fix(codex): preserve source reply mode for active runs by clawsweeper[bot] · Pull Request #86325 · openclaw/openclaw

clawsweeper · 2026-05-25T04:29:25Z

Makes #86287 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.
Known failing checks:

Failing check: check-dependencies:FAILURE (https://github.com/openclaw/openclaw/actions/runs/26379882434/job/77646999725)

ClawSweeper 🐠 replacement reef notes:

Cluster: automerge-openclaw-openclaw-86287
Source PRs: fix(codex): preserve source reply mode for active runs #86287
Credit: Source PR: fix(codex): preserve source reply mode for active runs #86287
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

Inherited issue-closing references from the source PR:
Fixes #86232

Co-author credit kept:

@ferminquant: Co-authored-by: Fermin Quant [email protected]

fish notes: model gpt-5.5, reasoning high; reviewed against e7fdf7b.

clawsweeper · 2026-05-25T04:31:09Z

Codex review: passed. Reviewed May 25, 2026, 1:56 AM ET / 05:56 UTC.

Summary
This PR forwards Codex app-server source reply delivery mode into active run handling, adds a focused regression test, and adds a changelog entry.

PR surface: Source +1, Tests +38, Docs +1. Total +40 across 3 files.

Reproducibility: yes. Source inspection shows the shared active-run queue rejects message_tool_only replies when the active handle lacks that mode, and current main's Codex app-server handle omits it.

Review metrics: 1 noteworthy metric.

Changed surfaces: 3 files: 1 runtime field, 1 regression test, 1 changelog entry. The small surface makes the active-run contract change easy to audit before merge.

Merge readiness
Overall: 🦞 diamond lobster
Proof: 🦞 diamond lobster
Patch quality: 🦞 diamond lobster
Result: ready for maintainer review.

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

Next step before merge
No repair lane is needed because the diff has no actionable findings; exact-head checks and mergeability can gate the armed automerge path.

Security
Cleared: The diff only propagates an existing run-scoped delivery-mode value, adds a regression test, and updates the changelog; I found no concrete security or supply-chain concern.

Review details

Best possible solution:

Land the narrow active-handle contract fix once exact-head checks and mergeability are green.

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

Yes. Source inspection shows the shared active-run queue rejects message_tool_only replies when the active handle lacks that mode, and current main's Codex app-server handle omits it.

Is this the best way to solve the issue?

Yes. The PR carries an already-prepared delivery-mode fact into the registered handle, matching the sibling PI embedded runner without widening fallback behavior.

AGENTS.md: found and applied where relevant.

Codex review notes: model gpt-5.5, reasoning high; reviewed against 3dd0e8ed6a7c.

Label changes

Label justifications:

P1: The linked issue affects sub-agent completion wakeups and message delivery in active Codex channel runs.
rating: 🦞 diamond lobster: Overall readiness is 🦞 diamond lobster; proof is 🦞 diamond lobster and patch quality is 🦞 diamond lobster.
status: 🚀 automerge armed: This PR is in ClawSweeper's automerge lane. Sufficient (live_output): The linked source PR includes after-fix source-runtime proof showing mismatched mode is rejected and matched message_tool_only mode queues turn/steer through the implicated guard.
proof: sufficient: Contributor real behavior proof is sufficient. The linked source PR includes after-fix source-runtime proof showing mismatched mode is rejected and matched message_tool_only mode queues turn/steer through the implicated guard.

Evidence reviewed

PR surface:

Source +1, Tests +38, Docs +1. Total +40 across 3 files.

View PR surface stats

Area	Files	Added	Net
Source	1	1	+1
Tests	1	38	+38
Docs	1	1	+1
Config	0	0	0
Generated	0	0	0
Other	0	0	0
Total	3	40	+40

What I checked:

Current-main behavior: Current main registers the Codex app-server active handle without sourceReplyDeliveryMode, so message-tool-only source replies can fail the shared active-run guard. (extensions/codex/src/app-server/run-attempt.ts:2926, 3dd0e8ed6a7c)
Patch source: The PR branch adds sourceReplyDeliveryMode: params.sourceReplyDeliveryMode to the registered Codex app-server active handle. (extensions/codex/src/app-server/run-attempt.ts:2932, d8fac59d8fc9)
Shared contract: The shared active-run queue rejects message_tool_only replies unless the handle also advertises message_tool_only, which is the contract this PR satisfies. (src/agents/pi-embedded-runner/runs.ts:253, d8fac59d8fc9)
Sibling surface: The PI embedded runner already carries sourceReplyDeliveryMode into its active embedded handle, so the PR aligns the Codex app-server path with the sibling runner. (src/agents/pi-embedded-runner/run/attempt.ts:3380, 3dd0e8ed6a7c)
Regression coverage: The new test starts a Codex app-server run with message_tool_only, queues a matching source reply, and asserts a turn/steer request is emitted. (extensions/codex/src/app-server/run-attempt.test.ts:7887, d8fac59d8fc9)
Changelog: The PR records the Codex/app-server fix under Unreleased fixes. (CHANGELOG.md:19, d8fac59d8fc9)

Likely related people:

Vincent Koc: Local blame attributes the current active-run handle and shared queue guard lines to the grafted current-main commit; the shallow history makes this a low-confidence routing hint. (role: line-history contributor; confidence: low; commits: 8ae997749d3a; files: extensions/codex/src/app-server/run-attempt.ts, src/agents/pi-embedded-runner/runs.ts)
Val Alexander: Recent history shows adjacent Codex app-server runtime and test work in the same files. (role: recent area contributor; confidence: medium; commits: 119a01c82998; files: extensions/codex/src/app-server/run-attempt.ts, extensions/codex/src/app-server/run-attempt.test.ts)
pashpashpash: Recent history shows Codex app-server boundary work touching the same runtime file. (role: recent adjacent contributor; confidence: medium; commits: dd47e479aedb; files: extensions/codex/src/app-server/run-attempt.ts)

What the crustacean ranks mean

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

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

How this review workflow works

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

clawsweeper · 2026-05-25T04:44:55Z

ClawSweeper PR egg

✨ Hatched: 🥚 common Neon Merge Sprite

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 diff observatory; accessory tiny test log scroll; palette seafoam, black, and opal; mood mischievous; pose waving from a small platform; shell starlit enamel shell; lighting gentle morning glow; background little resolved-comment flags.
Share on X: post this hatch
Copy: My PR egg hatched a 🥚 common Neon Merge Sprite 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 · 2026-05-25T04:45:11Z

🦞✅
ClawSweeper merged this PR after the passing review.

Source: clawsweeper[bot]
Feedback: structured ClawSweeper verdict: pass (sha=d8fac59d8fc930de20257fbfab184c73b80e5a65)
Merge status: merged by ClawSweeper automerge
Merged at: 2026-05-25T06:00:48Z
Merge commit: b96211063755

What merged:

This PR forwards Codex app-server source reply delivery mode into active run handling, adds a focused regression test, and adds a changelog entry.
PR surface: Source +1, Tests +38, Docs +1. Total +40 across 3 files.
Reproducibility: yes. Source inspection shows the shared active-run queue rejects message_tool_only replies when the active handle lacks that mode, and current main's Codex app-server handle omits it.

Automerge notes:

PR branch already contained follow-up commit before automerge: fix(codex): preserve source reply mode for active runs

The automerge loop is complete.

Automerge progress:

2026-05-25 05:22:45 UTC repair completed a127ddd75bc9 (branch updated) in 35m 5s Run: https://github.com/openclaw/clawsweeper/actions/runs/26383671493 initial automerge rebase is delegated to Codex repair

2026-05-25 05:22:45 UTC review queued a127ddd75bc9 (after repair)

2026-05-25 05:22:47 UTC automerge wait a127ddd75bc9 (waiting) in 35m 6s Run: https://github.com/openclaw/clawsweeper/actions/runs/26383671493 up to 600s

2026-05-25 05:32:53 UTC review passed a127ddd75bc9 (structured ClawSweeper verdict: pass (sha=a127ddd75bc9ba5b381bc4e48134a6e2f0138...)

2026-05-25 05:33:11 UTC repair queued a127ddd75bc9 (autonomous) Run: https://github.com/openclaw/clawsweeper/actions/runs/26385061588

2026-05-25 05:36:41 UTC repair started (running) in 0s Run: https://github.com/openclaw/clawsweeper/actions/runs/26385061588 automerge-openclaw-openclaw-86287

2026-05-25 05:36:56 UTC validation plan (passed) in 16s Run: https://github.com/openclaw/clawsweeper/actions/runs/26385061588 node scripts/run-vitest.mjs extensions/codex/src/app-server/run-attempt.test.ts; pnpm check:changed; pnpm lint; pnpm check:test-types

2026-05-25 05:37:09 UTC Codex write preflight (passed) in 28s Run: https://github.com/openclaw/clawsweeper/actions/runs/26385061588 danger-full-access

2026-05-25 05:42:17 UTC Codex edit 1 3e2e57919050 (complete) in 5m 37s Run: https://github.com/openclaw/clawsweeper/actions/runs/26385061588 exit 0

2026-05-25 05:50:57 UTC validation and review 1 d8fac59d8fc9 (base moved) in 14m 16s Run: https://github.com/openclaw/clawsweeper/actions/runs/26385061588 rebased

2026-05-25 05:51:01 UTC repair completed d8fac59d8fc9 (branch updated) in 14m 21s Run: https://github.com/openclaw/clawsweeper/actions/runs/26385061588 initial automerge rebase is delegated to Codex repair

2026-05-25 05:51:01 UTC review queued d8fac59d8fc9 (after repair)

2026-05-25 06:00:38 UTC automerge wait d8fac59d8fc9 (ready) in 23m 58s Run: https://github.com/openclaw/clawsweeper/actions/runs/26385061588 checks and exact-head review are ready

2026-05-25 06:00:39 UTC repair finished d8fac59d8fc9 (pushed) in 23m 59s Run: https://github.com/openclaw/clawsweeper/actions/runs/26385061588 repair_contributor_branch

2026-05-25 06:00:36 UTC review passed d8fac59d8fc9 (structured ClawSweeper verdict: pass (sha=d8fac59d8fc930de20257fbfab184c73b80e5...)

2026-05-25 06:00:50 UTC merged d8fac59d8fc9 (merged by ClawSweeper automerge)

Co-authored-by: Fermin Quant <[email protected]> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>

Summary: - This PR forwards Codex app-server source reply delivery mode into active run handling, adds a focused regression test, and adds a changelog entry. - PR surface: Source +1, Tests +38, Docs +1. Total +40 across 3 files. - Reproducibility: yes. Source inspection shows the shared active-run queue rejects `message_tool_only` replies when the active handle lacks that mode, and current main's Codex app-server handle omits it. Automerge notes: - PR branch already contained follow-up commit before automerge: fix(codex): preserve source reply mode for active runs Validation: - ClawSweeper review passed for head d8fac59. - Required merge gates passed before the squash merge. Prepared head SHA: d8fac59 Review: openclaw#86325 (comment) Co-authored-by: Fermin Quant <[email protected]> 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 <[email protected]>

clawsweeper Bot mentioned this pull request May 25, 2026

fix(codex): preserve source reply mode for active runs #86287

Closed

openclaw-barnacle Bot removed the proof: supplied External PR includes structured after-fix real behavior proof. label May 25, 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 25, 2026

clawsweeper Bot force-pushed the clawsweeper/automerge-openclaw-openclaw-86287 branch from e7fdf7b to a127ddd Compare May 25, 2026 05:22

ferminquant and others added 2 commits May 25, 2026 05:50

fix(codex): preserve source reply mode for active runs

22b4eec

fix(codex): preserve source reply mode for active runs

d8fac59

Co-authored-by: Fermin Quant <[email protected]> Co-authored-by: clawsweeper[bot] <274271284+clawsweeper[bot]@users.noreply.github.com>

clawsweeper Bot force-pushed the clawsweeper/automerge-openclaw-openclaw-86287 branch from a127ddd to d8fac59 Compare May 25, 2026 05:51

clawsweeper Bot merged commit b962110 into main May 25, 2026
91 checks passed

clawsweeper Bot deleted the clawsweeper/automerge-openclaw-openclaw-86287 branch May 25, 2026 06:00

github-actions Bot mentioned this pull request May 25, 2026

📡 Upstream Digest — 2026-05-25 08:12 UTC curtismercier/openclaw-mods#942

Open

clawsweeper Bot mentioned this pull request Jun 15, 2026

fix(codex): preserve telegram foreground run release #87613

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix(codex): preserve source reply mode for active runs#86325

fix(codex): preserve source reply mode for active runs#86325
clawsweeper[bot] merged 2 commits into
mainfrom
clawsweeper/automerge-openclaw-openclaw-86287

clawsweeper Bot commented May 25, 2026

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented May 25, 2026

Uh oh!

clawsweeper Bot commented May 25, 2026 •

edited

Loading

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

Uh oh!

Uh oh!

Conversation

clawsweeper Bot commented May 25, 2026

Uh oh!

clawsweeper Bot commented May 25, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented May 25, 2026

Hatch command

Uh oh!

clawsweeper Bot commented May 25, 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 25, 2026 •

edited

Loading

clawsweeper Bot commented May 25, 2026 •

edited

Loading