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:
董宏凯andClaude Opus 4.8 committed 2026-06-19 22:55:56 +08:00
1 parent 8ca16c74bc
commit 4a403c95c5
27 files changed
+1873 -61

No files matched your search

@@ -0,0 +1,173 @@
"""圆桌会商诊断日志查询 API(管理员)。
会商全流程(第一/二/三步 + 后台执行器 + 进程内网关)各处的报错与关键事件落在
``roundtable_diagnostics`` 表,本路由暴露**管理员**筛选查询 + facets + 清理。
Routes(prefix ``/api/roundtable-diagnostics``,全部 admin-gated)::
GET "" 筛选 + 分页列出(scope/stage/level/event/job_id/draft_id/task_id/user_id/q/since/until)
GET "/facets" 各筛选维度的 distinct 取值(下拉用)
POST "/admin/cleanup" 按保留天数清理旧日志
"""
from __future__ import annotations
import time
from datetime import UTC, datetime, timedelta
from typing import Any
from fastapi import APIRouter, HTTPException, Query, Request
from pydantic import BaseModel, Field
router = APIRouter(prefix="/api/roundtable-diagnostics", tags=["roundtable-diagnostics"])
def _get_store(request: Request):
store = getattr(request.app.state, "roundtable_diagnostic_store", None)
if store is None:
raise HTTPException(status_code=503, detail="Roundtable diagnostic store not available")
return store
async def _require_admin(request: Request) -> None:
"""放行 admin / auth-disabled,其余 403(与 roundtable_jobs / task_buttons 同套语义)。"""
from app.gateway.deps import get_optional_user_from_request
user = await get_optional_user_from_request(request)
if user is None:
return
if getattr(user, "system_role", None) != "admin":
raise HTTPException(status_code=403, detail="会商诊断日志仅限管理员查看")
class DiagnosticItem(BaseModel):
id: str
scope: str
stage: str
level: str
event: str
message: str | None = None
detail: Any = None
jobId: str | None = None
draftId: str | None = None
taskId: str | None = None
userId: str | None = None
agentId: str | None = None
agentName: str | None = None
cycle: int | None = None
createdAt: str | None = None
class DiagnosticListResponse(BaseModel):
items: list[DiagnosticItem]
total: int
limit: int
offset: int
class FacetsResponse(BaseModel):
scope: list[str] = Field(default_factory=list)
stage: list[str] = Field(default_factory=list)
level: list[str] = Field(default_factory=list)
event: list[str] = Field(default_factory=list)
class CleanupRequest(BaseModel):
retention_days: int = Field(default=30, ge=0)
batch_size: int = Field(default=1000, ge=1, le=10000)
class CleanupResponse(BaseModel):
deleted: int
elapsed_seconds: float
def _to_item(row: dict[str, Any]) -> DiagnosticItem:
return DiagnosticItem(
id=row["id"],
scope=row.get("scope") or "",
stage=row.get("stage") or "",
level=row.get("level") or "",
event=row.get("event") or "",
message=row.get("message"),
detail=row.get("detail"),
jobId=row.get("job_id"),
draftId=row.get("draft_id"),
taskId=row.get("task_id"),
userId=row.get("user_id"),
agentId=row.get("agent_id"),
agentName=row.get("agent_name"),
cycle=row.get("cycle"),
createdAt=row.get("created_at"),
)
def _parse_dt(raw: str | None) -> datetime | None:
if not raw:
return None
try:
# 容忍前端传的 ``...Z`` 后缀(datetime.fromisoformat 在 3.11+ 接受,旧版不接受)。
return datetime.fromisoformat(raw.replace("Z", "+00:00"))
except Exception:
return None
@router.get("", response_model=DiagnosticListResponse)
async def list_diagnostics(
request: Request,
scope: str | None = None,
stage: str | None = None,
level: str | None = None,
event: str | None = None,
job_id: str | None = None,
draft_id: str | None = None,
task_id: str | None = None,
user_id: str | None = None,
q: str | None = None,
since: str | None = None,
until: str | None = None,
limit: int = Query(default=100, ge=1, le=500),
offset: int = Query(default=0, ge=0),
) -> DiagnosticListResponse:
await _require_admin(request)
store = _get_store(request)
items, total = await store.list_logs(
scope=scope or None,
stage=stage or None,
level=level or None,
event=event or None,
job_id=job_id or None,
draft_id=draft_id or None,
task_id=task_id or None,
user_id=user_id or None,
q=q or None,
since=_parse_dt(since),
until=_parse_dt(until),
limit=limit,
offset=offset,
)
return DiagnosticListResponse(items=[_to_item(r) for r in items], total=total, limit=limit, offset=offset)
@router.get("/facets", response_model=FacetsResponse)
async def get_facets(request: Request) -> FacetsResponse:
await _require_admin(request)
store = _get_store(request)
facets = await store.facets()
return FacetsResponse(**facets)
@router.post("/admin/cleanup", response_model=CleanupResponse)
async def cleanup(request: Request, body: CleanupRequest) -> CleanupResponse:
await _require_admin(request)
store = _get_store(request)
cutoff = datetime.now(UTC) - timedelta(days=body.retention_days)
t0 = time.perf_counter()
deleted = 0
while True:
ids = await store.list_older_than(cutoff, limit=body.batch_size)
if not ids:
break
deleted += await store.delete_by_ids(ids)
if len(ids) < body.batch_size:
break
return CleanupResponse(deleted=deleted, elapsed_seconds=round(time.perf_counter() - t0, 3))