fix(agents): preserve accepted spawn terminal success by clawsweeper[bot] · Pull Request #85135 · openclaw/openclaw

clawsweeper · 2026-05-22T00:21:52Z

Makes #85054 merge-ready for the ClawSweeper automerge loop.
The edit pass should inspect the live PR diff, review comments, and failing checks; rebase if needed; keep the contributor branch credited; and stop only when validation is green or an external blocker is proven.

ClawSweeper 🐠 replacement reef notes:

Cluster: automerge-openclaw-openclaw-85054
Source PRs: fix(agents): preserve accepted spawn terminal success #85054
Credit: Source PR: fix(agents): preserve accepted spawn terminal success #85054
Validation: pnpm check:changed
Replacement reason: ClawSweeper could not update the source PR branch directly, so it opened a writable replacement PR instead.
Automerge requested by: @Takhoffman

Repair fallback: GitHub rejected the repair branch push because it updates workflow files and the ClawSweeper app token does not have workflows permission

Inherited issue-closing references from the source PR:
Fixes #72541

Co-author credit kept:

@samzong: Co-authored-by: samzong 13782141+samzong@users.noreply.github.com

fish notes: model gpt-5.5, reasoning high; reviewed against c1b3c30.

clawsweeper · 2026-05-22T00:23:25Z

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 adds accepted sessions_spawn tracking through embedded Pi subscribe, runner, fallback, replay, lifecycle, tests, deadcode allowlist, and changelog surfaces.

Reproducibility: yes. at source level. Current main documents accepted sessions_spawn results but the pre-PR runner and classifier paths do not carry that accepted child-run fact into incomplete-turn or fallback decisions.

PR rating
Overall: 🦞 diamond lobster
Proof: 🦞 diamond lobster
Patch quality: 🦞 diamond lobster
Summary: Strong real-behavior proof, focused implementation, and broad regression coverage make this above-average merge signal with no blocking findings.

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 (live_output): The source PR body includes after-fix QA Lab commands and copied terminal output showing the accepted child-session path no longer produces the false incomplete-turn error or duplicate spawn.

Risk before merge

The real-behavior proof covers QA-channel with mock-openai; live provider credentials and Discord thread-bound behavior were not exercised, but those are outside the changed classifier surface.

Maintainer options:

Decide the mitigation before merge
Land the narrow structured accepted-spawn evidence fix after exact-head required checks pass, preserving existing failed-spawn, malformed-spawn, and timeout behavior.
Pause or close
Do not merge this PR until maintainers decide whether the risk is worth taking.

Next step before merge
No repair lane is needed; keep this PR open for automerge or maintainer merge after exact-head required checks complete.

Security
Cleared: The diff adds internal runtime state, focused tests, a changelog entry, and a deadcode allowlist update without new dependencies, workflows, permissions, secrets handling, or external code execution.

Review details

Best possible solution:

Land the narrow structured accepted-spawn evidence fix after exact-head required checks pass, preserving existing failed-spawn, malformed-spawn, and timeout behavior.

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

Yes, at source level. Current main documents accepted sessions_spawn results but the pre-PR runner and classifier paths do not carry that accepted child-run fact into incomplete-turn or fallback decisions.

Is this the best way to solve the issue?

Yes. Carrying a structured accepted-spawn fact is narrower than a broad successful-tool exemption or new config flag, and the patch keeps malformed/error spawns and prompt timeout paths distinct.

Label justifications:

P2: This is a normal-priority agent runtime bug fix with limited blast radius, focused coverage, and supplied real-behavior proof.
rating: 🦞 diamond lobster: Current PR rating is 🦞 diamond lobster because proof is 🦞 diamond lobster, patch quality is 🦞 diamond lobster, and Strong real-behavior proof, focused implementation, and broad regression coverage make this above-average merge signal with no blocking findings.
status: 🚀 automerge armed: This PR is in ClawSweeper's automerge lane. Sufficient (live_output): The source PR body includes after-fix QA Lab commands and copied terminal output showing the accepted child-session path no longer produces the false incomplete-turn error or duplicate spawn.
proof: sufficient: Contributor real behavior proof is sufficient. The source PR body includes after-fix QA Lab commands and copied terminal output showing the accepted child-session path no longer produces the false incomplete-turn error or duplicate spawn.

What I checked:

Current main drops accepted-spawn evidence: Current main's incomplete-turn replay metadata only treats mutating tools, messaging delivery, and cron adds as side effects, so an accepted sessions_spawn result is not a structured completion signal before this PR. (src/agents/pi-embedded-runner/run/incomplete-turn.ts:204, 1f9ebb9dda36)
Documented sessions_spawn contract: The subagents docs state that sessions_spawn is non-blocking and returns { status: "accepted", runId, childSessionKey }, matching the PR's narrow success predicate. Public docs: docs/tools/subagents.md. (docs/tools/subagents.md:640, 1f9ebb9dda36)
PR records accepted spawn facts: The patch records only successful non-error sessions_spawn results whose sanitized details normalize to accepted run and child-session identifiers, then marks replay state as side-effectful. (src/agents/pi-embedded-subscribe.handlers.tools.ts:948, 0f6d92b8cd7b)
PR suppresses the false incomplete-turn path: The new accepted-spawn helper is used by incomplete-turn, trajectory, idle-breaker, replay, and fallback classifiers, while timeout and malformed-spawn paths remain covered separately. (src/agents/pi-embedded-runner/run/incomplete-turn.ts:258, 0f6d92b8cd7b)
Regression coverage added: The PR adds focused tests for accepted spawn suppressing retries/warnings, malformed spawns staying ignored, timeout still surfacing, fallback classification, trajectory success, lifecycle state, and compaction retry preservation. (src/agents/pi-embedded-runner/run.incomplete-turn.test.ts:1430, 0f6d92b8cd7b)
Real behavior proof supplied: The source PR body includes after-fix QA Lab commands and copied live output showing runtime-tool-sessions-spawn and subagent-handoff passed through QA-channel with a real gateway child and mock-openai.

Likely related people:

Peter Steinberger: History shows the non-blocking sessions_spawn behavior and several embedded runner/replay/subagent lifecycle changes in the same surface. (role: original sessions_spawn and adjacent runner contributor; confidence: high; commits: 77024cf77619, 761b71e268a7, c1467389967e; files: src/agents/tools/sessions-spawn-tool.ts, src/agents/pi-embedded-runner/run.ts, docs/tools/subagents.md)
Sarah Fortune: Current-main blame for the incomplete-turn and tool-handler regions points to recent work that reshaped replay metadata and tool result handling. (role: recent area contributor; confidence: medium; commits: 7ddcca6c77fd; files: src/agents/pi-embedded-runner/run/incomplete-turn.ts, src/agents/pi-embedded-subscribe.handlers.tools.ts)
Eva: Recent replay/liveness commits carried the state model that this PR extends for accepted child-session handoffs. (role: replay and liveness contributor; confidence: medium; commits: aa5bec4bdf40, 6b100ca559b1, 7f54cf73e259; files: src/agents/pi-embedded-runner/run/incomplete-turn.ts, src/agents/pi-embedded-subscribe.handlers.lifecycle.ts, src/agents/pi-embedded-subscribe.ts)
samzong: Beyond authoring the source PR, prior merged work touched adjacent subagent and compaction behavior, so they have relevant context for this fix. (role: source contributor with prior adjacent history; confidence: low; commits: 09bb93c6e046, 5c05347d119e; files: src/agents, src/agents/pi-embedded-runner)

Codex review notes: model gpt-5.5, reasoning high; reviewed against 1f9ebb9dda36.

clawsweeper · 2026-05-22T00:29:18Z

ClawSweeper PR egg

✨ Hatched: 🥚 common Frosted Shellbean

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: collects tiny proofs.
Image traits: location release reef; accessory green check lantern; palette seafoam, black, and opal; mood determined; pose waving from a small platform; shell brushed metal shell; lighting gentle morning glow; background quiet workflow signs.
Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Frosted Shellbean 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.

clawsweeper · 2026-05-22T00:29:36Z

🦞🧹
ClawSweeper automerge is enabled.

Head: 0f6d92b8cd7b
Label: clawsweeper:automerge
Action: exact-head review queued (workflow sweep.yml, event repository_dispatch).
Flow: review this head, repair/rebase only if needed, then re-review the exact repaired head before merge.

Draft PRs stay fix-only until GitHub marks them ready for review. Pause with /clawsweeper stop.

Automerge progress:

2026-05-22 00:29:17 UTC review passed c1b3c308db01 (structured ClawSweeper verdict: pass (sha=c1b3c308db0143836c06348b87461c12becd7...)

2026-05-22 00:29:36 UTC repair queued c1b3c308db01 (autonomous) Run: https://github.com/openclaw/clawsweeper/actions/runs/26261220426

2026-05-22 00:33:42 UTC repair started (running) in 0s Run: https://github.com/openclaw/clawsweeper/actions/runs/26261220426 automerge-openclaw-openclaw-85054

2026-05-22 00:33:56 UTC validation plan (passed) in 14s Run: https://github.com/openclaw/clawsweeper/actions/runs/26261220426 node scripts/run-vitest.mjs src/agents/pi-embedded-runner/run.incomplete-turn.test.ts src/agents/pi-embedded-runner/result-fallback-classifier.test.ts src/agen...

2026-05-22 00:34:10 UTC Codex write preflight (passed) in 28s Run: https://github.com/openclaw/clawsweeper/actions/runs/26261220426 danger-full-access

2026-05-22 00:39:06 UTC Codex edit 1 3c160c20e66b (complete) in 5m 25s Run: https://github.com/openclaw/clawsweeper/actions/runs/26261220426 exit 0

2026-05-22 00:44:46 UTC validation and review 1 0f6d92b8cd7b (base moved) in 11m 4s Run: https://github.com/openclaw/clawsweeper/actions/runs/26261220426 rebased

2026-05-22 00:44:50 UTC repair completed 0f6d92b8cd7b (branch updated) in 11m 9s Run: https://github.com/openclaw/clawsweeper/actions/runs/26261220426 initial automerge rebase is delegated to Codex repair

2026-05-22 00:44:50 UTC review queued 0f6d92b8cd7b (after repair)

2026-05-22 00:54:53 UTC automerge wait 0f6d92b8cd7b (waiting) in 21m 11s Run: https://github.com/openclaw/clawsweeper/actions/runs/26261220426 waiting for GitHub checks: Scan changed paths (precise):IN_PROGRESS

2026-05-22 00:54:54 UTC repair finished 0f6d92b8cd7b (pushed) in 21m 12s Run: https://github.com/openclaw/clawsweeper/actions/runs/26261220426 repair_contributor_branch

2026-05-22 00:51:39 UTC review passed 0f6d92b8cd7b (structured ClawSweeper verdict: pass (sha=0f6d92b8cd7bb07da58941ef3ed390d219fcc...)

2026-05-22 01:16:44 UTC merged 0f6d92b8cd7b (merged by ClawSweeper automerge)

2026-05-22 01:16:53 UTC review queued 0f6d92b8cd7b (queued)

Signed-off-by: samzong <samzong.lu@gmail.com>

Summary: - The branch adds accepted `sessions_spawn` tracking through embedded Pi subscribe, runner, fallback, replay, lifecycle, tests, deadcode allowlist, and changelog surfaces. - Reproducibility: yes. at source level. Current main documents accepted `sessions_spawn` results but the pre- ... and classifier paths do not carry that accepted child-run fact into incomplete-turn or fallback decisions. Automerge notes: - PR branch already contained follow-up commit before automerge: test(qa-lab): allow codex fixtures in deadcode - PR branch already contained follow-up commit before automerge: fix(agents): preserve accepted spawn terminal success Validation: - ClawSweeper review passed for head 0f6d92b. - Required merge gates passed before the squash merge. Prepared head SHA: 0f6d92b Review: openclaw#85135 (comment) Co-authored-by: samzong <samzong.lu@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>

clawsweeper Bot mentioned this pull request May 22, 2026

fix(agents): preserve accepted spawn terminal success #85054

Closed

25 tasks

openclaw-barnacle Bot removed the proof: supplied External PR includes structured after-fix real behavior proof. label May 22, 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 22, 2026

samzong and others added 4 commits May 22, 2026 00:44

fix(agents): preserve accepted spawn terminal success

5e084b3

Signed-off-by: samzong <samzong.lu@gmail.com>

test(qa-lab): allow codex fixtures in deadcode

32e100e

fix(agents): preserve accepted spawn terminal success

2c045f7

fix(agents): preserve accepted spawn terminal success

0f6d92b

clawsweeper Bot force-pushed the clawsweeper/automerge-openclaw-openclaw-85054 branch from c1b3c30 to 0f6d92b Compare May 22, 2026 00:44

clawsweeper Bot merged commit 7f4bd45 into main May 22, 2026
98 checks passed

clawsweeper Bot deleted the clawsweeper/automerge-openclaw-openclaw-85054 branch May 22, 2026 01:16

Haderach-Ram mentioned this pull request May 22, 2026

Ecosystem Digest — 2026-05-22 Haderach-Ram/openclaw-radar#15

Open

github-actions Bot mentioned this pull request May 22, 2026

📡 Upstream Digest — 2026-05-22 02:37 UTC curtismercier/openclaw-mods#913

Open

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

fix(agents): preserve accepted spawn terminal success#85135

fix(agents): preserve accepted spawn terminal success#85135
clawsweeper[bot] merged 4 commits into
mainfrom
clawsweeper/automerge-openclaw-openclaw-85054

clawsweeper Bot commented May 22, 2026

Uh oh!

clawsweeper Bot commented May 22, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 22, 2026

Uh oh!

clawsweeper Bot commented May 22, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Conversation

clawsweeper Bot commented May 22, 2026

Uh oh!

clawsweeper Bot commented May 22, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 22, 2026

Hatch command

Uh oh!

clawsweeper Bot commented May 22, 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!

1 participant

clawsweeper Bot commented May 22, 2026 •

edited

Loading

clawsweeper Bot commented May 22, 2026 •

edited

Loading