功能迁移,页面整体样式修改
This commit is contained in:
1 parent
04664c8d42
commit
bfd75da308
41 files changed
+2232
-1920
No files matched your search
@@ -71,12 +71,6 @@ logger = logging.getLogger(__name__)
|
||||
# firing signals into a worker that is stuck waiting for shutdown cleanup.
|
||||
_SHUTDOWN_HOOK_TIMEOUT_SECONDS = 5.0
|
||||
|
||||
# AI 写作 in-flight task 收尾的最大等待时间。一个 graph 片段通常在几秒内
|
||||
# 跑到下一个 interrupt 或结束,但单段草稿生成走完整个 LLM 可能耗时较久,
|
||||
# 给 30 秒兜底;超时则 cancel 强制结束,已落盘的 checkpoint 仍可用于重启
|
||||
# 后恢复,丢的只是最后一段 in-flight 但未 checkpoint 的进度。
|
||||
_AI_WRITING_DRAIN_TIMEOUT_SECONDS = 30.0
|
||||
|
||||
|
||||
async def _ensure_admin_user(app: FastAPI) -> None:
|
||||
"""Startup hook: handle first boot and migrate orphan threads otherwise.
|
||||
@@ -371,11 +365,10 @@ async def _curator_scheduler_loop() -> None:
|
||||
def _warn_if_multi_worker() -> None:
|
||||
"""检测 uvicorn / gunicorn 多 worker 部署并打 ERROR 日志。
|
||||
|
||||
AI 写作 + 主 agent 流式响应都依赖**进程内**的内存状态字典
|
||||
(``_event_queues``、``_session_pending_pause`` 等)。多 worker 下,
|
||||
用户的 /start /stream /resume 会被 OS 随机分配到不同 worker,
|
||||
per-worker 的内存字典互相看不见 → SSE 事件丢失、会话「凭空消失」、
|
||||
resume 走不通。
|
||||
主 agent / canvas / AI 写作流式响应在 Gateway 进程内通过 ``StreamBridge``
|
||||
维护 run_id → SSE 订阅者的内存 map。多 worker 下,用户在 worker A 发起
|
||||
``/runs/stream``、稍后在 worker B 调 join/resume,会因 in-process map 互相
|
||||
看不见而 404 / 卡死。
|
||||
|
||||
所以这里在 startup 打 ERROR 强提醒。**不抛异常 fail-fast** —— 万一
|
||||
运维确实知道自己在干嘛(比如配了 sticky session),不应该阻止启动。
|
||||
@@ -474,7 +467,7 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
|
||||
try:
|
||||
from app.gateway.ai_writing_cleanup import cleanup_scheduler_loop
|
||||
|
||||
app.state.ai_writing_cleanup_task = asyncio.create_task(cleanup_scheduler_loop())
|
||||
app.state.ai_writing_cleanup_task = asyncio.create_task(cleanup_scheduler_loop(app))
|
||||
except Exception:
|
||||
logger.exception("AI writing cleanup scheduler failed to start (non-fatal)")
|
||||
|
||||
@@ -526,32 +519,9 @@ async def lifespan(app: FastAPI) -> AsyncGenerator[None, None]:
|
||||
except Exception:
|
||||
logger.exception("AI writing cleanup scheduler shutdown error")
|
||||
|
||||
# 等待所有 in-flight 写作 graph task 跑到下一个 interrupt / 结束。
|
||||
# 这是「写作流程能完整继续」的关键 —— 如果直接关 checkpointer
|
||||
# connection,正在跑 astream 的 task 会在写 checkpoint 时抛错,
|
||||
# 已经生成但还没落盘的进度全丢。
|
||||
try:
|
||||
from app.gateway.routers.ai_writing import wait_for_inflight_graph_tasks
|
||||
|
||||
await wait_for_inflight_graph_tasks(timeout=_AI_WRITING_DRAIN_TIMEOUT_SECONDS)
|
||||
except Exception:
|
||||
logger.exception("Wait for in-flight AI writing tasks failed (non-fatal)")
|
||||
|
||||
# 关闭 AI 写作 graph 持有的 checkpointer 连接(aiosqlite Connection / pg pool)
|
||||
try:
|
||||
from deerflow.agents.ai_writing.graph import shutdown_ai_writing_graph
|
||||
|
||||
await asyncio.wait_for(
|
||||
shutdown_ai_writing_graph(),
|
||||
timeout=_SHUTDOWN_HOOK_TIMEOUT_SECONDS,
|
||||
)
|
||||
except TimeoutError:
|
||||
logger.warning(
|
||||
"AI writing checkpointer shutdown exceeded %.1fs; proceeding with worker exit.",
|
||||
_SHUTDOWN_HOOK_TIMEOUT_SECONDS,
|
||||
)
|
||||
except Exception:
|
||||
logger.exception("Failed to shutdown AI writing checkpointer")
|
||||
# 阶段 7 删冗余:AI 写作 graph 不再自管 checkpointer / in-flight task;
|
||||
# thread 状态由 LangGraph Server 主 checkpointer 接管,lifespan 出口由
|
||||
# ``langgraph_runtime()`` 的 contextmanager 统一关闭,无需在这里特殊处理。
|
||||
|
||||
try:
|
||||
scheduler_service = getattr(app.state, "scheduled_task_service", None)
|
||||
|
||||
Reference in new issue
Block a user