feat(actions): add reusable code-review composite action#5
Open
mabry1985 wants to merge 1 commit into
Open
Conversation
Bundles the async-parallel PR review flow that consumes `review-code`
as a single GitHub Action so downstream protoLabs repos don't each
re-implement the workflow plumbing.
## What's in here
- `.github/actions/code-review/action.yml` — composite action that runs
`review-code init → map → run → report` through the gateway and posts
findings as a sticky PR comment. `continue-on-error: true` on the
review step keeps it non-blocking. Marker-based dedup on the comment
so re-runs `PATCH` the existing comment rather than stacking new ones.
- `.github/actions/code-review/post-findings.mjs` — sticky comment poster
used by the composite action.
- README: documents the action under "Model-backed code review" with
inputs table, behavior notes, and required secrets.
## Why a composite action instead of leaving each repo to write its own
protoMaker already shipped a workflow that did exactly this; quinn,
AionUi, and any other consumer would copy-paste the same YAML. The
sticky-comment script, the env-var translation, the timeout config,
the `continue-on-error` choice — none of it is repo-specific. Owning
the plumbing here keeps it consistent across consumers and lets bug
fixes flow on a version bump instead of per-repo PRs.
## Usage
```yaml
- uses: protoLabsAI/release-tools/.github/actions/code-review@main
with:
gateway-api-key: ${{ secrets.GATEWAY_API_KEY }}
gateway-base-url: ${{ secrets.GATEWAY_BASE_URL }}
```
Inputs: gateway-api-key (required), gateway-base-url, model, timeout-ms,
pr-number, github-token, release-tools-ref. Outputs: findings,
report-path.
## Validation
- YAML lints cleanly (js-yaml parse).
- `node --check` clean on post-findings.mjs.
- review-code itself is already validated against the gateway from
protoMaker (PR #3615) — local end-to-end run with the same secrets
this action expects.
WalkthroughThis PR introduces a new composite GitHub Action for ChangesCode Review Workflow Action
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 minutes 🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In @.github/actions/code-review/action.yml:
- Around line 80-83: Replace the fixed /tmp/code-review.md with a unique per-run
temp file and update the subsequent existence check and GITHUB_OUTPUT write to
use that variable; specifically change the npx review-code command invocation
(the line calling "npx ... review-code report --output /tmp/code-review.md") to
write to a temp file created at runtime (e.g., via mktemp or using
RUNNER_TEMP/GITHUB_RUN_ID) and then change the if check and the echo that sets
report_path to reference that same temp variable instead of the hard-coded path,
optionally also ensure the script verifies the file is non-empty before
exporting report_path to avoid using stale/empty files.
In @.github/actions/code-review/post-findings.mjs:
- Around line 56-58: The current code assigns existingId = match.id from
gh(['pr','view', prNumber, '--json', 'comments']) but then PATCHes
/repos/${owner}/${repo}/issues/comments/${existingId}, which requires the REST
numeric comment ID; update the lookup so existingId is the REST comment id:
replace the gh pr view comments fetch with a call to the REST API (e.g., gh api
repos/:owner/:repo/issues/:issue_number/comments) and find the comment whose
body includes MARKER, then set existingId to that comment's id before calling
the PATCH endpoint; ensure the variables referenced are existingId, match (or
the found comment), and the PATCH URL
/repos/${owner}/${repo}/issues/comments/${existingId}.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: ASSERTIVE
Plan: Pro
Run ID: 2ed5236c-dc70-490b-afa7-fb08dee1ed11
⛔ Files ignored due to path filters (1)
README.mdis excluded by!*.md
📒 Files selected for processing (2)
.github/actions/code-review/action.yml.github/actions/code-review/post-findings.mjs
Comment on lines
+80
to
+83
| npx --yes -p "github:protoLabsAI/release-tools#${{ inputs.release-tools-ref }}" review-code report --output /tmp/code-review.md 2>&1 | tee /tmp/report.log || true | ||
| if [ -f /tmp/code-review.md ]; then | ||
| echo "report_path=/tmp/code-review.md" >> "$GITHUB_OUTPUT" | ||
| fi |
There was a problem hiding this comment.
Avoid stale report reuse by using a unique temp file per run.
Line 80 writes to a fixed /tmp/code-review.md and Line 81 only checks existence. On persistent runners, a previous file can be reused if report generation fails, leading to stale findings being posted.
Proposed fix
- npx --yes -p "github:protoLabsAI/release-tools#${{ inputs.release-tools-ref }}" review-code report --output /tmp/code-review.md 2>&1 | tee /tmp/report.log || true
- if [ -f /tmp/code-review.md ]; then
- echo "report_path=/tmp/code-review.md" >> "$GITHUB_OUTPUT"
+ report_file="${RUNNER_TEMP}/code-review-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}.md"
+ rm -f "$report_file"
+ npx --yes -p "github:protoLabsAI/release-tools#${{ inputs.release-tools-ref }}" review-code report --output "$report_file" 2>&1 | tee /tmp/report.log || true
+ if [ -s "$report_file" ]; then
+ echo "report_path=$report_file" >> "$GITHUB_OUTPUT"
fi📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| npx --yes -p "github:protoLabsAI/release-tools#${{ inputs.release-tools-ref }}" review-code report --output /tmp/code-review.md 2>&1 | tee /tmp/report.log || true | |
| if [ -f /tmp/code-review.md ]; then | |
| echo "report_path=/tmp/code-review.md" >> "$GITHUB_OUTPUT" | |
| fi | |
| report_file="${RUNNER_TEMP}/code-review-${GITHUB_RUN_ID}-${GITHUB_RUN_ATTEMPT}.md" | |
| rm -f "$report_file" | |
| npx --yes -p "github:protoLabsAI/release-tools#${{ inputs.release-tools-ref }}" review-code report --output "$report_file" 2>&1 | tee /tmp/report.log || true | |
| if [ -s "$report_file" ]; then | |
| echo "report_path=$report_file" >> "$GITHUB_OUTPUT" | |
| fi |
🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In @.github/actions/code-review/action.yml around lines 80 - 83, Replace the
fixed /tmp/code-review.md with a unique per-run temp file and update the
subsequent existence check and GITHUB_OUTPUT write to use that variable;
specifically change the npx review-code command invocation (the line calling
"npx ... review-code report --output /tmp/code-review.md") to write to a temp
file created at runtime (e.g., via mktemp or using RUNNER_TEMP/GITHUB_RUN_ID)
and then change the if check and the echo that sets report_path to reference
that same temp variable instead of the hard-coded path, optionally also ensure
the script verifies the file is non-empty before exporting report_path to avoid
using stale/empty files.
Comment on lines
+56
to
+58
| const comments = JSON.parse(gh(['pr', 'view', prNumber, '--json', 'comments'])); | ||
| const match = (comments.comments ?? []).find((c) => c.body?.includes(MARKER)); | ||
| if (match) existingId = match.id; |
There was a problem hiding this comment.
❓ Verification inconclusive
🏁 Script executed:
#!/bin/bash
# Verify whether comment IDs from `gh pr view --json comments` are REST-patchable IDs.
set -euo pipefail
PR_NUMBER="${PR_NUMBER:?set PR_NUMBER}"
# Shows the shape of IDs returned by pr view
gh pr view "$PR_NUMBER" --json comments --jq '.comments[] | {id, url}' | head -n 5
# Shows numeric IDs from REST issue comments for the same PR
gh api "repos/${GITHUB_REPOSITORY}/issues/${PR_NUMBER}/comments" --jq '.[] | {id, html_url}' | head -n 5Repository: protoLabsAI/release-tools
Length of output: 113
Confirm PATCH /issues/comments/{comment_id} uses REST numeric IDs; existingId currently comes from gh pr view --json comments.
post-findings.mjs sets existingId = match.id from gh pr view <prNumber> --json comments, then PATCHes /repos/${owner}/${repo}/issues/comments/${existingId}. The {comment_id} path for that REST endpoint must be the REST comment ID; ensure the id returned by gh pr view --json comments is numeric/REST-compatible, or the script may not update the existing comment.
Proposed fix (lookup via REST comments so IDs are patchable)
-let existingId = null;
+let existingId = null;
try {
- const comments = JSON.parse(gh(['pr', 'view', prNumber, '--json', 'comments']));
- const match = (comments.comments ?? []).find((c) => c.body?.includes(MARKER));
+ const comments = JSON.parse(
+ gh([
+ 'api',
+ `repos/${process.env.GITHUB_REPOSITORY}/issues/${prNumber}/comments`,
+ '--paginate',
+ ]),
+ );
+ const match = (comments ?? []).find((c) => c.body?.includes(MARKER));
if (match) existingId = match.id;
} catch (err) {
console.error(`Failed to list comments (continuing as new): ${err.message}`);
}🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
In @.github/actions/code-review/post-findings.mjs around lines 56 - 58, The
current code assigns existingId = match.id from gh(['pr','view', prNumber,
'--json', 'comments']) but then PATCHes
/repos/${owner}/${repo}/issues/comments/${existingId}, which requires the REST
numeric comment ID; update the lookup so existingId is the REST comment id:
replace the gh pr view comments fetch with a call to the REST API (e.g., gh api
repos/:owner/:repo/issues/:issue_number/comments) and find the comment whose
body includes MARKER, then set existingId to that comment's id before calling
the PATCH endpoint; ensure the variables referenced are existingId, match (or
the found comment), and the PATCH URL
/repos/${owner}/${repo}/issues/comments/${existingId}.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Bundles the async-parallel PR review flow that consumes
review-codeas a single GitHub Action so downstream protoLabs repos don't each re-implement the workflow plumbing.What's in here
.github/actions/code-review/action.yml— composite action that runsreview-code init → map → run → reportthrough the gateway and posts findings as a sticky PR comment.continue-on-error: trueon the review step keeps it non-blocking. Marker-based dedup on the comment so re-runsPATCHthe existing comment rather than stacking new ones..github/actions/code-review/post-findings.mjs— sticky comment poster used by the composite action.Why a composite action instead of leaving each repo to write its own
protoMaker already shipped a workflow that did exactly this (PR #3615 in protoMaker); quinn, AionUi, and any other consumer would copy-paste the same YAML. The sticky-comment script, the env-var translation, the timeout config, the
continue-on-errorchoice — none of it is repo-specific. Owning the plumbing here keeps it consistent across consumers and lets bug fixes flow on a version bump instead of per-repo PRs.Usage
Inputs
gateway-api-keyOPENAI_API_KEY.gateway-base-urlhttps://api.proto-labs.ai/v1— appended automatically.modelprotolabs/smart(review-code default)timeout-ms300000pr-numbergithub-token${{ github.token }}release-tools-refmainValidation
node --checkclean onpost-findings.mjs.review-codeitself already validated against the gateway from protoMaker (PR #3615) — local end-to-end run with the same secrets this action expects.Follow-up
protoMaker will get a separate slim PR that drops its bespoke
code-review.yml(54 lines + sticky-comment script) and replaces it with a 5-line workflow calling this action.Summary by CodeRabbit
New Features