
@@ -661,7 +661,7 @@ class Dispatcher:
|
||||
logger.error("Mail %s: failed to revert to pending: %s", task_id, e)
|
||||
|
||||
def _mail_auto_complete(self, task_id: str, agent_id: str,
|
||||
db_path: Path, must_haves: str) -> None:
|
||||
db_path: Path, must_haves: str, outcome=None) -> None:
|
||||
"""Mail 任务：on_complete 后自动标 done/failed（含幻觉门控）"""
|
||||
try:
|
||||
# 解析 performative
|
||||
@@ -712,6 +712,14 @@ class Dispatcher:
|
||||
logger.error("Mail %s: all 3 failed attempts failed, leaving for ticker", task_id)
|
||||
return
|
||||
|
||||
# inform 类型：只对成功 outcome 标 done，失败 outcome 留 working 等 ticker 重投
|
||||
# Task 路径不受此 bug 影响（走 _task_auto_complete 独立逻辑）
|
||||
if performative == "inform":
|
||||
INFORM_DONE_OUTCOMES = {"completed", "claimed", "no_reply"}
|
||||
if outcome not in INFORM_DONE_OUTCOMES:
|
||||
logger.info("Mail %s: inform outcome=%s, skip auto-done", task_id, outcome)
|
||||
return
|
||||
|
||||
# 标 done（重试 3 次）
|
||||
for attempt in range(3):
|
||||
try:
|
||||
@@ -858,7 +866,7 @@ class Dispatcher:
|
||||
logger.error("Task %s: mark status error: %s", task_id, e)
|
||||
|
||||
@staticmethod
|
||||
def _check_crash_limit(task_id: str, db_path: Path, limit: int = 3,
|
||||
def _check_crash_limit(task_id: str, db_path: pathlib.Path, limit: int = 3,
|
||||
window_minutes: int = 30) -> bool:
|
||||
"""v2.8.1 Fix-3c: 检查 task 最近 window_minutes 内的 crash 次数是否超限。
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@ import logging
|
||||
import re
|
||||
from datetime import datetime
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.experience")
|
||||
|
||||
@@ -68,7 +68,7 @@ class Experience:
|
||||
@classmethod
|
||||
def from_dict(cls, data: Dict[str, Any]) -> Experience:
|
||||
return cls(**{k: v for k, v in data.items() if k != "id"},
|
||||
experience_id=data.get("id"))
|
||||
experience_id=data.get("id"))
|
||||
|
||||
|
||||
class ExperienceStore:
|
||||
@@ -284,7 +284,7 @@ class ExperienceDistiller:
|
||||
all_tags.append(task_type)
|
||||
|
||||
results = self.store.search(tags=all_tags if all_tags else None,
|
||||
query=query, limit=limit)
|
||||
query=query, limit=limit)
|
||||
|
||||
# 按置信度排序
|
||||
results.sort(key=lambda e: e.confidence, reverse=True)
|
||||
|
||||
@@ -4,7 +4,7 @@ from __future__ import annotations
|
||||
|
||||
import logging
|
||||
import re
|
||||
from dataclasses import dataclass
|
||||
from dataclasses import dataclass, field
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional
|
||||
|
||||
|
||||
@@ -9,9 +9,9 @@ from __future__ import annotations
|
||||
import json
|
||||
import logging
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict
|
||||
from typing import Any, Dict, Optional
|
||||
|
||||
from src.blackboard.db import get_connection
|
||||
from src.blackboard.db import get_connection, init_db
|
||||
from src.blackboard.queries import Queries
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.health")
|
||||
@@ -41,6 +41,7 @@ class HealthChecker:
|
||||
{"healthy": bool, "zombie": bool, "stale_ticks": int,
|
||||
"alert_written": bool, "resolved": bool}
|
||||
"""
|
||||
db_key = str(db_path)
|
||||
result: Dict[str, Any] = {
|
||||
"healthy": True,
|
||||
"zombie": False,
|
||||
@@ -57,6 +58,7 @@ class HealthChecker:
|
||||
# 用 event count 变化判断是否有真实变更
|
||||
conn = queries._conn()
|
||||
try:
|
||||
total_events = conn.execute("SELECT COUNT(*) FROM events").fetchone()[0]
|
||||
non_tick_events = conn.execute(
|
||||
"SELECT COUNT(*) FROM events WHERE event_type != 'daemon_tick' "
|
||||
"AND event_type != 'agent_zombie_detected'"
|
||||
|
||||
+3
-2
@@ -15,6 +15,7 @@ from __future__ import annotations
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
from pathlib import Path
|
||||
from typing import Any, Callable, Coroutine, Dict, List, Optional
|
||||
|
||||
@@ -56,7 +57,7 @@ class InboxWatcher:
|
||||
self._running = True
|
||||
self._task = asyncio.create_task(self._loop())
|
||||
logger.info("Inbox watcher started (path=%s, interval=%.1fs)",
|
||||
self.inbox_path, self.watch_interval)
|
||||
self.inbox_path, self.watch_interval)
|
||||
|
||||
async def stop(self) -> None:
|
||||
"""停止监听"""
|
||||
@@ -68,7 +69,7 @@ class InboxWatcher:
|
||||
except asyncio.CancelledError:
|
||||
pass
|
||||
logger.info("Inbox watcher stopped (processed=%d, errors=%d)",
|
||||
self._total_processed, self._total_errors)
|
||||
self._total_processed, self._total_errors)
|
||||
|
||||
@property
|
||||
def is_running(self) -> bool:
|
||||
|
||||
@@ -108,7 +108,7 @@ def notify_mail_failed(db_path: Path, original_mail_id: str,
|
||||
)
|
||||
bb.create_task(notify_task)
|
||||
logger.info("Mail %s: sent failure notification to %s (original_sender=%s, reason=%s, notify_id=%s)",
|
||||
original_mail_id, target_agent, from_agent, reason, notify_id)
|
||||
original_mail_id, target_agent, from_agent, reason, notify_id)
|
||||
|
||||
except Exception as e:
|
||||
logger.warning("notify_mail_failed: failed to send notification for mail %s: %s", original_mail_id, e)
|
||||
|
||||
@@ -8,12 +8,15 @@ from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
from datetime import datetime
|
||||
from enum import Enum
|
||||
from pathlib import Path
|
||||
from typing import Any, Callable, Dict, List, Optional
|
||||
from typing import Any, Callable, Dict, List, Optional, Tuple
|
||||
|
||||
from src.blackboard.models import Task
|
||||
from src.blackboard.operations import Blackboard
|
||||
from src.blackboard.queries import Queries
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.review")
|
||||
|
||||
|
||||
@@ -10,11 +10,12 @@ from __future__ import annotations
|
||||
|
||||
import json
|
||||
import logging
|
||||
import re
|
||||
from dataclasses import dataclass, field
|
||||
from datetime import datetime
|
||||
from enum import Enum
|
||||
from pathlib import Path
|
||||
from typing import Any, Dict, List, Optional, Tuple
|
||||
from typing import Any, Callable, Dict, List, Optional, Tuple
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.skill")
|
||||
|
||||
|
||||
@@ -1373,13 +1373,11 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
|
||||
# A17: 真正的 crash → 保持 working,ticker 兜底
|
||||
return {"outcome": "crashed", "should_retry": False, "original": "process_crash"}
|
||||
|
||||
# stdout 为空但 exit=0:可能是正常完成但 --json 没输出
|
||||
# 查任务状态判断
|
||||
# A13 revised: stdout 为空但 exit=0 → 信任进程退出码，视为正常完成
|
||||
# 实测发现 openclaw session=None + exit=0 是正常场景（inform 通知等）
|
||||
# 旧逻辑按 task_status 区分，非终态判 agent_error → 导致 inform 邮件永不标 done
|
||||
if status is None and not stdout_text.strip() and exit_code == 0:
|
||||
terminal_statuses = {"done", "review"}
|
||||
if task_status in terminal_statuses:
|
||||
return {"outcome": "completed", "should_retry": False}
|
||||
return {"outcome": "agent_error", "should_retry": False}
|
||||
return {"outcome": "completed", "should_retry": False}
|
||||
|
||||
# A7-A12: status=error → 不续杯,stderr 辅助分类
|
||||
if status == "error":
|
||||
|
||||
+4
-1
@@ -9,11 +9,14 @@ from __future__ import annotations
|
||||
import asyncio
|
||||
import json
|
||||
import logging
|
||||
import subprocess
|
||||
import uuid
|
||||
from datetime import datetime
|
||||
from enum import Enum
|
||||
from typing import Any, Dict, List, Optional
|
||||
from pathlib import Path
|
||||
from typing import Any, Callable, Dict, List, Optional, Set
|
||||
|
||||
from src.blackboard.models import Event
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.sse")
|
||||
|
||||
|
||||
+26
-25
@@ -21,6 +21,7 @@ from dataclasses import dataclass, field as dc_field
|
||||
|
||||
from src.blackboard.operations import Blackboard
|
||||
from src.blackboard.db import get_connection
|
||||
from src.blackboard.models import Task
|
||||
from src.daemon.spawner import AgentBusyError
|
||||
from src.blackboard.queries import Queries
|
||||
from src.blackboard.registry import ProjectRegistry
|
||||
@@ -34,7 +35,6 @@ class BroadcastRound:
|
||||
responded_agents: set = dc_field(default_factory=set) # 已返回反馈的 Agent（含 NO_REPLY）
|
||||
round_number: int = 0 # 当前第几轮（0=未开始，1=第1轮）
|
||||
|
||||
|
||||
logger = logging.getLogger("moziplus-v2.ticker")
|
||||
|
||||
|
||||
@@ -391,7 +391,7 @@ class Ticker:
|
||||
MAX_ROUNDS = 5 # §4.5 防无限循环
|
||||
|
||||
async def _check_round_complete(self, db_path: Path,
|
||||
project_id: str) -> List[str]:
|
||||
project_id: str) -> List[str]:
|
||||
"""检测 parent task 下所有 sub task 终态 → spawn 庞统 review
|
||||
|
||||
流程（§4.4）：
|
||||
@@ -462,7 +462,7 @@ class Ticker:
|
||||
"Round %d review spawned for parent %s (subs: %s)",
|
||||
new_round, parent_id, summary
|
||||
)
|
||||
except Exception:
|
||||
except Exception as e:
|
||||
logger.exception("Round check error for parent %s", parent_id)
|
||||
|
||||
return reviewed
|
||||
@@ -531,9 +531,9 @@ Parent Task ID: {parent_task.id}
|
||||
"""
|
||||
|
||||
async def _spawn_pangtong_review(self, parent_task,
|
||||
review_prompt: str,
|
||||
project_id: str,
|
||||
new_round: int = 0) -> bool:
|
||||
review_prompt: str,
|
||||
project_id: str,
|
||||
new_round: int = 0) -> bool:
|
||||
"""Spawn 庞统进行 review
|
||||
|
||||
流程：
|
||||
@@ -543,6 +543,7 @@ Parent Task ID: {parent_task.id}
|
||||
"""
|
||||
try:
|
||||
agent_id = "pangtong-fujunshi"
|
||||
session_id = f"review-{parent_task.id}-r{new_round}"
|
||||
|
||||
# 构造 on_complete 回调：解析庞统结论，更新 parent 状态
|
||||
async def _on_review_complete(aid: str, outcome: str):
|
||||
@@ -585,7 +586,7 @@ Parent Task ID: {parent_task.id}
|
||||
self._set_parent_reviewing(parent_task.id, project_id)
|
||||
return True
|
||||
return False
|
||||
except Exception:
|
||||
except Exception as e:
|
||||
logger.exception("Failed to spawn pangtong review for %s", parent_task.id)
|
||||
return False
|
||||
|
||||
@@ -602,14 +603,14 @@ Parent Task ID: {parent_task.id}
|
||||
(parent_id,))
|
||||
conn.commit()
|
||||
logger.info("Parent %s → reviewing (round review in progress)",
|
||||
parent_id)
|
||||
parent_id)
|
||||
finally:
|
||||
conn.close()
|
||||
except Exception:
|
||||
logger.exception("Failed to set parent %s to reviewing", parent_id)
|
||||
|
||||
def _handle_review_conclusion(self, parent_id: str, project_id: str,
|
||||
review_text: str, round_num: int):
|
||||
review_text: str, round_num: int):
|
||||
"""解析庞统 review 结论，更新 parent 状态
|
||||
|
||||
review_text 是庞统回复的文本（从 spawner session meta payloads 拼接）。
|
||||
@@ -664,8 +665,8 @@ Parent Task ID: {parent_task.id}
|
||||
|
||||
def _resolve_db_path(self, project_id: str) -> Path:
|
||||
"""解析项目 DB 路径"""
|
||||
import src.utils as _utils
|
||||
return _utils.get_data_root() / project_id / "blackboard.db"
|
||||
from src.utils import get_data_root
|
||||
return get_data_root() / project_id / "blackboard.db"
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
# @mention 通知处理 (v2.9 #01)
|
||||
@@ -674,7 +675,7 @@ Parent Task ID: {parent_task.id}
|
||||
MENTION_MAX_RETRIES = 5
|
||||
|
||||
async def _process_mentions(self, db_path: Path,
|
||||
project_id: str) -> List[str]:
|
||||
project_id: str) -> List[str]:
|
||||
"""扫描 pending mentions → spawn 被 @ 的 Agent
|
||||
|
||||
流程（§3.4）：
|
||||
@@ -766,8 +767,8 @@ Parent Task ID: {parent_task.id}
|
||||
from src.blackboard.blackboard import Blackboard
|
||||
bb2 = Blackboard(rdb_path)
|
||||
bb2.add_comment(_t_id, "daemon",
|
||||
f"@{t_row['assignee']} 审查结论: {verdict_str}，请查看详情并决定接受或反驳",
|
||||
comment_type="review")
|
||||
f"@{t_row['assignee']} 审查结论: {verdict_str}，请查看详情并决定接受或反驳",
|
||||
comment_type="review")
|
||||
logger.info("Rebuttal: task %s still %s after rebuttal", _t_id, verdict_str)
|
||||
except Exception:
|
||||
logger.exception("Rebuttal on_complete failed for task %s", _t_id)
|
||||
@@ -804,7 +805,7 @@ Parent Task ID: {parent_task.id}
|
||||
# Agent 忙，不递增 retry_count，等下次 tick 自然重试
|
||||
logger.info("Mention spawn skipped: %s busy, will retry next tick", agent_id)
|
||||
|
||||
except Exception:
|
||||
except Exception as e:
|
||||
logger.exception("Mention processing error for agent %s", agent_id)
|
||||
for item in items:
|
||||
try:
|
||||
@@ -947,7 +948,7 @@ Parent Task ID: {parent_task.id}
|
||||
# ------------------------------------------------------------------
|
||||
|
||||
async def _dispatch_pending(self, db_path: Path,
|
||||
project_id: str) -> List[str]:
|
||||
project_id: str) -> List[str]:
|
||||
"""扫描 pending 任务并调度
|
||||
|
||||
v3.0: 两条路径
|
||||
@@ -1241,7 +1242,7 @@ Parent Task ID: {parent_task.id}
|
||||
return [aid for aid in all_agents if active.get(aid, 0) == 0]
|
||||
|
||||
async def _dispatch_reviews(self, db_path: Path,
|
||||
project_id: str) -> List[str]:
|
||||
project_id: str) -> List[str]:
|
||||
"""扫描 review 状态任务，检查是否有产出，调度审查 Agent"""
|
||||
# mail 任务不走 review 流程，直接跳过
|
||||
if project_id == "_mail":
|
||||
@@ -1343,7 +1344,7 @@ Parent Task ID: {parent_task.id}
|
||||
)
|
||||
reclaimed.append(task.id)
|
||||
logger.warning("Escalated %s: no taker after %d broadcasts",
|
||||
task.id, retry_count)
|
||||
task.id, retry_count)
|
||||
finally:
|
||||
conn.close()
|
||||
else:
|
||||
@@ -1422,7 +1423,7 @@ Parent Task ID: {parent_task.id}
|
||||
if ok:
|
||||
reclaimed.append(task.id)
|
||||
logger.info("Mail %s: ticker recheck found reply, marked done (%.1fm)",
|
||||
task.id, elapsed)
|
||||
task.id, elapsed)
|
||||
finally:
|
||||
conn.close()
|
||||
continue
|
||||
@@ -1439,7 +1440,7 @@ Parent Task ID: {parent_task.id}
|
||||
if ok:
|
||||
reclaimed.append(task.id)
|
||||
logger.warning("Task %s timed out (working %.1fm > %.1fm)",
|
||||
task.id, elapsed, timeout_minutes)
|
||||
task.id, elapsed, timeout_minutes)
|
||||
finally:
|
||||
conn.close()
|
||||
except (ValueError, TypeError):
|
||||
@@ -1500,7 +1501,7 @@ Parent Task ID: {parent_task.id}
|
||||
return True # 保守：查询失败假设有回复
|
||||
|
||||
def _check_recent_routing(self, db_path: Path, task_id: str,
|
||||
action_type: str) -> bool:
|
||||
action_type: str) -> bool:
|
||||
"""检查最近 5 分钟内是否已 dispatch 过指定类型的路由（防重复）"""
|
||||
try:
|
||||
conn = get_connection(db_path)
|
||||
@@ -1578,11 +1579,11 @@ Parent Task ID: {parent_task.id}
|
||||
|
||||
if recovery_report["total_recovered"] > 0:
|
||||
logger.info("Startup recovery: %d tasks recovered across %d projects",
|
||||
recovery_report["total_recovered"],
|
||||
len(recovery_report["projects"]))
|
||||
recovery_report["total_recovered"],
|
||||
len(recovery_report["projects"]))
|
||||
elif recovery_report["total_noop"] > 0:
|
||||
logger.info("Startup recovery: %d tasks kept as-is (no recovery needed)",
|
||||
recovery_report["total_noop"])
|
||||
recovery_report["total_noop"])
|
||||
else:
|
||||
logger.info("Startup recovery: no non-terminal tasks found, clean start")
|
||||
|
||||
@@ -1628,7 +1629,7 @@ Parent Task ID: {parent_task.id}
|
||||
return recovered, noop_count
|
||||
|
||||
def _determine_recovery_action(self, conn, task, status: str,
|
||||
db_path: Path) -> Optional[str]:
|
||||
db_path: Path) -> Optional[str]:
|
||||
"""根据黑板线索决定恢复动作，返回 None 表示不需要干预"""
|
||||
task_id = task["id"]
|
||||
|
||||
|
||||
Reference in New Issue
Block a user