fix(chat): resolve Auto-route failover event-loop freeze (#812)

Root cause: ensure_structured_column() executed a synchronous blocking
engine.connect().execute(SELECT information_schema.columns ...) inside the
async request path (_build_chat_history / _maybe_compress_history), freezing
the uvicorn event loop and hanging all endpoints (~200s, recovered only by
docker restart).

Fix:
- chat_context.py: remove per-request ensure_structured_column() calls; run
  once idempotently at app startup (main.py lifespan). Use CURRENT_DATABASE()
  for PostgreSQL compatibility.
- main.py: add startup-only ensure_structured_column() hook (try/except).
- llm_client.py: trust_env=False + bounded httpx.Timeout/wait_for so broken
  endpoints fail fast instead of hanging the event loop.
- chat_service.py: run media generation in a background daemon thread with its
  own event loop (_launch_media_task_bg) so SSE end does not cancel image/video
  tasks (#811); remove TEMP faulthandler diagnostic.

Safe-align: persist accumulated live container changes (admin/*, knowledge,
market, models, config, observability, mcp_client, platform_knowledge,
im_bot_platform, chat_media, capability_registry, requirements) and add
workflow_templates.

Verified: live failover test (model-006 -> conn-refused) returns in ~1.9s with
concurrent login 0.83s/200; event-loop responsiveness restored (sub-second).
This commit is contained in:
QihuAI Design committed 2026-07-26 00:35:35 +08:00
1 parent 394a7786e0
commit a2504bce34
27 files changed
+253 -59

No files matched your search

+2 -2
View File
@@ -1,8 +1,8 @@
"""
MCP (Model Context Protocol) 客户端 —— 基于官方 `mcp` Python SDK (Phase 1.E 标准化)
MCP (Model Context Protocol) 客户端 —— 基于官方 \"mcp\" Python SDK (Phase 1.E 标准化)
设计基准(标准对照表见 STANDARDS_AUDIT_2026-07-24.md §E):
- 采用 Anthropic 官方 `mcp` SDK 处理 JSON-RPC 帧 + 协议版本协商,
- 采用 Anthropic 官方 \"mcp\" SDK 处理 JSON-RPC 帧 + 协议版本协商,
不再手写解析、不再写死 MCP_PROTOCOL_VERSION 常量(旧实现写死 "2024-11-05",
上游协议一升级即碎)。
- 支持 streamable_http(默认)与 sse 两种传输,按 server['transport_type'] 选择。