增强 Deep Research 可靠性,并接入 8BF 任务卡片与会商上下文。

修复 MySQL 读写分离下的持久化与 SSE 重连问题,报告完成前先落库;8BF 嵌入页支持 taskId 任务卡与独立意图 metadata;前端统一 createClientId 并更新 runtime 配置。

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
董宏凯andCursor committed 2026-08-17 18:16:05 +08:00
1 parent 47faa9bcdf
commit 771957429a
36 files changed
+2038 -300

No files matched your search

@@ -61,6 +61,8 @@ WORKER_ID = f"w-{os.getpid()}-{_uuid.uuid4().hex[:8]}"
_LEASE_TTL_SECONDS = 60
_HEARTBEAT_INTERVAL = 20.0
_CANCEL_POLL_INTERVAL = 5.0
_REPORT_PROJECTION_RETRY_ATTEMPTS = 3
_REPORT_PROJECTION_RETRY_DELAY_SECONDS = 0.5
# Phase → progress% mapping for the job timeline.
_PHASE_PROGRESS: dict[str, int] = {
@@ -1372,7 +1374,17 @@ class DeepResearchJobExecutor:
async def _mark_completed(
self, job_id: str, session_id: str, lease_owner: str | None, result: DeepResearchResult
) -> None:
# Job row → completed.
# Persist the report projection before exposing a terminal completed
# job. The session row is the durable report itself; marking the job
# complete first and suppressing a session-write failure can otherwise
# make a successfully generated report disappear after refresh.
await self._persist_completed_report_projection(
job_id=job_id,
session_id=session_id,
result=result,
)
# Job row → completed only after the report is durable.
await self._job_store.update_progress(
job_id,
lease_owner=lease_owner,
@@ -1385,26 +1397,62 @@ class DeepResearchJobExecutor:
"plan": result.plan,
},
)
# Session row → completed + report.
source_count = len(result.source_ids)
with suppress(Exception): # noqa: BLE001
await self._session_store.update(
session_id,
status="completed",
report_markdown=result.report_markdown,
report_html=result.report_html,
plan_snapshot=result.plan,
# Keep the terminal job id alongside model usage. The
# frontend uses it only to replay the persisted research trace
# after a refresh; it does not affect billing or job state.
usage_snapshot={**(result.usage or {}), "lastJobId": job_id},
source_count=source_count,
active_job_id=None,
)
# Emit a terminal event for SSE consumers.
with suppress(Exception): # noqa: BLE001
await self._emit_terminal(job_id, session_id, "job_completed")
async def _persist_completed_report_projection(
self,
*,
job_id: str,
session_id: str,
result: DeepResearchResult,
) -> None:
"""Durably save the report before publishing job completion.
A write can succeed while a short-lived MySQL proxy/readback hiccup
makes its caller fail. Retry the full owner-scoped update a few times;
if it still cannot be confirmed, propagate the error so ``_run`` marks
the job failed instead of advertising a report that cannot be reopened.
"""
last_error: Exception | None = None
for attempt in range(1, _REPORT_PROJECTION_RETRY_ATTEMPTS + 1):
try:
updated = await self._session_store.update(
session_id,
status="completed",
report_markdown=result.report_markdown,
report_html=result.report_html,
plan_snapshot=result.plan,
# Keep the terminal job id alongside model usage. The
# frontend uses it only to replay the persisted research
# trace after a refresh; it does not affect billing.
usage_snapshot={**(result.usage or {}), "lastJobId": job_id},
source_count=len(result.source_ids),
active_job_id=None,
)
if updated is not None:
return
last_error = RuntimeError(f"Deep Research session {session_id} no longer exists")
except asyncio.CancelledError:
raise
except Exception as exc: # noqa: BLE001
last_error = exc
if attempt < _REPORT_PROJECTION_RETRY_ATTEMPTS:
logger.warning(
"deep-research report projection failed for %s (attempt %s/%s); retrying",
job_id,
attempt,
_REPORT_PROJECTION_RETRY_ATTEMPTS,
exc_info=True,
)
await asyncio.sleep(_REPORT_PROJECTION_RETRY_DELAY_SECONDS * attempt)
raise RuntimeError(
f"研究报告未能保存到会话 {session_id},任务不会标记为完成"
) from last_error
async def _mark_awaiting(
self, job_id: str, session_id: str, pause: ResearchAwaitingInput
) -> None:
@@ -639,17 +639,30 @@ async def start_job(session_id: str, body: StartJobRequest, request: Request) ->
input_snapshot=input_snapshot,
)
# Update session status.
await session_store.update(
session_id,
user_id=user_id,
status="running",
active_job_id=job["id"],
)
# The durable job is the source of truth once it has been committed. A
# transient failure updating the display projection must not turn that
# successful write into a misleading 500 response or leave it undispatched.
# The executor re-projects the terminal status when it completes.
try:
await session_store.update(
session_id,
user_id=user_id,
status="running",
active_job_id=job["id"],
)
except Exception: # noqa: BLE001
logger.exception(
"deep-research job %s was queued but its session running projection could not be updated",
job["id"],
)
# Nudge the dispatcher to claim immediately.
# Nudge the dispatcher even for an idempotent retry. If an earlier request
# committed the job but failed before this point (for example a transient
# MySQL read-after-write failure), the retry receives the existing queued
# job. Restricting the nudge to ``created`` would leave that durable job
# queued until the next periodic scan and make the UI appear stuck.
dispatcher = _get_dispatcher(request)
if dispatcher is not None and created:
if dispatcher is not None:
dispatcher.nudge()
return {
@@ -810,36 +823,68 @@ async def stream_job(
if loop.time() >= next_durable_poll:
# Durable replay repairs a missed live delta after
# reconnect or when another worker owned the job.
events = await event_store.list_after(job_id, after=cursor, limit=200)
for ev in events:
payload = {
"seq": ev["seq"],
"sessionId": session_id,
"jobId": job_id,
"type": ev["event_type"],
"phase": ev.get("phase", "initializing"),
"timestamp": _iso(ev.get("created_at")),
"payload": ev.get("payload") or {},
}
yield format_sse("progress", payload, event_id=str(ev["seq"]))
cursor = max(cursor, ev["seq"])
current = await job_store.get_unscoped(job_id)
if current and current.get("status") in TERMINAL_STATUSES:
try:
events = await event_store.list_after(job_id, after=cursor, limit=200)
for ev in events:
payload = {
"seq": ev["seq"],
"sessionId": session_id,
"jobId": job_id,
"type": ev["event_type"],
"phase": ev.get("phase", "initializing"),
"timestamp": _iso(ev.get("created_at")),
"payload": ev.get("payload") or {},
}
yield format_sse("progress", payload, event_id=str(ev["seq"]))
cursor = max(cursor, ev["seq"])
current = await job_store.get_unscoped(job_id)
if current and current.get("status") in TERMINAL_STATUSES:
yield format_sse(
"progress",
{
"seq": cursor + 1,
"sessionId": session_id,
"jobId": job_id,
"type": "job_status",
"phase": current.get("phase", "done"),
"timestamp": _iso(datetime.now(UTC)),
"payload": {"status": current["status"], "progress": current.get("progress", 0)},
},
event_id=str(cursor + 1),
)
return
next_durable_poll = loop.time() + _POLL_INTERVAL_S
except asyncio.CancelledError:
raise
except Exception: # noqa: BLE001
# Do not let one read-replica / transient DB failure
# abort the ASGI generator (which surfaces as an
# ExceptionGroup and leaves the page stuck). Live
# frames can still reach an attached browser, and the
# next durable poll repairs the cursor on recovery.
logger.warning(
"deep-research SSE durable replay temporarily failed for job %s; keeping stream open",
job_id,
exc_info=True,
)
yield format_sse(
"progress",
{
"seq": cursor + 1,
"seq": 0,
"liveId": f"durable-replay-retry:{job_id}:{int(loop.time() * 1000)}",
"sessionId": session_id,
"jobId": job_id,
"type": "job_status",
"phase": current.get("phase", "done"),
"type": "warning",
"phase": "initializing",
"timestamp": _iso(datetime.now(UTC)),
"payload": {"status": current["status"], "progress": current.get("progress", 0)},
"payload": {
"code": "durable_replay_temporarily_unavailable",
"message": "进度同步暂时不可用,任务仍在继续;正在自动重试。",
"recoverable": True,
},
},
event_id=str(cursor + 1),
)
return
next_durable_poll = loop.time() + _POLL_INTERVAL_S
next_durable_poll = loop.time() + max(_POLL_INTERVAL_S, 3.0)
if live_queue is None:
await asyncio.sleep(max(0.01, next_durable_poll - loop.time()))
continue
@@ -195,17 +195,22 @@ def _intent_thread_metadata(
if not task_id:
return metadata
metadata.update(
{
"taskId": task_id,
"position_roundtable_task_id": task_id,
"position_task_id": f"{task_id}:intelligence",
"position_id": "intelligence",
"position_roundtable_phase": "intent",
}
)
if intent_agent_id == POSITION_INTENT_AGENT_ID:
metadata["position_roundtable_intent_agent_id"] = intent_agent_id
metadata["taskId"] = task_id
# 8BF 使用通用意图接口但有明确的上下文 kind;它不能被岗位会商的
# 会话索引误认为岗位任务,否则两个页面的历史记录会串在一起。
# 其它历史调用保持原有 metadata 形状,避免影响既有会商恢复逻辑。
is_eightbf_context = task_context.get("kind") == "eightbf_roundtable_task"
if intent_agent_id == POSITION_INTENT_AGENT_ID or not is_eightbf_context:
metadata.update(
{
"position_roundtable_task_id": task_id,
"position_task_id": f"{task_id}:intelligence",
"position_id": "intelligence",
"position_roundtable_phase": "intent",
}
)
if intent_agent_id == POSITION_INTENT_AGENT_ID:
metadata["position_roundtable_intent_agent_id"] = intent_agent_id
return metadata