Skip to content

fix(autofix): Extend suggestion handling to ten rounds #8247

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
wenshao merged 2 commits into from
Jul 31, 2026
Merged

fix(autofix): Extend suggestion handling to ten rounds #8247

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3f659fc
fix(autofix): extend takeover suggestion window
wenshao Jul 31, 2026
316ff2d
fix(autofix): use ten-round suggestion threshold
wenshao Jul 31, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
24 changes: 12 additions & 12 deletions .github/workflows/qwen-autofix.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,12 +113,12 @@ env:
# exists to stop an unproductive LOOP, not to ration ordinary iteration —
# a genuinely stuck PR still stops, just later.
MAX_ROUNDS: '10'
# Suggestions may improve a young PR, but continuing to implement them after
# five change-producing rounds expands the diff and creates fresh review
# churn. From round 6 onward, only Critical findings, formally requested
# changes, failed checks, and base conflicts may drive code changes;
# lower-severity feedback is recorded and left open.
CRITICAL_ONLY_AFTER_ROUND: '5'
# Suggestions may improve a PR, but continuing to implement them after ten
# change-producing rounds expands the diff and creates fresh review churn.
# From round 11 onward, only Critical findings, formally requested changes,
# failed checks, and base conflicts may drive code changes; lower-severity
# feedback is recorded and left open.
CRITICAL_ONLY_AFTER_ROUND: '10'
# Per-author tail budget inside Critical-only mode. An account is an
# ACCOUNTABILITY unit, not a throttle: a human login can host an automated
# reviewer loop with the exact regeneration property the review bot has
Expand Down Expand Up @@ -2471,10 +2471,10 @@ jobs:
| select((.state // "") | IN("CHANGES_REQUESTED", "COMMENTED")) ] | length' \
"${WORKDIR}/rv.json")"
# Per AGENTS.md's review policy, Suggestion-level findings are
# actionable during the first five change-producing rounds. The
# scan still selects later feedback so prepare can record and
# watermark its deferral; only the address job filters what may
# drive code changes.
# actionable during the initial change-producing rounds; takeover
# extends that window. The scan still selects later feedback so
# prepare can record and watermark its deferral; only the address
# job filters what may drive code changes.
N_COMMENTS="$(jq --arg wm "${EFF_WM}" --arg rb "${REVIEW_BOT}" --arg ab "${AUTOFIX_BOT}" \
--argjson trust "${TRUSTED_ASSOC}" '
[ .[]
Expand Down Expand Up @@ -3048,7 +3048,7 @@ jobs:
OVER_BUDGET_AUTHORS="$(jq -n \
--arg key "${LIVE_REARM_KEY}" --arg ab "${AUTOFIX_BOT}" --arg rb "${REVIEW_BOT}" \
--argjson trust "${TRUSTED_ASSOC}" \
--argjson r5 "${CRITICAL_ONLY_AFTER_ROUND}" \
--argjson critical_after "${CRITICAL_ONLY_AFTER_ROUND}" \
--argjson k "${CRITICAL_ONLY_HUMAN_BATCHES}" \
--slurpfile rv "${WORKDIR}/rv.json" --slurpfile rc "${WORKDIR}/rc.json" --slurpfile ic "${WORKDIR}/ic.json" '
([ ($ic | add)[] | select((.user.login // "") == $ab) | . as $c | ($c.body // "")
Expand All @@ -3058,7 +3058,7 @@ jobs:
| sort_by(.at)) as $ms
| ([ range(0; ($ms | length)) as $i
| ($ms[$i]
| select((.acted == "true" and .round > $r5) or (.acted == "false" and .round >= $r5))
| select((.acted == "true" and .round > $critical_after) or (.acted == "false" and .round >= $critical_after))
| {lo: (if $i == 0 then "" else ($ms[$i - 1].ts) end), hi: .ts}) ]) as $spans
| ($rv | add) as $reviews
| ($rc | add) as $comments
Expand Down
15 changes: 8 additions & 7 deletions scripts/tests/qwen-autofix-workflow.test.js
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3812,10 +3812,11 @@ describe('qwen-autofix workflow', () => {
);
});

it('switches to Critical-only feedback after five change rounds', () => {
// ROUND counts change-producing rounds, so 4 still starts the fifth
// suggestion-capable change while 5 starts the first Critical-only round.
expect(workflow).toContain("CRITICAL_ONLY_AFTER_ROUND: '5'");
it('switches to Critical-only feedback after ten change rounds', () => {
// ROUND counts change-producing rounds, so 9 still starts the tenth
// suggestion-capable change while 10 starts the first Critical-only round.
expect(workflow).toContain("CRITICAL_ONLY_AFTER_ROUND: '10'");
expect(workflow).not.toContain('TAKEOVER_CRITICAL_ONLY_AFTER_ROUND');
expect(prepareBranchAndFeedbackStep).toContain(
'[[ "${ROUND}" -ge "${CRITICAL_ONLY_AFTER_ROUND}" ]]',
);
Expand All @@ -3828,12 +3829,12 @@ describe('qwen-autofix workflow', () => {
'bash',
[
'-c',
`ROUND=${round}\nCRITICAL_ONLY_AFTER_ROUND=5\n${modeBlock}\nprintf '%s' "$CRITICAL_ONLY"`,
`ROUND=${round}\nCRITICAL_ONLY_AFTER_ROUND=10\n${modeBlock}\nprintf '%s' "$CRITICAL_ONLY"`,
],
{ encoding: 'utf8' },
);
expect(modeAt(4)).toBe('false');
expect(modeAt(5)).toBe('true');
expect(modeAt(9)).toBe('false');
expect(modeAt(10)).toBe('true');

// Once the boundary is crossed, only an explicit Critical inline finding
// or a formal changes-requested review is actionable. Suggestion and
Expand Down
Loading