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): enforce request_timeout_seconds on OpenAI-wire primary calls

Browse source 
Live test with timeout_seconds: 0.5 on claude-sonnet-4.6 proved the
initial wiring was insufficient: run_agent.py was overriding the
client-level timeout on every call via hardcoded per-request kwargs.

Root cause: run_agent.py had two sites that pass an explicit timeout=
kwarg into chat.completions.create() — api_kwargs['timeout'] at line
7075 (HERMES_API_TIMEOUT=1800s default) and the streaming path's
_httpx.Timeout(..., read=HERMES_STREAM_READ_TIMEOUT=120s, ...) at line
5760. Both override the per-provider config value the client was
constructed with, so a 0.5s config timeout would silently not enforce.

This commit:
- Adds AIAgent._resolved_api_call_timeout() — config > HERMES_API_TIMEOUT env > 1800s default.
- Uses it for the non-streaming api_kwargs['timeout'] field.
- Uses it for the streaming path's httpx.Timeout(connect, read, write, pool)
  so both connect and read respect the configured value when set.
  Local-provider auto-bump (Ollama/vLLM cold-start) only applies when
  no explicit config value is set.
- New test: test_resolved_api_call_timeout_priority covers all three
  precedence cases (config, env, default).

Live verified: 0.5s config on claude-sonnet-4.6 now triggers
APITimeoutError at ~3s per retry, exhausts 3 retries in ~15s total
(was: 29-47s success with timeout ignored). Positive case (60s config
+ gpt-4o-mini) still succeeds at 1.3s.
This commit is contained in:
Teknium 2026-04-19 11:10:47 -07:00 • committed by Teknium
parent f1fe29d1c3
commit c11ab6f64d
4 changed files with 115 additions and 16 deletions
Download patch file Download diff file Expand all files Collapse all files

8
cli-config.yaml.example
View file

@ -69,8 +69,12 @@ model:
# Use this for per-provider request 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. Leaving these unset keeps the
# SDK defaults (OpenAI ≈ 600s, native Anthropic 900s).
# 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).
#
# providers:
# ollama-local: