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

fix(config): add stale timeout settings

Browse source
This commit is contained in:
helix4u 2026-04-19 13:40:09 -06:00 • committed by Teknium
parent 440764e013
commit 03e3c22e86
6 changed files with 267 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

14
cli-config.yaml.example
View file

@ -66,15 +66,18 @@ model:
# max_tokens: 8192
# Named provider overrides (optional)
# Use this for per-provider request timeouts and per-model exceptions.
# Use this for per-provider request timeouts, non-stream stale timeouts,
# and per-model exceptions.
# Applies to the primary turn client on every api_mode (OpenAI-wire, native
# Anthropic, and Anthropic-compatible providers), the fallback chain, and
# client rebuilds during credential rotation. For OpenAI-wire chat
# completions (streaming and non-streaming) the configured value is also
# used as the per-request ``timeout=`` kwarg so it wins over the legacy
# HERMES_API_TIMEOUT env var (which still applies when no config is set).
# Leaving these unset keeps the legacy defaults (HERMES_API_TIMEOUT=1800s,
# native Anthropic 900s).
# ``stale_timeout_seconds`` controls the non-streaming stale-call detector and
# wins over the legacy HERMES_API_CALL_STALE_TIMEOUT env var. Leaving these
# unset keeps the legacy defaults (HERMES_API_TIMEOUT=1800s,
# HERMES_API_CALL_STALE_TIMEOUT=300s, native Anthropic 900s).
#
# Not currently wired for AWS Bedrock (bedrock_converse + AnthropicBedrock
# SDK paths) — those use boto3 with its own timeout configuration.
@ -82,11 +85,16 @@ model:
# providers:
# ollama-local:
# request_timeout_seconds: 300 # Longer timeout for local cold-starts
# stale_timeout_seconds: 900 # Explicitly re-enable stale detection on local endpoints
# anthropic:
# request_timeout_seconds: 30 # Fast-fail cloud requests
# models:
# claude-opus-4.6:
# timeout_seconds: 600 # Longer timeout for extended-thinking Opus calls
# openai-codex:
# models:
# gpt-5.4:
# stale_timeout_seconds: 1800 # Longer non-stream stale timeout for slow large-context turns
# =============================================================================
# OpenRouter Provider Routing (only applies when using OpenRouter)