fix(subagents): collect unresolved announce batches by TurboTheTurtle · Pull Request #83701 · openclaw/openclaw

TurboTheTurtle · 2026-05-18T16:59:01Z

Summary

Treat unresolved-origin queued announce items as compatible with an otherwise single keyed route, so collect mode can batch them instead of forcing individual delivery.
Let collect mode resume batching a later compatible slice after one true cross-channel drain.
Cover both the helper classification and drain behavior with focused regressions.

Root cause

hasCrossChannelItems treated any unkeyed item mixed with keyed items as cross-channel, even when every resolved item pointed at the same route. Once collect mode saw a cross-channel slice, forceIndividualCollect also stayed sticky for the rest of the drain, so a later same-route batch could still be split.

Real behavior proof

Behavior addressed: Collect-mode follow-up drains now batch unresolved-origin announce items with the resolved same-route items instead of forcing every queued item into individual delivery, and batching resumes after a true cross-channel slice.
Real environment tested: Local OpenClaw checkout on this PR branch using the production queue implementation imported by a standalone Node/TSX harness; no Vitest module mocks were used for the after-fix behavior proof.

Exact steps or command run after this patch:

PATH=/Users/andy/.cache/codex-runtimes/codex-primary-runtime/dependencies/node/bin:$PATH     node_modules/.bin/tsx /private/tmp/prove-queue-collect-real.ts

Supplemental regression commands also run:

PATH=/Users/andy/.cache/codex-runtimes/codex-primary-runtime/dependencies/node/bin:$PATH node scripts/run-vitest.mjs src/utils/queue-helpers.test.ts
PATH=/Users/andy/.cache/codex-runtimes/codex-primary-runtime/dependencies/node/bin:$PATH node scripts/run-vitest.mjs src/auto-reply/reply/queue.collect.test.ts
PATH=/Users/andy/.cache/codex-runtimes/codex-primary-runtime/dependencies/node/bin:$PATH node_modules/.bin/oxfmt --check --threads=1 CHANGELOG.md src/utils/queue-helpers.ts src/utils/queue-helpers.test.ts src/auto-reply/reply/queue/drain.ts src/auto-reply/reply/queue.collect.test.ts
git diff --check

Evidence after fix: Terminal output from the production-queue harness was copied into the PR discussion on 2026-05-18. It exercised the real enqueueFollowupRun + scheduleFollowupDrain drain path used before subagent announce delivery and observed one collected delivery for the unresolved/same-route slice, then individual delivery only for the true cross-channel slice.
Observed result after fix: The unresolved-origin same-route batch was delivered through collect mode as one combined follow-up instead of being split; the later cross-channel slice still drained individually; focused queue helper and collect regression tests passed.
Not tested: The broader Vitest e2e collect slice using test/vitest/vitest.e2e.config.ts could not run in this local dependency tree because @openclaw/proxyline is missing.

Attribution

Please preserve commit author attribution when squashing/reworking, or include:

Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com>

clawsweeper · 2026-05-18T17:00:14Z

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 PR changes collect-mode follow-up queue routing so unresolved-origin items can batch with a single resolved route and later compatible items can resume batching after a true cross-channel drain.

Reproducibility: yes. at source level: current main treats unkeyed-plus-same-keyed queue items as cross-channel and keeps forced individual collection sticky across the drain. I did not run tests because this review is read-only, but the failing path is directly visible in src/utils/queue-helpers.ts and src/auto-reply/reply/queue/drain.ts.

PR rating
Overall: 🐚 platinum hermit
Proof: 🐚 platinum hermit
Patch quality: 🦞 diamond lobster
Summary: The patch is focused and well covered, with good production-path proof and only live transport residual risk.

Rank-up moves:

none

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.

PR egg
✨ Hatched: 🌱 uncommon Gilded Patch Peep

        /\     /\            
      _/  \___/  \_          
     /  ( o   o )  \         
    |      \_/      |        
    |   /\  ===  /\ |        
     \_/  \_____/  \_/       
        _/|_| |_|\_          
       /__| | | |__\         
          ' ' ' '            
         /_/     \_\         
       .-----------.         
      '-------------'

Rarity: 🌱 uncommon.
Trait: purrs at green checks.
Share on X: post this hatch
Copy: My PR egg hatched a 🌱 uncommon Gilded Patch Peep 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.
How to hatch it: reach status: 👀 ready for maintainer look or status: 🚀 automerge armed; that usually means sufficient real-behavior proof, no blocking P0/P1/P2 findings, no security attention needed, and clean correctness.
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.

Real behavior proof
Override: A maintainer applied proof: override for this PR.

Risk before merge
Why this matters: - This changes message-delivery batching and route inheritance for unresolved-origin queued items; a bad assumption could still batch to the wrong destination or split messages unexpectedly.

The supplied proof exercises the production queue/drain path, but not a full live subagent transport run; maintainers have already applied proof: override if they accept that residual risk.

Maintainer options:

Accept queue-path proof with exact-head gates (recommended)
The production queue harness and focused regressions cover the changed batching behavior, so maintainers can let automerge proceed if required checks pass on e6ad029.
Require live subagent transcript
If transport-level confidence is required, ask for a redacted live or Testbox collect-mode subagent run showing unresolved-origin announces collected into the requester session before merge.

Next step before merge
No repair lane is needed because review found no blocking defect; the remaining action is exact-head automerge validation or maintainer choice on live-transport proof.

Security
Cleared: The diff is limited to queue logic, focused tests, and a changelog entry; it does not change dependencies, credentials, workflows, install scripts, or code-execution surfaces.

Review details

Best possible solution:

Merge this focused queue fix through exact-head automerge gates, then let the linked issue close from #83701.

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

Yes at source level: current main treats unkeyed-plus-same-keyed queue items as cross-channel and keeps forced individual collection sticky across the drain. I did not run tests because this review is read-only, but the failing path is directly visible in src/utils/queue-helpers.ts and src/auto-reply/reply/queue/drain.ts.

Is this the best way to solve the issue?

Yes: the PR targets the two implicated queue conditions without adding a new mode or changing plugin/provider policy. The safer merge path is exact-head automated checks plus maintainer acceptance of the production queue proof or a requested live subagent transcript.

Label justifications:

P1: The linked issue reports silent loss of subagent announce messages in real collect-mode fan-out workflows.
merge-risk: 🚨 message-delivery: The PR changes how queued follow-up messages are classified, batched, and routed after cross-channel detection.

What I checked:

Current-main false-positive route classification: Current main records hasUnkeyed and returns cross-channel when any unkeyed item appears with keyed items, matching the linked issue's unresolved-origin batching failure. (src/utils/queue-helpers.ts:240, 3e6f7494af75)
Current-main sticky collect state: Current main initializes collectState once before the drain loop, so a cross-channel iteration keeps forceIndividualCollect set for later iterations. (src/auto-reply/reply/queue/drain.ts:308, 3e6f7494af75)
PR head helper fix: The PR head removes the unkeyed-item cross-channel shortcut and returns true only for explicit cross items or more than one resolved key. (src/utils/queue-helpers.ts:235, e6ad029e2387)
PR head drain reset: The PR head resets forced individual collection when the remaining collect slice is no longer cross-channel and has multiple items, allowing a later compatible batch to collect. (src/auto-reply/reply/queue/drain.ts:335, e6ad029e2387)
Regression coverage: The PR adds collect-drain tests for cross-channel-then-compatible batching and unresolved-origin-plus-single-route batching, plus helper tests for unkeyed items and explicit cross items. (src/auto-reply/reply/queue.collect.test.ts:99, e6ad029e2387)
Live PR state: GitHub API reports the PR open, non-draft, mergeable, at head e6ad029 with five changed files and the clawsweeper:automerge, proof: override, P1, and message-delivery merge-risk labels. (e6ad029e2387)

Likely related people:

@steipete: GitHub commit history for queue helpers, collect-mode drain refactors, and subagent announce delivery includes several central changes by Peter Steinberger. (role: recent area contributor; confidence: high; commits: b22deada9e86, dacb3d1aa2c6, 712644f0d9a4; files: src/utils/queue-helpers.ts, src/auto-reply/reply/queue/drain.ts, src/agents/subagent-announce-delivery.ts)
@vincentkoc: Recent follow-up queue history includes callback, metadata, and reply queue fixes by Vincent Koc on the same drain path. (role: recent queue maintainer; confidence: medium; commits: 8a2348547251, a35dcf608e8e; files: src/auto-reply/reply/queue/drain.ts)
Agustin Rivera: The collect-mode authorization split that this PR must preserve was introduced in a recent queue PR by Agustin Rivera. (role: adjacent collect-mode contributor; confidence: medium; commits: 43d4be902755; files: src/auto-reply/reply/queue/drain.ts, src/auto-reply/reply/queue.collect.test.ts)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 3e6f7494af75.

TurboTheTurtle · 2026-05-18T17:59:24Z

Real behavior proof for the collect-mode queue path:

I ran a standalone Node harness against this PR branch that imports the production queue implementation and uses the real enqueueFollowupRun + scheduleFollowupDrain path. This is outside Vitest and uses no module mocks. It directly exercises the collect-mode drain path used before subagent announce delivery.

Command:

PATH=/Users/andy/.cache/codex-runtimes/codex-primary-runtime/dependencies/node/bin:$PATH node_modules/.bin/tsx /private/tmp/prove-83701-collect-mode.mts

Result:

{
  "proofKind": "production followup queue collect-mode drain",
  "note": "Standalone Node harness; imports production queue.ts, uses real enqueueFollowupRun and scheduleFollowupDrain, no Vitest and no module mocks.",
  "startedAt": "2026-05-18T17:58:49.212Z",
  "scenarios": {
    "unresolvedOriginPlusSingleRoute": {
      "queuedItems": 3,
      "deliveredRuns": 1,
      "expectedBehavior": "one collected delivery routed to the resolved slack/channel:B route",
      "deliveries": [
        {
          "originatingChannel": "slack",
          "originatingTo": "channel:B",
          "promptLines": [
            "[Queued messages while agent was busy]",
            "",
            "---",
            "Queued #1",
            "unresolved origin",
            "",
            "---",
            "Queued #2",
            "keyed one",
            "",
            "---",
            "Queued #3",
            "keyed two"
          ]
        }
      ],
      "result": "PASS"
    },
    "crossChannelThenCompatibleBatch": {
      "queuedItems": 3,
      "deliveredRuns": 2,
      "expectedBehavior": "first cross-channel item delivered individually; later same-route items collected together",
      "deliveries": [
        {
          "originatingChannel": "slack",
          "originatingTo": "channel:A",
          "promptLines": [
            "first route"
          ]
        },
        {
          "originatingChannel": "slack",
          "originatingTo": "channel:B",
          "promptLines": [
            "[Queued messages while agent was busy]",
            "",
            "---",
            "Queued #1",
            "second route one",
            "",
            "---",
            "Queued #2",
            "second route two"
          ]
        }
      ],
      "result": "PASS"
    }
  },
  "completedAt": "2026-05-18T17:58:49.239Z",
  "result": "PASS"
}

Interpretation:

Unresolved-origin queued item + two resolved same-route items produced one collected delivery.
The collected delivery inherited the resolved route: slack / channel:B.
A true cross-channel first item still delivered individually.
The later compatible channel:B slice resumed collection and delivered as one batch, proving forceIndividualCollect did not stay sticky.

I could not run the Docker live subagent harness from this machine because Docker is not installed here and no live model credentials are exposed, but this proof uses the production queue/drain code path directly and shows the corrected delivery payload shape.

@clawsweeper re-review

clawsweeper · 2026-05-18T18:00:30Z

🦞🧹
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/26051096967
Updated: 2026-05-18T18:08:18.790Z

# Conflicts: # CHANGELOG.md

Takhoffman · 2026-05-18T18:24:55Z

@clawsweeper automerge

clawsweeper · 2026-05-18T18:27:14Z

🦞✅
ClawSweeper merged this PR after the passing review.

Source: clawsweeper[bot]
Feedback: structured ClawSweeper verdict: pass (sha=e6ad029e23873fdac7aaa735d10589b20ac92e55)
Merge status: merged by ClawSweeper automerge
Merged at: 2026-05-18T18:34:59Z
Merge commit: 44c6ad7dce27

What merged:

The PR changes collect-mode follow-up queue routing so unresolved-origin items can batch with a single resolved route and later compatible items can resume batching after a true cross-channel drain.
Reproducibility: yes. at source level: current main treats unkeyed-plus-same-keyed queue items as cross-chan ... failing path is directly visible in src/utils/queue-helpers.ts and src/auto-reply/reply/queue/drain.ts.

Automerge notes:

PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'origin/main' into maint-83701-20260518

The automerge loop is complete.

Automerge progress:

2026-05-18 18:27:13 UTC review queued e6ad029e2387 (queued)

2026-05-18 18:34:46 UTC review passed e6ad029e2387 (structured ClawSweeper verdict: pass (sha=e6ad029e23873fdac7aaa735d10589b20ac92...)

2026-05-18 18:35:02 UTC merged e6ad029e2387 (merged by ClawSweeper automerge)

Summary: - The PR changes collect-mode follow-up queue routing so unresolved-origin items can batch with a single resolved route and later compatible items can resume batching after a true cross-channel drain. - Reproducibility: yes. at source level: current main treats unkeyed-plus-same-keyed queue items as cross-chan ... failing path is directly visible in `src/utils/queue-helpers.ts` and `src/auto-reply/reply/queue/drain.ts`. Automerge notes: - PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'origin/main' into maint-83701-20260518 Validation: - ClawSweeper review passed for head e6ad029. - Required merge gates passed before the squash merge. Prepared head SHA: e6ad029 Review: openclaw#83701 (comment) Co-authored-by: Andy Ye <35905412+TurboTheTurtle@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>

* fix(gateway): clear CLI bindings on session reset * fix(gateway): preserve spawned sessions in configured lists * fix(channels): clear canonical stale routes * fix(telegram): preserve forum topic origin targets * fix(agents): skip fallback for session coordination errors * fix(agents): persist subagent registry before returning accepted (openclaw#83132) (openclaw#83238) * fix(memory): catch up stale sessions on startup (openclaw#82341) * fix(memory): preserve qmd lexical search for hyphenated queries (openclaw#81423) * fix(anthropic): preserve Claude image capability (openclaw#83756) * fix(agents): exclude tool result details from guard budget (openclaw#75525) * fix(provider): use Together video API endpoint * fix(telegram): preserve implicit default account (openclaw#82794) * fix(gateway): allow trusted-proxy local-direct password fallback (openclaw#82953) * fix(discord): return subagent thread delivery origin * fix: add missing prerequisites for upstream-ported fixes Add SessionWriteLockTimeoutError class and hasSessionWriteLockTimeout helper needed by the ported fix(agents) skip-fallback commit. Remove route property references from session-delivery.ts that don't exist in gemmaclaw's SessionEntry type. Add authorizePasswordAuth helper that was present in upstream but missing from gemmaclaw's auth.ts. * fix: remove route assertions incompatible with gemmaclaw SessionEntry Remove test assertions using .route property that exists in upstream's SessionEntry type but not in gemmaclaw's, restoring typecheck green. * fix(memory-core): yield event loop during fallback vector search (openclaw#81172) (openclaw#83758) Summary: - The branch changes memory-core fallback vector search to scan chunks in 256-row rowid batches with `setImmediate` yields, updates regression tests, and adds a changelog entry. - Reproducibility: yes. from source and supplied live output. Current main synchronously scans fallback vector ... and the PR body shows the before/after heartbeat behavior through the actual `searchVector` fallback path. Automerge notes: - PR branch already contained follow-up commit before automerge: test(memory-core): add boundary, parity, and concurrent-insert covera… - PR branch already contained follow-up commit before automerge: fix(memory-core): yield event loop during fallback vector search (#81… Validation: - ClawSweeper review passed for head 0ede3d7. - Required merge gates passed before the squash merge. Prepared head SHA: 0ede3d7 Review: openclaw#83758 (comment) Co-authored-by: NW <nitinwadhawan66@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> * fix(subagents): collect unresolved announce batches (openclaw#83701) Summary: - The PR changes collect-mode follow-up queue routing so unresolved-origin items can batch with a single resolved route and later compatible items can resume batching after a true cross-channel drain. - Reproducibility: yes. at source level: current main treats unkeyed-plus-same-keyed queue items as cross-chan ... failing path is directly visible in `src/utils/queue-helpers.ts` and `src/auto-reply/reply/queue/drain.ts`. Automerge notes: - PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'origin/main' into maint-83701-20260518 Validation: - ClawSweeper review passed for head e6ad029. - Required merge gates passed before the squash merge. Prepared head SHA: e6ad029 Review: openclaw#83701 (comment) Co-authored-by: Andy Ye <35905412+TurboTheTurtle@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> * fix(config): accept gateway remote port * fix: restore Array<{}> closing bracket in manager-search.ts Cherry-pick 68b3729 accidentally dropped the '>' from '}>', producing a syntax error. Restore '}>;' as it was in origin/main. * fix: add remotePort to GatewayRemoteConfig and GatewayRemoteConfigSchema * fix(agents): prioritize manual session turns (openclaw#82765) * fix(agents): prioritize manual session turns * docs: update changelog for session priority --------- Co-authored-by: Galin Iliev <Galin.Iliev@microsoft.com> * revert: fix(agents): prioritize manual session turns (openclaw#82765) - upstream deps not in gemmaclaw * fix: resolve undefined variable errors in cherry-picked extension code * fix(tui): preserve draft while chat is busy * fix(tui): add pendingChatRunId to TuiStateAccess for cherry-picked tui commit * fix(memory-wiki): make wiki_lint tool output path-safe (openclaw#83687) * fix(ui): render session-scoped tool events (openclaw#83734) * chore: regenerate base config schema after upstream cherry-picks * fix(agents): add persistSubagentRunsToDiskOrThrow to subagent-registry test mock New export added to subagent-registry-state.ts was missing from the vi.mock definition, causing all tests in the suite to skip and the module to fail to load. * fix(telegram): wire buildTelegramInboundOriginTarget into session context Cherry-pick 675e053 added the helper and the test assertion but did not update bot-message-context.session.ts to use it. OriginatingTo now correctly includes :topic:<id> for forum groups. * fix(memory): correct session path format in startup-catchup test sessionPathForFile returns sessions/<basename> (no agent dir), but the cherry-picked test used sessions/main/<basename>. The clean-file test always failed because the path mismatch made every file look unindexed. * fix(together): update video generation test URL from v1 to v2 The source uses TOGETHER_VIDEO_BASE_URL = https://api.together.xyz/v2 but the cherry-picked test still asserted the old v1 URL. --------- Co-authored-by: nitinjwadhawan <nitinwadhawan66@gmail.com> Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com> Co-authored-by: takhoffman <781889+takhoffman@users.noreply.github.com> Co-authored-by: Andy Ye <35905412+TurboTheTurtle@users.noreply.github.com> Co-authored-by: Peter Steinberger <steipete@gmail.com> Co-authored-by: Galin Iliev <iliev@galcho.com> Co-authored-by: Galin Iliev <Galin.Iliev@microsoft.com> Co-authored-by: Harry Xie <harryhsieh963@yahoo.com>

Summary: - The PR changes collect-mode follow-up queue routing so unresolved-origin items can batch with a single resolved route and later compatible items can resume batching after a true cross-channel drain. - Reproducibility: yes. at source level: current main treats unkeyed-plus-same-keyed queue items as cross-chan ... failing path is directly visible in `src/utils/queue-helpers.ts` and `src/auto-reply/reply/queue/drain.ts`. Automerge notes: - PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'origin/main' into maint-83701-20260518 Validation: - ClawSweeper review passed for head e6ad029e23873fdac7aaa735d10589b20ac92e55. - Required merge gates passed before the squash merge. Prepared head SHA: e6ad029e23873fdac7aaa735d10589b20ac92e55 Review: openclaw/openclaw#83701 (comment) Co-authored-by: Andy Ye <35905412+TurboTheTurtle@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 changes collect-mode follow-up queue routing so unresolved-origin items can batch with a single resolved route and later compatible items can resume batching after a true cross-channel drain. - Reproducibility: yes. at source level: current main treats unkeyed-plus-same-keyed queue items as cross-chan ... failing path is directly visible in `src/utils/queue-helpers.ts` and `src/auto-reply/reply/queue/drain.ts`. Automerge notes: - PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'origin/main' into maint-83701-20260518 Validation: - ClawSweeper review passed for head e6ad029. - Required merge gates passed before the squash merge. Prepared head SHA: e6ad029 Review: openclaw#83701 (comment) Co-authored-by: Andy Ye <35905412+TurboTheTurtle@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>

fix(subagents): collect unresolved announce batches

b2e70a4

openclaw-barnacle Bot added size: S triage: needs-real-behavior-proof Candidate: external PR needs after-fix proof from a real setup. labels May 18, 2026

Merge remote-tracking branch 'origin/main' into maint-83701-20260518

e6ad029

# Conflicts: # CHANGELOG.md

Takhoffman added proof: override Maintainer override for the external PR real behavior proof gate. proof: sufficient ClawSweeper judged the real behavior proof convincing. labels May 18, 2026

openclaw-barnacle Bot removed proof: supplied External PR includes structured after-fix real behavior proof. proof: sufficient ClawSweeper judged the real behavior proof convincing. labels May 18, 2026

clawsweeper Bot added the clawsweeper:automerge Maintainer opted this PR into bounded ClawSweeper-reviewed automerge label May 18, 2026

clawsweeper Bot added status: 🚀 automerge armed This PR is in ClawSweeper's automerge lane. and removed status: 👀 ready for maintainer look ClawSweeper has no concrete contributor-facing blocker left for this PR. labels May 18, 2026

clawsweeper Bot merged commit 44c6ad7 into openclaw:main May 18, 2026
130 of 135 checks passed

github-actions Bot mentioned this pull request May 18, 2026

📡 Upstream Digest — 2026-05-18 19:27 UTC curtismercier/openclaw-mods#892

Open

TurboTheTurtle deleted the fix/subagent-collect-unresolved-origin-83577 branch May 18, 2026 22:23

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(subagents): collect unresolved announce batches#83701

fix(subagents): collect unresolved announce batches#83701
clawsweeper[bot] merged 2 commits into
openclaw:mainfrom
TurboTheTurtle:fix/subagent-collect-unresolved-origin-83577

TurboTheTurtle commented May 18, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 18, 2026 •

edited

Loading

Uh oh!

TurboTheTurtle commented May 18, 2026

Uh oh!

clawsweeper Bot commented May 18, 2026 •

edited

Loading

Uh oh!

Takhoffman commented May 18, 2026

Uh oh!

clawsweeper Bot commented May 18, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

Uh oh!

Conversation

TurboTheTurtle commented May 18, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

Root cause

Real behavior proof

Attribution

Uh oh!

clawsweeper Bot commented May 18, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

TurboTheTurtle commented May 18, 2026

Uh oh!

clawsweeper Bot commented May 18, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Takhoffman commented May 18, 2026

Uh oh!

clawsweeper Bot commented May 18, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

TurboTheTurtle commented May 18, 2026 •

edited

Loading

clawsweeper Bot commented May 18, 2026 •

edited

Loading

clawsweeper Bot commented May 18, 2026 •

edited

Loading

clawsweeper Bot commented May 18, 2026 •

edited

Loading