vrr/openclaw
2
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-07-09 15:59:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 22

fix(agents): keep finite LLM idle watchdog under unlimited run budgets

Browse source
This commit is contained in:
Ayaan Zaidi 2026-07-08 08:12:27 +05:30
parent c2789b52a7
commit 215be4e4ee
5 changed files with 135 additions and 18 deletions
Download patch file Download diff file Expand all files Collapse all files

14
docs/concepts/agent-loop.md
View file

@ -127,13 +127,13 @@ Assistant deltas buffer into chat `delta` messages. A chat `final` is emitted on
## Timeouts
| Timeout | Default | Notes |
| ------------------------------------------------ | ----------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `agent.wait` | 30s | Wait-only; `timeoutMs` param overrides. Does not stop the underlying run. |
| Agent runtime (`agents.defaults.timeoutSeconds`) | 172800s (48h) | Enforced by `runEmbeddedAgent`'s abort timer. |
| Cron isolated agent turn | owned by cron | The scheduler starts its own timer when execution begins, aborts the run at the configured deadline, then runs bounded cleanup before recording the timeout so a stale child session cannot keep the lane stuck. |
| Model idle timeout | `agents.defaults.timeoutSeconds`, capped at 120s by default | OpenClaw aborts a model request when no response chunks arrive before the idle window. `models.providers.<id>.timeoutSeconds` extends this idle watchdog for slow local/self-hosted providers, but stays bounded by any lower `agents.defaults.timeoutSeconds` or run-specific timeout, since those govern the whole agent run. Cron-triggered cloud model runs with no explicit model/agent timeout use the same default; with an explicit cron run timeout, cloud model stream stalls cap at 60s so configured model fallbacks can still run before the outer cron deadline. Cron-triggered local/self-hosted model runs disable the implicit watchdog unless an explicit timeout is configured; set `models.providers.<id>.timeoutSeconds` for slow local providers. |
| Provider HTTP request timeout | `models.providers.<id>.timeoutSeconds` | Covers connect, headers, body, SDK request timeout, guarded-fetch abort handling, and the model stream idle watchdog for that provider. Use for slow local/self-hosted providers (for example Ollama) before raising the whole agent runtime timeout; keep the agent/runtime timeout at least as high when the model request needs to run longer. |
| Timeout | Default | Notes |
| ------------------------------------------------ | -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `agent.wait` | 30s | Wait-only; `timeoutMs` param overrides. Does not stop the underlying run. |
| Agent runtime (`agents.defaults.timeoutSeconds`) | 172800s (48h) | Enforced by `runEmbeddedAgent`'s abort timer. Set `0` for an unlimited run budget; model stream liveness watchdogs still apply. |
| Cron isolated agent turn | owned by cron | The scheduler starts its own timer when execution begins, aborts the run at the configured deadline, then runs bounded cleanup before recording the timeout so a stale child session cannot keep the lane stuck. |
| Model idle timeout | Cloud 120s; self-hosted 300s | OpenClaw aborts a model request when no response chunks arrive before the idle window. `models.providers.<id>.timeoutSeconds` extends this idle watchdog for slow local/self-hosted providers, but stays bounded by any lower finite `agents.defaults.timeoutSeconds` or run-specific timeout, since those govern the whole agent run. Unlimited run budgets still keep the provider-class idle watchdog. Cron-triggered cloud model runs with no explicit model/agent timeout use the same default; with an explicit cron run timeout, cloud model stream stalls cap at 60s so configured model fallbacks can still run before the outer cron deadline. Cron-triggered local/self-hosted model runs disable the implicit watchdog unless an explicit timeout is configured; set `models.providers.<id>.timeoutSeconds` for slow local providers. |
| Provider HTTP request timeout | `models.providers.<id>.timeoutSeconds` | Covers connect, headers, body, SDK request timeout, guarded-fetch abort handling, and the model stream idle watchdog for that provider. Use for slow local/self-hosted providers (for example Ollama) before raising the whole agent runtime timeout; keep the agent/runtime timeout at least as high when the model request needs to run longer. |
### Stuck session diagnostics