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

@@ -62,7 +62,9 @@ from fastapi import APIRouter, Body, HTTPException, Request
from fastapi.responses import StreamingResponse
from langgraph.checkpoint.base import empty_checkpoint
from app.gateway.roundtable_diag import record_foreground_diag
from app.gateway.roundtable_run_policy import merge_skill_stop_names, roundtable_run_policy
from app.gateway.roundtable_seat_skills import append_seat_skill_directive
from app.gateway.routers._roundtable_seed import (
COORDINATOR_AGENT_ID,
DASHBOARD_AGENT_ID,
@@ -80,6 +82,23 @@ logger = logging.getLogger(__name__)
router = APIRouter(prefix="/api/multi-agent", tags=["multi-agent"])
def _stage_for_agent(agent_type: str, agent_name: str) -> str:
"""把一次 /run/stream 的 (agent_type, agent_name) 映射成诊断日志的 stage。
Step3 的四个内置单例(report/summary/dashboard/structure)也走 special 路径,
据 agent_name 归到对应 step3_* 阶段;其余 leader→step2_leader、special→step2_seat。
"""
if agent_name == REPORT_AGENT_ID:
return "step3_report"
if agent_name == SUMMARY_AGENT_ID:
return "step3_summary"
if agent_name == DASHBOARD_AGENT_ID:
return "step3_dashboard"
if agent_name == STRUCTURE_AGENT_ID:
return "step3_structure"
return "step2_leader" if agent_type == "leader" else "step2_seat"
# 圆桌(intent / recommend / 席位 / 协调)创建的 thread 都是功能型内部线程,
# 不是用户的普通对话。打上这个 metadata,前端「最近的对话」列表(recent-chat-list.tsx)
# 据 `metadata.thread_type` 过滤掉,与 scheduler / bootstrap 系统会话同一套机制。
@@ -892,9 +911,19 @@ async def init_multi_agent(request: Request, payload: dict = Body(...)) -> Strea
})
except HTTPException as exc:
logger.warning("multi-agent init HTTPException: %s %s", exc.status_code, exc.detail)
await record_foreground_diag(
request, stage="step2_init", level="error", event="init_http_error",
message=f"会商初始化失败 [{exc.status_code}]:{exc.detail}",
detail={"status_code": exc.status_code, "detail": str(exc.detail)},
)
yield _frame({"event": "error", "detail": f"[{exc.status_code}] {exc.detail}"})
except Exception as exc:
logger.exception("multi-agent init unexpected failure")
await record_foreground_diag(
request, stage="step2_init", level="error", event="init_unexpected",
message=f"会商初始化未预期异常:{exc!r}",
detail={"type": type(exc).__name__, "error": str(exc)},
)
yield _frame({"event": "error", "detail": f"unexpected: {exc!r}"})
return StreamingResponse(
@@ -922,8 +951,16 @@ async def init_report_thread(request: Request) -> dict[str, str]:
``agent_name="roundtable-report"``、``d_agent_thread_id={REPORT_AGENT_ID: thread_id}``)
跑这一轮,智能体把图表 HTML 写进该线程的 ``outputs/``,再由沙箱预览。
"""
ensure_roundtable_functional_agents()
thread_id = await _create_thread_direct(request, metadata=_ROUNDTABLE_THREAD_METADATA)
try:
ensure_roundtable_functional_agents()
thread_id = await _create_thread_direct(request, metadata=_ROUNDTABLE_THREAD_METADATA)
except Exception as exc:
await record_foreground_diag(
request, stage="step3_report", level="error", event="thread_init_failed",
message=f"创建结果绘制线程失败:{exc}", detail={"type": type(exc).__name__, "error": str(exc)},
agent_id=REPORT_AGENT_ID,
)
raise
return {"agent_name": REPORT_AGENT_ID, "thread_id": thread_id}
@@ -942,8 +979,16 @@ async def init_summary_thread(request: Request) -> dict[str, str]:
跑这一轮(后续问答/增量改**复用同一线程**,不重新 init),智能体把 Markdown 报告
写进该线程的 ``outputs/方案总结报告.md``,再由沙箱预览。
"""
ensure_roundtable_functional_agents()
thread_id = await _create_thread_direct(request, metadata=_ROUNDTABLE_THREAD_METADATA)
try:
ensure_roundtable_functional_agents()
thread_id = await _create_thread_direct(request, metadata=_ROUNDTABLE_THREAD_METADATA)
except Exception as exc:
await record_foreground_diag(
request, stage="step3_summary", level="error", event="thread_init_failed",
message=f"创建总结报告线程失败:{exc}", detail={"type": type(exc).__name__, "error": str(exc)},
agent_id=SUMMARY_AGENT_ID,
)
raise
return {"agent_name": SUMMARY_AGENT_ID, "thread_id": thread_id}
@@ -964,8 +1009,16 @@ async def init_dashboard_thread(request: Request) -> dict[str, str]:
跑这一轮(后续问答/增量改**复用同一线程**,不重新 init),智能体在对话里输出
```report-json,前端用 ``extractReportData`` 抽取后按当前主题渲染大屏。
"""
ensure_roundtable_functional_agents()
thread_id = await _create_thread_direct(request, metadata=_ROUNDTABLE_THREAD_METADATA)
try:
ensure_roundtable_functional_agents()
thread_id = await _create_thread_direct(request, metadata=_ROUNDTABLE_THREAD_METADATA)
except Exception as exc:
await record_foreground_diag(
request, stage="step3_dashboard", level="error", event="thread_init_failed",
message=f"创建大屏数据线程失败:{exc}", detail={"type": type(exc).__name__, "error": str(exc)},
agent_id=DASHBOARD_AGENT_ID,
)
raise
return {"agent_name": DASHBOARD_AGENT_ID, "thread_id": thread_id}
@@ -986,8 +1039,16 @@ async def init_structure_thread(request: Request) -> dict[str, str]:
跑这一轮,把 taskId + 总结报告 + 结构化流程图交给它,由它挑选合适的入库技能(名称
可能含「六步法」/自行判断适用性)读 SKILL.md 并按其契约调用完成入库。
"""
ensure_roundtable_functional_agents()
thread_id = await _create_thread_direct(request, metadata=_ROUNDTABLE_THREAD_METADATA)
try:
ensure_roundtable_functional_agents()
thread_id = await _create_thread_direct(request, metadata=_ROUNDTABLE_THREAD_METADATA)
except Exception as exc:
await record_foreground_diag(
request, stage="step3_structure", level="error", event="thread_init_failed",
message=f"创建数据入库线程失败:{exc}", detail={"type": type(exc).__name__, "error": str(exc)},
agent_id=STRUCTURE_AGENT_ID,
)
raise
return {"agent_name": STRUCTURE_AGENT_ID, "thread_id": thread_id}
@@ -995,6 +1056,16 @@ async def init_structure_thread(request: Request) -> dict[str, str]:
# 上游 LangGraph SSE 透传(intent / recommend / leader / special 共用)
# ---------------------------------------------------------------------------
# 回环 /runs/stream 在**响应头阶段**返回这些状态码时,视为「单 worker + 单 sqlite 锁被
# 并发打满」造成的瞬时失败,退避重试(详见 _stream_upstream 内注释):
# 409 同 thread 抢占竞态;429 限流;500/503/504 高并发下 start_run 里 DB/checkpoint 写抖动。
# 不含 400/401/403/404/422 等确定性错误——那些重试也没用,立即上报。
_UPSTREAM_RETRYABLE_STATUSES = frozenset({409, 429, 500, 502, 503, 504})
# 重试次数(不含首次)。总尝试 = 1 + _UPSTREAM_MAX_RETRIES。
_UPSTREAM_MAX_RETRIES = 2
# 指数退避基数(秒):0.4 → 0.8 → …,足够让在跑的席位 run 让出 sqlite 锁,又不至于明显拖慢。
_UPSTREAM_RETRY_BASE_DELAY = 0.4
async def _stream_upstream(
client: httpx.AsyncClient,
@@ -1017,36 +1088,74 @@ async def _stream_upstream(
url = f"{base}/api/threads/{thread_id}/runs/stream"
captured: list[str] = []
t_send = time.perf_counter()
async with client.stream("POST", url, json=body, headers=headers) as resp:
t_headers = time.perf_counter()
if resp.status_code != 200:
body_text = (await resp.aread()).decode("utf-8", "replace")[:1000]
raise HTTPException(
status_code=502,
detail=f"upstream {url} returned HTTP {resp.status_code}: {body_text}",
)
agent_for_log = (body.get("context") or {}).get("agent_name") or thread_id
logger.info(
"[upstream-timing] %s headers_in=%.3fs",
agent_for_log,
t_headers - t_send,
)
first_line = True
async for line in resp.aiter_lines():
if not line:
continue
if first_line:
first_line = False
logger.info(
"[upstream-timing] %s first_line=%.3fs (LangGraph runtime startup + LLM first byte)",
agent_for_log,
time.perf_counter() - t_headers,
agent_for_log = (body.get("context") or {}).get("agent_name") or thread_id
# 头阶段非 200 的瞬时重试。
# 背景:网关是**单 worker** + checkpointer 是**单连接 aiosqlite**(全进程一把
# asyncio.Lock 串行 checkpoint 读写)。圆桌第三步进入时,前端把「方案总结/结果绘制/
# 大屏」三个重 run **同一刻并行**打出来,叠加第二步 on_disconnect=continue 仍在后台
# 跑的席位 run,瞬时把单锁/单 worker 打满 —— 此时回环子请求 /runs/stream 的 start_run
# 里那串 DB / checkpoint 写有概率抛错(或同 thread 抢占竞态),返回非 200,被本函数原样
# 包成 502 漏给前端(用户侧表现为"进第三步概率性 502")。
# 关键安全前提:这个非 200 发生在**响应头阶段**,本函数**尚未 yield 任何 SSE 行**给下游,
# 所以"换条连接重发"是幂等安全的(不会重复透传半截流)。对可恢复的瞬时状态码退避重试几次,
# 把绝大多数并发尖峰造成的偶发失败吃掉;非可恢复状态码(如 400/401/403/404)立即按原逻辑
# 报错,不浪费重试。一旦进入流式(已 yield 行)就绝不重试。
last_status = 0
last_body = ""
for attempt in range(_UPSTREAM_MAX_RETRIES + 1):
t_send = time.perf_counter()
async with client.stream("POST", url, json=body, headers=headers) as resp:
t_headers = time.perf_counter()
if resp.status_code != 200:
last_status = resp.status_code
last_body = (await resp.aread()).decode("utf-8", "replace")[:1000]
if resp.status_code in _UPSTREAM_RETRYABLE_STATUSES and attempt < _UPSTREAM_MAX_RETRIES:
delay = _UPSTREAM_RETRY_BASE_DELAY * (2**attempt)
logger.warning(
"[upstream-retry] %s 回环 %s 返回 HTTP %s,%.2fs 后重试(第 %d/%d 次):%s",
agent_for_log,
url,
resp.status_code,
delay,
attempt + 1,
_UPSTREAM_MAX_RETRIES,
last_body[:200],
)
await asyncio.sleep(delay)
continue # 重连:换条新连接重发同一 body(尚未 yield 任何行,幂等安全)
raise HTTPException(
status_code=502,
detail=f"upstream {url} returned HTTP {resp.status_code}: {last_body}",
)
yield line, None
if line.startswith("data:"):
captured.append(line)
yield None, captured
logger.info(
"[upstream-timing] %s headers_in=%.3fs%s",
agent_for_log,
t_headers - t_send,
f" (retried x{attempt})" if attempt else "",
)
first_line = True
async for line in resp.aiter_lines():
if not line:
continue
if first_line:
first_line = False
logger.info(
"[upstream-timing] %s first_line=%.3fs (LangGraph runtime startup + LLM first byte)",
agent_for_log,
time.perf_counter() - t_headers,
)
yield line, None
if line.startswith("data:"):
captured.append(line)
yield None, captured
return
# 理论上不可达(循环要么 return、要么 raise);留一条兜底防御。
raise HTTPException(
status_code=502,
detail=f"upstream {url} returned HTTP {last_status}: {last_body}",
)
def _parse_last_messages(captured: list[str]) -> list[dict[str, Any]] | None:
@@ -1677,11 +1786,18 @@ async def _special_run(
if files:
_read_tools = {"read_file", "ls", "grep", "view_image"}
seat_excluded = [t for t in seat_excluded if t not in _read_tools]
# 弱模型补偿:仅对真正的研讨席位(seat / seat_parallel;report/summary/dashboard/ingest
# 等 Step3 单例不在此列)把其配置技能(名称 + SKILL.md 路径 + 必须先 read_file 再按其
# 流程取信息的硬指令)显式拼进本轮任务,避免弱模型无视系统提示里的技能块(见
# roundtable_seat_skills 模块说明)。无配置技能时原样返回。
seat_message = new_message
if role in ("seat", "seat_parallel"):
seat_message = append_seat_skill_directive(agent_name, new_message)
body = _run_payload(
agent_name=agent_name,
model_name=model_name,
thread_id=thread_id,
new_message=new_message,
new_message=seat_message,
excluded_tools=seat_excluded,
skill_stop_names=merge_skill_stop_names(policy.skill_stop_names, skill_stop_names),
# 席位执行模式覆盖 policy 的 thinking/reasoning(None → 回退 policy 默认);
@@ -1899,6 +2015,13 @@ async def run_multi_agent_stream(request: Request, payload: dict = Body(...)) ->
yield chunk if chunk.endswith("\n") else chunk + "\n"
except HTTPException as exc:
logger.warning("multi-agent stream HTTPException: %s %s", exc.status_code, exc.detail)
await record_foreground_diag(
request, stage=_stage_for_agent(agent_type, agent_name), level="error",
event="run_http_error",
message=f"「{agent_name}」运行失败 [{exc.status_code}]:{exc.detail}",
detail={"status_code": exc.status_code, "detail": str(exc.detail), "agent_type": agent_type},
agent_id=agent_name, agent_name=display_name or agent_name,
)
err_frame = {
"status": "error",
"content": f"[{exc.status_code}] {exc.detail}",
@@ -1907,6 +2030,13 @@ async def run_multi_agent_stream(request: Request, payload: dict = Body(...)) ->
yield f"data: {json.dumps(err_frame, ensure_ascii=False)}\n\n"
except Exception as exc:
logger.exception("multi-agent stream unexpected failure")
await record_foreground_diag(
request, stage=_stage_for_agent(agent_type, agent_name), level="error",
event="run_unexpected",
message=f"「{agent_name}」运行未预期异常:{exc!r}",
detail={"type": type(exc).__name__, "error": str(exc), "agent_type": agent_type},
agent_id=agent_name, agent_name=display_name or agent_name,
)
err_frame = {
"status": "error",
"content": f"unexpected: {exc!r}",