Summary:
- The branch adds Vitest coverage for browser action-input CLI request bodies across element, navigation/resize, fill/evaluate, and upload paths, plus blank-ref validation.
- PR surface: Tests +278. Total +278 across 4 files.
- Reproducibility: yes. for a source-level coverage gap: current main exposes the browser action-input command ... isting tests still lack broad success-path request-body assertions. This is not a runtime bug reproduction.
Automerge notes:
- PR branch already contained follow-up commit before automerge: test(browser): cover click-coords action body
Validation:
- ClawSweeper review passed for head c070a8d51b.
- Required merge gates passed before the squash merge.
Prepared head SHA: c070a8d51b
Review: https://github.com/openclaw/openclaw/pull/92574#issuecomment-4697124920
Co-authored-by: Stellar鱼 <2182712990@qq.com>
Co-authored-by: yu-xin-c <2182712990@qq.com>
Summary:
- The PR changes gateway chat-history byte-budget fallback behavior to return a small metadata-free unavailable sentinel instead of an empty transcript, with focused budget tests.
- PR surface: Source +20, Tests +73. Total +93 across 2 files.
- Reproducibility: yes. Source inspection shows current main reaches `messages: []` when the full history, las ... d copied oversized placeholder all exceed `maxBytes`; I did not run tests because this review is read-only.
Automerge notes:
- PR branch already contained follow-up commit before automerge: test: access __openclaw via bracket notation for no-underscore-dangle
Validation:
- ClawSweeper review passed for head f2fa246ab7.
- Required merge gates passed before the squash merge.
Prepared head SHA: f2fa246ab7
Review: https://github.com/openclaw/openclaw/pull/92383#issuecomment-4688688923
Co-authored-by: Hidetsugu55 <183473679+Hidetsugu55@users.noreply.github.com>
Summary:
- The PR reorganizes the Android Settings home rows into titled intent sections and adds ShellScreen logic tests for section title mapping and section ordering.
- PR surface: Other +106. Total +106 across 2 files.
- Reproducibility: not applicable. this is a UI organization cleanup rather than a bug report. The relevant ve ... ion path is the before/after Android emulator screenshot proof plus source comparison against current main.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head da9bf5c5b5.
- Required merge gates passed before the squash merge.
Prepared head SHA: da9bf5c5b5
Review: https://github.com/openclaw/openclaw/pull/94539#issuecomment-4741795253
Co-authored-by: Tosko4 <tosko4@gmail.com>
Summary:
- The PR extends TUI session info to carry `totalTokensFresh`, maps fresh missing totals to `0`, and adds a focused regression test for the footer merge path.
- PR surface: Source +15, Tests +38. Total +53 across 4 files.
- Reproducibility: yes. at source level: `chat.history` returns session info with `totalTokensFresh`, but curr ... `null` before footer formatting. I did not run local tests or a live TUI session in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: Merge branch 'main' into fix/followup-93798
Validation:
- ClawSweeper review passed for head 43657b52c8.
- Required merge gates passed before the squash merge.
Prepared head SHA: 43657b52c8
Review: https://github.com/openclaw/openclaw/pull/94337#issuecomment-4737123127
Co-authored-by: 杨浩宇0668001029 <yang.haoyu@xydigit.com>
Co-authored-by: mushuiyu_xydt <yang.haoyu@xydigit.com>
Summary:
- The PR retargets stale generated plugin-skill symlinks when their old target disappeared and adds regression coverage for that case.
- PR surface: Source +11, Tests +17. Total +28 across 2 files.
- Reproducibility: no. high-confidence current-main failure was run in this read-only review. The linked issue ... ased-build filesystem state and source inspection confirms the runtime publisher path that this PR changes.
Automerge notes:
- PR branch already contained follow-up commit before automerge: Merge remote-tracking branch 'upstream/main' into fix/plugin-skill-st…
- PR branch already contained follow-up commit before automerge: fix(skills): unlink generated plugin skill symlinks
Validation:
- ClawSweeper review passed for head 94a9765735.
- Required merge gates passed before the squash merge.
Prepared head SHA: 94a9765735
Review: https://github.com/openclaw/openclaw/pull/86719#issuecomment-4539047343
Co-authored-by: Steven Palmer <palmer.e.steven@gmail.com>
Summary:
- The PR widens the virtual Clack output columns for wrapped terminal notes and adds a rendered-output regression test for copy-sensitive session-lock paths.
- PR surface: Source +8, Tests +28. Total +36 across 2 files.
- Reproducibility: yes. Current source routes session lock paths through `note()`, and the pinned Clack note renderer hard-wraps final content from `getColumns(output) - 6` after OpenClaw's first wrapping pass.
Automerge notes:
- PR branch already contained follow-up commit before automerge: test(note): add rendered-output regression test for copy-sensitive to…
Validation:
- ClawSweeper review passed for head b17a4ff571.
- Required merge gates passed before the squash merge.
Prepared head SHA: b17a4ff571
Review: https://github.com/openclaw/openclaw/pull/94746#issuecomment-4747714518
Co-authored-by: Dirk <0668000837@xydigit.com>
* fix: default cron runMode to 'due' instead of 'force'
When the runMode parameter is omitted from a cron 'run' action,
the default value now respects schedule guards ('due') instead
of bypassing them ('force'). This prevents unintended execution
of scheduled jobs outside their configured time windows.
Fixes#94270
Co-Authored-By: Claude <noreply@anthropic.com>
* test: update runMode expectations for default 'due' (#94270)
* ci: trigger re-evaluation of real behavior proof
* fix(cron): document due-by-default agent runs
Signed-off-by: sallyom <somalley@redhat.com>
---------
Signed-off-by: sallyom <somalley@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: sallyom <somalley@redhat.com>
Summary:
- The PR changes the WhatsApp auto-reply first-media failure fallback to resend the saved leading caption chunk and adds a multi-chunk regression test for that failure path.
- PR surface: Source 0, Tests +26. Total +26 across 2 files.
- Reproducibility: yes. Source inspection of current main gives a deterministic path: the first chunk is shift ... fallback shifts `remainingText` again before checking `caption`; this read-only review did not rerun tests.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head b609e44654.
- Required merge gates passed before the squash merge.
Prepared head SHA: b609e44654
Review: https://github.com/openclaw/openclaw/pull/93823#issuecomment-4724923171
Co-authored-by: yetval <yetvald@gmail.com>
Summary:
- The branch changes `formatMessageCliText` to render dry-run message output from `result.dryRun` instead of only `handledBy === "dry-run"`.
- PR surface: Source 0. Total 0 across 1 file.
- Reproducibility: yes. source-reproducible. The linked issue has captured CLI output, and current main shows ... e the formatter still checks `handledBy === "dry-run"`; I did not execute the CLI in this read-only review.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head dce6d6a0d3.
- Required merge gates passed before the squash merge.
Prepared head SHA: dce6d6a0d3
Review: https://github.com/openclaw/openclaw/pull/94684#issuecomment-4746101038
Co-authored-by: lizeyu-xydt <li.zeyu@xydigit.com>
Summary:
- This PR replaces the generated Documentation prompt wording with self-knowledge docs-authority guidance and updates prompt tests plus the system-prompt docs.
- PR surface: Source 0, Tests +27, Docs +6. Total +33 across 4 files.
- Reproducibility: yes. from source for the prompt gap: current main and v2026.6.8 have only broad docs-first ... ledge failure example. I did not run a fresh current-main live model conversation in this read-only review.
Automerge notes:
- PR branch already contained follow-up commit before automerge: fix: strengthen self-knowledge docs prompt
- PR branch already contained follow-up commit before automerge: test: narrow cli prompt tool assertion
- PR branch already contained follow-up commit before automerge: fix: condense self-knowledge docs prompt
- PR branch already contained follow-up commit before automerge: fix: clarify self-knowledge docs authority
- PR branch already contained follow-up commit before automerge: Merge branch 'main' into sutrah/self-knowledge-docs-prompt
Validation:
- ClawSweeper review passed for head 88a7db5d2a.
- Required merge gates passed before the squash merge.
Prepared head SHA: 88a7db5d2a
Review: https://github.com/openclaw/openclaw/pull/90882#issuecomment-4637990339
Co-authored-by: Sutra Hsing <sutrahsing@163.com>
Co-authored-by: sutra <sutrahsing@163.com>
