feat(roundtable): 会商诊断日志 + 后台挂起卡死兜底(idle 超时)
- 新增会商全流程诊断日志:新表 roundtable_diagnostics + 仓储 + admin API (/api/roundtable-diagnostics) + 管理员诊断页(会商页右上角设置按钮入口), 覆盖第一/二/三步及后台执行器/进程内网关各处报错与关键事件,支持按 范围/阶段/级别/事件/关键词筛选 + 分页。诊断写入全程 best-effort,绝不打断会商。 - 修复后台挂起「执行完第一个席位后永久卡死」:进程内网关每轮 agent run 改为 idle(无活动)超时(默认 20min)——只要还在持续产出 token/工具事件就一直等, 仅当连续无任何输出才判卡死并取消+报错+落 seat_turn_timeout 诊断;慢但活着的 生成绝不打断。可经 ROUNDTABLE_SEAT_IDLE_TIMEOUT_SECONDS 调整。 - 一并提交进行中的会商 seat-skill 注入 / 业务链条编辑器相关改动。 Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
8ca16c74bc
commit
4a403c95c5
27 files changed
+1873
-61
No files matched your search
@@ -26,6 +26,7 @@ from deerflow.agents.roundtable_orchestrator import (
|
||||
SeatRef,
|
||||
run_orchestration,
|
||||
)
|
||||
from deerflow.persistence.roundtable_diagnostics import DiagnosticsRecorder, get_default_store
|
||||
from deerflow.runtime.user_context import reset_current_user, set_current_user
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -219,7 +220,20 @@ class RoundtableJobExecutor:
|
||||
|
||||
async def _run(self, params: StartParams) -> None:
|
||||
token = set_current_user(_JobUser(params.user_id))
|
||||
diag = DiagnosticsRecorder(
|
||||
get_default_store(),
|
||||
scope="background",
|
||||
job_id=params.job_id,
|
||||
draft_id=params.draft_id,
|
||||
task_id=params.task_id,
|
||||
user_id=params.user_id,
|
||||
)
|
||||
try:
|
||||
await diag.record(
|
||||
stage="job", level="info", event="job_started",
|
||||
message=f"后台挂起作业启动(mode={params.mode}{',续跑' if params.is_resume else ''})",
|
||||
detail={"mode": params.mode, "is_resume": params.is_resume, "agents": [a.agent_id for a in params.agents]},
|
||||
)
|
||||
gateway = self._gateway_factory(params)
|
||||
thread_ids = params.thread_ids or {}
|
||||
coordinator_name = params.coordinator_name
|
||||
@@ -248,6 +262,7 @@ class RoundtableJobExecutor:
|
||||
job_id=params.job_id,
|
||||
agents=params.agents,
|
||||
on_dialogue=_on_dialogue if (self._draft_store_for(params) and params.draft_id) else None,
|
||||
recorder=diag,
|
||||
)
|
||||
result = await run_orchestration(
|
||||
gateway=gateway,
|
||||
@@ -283,8 +298,13 @@ class RoundtableJobExecutor:
|
||||
# 路由的 cancel 端点(executor.cancel + store.update_progress)权威写入。
|
||||
logger.info("roundtable job %s cancelled", params.job_id)
|
||||
raise
|
||||
except Exception: # noqa: BLE001 — 顶层兜底:run_orchestration 内部已尽量标 error
|
||||
except Exception as exc: # noqa: BLE001 — 顶层兜底:run_orchestration 内部已尽量标 error
|
||||
logger.exception("roundtable job %s crashed", params.job_id)
|
||||
await diag.record(
|
||||
stage="job", level="error", event="job_crashed",
|
||||
message=f"后台挂起作业崩溃:{exc}",
|
||||
detail={"type": type(exc).__name__, "error": str(exc)},
|
||||
)
|
||||
finally:
|
||||
reset_current_user(token)
|
||||
|
||||
@@ -363,8 +383,16 @@ class RoundtableJobExecutor:
|
||||
update_kwargs["step3"] = effective_step3
|
||||
try:
|
||||
await draft_store.update_draft(params.draft_id, params.user_id, **update_kwargs)
|
||||
except Exception: # noqa: BLE001 — 写草稿失败不影响作业本身
|
||||
except Exception as exc: # noqa: BLE001 — 写草稿失败不影响作业本身
|
||||
logger.warning("write run to draft %s failed", params.draft_id, exc_info=True)
|
||||
from deerflow.persistence.roundtable_diagnostics import record_diagnostic
|
||||
|
||||
await record_diagnostic(
|
||||
scope="background", stage="job", level="error", event="draft_write_failed",
|
||||
message=f"研讨结果写回草稿失败(status={status}):{exc}",
|
||||
detail={"type": type(exc).__name__, "error": str(exc)},
|
||||
job_id=params.job_id, draft_id=params.draft_id, task_id=params.task_id, user_id=params.user_id,
|
||||
)
|
||||
|
||||
def cancel(self, job_id: str) -> bool:
|
||||
"""请求取消一个在跑的作业。返回是否命中在跑任务。"""
|
||||
|
||||
Reference in new issue
Block a user