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

@@ -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