Skip to content

fix(autofix): keep a still-red check visible until its head is judged #7438

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 6 commits into from
Jul 22, 2026
Merged

fix(autofix): keep a still-red check visible until its head is judged #7438

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2b9afd3
fix(autofix): keep a still-red check visible until its head is judged
Jul 21, 2026
b71abe8
fix(autofix): pair REPORT_HEAD with the steps that emit its marker
Jul 21, 2026
1d7c65d
fix(autofix): note fail-closed asymmetry on empty LIVE_HEAD (#7438)
qwen-code Jul 21, 2026
7474163
fix(autofix): close three state-transition gaps in persistent red-che…
qwen-code-dev-bot Jul 21, 2026
bbf34c1
fix(autofix): test empty-LIVE_HEAD fail-closed path (#7438)
qwen-code-dev-bot Jul 21, 2026
c04e264
fix(autofix): discard no-op same-head duplicates in the queued-job st…
qwen-code-dev-bot Jul 21, 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
108 changes: 99 additions & 9 deletions .github/workflows/qwen-autofix.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1744,7 +1744,7 @@ jobs:
# (the watermark floor below), and labels (the effective round
# cap) — avoids extra round-trips per candidate PR.
PR_META="$(gh pr view "${PR}" --repo "${REPO}" \
--json headRefName,statusCheckRollup,createdAt,labels,isCrossRepository,headRepositoryOwner,headRepository 2> /dev/null || echo '{}')"
--json headRefName,headRefOid,statusCheckRollup,createdAt,labels,isCrossRepository,headRepositoryOwner,headRepository 2> /dev/null || echo '{}')"
HEAD_REPO_FULL="${REPO}"
if [[ "$(jq -r '.isCrossRepository // false' <<< "${PR_META}")" == "true" ]]; then
HR_OWNER="$(jq -r '.headRepositoryOwner.login // ""' <<< "${PR_META}")"
Expand Down Expand Up @@ -1902,6 +1902,16 @@ jobs:
[ .[] | select((.user.login // "") == $ab)
| select((.body // "") | contains("<!-- autofix-rearm -->"))
| .created_at ] | max // ""' "${WORKDIR}/ic.json")"
# The head this PR's red checks were last reported against. Carried
# as its OWN marker inside the eval comment rather than a new field
# on autofix-eval, so none of the ts/acted/round parsers change —
# and the comment still matches the eval filter, so the agent never
# sees it as feedback.
RED_HEAD="$(jq -r --arg ab "${AUTOFIX_BOT}" '
[ .[] | select((.user.login // "") == $ab) | . as $c | ($c.body // "")
| [ scan("<!-- autofix-redcheck head=([0-9a-f]+) -->") ] | .[]
| {sha: .[0], at: ($c.created_at // "")} ]
| sort_by(.at) | last | .sha // ""' "${WORKDIR}/ic.json")"
# A maintainer '@qwen-code /retry' posts that marker to say
# "evaluate this feedback again": markers written BEFORE it stop
# holding the watermark down. This is the sanctioned exception to
Expand Down Expand Up @@ -1995,6 +2005,30 @@ jobs:
| select((.completedAt // .updatedAt // "") > $wm) ]
| length
' <<< "${CHECKS_JSON}")"
# A red check is a persistent STATE, not the instant it turned red.
# Counting only "failed since the watermark" made a still-failing PR
# invisible the moment the watermark passed the failure: measured on
# #6451 (3 reds, all completed 09:30-09:51, watermark 10:55),
# #7357 (red 07:59, watermark 09:18) and #7390 (red and watermark
# both 11:27:37, so a strict `>` hid it the instant it appeared) —
# all three sat red for hours while every scan logged "nothing new".
#
# So: a currently-red check counts as feedback until the head it ran
# against has been evaluated. The address job records the head it
# reported on; a PR whose recorded head still matches is left alone,
# which bounds this to ONE look per head instead of every scan.
# Empty LIVE_HEAD → N_RED_NOW stays 0: fail-closed (no head → cannot judge → do not act),
# unlike the recording side where an empty REPORT_HEAD keeps reds visible.
LIVE_HEAD="$(jq -r '.headRefOid // ""' <<< "${PR_META}")"
N_RED_NOW=0
if [[ -n "${LIVE_HEAD}" && "${RED_HEAD}" != "${LIVE_HEAD}" ]]; then
Comment thread
qwen-code-dev-bot marked this conversation as resolved.
N_RED_NOW="$(jq '
[ .[]
| select((.conclusion // .state // "") | IN("FAILURE", "FAILED", "ERROR", "TIMED_OUT", "ACTION_REQUIRED"))
| select(((.workflowName // "") != "Qwen Autofix") or (((.name // "") | startswith("review-address")))) ]
Comment thread
qwen-code-dev-bot marked this conversation as resolved.
| length
' <<< "${CHECKS_JSON}")"
fi

gh api "repos/${REPO}/pulls/${PR}/reviews" --paginate > "${WORKDIR}/rv.json"
gh api "repos/${REPO}/pulls/${PR}/comments" --paginate > "${WORKDIR}/rc.json"
Expand Down Expand Up @@ -2049,14 +2083,14 @@ jobs:
HAS_CONFLICT='false'
if [[ "${MERGEABLE}" == "CONFLICTING" ]]; then HAS_CONFLICT='true'; fi

if [[ "${N_REVIEWS}" -eq 0 && "${N_COMMENTS}" -eq 0 && "${N_ISSUE_COMMENTS}" -eq 0 && "${N_FAILED_CHECKS}" -eq 0 && "${HAS_CONFLICT}" != "true" ]]; then
if [[ "${N_REVIEWS}" -eq 0 && "${N_COMMENTS}" -eq 0 && "${N_ISSUE_COMMENTS}" -eq 0 && "${N_FAILED_CHECKS}" -eq 0 && "${N_RED_NOW}" -eq 0 && "${HAS_CONFLICT}" != "true" ]]; then
echo "✅ #${PR}: nothing new since ${EFF_WM} (conflict=${HAS_CONFLICT})"
fleet_row "${PR}" 'idle' "nothing new since ${EFF_WM} (round ${ROUND}/${EFF_MAX_ROUNDS}, conflict=${HAS_CONFLICT})"
continue
fi

echo "🔎 #${PR}: ${N_REVIEWS} review(s) + ${N_COMMENTS} inline + ${N_ISSUE_COMMENTS} issue comment(s) + ${N_FAILED_CHECKS} failed check(s) new, conflict=${HAS_CONFLICT}, round=${ROUND}"
fleet_row "${PR}" 'SELECTED' "${N_REVIEWS} review + ${N_COMMENTS} inline + ${N_ISSUE_COMMENTS} comment + ${N_FAILED_CHECKS} failed-check new (round ${ROUND}/${EFF_MAX_ROUNDS}, conflict=${HAS_CONFLICT})"
echo "🔎 #${PR}: ${N_REVIEWS} review(s) + ${N_COMMENTS} inline + ${N_ISSUE_COMMENTS} issue comment(s) + ${N_FAILED_CHECKS} failed check(s) new, ${N_RED_NOW} still-red on ${LIVE_HEAD:0:9}, conflict=${HAS_CONFLICT}, round=${ROUND}"
fleet_row "${PR}" 'SELECTED' "${N_REVIEWS} review + ${N_COMMENTS} inline + ${N_ISSUE_COMMENTS} comment + ${N_FAILED_CHECKS} failed-check new, ${N_RED_NOW} still-red (round ${ROUND}/${EFF_MAX_ROUNDS}, conflict=${HAS_CONFLICT})"
TARGETS="$(jq -c \
--arg pr "${PR}" --arg branch "${BRANCH}" --arg issue "${ISSUE}" \
--arg round "${ROUND}" --arg wm "${EFF_WM}" --arg mr "${EFF_MAX_ROUNDS}" \
Expand Down Expand Up @@ -2402,6 +2436,12 @@ jobs:
git checkout -B "${BRANCH}" "origin/${BRANCH}"
fi

# The exact SHA the agent will evaluate. Captured HERE, before any
# agent mutation, so the marker records what was actually looked at —
# not the report-time remote head, which can move during the run.
CHECKED_OUT_HEAD="$(git rev-parse HEAD)"
echo "checked_out_head=${CHECKED_OUT_HEAD}" >> "${GITHUB_OUTPUT}"

# Does the branch conflict with base? merge-tree computes the merge
# without touching the tree; exit 1 means conflicts. UNKNOWN/errors are
# treated as no-conflict so we never block on a transient state.
Expand Down Expand Up @@ -2455,14 +2495,17 @@ jobs:
# QUEUES the duplicate rather than discarding it — but that queueing
# is exactly what makes this check sound: address jobs for one PR run
# strictly one at a time, so by the time the duplicate runs here, the
# first job's eval marker is posted and visible. Two duplicate
# first job's eval marker is posted and visible. Three duplicate
# signatures: (a) a sibling evaluated through a NEWER live ts than
# our matrix watermark; (b) a conflict-only sibling resolved and
# marked at the SAME ts — with no newer feedback its marker keeps
# ts=watermark while its ROUND advances past ours (ours is the max
# round observed at scan time). Either way, if there is no live
# conflict left and nothing newer than the live watermark, this run
# is a stale duplicate and discards itself.
# round observed at scan time); (c) a no-op sibling judged THIS exact
# head (its redcheck marker matches CHECKED_OUT_HEAD) while keeping
# BOTH ts and round unchanged — neither (a) nor (b) fires, but
# re-running would post a duplicate report for the same head. Either
# way, if there is no live conflict left and nothing newer than the
# live watermark, this run is a stale duplicate and discards itself.
STALE='false'
LIVE_MARKS="$(jq -r --arg ab "${AUTOFIX_BOT}" '
[ .[] | select((.user.login // "") == $ab) | . as $c | ($c.body // "")
Expand All @@ -2486,6 +2529,16 @@ jobs:
or ((.body // "") | contains("<!-- autofix-rearm -->")))
| .created_at ] | max // "none"' "${WORKDIR}/ic.json")"
LIVE_MAX_ROUND="$(jq -r --arg key "${LIVE_REARM_KEY}" 'map(select(.win == $key)) | map(.round) | max // 0' <<< "${LIVE_MARKS}")"
# The head a sibling last judged, mirrored from the scan's RED_HEAD
# parse. A no-op sibling records this marker while leaving BOTH ts and
# round UNCHANGED — so the watermark/round triggers below never fire,
# yet a second same-watermark target for the same head would otherwise
# run the agent again and post a duplicate report for that head.
LIVE_RED_HEAD="$(jq -r --arg ab "${AUTOFIX_BOT}" '
[ .[] | select((.user.login // "") == $ab) | . as $c | ($c.body // "")
| [ scan("<!-- autofix-redcheck head=([0-9a-f]+) -->") ] | .[]
| {sha: .[0], at: ($c.created_at // "")} ]
| sort_by(.at) | last | .sha // ""' "${WORKDIR}/ic.json")"
# A re-arm SUPERSEDES every job selected under the old window key:
# the maintainer asked for a fresh start, so a queued old-window job
# must discard instead of finishing and stamping an old-sequence
Expand All @@ -2495,7 +2548,8 @@ jobs:
echo "🫥 window superseded: selected under key '${WINDOW:-none}' but the live window is '${LIVE_REARM_KEY}' (re-armed while queued) — discarding without action or marker"
fi
if [[ -n "${LIVE_EVAL_WM}" && "${CONFLICT}" != "true" ]] \
&& { [[ "${LIVE_EVAL_WM}" > "${WATERMARK}" ]] || [[ "${LIVE_MAX_ROUND}" -gt "${ROUND}" ]]; }; then
&& { [[ "${LIVE_EVAL_WM}" > "${WATERMARK}" ]] || [[ "${LIVE_MAX_ROUND}" -gt "${ROUND}" ]] \
|| { [[ -n "${LIVE_RED_HEAD}" ]] && [[ "${LIVE_RED_HEAD}" == "${CHECKED_OUT_HEAD}" ]]; }; }; then
LIVE_NEW="$(jq -rs \
--arg wm "${LIVE_EVAL_WM}" --arg rb "${REVIEW_BOT}" --arg ab "${AUTOFIX_BOT}" \
--argjson trust "${TRUSTED_ASSOC}" '
Expand Down Expand Up @@ -2599,6 +2653,20 @@ jobs:
| select((.completedAt // .updatedAt // "") > $wm)
| "- \(((.name // .workflowName) // "external check") | gsub("[^A-Za-z0-9 _./()-]"; "") | .[0:80]): \(.conclusion // .state // "?")"' \
"${WORKDIR}/checks.json"
# Checks that turned red BEFORE the watermark and are STILL red.
# The section above only shows checks that failed AFTER the
# watermark, so a persistent red (the exact case the scan's
# N_RED_NOW gate selects) would leave the agent with an empty
# "Failed checks" section and no check name to reproduce.
echo
echo "## Still-red checks (persisting from before the last evaluation)"
jq -r --arg wm "${WATERMARK}" '
.[]
| select((.conclusion // .state // "") | IN("FAILURE", "FAILED", "ERROR", "TIMED_OUT", "ACTION_REQUIRED"))
| select(((.workflowName // "") != "Qwen Autofix") or (((.name // "") | startswith("review-address"))))
| select((.completedAt // .updatedAt // "") <= $wm)
| "- \(((.name // .workflowName) // "external check") | gsub("[^A-Za-z0-9 _./()-]"; "") | .[0:80]): \(.conclusion // .state // "?")"' \
"${WORKDIR}/checks.json"
# If the LAST round ended in a gate rejection, show the agent WHY.
# It is otherwise invisible on the retry: the reason lives in the
# bot's own handoff comment, which the feedback filter above
Expand Down Expand Up @@ -2905,7 +2973,13 @@ jobs:
# Surfaced in the report footer for diagnosis + attribution; a repo
# variable (not a secret), already the agent's OPENAI_MODEL.
MODEL: '${{ vars.QWEN_AUTOFIX_MODEL || vars.QWEN_PR_REVIEW_MODEL }}'
CHECKED_OUT_HEAD: '${{ steps.prepare.outputs.checked_out_head }}'
run: |-
# The head the agent actually evaluated — captured in prepare before
# any mutation, not the report-time remote head (which can move
# during the run). Empty when prepare exited early, which matches
# no marker and keeps reds visible — fail-open.
REPORT_HEAD="${CHECKED_OUT_HEAD}"
# Prepare may have adopted a sibling's live round; the matrix value
# would double-write that round's marker.
ROUND="${EFFECTIVE_ROUND:-${ROUND}}"
Expand Down Expand Up @@ -3011,6 +3085,7 @@ jobs:
echo "🧠 Handled by **Qwen Code** · model/模型 \`${MODEL_DISPLAY}\`"
echo
echo "<!-- autofix-eval ts=${NEWEST} acted=true round=${NEXT_ROUND} win=${WINDOW:-none} -->"
echo "<!-- autofix-redcheck head=${REPORT_HEAD} -->"
} > "${WORKDIR}/report.md"
STATUS="pushed (round ${NEXT_ROUND}/${MAX_ROUNDS})"
else
Expand All @@ -3027,6 +3102,7 @@ jobs:
echo "🧠 Handled by **Qwen Code** · model/模型 \`${MODEL_DISPLAY}\`"
echo
echo "<!-- autofix-eval ts=${NEWEST} acted=false round=${ROUND} win=${WINDOW:-none} -->"
echo "<!-- autofix-redcheck head=${REPORT_HEAD} -->"
} > "${WORKDIR}/report.md"
STATUS="no action needed"
fi
Expand Down Expand Up @@ -3061,7 +3137,13 @@ jobs:
STALE: '${{ steps.prepare.outputs.stale }}'
EFFECTIVE_ROUND: '${{ steps.prepare.outputs.effective_round }}'
MODEL: '${{ vars.QWEN_AUTOFIX_MODEL || vars.QWEN_PR_REVIEW_MODEL }}'
CHECKED_OUT_HEAD: '${{ steps.prepare.outputs.checked_out_head }}'
run: |-
# The head the agent actually evaluated — captured in prepare before
# any mutation, not the report-time remote head (which can move
# during the run). Empty when prepare exited early, which matches
# no marker and keeps reds visible — fail-open.
REPORT_HEAD="${CHECKED_OUT_HEAD}"
ROUND="${EFFECTIVE_ROUND:-${ROUND}}"
MODEL_DISPLAY="${MODEL:-default}"
SUFFIX=''
Expand Down Expand Up @@ -3313,6 +3395,14 @@ jobs:
echo "🧠 Handled by **Qwen Code** · model/模型 \`${MODEL_DISPLAY}\`"
echo
echo "<!-- autofix-eval ts=${MARK_TS} acted=false round=${MARK_ROUND} win=${WINDOW:-none} -->"
# A sentinel ts means the agent evaluated NOTHING (crash, API
# error, gate crash) and the next scan must retry. Recording a
# judged head here would make RED_HEAD == LIVE_HEAD, so the
# retry scan sees N_RED_NOW=0 and goes idle despite the handoff
# promising a retry.
if [[ "${MARK_TS}" != '9999-12-31T23:59:59Z' ]]; then
echo "<!-- autofix-redcheck head=${REPORT_HEAD} -->"
fi
} > "${WORKDIR}/report.md"
gh pr comment "${PR}" --repo "${REPO}" --body-file "${WORKDIR}/report.md" || echo "::warning::Failed to post handoff comment on PR #${PR}"
fi
Loading
Loading