chore: tighten codex review skill · openclaw/openclaw@a582fc2
steipete
·
2026-05-14
·
via Recent Commits to openclaw:main
| Original file line number | Diff line number | Diff line change |
|---|
@@ -19,7 +19,9 @@ Use when:
|
19 | 19 | - Read dependency docs/source/types when the finding depends on external behavior. |
20 | 20 | - Reject unrealistic edge cases, speculative risks, broad rewrites, and fixes that over-complicate the codebase. |
21 | 21 | - Prefer small fixes at the right ownership boundary; no refactor unless it clearly improves the bug class. |
22 | | -- If a review-triggered fix changes code, rerun focused tests and rerun Codex review once. |
| 22 | +- Keep going until Codex review returns no accepted/actionable findings. |
| 23 | +- If a review-triggered fix changes code, rerun focused tests and rerun Codex review. |
| 24 | +- If rejecting a finding as intentional/not worth fixing, add a brief inline code comment only when it explains a real invariant or ownership decision that future reviewers should know. |
23 | 25 | - Do not push just to review. Push only when the user requested push/ship/PR update. |
24 | 26 | |
25 | 27 | ## Pick Target |
@@ -58,7 +60,7 @@ Format first if formatting can change line locations. Then it is OK to run tests
|
58 | 60 | scripts/codex-review --parallel-tests "<focused test command>" |
59 | 61 | ``` |
60 | 62 | |
61 | | -Tradeoff: tests may force code changes that stale the review. If tests or review lead to code edits, rerun the affected tests and rerun review once. |
| 63 | +Tradeoff: tests may force code changes that stale the review. If tests or review lead to code edits, rerun the affected tests and rerun review until no accepted/actionable findings remain. |
62 | 64 | |
63 | 65 | ## Context Efficiency |
64 | 66 | |
@@ -96,4 +98,4 @@ Include:
|
96 | 98 | - review command used |
97 | 99 | - tests/proof run |
98 | 100 | - findings accepted/rejected, briefly why |
99 | | -- whether review was rerun after review-triggered edits |
| 101 | +- final clean review command, or why a remaining finding was consciously rejected |
| Original file line number | Diff line number | Diff line change |
|---|
@@ -6,7 +6,7 @@ Docs: https://docs.openclaw.ai
|
6 | 6 | |
7 | 7 | ### Changes |
8 | 8 | |
9 | | -- Maintainer tooling: add a repo-local `codex-review` skill for Codex closeout reviews, including local dirty-work and PR-branch review helpers. |
| 9 | +- Maintainer tooling: add a repo-local `codex-review` skill for Codex closeout reviews, including local dirty-work and PR-branch review helpers that rerun until no accepted/actionable findings remain. |
10 | 10 | - Maintainer tooling: fail CI when pull requests add package patch files or pnpm patched dependencies, preserving the upstream-and-bump dependency workflow. |
11 | 11 | - Amazon Bedrock: externalize the Bedrock and Bedrock Mantle provider packages so core installs no longer pull AWS SDK dependencies unless those providers are installed. |
12 | 12 | - Plugins: externalize Slack, OpenShell sandbox, and Anthropic Vertex so their runtime dependency cones install only when those plugins are installed. |
|
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。
