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

1
website/docs/reference/environment-variables.md
View file

@ -360,6 +360,7 @@ For cloud sandbox backends, persistence is filesystem-oriented. `TERMINAL_LIFETI
| `HERMES_HUMAN_DELAY_MAX_MS` | Custom delay range maximum (ms) |
| `HERMES_QUIET` | Suppress non-essential output (`true`/`false`) |
| `HERMES_API_TIMEOUT` | LLM API call timeout in seconds (default: `1800`) |
| `HERMES_API_CALL_STALE_TIMEOUT` | Non-streaming stale-call timeout in seconds (default: `300`). Auto-disabled for local providers when left unset. Also configurable via `providers.<id>.stale_timeout_seconds` or `providers.<id>.models.<model>.stale_timeout_seconds` in `config.yaml`. |
| `HERMES_STREAM_READ_TIMEOUT` | Streaming socket read timeout in seconds (default: `120`). Auto-increased to `HERMES_API_TIMEOUT` for local providers. Increase if local LLMs time out during long code generation. |
| `HERMES_STREAM_STALE_TIMEOUT` | Stale stream detection timeout in seconds (default: `180`). Auto-disabled for local providers. Triggers connection kill if no chunks arrive within this window. |
| `HERMES_EXEC_ASK` | Enable execution approval prompts in gateway mode (`true`/`false`) |

21
website/docs/user-guide/configuration.md
View file

@ -73,9 +73,13 @@ Multiple references in a single value work: `url: "${HOST}:${PORT}"`. If a refer
For AI provider setup (OpenRouter, Anthropic, Copilot, custom endpoints, self-hosted LLMs, fallback models, etc.), see [AI Providers](/docs/integrations/providers).
### Provider Request Timeouts
### Provider Timeouts
You can set `providers.<id>.request_timeout_seconds` for a provider-wide timeout, plus `providers.<id>.models.<model>.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).
You can set `providers.<id>.request_timeout_seconds` for a provider-wide request timeout, plus `providers.<id>.models.<model>.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.
You can also set `providers.<id>.stale_timeout_seconds` for the non-streaming stale-call detector, plus `providers.<id>.models.<model>.stale_timeout_seconds` for a model-specific override. This wins over the legacy `HERMES_API_CALL_STALE_TIMEOUT` env var.
Leaving these unset keeps the legacy defaults (`HERMES_API_TIMEOUT=1800`s, `HERMES_API_CALL_STALE_TIMEOUT=300`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
@ -554,20 +558,23 @@ Budget pressure is enabled by default. The agent sees warnings naturally as part
When the iteration budget is fully exhausted, the CLI shows a notification to the user: `⚠ Iteration budget reached (90/90) — response may be incomplete`. If the budget runs out during active work, the agent generates a summary of what was accomplished before stopping.
### Streaming Timeouts
### API Timeouts
The LLM streaming connection has two timeout layers. Both auto-adjust for local providers (localhost, LAN IPs) — no configuration needed for most setups.
Hermes has separate timeout layers for streaming, plus a stale detector for non-streaming calls. The stale detectors auto-adjust for local providers only when you leave them at their implicit defaults.
| Timeout | Default | Local providers | Env var |
|---------|---------|----------------|---------|
| Timeout | Default | Local providers | Config / env |
|---------|---------|----------------|--------------|
| Socket read timeout | 120s | Auto-raised to 1800s | `HERMES_STREAM_READ_TIMEOUT` |
| Stale stream detection | 180s | Auto-disabled | `HERMES_STREAM_STALE_TIMEOUT` |
| API call (non-streaming) | 1800s | Unchanged | `HERMES_API_TIMEOUT` |
| Stale non-stream detection | 300s | Auto-disabled when left implicit | `providers.<id>.stale_timeout_seconds` or `HERMES_API_CALL_STALE_TIMEOUT` |
| API call (non-streaming) | 1800s | Unchanged | `providers.<id>.request_timeout_seconds` / `timeout_seconds` or `HERMES_API_TIMEOUT` |
The **socket read timeout** controls how long httpx waits for the next chunk of data from the provider. Local LLMs can take minutes for prefill on large contexts before producing the first token, so Hermes raises this to 30 minutes when it detects a local endpoint. If you explicitly set `HERMES_STREAM_READ_TIMEOUT`, that value is always used regardless of endpoint detection.
The **stale stream detection** kills connections that receive SSE keep-alive pings but no actual content. This is disabled entirely for local providers since they don't send keep-alive pings during prefill.
The **stale non-stream detection** kills non-streaming calls that produce no response for too long. By default Hermes disables this on local endpoints to avoid false positives during long prefills. If you explicitly set `providers.<id>.stale_timeout_seconds`, `providers.<id>.models.<model>.stale_timeout_seconds`, or `HERMES_API_CALL_STALE_TIMEOUT`, that explicit value is honored even on local endpoints.
## Context Pressure Warnings
Separate from iteration budget pressure, context pressure tracks how close the conversation is to the **compaction threshold** — the point where context compression fires to summarize older messages. This helps both you and the agent understand when the conversation is getting long.