fix: split image setup and request timeout semantics by clawsweeper[bot] · Pull Request #92673 · openclaw/openclaw

clawsweeper · 2026-06-13T12:55:18Z

Makes #85415 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: checks-node-agentic-agents-core-models:FAILURE (https://github.com/openclaw/openclaw/actions/runs/27322450334/job/80716398924)
Failing check: checks-node-agentic-agents-core-runtime:FAILURE (https://github.com/openclaw/openclaw/actions/runs/27322450334/job/80716398945)
Failing check: check-lint:FAILURE (https://github.com/openclaw/openclaw/actions/runs/27322450334/job/80716397550)

ClawSweeper 🐠 replacement reef notes:

Cluster: automerge-openclaw-openclaw-85415
Source PRs: fix: split image setup and request timeout semantics #85415
Credit: Source PR: fix: split image setup and request timeout semantics #85415
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: @hxy91819

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

Co-author credit kept:

@hxy91819: Co-authored-by: Mason Huang [email protected]

fish notes: reasoning high; reviewed against b84f60d.

clawsweeper · 2026-06-13T12:56:51Z

Codex review: passed. Reviewed June 13, 2026, 9:28 AM ET / 13:28 UTC.

Summary
The PR separates image media-understanding setup and provider request timeout handling, adds focused timeout regression tests, and updates gateway/Codex docs for the existing image timeout setting.

PR surface: Source +39, Tests +67, Docs +8. Total +114 across 5 files.

Reproducibility: yes. Source inspection shows current main subtracts setup elapsed time from the provider request timeout, and the PR adds a slow-setup regression test that exercises the failure path.

Review metrics: 1 noteworthy metric.

Timeout Semantics: 1 existing timeout field behavior clarified/changed. tools.media.image.timeoutSeconds is an existing operator setting, so maintainers should notice that observed timing behavior changes without adding a new config key.

Merge readiness
Overall: 🐚 platinum hermit
Proof: 🌊 off-meta tidepool
Patch quality: 🐚 platinum hermit
Result: ready for maintainer review.

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

Rank-up moves:

Confirm maintainers accept the per-request timeout semantics for the existing image timeout setting before automerge.

Risk before merge

[P1] Existing users who mentally treated tools.media.image.timeoutSeconds as a whole-operation cap may see image operations run longer because setup no longer consumes the provider request budget.
[P2] The Codex image tool still has an outer item/tool/call watchdog, so maintainers should be comfortable with the documented nested-timeout behavior before automerge.

Maintainer options:

Accept Request-Timeout Semantics (recommended)
Accept that the existing image timeout setting gives setup and provider request phases their own budget, with the Codex dynamic-tool watchdog remaining as the outer cap.
Pause For Whole-Operation Cap
Pause the PR if maintainers want tools.media.image.timeoutSeconds to stay a single whole-operation budget across setup and request work.
Add An Explicit Outer Cap
If both semantics are needed, add a separate documented outer operation cap instead of overloading the existing request timeout setting.

Next step before merge

[P2] No repair job is needed; this automerge-armed PR should proceed through exact-head review, checks, mergeability, and maintainer risk acceptance.

Security
Cleared: The diff is limited to media-understanding timeout control flow, focused tests, and docs; it does not change dependencies, workflows, credentials, permissions, package resolution, or generated code.

Review details

Best possible solution:

Land the focused runtime/test/docs fix if maintainers accept the existing timeout setting as a request-phase contract with the Codex outer watchdog documented separately.

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

Yes. Source inspection shows current main subtracts setup elapsed time from the provider request timeout, and the PR adds a slow-setup regression test that exercises the failure path.

Is this the best way to solve the issue?

Yes. The narrowest maintainable fix is to keep setup and provider request watchdogs separate in the image media-understanding runtime, with docs clarifying the separate Codex outer watchdog rather than redefining the existing setting as a whole-operation cap.

AGENTS.md: found and applied where relevant.

Codex review notes: model internal, reasoning high; reviewed against eaeedbf1f96b.

Label changes

Label changes:

add rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🌊 off-meta tidepool and patch quality is 🐚 platinum hermit.
remove rating: 🦐 gold shrimp: Current PR rating is rating: 🐚 platinum hermit, so this older rating label is no longer current.

Label justifications:

P2: This is a bounded media-understanding timeout bug fix with focused docs/tests and limited blast radius.
merge-risk: 🚨 compatibility: The PR changes the observed behavior of an existing timeout setting for users whose setup latency previously consumed request budget.
merge-risk: 🚨 availability: Image operations may remain active longer than before when setup is slow, even though the Codex outer watchdog still bounds dynamic tool calls.
rating: 🐚 platinum hermit: Overall readiness is 🐚 platinum hermit; proof is 🌊 off-meta tidepool and patch quality is 🐚 platinum hermit.
status: 🚀 automerge armed: This PR is in ClawSweeper's automerge lane. Not applicable: This is a ClawSweeper bot replacement for a maintainer-automerge source PR; the source PR records Crabbox Docker targeted verification, so the external-contributor proof gate does not apply to the bot replacement.

Evidence reviewed

PR surface:

Source +39, Tests +67, Docs +8. Total +114 across 5 files.

View PR surface stats

Area	Files	Added	Removed	Net
Source	1	45	6	+39
Tests	1	69	2	+67
Docs	3	12	4	+8
Config	0	0	0	0
Generated	0	0	0	0
Other	0	0	0	0
Total	5	126	12	+114

What I checked:

Current-main bug source: Current main subtracts elapsed setup time before passing timeoutMs to the provider request, so slow setup can collapse the request budget despite the setting being described as a request timeout. (src/media-understanding/image.ts:431, eaeedbf1f96b)
PR runtime fix: The PR resolves the configured timeout once, uses it for the setup watchdog, and then passes the full configured timeout into the provider request watchdog instead of subtracting setup duration. (src/media-understanding/image.ts:431, 001dee3fb088)
Regression coverage: The PR adds a slow-setup test proving the provider request still receives timeoutMs: 1000 after a 400ms setup delay, plus separate setup/request timeout messages. (src/media-understanding/image.test.ts:1046, 001dee3fb088)
Codex outer watchdog docs repaired: The latest head now says the Codex dynamic item/tool/call watchdog is the outer budget and provider request timeouts run inside it, which resolves the earlier docs mismatch. Public docs: docs/plugins/codex-harness.md. (docs/plugins/codex-harness.md:553, 001dee3fb088)
Codex protocol contract checked: Sibling Codex source defines DynamicToolCall as the item/tool/call server request, matching the OpenClaw Codex harness surface documented by this PR. (../codex/codex-rs/app-server-protocol/src/protocol/common.rs:1438, f297b9f07de1)
OpenClaw Codex watchdog source: OpenClaw still resolves the Codex image dynamic-tool budget from tools.media.image.timeoutSeconds or the 60s default and wraps the whole dynamic tool call in a timeout, so the docs qualification is necessary and now present. (extensions/codex/src/app-server/dynamic-tool-execution.ts:124, eaeedbf1f96b)

Likely related people:

steipete: GitHub path history shows multiple recent commits across media image runtime, image-tool, and Codex dynamic-tool documentation surfaces that define this timeout behavior. (role: recent area contributor; confidence: high; commits: 9b42f399a1af, 5d1f7bf05894, 7139f473332f; files: src/media-understanding/image.ts, src/agents/tools/image-tool.ts, docs/plugins/codex-harness.md)
hxy91819: The closed source PR carried the original fix and a maintainer-visible explanation that the existing setting should be treated as a per-request or per-phase timeout rather than a whole-operation budget. (role: source contributor and contract discussion participant; confidence: medium; commits: af492450db2f, e4b0b9970462, 57d8f882ce21; files: src/media-understanding/image.ts, src/media-understanding/image.test.ts, docs/gateway/config-tools.md)

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 · 2026-06-13T13:05:10Z

🦞✅
ClawSweeper merged this PR after the passing review.

Source: clawsweeper[bot]
Feedback: structured ClawSweeper verdict: pass (sha=001dee3fb0885db0bb4713d6aa0435deedab3fcf)
Merge status: merged by ClawSweeper automerge
Merged at: 2026-06-13T13:29:45Z
Merge commit: 5854e0c8f6b5

What merged:

The PR separates image media-understanding setup and provider request timeout handling, adds focused timeout regression tests, and updates gateway/Codex docs for the existing image timeout setting.
PR surface: Source +39, Tests +67, Docs +8. Total +114 across 5 files.
Reproducibility: yes. Source inspection shows current main subtracts setup elapsed time from the provider request timeout, and the PR adds a slow-setup regression test that exercises the failure path.

Automerge notes:

PR branch already contained follow-up commit before automerge: docs: clarify image timeout phase semantics
PR branch already contained follow-up commit before automerge: fix: bound image setup timeout separately
PR branch already contained follow-up commit before automerge: Revert "fix: bound image setup timeout separately"
PR branch already contained follow-up commit before automerge: fix: split image setup and request timeout semantics

The automerge loop is complete.

Automerge progress:

2026-06-13 13:04:46 UTC review requested repair b84f60d28c35 (structured ClawSweeper marker: fix-required (finding=review-feedback sha=b84f60...)

2026-06-13 13:05:10 UTC repair queued b84f60d28c35 (autonomous) Run: https://github.com/openclaw/clawsweeper/actions/runs/27467595104

2026-06-13 13:06:49 UTC repair started (running) in 1s Run: https://github.com/openclaw/clawsweeper/actions/runs/27467595104 automerge-openclaw-openclaw-92673

2026-06-13 13:07:12 UTC validation plan (passed) in 23s Run: https://github.com/openclaw/clawsweeper/actions/runs/27467595104 pnpm check:changed; pnpm lint; pnpm check:test-types

2026-06-13 13:07:23 UTC Codex write preflight (passed) in 34s Run: https://github.com/openclaw/clawsweeper/actions/runs/27467595104 danger-full-access

2026-06-13 13:15:04 UTC Codex edit 1 bbd13091937e (complete) in 8m 16s Run: https://github.com/openclaw/clawsweeper/actions/runs/27467595104 exit 0

2026-06-13 13:21:33 UTC validation and review 1 001dee3fb088 (base moved) in 14m 45s Run: https://github.com/openclaw/clawsweeper/actions/runs/27467595104 rebased

2026-06-13 13:21:38 UTC repair completed 001dee3fb088 (branch updated) in 14m 50s Run: https://github.com/openclaw/clawsweeper/actions/runs/27467595104 initial automerge rebase is delegated to Codex repair

2026-06-13 13:21:38 UTC review queued 001dee3fb088 (after repair)

2026-06-13 13:29:40 UTC automerge wait 001dee3fb088 (ready) in 22m 52s Run: https://github.com/openclaw/clawsweeper/actions/runs/27467595104 checks and exact-head review are ready

2026-06-13 13:29:13 UTC review passed 001dee3fb088 (structured ClawSweeper verdict: pass (sha=001dee3fb0885db0bb4713d6aa0435deedab3...)

2026-06-13 13:29:41 UTC repair finished 001dee3fb088 (pushed) in 22m 53s Run: https://github.com/openclaw/clawsweeper/actions/runs/27467595104 repair_contributor_branch

2026-06-13 13:29:47 UTC merged 001dee3fb088 (merged by ClawSweeper automerge)

This reverts commit 9aff5d0.

Summary: - The PR separates image media-understanding setup and provider request timeout handling, adds focused timeout regression tests, and updates gateway/Codex docs for the existing image timeout setting. - PR surface: Source +39, Tests +67, Docs +8. Total +114 across 5 files. - Reproducibility: yes. Source inspection shows current main subtracts setup elapsed time from the provider request timeout, and the PR adds a slow-setup regression test that exercises the failure path. Automerge notes: - PR branch already contained follow-up commit before automerge: docs: clarify image timeout phase semantics - PR branch already contained follow-up commit before automerge: fix: bound image setup timeout separately - PR branch already contained follow-up commit before automerge: Revert "fix: bound image setup timeout separately" - PR branch already contained follow-up commit before automerge: fix: split image setup and request timeout semantics Validation: - ClawSweeper review passed for head 001dee3. - Required merge gates passed before the squash merge. Prepared head SHA: 001dee3 Review: openclaw#92673 (comment) Co-authored-by: Mason Huang <[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: hxy91819 Co-authored-by: hxy91819 <[email protected]>

clawsweeper Bot added docs Improvements or additions to documentation gateway Gateway runtime maintainer Maintainer-authored PR clawsweeper:automerge Maintainer opted this PR into bounded ClawSweeper-reviewed automerge clawsweeper Tracked by ClawSweeper automation labels Jun 13, 2026

openclaw-barnacle Bot added the size: S label Jun 13, 2026

clawsweeper Bot mentioned this pull request Jun 13, 2026

fix: split image setup and request timeout semantics #85415

Closed

hxy91819 and others added 6 commits June 13, 2026 13:21

fix: split image setup and request timeout semantics

af49245

docs: clarify image timeout phase semantics

e4b0b99

fix: bound image setup timeout separately

57d8f88

Revert "fix: bound image setup timeout separately"

1caec58

This reverts commit 9aff5d0.

fix: split image setup and request timeout semantics

28dd480

fix: split image setup and request timeout semantics

001dee3

clawsweeper Bot force-pushed the clawsweeper/automerge-openclaw-openclaw-85415 branch from b84f60d to 001dee3 Compare June 13, 2026 13:21

clawsweeper Bot added rating: 🐚 platinum hermit Good normal PR readiness with ordinary maintainer review expected. and removed rating: 🦐 gold shrimp Decent PR readiness signal, but merge confidence is limited. labels Jun 13, 2026

clawsweeper Bot merged commit 5854e0c into main Jun 13, 2026
170 of 172 checks passed

clawsweeper Bot deleted the clawsweeper/automerge-openclaw-openclaw-85415 branch June 13, 2026 13:29

clawsweeper Bot mentioned this pull request Jun 13, 2026

[Bug]: Qwen vision models fail with 400 "Unexpected item type in content" on DashScope #92688

Closed

github-actions Bot mentioned this pull request Jun 13, 2026

📡 Upstream Digest — 2026-06-13 15:26 UTC curtismercier/openclaw-mods#1067

Open

clawsweeper Bot mentioned this pull request Jun 14, 2026

[Bug]: image-understanding deadline budget collapses to 1ms via Math.max(1, …), causing tight retry loop #80771

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Uh oh!

fix: split image setup and request timeout semantics#92673

fix: split image setup and request timeout semantics#92673
clawsweeper[bot] merged 6 commits into
mainfrom
clawsweeper/automerge-openclaw-openclaw-85415

clawsweeper Bot commented Jun 13, 2026

Uh oh!

clawsweeper Bot commented Jun 13, 2026 •

edited

Loading

Uh oh!

clawsweeper Bot commented Jun 13, 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 Jun 13, 2026

Uh oh!

clawsweeper Bot commented Jun 13, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

clawsweeper Bot commented Jun 13, 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 Jun 13, 2026 •

edited

Loading

clawsweeper Bot commented Jun 13, 2026 •

edited

Loading