mirrors/hermes-agent
1
0
Fork 0
mirror of https://github.com/NousResearch/hermes-agent.git synced 2026-04-25 00:51:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(providers): add per-provider and per-model request_timeout_seconds config

Browse source 
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.
This commit is contained in:
Matt Van Horn 2026-04-18 21:38:31 -07:00 • committed by Teknium
parent fd119a1c4a
commit 3143d32330
5 changed files with 141 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

14
cli-config.yaml.example
View file

@ -63,7 +63,19 @@ model:
# Leave unset to use the model's native output ceiling (recommended).
# Set only if you want to deliberately limit individual response length.
#
# max_tokens: 8192
# max_tokens: 8192
# Named provider overrides (optional)
# Use this for per-provider request timeouts and per-model exceptions.
#
# providers:
# ollama-local:
# request_timeout_seconds: 300 # Longer timeout for local cold-starts
# anthropic:
# request_timeout_seconds: 30 # Fast-fail cloud requests
# models:
# claude-opus-4.6:
# timeout_seconds: 600 # Longer timeout for extended-thinking Opus calls
# =============================================================================
# OpenRouter Provider Routing (only applies when using OpenRouter)