fix: yield diagnostic event drains by galiniliev · Pull Request #82937 · openclaw/openclaw

galiniliev · 2026-05-17T05:37:24Z

Summary

Problem: high-frequency async diagnostic events could drain a large backlog in one setImmediate turn, monopolizing the gateway event loop during agent/subagent bursts.
Why it matters: diagnostic traffic should not create liveness-delay spikes or duplicate/lost dynamic-tool terminal diagnostics.
What changed: async diagnostic drains now process at most 100 queued events per turn; callers can explicitly wait for a full diagnostic drain; Codex dynamic-tool fallback diagnostics check the pending queue for the matching terminal event instead of waiting on unrelated global backlog; trusted terminal tool diagnostics get queue priority at saturation.
What did NOT change (scope boundary): diagnostic payload shapes, public diagnostic stream filtering, listener ordering, and the 10k async queue cap remain intact.

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

Closes [Bug]: Gateway liveness reports severe event-loop stalls under subagent load #82936
Related #
This PR fixes a bug or regression

Real behavior proof (required for external PRs)

Behavior addressed: Diagnostic event bursts from concurrent gateway agent/subagent activity no longer drain the whole async queue in one event-loop turn, and Codex dynamic-tool terminal diagnostics are not duplicated or dropped behind diagnostic backlog.
Real environment tested: Local OpenClaw worktree, Node v24.15.0, rebased on origin/main 0556ac0291a894836382307eeeeb3b503aa1c0e5.
Exact steps or command run after this patch:

node --import tsx -e "import { emitDiagnosticEvent, onDiagnosticEvent, resetDiagnosticEventsForTest } from './src/infra/diagnostic-events.ts'; resetDiagnosticEventsForTest(); const events=[]; onDiagnosticEvent((event)=>events.push(event)); for (let index=0; index<250; index+=1) emitDiagnosticEvent({type:'model.call.started', runId:'run-'+index, callId:'call-'+index, provider:'openai', model:'gpt-5.4'}); if (events.length !== 0) throw new Error('expected async queue before first turn, got '+events.length); await new Promise((resolve)=>setImmediate(resolve)); if (events.length !== 100) throw new Error('expected 100 after one turn, got '+events.length); await new Promise((resolve)=>setImmediate(resolve)); if (events.length !== 200) throw new Error('expected 200 after two turns, got '+events.length); await new Promise((resolve)=>setImmediate(resolve)); if (events.length !== 250) throw new Error('expected 250 after three turns, got '+events.length); console.log('diagnostic async drain burst probe passed: 250 events over 3 turns');"
node --max-old-space-size=8192 --import tsx scripts/generate-plugin-sdk-api-baseline.ts --check
node scripts/run-tsgo.mjs -p test/tsconfig/tsconfig.core.test.json --incremental --tsBuildInfoFile .artifacts/tsgo-cache/core-test.tsbuildinfo
node scripts/run-vitest.mjs src/infra/diagnostic-events.test.ts
node scripts/run-vitest.mjs extensions/codex/src/app-server/run-attempt.test.ts -t "does not duplicate terminal diagnostics for wrapped dynamic tool errors"
AUTOREVIEW_AUTO_TESTS=0 .agents/skills/autoreview/scripts/autoreview --mode branch --base origin/main

Evidence after fix:

diagnostic async drain burst probe passed: 250 events over 3 turns
OK docs/.generated/plugin-sdk-api-baseline.sha256
core test typecheck completed with exit code 0
Test Files  1 passed (1)
Tests  25 passed (25)
Test Files  1 passed (1)
Tests  1 passed | 183 skipped (184)
autoreview clean: no accepted/actionable findings reported
Test Files  2 passed (2)
Tests  210 passed (210)

Observed result after fix: The scheduler delivered a 250-event burst as 100/200/250 across three event-loop turns; the focused diagnostic tests cover full drain, pending queue inspection, terminal priority under saturation, immutable inspector inputs, and uncloneable pending entries; the Codex regression did not duplicate terminal diagnostics behind a 150-event async backlog.
What was not tested: I did not rerun the original private multi-subagent gateway workload. Full PR CI was restarted after the refreshed push and is expected to provide broader repository proof.
Before evidence (optional but encouraged): Redacted log excerpt from the captured bug evidence:

"liveness warning: reasons=event_loop_delay,event_loop_utilization,cpu interval=30s eventLoopDelayP99Ms=6123.7 eventLoopDelayMaxMs=7709.1 eventLoopUtilization=0.975 cpuCoreRatio=0.983 active=5 waiting=0 queued=1 ..."
"liveness warning: reasons=event_loop_delay,event_loop_utilization interval=329s eventLoopDelayP99Ms=12750.7 eventLoopDelayMaxMs=12750.7 eventLoopUtilization=1 ..."
"liveness warning: reasons=event_loop_delay,cpu interval=30s eventLoopDelayP99Ms=1780.5 eventLoopDelayMaxMs=2128.6 eventLoopUtilization=0.892 cpuCoreRatio=0.951 active=6 ..."

Root Cause (if applicable)

Root cause: scheduleAsyncDiagnosticDrain moved high-frequency diagnostic events out of the emitter path, but processed every queued event in one async drain turn. Under agent/subagent bursts, listener cloning/freezing and stability recording could still monopolize the event loop until the backlog was empty.
Missing detection / guardrail: Existing coverage only asserted that high-frequency events were asynchronous; it did not assert that large bursts yield between drain turns or that terminal tool diagnostics survive backlog/saturation cases.
Contributing context (if known): Liveness warnings showed active agent/subagent work and queued work while event-loop delay P99 reached seconds.

Regression Test Plan (if applicable)

Coverage level that should have caught this:
- Unit test
- Seam / integration test
- End-to-end test
- Existing coverage already sufficient
Target test or file: src/infra/diagnostic-events.test.ts; extensions/codex/src/app-server/run-attempt.test.ts
Scenario the test should lock in: A burst of 250 async model-call diagnostic events drains as 100/200/250 across three setImmediate turns; full-drain callers can await the entire queue; pending diagnostic inspection does not mutate or throw on malformed queued entries; trusted terminal tool diagnostics survive queue saturation; Codex dynamic-tool fallback diagnostics are not duplicated behind backlog.
Why this is the smallest reliable guardrail: The bug is in the diagnostic event queue scheduler and Codex’s dynamic-tool terminal fallback path, so focused scheduler and app-server tests prove the exact contracts without provider or channel setup.
Existing test that already covers this (if any): Existing async dispatch coverage only covered a two-event burst.
If no new test is added, why not: N/A

User-visible / Behavior Changes

The gateway should remain more responsive during diagnostic event bursts from concurrent agent/subagent workloads.

Diagram (if applicable)

Before:
[diagnostic burst] -> [one drain turn processes entire backlog] -> [event-loop stall risk]

After:
[diagnostic burst] -> [100-event drain turn] -> [yield] -> [next drain turn] -> [continued gateway work]

Security Impact (required)

New permissions/capabilities? (Yes/No): No
Secrets/tokens handling changed? (Yes/No): No
New/changed network calls? (Yes/No): No
Command/tool execution surface changed? (Yes/No): No
Data access scope changed? (Yes/No): No
If any Yes, explain risk + mitigation: N/A

Repro + Verification

Environment

OS: Linux local worktree
Runtime/container: Node v24.15.0
Model/provider: N/A for focused diagnostic queue probe
Integration/channel (if any): Gateway diagnostics, Codex app-server dynamic tools
Relevant config (redacted): Diagnostics event dispatch defaults

Steps

Register a diagnostic event listener.
Emit 250 high-frequency model.call.started diagnostic events.
Await successive setImmediate turns and count delivered events.

Expected

The async drain yields between chunks instead of delivering all 250 events in one turn.

Actual

After patch, delivery progressed as 0 before yield, then 100, 200, and 250 across three event-loop turns.

Evidence

Attach at least one:

Failing test/log before + passing after
Trace/log snippets
Screenshot/recording
Perf numbers (if relevant)

Human Verification (required)

What you personally verified (not just CI), and how:

Verified scenarios: Focused runtime probe for the diagnostic async queue burst; scheduler Vitest coverage; Codex dynamic-tool duplicate-terminal regression; Plugin SDK API baseline check; core test typecheck matching the CI failure shard; git diff --check; autoreview.
Edge cases checked: Existing two-event async behavior remains compatible because it still drains in the first turn; large backlog continues scheduling while queue entries remain; terminal diagnostics queued behind large async backlog are detected before fallback emission; trusted terminal diagnostics are preserved at queue saturation; pending queue inspection does not expose mutable queued entries or throw on uncloneable queued entries.
What you did not verify: Original private gateway/subagent workload; full CI is running after the refreshed push.

Review Conversations

I replied to or resolved every bot review conversation I addressed in this PR.
I left unresolved only the conversations that still need reviewer or maintainer judgment.

If a bot review conversation is addressed by this PR, resolve that conversation yourself. Do not leave bot review conversation cleanup for maintainers.

Compatibility / Migration

Backward compatible? (Yes/No): Yes
Config/env changes? (Yes/No): No
Migration needed? (Yes/No): No
If yes, exact upgrade steps: N/A

Risks and Mitigations

Risk: Diagnostic event listeners may observe large async bursts over more event-loop turns instead of one immediate turn.
- Mitigation: Ordering is preserved and small bursts still drain in a single turn; the queue keeps scheduling until empty.

clawsweeper · 2026-05-17T05:38:18Z

Codex review: passed.

Workflow note: Future ClawSweeper reviews update this same comment in place.

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.

Summary
The branch caps async diagnostic drains at 100 events per turn, adds pending/full-drain diagnostic helpers, updates Codex dynamic-tool terminal diagnostics to inspect pending events, and adds regression coverage plus changelog/baseline updates.

Reproducibility: yes. from source inspection. Current main drains the entire async diagnostic queue in one setImmediate callback, and the PR body supplies a focused 250-event after-fix probe showing 100/200/250 delivery across turns.

PR rating
Overall: 🐚 platinum hermit
Proof: 🦞 diamond lobster
Patch quality: 🐚 platinum hermit
Summary: Good focused bug-fix PR with strong terminal proof and no blocking findings; the remaining risk is maintainer acceptance of chunked diagnostic listener timing.

Rank-up moves:

Let exact-head checks finish before automerge.

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.

Real behavior proof
Sufficient (terminal): The PR body contains exact terminal commands and copied after-fix output for the runtime burst probe, focused tests, typecheck, baseline check, and autoreview, which is sufficient for this non-visual runtime change.

Risk before merge

Large async diagnostic bursts will now reach listeners over multiple setImmediate turns instead of one callback; event order is preserved, but this is a listener-timing compatibility change.
The original private multi-subagent gateway workload was not rerun; the supplied proof is a focused runtime probe, focused regression tests, and copied terminal output.

Maintainer options:

Accept Chunked Diagnostic Timing (recommended)
Land once exact-head checks pass if maintainers accept preserving diagnostic ordering while spreading large backlogs across event-loop turns.
Request Broader Gateway Proof
Ask for a live or packaged multi-agent gateway workload if focused scheduler and Codex regression proof is not enough for the timing change.
Pause The Timing Change
Pause or close if diagnostic listeners must continue seeing every large async burst fully drained in one event-loop turn.

Next step before merge
No ClawSweeper repair job is needed; this automerge-opted PR has no actionable review findings, so exact-head checks and maintainer timing acceptance should gate merge.

Security
Cleared: The diff changes in-memory diagnostic scheduling, an existing SDK diagnostic-runtime export surface, tests, generated baseline hash metadata, and changelog text with no dependency, workflow, secret, network, permission, or package-resolution changes.

Review details

Best possible solution:

Land the scheduler cap and pending-terminal-diagnostic guard through the existing automerge path once exact-head gates pass and maintainers accept the chunked listener timing.

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

Yes from source inspection. Current main drains the entire async diagnostic queue in one setImmediate callback, and the PR body supplies a focused 250-event after-fix probe showing 100/200/250 delivery across turns.

Is this the best way to solve the issue?

Yes, with the compatibility caveat. The patch changes the existing scheduler and Codex fallback path directly, preserves queue order and caps, and adds focused tests instead of creating a parallel diagnostic mechanism.

What I checked:

Current-main behavior: Current main schedules high-frequency diagnostic events with setImmediate but drains the entire async queue with state.asyncQueue.splice(0), matching the reported event-loop monopolization path. (src/infra/diagnostic-events.ts:803, 0556ac0291a8)
Scheduler patch: The PR head adds MAX_ASYNC_DIAGNOSTIC_EVENTS_PER_TURN=100, drains only that many events per turn, and exposes waitForDiagnosticEventsDrained for callers that need the full async queue flushed. (src/infra/diagnostic-events.ts:652, 95610934cde8)
Pending diagnostic guard: The Codex run-attempt path no longer waits behind unrelated backlog; it checks for a matching pending terminal diagnostic before emitting a fallback terminal diagnostic. (extensions/codex/src/app-server/run-attempt.ts:2187, 95610934cde8)
Regression coverage: The PR adds tests for 250-event chunked draining, full-drain waiting, immutable pending inspection, uncloneable pending entries, queue saturation priority, and the Codex duplicate-terminal diagnostic backlog case. (src/infra/diagnostic-events.test.ts:421, 95610934cde8)
Proof supplied by PR body: The PR body includes terminal commands and copied after-fix output for a 250-event runtime probe, focused diagnostic tests, the Codex regression test, SDK baseline check, core test typecheck, and autoreview. (95610934cde8)
History provenance: git blame ties the current all-at-once async drain and Codex fallback wait path on main to commit 5d19beb; the PR directly changes those blamed areas. (src/infra/diagnostic-events.ts:803, 5d19beb547e1)

Likely related people:

hcl: git blame attributes the current main diagnostic scheduler and Codex dynamic-tool terminal fallback lines changed by this PR to commit 5d19beb. (role: recent area contributor; confidence: medium; commits: 5d19beb547e1; files: src/infra/diagnostic-events.ts, extensions/codex/src/app-server/run-attempt.ts, src/plugin-sdk/diagnostic-runtime.ts)
Vincent Koc: git log -G for diagnostic-events shows prior diagnostics and plugin-hook work touching the diagnostic event area, including OpenTelemetry migration and hook registry preservation commits. (role: diagnostics history contributor; confidence: medium; commits: de656e319471, d22279d2e873; files: src/infra/diagnostic-events.ts)
pash-openai: recent history for extensions/codex/src/app-server/run-attempt.ts includes adjacent Codex app-server work, making this a plausible review route for Codex run-attempt behavior. (role: recent adjacent Codex contributor; confidence: low; commits: e0d1a2a9b9a8; files: extensions/codex/src/app-server/run-attempt.ts)
Peter Steinberger: git log -G for diagnostic-events shows adjacent core runtime state consolidation and release-history work touching the diagnostics area. (role: adjacent core runtime contributor; confidence: low; commits: 9428b38452f8, 50a2481652b6; files: src/infra/diagnostic-events.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 0556ac0291a8.

Takhoffman · 2026-05-19T17:37:05Z

@clawsweeper automerge

clawsweeper · 2026-05-19T17:39:25Z

🦞✅
ClawSweeper merged this PR after the passing review.

Source: clawsweeper[bot]
Feedback: structured ClawSweeper verdict: pass (sha=95610934cde899f5d6549d2c8c99425d4d26a2db)
Merge status: merged by ClawSweeper automerge
Merged at: 2026-05-20T02:55:18Z
Merge commit: 5d799c2d2052

What merged:

The branch caps async diagnostic drains at 100 events per turn, adds pending/full-drain diagnostic helpers, ... rminal diagnostics to inspect pending events, and adds regression coverage plus changelog/baseline updates.
Reproducibility: yes. from source inspection. Current main drains the entire async diagnostic queue in one s ... ck, and the PR body supplies a focused 250-event after-fix probe showing 100/200/250 delivery across turns.

Automerge notes:

PR branch already contained follow-up commit before automerge: fix: yield diagnostic event drains

The automerge loop is complete.

Automerge progress:

2026-05-20 01:49:58 UTC review queued f1afdb6ad943 (after repair)

2026-05-20 02:00:02 UTC automerge wait f1afdb6ad943 (waiting) in 26m 49s Run: https://github.com/openclaw/clawsweeper/actions/runs/26135705990 waiting for GitHub checks: build-artifacts:IN_PROGRESS, check-additional-boundaries-a:IN_PROGRESS

2026-05-20 01:56:13 UTC review passed f1afdb6ad943 (structured ClawSweeper verdict: pass (sha=f1afdb6ad94352025ed49260e80829e35680e...)

2026-05-20 02:00:03 UTC repair finished f1afdb6ad943 (pushed) in 26m 50s Run: https://github.com/openclaw/clawsweeper/actions/runs/26135705990 repair_contributor_branch

2026-05-20 02:20:23 UTC review queued f1afdb6ad943 (queued)

2026-05-20 02:22:30 UTC repair queued f1afdb6ad943 (autonomous) Run: https://github.com/openclaw/clawsweeper/actions/runs/26137352287

2026-05-20 02:26:40 UTC repair started (running) in 1s Run: https://github.com/openclaw/clawsweeper/actions/runs/26137352287 automerge-openclaw-openclaw-82937

2026-05-20 02:26:58 UTC validation plan (passed) in 18s Run: https://github.com/openclaw/clawsweeper/actions/runs/26137352287 pnpm check:changed; pnpm lint; pnpm check:test-types

2026-05-20 02:27:23 UTC Codex write preflight (passed) in 43s Run: https://github.com/openclaw/clawsweeper/actions/runs/26137352287 danger-full-access

2026-05-20 02:35:20 UTC Codex edit 1 e921e19de164 (complete) in 8m 40s Run: https://github.com/openclaw/clawsweeper/actions/runs/26137352287 exit 0

2026-05-20 02:32:21 UTC review passed e921e19de164 (structured ClawSweeper verdict: pass (sha=e921e19de1645b035dc852b2b6d1d925b72b0...)

2026-05-20 02:46:00 UTC validation and review 1 697a216ae14a (base moved) in 19m 20s Run: https://github.com/openclaw/clawsweeper/actions/runs/26137352287 rebased

2026-05-20 02:46:04 UTC repair completed (no branch change) in 19m 24s Run: https://github.com/openclaw/clawsweeper/actions/runs/26137352287 source PR branch changed while the repair worker was preparing its push; requeue against the latest head

2026-05-20 02:46:05 UTC repair finished (blocked) in 19m 25s Run: https://github.com/openclaw/clawsweeper/actions/runs/26137352287 source PR branch changed while the repair worker was preparing its push; requeue against the latest head

2026-05-20 02:50:54 UTC review passed 95610934cde8 (structured ClawSweeper verdict: pass (sha=95610934cde899f5d6549d2c8c99425d4d26a...)

2026-05-20 02:55:20 UTC merged 95610934cde8 (merged by ClawSweeper automerge)

clawsweeper · 2026-05-19T18:31:38Z

🦞✅
ClawSweeper is pausing this repair loop for human review.

Source: clawsweeper[bot]
Reason: The protected maintainer label and absence of actionable review findings make this a human landing/review decision, not a ClawSweeper repair job.; Cleared: Cleared: the diff changes in-memory diagnostic scheduling, an SDK re-export, and tests, with no dependency, workflow, secret, network, package-resolution, or permission changes. (sha=4024e1172d5343681d8d465132420b11063ae90d)

Why human review is needed:
This item touches a maintainer-protected decision point. ClawSweeper is keeping the item open so a maintainer can own the final validation choice.

Recommended next action:
Have a maintainer review the flagged decision, then either add the missing proof and re-run ClawSweeper or merge manually if the maintainer accepts the remaining risk.

I added clawsweeper:human-review and left the final call with a maintainer.

clawsweeper · 2026-05-20T01:30:03Z

ClawSweeper PR egg

✨ Hatched: 🥚 common Pearl Crabkin

Hatch command

Comment @clawsweeper hatch when this PR is hatchable.

Hatchability rules:

Merged PRs are hatchable.
Open PRs are hatchable when they are status: 👀 ready for maintainer look, status: 🚀 automerge armed, or labeled clawsweeper:automerge.
Closed unmerged PRs are hatchable only when one of those hatchable labels is still present in the durable record.

Rarity: 🥚 common.
Trait: purrs at green checks.
Image traits: location artifact grotto; accessory CI status badge; palette charcoal, cyan, and signal green; mood curious; pose balancing on a branch marker; shell woven fiber shell; lighting moonlit rim light; background gentle dashboard dots.
Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Pearl Crabkin in ClawSweeper.

What is this egg doing here?

Eggs appear after the PR passes real-behavior proof. It is here for vibes, not verdicts: it does not change labels, ratings, merge decisions, or automation.
The shell reacts to review momentum: open follow-up work warms it up, re-review makes it wobble, and a clean final review lets it hatch.
Hatchability usually comes from sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness. A merged PR is already final, so merge makes the egg hatchable independently.
The hatch is seeded from this repository and PR number, so the same PR keeps the same creature; the reviewed head SHA can only change safe visual details.
Rarity is just collectible sparkle: 🥚 common, 🌱 uncommon, 💎 rare, ✨ glimmer, and 🌈 legendary.

Summary: - The branch caps async diagnostic drains at 100 events per turn, adds pending/full-drain diagnostic helpers, ... rminal diagnostics to inspect pending events, and adds regression coverage plus changelog/baseline updates. - Reproducibility: yes. from source inspection. Current main drains the entire async diagnostic queue in one s ... ck, and the PR body supplies a focused 250-event after-fix probe showing 100/200/250 delivery across turns. Automerge notes: - PR branch already contained follow-up commit before automerge: fix: yield diagnostic event drains Validation: - ClawSweeper review passed for head 95610934cde899f5d6549d2c8c99425d4d26a2db. - Required merge gates passed before the squash merge. Prepared head SHA: 95610934cde899f5d6549d2c8c99425d4d26a2db Review: openclaw/openclaw#82937 (comment) Co-authored-by: Galin Iliev <galini@microsoft.com> Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>

…026.5.20) (#615) This PR contains the following updates: | Package | Update | Change | |---|---|---| | [ghcr.io/openclaw/openclaw](https://openclaw.ai) ([source](https://github.com/openclaw/openclaw)) | patch | `2026.5.19` → `2026.5.20` | --- > ⚠️ **Warning** > > Some dependencies could not be looked up. Check the [Dependency Dashboard](issues/567) for more information. --- ### Release Notes <details> <summary>openclaw/openclaw (ghcr.io/openclaw/openclaw)</summary> ### [`v2026.5.20`](https://github.com/openclaw/openclaw/blob/HEAD/CHANGELOG.md#2026520) [Compare Source](openclaw/openclaw@v2026.5.19...v2026.5.20) ##### Changes - Exec approvals: remove the old `cat SKILL.md && printf ... && <skill-wrapper>` allowlist compatibility path so skill files must be loaded with the read tool and only the real skill executable is auto-allowed. - Discord: let voice sessions follow configured Discord users into voice channels, with allowed-channel checks, multi-user handoff, bounded reconciliation, and DAVE recovery preservation. ([#84264](openclaw/openclaw#84264)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Discord/voice: include bounded `IDENTITY.md`, `USER.md`, and `SOUL.md` profile context in realtime voice session instructions by default, with `voice.realtime.bootstrapContextFiles: []` available to disable it. ([#84499](openclaw/openclaw#84499)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Dependencies: bump the bundled Codex harness to `@openai/codex` `0.132.0` and refresh the app-server model-list docs for the new catalog. - CLI/policy: add the bundled Policy plugin for policy-backed channel conformance checks, doctor lint findings, and opt-in workspace repair. ([#80407](openclaw/openclaw#80407)) Thanks [@giodl73-repo](https://github.com/giodl73-repo). - Agents/config: allow `agents.list[].experimental.localModelLean` so lean local-model mode can be enabled for one configured agent instead of globally. - Providers/xAI: add device-code OAuth login so remote and headless setups can authorize xAI without a localhost browser callback. ([#84005](openclaw/openclaw#84005)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Providers/OpenRouter: honor provider-level `params.provider` routing policy for OpenRouter requests, with model and agent params overriding the defaults. Thanks [@amknight](https://github.com/amknight). ##### Fixes - CLI/tasks: include stale-running task maintenance decisions in `openclaw tasks maintenance --json` so retained and reconcile candidates explain backing-session, cron, CLI, and wedged-subagent state. ([#84691](openclaw/openclaw#84691)) Thanks [@efpiva](https://github.com/efpiva). - Codex app-server: keep system-prompt reports working when bootstrap hooks provide workspace files with only a path and content, so hook-supplied SOUL/IDENTITY/TOOLS/USER context still reports injected characters correctly. ([#84736](openclaw/openclaw#84736)) Thanks [@JARVIS-Glasses](https://github.com/JARVIS-Glasses). - Providers/MiniMax music: stop advertising `durationSeconds` control and remove prompt-injected duration hints, so `music_generate` reports MiniMax duration as an unsupported override instead of suggesting MiniMax can enforce track length. Fixes [#84508](openclaw/openclaw#84508). Thanks [@neeravmakwana](https://github.com/neeravmakwana). - Doctor: warn when sandbox tool policy hides configured MCP server tools before provider requests. ([#84699](openclaw/openclaw#84699)) Thanks [@nxmxbbd](https://github.com/nxmxbbd). - WhatsApp: update Baileys to `7.0.0-rc12`. - Build: suppress per-locale `rolldown-plugin-dts:fake-js` CommonJS dts warnings emitted while bundling the intentionally-inlined `zod/v4/locales/*.d.cts` files, so `pnpm build` output stays readable after the 0.25.1 plugin bump. Thanks [@romneyda](https://github.com/romneyda). - CLI/nodes: route lazy plugin-registration logs to stderr for JSON-mode `openclaw nodes` commands so stdout stays parseable. ([#84684](openclaw/openclaw#84684)) Thanks [@TurboTheTurtle](https://github.com/TurboTheTurtle). - Approvals: route manual `/approve` decisions through the trusted approval runtime so active exec and plugin approvals no longer look unknown or expired. - Mac app: update the About settings copyright year to 2026. ([#84385](openclaw/openclaw#84385)) Thanks [@pejmanjohn](https://github.com/pejmanjohn). - Dependencies: update `@openclaw/fs-safe` to `0.2.7` so OpenClaw's default Python-helper-off policy keeps best-effort Node write fallbacks for private stores, secret writes, run logs, and media attachments on Linux/macOS. - Infra/secrets: restore the fail-closed contract for `tryReadSecretFileSync` so credential loaders that pass `rejectSymlink: true` (Telegram, LINE, Zalo, IRC, Nextcloud Talk tokens) refuse symlinked credential files instead of silently accepting them, and the infra-state CI shard's secret-file symlink test passes again. Thanks [@romneyda](https://github.com/romneyda). - Browser: honor the configured image sanitization limit for screenshots and labeled snapshots so browser-captured images follow the same resize policy as other image results. ([#84595](openclaw/openclaw#84595)) - Doctor: remove unrecognized `models.providers.*.models[*].compat.thinkingFormat` values during `doctor --fix` so stale provider model config can validate after upgrade. Fixes [#77803](openclaw/openclaw#77803). - Doctor: warn when `openclaw.json` stores plaintext secret-bearing config fields, including model provider API keys and sensitive provider headers. ([#84718](openclaw/openclaw#84718)) Thanks [@lukaIvanic](https://github.com/lukaIvanic). - Status: show the configured default, session-selected model, reason, clear hint, and docs link when a session remains pinned to a model that differs from `agents.defaults.model.primary`. - WebChat: clear stale typing indicators when session change events mark the active chat run complete. - Mac app: keep local packaging signed with a stable app identity for permission testing and fix Control UI production builds under current Vite/Highlight.js exports. - macOS app: update the embedded Peekaboo bridge to 3.2.1 so OpenClaw-hosted UI automation works with current Peekaboo CLI capture flows. - Cron: deliver preferred final assistant output for successful scheduled runs when trailing plain tool warnings remain in diagnostics instead of marking the run failed. - fix(mattermost): fail closed on missing channel type \[AI]. ([#84091](openclaw/openclaw#84091)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Recheck rebuilt system.run argv \[AI]. ([#84090](openclaw/openclaw#84090)) Thanks [@pgondhi987](https://github.com/pgondhi987). - CLI: keep the private QA subcommand out of exported command descriptors unless `OPENCLAW_ENABLE_PRIVATE_QA_CLI=1`, so root help and subcommand markers match runtime registration. ([#84519](openclaw/openclaw#84519)) - CLI/cron: bound `openclaw cron show` job lookup pagination so non-advancing or unbounded `cron.list` responses fail instead of hanging the command. Fixes [#83856](openclaw/openclaw#83856). ([#83989](openclaw/openclaw#83989)) - Agents/messages: stop message-tool-only turns after a successful source-channel `message` send while keeping transcript mirrors under the session write lock. ([#84289](openclaw/openclaw#84289)) - Agents: filter silent heartbeat response-tool transcript artifacts out of embedded context snapshots so later user turns are not polluted by heartbeat no-op messages. ([#83477](openclaw/openclaw#83477)) Thanks [@fuller-stack-dev](https://github.com/fuller-stack-dev). - Agents/OpenAI: log repeated strict tool-schema downgrade diagnostics once per provider/model/tool signature, reducing duplicate debug noise while preserving `strict=false` fallback behavior. Fixes [#82930](openclaw/openclaw#82930). ([#82933](openclaw/openclaw#82933)) Thanks [@galiniliev](https://github.com/galiniliev). - Agents/code mode: spell out the `exec` tool's JavaScript/TypeScript, no Node module, and catalog-bridge constraints in model-visible schema text so agents can use enabled tools without trial-and-error. ([#84269](openclaw/openclaw#84269)) Thanks [@Kaspre](https://github.com/Kaspre). - Codex: give `image_generate` dynamic-tool calls a 120s default watchdog when no per-call or configured image timeout is set, so image generation no longer falls back to the generic 30s bridge timeout. ([#84254](openclaw/openclaw#84254)) Thanks [@moritzmmayerhofer](https://github.com/moritzmmayerhofer). - Codex: avoid duplicate dynamic tool terminal diagnostics while large diagnostic backlogs drain without blocking tool responses. ([#82937](openclaw/openclaw#82937)) Thanks [@galiniliev](https://github.com/galiniliev). - CLI/message: include a stable top-level `messageId` in `openclaw message --json` output when channel sends return one. ([#84191](openclaw/openclaw#84191)) Thanks [@100menotu001](https://github.com/100menotu001). - Cron: preserve legacy top-level array `jobs.json` stores when loading or adding scheduled jobs so old cron jobs are no longer treated as an empty store during upgrade. Fixes [#60799](openclaw/openclaw#60799). ([#84433](openclaw/openclaw#84433)) Thanks [@IWhatsskill](https://github.com/IWhatsskill). - Gateway/agents: use an agent's `identity.name` in Gateway agent summaries when `agents.list[].name` is unset, so configured agent labels remain visible in clients. ([#84355](openclaw/openclaw#84355); refs [#57835](openclaw/openclaw#57835)) Thanks [@luoyanglang](https://github.com/luoyanglang). - Channels/replies: keep normal `/verbose` failed-tool progress compact in message-tool replies and prevent late text-only tool output from appearing after the final answer. ([#84303](openclaw/openclaw#84303)) Thanks [@VACInc](https://github.com/VACInc). - Plugins/hooks: apply a default 30-second timeout to `before_compaction` and `after_compaction` hooks so a hung plugin handler no longer blocks compaction completion. ([#84153](openclaw/openclaw#84153)) - Discord: preserve disabled presentation buttons when adapting and rendering Discord message controls. ([#84188](openclaw/openclaw#84188)) Thanks [@100menotu001](https://github.com/100menotu001). - Twitch: add a test-only client-manager registry reset helper so non-isolated Twitch tests can clear cached managers between cases. Fixes [#83887](openclaw/openclaw#83887). ([#84244](openclaw/openclaw#84244)) Thanks [@hclsys](https://github.com/hclsys). - Cron: run main-session scheduled work on a cron-owned wake lane while preserving reply delivery context, so background cron turns no longer block human main-session chat. Fixes [#82766](openclaw/openclaw#82766). ([#82767](openclaw/openclaw#82767)) Thanks [@galiniliev](https://github.com/galiniliev). - Cron: use structured embedded-run denial metadata for isolated scheduled tasks so blocked exec requests fail the job without treating ordinary assistant prose as a denial. ([#84067](openclaw/openclaw#84067)) Thanks [@abnershang](https://github.com/abnershang). - Cron: keep recovered tool warnings diagnostic for successful scheduled runs so final cron output is delivered instead of being replaced by a post-processing warning. ([#84045](openclaw/openclaw#84045)) Thanks [@abnershang](https://github.com/abnershang). - Plugins/perf: thread explicit plugin discovery results through `loadBundledCapabilityRuntimeRegistry`, `resolveBundledPluginSources`, and `listChannelCatalogEntries` so callers that already hold a discovery result skip redundant filesystem walks. Thanks [@SebTardif](https://github.com/SebTardif). - harden update restart script creation \[AI]. ([#84088](openclaw/openclaw#84088)) Thanks [@pgondhi987](https://github.com/pgondhi987). - Docker: keep the bundled Codex plugin in official release image keep lists so the default OpenAI agent harness remains available after Docker pruning. Fixes [#83613](openclaw/openclaw#83613). ([#83626](openclaw/openclaw#83626)) Thanks [@YuanHanzhong](https://github.com/YuanHanzhong). - CLI/channels: preserve the first line of `openclaw channels logs` output when the rolling tail window starts exactly on a line boundary, mirroring the already-fixed `readLogSlice` behavior in `src/logging/log-tail.ts`. - Control UI: treat terminal session status as authoritative over stale active-run flags so completed terminal runs stop showing abort/live UI. ([#84057](openclaw/openclaw#84057)) - CLI: preserve embedded equals signs in inline root option values instead of truncating after the second separator. ([#83995](openclaw/openclaw#83995)) Thanks [@ThiagoCAltoe](https://github.com/ThiagoCAltoe). - Matrix/config: accept `messages.queue.byChannel.matrix` queue overrides and keep queue provider schema/type keys aligned for Matrix, Google Chat, and Mattermost. Thanks [@bdjben](https://github.com/bdjben). - CLI: format `openclaw acp client` failures through the shared error formatter so object-shaped errors stay readable instead of printing `[object Object]`. Fixes [#83904](openclaw/openclaw#83904). ([#84080](openclaw/openclaw#84080)) - Providers/Ollama: default unknown-capabilities models to tool-capable so discovered native Ollama models can use tools when `/api/show` omits capabilities. ([#84055](openclaw/openclaw#84055)) Thanks [@dutifulbob](https://github.com/dutifulbob). - Installer/Windows: launch `install.ps1` onboarding as an attached child process so fresh native Windows installs do not freeze visibly at `Starting setup...` or corrupt the wizard's terminal rendering. - CLI/update: keep restart health checks working across one-version CLI/Gateway protocol skew and use the managed Gateway service Node for all follow-up commands even when the package root is unchanged, so `openclaw update` no longer silently switches the gateway to a different Node binary when multiple Node installations are present. Thanks [@amknight](https://github.com/amknight). - CLI/gateway: include the running Gateway version in `gateway status` JSON output, preserving existing server metadata while falling back to status RPC data for read probes. Fixes [#56222](openclaw/openclaw#56222). Thanks [@galiniliev](https://github.com/galiniliev). - Memory/search: close local embedding providers when active-memory searches time out so pending local model loads and embedding contexts are aborted and released. ([#83858](openclaw/openclaw#83858)) Thanks [@brokemac79](https://github.com/brokemac79). - CLI/nodes: request pending node surface approval scopes before `openclaw nodes approve` so exec-capable node approval can use admin-scoped Gateway credentials instead of failing with `missing scope: operator.admin`. ([#84392](openclaw/openclaw#84392)) Thanks [@joshavant](https://github.com/joshavant). - Gateway: reject slow node event sends before outbound buffers grow unbounded and log the rejected payload diagnostic. ([#84387](openclaw/openclaw#84387)) Thanks [@samzong](https://github.com/samzong). - Agents: include bounded trajectory queued-writer diagnostics in `pi-trajectory-flush` timeout warnings so flush stalls show pending writes, queued bytes, and append state. Fixes [#82961](openclaw/openclaw#82961). ([#82962](openclaw/openclaw#82962)) Thanks [@galiniliev](https://github.com/galiniliev). - Agents/subagents: recover stale completion announces by retrying unsupported transcript-wait wakes without transcript waiting and forcing a message-tool handoff when the requester run is already stale. Fixes [#83699](openclaw/openclaw#83699). ([#83700](openclaw/openclaw#83700)) Thanks [@galiniliev](https://github.com/galiniliev). - Agents/subagents: constrain wildcard subagent target allowlists to configured agents while preserving explicitly listed compatibility targets. Fixes [#84040](openclaw/openclaw#84040). ([#84357](openclaw/openclaw#84357)) Thanks [@joshavant](https://github.com/joshavant). - Providers/Anthropic: route Anthropic model refs selected with Claude CLI auth through the Claude CLI runtime so shorthand refs such as `anthropic/opus-4.7` no longer fall back to embedded Anthropic billing. Fixes [#84222](openclaw/openclaw#84222). ([#84374](openclaw/openclaw#84374)) Thanks [@joshavant](https://github.com/joshavant). - Agents: honor explicit `models.providers.<id>.timeoutSeconds` values above the default idle watchdog for cloud and self-hosted providers, so long first-token waits no longer fall back at \~120s when the provider timeout is higher. ([#83979](openclaw/openclaw#83979)) Thanks [@yujiawei](https://github.com/yujiawei). - Agents/Codex: keep encrypted Responses reasoning replay provenance-bound so stale mirrored Codex transcripts drop invalid encrypted content before request assembly while preserving matching same-session replay. Fixes [#83836](openclaw/openclaw#83836). ([#84367](openclaw/openclaw#84367)) Thanks [@joshavant](https://github.com/joshavant). - Agents/subagents: skip stale embedded-run wake probes for dormant completion requesters, so late subagent completions go straight to requester-agent/direct handoff instead of producing `reason=no_active_run` queue noise. ([#82964](openclaw/openclaw#82964)) Thanks [@galiniliev](https://github.com/galiniliev). - CLI: retry config snapshot reads after a transient failure so one rejected read no longer poisons later commands in the same process. ([#83931](openclaw/openclaw#83931)) Thanks [@honor2030](https://github.com/honor2030). - Media: decode URL path basenames before using them as remote media fallback filenames, so files like `My%20Report.pdf` are surfaced as `My Report.pdf`. Fixes [#84050](openclaw/openclaw#84050). ([#84052](openclaw/openclaw#84052)) Thanks [@jbetala7](https://github.com/jbetala7). - WhatsApp: clarify inbound group diagnostics so observed but unregistered groups point to `channels.whatsapp.groups` without changing routing or sender authorization. ([#83846](openclaw/openclaw#83846)) Thanks [@neeravmakwana](https://github.com/neeravmakwana). - WhatsApp: drain pending outbound deliveries on a 30s periodic timer in addition to the reconnect handler, so messages enqueued while the provider is already connected no longer wait for the next reconnect to send. ([#79083](openclaw/openclaw#79083)) Thanks [@Oviemudiaga](https://github.com/Oviemudiaga). - CLI/TUI: include gateway plugin slash commands in TUI autocomplete, so connected sessions can suggest plugin-owned commands exposed by the running Gateway. ([#83640](openclaw/openclaw#83640)) Thanks [@se7en-agent](https://github.com/se7en-agent). - Gateway/mobile: restore QR setup-code handoff of bounded operator tokens for iOS and Android onboarding while keeping admin and pairing scopes out of bootstrap. ([#83684](openclaw/openclaw#83684)) Thanks [@ngutman](https://github.com/ngutman). - iOS: repair Release archive compilation for the TestFlight build. ([#84255](openclaw/openclaw#84255)) Thanks [@ngutman](https://github.com/ngutman). - Agents/compaction: bound plugin-owned CLI transcript compaction with the host safety timeout so a hung context engine can no longer stall post-turn cleanup. ([#84083](openclaw/openclaw#84083)) Thanks [@100yenadmin](https://github.com/100yenadmin). - Control UI/usage: truncate long context skill, tool, and file names in the usage panel while keeping the full name available on hover. ([#42197](openclaw/openclaw#42197)) Thanks [@Rain120](https://github.com/Rain120). - Codex: respect explicit `models auth order set` and `config.auth.order` precedence over stale `lastGood` in `/codex account`, and show `no working credential` when every explicit-order profile is ineligible instead of marking a lower-ranked profile as active. Fixes [#84386](openclaw/openclaw#84386). ([#84412](openclaw/openclaw#84412)) Thanks [@openperf](https://github.com/openperf). - Agents: honor `messages.suppressToolErrors` for mutating tool failures so configured chat surfaces do not receive separate warning payloads. ([#81561](openclaw/openclaw#81561)) Thanks [@moeedahmed](https://github.com/moeedahmed). - Agents/fallback: surface billing guidance for mixed rate-limit plus billing fallback exhaustion instead of generic failure copy. Fixes [#79396](openclaw/openclaw#79396). ([#79489](openclaw/openclaw#79489)) Thanks [@aayushprsingh](https://github.com/aayushprsingh). </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/615

Summary: - The branch caps async diagnostic drains at 100 events per turn, adds pending/full-drain diagnostic helpers, ... rminal diagnostics to inspect pending events, and adds regression coverage plus changelog/baseline updates. - Reproducibility: yes. from source inspection. Current main drains the entire async diagnostic queue in one s ... ck, and the PR body supplies a focused 250-event after-fix probe showing 100/200/250 delivery across turns. Automerge notes: - PR branch already contained follow-up commit before automerge: fix: yield diagnostic event drains Validation: - ClawSweeper review passed for head 9561093. - Required merge gates passed before the squash merge. Prepared head SHA: 9561093 Review: openclaw#82937 (comment) Co-authored-by: Galin Iliev <galini@microsoft.com> Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>

openclaw-barnacle Bot added size: XS maintainer Maintainer-authored PR labels May 17, 2026

clawsweeper Bot mentioned this pull request May 17, 2026

[Bug]: Gateway liveness reports severe event-loop stalls under subagent load #82936

Closed

clawsweeper Bot added proof: sufficient ClawSweeper judged the real behavior proof convincing. P1 High-priority user-facing bug, regression, or broken workflow. impact:crash-loop Crash, hang, restart loop, or process-level availability failure. labels May 17, 2026

clawsweeper Bot mentioned this pull request May 19, 2026

Gateway process alive but event loop frozen — all HTTP requests silently timeout #56733

Open

galiniliev self-assigned this May 19, 2026

galiniliev force-pushed the bug-008-gateway-liveness-drain branch from f2782b2 to 4024e11 Compare May 19, 2026 06:51

openclaw-barnacle Bot added extensions: codex size: S and removed size: XS labels May 19, 2026

clawsweeper Bot added the clawsweeper:automerge Maintainer opted this PR into bounded ClawSweeper-reviewed automerge label May 19, 2026

clawsweeper Bot added the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label May 19, 2026

galiniliev force-pushed the bug-008-gateway-liveness-drain branch from 4024e11 to 2ef7487 Compare May 20, 2026 01:17

openclaw-barnacle Bot added docs Improvements or additions to documentation size: M and removed size: S labels May 20, 2026

galiniliev force-pushed the bug-008-gateway-liveness-drain branch from 2ef7487 to cb66da3 Compare May 20, 2026 01:23

clawsweeper Bot removed the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label May 20, 2026

clawsweeper Bot force-pushed the bug-008-gateway-liveness-drain branch from cb66da3 to f1afdb6 Compare May 20, 2026 01:49

openclaw-barnacle Bot added the cli CLI command changes label May 20, 2026

galiniliev force-pushed the bug-008-gateway-liveness-drain branch from f1afdb6 to e921e19 Compare May 20, 2026 02:25

openclaw-barnacle Bot removed the cli CLI command changes label May 20, 2026

galiniliev force-pushed the bug-008-gateway-liveness-drain branch from e921e19 to e5da1d7 Compare May 20, 2026 02:42

galiniliev and others added 2 commits May 20, 2026 02:42

fix: yield diagnostic event drains

d3f9e44

fix: yield diagnostic event drains

9561093

galiniliev force-pushed the bug-008-gateway-liveness-drain branch from e5da1d7 to 9561093 Compare May 20, 2026 02:43

clawsweeper Bot merged commit 5d799c2 into openclaw:main May 20, 2026
101 of 104 checks passed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix: yield diagnostic event drains#82937

fix: yield diagnostic event drains#82937
clawsweeper[bot] merged 2 commits into
openclaw:mainfrom
galiniliev:bug-008-gateway-liveness-drain

galiniliev commented May 17, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 17, 2026 •

edited

Loading

Uh oh!

Takhoffman commented May 19, 2026

Uh oh!

clawsweeper Bot commented May 19, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 19, 2026

Uh oh!

clawsweeper Bot commented May 20, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

galiniliev commented May 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Change Type (select all)

Scope (select all touched areas)

Linked Issue/PR

Real behavior proof (required for external PRs)

Root Cause (if applicable)

Regression Test Plan (if applicable)

User-visible / Behavior Changes

Diagram (if applicable)

Security Impact (required)

Repro + Verification

Environment

Steps

Expected

Actual

Evidence

Human Verification (required)

Review Conversations

Compatibility / Migration

Risks and Mitigations

Uh oh!

clawsweeper Bot commented May 17, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Takhoffman commented May 19, 2026

Uh oh!

clawsweeper Bot commented May 19, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 19, 2026

Uh oh!

clawsweeper Bot commented May 20, 2026

Hatch command

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

galiniliev commented May 17, 2026 •

edited

Loading

clawsweeper Bot commented May 17, 2026 •

edited

Loading

clawsweeper Bot commented May 19, 2026 •

edited

Loading