Chiguyong ed1e289785 fix(board): add first-chunk timeout to _stream_expert_speech ... Commit 36b0296 changed expert speech generation from gateway.chat() (non-streaming) to gateway.chat_stream() (streaming) for progressive UI output. However, DashScope/DeepSeek via LiteLLM occasionally accept the streaming request but never emit the first SSE chunk — the async generator hangs indefinitely with no error and no timeout, freezing the entire board. Root cause: `async for chunk in gateway.chat_stream(...)` blocks forever when the provider silently stalls. The moderator path (gateway.chat) still works because it's synchronous — that's why the moderator opening always succeeds but experts hang. Fix: pull the first chunk via `__anext__()` wrapped in `asyncio.wait_for(timeout=30s)`. If no chunk arrives within 30s, close the stream and fall back to non-streaming gateway.chat() + _replay_stream() (which splits the response into small chunks for progressive UI rendering). This preserves the "逐个输出" UX while guaranteeing the board never hangs on a stalled streaming provider. Add 4 unit tests covering: - Normal streaming works (existing path) - First-chunk timeout → fallback to chat() - Empty stream → fallback to chat() - chat_stream raising → fallback to chat() E2E verification: 5-expert board with DashScope completes in ~277s (status=completed), all experts produce content, no hang. Same branch as the earlier _handle_llm_gateway fix (commit d0fe661).		2026-07-06 15:35:15 +08:00
..
documents	feat(documents): add document processing capability (U1-U9)	2026-06-23 15:05:01 +08:00
e2e	refactor: remove all emoji from source code (#20)	2026-07-03 02:46:40 +08:00
integration	fix(review): apply ce-code-review findings	2026-06-30 12:42:15 +08:00
manual	test(u6): add L4 real-LLM smoke test for ReAct tool-use prompt	2026-07-02 22:08:45 +08:00
routes	feat(documents): add document processing capability (U1-U9)	2026-06-23 15:05:01 +08:00
tools	feat(documents): add document processing capability (U1-U9)	2026-06-23 15:05:01 +08:00
unit	fix(board): add first-chunk timeout to _stream_expert_speech	2026-07-06 15:35:15 +08:00
__init__.py	feat: initial fischer-agentkit package with unified agent architecture	2026-06-04 22:24:06 +08:00
conftest.py	fix: 私董会数据持久化修复 + emoji 移除计划	2026-07-02 01:07:12 +08:00
test_routing_chain.py	feat: accumulated frontend enhancements, docs, and static assets	2026-06-14 16:35:01 +08:00