5c32bd10ec
* fix(llm): set HTTP timeout on Gemini clients (#785) * fix(embedding): set HTTP timeout on Gemini embedding client (#785) Same wedge-class failure as the LLM client: a stalled Gemini embedding socket hangs the in-process reconciler, which shares the deriver worker's uvloop event loop. Apply the same 10-minute timeout here, in lockstep with src/llm/registry.py's _build_gemini_http_options. * style(test): drop extra blank line in test_registry imports |
||
|---|---|---|
| .. | ||
| backends | ||
| __init__.py | ||
| api.py | ||
| backend.py | ||
| caching.py | ||
| capture.py | ||
| conversation.py | ||
| credentials.py | ||
| executor.py | ||
| history_adapters.py | ||
| registry.py | ||
| request_builder.py | ||
| runtime.py | ||
| structured_output.py | ||
| tool_loop.py | ||
| types.py | ||