fix(spawner): crash cooldown分级 + inform mail crash误标done修复
- crashed outcome cooldown 60s(vs 其他 300s) - import init_db - whitespace/lint fixes
This commit is contained in:
+20
-14
@@ -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:
|
||||
|
||||
Reference in New Issue
Block a user