4669db230a
docs(agents): require architectural root-cause repairs
2026-07-31 11:06:32 -07:00
45270a02c8
chore(autoreview): centralize secret scanning ( #112036 )
...
* chore(autoreview): centralize secret scanning
* chore(autoreview): remove generated caches
* chore(autoreview): remove generated caches
2026-07-20 22:59:20 -07:00
ccbbd8b08c
fix(autoreview): sync config token fixture ( #109182 )
2026-07-16 09:44:42 -07:00
e291b8ccc9
chore(skills): sync autoreview fixture handling ( #109102 )
2026-07-16 08:28:05 -07:00
1fe3a5f557
fix(skills): shorten Testbox SSH socket paths
2026-07-15 08:52:05 +01:00
ca9bbf6ee0
refactor: split embedded agent runner orchestration ( #107900 )
...
* chore(skills): sync autoreview security scanner
* refactor(agents): split embedded runner orchestration
* test(agents): verify timeout media recovery
* fix(agents): handle missing timeout assistant text
* fix(autoreview): restrict quoted credential keys
2026-07-14 18:38:55 -07:00
623ec0f369
improve(qa-matrix): split E2EE runtime and protect recovery keys ( #107828 )
...
* fix(autoreview): handle verified QA source references
* refactor(qa-matrix): split E2EE scenario runtime
* style(qa-matrix): format recovery scenario
* chore(qa-matrix): prune split runtime baseline
* chore: keep release note in PR
2026-07-14 16:13:41 -07:00
96eaf2be80
fix: restore recent native, browser, and audio behavior ( #107631 )
...
* fix: repair recent landed regressions
* chore: keep release changelog owned
* test(macos): align CLI fixtures with Node floor
* fix(macos): document Node runtime floor contract
* style(auto-reply): restore runtime mode formatting
2026-07-14 10:47:33 -07:00
6958e4c969
chore(skills): support large autoreview diffs ( #106970 )
...
* chore(skills): sync large-diff autoreview
* fix(skills): state source-blind review limits
2026-07-13 19:25:04 -07:00
9b7f828d01
chore(skills): sync canonical autoreview ( #105250 )
2026-07-12 17:37:15 +08:00
fd9f84ffdc
chore(autoreview): align canonical skill ( #104701 )
2026-07-12 05:00:26 +08:00
b3136854f0
chore(autoreview): align org review defaults ( #104343 )
...
* docs(autoreview): sync canonical review policy
* fix(autoreview): sync isolated review runtime
* test(autoreview): sync hardening coverage
* fix(autoreview): sync final isolation hardening
* test(autoreview): sync final isolation coverage
* fix(autoreview): sync final input hardening
* test(autoreview): sync final hardening coverage
* fix(autoreview): sync reviewer trust hardening
* test(autoreview): sync fallback coverage
* test(autoreview): sync boundary coverage
* docs(autoreview): align runtime contracts
* fix(autoreview): reject unbundled gitlinks
* test(autoreview): cover final trust guards
* feat(autoreview): accept max Codex reasoning
2026-07-11 22:49:50 +08:00
fa77fe10d5
chore: migrate active GPT-5.5 references to GPT-5.6 ( #104452 )
...
* chore(models): migrate active GPT-5.5 references
* test(workboard): expect GPT-5.6 Sol default
* chore: keep release notes in PR body
* test(models): align picker fixtures with Sol default
* test: update PDF default model expectation
* test(qa): migrate thinking smoke to Luna
* test(gateway): align mock catalog with Sol default
* ci: retrigger exact-head PR checks
* test(gateway): document default catalog invariant
2026-07-11 06:30:57 -07:00
7bf80dc2c6
chore(tooling): enforce formatting and refresh TypeScript checks ( #104239 )
...
* chore(tooling): enforce current formatter and refresh checks
* chore(tooling): keep release changelog formatter-owned
* chore(tooling): retain compatible Node type surface
* ci: enforce formatting for docs-only changes
* ci: isolate docs formatter check
* chore(tooling): apply updated lint and format rules
* chore(tooling): satisfy updated switch lint
* style(ui): apply Linux formatter layout
* test(doctor): match quiet local audio contribution
* test(doctor): assert quiet output only
* test(doctor): follow restored information contract
2026-07-11 01:09:51 -07:00
1a7f1133db
chore: sync canonical autoreview skill ( #100210 )
...
* chore: sync canonical autoreview skill
* fix: preserve autoreview Cursor aliases
* fix: harden autoreview isolation
* fix: require explicit trust for Cursor reviews
* fix: preserve autoreview closeout integrity
* fix: close autoreview isolation gaps
* fix: reject incomplete autoreview inputs
* fix: isolate tool-less autoreview engines
* fix: fail closed for unsupported Droid isolation
* fix: fail closed for unsupported Droid isolation
* fix: fail closed for unsupported Droid isolation
* test: route package git fixture through temp dir tests
* fix: fail closed for unsupported Droid isolation
* fix: fail closed for unsupported Droid isolation
* fix: fail closed for unsupported Droid isolation
2026-07-05 05:31:13 -07:00
634a02e9e6
feat(autoreview): support cursor-agent engine ( #97348 )
...
Summary:
- The PR adds `cursor-agent` as an opt-in autoreview engine, updates the helper docs, runner dispatch, stream filtering, report parsing, and harness allowlists.
- PR surface: Docs +1, Other +99. Total +100 across 4 files.
- Reproducibility: not applicable. this is a feature PR, not a reported bug. The relevant check is source review plus maintainer validation of the external engine path.
Automerge notes:
- No ClawSweeper repair was needed after automerge opt-in.
Validation:
- ClawSweeper review passed for head 807659492b807659492bhttps://github.com/openclaw/openclaw/pull/97348#issuecomment-4824183439
Co-authored-by: Mason Huang <masonxhuang@tencent.com >
Approved-by: hxy91819
2026-07-01 13:48:12 +00:00
99bce5fef4
fix(agents): don't crash autoreview copilot engine on Windows temp-dir cleanup ( #97901 )
...
On Windows the spawned copilot process and its MCP subprocesses keep the
TemporaryDirectory as their cwd briefly after exit, holding a directory handle.
That makes TemporaryDirectory's rmtree raise PermissionError (WinError 32) on
__exit__, aborting the run with a traceback even though the review completed
successfully. Pass ignore_cleanup_errors=True so cleanup is best-effort and a
post-review cleanup race never fails the run.
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com >
2026-07-01 03:08:29 -07:00
fd806ada64
fix(agents): bound autoreview scope ( #93435 )
2026-06-16 07:58:07 +08:00
c3baec7136
docs: clarify autoreview follow-up scope
2026-06-02 06:15:51 -07:00
35ce103378
fix(agents): harden autoreview Windows harness ( #88284 )
2026-05-30 10:43:52 +01:00
ff0990d800
fix: accept uncommitted autoreview mode
2026-05-28 00:55:08 +01:00
fa384d4de0
fix: filter claude autoreview streaming
2026-05-27 00:41:34 +01:00
322ceb36ce
feat: stream autoreview progress
2026-05-27 00:22:05 +01:00
6f57286678
refactor: use Rastermill for image processing ( #86621 )
...
* refactor: use Rastermill for image processing
* docs: clarify autoreview heartbeat patience
* refactor: use simplified rastermill api
* fix: preserve rastermill media safety boundaries
* build: update rastermill api pin
* build: use published rastermill package
2026-05-26 02:54:49 +01:00
236edb267d
fix: make autoreview progress visible
2026-05-25 08:50:15 +01:00
8cc93293a1
fix(tools): tolerate out-of-scope autoreview findings
2026-05-24 03:55:49 +01:00
2cd73d4c89
chore: sync autoreview skill snapshot
2026-05-23 23:10:40 +01:00
31a189db0a
feat: support pi and opencode autoreview engines
2026-05-22 14:20:54 +01:00
ab1fedb63f
feat: update autoreview engine coverage
2026-05-22 12:38:15 +01:00
88ad5cb2f4
feat: update autoreview skill
2026-05-22 09:47:22 +01:00
373e3fc719
fix: harden autoreview target handling
2026-05-21 23:26:49 +01:00
c49647ee23
docs: document rejected autoreview findings
2026-05-21 14:55:07 +01:00
508945965a
docs: record ci snapshot closeout notes
2026-05-18 13:08:51 +01:00
8bfdffad32
fix: keep autoreview pnpm checks local
2026-05-18 10:43:30 +01:00
f14a0ed6cf
fix: run autoreview checks from repo root
2026-05-18 10:43:30 +01:00
b4cf06b0d7
fix: preserve autoreview prompt review status
2026-05-18 10:43:30 +01:00
3015eeca94
fix: preserve autoreview maintainer policy
2026-05-18 10:43:30 +01:00
53773ccee4
fix: keep autoreview checks offline
2026-05-18 10:43:30 +01:00
f85534fc52
chore: auto-run offline package checks in autoreview
2026-05-18 10:43:30 +01:00
9eda9d1114
docs: clarify autoreview base prompt fallback
2026-05-18 10:34:36 +01:00
81b9058cc3
chore(autoreview): scope Testbox policy to maintainers
2026-05-18 15:27:06 +08:00
3b5d30b5fd
chore(autoreview): route OpenClaw validation to Testbox
2026-05-18 15:14:28 +08:00
696b4863c3
chore: quiet autoreview default fallback
2026-05-18 04:37:19 +01:00
11d7499db1
feat: extend autoreview fallback reviewers
2026-05-18 03:49:23 +01:00
77bbffb998
docs: run autoreview with full-access sandbox
2026-05-18 00:58:30 +01:00
006ebe692d
chore: rename codex review skill to autoreview
2026-05-17 13:15:30 +01:00
Peter Steinberger