fix(cron): cancel active cron task runs by ai-hpc · Pull Request #90666 · openclaw/openclaw

ai-hpc · 2026-06-05T12:39:58Z

Summary

Track active cron runs by job id and run id with their live abort handles.
Allow the task registry to cancel active cron task rows when the cron wrapper owns the live run.
Keep main-session cron task rows honest: the wrapper no longer exposes a cancellation handle for work it only enqueued into a downstream child session.
Route openclaw tasks cancel for cron tasks through the live Gateway first, so a CLI process can cancel the Gateway-owned cron run.
Keep cron timeout cleanup armed after operator cancellation when a runner ignores the abort signal.

Verification

OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree OPENCLAW_VITEST_MAX_WORKERS=1 pnpm test src/cron/service/timer.regression.test.ts -- -t "does not report main-session cron task rows cancelled"
OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree OPENCLAW_VITEST_MAX_WORKERS=1 pnpm test src/cron/service/timer.regression.test.ts src/tasks/task-registry.test.ts src/commands/tasks.test.ts
OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree pnpm tsgo:core
OPENCLAW_HEAVY_CHECK_LOCK_SCOPE=worktree pnpm tsgo:core:test
node_modules/.bin/oxfmt --check --threads=1 src/cron/service/timer.ts src/cron/service/timer.regression.test.ts
node_modules/.bin/oxlint src/cron/service/timer.ts src/cron/service/timer.regression.test.ts
git diff --check

Real behavior proof

behavior: A running cron task shown in the task ledger can be cancelled through the task cancellation surface when the cron service owns the active run. Main-session cron wrapper rows do not claim cancellation unless the downstream queued work is actually cancellable.

environment: Ubuntu source checkout, Node 22.22.2, fixed branch ai-hpc/fix-cron-task-cancel.

steps:

Create an isolated OpenClaw state directory.
Create a real task registry row for a running cron task with sourceId and runId.
Register the matching active cron run with a real AbortController.
Cancel the task through the shared detached task cancellation surface.
Confirm the abort signal and terminal task state.
Exercise a main-session cron run that enqueues into a per-run child session while the heartbeat remains in progress.
Cancel the main-session cron task row and confirm it does not report a false terminal cancellation while queued downstream work can still continue.

evidence:

{
  "behavior": "cron task cancellation aborts the active run and marks the ledger row cancelled",
  "stateLayout": "isolated state-only OpenClaw home",
  "taskIdPrefix": "f0e0a630",
  "runtime": "cron",
  "sourceId": "proof-cron-job",
  "runId": "cron:proof-cron-job:run-1",
  "beforeStatus": "running",
  "cancellation": {
    "found": true,
    "cancelled": true,
    "task": {
      "runtime": "cron",
      "sourceId": "proof-cron-job",
      "runId": "cron:proof-cron-job:run-1",
      "task": "Proof cron run",
      "status": "cancelled",
      "deliveryStatus": "not_applicable",
      "notifyPolicy": "silent",
      "error": "Cancelled by operator."
    }
  },
  "signalAborted": true,
  "signalReason": "Cancelled by operator.",
  "afterStatus": "cancelled",
  "stateDirCreated": true
}

observedResult: The cron run abort signal was triggered with Cancelled by operator., and the task row moved from running to terminal cancelled.

additional main-session boundary proof:

src/cron/service/timer.regression.test.ts
  ✓ does not report main-session cron task rows cancelled while queued work can continue

The regression starts a main-session cron run, creates its task row, enqueues the payload into the per-run child session, holds the heartbeat in progress, and calls the shared task cancellation surface. The result is found=true, cancelled=false with "Cron task has no active cancellation handle.", and the task row remains running while the queued child-session work can continue.

observedResult: Main-session cron wrapper cancellation no longer marks the task row cancelled when the wrapper does not own the downstream child-session work.

additional watchdog proof:

src/cron/service/timer.regression.test.ts
  ✓ keeps timeout cleanup armed after operator cancellation

The regression starts a timeout-enabled isolated cron run, cancels the matching active run, leaves the runner unresolved, advances past timeout, and verifies cleanupTimedOutAgentRun is called and the job records a timed-out error.

observedResult: Operator cancellation no longer prevents timeout cleanup when the underlying cron runner ignores the abort signal.

notTested: Full Gmail MCP runaway cron E2E from the original report was not replayed locally. The focused proof covers the shared cron runtime and task cancellation path that produced the unsupported-runtime failure; regression tests cover task-registry cancellation, CLI-to-Gateway routing, cancel-before-timeout cleanup, and the main-session queued-work cancellation boundary.

clawsweeper · 2026-06-05T12:42:15Z

Codex review: needs changes before merge. Reviewed June 8, 2026, 8:09 PM ET / 00:09 UTC.

Summary
Adds active cron cancellation handles, routes cron task cancellation through the Gateway, updates task-registry cron cancellation, and adds cron/task command regression coverage.

PR surface: Source +168, Tests +441. Total +609 across 8 files.

Reproducibility: yes. source inspection gives a high-confidence path: current main routes cron task cancellation to the generic unsupported-runtime branch, and the PR's latest timed-cancel test shows cleanup is not called for an unresolved runner after operator cancellation.

Review metrics: none identified.

Merge readiness
Overall: 🧂 unranked krab
Proof: 🌊 off-meta tidepool
Patch quality: 🧂 unranked krab
Result: blocked by patch quality or review findings.

Overall follows the weaker of proof and patch quality, so missing proof can cap an otherwise strong patch.

Rank-up moves:

[P2] Fix the timed operator-cancel path so abort-ignoring runners still reach timeout cleanup.
[P2] Update the PR body or verification notes after the fix so the described watchdog proof matches the current head.

Risk before merge

[P2] Timed cron cancellation can now mark the wrapper cancelled/error and dispose the watchdog while an abort-ignoring runner remains alive, leaving the original runaway-resource failure mode without timeout cleanup.
[P1] The task ledger can become misleading for timed runs: it can report terminal operator cancellation even though the underlying cron agent work has not actually stopped.
[P1] A second open implementation, fix(cron): cancel active cron task runs #90671, targets the same linked bug, so maintainers should choose one canonical owner-boundary shape before landing.

Maintainer options:

Preserve timed cleanup before merge (recommended)
Update the timed cancellation path so operator cancel aborts the run without disposing the timeout watchdog before cleanupTimedOutCronAgentRun can handle an unresolved runner.
Choose the alternate canonical PR
If maintainers prefer the alternate open implementation, pause or close this PR after moving any useful unique tests or behavior into fix(cron): cancel active cron task runs #90671.
Accept immediate unwind knowingly
Maintainers could intentionally accept that cancelled timed runs may skip timeout cleanup, but that should be an explicit product/operations tradeoff because it weakens the runaway-job escape hatch.

Copy recommended automerge instruction

@clawsweeper automerge

Special instructions:
Update this PR branch so executeJobCoreWithTimeout preserves timeout cleanup after operator cancellation for timed cron runs whose runner ignores AbortSignal. Adjust src/cron/service/timer.regression.test.ts so the unresolved timed-run cancellation test expects cleanupTimedOutCronAgentRun to run after the configured timeout, while keeping main-session cron rows non-cancellable and timeout-disabled cancellation behavior intentional. Validate with node scripts/run-vitest.mjs src/cron/service/timer.regression.test.ts src/tasks/task-registry.test.ts src/commands/tasks.test.ts.

Next step before merge

[P2] A narrow automated repair can target the timed-cancellation watchdog regression without changing the broader Gateway-first cron cancellation design.

Security
Cleared: No concrete security or supply-chain concern was found in the cron/task runtime and test changes.

Review findings

[P1] Keep the watchdog cleanup after cancellation — src/cron/service/timer.ts:211-212

Review details

Best possible solution:

Keep the Gateway-owned active cron handle approach, but merge only after timed cancellation preserves cleanup for abort-ignorant runners and the branch/proof matches that behavior.

Do we have a high-confidence way to reproduce the issue?

Yes, source inspection gives a high-confidence path: current main routes cron task cancellation to the generic unsupported-runtime branch, and the PR's latest timed-cancel test shows cleanup is not called for an unresolved runner after operator cancellation.

Is this the best way to solve the issue?

No, not yet: the active-handle and Gateway-first shape is a good owner-boundary direction, but the timed cancellation path must keep or replace watchdog cleanup before this is the safest fix.

Full review comments:

[P1] Keep the watchdog cleanup after cancellation — src/cron/service/timer.ts:211-212
For timed cron runs, operator cancellation now wins the race and returns immediately, then the finally block disposes the watchdog. If the runner ignores AbortSignal, cleanupTimedOutCronAgentRun never fires, so the task ledger can show cancellation while the underlying cron agent keeps running, which is the runaway case this PR is trying to fix. Keep the abort/cancel result, but leave timeout cleanup armed or explicitly clean up ignored-abort runners.
Confidence: 0.91

Overall correctness: patch is incorrect
Overall confidence: 0.89

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against ebb9c6a013b5.

Label changes

Label changes:

add status: ⏳ waiting on author: ClawSweeper has contributor-facing work open and is waiting for author action. Not applicable: The contributor proof gate is not applicable to this member-authored PR, though the PR body proof should be refreshed after the timed cleanup behavior is fixed.
remove status: 📣 needs proof: Current PR status label is status: ⏳ waiting on author.

Label justifications:

P2: This is a normal-priority user-visible cron/task cancellation bug with limited blast radius but real operator impact for runaway jobs.
merge-risk: 🚨 session-state: The PR can make task state terminal while the underlying timed cron runner is still unresolved after an ignored abort.
merge-risk: 🚨 availability: Disposing the watchdog after operator cancellation can skip cleanup for an abort-ignoring timed cron run, preserving the runaway-resource failure mode.
rating: 🧂 unranked krab: Overall readiness is 🧂 unranked krab; proof is 🌊 off-meta tidepool and patch quality is 🧂 unranked krab.
status: ⏳ waiting on author: ClawSweeper has contributor-facing work open and is waiting for author action. Not applicable: The contributor proof gate is not applicable to this member-authored PR, though the PR body proof should be refreshed after the timed cleanup behavior is fixed.

Evidence reviewed

PR surface:

Source +168, Tests +441. Total +609 across 8 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	5	224	56	+168
Tests	3	442	1	+441
Docs	0	0	0	0
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	8	666	57	+609

Acceptance criteria:

[P1] node scripts/run-vitest.mjs src/cron/service/timer.regression.test.ts src/tasks/task-registry.test.ts src/commands/tasks.test.ts.
[P1] pnpm tsgo:core.
[P1] pnpm tsgo:core:test.
[P1] git diff --check.

What I checked:

Root policy read: Root AGENTS.md was read fully; its PR review, best-fix, proof, owner-boundary, and merge-risk guidance applies to this cron/task PR. (AGENTS.md:8, ebb9c6a013b5)
Current-main source repro: Current main has no cron-specific cancellation branch, so a non-CLI cron task without a cancellable child session reaches the unsupported-runtime result reported by the linked issue. (src/tasks/task-registry.ts:2118, ebb9c6a013b5)
PR implementation path: The PR registers process-local cron abort handles for non-main cron runs and routes cron task cancellation through cancelActiveCronTaskRun before marking the task cancelled. (src/tasks/task-registry.ts:2084, 62c3d3633078)
Blocking cleanup regression: For timed cron runs, operator cancellation now wins the race and returns a cancellation outcome before the timeout path can call cleanupTimedOutCronAgentRun; the finally block then disposes the watchdog. (src/cron/service/timer.ts:210, 62c3d3633078)
Regression test currently locks in the risky behavior: The latest regression test asserts cleanupTimedOutAgentRun is not called after operator cancellation even though the mocked runner remains unresolved, which contradicts the PR body's watchdog-cleanup claim. (src/cron/service/timer.regression.test.ts:1001, 62c3d3633078)
Related open implementation: The provided GitHub context shows fix(cron): cancel active cron task runs #90671 is still open for the same linked cron cancellation issue, so maintainers should avoid landing two competing shapes.

Likely related people:

shakkernerd: The timeline shows assignment and force-pushes by shakkernerd, and the latest branch commits address cron cancellation runtime cycles, timeout terminal state, and timed cancellation behavior. (role: current PR branch steward and recent fix author; confidence: high; commits: 29b6a406f047, 211376c5033a, 4cb0f4914fed; files: src/cron/service/timer.ts, src/tasks/task-registry.ts, src/tasks/cron-task-cancel.ts)
Vincent Koc: Current-main blame/log in this checkout points the central cron timer and task registry files at Vincent Koc commits, but the local history is shallow/collapsed so this is a weak routing signal. (role: current-main area provenance; confidence: low; commits: 0176429ad787, ebb9c6a013b5; files: src/cron/service/timer.ts, src/tasks/task-registry.ts)

What the crustacean ranks mean

🦀 challenger crab: rare, exceptional readiness with strong proof, clean implementation, and convincing validation.
🦞 diamond lobster: very strong readiness with only minor maintainer review expected.
🐚 platinum hermit: good normal PR, likely mergeable with ordinary maintainer review.
🦐 gold shrimp: useful signal, but proof or patch confidence is still limited.
🦪 silver shellfish: thin signal; proof, validation, or implementation needs work.
🧂 unranked krab: not merge-ready because proof is missing/unusable or there are serious correctness or safety concerns.
🌊 off-meta tidepool: rating does not apply to this item.

Shiny media proof means a screenshot, video, or linked artifact directly shows the changed behavior. Runtime, network, CSP, and security claims still need visible diagnostics.

How this review workflow works

ClawSweeper keeps one durable marker-backed review comment per issue or PR.
Re-runs edit this comment so the latest verdict, findings, and automation markers stay together instead of adding duplicate bot comments.
A fresh review can be triggered by eligible @clawsweeper re-review comments, exact-item GitHub events, scheduled/background review runs, or manual workflow dispatch.
PR/issue authors and users with repository write access can comment @clawsweeper re-review or @clawsweeper re-run on an open PR or issue to request a fresh review only.
Maintainers can also comment @clawsweeper review to request a fresh review only.
Fresh-review commands do not start repair, autofix, rebase, CI repair, or automerge.
Maintainer-only repair and merge flows require explicit commands such as @clawsweeper autofix, @clawsweeper automerge, @clawsweeper fix ci, or @clawsweeper address review.
Maintainers can comment @clawsweeper explain to ask for more context, or @clawsweeper stop to stop active automation.

ai-hpc · 2026-06-06T19:09:50Z

@clawsweeper re-review

clawsweeper · 2026-06-06T19:09:53Z

🦞🧹
ClawSweeper re-review requested.

I asked ClawSweeper to review this item again.
Action: item re-review queued (workflow sweep.yml, event repository_dispatch).
Result: the existing ClawSweeper review comment will be edited in place when the review finishes.

Re-review progress:

State: Complete
Detail: The targeted re-review finished, the durable review comment was updated, and the synced verdict was routed.
Run: https://github.com/openclaw/clawsweeper/actions/runs/27071315571
Updated: 2026-06-06T19:18:21.737Z

shakkernerd · 2026-06-09T00:22:21Z

Rebased onto current origin/main (ebb9c6a) and resolved the conflict in src/commands/tasks.test.ts by preserving both the session-state cleanup from main and the cron cancellation gateway mock from this PR.

Verification:

Local sanity: git diff --check; conflict-marker/stale-symbol scan across the touched cron/task files.
Blacksmith Testbox tbx_01ktmtrcsefnx929fxcdwdq3n5 / run 27174702268: corepack pnpm check:architecture; focused tests for src/commands/tasks.test.ts, src/cron/service/timer.regression.test.ts, src/tasks/task-registry.test.ts, and src/tasks/task-executor.test.ts; corepack pnpm build; scripts/check-gateway-watch-regression.mjs --skip-build.
GitHub CI on head 62c3d36: initial CI attempt hit self-hosted runner communication failures; reran failed jobs and attempt 2 passed. Latest Real behavior proof run also passed.
Confirmed the contributor-authored commits still resolve to @ai-hpc after the rebase.

…26.6.6) (#1040) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.6.5` → `2026.6.6` | --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.6.6`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#202666) [Compare Source](openclaw/openclaw@v2026.6.5...v2026.6.6) ##### Highlights - Security boundaries are substantially tighter across transcripts, sandbox binds, host environment inheritance, MCP stdio, Codex HTTP access, native search policy, elevated sender checks, deleted-agent ACP bypasses, loopback tools, Discord moderation, and Teams group actions; exec approvals now fail closed on timeout. ([#91529](openclaw/openclaw#91529), [#91618](openclaw/openclaw#91618), [#91615](openclaw/openclaw#91615), [#91619](openclaw/openclaw#91619), [#91741](openclaw/openclaw#91741), [#91745](openclaw/openclaw#91745), [#91746](openclaw/openclaw#91746), [#91748](openclaw/openclaw#91748), [#91749](openclaw/openclaw#91749), [#91750](openclaw/openclaw#91750), [#91751](openclaw/openclaw#91751), [#91752](openclaw/openclaw#91752), [#91763](openclaw/openclaw#91763), [#89938](openclaw/openclaw#89938)) Thanks [@joshavant](https://github.com/joshavant), [@pgondhi987](https://github.com/pgondhi987), [@mmaps](https://github.com/mmaps), [@eleqtrizit](https://github.com/eleqtrizit), [@shakkernerd](https://github.com/shakkernerd), and [@drobison00](https://github.com/drobison00). - Telegram delivery is safer and more coherent: account-scoped topics route to the right agent, streamed text survives tool calls, `/compact` works on generic ingress, callback handling uses concrete APIs, draft chunking is shared, durable dispatch dedupe moved into the SDK, and unauthorized DM text stays out of cache and prompt context. ([#91189](openclaw/openclaw#91189), [#88682](openclaw/openclaw#88682), [#89588](openclaw/openclaw#89588), [#90212](openclaw/openclaw#90212), [#91876](openclaw/openclaw#91876), [#91874](openclaw/openclaw#91874), [#91904](openclaw/openclaw#91904), [#91478](openclaw/openclaw#91478), [#91915](openclaw/openclaw#91915)) Thanks [@codysai001](https://github.com/codysai001), [@alexzhu0](https://github.com/alexzhu0), [@joelnishanth](https://github.com/joelnishanth), [@snowzlm](https://github.com/snowzlm), [@obviyus](https://github.com/obviyus), and [@sallyom](https://github.com/sallyom). - iMessage recovery and delivery now cover always-on inbound restart, durable echo markers, block streaming, idle approval discovery, hardened outbound transport, and actionable inbound startup diagnostics. ([#91335](openclaw/openclaw#91335), [#91449](openclaw/openclaw#91449), [#88969](openclaw/openclaw#88969), [#88530](openclaw/openclaw#88530), [#91783](openclaw/openclaw#91783), [#91785](openclaw/openclaw#91785)) Thanks [@omarshahine](https://github.com/omarshahine), [@jmissig](https://github.com/jmissig), and [@colmbrogan](https://github.com/colmbrogan). - Browser and MCP connectivity gained existing-session CDP support, discovered WebSocket validation, default-profile `cdpUrl` handling, safer browser-output boundaries, Streamable HTTP loopback transport, corrected OAuth/SSE authorization handling, and broader schema compatibility. ([#91422](openclaw/openclaw#91422), [#89851](openclaw/openclaw#89851), [#91736](openclaw/openclaw#91736), [#91747](openclaw/openclaw#91747), [#91451](openclaw/openclaw#91451), [#80143](openclaw/openclaw#80143)) Thanks [@pgondhi987](https://github.com/pgondhi987), [@anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia), [@lifuyue](https://github.com/lifuyue), [@eleqtrizit](https://github.com/eleqtrizit), [@LiuwqGit](https://github.com/LiuwqGit), and [@HemantSudarshan](https://github.com/HemantSudarshan). - Control UI startup and first-reply latency are lower through cached model metadata, removal of the startup catalog wait, lazy slash-command loading, and first-event tracing with slow-reply diagnostics. ([#91531](openclaw/openclaw#91531), [#91538](openclaw/openclaw#91538), [#91568](openclaw/openclaw#91568), [#91583](openclaw/openclaw#91583), [#91598](openclaw/openclaw#91598)) - Provider support expands with OpenRouter OAuth onboarding and Claude Fable 5 adaptive thinking, while Codex sessions keep correct compaction ownership, local models skip guardian review, dynamic tool progress normalizes cleanly, and Gemma 4 reasoning replay is preserved. ([#91830](openclaw/openclaw#91830), [#91882](openclaw/openclaw#91882), [#91590](openclaw/openclaw#91590), [#88630](openclaw/openclaw#88630), [#88768](openclaw/openclaw#88768), [#91696](openclaw/openclaw#91696)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@joshavant](https://github.com/joshavant), [@bdjben](https://github.com/bdjben), and [@Coder-Wangyankun](https://github.com/Coder-Wangyankun). ##### Changes - CLI progress: emit Claude CLI commentary progress events and bridge inter-tool commentary into channel progress without exposing internal protocol scaffolding. ([#89834](openclaw/openclaw#89834), [#90883](openclaw/openclaw#90883)) Thanks [@anagnorisis2peripeteia](https://github.com/anagnorisis2peripeteia). - Observability: allow trusted diagnostics channels to capture tool input/output content, add first-assistant-event traces, and warn on slow initial replies. ([#91256](openclaw/openclaw#91256), [#91568](openclaw/openclaw#91568), [#91583](openclaw/openclaw#91583)) Thanks [@amknight](https://github.com/amknight). - Plugins/ClawHub: dogfood reusable package publishing, let dry runs skip publish approval, allow declared installed trusted hooks, report managed plugin version drift, and warn instead of failing on retired Skill Workshop configuration. ([#91574](openclaw/openclaw#91574), [#91591](openclaw/openclaw#91591), [#90004](openclaw/openclaw#90004), [#90927](openclaw/openclaw#90927), [#90838](openclaw/openclaw#90838)) Thanks [@Patrick-Erichsen](https://github.com/Patrick-Erichsen), [@brokemac79](https://github.com/brokemac79), and [@lonexreb](https://github.com/lonexreb). - Memory/providers: move the local llama.cpp runtime into its provider plugin, batch embeddings across files, persist the agent model catalog cache, and keep QMD JSON search one-shot while filtering stale REM recall previews. ([#91324](openclaw/openclaw#91324), [#89138](openclaw/openclaw#89138), [#90457](openclaw/openclaw#90457), [#91837](openclaw/openclaw#91837), [#91851](openclaw/openclaw#91851)) Thanks [@osolmaz](https://github.com/osolmaz), [@mushuiyu886](https://github.com/mushuiyu886), [@ai-hpc](https://github.com/ai-hpc), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Channels/mobile: add the QQBot group mention toggle, improve iPad and iPhone control surfaces, and expose the active connection host in the TUI footer. ([#91423](openclaw/openclaw#91423), [#91557](openclaw/openclaw#91557), [#89909](openclaw/openclaw#89909)) Thanks [@cxyhhhhh](https://github.com/cxyhhhhh), [@Solvely-Colin](https://github.com/Solvely-Colin), and [@baskduf](https://github.com/baskduf). - Performance: prewarm TUI runtime plugins, deduplicate plugin auto-enable fanout, trim dense text-delta snapshots, and reuse prepared startup model metadata. ([#90782](openclaw/openclaw#90782), [#89978](openclaw/openclaw#89978), [#91580](openclaw/openclaw#91580), [#91531](openclaw/openclaw#91531)) Thanks [@RomneyDa](https://github.com/RomneyDa) and [@ai-hpc](https://github.com/ai-hpc). ##### Fixes - Agent/session recovery: drop stale approval follow-ups after session rebind, remove drained reply-queue items by identity, recover stale main and visible replies, preserve Codex context-engine compaction ownership, lower the default compaction timeout to 180 seconds while respecting explicit configuration, and keep provider-failure terminal lifecycle state correct. ([#85679](openclaw/openclaw#85679), [#91450](openclaw/openclaw#91450), [#91566](openclaw/openclaw#91566), [#91840](openclaw/openclaw#91840), [#91590](openclaw/openclaw#91590), [#91361](openclaw/openclaw#91361), [#91895](openclaw/openclaw#91895)) Thanks [@openperf](https://github.com/openperf), [@yetval](https://github.com/yetval), [@joshavant](https://github.com/joshavant), [@wangmiao0668000666](https://github.com/wangmiao0668000666), and [@TurboTheTurtle](https://github.com/TurboTheTurtle). - User-visible content boundaries: suppress Codex/Harmony protocol artifacts, neutralize browser and LanceDB memory media directives, redact transcript images, and preserve native `/compact` replies through source suppression. ([#89151](openclaw/openclaw#89151), [#91422](openclaw/openclaw#91422), [#91425](openclaw/openclaw#91425), [#91529](openclaw/openclaw#91529), [#90212](openclaw/openclaw#90212)) Thanks [@joelnishanth](https://github.com/joelnishanth), [@pgondhi987](https://github.com/pgondhi987), [@joshavant](https://github.com/joshavant), and [@snowzlm](https://github.com/snowzlm). - Channel delivery: keep WhatsApp captured replies attached to the successor controller after restart, retry Feishu rate limits, preserve Mattermost thread replies, canonicalize LINE webhook paths, restore Discord reply hydration and runtime timeout exports, and show OpenAI Realtime WebRTC assistant transcripts. ([#85823](openclaw/openclaw#85823), [#89659](openclaw/openclaw#89659), [#91684](openclaw/openclaw#91684), [#91649](openclaw/openclaw#91649), [#90263](openclaw/openclaw#90263), [#91686](openclaw/openclaw#91686), [#90426](openclaw/openclaw#90426)) Thanks [@itsuzef](https://github.com/itsuzef), [@ladygege](https://github.com/ladygege), [@jacobtomlinson](https://github.com/jacobtomlinson), [@fuller-stack-dev](https://github.com/fuller-stack-dev), and [@shushushv](https://github.com/shushushv). - Cron: cancel active task runs cleanly, preserve terminal timeout/cancel state, and recover no-deliver tool warnings instead of silently losing the outcome. ([#90666](openclaw/openclaw#90666), [#90678](openclaw/openclaw#90678)) Thanks [@ai-hpc](https://github.com/ai-hpc). - Gateway/config/auth: share the approval runtime socket token, replace arrays explicitly in `config.patch`, skip the deleted-agent guard only for valid ACP harness sessions, surface headless LaunchAgent state, verify SQLite auth migration before cleanup, and arm QMD startup maintenance. ([#87105](openclaw/openclaw#87105), [#91551](openclaw/openclaw#91551), [#91219](openclaw/openclaw#91219), [#91614](openclaw/openclaw#91614), [#91740](openclaw/openclaw#91740), [#91978](openclaw/openclaw#91978)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev) and [@scotthuang](https://github.com/scotthuang). - Providers/Codex: clarify quota errors, restore the Codex synthetic usage line, canonicalize Codex protocol assets, require API-key auth for realtime voice, normalize ACP model refs, preserve Gemma 4 `reasoning_content`, and avoid guardian review for local models. ([#91390](openclaw/openclaw#91390), [#91709](openclaw/openclaw#91709), [#91507](openclaw/openclaw#91507), [#91567](openclaw/openclaw#91567), [#88630](openclaw/openclaw#88630), [#91696](openclaw/openclaw#91696)) Thanks [@hxy91819](https://github.com/hxy91819), [@brokemac79](https://github.com/brokemac79), [@RomneyDa](https://github.com/RomneyDa), [@joshavant](https://github.com/joshavant), and [@Coder-Wangyankun](https://github.com/Coder-Wangyankun). - Updates/builds: recover package Gateway restarts after refresh failure, expose plugin convergence repair, fall back to Corepack in PATH-less pnpm environments, seed the correct Docker store packages, and keep ClawHub dry-run and publish paths reusable. ([#91581](openclaw/openclaw#91581), [#91599](openclaw/openclaw#91599), [#91547](openclaw/openclaw#91547), [#91591](openclaw/openclaw#91591)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev), [@sallyom](https://github.com/sallyom), and [@Patrick-Erichsen](https://github.com/Patrick-Erichsen). - UI: require explicit user intent before opening chat sessions and drain restored chat queues after session switches. ([#91480](openclaw/openclaw#91480)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Android: avoid the `dataSync` foreground-service type for persistent nodes. ([#80082](openclaw/openclaw#80082)) Thanks [@davelutztx](https://github.com/davelutztx). - Native hooks: bound relay lifetimes so abandoned native hook connections cannot linger indefinitely. ([#91550](openclaw/openclaw#91550)) Thanks [@joshavant](https://github.com/joshavant). </details> --- ### Configuration 📅 **Schedule**: Branch creation - At any time (no schedule defined), Automerge - At any time (no schedule defined). 🚦 **Automerge**: Disabled by config. Please merge this manually once you are satisfied. ♻ **Rebasing**: Whenever PR becomes conflicted, or you tick the rebase/retry checkbox. 🔕 **Ignore**: Close this PR and you won't be reminded about these updates again. --- - [ ] If you want to rebase/retry this PR, check this box --- This PR has been generated by [Renovate Bot](https://github.com/renovatebot/renovate).  Reviewed-on: https://git.erwanleboucher.dev/eleboucher/homelab/pulls/1040

openclaw-barnacle Bot added commands Command implementations size: M labels Jun 5, 2026

849261680 mentioned this pull request Jun 5, 2026

fix(cron): cancel active cron task runs #90671

Closed

openclaw-barnacle Bot added size: L and removed size: M labels Jun 5, 2026

shakkernerd self-assigned this Jun 8, 2026

shakkernerd force-pushed the ai-hpc/fix-cron-task-cancel branch 2 times, most recently from 80dd7ea to c005608 Compare June 8, 2026 22:44

ai-hpc and others added 10 commits June 9, 2026 00:57

fix(cron): cancel active cron task runs

2a8eb61

fix(cron): preserve timeout cleanup after cancel

6a5db11

test(cron): type unresolved runner mock

5426a8e

fix(cron): keep main-session cron cancel honest

df185eb

fix: avoid cron cancel runtime cycle

29b6a40

test: remove stale cron cancel harness hook

a49a210

fix: preserve cron timeout terminal state

211376c

fix: unwind timeout-disabled cron cancellation

4cb0f49

fix: unblock timed cron cancellation

9a1ba06

test: satisfy cron cancellation lint

62c3d36

shakkernerd force-pushed the ai-hpc/fix-cron-task-cancel branch from c005608 to 62c3d36 Compare June 9, 2026 00:02

clawsweeper Bot added status: ⏳ waiting on author ClawSweeper has contributor-facing work open and is waiting for author action. and removed status: 📣 needs proof The PR needs real behavior proof before ClawSweeper can clear the contributor ask. labels Jun 9, 2026

shakkernerd merged commit 5b76436 into openclaw:main Jun 9, 2026
276 of 291 checks passed

Haderach-Ram mentioned this pull request Jun 9, 2026

Ecosystem Digest — 2026-06-09 Haderach-Ram/openclaw-radar#33

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(cron): cancel active cron task runs#90666

fix(cron): cancel active cron task runs#90666
shakkernerd merged 10 commits into
openclaw:mainfrom
ai-hpc:ai-hpc/fix-cron-task-cancel

ai-hpc commented Jun 5, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jun 5, 2026 •

edited

Loading

Uh oh!

ai-hpc commented Jun 6, 2026

Uh oh!

clawsweeper Bot commented Jun 6, 2026 •

edited

Loading

Uh oh!

shakkernerd commented Jun 9, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

ai-hpc commented Jun 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Verification

Real behavior proof

Uh oh!

clawsweeper Bot commented Jun 5, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

ai-hpc commented Jun 6, 2026

Uh oh!

clawsweeper Bot commented Jun 6, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

shakkernerd commented Jun 9, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

ai-hpc commented Jun 5, 2026 •

edited

Loading

clawsweeper Bot commented Jun 5, 2026 •

edited

Loading

clawsweeper Bot commented Jun 6, 2026 •

edited

Loading