Matt Van Horn 3143d32330 feat(providers): add per-provider and per-model request_timeout_seconds config ... Adds optional providers.<id>.request_timeout_seconds and providers.<id>.models.<model>.timeout_seconds config, resolved via a new hermes_cli/timeouts.py helper and applied where client_kwargs is built in run_agent.py. Zero default behavior change: when both keys are unset, the openai SDK default takes over. Mirrors the existing _get_task_timeout pattern in agent/auxiliary_client.py for auxiliary tasks - the primary turn path just never got the equivalent knob. Cross-project demand: openclaw/openclaw#43946 (17 reactions) asks for exactly this config - specifically calls out Ollama cold-start hanging the client.		2026-04-19 11:23:00 -07:00
..
developer-guide	fix(ci): resolve 4 pre-existing main failures (docs lint + 3 stale tests) (#11373)	2026-04-16 20:43:41 -07:00
getting-started	docs: add PR review guides, rework quickstart, slim down installation	2026-04-19 05:30:50 -07:00
guides	docs: add PR review guides, rework quickstart, slim down installation	2026-04-19 05:30:50 -07:00
integrations	docs(custom-providers): use key_env in examples	2026-04-18 23:07:59 -07:00
reference	feat(skills): consolidate find-nearby into maps as a single location skill	2026-04-19 05:19:22 -07:00
user-guide	feat(providers): add per-provider and per-model request_timeout_seconds config	2026-04-19 11:23:00 -07:00
index.md	fix(docs): show sidebar on docs homepage	2026-04-16 04:24:45 -07:00