Skip to content

fix (Computer Use) Stabilize Codex Computer Use readiness#103331

Merged
Takhoffman merged 7 commits into
mainfrom
clawsweeper/automerge-openclaw-openclaw-102264
Jul 11, 2026
Merged

fix (Computer Use) Stabilize Codex Computer Use readiness#103331
Takhoffman merged 7 commits into
mainfrom
clawsweeper/automerge-openclaw-openclaw-102264

Conversation

@clawsweeper

@clawsweeper clawsweeper Bot commented Jul 10, 2026

Copy link
Copy Markdown
Contributor

Makes #102264 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.

Source

Replacement for #102264 because the source branch could not be updated.

Original contributor: @bdjben.

@clawsweeper clawsweeper Bot added docs Improvements or additions to documentation commands Command implementations extensions: codex clawsweeper:automerge Maintainer opted this PR into bounded ClawSweeper-reviewed automerge clawsweeper Tracked by ClawSweeper automation labels Jul 10, 2026
@clawsweeper clawsweeper Bot mentioned this pull request Jul 10, 2026
Closed
@clawsweeper

clawsweeper Bot commented Jul 10, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor Author

🦞🔧
ClawSweeper applied a repair to this PR branch.

Repair: kept the fix on this contributor branch instead of opening a replacement PR.
Validation: pnpm check:changed; pnpm lint; pnpm check:test-types
Updated head: 6f2ea1aba973
Run: https://github.com/openclaw/clawsweeper/actions/runs/29155769850

Current state: exact-head review queued immediately; GitHub checks and the review verdict gate final merge.

Automerge progress:

  • 2026-07-11 14:01:55 UTC review queued 8f59f074990b (after repair)
  • 2026-07-11 14:10:19 UTC review requested repair 8f59f074990b (structured ClawSweeper needs-human verdict with repairable P-severity findings...)
  • 2026-07-11 14:40:30 UTC review queued 8f59f074990b (queued)
  • 2026-07-11 14:39:49 UTC review queued 8f59f074990b (queued)
  • 2026-07-11 14:42:14 UTC review queued 6f2ea1aba973 (after repair)

Re-review progress:

@Takhoffman

Takhoffman commented Jul 10, 2026

Copy link
Copy Markdown
Contributor

@clawsweeper automerge

@clawsweeper clawsweeper Bot added proof: sufficient ClawSweeper judged the real behavior proof convincing. rating: 🦪 silver shellfish Thin PR readiness signal; proof, validation, or implementation needs work. status: 🚀 automerge armed This PR is in ClawSweeper's automerge lane. P1 High-priority user-facing bug, regression, or broken workflow. merge-risk: 🚨 compatibility 🚨 May break existing users, config, migrations, defaults, or upgrade paths. merge-risk: 🚨 security-boundary 🚨 May affect sandboxing, authorization, credentials, or sensitive data. labels Jul 10, 2026
@clawsweeper

clawsweeper Bot commented Jul 10, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor Author

Codex review: needs changes before merge. Reviewed July 11, 2026, 10:08 AM ET / 14:08 UTC.

Summary
Adds opt-in shared Computer Use cache reconciliation, layered installation/exposure/live readiness checks, periodic health monitoring and scoped repair controls, seven configuration fields, richer diagnostics, documentation, and regression tests for the Codex plugin.

PR surface: Source +1152, Tests +1114, Docs +25. Total +2291 across 23 files.

Reproducibility: yes. source inspection gives a high-confidence interleaving: cache reconciliation runs before shared-client coordination and deletes all non-current versions, so another same-home startup or active runtime can retain a reference to files that are then removed. A deterministic regression test has not yet been added or run.

Review metrics: 1 noteworthy metric.

  • Computer Use config surfaces: 7 added, 0 changed, 0 removed. New timeout, health, cache, strictness, and repair settings expand upgrade and operator behavior and require exact-head compatibility proof.

Stored data model
Persistent data-model change detected: migration/backfill/repair: src/commands/doctor/shared/codex-route-warnings.test.ts, migration/backfill/repair: src/commands/doctor/shared/codex-route-warnings.ts, persistent cache schema: docs/docs_map.md, persistent cache schema: extensions/codex/src/app-server/auth-bridge.ts, persistent cache schema: extensions/codex/src/app-server/computer-use-cache.test.ts, persistent cache schema: extensions/codex/src/app-server/computer-use-cache.ts, and 3 more. Confirm migration or upgrade compatibility proof before merge.

Root-cause cluster
Relationship: canonical
Canonical: #103331
Summary: This PR is the active replacement and landing candidate for the closed original contribution.

Members:

Proposal only: this assessment does not dispatch repair, suppress jobs, mutate sibling items, close, or merge anything.

Merge readiness
Overall: 🦐 gold shrimp
Proof: 🦐 gold shrimp
Patch quality: 🦐 gold shrimp
Result: blocked until stronger real behavior proof is added.

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

Rank-up moves:

  • [P1] Coordinate cache lifetimes and add a deterministic concurrent startup or active-client regression.
  • Post redacted macOS readiness output or a linked artifact from the repaired exact head.

Proof guidance:

  • [P1] Needs stronger real behavior proof before merge: The source contribution documents a real macOS ChatGPT.app readiness run, but the final head lacks inspected after-fix proof for the unresolved cache-lifetime behavior; after repair, post redacted exact-head live output or a linked artifact and update the PR body to trigger re-review, or ask a maintainer to comment @clawsweeper re-review.

Risk before merge

  • [P1] Merging shared-cache pruning as written can remove plugin files while another same-home startup or active Codex runtime still depends on that cached version.
  • [P1] The PR adds seven operator-facing settings and changes readiness/startup semantics; conservative defaults reduce blast radius, but fresh-install and upgrade behavior should be re-proven on the repaired exact head.

Maintainer options:

  1. Repair cache lifetime coordination (recommended)
    Serialize same-home reconciliation and defer stale-version pruning until no startup or active client can reference the old version.
  2. Remove stale-version pruning for now
    Land the layered readiness improvements while retaining old cache versions until a lifecycle-owned pruning contract is implemented.
Copy recommended automerge instruction 
@clawsweeper automerge

Special instructions:
Coordinate shared-cache version lifetimes per Codex home, add a deterministic concurrent startup/active-client regression, then rerun exact-head checks and redacted macOS proof.

Next step before merge

  • [P2] The remaining blocker is a concrete cache-lifecycle defect with a bounded implementation and deterministic regression path, suitable for the already armed repair loop.

Security
Cleared: The final diff uses current upstream Codex request methods, keeps the readiness probe on a trusted internal path, and limits optional macOS child termination to matching descendants of the owned app-server PID.

Review findings

  • [P1] Protect active clients before pruning stale cache versions — extensions/codex/src/app-server/computer-use-cache.ts:79
Review details

Best possible solution:

Make cache version ownership lifecycle-aware per Codex home: atomically promote the new version, retain old versions while any startup or active client may reference them, prune only after the final owner releases, and prove the invariant with deterministic concurrency coverage plus refreshed exact-head macOS readiness output.

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

Yes, source inspection gives a high-confidence interleaving: cache reconciliation runs before shared-client coordination and deletes all non-current versions, so another same-home startup or active runtime can retain a reference to files that are then removed. A deterministic regression test has not yet been added or run.

Is this the best way to solve the issue?

No, not yet. Layered live readiness and opt-in shared cache management are appropriate, but immediate stale-version pruning is not the safest implementation; version lifetime must be owned by the client lifecycle or pruning must be deferred.

Full review comments:

  • [P1] Protect active clients before pruning stale cache versions — extensions/codex/src/app-server/computer-use-cache.ts:79
    removeStalePluginCacheVersions() deletes every non-current version immediately after promotion, but reconciliation runs before shared-client acquisition coordination. A concurrent same-home startup or already-active client can therefore still be loading or using the old version when its directory is removed. This code is unchanged since the prior review raised the blocker; coordinate version lifetimes per Codex home or defer pruning, and add a concurrent-start/active-client regression.
    Confidence: 0.96

Overall correctness: patch is incorrect
Overall confidence: 0.96

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against f73c5541fe56.

Label changes

Label changes:

  • add merge-risk: 🚨 availability: Immediate stale-version deletion can make a concurrent or active Codex runtime lose the plugin files it needs.
  • add rating: 🦐 gold shrimp: Overall readiness is 🦐 gold shrimp; proof is 🦐 gold shrimp and patch quality is 🦐 gold shrimp.
  • remove rating: 🐚 platinum hermit: Current PR rating is rating: 🦐 gold shrimp, so this older rating label is no longer current.

Label justifications:

  • P1: The shared-cache race can break a real Codex Computer Use startup or active agent workflow when shared mode is enabled.
  • merge-risk: 🚨 compatibility: Seven new settings and changed readiness/startup semantics create upgrade and operator behavior that green CI alone does not settle.
  • merge-risk: 🚨 availability: Immediate stale-version deletion can make a concurrent or active Codex runtime lose the plugin files it needs.
  • rating: 🦐 gold shrimp: Overall readiness is 🦐 gold shrimp; proof is 🦐 gold shrimp and patch quality is 🦐 gold shrimp.
  • status: 🚀 automerge armed: This PR is in ClawSweeper's automerge lane. Needs stronger real behavior proof before merge: The source contribution documents a real macOS ChatGPT.app readiness run, but the final head lacks inspected after-fix proof for the unresolved cache-lifetime behavior; after repair, post redacted exact-head live output or a linked artifact and update the PR body to trigger re-review, or ask a maintainer to comment @clawsweeper re-review.
Evidence reviewed

PR surface:

Source +1152, Tests +1114, Docs +25. Total +2291 across 23 files.

View PR surface stats
Area Files Added Removed Net
Source 14 1196 44 +1152
Tests 7 1222 108 +1114
Docs 2 25 0 +25
Config 0 0 0 0
Generated 0 0 0 0
Other 0 0 0 0
Total 23 2443 152 +2291

Acceptance criteria:

  • [P1] pnpm test extensions/codex/src/app-server/computer-use-cache.test.ts.
  • [P1] pnpm test extensions/codex/src/app-server/computer-use.test.ts.
  • [P1] pnpm test extensions/codex/src/app-server/computer-use-health.test.ts.
  • [P1] pnpm check:changed -- extensions/codex/src/app-server/computer-use-cache.ts extensions/codex/src/app-server/computer-use-cache.test.ts extensions/codex/src/app-server/shared-client.ts.

What I checked:

  • Blocking cache behavior: After ensuring the current version exists, shared mode immediately calls stale-version removal, which recursively deletes every version directory except the newly selected version. (extensions/codex/src/app-server/computer-use-cache.ts:79, 8f59f074990b)
  • Lifecycle gap: Client start-context resolution, including cache reconciliation through the auth bridge, completes before the shared-client key, entry, and pending-acquire coordination are obtained; that coordination therefore cannot protect cache version lifetimes. (extensions/codex/src/app-server/shared-client.ts:178, 8f59f074990b)
  • Re-review continuity: The cache implementation and its tests have no changes between the latest previously reviewed SHA and the final head, so the prior P1 stale-version-pruning finding is still unresolved rather than fixed by the later CI repairs. (extensions/codex/src/app-server/computer-use-cache.ts:79, 8f59f074990b)
  • Missing regression shape: Cache coverage verifies successful pruning, explicit marketplace preservation, and failed-copy preservation, but does not cover concurrent same-home startup or an active client spanning a bundled-version change. (extensions/codex/src/app-server/computer-use-cache.test.ts:285, 8f59f074990b)
  • Upstream Codex contract: Direct inspection of the sibling Codex source confirms the request methods used by the readiness path—thread/start, thread/archive, thread/unsubscribe, and mcpServer/tool/call—are current app-server protocol operations. (../codex/codex-rs/app-server/tests/common/test_app_server.rs:463, 50cd5ab0acea)
  • Exact-head CI: The final head completed the relevant production types, test types, lint, dependencies, docs, extension boundaries, process/MCP security, CodeQL, and Opengrep checks successfully; these checks do not settle the runtime cache-lifetime race. (8f59f074990b)

Likely related people:

  • xingzhou: Authored the recent bounded shared app-server startup work that owns the lifecycle coordination adjacent to the cache race. (role: introduced shared-client lifecycle behavior; confidence: high; commits: 745cfc028edb; files: extensions/codex/src/app-server/shared-client.ts)
  • steipete: Co-authored the shared startup work and most recently refactored the central Codex app-server lifecycle paths on current main. (role: recent adjacent lifecycle contributor; confidence: high; commits: 745cfc028edb, c49e5c480dc2; files: extensions/codex/src/app-server/shared-client.ts, extensions/codex/src/app-server/computer-use.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.
Review history (14 earlier review cycles; latest 8 shown)
  • reviewed 2026-07-11T06:02:57.446Z sha cdf8682 :: needs changes before merge. :: [P1] Preserve the old cache until the replacement is ready | [P1] Remove the lease surface until tool calls enforce it | [P1] Authorize the probe through a trusted internal path
  • reviewed 2026-07-11T07:20:12.067Z sha 099556c :: needs changes before merge. :: [P1] Preserve the old cache until replacement succeeds
  • reviewed 2026-07-11T07:28:25.760Z sha 099556c :: needs changes before merge. :: [P1] Preserve the old cache until replacement succeeds
  • reviewed 2026-07-11T08:15:34.092Z sha b52e8f0 :: needs maintainer review before merge. :: none
  • reviewed 2026-07-11T12:37:40.317Z sha b52e8f0 :: needs changes before merge. :: [P2] Start the periodic health monitor from the owning client lifecycle | [P2] Use the repository temp helper for Codex test directories
  • reviewed 2026-07-11T13:29:07.100Z sha 572b78a :: needs maintainer review before merge. :: none
  • reviewed 2026-07-11T13:36:15.630Z sha 572b78a :: needs maintainer review before merge. :: none
  • reviewed 2026-07-11T13:54:56.463Z sha 572b78a :: needs changes before merge. :: [P1] Protect in-flight cache operations from stale-version pruning

@clawsweeper clawsweeper Bot added the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label Jul 10, 2026
@clawsweeper

clawsweeper Bot commented Jul 10, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor Author

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

Source: clawsweeper[bot]
Reason: - [P2] This automerge-opted PR has three concrete mechanical blockers with explicit assignee-approved repair instructions, but the published head has not incorporated them.; Needs attention: The live MCP readiness probe is legitimate, but its authorization is currently caller-selected across a general request boundary.; Review finding: [P1] Preserve the old cache until the replacement is ready — extensions/codex/src... (sha=cdf8682589212255f5f6c6361aa27fa5c4e0ae46)

Why human review is needed:
ClawSweeper found a blocker that should be resolved or accepted by a maintainer before the repair or automerge loop continues.

What the maintainer can do as a next step:
If the maintainer accepts the current risk and wants ClawSweeper to continue merge gates, comment @clawsweeper approve. If more work is needed, resolve the blocker first, then comment @clawsweeper automerge to re-review and continue. If automation should stay paused, leave clawsweeper:human-review in place or comment @clawsweeper stop.

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

@Takhoffman Takhoffman self-assigned this Jul 10, 2026
@Takhoffman

Takhoffman commented Jul 10, 2026

Copy link
Copy Markdown
Contributor

@clawsweeper automerge

Special instructions:
Rebase on current main and retain only unique readiness work; stage and validate shared-cache copies before pruning old versions; remove leaseTimeoutMs and lease exports until a real tool-call enforcement path exists; replace the caller-asserted Computer Use sandbox exception with a trusted readiness path; add focused regression tests and refresh exact-head macOS proof.

@clawsweeper

clawsweeper Bot commented Jul 10, 2026

Copy link
Copy Markdown
Contributor Author

🦞👀
ClawSweeper picked this up.

Command router queued. I will update this comment with the next step.

@Takhoffman Takhoffman removed the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label Jul 10, 2026
@Takhoffman

Takhoffman commented Jul 10, 2026

Copy link
Copy Markdown
Contributor

@clawsweeper automerge

Special instructions:
Rebase on current main and retain only unique readiness work; stage and validate shared-cache copies before pruning old versions; remove leaseTimeoutMs and lease exports until a real tool-call enforcement path exists; replace the caller-asserted Computer Use sandbox exception with a trusted readiness path; add focused regression tests and refresh exact-head macOS proof.

@clawsweeper clawsweeper Bot added the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label Jul 10, 2026
@Takhoffman Takhoffman removed the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label Jul 10, 2026
@Takhoffman

Takhoffman commented Jul 10, 2026

Copy link
Copy Markdown
Contributor

@clawsweeper automerge

Special instructions:
Resume the prior remote repair from checkpoint fd24a3678e68e3db8d584246748886e905e048b6 (edit checkpoint 729c1e6ecf3d0d6bfff868ade1a3085378a9ffc3). Reuse that repaired tree instead of repeating the edit pass. Validate it once against its pinned base, perform deterministic final main synchronization, then exact-head review and CI. Preserve the approved scope: failure-safe cache promotion, no unenforced lease surface, no caller-selected sandbox bypass, and only unique readiness work beyond current main.

@Takhoffman Takhoffman mentioned this pull request Jul 10, 2026
Closed
@clawsweeper clawsweeper Bot added the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label Jul 10, 2026
@Takhoffman

Takhoffman commented Jul 11, 2026

Copy link
Copy Markdown
Contributor

@clawsweeper automerge

Special instructions:
Resume the approved current-main repair now that openclaw/clawsweeper#488 has merged the coherent 30/70/75-minute repair timeout contract. Rebase on current main and retain only unique readiness work. Stage and validate shared-cache copies before pruning old versions; remove leaseTimeoutMs and lease exports until a real tool-call enforcement path exists; replace the caller-selected Computer Use sandbox exception with a trusted readiness-only path; add focused regression coverage. Do not reuse stale partial commits unless they apply cleanly to the pinned current base. Run configured validation, deterministic final main synchronization, exact-head review and CI, and refresh redacted exact-head macOS proof. Preserve credential, sandbox, cleanup, publication, and merge gates; do not merge unless the repaired exact head clears the security-boundary findings.

@clawsweeper clawsweeper Bot removed the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label Jul 11, 2026
@Takhoffman

Takhoffman commented Jul 11, 2026

Copy link
Copy Markdown
Contributor

@clawsweeper approve

@clawsweeper clawsweeper Bot removed the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label Jul 11, 2026
@Takhoffman

Takhoffman commented Jul 11, 2026

Copy link
Copy Markdown
Contributor

@clawsweeper fix ci

Exact-head b52e8f0e163fd7b04bf5357b0f20c17d1497eb4e has two actionable CI failures:

  • check-dependencies: extensions/codex/src/app-server/computer-use-health.ts is reported as an unexpected unused file. Wire it into the intended runtime path or remove it if redundant.
  • check-additional-boundaries-bcd: extensions/codex/src/app-server/test-support.ts:27 uses os.tmpdir()/tmpdir(); use resolvePreferredOpenClawTmpDir() or the appropriate plugin-sdk temp helper.

Please repair only these exact-head failures, preserve the approved security posture and reviewed behavior, run focused validation, publish the synchronized repaired head, and keep automerge armed.

@clawsweeper

clawsweeper Bot commented Jul 11, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor Author

🦞🔧
ClawSweeper picked this up.

Command: fix ci
Action: repair worker queued. Run: https://github.com/openclaw/clawsweeper/actions/runs/29152713910

I will keep the change narrow and update the PR branch if the repair worker finds a safe fix.

@clawsweeper
clawsweeper Bot force-pushed the clawsweeper/automerge-openclaw-openclaw-102264 branch from b52e8f0 to 572b78a Compare July 11, 2026 13:22
@clawsweeper

clawsweeper Bot commented Jul 11, 2026 •
edited
Loading

Copy link
Copy Markdown
Contributor Author

🦞🔧
ClawSweeper picked this up.

Command: fix ci
Action: repair worker queued. Run: https://github.com/openclaw/clawsweeper/actions/runs/29154496570

I will keep the change narrow and update the PR branch if the repair worker finds a safe fix.

@clawsweeper clawsweeper Bot added the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label Jul 11, 2026
@clawsweeper

clawsweeper Bot commented Jul 11, 2026

Copy link
Copy Markdown
Contributor Author

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

Source: clawsweeper[bot]
Reason: - [P2] No concrete code repair remains; the armed automerge workflow should perform the final synchronization and enforce exact-head checks, review, proof, and mergeability.; Cleared: The repaired head uses a trusted internal live-probe path and confines optional process termination to matching descendants of the active Codex app-server; no concrete security or supply-chain concern remains. (sha=572b78a60f63cb796fb98157b65562a3dcfca201)

Why human review is needed:
This item has security-sensitive risk. ClawSweeper is pausing instead of making an autonomous change that could affect trust, credentials, permissions, or exposure.

What the maintainer can do as a next step:
If the maintainer accepts the current risk and wants ClawSweeper to continue merge gates, comment @clawsweeper approve. If the security-sensitive detail still needs changes, describe the safe path or push the fix, then comment @clawsweeper automerge. If the risk should not be automated, keep the PR paused for manual review or comment @clawsweeper stop.

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

@clawsweeper clawsweeper Bot removed the clawsweeper:human-review Needs maintainer review before ClawSweeper can continue label Jul 11, 2026
@Takhoffman

Takhoffman commented Jul 11, 2026

Copy link
Copy Markdown
Contributor

@clawsweeper approve

@clawsweeper

clawsweeper Bot commented Jul 11, 2026

Copy link
Copy Markdown
Contributor Author

🦞👀
ClawSweeper picked this up.

Command router queued. I will update this comment with the next step.

@clawsweeper
clawsweeper Bot force-pushed the clawsweeper/automerge-openclaw-openclaw-102264 branch from 572b78a to 8f59f07 Compare July 11, 2026 14:01
@clawsweeper clawsweeper Bot added rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. merge-risk: 🚨 availability 🚨 May cause crashes, hangs, restart loops, stalls, or process outages. and removed rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. labels Jul 11, 2026
@Takhoffman

Takhoffman commented Jul 11, 2026

Copy link
Copy Markdown
Contributor

@clawsweeper automerge

@clawsweeper
clawsweeper Bot force-pushed the clawsweeper/automerge-openclaw-openclaw-102264 branch from 8f59f07 to 6f2ea1a Compare July 11, 2026 14:42
@Takhoffman
Takhoffman merged commit 1b6393c into main Jul 11, 2026
41 of 42 checks passed
@Takhoffman
Takhoffman deleted the clawsweeper/automerge-openclaw-openclaw-102264 branch July 11, 2026 14:42
@github-actions github-actions Bot mentioned this pull request Jul 11, 2026
Open
This was referenced Jul 11, 2026
Merged
Closed
github-actions Bot pushed a commit to Desicool/openclaw that referenced this pull request Jul 12, 2026
@clawsweeper @bdjben
fix (Computer Use) Stabilize Codex Computer Use readiness (openclaw#1…
c436e3b 
…03331)

* fix (Computer Use) Stabilize Codex Computer Use readiness

Co-authored-by: Ben Badejo <[email protected]>

* fix (Computer Use) Stabilize Codex Computer Use readiness

* fix (Computer Use) Stabilize Codex Computer Use readiness

* fix (Computer Use) Stabilize Codex Computer Use readiness

* fix(clawsweeper): address review for automerge-openclaw-openclaw-103331 (1)

* fix (Computer Use) Stabilize Codex Computer Use readiness

---------

Co-authored-by: clawsweeper <274271284+clawsweeper[bot]@users.noreply.github.com>
Co-authored-by: Ben Badejo <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

@Takhoffman Takhoffman

Labels

clawsweeper:automerge Maintainer opted this PR into bounded ClawSweeper-reviewed automerge clawsweeper Tracked by ClawSweeper automation commands Command implementations docs Improvements or additions to documentation extensions: codex merge-risk: 🚨 availability 🚨 May cause crashes, hangs, restart loops, stalls, or process outages. merge-risk: 🚨 compatibility 🚨 May break existing users, config, migrations, defaults, or upgrade paths. P1 High-priority user-facing bug, regression, or broken workflow. rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. size: XL status: 🚀 automerge armed This PR is in ClawSweeper's automerge lane.

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@Takhoffman