DEFAULT_VOID_HOOK_TIMEOUT_MS_BY_HOOK only listed agent_end, so the
before_compaction and after_compaction void hooks ran fully unbounded
when a plugin supplied no hook.timeoutMs. In the codex agent harness
these hooks fire on the serialized notification queue, so a slow or hung
handler froze processing of every later codex notification — including
turn/completed — hanging the whole agent turn.
Add defensive default timeout entries for both hooks, mirroring the
existing agent_end pattern. The budget matches agent_end's 30s rather
than the tighter modifying-hook defaults because compaction hooks can
legitimately do real work (e.g. a memory flush). The runner is fail-open
for void hooks, so a timed-out handler is logged and compaction proceeds.
Fixes#83901. Honors Commander negated option handling for ACP prompt-prefix forwarding and adds focused CLI regression coverage. Verified with Crabbox AWS cbx_1689d0ad78e9 run run_a406418db6fe and Real behavior proof run 26127392365.
Summary:
- The PR registers Twitch refreshing-token users with Twurple's chat intent and adds regression coverage for that contract.
- Reproducibility: yes. by source and dependency contract. Current main does not register the chat intent, and ... RefreshingAuthProvider only resolves getAccessTokenForIntent('chat') when that intent is mapped to a user.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(twitch): register chat intent for refreshing auth
Validation:
- ClawSweeper review passed for head 1fdadcff04.
- Required merge gates passed before the squash merge.
Prepared head SHA: 1fdadcff04
Review: https://github.com/openclaw/openclaw/pull/83750#issuecomment-4481748086
Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Summary:
- The PR pins managed Gateway package updates, runtime preflight, post-install doctor, post-core update, service refresh, and restart follow-ups to the Node binary and package root baked into the Gateway service.
- Reproducibility: yes. source-level. Current main validates and follows up with the shell process Node in the ... body provides a concrete two-Node Docker reproduction, though I did not execute it in this read-only pass.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(update): detect service node mismatch even when package roots match
- PR branch already contained follow-up commit before automerge: fix(update): pin package install to service root when nodes differ wi…
Validation:
- ClawSweeper review passed for head 5607e441f6.
- Required merge gates passed before the squash merge.
Prepared head SHA: 5607e441f6
Review: https://github.com/openclaw/openclaw/pull/84043#issuecomment-4485613931
Co-authored-by: Alex Knight <15041791+amknight@users.noreply.github.com>
Co-authored-by: Alex Knight <aknight@atlassian.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: amknight
Co-authored-by: amknight <15041791+amknight@users.noreply.github.com>
Follow-up to #75451. Threads optional discovery?: PluginDiscoveryResult
through the remaining helpers that still call discoverOpenClawPlugins
internally during startup:
- loadOpenClawPlugins / loadOpenClawPluginCliRegistry (src/plugins/loader.ts):
add discovery? to PluginLoadOptions and consult it before falling back to
an internal scan at both call sites.
- loadPluginManifestRegistry (src/plugins/manifest-registry.ts): accept
discovery? as a more ergonomic alternative to the existing candidates? /
diagnostics? pair; candidates? still wins when both are supplied.
- resolveInstalledPluginIndexRegistry (src/plugins/installed-plugin-index-registry.ts):
add discovery? to LoadInstalledPluginIndexParams and use it when
candidates aren't supplied.
- resolvePluginConfigContractsById (src/plugins/config-contracts.ts): add
discovery? and thread it into the bundled-fallback discovery call.
Add discovery-threading.test.ts asserting each entry point skips its
internal discoverOpenClawPlugins call when discovery is supplied, calls it
when nothing is supplied, and prefers explicit candidates over discovery
when both are present (6 tests, all pass).
discoverOpenClawPlugins remains stateless; sharing is function-scoped per
src/plugins/CLAUDE.md guidance. Backward compatible: every change is
additive (new optional param).
Add optional discovery parameter to loadBundledCapabilityRuntimeRegistry,
resolveBundledPluginSources, and listChannelCatalogEntries so callers
that already hold a PluginDiscoveryResult can skip redundant filesystem
walks.
In contracts/registry.ts, the retry loop in
loadScopedCapabilityRuntimeRegistryEntries computes discovery once
and shares it across retry attempts (function-scoped, not module-scoped).
discoverOpenClawPlugins() itself remains stateless with no hidden cache.
Closes#82308
Signed-off-by: Sebastien Tardif <sebtardif@ncf.ca>
Summary:
- The PR changes one bullet in `docs/tools/slash-commands.md` to distinguish `/new` from `/reset` and remove the misleading alias wording.
- Reproducibility: yes. Reading current main reproduces the misleading docs line at `docs/tools/slash-commands.md:127`, and adjacent source/tests show `/new` and `/reset` take different paths in the Control UI.
Automerge notes:
- PR branch already contained follow-up commit before automerge: docs/slash-commands: drop inaccurate Control UI/ACP cross-reference (…
- PR branch already contained follow-up commit before automerge: Merge branch 'main' into docs/fix-reset-alias-misleading
Validation:
- ClawSweeper review passed for head bb92b6050a.
- Required merge gates passed before the squash merge.
Prepared head SHA: bb92b6050a
Review: https://github.com/openclaw/openclaw/pull/81073#issuecomment-4432165259
Co-authored-by: Md. Al-Mosabbir Rakib <mrakib50.cse@gmail.com>
Co-authored-by: Md. Al-Mosabbir Rakib <34891461+mosabbirrakib@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The PR updates `docs/cli/gateway.md` and `docs/reference/test.md` to document Gateway startup/restart benchmark prerequisites, commands, case IDs, probes, output semantics, and platform limits.
- Reproducibility: not applicable. as a runtime bug; docs correctness is source-checkable against the benchmar ... ipts, and readiness source. The current PR head corrected the earlier startup-hook readiness wording issue.
Automerge notes:
- PR branch already contained follow-up commit before automerge: docs(gateway): correct benchmark readiness wording
Validation:
- ClawSweeper review passed for head 5bd0f6c463.
- Required merge gates passed before the squash merge.
Prepared head SHA: 5bd0f6c463
Review: https://github.com/openclaw/openclaw/pull/83866#issuecomment-4483820005
Co-authored-by: samzong <samzong.lu@gmail.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
The schema.help text for `models.providers.*.timeoutSeconds` documents the
key as the user-facing knob for "slow local or self-hosted model servers".
In practice the option is also the only configurable lever for the LLM
idle/first-token watchdog. However `resolveLlmIdleTimeoutMs` was still
running the explicit provider timeout through `clampImplicitTimeoutMs`,
clamping it back down to the implicit ~120s `DEFAULT_LLM_IDLE_TIMEOUT_MS`
ceiling for any non-cron, non-local provider.
Consequence (matches #77744 and #78361):
- User sets `models.providers.llamacpp.timeoutSeconds: 14400` (or 600 for
a slow Gemini/Opus turn with a large tool payload).
- Hot reload accepts the value, runtime resolves
`modelRequestTimeoutMs = 14_400_000`.
- Idle watchdog still trips at ~120s with
"LLM idle timeout (120s): no response from model", aborting an
otherwise-healthy upstream that is mid-prefill or buffering thinking
tokens.
Fix: when the caller passes an explicit `modelRequestTimeoutMs`
(sourced from `models.providers.<id>.timeoutSeconds` /
`model.requestTimeoutMs`), treat it as a deliberate ceiling for cloud
providers too. The run-timeout / agent-timeout bounds still apply via
`timeoutBounds`, so a shorter explicit run timeout always wins. The
implicit default watchdog still kicks in when the user has not set a
provider timeout, preserving the network-silence-as-hang guard for
default configs.
Updated the two corresponding test cases that asserted the old
clamp-on-cloud behavior; all 71 tests in `llm-idle-timeout.test.ts`
and the wider 430-test `src/agents/pi-embedded-runner/run/` lane pass.
Schema help text refreshed to call out that the same knob raises the
idle watchdog ceiling.
Refs: #77744, #78361
Summary:
- The PR changes `openclaw acp client` error handling to use `formatErrorMessage`, adds a plain-object rejection regression test, and adds a changelog entry.
- Reproducibility: yes. Current main visibly sends `openclaw acp client` caught errors through `String(err)`, ... catch already uses `formatErrorMessage`; I did not run a live failing ACP server in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(cli): format acp client errors with formatErrorMessage (#83904)
Validation:
- ClawSweeper review passed for head 69ef0e7270.
- Required merge gates passed before the squash merge.
Prepared head SHA: 69ef0e7270
Review: https://github.com/openclaw/openclaw/pull/84080#issuecomment-4486666922
Co-authored-by: HCL <chenglunhu@gmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The branch adds per-agent `agents.list[].experimental.localModelLean` config and applies lean tool filtering through agent, session, and default-agent resolution.
- Reproducibility: not applicable. this is a feature/config PR rather than a current-main bug report. The chan ... or is supported by source review, focused tests in the branch, and the PR body's redacted live runtime log.
Automerge notes:
- PR branch already contained follow-up commit before automerge: feat(agents): support per-agent local model lean mode
- PR branch already contained follow-up commit before automerge: fix(clawsweeper): address review for automerge-openclaw-openclaw-8407…
Validation:
- ClawSweeper review passed for head 1f9a9554da.
- Required merge gates passed before the squash merge.
Prepared head SHA: 1f9a9554da
Review: https://github.com/openclaw/openclaw/pull/84073#issuecomment-4486397570
Co-authored-by: Bob <dutifulbob@gmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: osolmaz
Co-authored-by: osolmaz <2453968+osolmaz@users.noreply.github.com>
Summary:
- The PR updates `openclaw channels logs` tail-window reading to keep a complete first line when the 1 MB window starts on a newline boundary, adds a regression test, and adds a changelog entry.
- Reproducibility: yes. Source inspection on current main shows the unconditional first-line drop, and the PR ... s provide terminal before/after CLI output for a 2 MB log whose tail window starts exactly after a newline.
Automerge notes:
- PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'origin/main' into fix/channels-logs-dro…
- PR branch already contained follow-up commit before automerge: fix(cli): preserve first line of channels logs at window boundary
Validation:
- ClawSweeper review passed for head 284b312b31.
- Required merge gates passed before the squash merge.
Prepared head SHA: 284b312b31
Review: https://github.com/openclaw/openclaw/pull/84106#issuecomment-4487313048
Co-authored-by: BSG2000 <bsg2000@users.noreply.github.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The branch updates queue-by-channel config schema/types for Matrix, Google Chat, and Mattermost, refreshes config baseline hashes, adds config/schema regression tests, and records the user-visible fix in the changelog.
- Reproducibility: yes. Source inspection gives a high-confidence path: current main's strict `messages.queue. ... matrix`, and the linked source PR records the same config failing before the patch and validating after it.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 3865178550.
- Required merge gates passed before the squash merge.
Prepared head SHA: 3865178550
Review: https://github.com/openclaw/openclaw/pull/84104#issuecomment-4487285061
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- Adds shared Control UI session-run active-state handling, applies terminal-status precedence in chat/session rendering and lifecycle recovery, and adds focused regressions plus a changelog entry.
- Reproducibility: yes. Current main has a source-visible path where `status: "done"` plus stale `hasActiveRun ... eeps abort/in-progress UI alive, and the linked proof exercises the fixed stale-terminal state in Chromium.
Automerge notes:
- PR branch already contained follow-up commit before automerge: [codex] Fix Control UI terminal run status recovery
Validation:
- ClawSweeper review passed for head f9f503add0.
- Required merge gates passed before the squash merge.
Prepared head SHA: f9f503add0
Review: https://github.com/openclaw/openclaw/pull/84112#issuecomment-4487409085
Co-authored-by: NianJiuZst <3235467914@qq.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- This PR updates CLI root option parsing to preserve embedded equals signs, adds focused Vitest coverage for inline and space-separated values, and records the fix in the changelog.
- Reproducibility: yes. by source inspection: current main uses `raw.split("=", 2)`, so `--token=abc=def` returns only `abc`; the PR body also supplies after-fix live output for the same path.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(cli): preserve equals in root option values [AI-assisted]
Validation:
- ClawSweeper review passed for head 8a15801e79.
- Required merge gates passed before the squash merge.
Prepared head SHA: 8a15801e79
Review: https://github.com/openclaw/openclaw/pull/84107#issuecomment-4487314163
Co-authored-by: Thiago Costa <thiago12_fera@hotmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The PR adds a 65,535 upper-bound check to the shared CLI `parsePort` helper, a colocated regression test, and a changelog entry for the linked port-range bug.
- Reproducibility: yes. Source inspection on current main shows `parsePort('99999')` delegates to `parseStrict ... sitive safe integer, so the return would be `99999`; I did not execute it because this review is read-only.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(cli): reject out-of-range port numbers in parsePort (#83900)
Validation:
- ClawSweeper review passed for head 9ad0705c44.
- Required merge gates passed before the squash merge.
Prepared head SHA: 9ad0705c44
Review: https://github.com/openclaw/openclaw/pull/84008#issuecomment-4484883200
Co-authored-by: HCL <chenglunhu@gmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- This PR moves the existing Motivation section in `.github/pull_request_template.md` from below Linked Issue/PR to immediately after Summary without changing the section text.
- Reproducibility: not applicable. this is a PR-template ordering cleanup, not a runtime bug. Source inspection of current main and the PR head verifies the before/after section order.
Automerge notes:
- PR branch already contained follow-up commit before automerge: chore: move Motivation section above Change Type in PR template
Validation:
- ClawSweeper review passed for head 6c68583fac.
- Required merge gates passed before the squash merge.
Prepared head SHA: 6c68583fac
Review: https://github.com/openclaw/openclaw/pull/84098#issuecomment-4487082864
Co-authored-by: Huan Jiang <seraphjiang@gmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- The branch makes unknown-capabilities Ollama model definitions explicitly tool-capable, adds regression assertions and changelog text, and guards the issue-labeler job to run only on issue events.
- Reproducibility: yes. for the metadata gap: current main builds unknown-capabilities Ollama models without a ... er-fix live provider output with `supportsTools: true`. I did not run local tests in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(ollama): default unknown capabilities to tools
Validation:
- ClawSweeper review passed for head 27527716c0.
- Required merge gates passed before the squash merge.
Prepared head SHA: 27527716c0
Review: https://github.com/openclaw/openclaw/pull/84075#issuecomment-4486492661
Co-authored-by: Bob <dutifulbob@gmail.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: osolmaz
Co-authored-by: osolmaz <2453968+osolmaz@users.noreply.github.com>
Summary:
- The branch adds a close lifecycle for local memory embedding providers, scoped memory search/index teardown for one agent, Active Memory timeout cleanup, focused tests, and a changelog entry.
- Reproducibility: yes. The linked issue gives a concrete OpenClaw 2026.5.18 Telegram Active Memory timeout pa ... current-main source inspection confirms there is no timeout cleanup for that local embedding provider path.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(memory): close local embedding providers on timeout
Validation:
- ClawSweeper review passed for head 8e2e369b5c.
- Required merge gates passed before the squash merge.
Prepared head SHA: 8e2e369b5c
Review: https://github.com/openclaw/openclaw/pull/84048#issuecomment-4485705481
Co-authored-by: brokemac79 <martin_cleary@yahoo.co.uk>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: hxy91819
Co-authored-by: hxy91819 <8814856+hxy91819@users.noreply.github.com>
Adds bounded queued-writer diagnostics to pi-trajectory-flush cleanup timeout warnings so operators can see pending write count, queued bytes, active operation, and append size without exposing paths or payloads.
Closes#82961
Recover stale subagent completion delivery by retrying unsupported transcript-wait wakes without transcript waiting and forcing the existing message-tool handoff when the requester run is stale and direct completion is invisible.\n\nAdds regression coverage for the stale wake sequence and records the maintainer changelog entry.\n\nFixes #83699.
* fix config provider timeout overlays
Allow bundled model provider config entries to act as overlays so fields like timeoutSeconds can be configured without redeclaring baseUrl and models. Keep unknown custom provider declarations strict, and guard configured-provider fallback against overlay entries without models.
* fix(config): include provider aliases in model overlays
* fix(config): guard Foundry timeout overlays
* fix(config): normalize bundled provider overlays
* fix(models): reject overlay-only fallback models
Summary:
- The PR updates WhatsApp inbound listener and group-drop diagnostics, adds focused tests, and documents that observed but unregistered groups must be admitted through `channels.whatsapp.groups`.
- Reproducibility: yes. from source inspection: current main still emits the DM-only startup log and vague gro ... sions/whatsapp/src/auto-reply/monitor.ts` and `extensions/whatsapp/src/auto-reply/monitor/group-gating.ts`.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix(whatsapp): clarify group drop guidance
- PR branch already contained follow-up commit before automerge: fix(whatsapp): make inbound diagnostics policy-aware
- PR branch already contained follow-up commit before automerge: fix(whatsapp): clarify inbound group diagnostics
Validation:
- ClawSweeper review passed for head 0da24e3bbb.
- Required merge gates passed before the squash merge.
Prepared head SHA: 0da24e3bbb
Review: https://github.com/openclaw/openclaw/pull/83969#issuecomment-4484218945
Co-authored-by: Neerav Makwana <261249544+neeravmakwana@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
Summary:
- This PR clears the cached CLI config snapshot promise when a read rejects, adds a reject-retry-cache regression test, and adds an Unreleased changelog entry.
- Reproducibility: yes. Current main clearly caches the first snapshot-read promise, and the source PR supplied a focused reject, recover, cached-success probe; I did not rerun it in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix: retry config snapshot after rejection
Validation:
- ClawSweeper review passed for head a46b5ec5c7.
- Required merge gates passed before the squash merge.
Prepared head SHA: a46b5ec5c7
Review: https://github.com/openclaw/openclaw/pull/83944#issuecomment-4484051060
Co-authored-by: honor2030 <19909783+honor2030@users.noreply.github.com>
Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>
Approved-by: takhoffman
Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com>
