From 611657487f5e925f2079a2e74ad6f06fd8dc4739 Mon Sep 17 00:00:00 2001 From: Teknium Date: Sun, 19 Apr 2026 11:19:37 -0700 Subject: [PATCH] docs(providers): call out Bedrock as not covered by request_timeout_seconds AWS Bedrock paths (bedrock_converse + AnthropicBedrock SDK) use boto3 with its own timeout config and are not wired to the per-provider knob. Documented in cli-config.yaml.example and website configuration.md so users don't expect it to take effect there. --- cli-config.yaml.example | 3 +++ website/docs/user-guide/configuration.md | 2 +- 2 files changed, 4 insertions(+), 1 deletion(-) diff --git a/cli-config.yaml.example b/cli-config.yaml.example index 34a3fc7e540..6bb422ae068 100644 --- a/cli-config.yaml.example +++ b/cli-config.yaml.example @@ -76,6 +76,9 @@ model: # Leaving these unset keeps the legacy defaults (HERMES_API_TIMEOUT=1800s, # native Anthropic 900s). # +# Not currently wired for AWS Bedrock (bedrock_converse + AnthropicBedrock +# SDK paths) — those use boto3 with its own timeout configuration. +# # providers: # ollama-local: # request_timeout_seconds: 300 # Longer timeout for local cold-starts diff --git a/website/docs/user-guide/configuration.md b/website/docs/user-guide/configuration.md index 007794554e5..59ac078bfa9 100644 --- a/website/docs/user-guide/configuration.md +++ b/website/docs/user-guide/configuration.md @@ -75,7 +75,7 @@ For AI provider setup (OpenRouter, Anthropic, Copilot, custom endpoints, self-ho ### Provider Request Timeouts -You can set `providers..request_timeout_seconds` for a provider-wide timeout, plus `providers..models..timeout_seconds` for a model-specific override. Applies to the primary turn client on every transport (OpenAI-wire, native Anthropic, Anthropic-compatible), the fallback chain, rebuilds after credential rotation, and (for OpenAI-wire) the per-request timeout kwarg — so the configured value wins over the legacy `HERMES_API_TIMEOUT` env var. Leaving these unset keeps legacy defaults (`HERMES_API_TIMEOUT=1800`s, native Anthropic 900s). See the commented example in [`cli-config.yaml.example`](https://github.com/NousResearch/hermes-agent/blob/main/cli-config.yaml.example). +You can set `providers..request_timeout_seconds` for a provider-wide timeout, plus `providers..models..timeout_seconds` for a model-specific override. Applies to the primary turn client on every transport (OpenAI-wire, native Anthropic, Anthropic-compatible), the fallback chain, rebuilds after credential rotation, and (for OpenAI-wire) the per-request timeout kwarg — so the configured value wins over the legacy `HERMES_API_TIMEOUT` env var. Leaving these unset keeps legacy defaults (`HERMES_API_TIMEOUT=1800`s, native Anthropic 900s). Not currently wired for AWS Bedrock (both `bedrock_converse` and AnthropicBedrock SDK paths use boto3 with its own timeout configuration). See the commented example in [`cli-config.yaml.example`](https://github.com/NousResearch/hermes-agent/blob/main/cli-config.yaml.example). ## Terminal Backend Configuration