sanguo/sanguo_moziplus_v2
8
0
Fork 0
Code Issues Pull Requests 1 Actions Packages Projects Releases Wiki Activity

Merge PR #56

Browse Source
This commit was merged in pull request #56.
This commit is contained in:
庞统 副军师
2026-06-13 01:34:39 +00:00
parent 6520e78c0b a116f7e6c0
commit 79da0bd07e
3 changed files with 122 additions and 24 deletions
Download Patch File Download Diff File Expand all files Collapse all files
src/daemon/mail_notify.py
+114 -21
View File
@@ -1,4 +1,4 @@
"""Mail 失败通知 — 以 system 身份通知发件人"""
"""Mail 失败通知 v2.0 — 以 system 身份通知发件人（AI Native）"""
from __future__ import annotations
@@ -6,7 +6,7 @@ import json
import logging
from datetime import datetime
from pathlib import Path
from typing import Optional
from typing import Dict, Optional
from src.blackboard.models import Task
from src.blackboard.operations import Blackboard
@@ -15,21 +15,118 @@ from src.config.agents import AGENT_IDS
logger = logging.getLogger(__name__)
# 邮件通知正文模板（统一模板，包含所有可能的失败原因和建议）
_NOTIFY_TEMPLATE = """你的邮件投递失败了。
# ── Reason 人话翻译 + detail 提取 ──────────────────────────────
📧 原始邮件：「{title}」
👤 收件人：{to_agent}
❌ 失败原因：{reason}
def _extract_stderr(detail: dict, max_len: int = 200) -> str:
"""从 detail 中提取 stderr_preview"""
preview = (detail or {}).get("stderr_preview", "")
if preview and len(preview) > max_len:
preview = preview[:max_len] + "..."
return preview
常见失败原因及处理建议：
• no_reply_found：收件人未回复。建议重发邮件，或通过黑板任务方式联系
• auth_failed：收件人认证失败。需检查 Agent 配置，联系姜维(jiangwei-infra)排查
• crash_limit：收件人处理时多次崩溃。系统异常，建议稍后重试
• task_timeout：处理超时。建议重发或通过其他方式联系
• 其他原因：建议联系副军师(pangtong-fujunshi)排查
——系统自动通知"""
def _fmt_retry_info(reason: str, detail: dict) -> str:
"""格式化重试情况描述"""
_NO_RETRY_REASONS = {
"no_reply_found", "auth_failed", "agent_error",
"agent_failed", "compact_failed",
}
if reason in _NO_RETRY_REASONS:
reason_human = _REASON_MAP.get(reason, _REASON_MAP.get("_default", ("未知原因", lambda d: "")))[0]
return f"无法重试（{reason_human}）"
count = (detail or {}).get("count", 0)
fallback_count = (detail or {}).get("fallback_count", 0)
if count > 0:
return f"已自动重试 {count} 次"
if fallback_count > 0:
return f"已自动重试 {fallback_count} 次（fallback）"
return "系统已尝试恢复，但仍失败"
# reason_raw → (reason_human_readable, detail_format_fn)
_REASON_MAP: Dict[str, tuple] = {
"no_reply_found": ("收件人未回复（Agent 未能识别或处理此邮件）", lambda d: ""),
"crashed": ("处理时进程崩溃", lambda d: f"stderr: {_extract_stderr(d)}" if _extract_stderr(d) else "无 stderr 输出"),
"max_crash_count": ("连续崩溃达上限", lambda d: f"崩溃 {d.get('count', '?')} 次"),
"max_retries": ("续杯耗尽（已自动重试）", lambda d: f"重试 {d.get('count', '?')} 次"),
"max_api_retry_count": ("API 连续失败达上限", lambda d: f"API 重试 {d.get('count', '?')} 次"),
"max_monitor_timeouts": (
"处理超时达上限",
lambda d: f"超时 {d.get('count', '?')} 次，"
f"共约 {d.get('elapsed_seconds', 0) // 60} 分钟"),
"gateway_timeout": ("Agent 执行超时（已续杯重试）", lambda d: ""),
"session_stuck": ("会话假死（lock PID 死亡）", lambda d: f"假死 {d.get('stuck_count', '?')} 次"),
"revive_failed": ("会话恢复失败", lambda d: f"假死 {d.get('stuck_count', '?')} 次"),
"auth_failed": ("Agent 认证失败（配置问题）", lambda d: f"stderr: {_extract_stderr(d)}" if _extract_stderr(d) else ""),
"fallback_exhausted": (
"主模型和备用模型均失败",
lambda d: f"fallback {d.get('fallback_count', '?')} 次，"
f"原因: {d.get('fallback_reason', '未知')}"),
"agent_failed": ("收件人主动标记失败", lambda d: ""),
"compact_failed": ("上下文压缩失败", lambda d: f"stderr: {_extract_stderr(d)}" if _extract_stderr(d) else ""),
"compact_hanging": ("上下文压缩长时间未完成", lambda d: ""),
"compact_interrupted": ("上下文压缩被中断（已自动重试）", lambda d: ""),
"gateway_unreachable": (
"Gateway 不可达（已自动重试）",
lambda d: f"stderr: {_extract_stderr(d)}"
if _extract_stderr(d) else ""),
"lock_conflict": ("会话锁冲突（已自动重试）", lambda d: ""),
"max_retry_count": ("重试耗尽", lambda d: f"重试 {d.get('count', '?')} 次"),
"max_lock_retry_count": ("锁冲突重试耗尽", lambda d: f"重试 {d.get('count', '?')} 次"),
"max_connect_retry_count": ("连接重试耗尽", lambda d: f"重试 {d.get('count', '?')} 次"),
"_default": ("未知原因", lambda d: f"stderr: {_extract_stderr(d)}" if _extract_stderr(d) else ""),
}
# 常见失败原因参考（AI Native：提供知识库让收件 AI 自行判断）
_REASON_REFERENCE = """常见失败原因参考：
• no_reply_found：收件人未回复（Agent 未能识别或处理此邮件）
• crashed / max_crash_count：收件人处理时进程崩溃（已自动重试 3 次）
• max_retries：续杯耗尽（已自动重试 3 次，共约 34 分钟）
• max_api_retry_count：API 连续失败达上限（rate_limit/500/503）
• max_monitor_timeouts：处理超时达上限（共约 31.5 分钟）
• gateway_timeout：Agent 执行超时（已续杯重试）
• session_stuck：Agent 会话假死（lock PID 死亡，revive 失败）
• revive_failed：会话假死后恢复失败
• auth_failed：Agent 认证失败（配置问题）
• fallback_exhausted：主模型和备用模型均失败
• agent_failed：收件人主动标记失败
• compact_failed：上下文压缩失败
• compact_hanging：上下文压缩长时间未完成（等待超 31.5 分钟）
• compact_interrupted：上下文压缩被中断（已自动重试 3 次）
• gateway_unreachable：Gateway 不可达（已自动重试 3 次）
• lock_conflict：会话锁冲突（已自动重试 3 次）
• 其他：建议排查系统日志"""
def _build_notify_text(title: str, to_agent: str, reason: str,
detail: Optional[dict] = None) -> str:
"""构建通知正文（v2.0 AI Native）"""
reason_human, detail_fn = _REASON_MAP.get(reason, _REASON_MAP["_default"])
detail_info = detail_fn(detail or {})
retry_info = _fmt_retry_info(reason, detail or {})
lines = [
"邮件投递失败通知",
"",
f"📧 原始邮件：「{title}」",
f"👤 收件人：{to_agent}",
f"❌ 失败原因：{reason_human}（{reason}）",
f"📊 重试情况：{retry_info}",
]
if detail_info:
lines.append("📋 上下文信息：")
lines.append(f" {detail_info}")
lines.append("")
lines.append(_REASON_REFERENCE)
lines.append("")
lines.append("——系统自动通知")
return "\n".join(lines)
def _is_mail_project(db_path: Path) -> bool:
@@ -43,7 +140,7 @@ def notify_mail_failed(db_path: Path, original_mail_id: str,
"""Mail 失败后以 system 身份给发件人发通知邮件
直接通过 Blackboard 创建 Task，不走 HTTP API。
防递归：检查原邮件 must_hives.system_notify，为 true 则跳过。
防递归：检查原邮件 must_haves.system_notify，为 true 则跳过。
发件人不是有效 Agent（如 system）→ 通知庞统代处理，避免广播风暴。
"""
try:
@@ -83,12 +180,8 @@ def notify_mail_failed(db_path: Path, original_mail_id: str,
original_mail_id, from_agent)
target_agent = "pangtong-fujunshi"
# 构造通知正文
text = _NOTIFY_TEMPLATE.format(
title=title,
to_agent=to_agent,
reason=reason,
)
# 构造通知正文（v2.0 AI Native）
text = _build_notify_text(title, to_agent, reason, detail)
# 创建通知邮件 Task
notify_id = f"mail-{int(datetime.now().timestamp() * 1000)}"
src/daemon/spawner.py
+4 -1
View File
@@ -845,6 +845,8 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
cls.get("retry_field", "retry_count")
)
elif outcome == "api_error":
# A9: [DEPRECATED] api_error 已改为 should_retry=True 走续杯路径。
# 此分支理论上不再命中，保留作为安全兜底。
# A9: 429/API 错误 → release counter(on_complete)+ 推回 pending + 冷却
# 有上限:api_retry_count 累计达 max_retries 则标 failed
await self._do_on_complete_async(on_complete, agent_id, outcome)
@@ -1842,7 +1844,8 @@ curl -X POST http://{api_host}:{api_port}/api/projects/{project_id}/tasks/{task_
"retry_field": "retry_count", "cooldown_seconds": 60}
if any(kw in stderr_lower for kw in [
"rate_limit", "500", "503", "api error"]):
return {"outcome": "api_error", "should_retry": False}
return {"outcome": "api_error", "should_retry": True,
"retry_field": "retry_count", "cooldown_seconds": 60}
if any(kw in stderr_lower for kw in [
"compaction-diag", "context-overflow"]):
return {"outcome": "compact_failed", "should_retry": False}
tests/unit/test_classify_outcome.py
+4 -2
View File
@@ -165,14 +165,16 @@ class TestClassifyErrorApi:
1, {"status": "error"}, "rate_limit exceeded", None
)
assert result["outcome"] == "api_error"
assert result["should_retry"] is False
assert result["should_retry"] is True
assert result["cooldown_seconds"] == 60
def test_stderr_500(self):
result = Spawner._classify_outcome(
1, {"status": "error"}, "HTTP 500 Internal Server Error", None
)
assert result["outcome"] == "api_error"
assert result["should_retry"] is False
assert result["should_retry"] is True
assert result["cooldown_seconds"] == 60
class TestClassifyErrorCompact: