ci(prs): separate validation readiness from description checks (#5939)

* ci(prs): separate validation readiness from description checks

* fix(ci): harden PR readiness state

---------

Co-authored-by: Alexandre Teixeira <alexandremagteixeira@gmail.com>
This commit is contained in:
RaresKeY
2026-08-16 13:03:06 +01:00
committed by GitHub
co-authored by Alexandre Teixeira
parent 2e2bb5231e
commit 67e08cce1b
4 changed files with 461 additions and 35 deletions
+1
View File
@@ -28,6 +28,7 @@ Fixes #
- [ ] This PR targets `dev`
- [ ] My changes are limited to the scope described above — no unrelated refactors or whitespace changes mixed in.
- [ ] I actually ran the app (`docker compose up` or `uvicorn app:app`) and verified the change works end-to-end. Type-checks and unit tests are not enough.
- [ ] I did not run the app/runtime validation and stated that gap in **How to Test**. Leave this unchecked when the app-run box above is checked.
## How to Test
+138 -32
View File
@@ -21,11 +21,11 @@ module.exports = async ({ github, context, core }) => {
return strip(m?.[0].replace(new RegExp(`#+\\s+${heading}`, 'i'), '') ?? '');
}
const problems = [];
const descriptionProblems = [];
// 1. Summary must be filled in.
if (section('Summary').length < 20) {
problems.push('**Summary** is empty or too short — describe what changed and why.');
descriptionProblems.push('**Summary** is empty or too short — describe what changed and why.');
}
// 2. Linked Issue must reference a real issue. Accept a bare #NNN, a closing
@@ -34,18 +34,18 @@ module.exports = async ({ github, context, core }) => {
const linkedSection = section('Linked Issue');
const hasIssueRef = /#\d+\b/.test(linkedSection) || /\/issues\/\d+/.test(linkedSection);
if (!linkedSection || !hasIssueRef) {
problems.push('**Linked Issue** — add a reference like `Fixes #NNN`, a bare `#NNN`, or a link to the issue.');
descriptionProblems.push('**Linked Issue** — add a reference like `Fixes #NNN`, a bare `#NNN`, or a link to the issue.');
}
// 3. At least one Type of Change box must be checked.
const typeBlock = body.match(/##\s+Type of Change[\s\S]*?(?=\n##\s|$)/i)?.[0] ?? '';
if (!/- \[x\]/i.test(typeBlock)) {
problems.push('**Type of Change** — check at least one box.');
descriptionProblems.push('**Type of Change** — check at least one box.');
}
// 4. Duplicate-search checklist item must be checked.
if (!/- \[x\] I searched/i.test(body)) {
problems.push('**Checklist** — check the duplicate-search box to confirm you searched existing issues and PRs.');
descriptionProblems.push('**Checklist** — check the duplicate-search box to confirm you searched existing issues and PRs.');
}
// 5. How to Test must contain enough real detail for a reviewer to act on.
@@ -53,7 +53,79 @@ module.exports = async ({ github, context, core }) => {
// code block — so we only require non-trivial content, not a specific shape.
const howTo = section('How to Test');
if (howTo.length < 30) {
problems.push('**How to Test** — explain how a reviewer can verify this change. Numbered steps, the commands you ran, or a short code block all work — give a sentence or two of real detail (not just "tested locally").');
descriptionProblems.push('**How to Test** — explain how a reviewer can verify this change. Numbered steps, the commands you ran, or a short code block all work — give a sentence or two of real detail (not just "tested locally").');
}
// Classify paths from GitHub's API. This workflow runs in the privileged base
// context, so it must never check out or execute code from the PR branch.
const changedFiles = await github.paginate(github.rest.pulls.listFiles, {
owner, repo, pull_number: prNum, per_page: 100,
});
const changedPaths = changedFiles.map(file => file.filename);
function isUiSensitivePath(filename) {
const path = filename.toLowerCase();
return path.startsWith('static/')
|| path.startsWith('templates/')
|| /\.(?:html?|css|svg)$/.test(path);
}
function isDocsOnlyPath(filename) {
const path = filename.toLowerCase();
return /\.(?:md|mdx|rst|adoc|txt)$/.test(path)
|| (path.startsWith('docs/') && !isUiSensitivePath(path));
}
function isRuntimeSensitivePath(filename) {
const path = filename.toLowerCase();
if (isUiSensitivePath(path)) return false;
if (path.startsWith('tests/') || path.startsWith('.github/')) return false;
return /^(?:app\.py|routes\/|services\/|src\/|core\/|mcp_servers\/|scripts\/|docker\/)/.test(path)
|| /^(?:dockerfile|docker-compose.*\.ya?ml|requirements(?:-optional)?\.txt|pyproject\.toml|setup\.py)$/.test(path)
|| /\.(?:py|sh|ps1|bat)$/.test(path);
}
let classification = 'tooling';
if (changedPaths.some(isUiSensitivePath)) {
classification = 'UI-sensitive';
} else if (changedPaths.some(isRuntimeSensitivePath)) {
classification = 'backend/runtime';
} else if (changedPaths.length > 0 && changedPaths.every(isDocsOnlyPath)) {
classification = 'docs-only';
}
const appRan = /- \[x\]\s+I actually ran the app\b/i.test(body);
const appNotRun = /- \[x\]\s+I did not run the app\/runtime validation\b/i.test(body);
const screenshotChecked = /- \[x\]\s+\*\*Screenshot or short clip\*\*/i.test(body);
const screenshotSection = section('Screenshots / clips');
const hasVisualEvidence = /!\[[^\]]*\]\([^)]+\)|<(?:img|video|source)\b[^>]*(?:src|href)=|https?:\/\/[^\s)]+/i.test(screenshotSection);
const evidenceGaps = [];
let needsRuntimeValidation = false;
let needsVisualEvidence = false;
if (classification === 'backend/runtime' || classification === 'UI-sensitive') {
if (appRan && appNotRun) {
needsRuntimeValidation = true;
evidenceGaps.push('The app-run and explicit not-run boxes are both checked. Select the one state that is true.');
} else if (!appRan) {
needsRuntimeValidation = true;
if (appNotRun) {
evidenceGaps.push('The author explicitly reports that app/runtime validation was not performed.');
} else {
evidenceGaps.push('App/runtime validation is not author-attested. Check the run box only after running it, or check the explicit not-run box and describe the gap.');
}
}
}
if (classification === 'UI-sensitive') {
if (!screenshotChecked) {
needsVisualEvidence = true;
evidenceGaps.push('The screenshot/clip checkbox is not checked for this UI-sensitive change.');
}
if (!hasVisualEvidence) {
needsVisualEvidence = true;
evidenceGaps.push('The Screenshots / clips section does not contain an actual attachment or link.');
}
}
// ── Comment ──────────────────────────────────────────────────────────────
@@ -62,22 +134,43 @@ module.exports = async ({ github, context, core }) => {
});
const existing = comments.find(c => (c.body ?? '').includes(MARKER));
if (problems.length === 0) {
if (descriptionProblems.length === 0 && evidenceGaps.length === 0) {
if (existing) {
await github.rest.issues.deleteComment({ owner, repo, comment_id: existing.id });
}
} else {
const commentBody = [
MARKER,
'⚠️ **PR description — action needed**',
'',
'The following required sections are missing or incomplete. Please update the PR description to address them:',
'',
problems.map(p => `- ${p}`).join('\n'),
const commentLines = [MARKER];
if (descriptionProblems.length > 0) {
commentLines.push(
'⚠️ **PR description — action needed**',
'',
'The following required sections are missing or incomplete. Please update the PR description to address them:',
'',
descriptionProblems.map(problem => `- ${problem}`).join('\n'),
);
} else {
commentLines.push(
'⚠️ **PR description is complete; validation evidence is still outstanding**',
'',
`Changed-file classification: **${classification}**.`,
);
}
if (evidenceGaps.length > 0) {
commentLines.push(
'',
'**Author-reported runtime / visual state**',
'',
evidenceGaps.map(gap => `- ${gap}`).join('\n'),
'',
'Checkboxes are author attestations. GitHub Actions results remain the execution evidence for CI; this check does not prove that a local command ran.',
);
}
commentLines.push(
'',
'---',
'_This comment is deleted automatically once all sections are complete._',
].join('\n');
'_This comment updates automatically when the description or changed files change._',
);
const commentBody = commentLines.join('\n');
if (existing) {
await github.rest.issues.updateComment({ owner, repo, comment_id: existing.id, body: commentBody });
@@ -97,34 +190,47 @@ module.exports = async ({ github, context, core }) => {
return true;
} catch (e) {
if (e.status === 404) return false;
if (e.status === 403) {
core.warning(`Could not inspect label "${name}" — token lacks label read access; skipping.`);
return false;
}
throw e;
}
}
async function swapLabel(num, add, remove) {
if (await labelExists(add)) {
async function setLabel(name, wanted) {
if (wanted && await labelExists(name)) {
try {
await github.rest.issues.addLabels({ owner, repo, issue_number: num, labels: [add] });
await github.rest.issues.addLabels({ owner, repo, issue_number: prNum, labels: [name] });
} catch (e) {
// Fail soft on a token that can't write labels so a label permission
// problem never masks the actual description verdict.
if (e.status !== 403) throw e;
core.warning(`Could not add "${add}" — token lacks label write here; skipping.`);
if (e.status !== 403 && e.status !== 404) throw e;
core.warning(`Could not add "${name}" — label is unavailable or the token lacks label write access; skipping.`);
}
} else if (wanted) {
core.warning(`Label "${name}" does not exist in the repo — skipping. Create it once to enable labelling.`);
} else {
core.warning(`Label "${add}" does not exist in the repo — skipping. Create it once to enable labelling.`);
}
try {
await github.rest.issues.removeLabel({ owner, repo, issue_number: num, name: remove });
} catch (e) {
if (e.status !== 404 && e.status !== 410 && e.status !== 403) throw e;
try {
await github.rest.issues.removeLabel({ owner, repo, issue_number: prNum, name });
} catch (e) {
if (e.status !== 404 && e.status !== 410 && e.status !== 403) throw e;
}
}
}
if (problems.length === 0) {
await swapLabel(prNum, 'ready for review', 'needs work');
} else {
await swapLabel(prNum, 'needs work', 'ready for review');
core.setFailed(`PR description has ${problems.length} issue(s) — see bot comment for details.`);
const descriptionComplete = descriptionProblems.length === 0;
const evidenceComplete = evidenceGaps.length === 0;
const isDraft = Boolean(context.payload.pull_request.draft);
await setLabel(
'ready for review',
descriptionComplete && evidenceComplete && !isDraft,
);
await setLabel('needs work', !descriptionComplete);
await setLabel('needs runtime validation', needsRuntimeValidation);
await setLabel('needs visual evidence', needsVisualEvidence);
if (!descriptionComplete) {
core.setFailed(`PR description has ${descriptionProblems.length} issue(s) — see bot comment for details.`);
}
};
+9 -3
View File
@@ -5,7 +5,11 @@ on:
# works on fork PRs. Safe here: the checkout pins to the base branch (no fork
# code runs) and the scripts only read context.payload and call the GitHub API.
pull_request_target: # zizmor: ignore[dangerous-triggers]
types: [opened, edited, synchronize, reopened, ready_for_review]
types: [opened, edited, synchronize, reopened, ready_for_review, converted_to_draft]
concurrency:
group: pr-description-${{ github.event.pull_request.number }}
cancel-in-progress: true
# Default-deny at the workflow level; each job opts into only the scopes it needs.
# Note: modifying a PR's labels/comments needs pull-requests:write even though the
@@ -59,12 +63,14 @@ jobs:
check-mergeable:
name: Flag unmergeable PRs
needs: check-description
runs-on: ubuntu-latest
permissions:
pull-requests: write
issues: write
# Skip bots: they open PRs programmatically and have their own process.
if: github.event.pull_request.user.type != 'Bot'
# Run after description validation failures, but never from an obsolete
# workflow run canceled by a newer PR event.
if: ${{ !cancelled() && github.event.pull_request.user.type != 'Bot' }}
steps:
- uses: actions/github-script@3a2844b7e9c422d3c10d287c895573f7108da1b3 # v9.0.0
with:
+313
View File
@@ -0,0 +1,313 @@
"""Regression coverage for PR description and validation-state checks."""
import json
import shutil
import subprocess
from pathlib import Path
import pytest
_REPO = Path(__file__).resolve().parent.parent
_CHECKER = _REPO / ".github" / "scripts" / "check-pr-description.js"
_WORKFLOW = _REPO / ".github" / "workflows" / "pr-description-check.yml"
pytestmark = pytest.mark.skipif(not shutil.which("node"), reason="node not on PATH")
def _body(*, app_ran=False, app_not_run=False, screenshot=False, media=""):
return f"""## Summary
This focused change has enough concrete summary detail for the checker.
## Linked Issue
Fixes #5934
## Type of Change
- [x] CI / tooling / configuration
## Checklist
- [x] I searched open issues and open PRs.
- [{'x' if app_ran else ' '}] I actually ran the app and verified the change works end-to-end.
- [{'x' if app_not_run else ' '}] I did not run the app/runtime validation and stated that gap in How to Test.
## How to Test
Run the focused checker regression tests and inspect their exact assertions.
## Visual / UI changes
- [{'x' if screenshot else ' '}] **Screenshot or short clip** of the running change.
### Screenshots / clips
{media}
"""
def _run_checker(files, body, *, missing_labels=(), draft=False):
harness = r"""
const checkPrDescription = require(process.argv[1]);
const input = JSON.parse(process.argv[2]);
const calls = [];
const listFiles = async () => {};
const listComments = async () => {};
const github = {
paginate: async (method) => {
if (method === listFiles) return input.files.map(filename => ({ filename }));
if (method === listComments) return [];
throw new Error('unexpected paginated method');
},
rest: {
pulls: { listFiles },
issues: {
listComments,
getLabel: async ({ name }) => {
if (input.missingLabels.includes(name)) {
const error = new Error(`missing label: ${name}`);
error.status = 404;
throw error;
}
return { data: { name } };
},
addLabels: async (params) => calls.push({ method: 'addLabels', params }),
removeLabel: async (params) => calls.push({ method: 'removeLabel', params }),
createComment: async (params) => calls.push({ method: 'createComment', params }),
updateComment: async (params) => calls.push({ method: 'updateComment', params }),
deleteComment: async (params) => calls.push({ method: 'deleteComment', params }),
},
},
};
const context = {
payload: {
pull_request: {
number: 42,
body: input.body,
draft: input.draft,
},
},
repo: { owner: 'odysseus-dev', repo: 'odysseus' },
};
const core = {
warning: (message) => calls.push({ method: 'warning', message }),
setFailed: (message) => calls.push({ method: 'setFailed', message }),
};
checkPrDescription({ github, context, core })
.then(() => process.stdout.write(JSON.stringify(calls)))
.catch((error) => {
console.error(error);
process.exitCode = 1;
});
"""
payload = json.dumps(
{
"files": files,
"body": body,
"missingLabels": list(missing_labels),
"draft": draft,
}
)
proc = subprocess.run(
["node", "-e", harness, str(_CHECKER), payload],
capture_output=True,
text=True,
cwd=str(_REPO),
timeout=30,
)
assert proc.returncode == 0, proc.stderr
return json.loads(proc.stdout)
def _added_labels(calls):
return {
call["params"]["labels"][0]
for call in calls
if call["method"] == "addLabels"
}
def _comment(calls):
comments = [call for call in calls if call["method"] == "createComment"]
return comments[0]["params"]["body"] if comments else ""
@pytest.mark.parametrize(
("files", "body"),
[
(["README.md"], _body()),
(["routes/example.py"], _body(app_ran=True)),
(
["static/js/example.js"],
_body(
app_ran=True,
screenshot=True,
media="https://github.com/user-attachments/assets/example",
),
),
],
)
def test_complete_expected_state_is_ready(files, body):
calls = _run_checker(files, body)
assert _added_labels(calls) == {"ready for review"}
assert not _comment(calls)
assert not any(call["method"] == "setFailed" for call in calls)
def test_ui_checkbox_without_media_still_needs_visual_evidence():
calls = _run_checker(
["static/js/example.js"],
_body(app_ran=True, screenshot=True),
)
assert _added_labels(calls) == {"needs visual evidence"}
assert "does not contain an actual attachment or link" in _comment(calls)
assert not any(call["method"] == "setFailed" for call in calls)
def test_explicit_not_run_is_honest_but_not_ready():
calls = _run_checker(
["services/example.py"],
_body(app_not_run=True),
)
assert _added_labels(calls) == {"needs runtime validation"}
assert "explicitly reports that app/runtime validation was not performed" in _comment(calls)
assert "does not prove that a local command ran" in _comment(calls)
assert not any(call["method"] == "setFailed" for call in calls)
def test_missing_validation_label_fails_soft():
calls = _run_checker(
["services/example.py"],
_body(app_not_run=True),
missing_labels=("needs runtime validation",),
)
assert "needs runtime validation" not in _added_labels(calls)
assert any(
call["method"] == "warning"
and 'Label "needs runtime validation" does not exist' in call["message"]
for call in calls
)
assert not any(call["method"] == "setFailed" for call in calls)
@pytest.mark.parametrize(
"filename",
("requirements.txt", "requirements-optional.txt"),
)
def test_requirement_manifests_require_runtime_validation(filename):
calls = _run_checker(
[filename],
_body(app_not_run=True),
)
assert _added_labels(calls) == {"needs runtime validation"}
assert not any(
call["method"] == "addLabels"
and call["params"]["labels"] == ["ready for review"]
for call in calls
)
assert any(
call["method"] == "removeLabel"
and call["params"]["name"] == "ready for review"
for call in calls
)
assert "Changed-file classification: **backend/runtime**." in _comment(calls)
def test_old_template_runtime_pr_is_not_ready_without_attestation():
calls = _run_checker(
["routes/example.py"],
_body(),
)
assert _added_labels(calls) == {"needs runtime validation"}
assert "App/runtime validation is not author-attested" in _comment(calls)
assert not any(call["method"] == "setFailed" for call in calls)
def test_conflicting_runtime_attestations_are_not_ready():
calls = _run_checker(
["services/example.py"],
_body(app_ran=True, app_not_run=True),
)
assert _added_labels(calls) == {"needs runtime validation"}
assert "both checked" in _comment(calls)
assert not any(
call["method"] == "addLabels"
and call["params"]["labels"] == ["ready for review"]
for call in calls
)
def test_structurally_invalid_description_still_fails_hard_gate():
calls = _run_checker(
["README.md"],
"## Summary\nshort\n",
)
assert any(call["method"] == "setFailed" for call in calls)
assert "PR description" in _comment(calls)
assert "needs work" in _added_labels(calls)
assert "ready for review" not in _added_labels(calls)
def test_github_workflow_only_change_does_not_require_app_runtime():
calls = _run_checker(
[".github/workflows/example.yml"],
_body(),
)
assert _added_labels(calls) == {"ready for review"}
assert not _comment(calls)
assert not any(call["method"] == "setFailed" for call in calls)
def test_draft_pr_never_receives_ready_for_review():
calls = _run_checker(
["README.md"],
_body(),
draft=True,
)
assert "ready for review" not in _added_labels(calls)
assert any(
call["method"] == "removeLabel"
and call["params"]["name"] == "ready for review"
for call in calls
)
assert not any(call["method"] == "setFailed" for call in calls)
def test_workflow_serializes_readiness_before_mergeability():
workflow = _WORKFLOW.read_text()
assert (
"types: [opened, edited, synchronize, reopened, ready_for_review, "
"converted_to_draft]"
) in workflow
assert "group: pr-description-${{ github.event.pull_request.number }}" in workflow
assert "cancel-in-progress: true" in workflow
mergeable = workflow.split(" check-mergeable:", 1)[1]
assert "needs: check-description" in mergeable
assert (
"if: ${{ !cancelled() && github.event.pull_request.user.type != 'Bot' }}"
in mergeable
)
def test_privileged_pr_workflow_executes_only_base_code():
workflow = _WORKFLOW.read_text()
assert "pull_request_target:" in workflow
assert "ref: ${{ github.base_ref }}" in workflow
assert "persist-credentials: false" in workflow
assert "github.event.pull_request.head" not in workflow