vultr/openclaw
1
0
Fork 0
mirror of https://github.com/openclaw/openclaw.git synced 2026-05-06 12:50:42 +00:00
Code Issues Packages Projects Releases Wiki Activity

fix(gateway): recover stale session lanes

Browse Source
This commit is contained in:
Peter Steinberger
2026-04-28 20:36:40 +01:00
parent 933c7968dc
commit c500e8704f
14 changed files with 729 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
docs/concepts/agent-loop.md
View File

@@ -162,6 +162,7 @@ surfaces, while Codex native hooks remain a separate lower-level Codex mechanism
- `agent.wait` default: 30s (just the wait). `timeoutMs` param overrides.
- Agent runtime: `agents.defaults.timeoutSeconds` default 172800s (48 hours); enforced in `runEmbeddedPiAgent` abort timer.
- Stuck-session recovery: with diagnostics enabled, `diagnostics.stuckSessionWarnMs` detects long `processing` sessions. Active embedded runs, active reply operations, and active session-lane tasks remain warning-only by default; if diagnostics show no active work for the session, the watchdog releases the affected session lane so queued startup work can drain.
- Model idle timeout: 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; otherwise OpenClaw uses `agents.defaults.timeoutSeconds` when configured, capped at 120s by default. Cron-triggered runs with no explicit model or agent timeout disable the idle watchdog and rely on the cron outer timeout.
- Provider HTTP request timeout: `models.providers.<id>.timeoutSeconds` applies to that provider's model HTTP fetches, including connect, headers, body, SDK request timeout, total guarded-fetch abort handling, and model stream idle watchdog. Use this for slow local/self-hosted providers such as Ollama before raising the whole agent runtime timeout.

1
docs/concepts/queue.md
View File

@@ -85,6 +85,7 @@ Defaults: `debounceMs: 1000`, `cap: 20`, `drop: summarize`.
- If commands seem stuck, enable verbose logs and look for “queued for …ms” lines to confirm the queue is draining.
- If you need queue depth, enable verbose logs and watch for queue timing lines.
- When diagnostics are enabled, sessions that remain in `processing` past `diagnostics.stuckSessionWarnMs` log a stuck-session warning. Active embedded runs, active reply operations, and active lane tasks remain warning-only by default; stale startup bookkeeping with no active session work can release the affected session lane so queued work drains.
## Related