fix: divergence alerting — alert suppression bug + stale ref detection

Bug: echo "alerted" ran regardless of curl success, permanently suppressing
alerts on delivery failure. Fix: if/then/else wraps the state write.

Warning: stale tracking refs after push steps caused false divergence.
Fix: re-fetch both remotes before comparing.

Both findings from Ganymede review of Step 6.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
m3taversal 2026-04-17 11:10:32 +01:00
parent 0f868aefab
commit 25a537d2e1

View file

@ -191,10 +191,11 @@ print('no')
else
PR_TITLE=$(echo "$branch" | sed 's|/|: |;s/-/ /g')
fi
PAYLOAD=$(python3 -c "import sys,json; print(json.dumps({'title':sys.argv[1],'head':sys.argv[2],'base':'main'}))" "$PR_TITLE" "$branch")
RESULT=$(curl -sf -X POST "http://localhost:3000/api/v1/repos/teleo/teleo-codex/pulls" \
-H "Authorization: token $FORGEJO_TOKEN" \
-H "Content-Type: application/json" \
-d "{\"title\":\"$PR_TITLE\",\"head\":\"$branch\",\"base\":\"main\"}" 2>/dev/null || echo "")
-d "$PAYLOAD" 2>/dev/null || echo "")
PR_NUM=$(echo "$RESULT" | grep -o '"number":[0-9]*' | head -1 | grep -o "[0-9]*" || true)
if [ -n "$PR_NUM" ]; then
log "Auto-created PR #$PR_NUM on Forgejo for $branch"
@ -210,7 +211,7 @@ print('no')
python3 -c "import sys,json; prs=json.load(sys.stdin); print(prs[0]['number'] if prs else '')" 2>/dev/null || true)
fi
fi
if [ -n "$GH_PR_NUM" ]; then
if [[ "$GH_PR_NUM" =~ ^[0-9]+$ ]] && [[ "$PR_NUM" =~ ^[0-9]+$ ]]; then
sqlite3 "$PIPELINE_DB" "UPDATE prs SET github_pr = $GH_PR_NUM WHERE number = $PR_NUM;" 2>/dev/null && \
log "Linked GitHub PR #$GH_PR_NUM -> Forgejo PR #$PR_NUM" || \
log "WARN: Failed to link GitHub PR #$GH_PR_NUM to Forgejo PR #$PR_NUM in DB"
@ -225,4 +226,57 @@ else
log "No new GitHub-only branches"
fi
# Step 6: Divergence alerting
# After all sync steps, check if GitHub and Forgejo main still differ.
# 2 consecutive divergent cycles (4 min) triggers a one-shot Telegram alert.
DIVERGENCE_FILE="/opt/teleo-eval/logs/.divergence-count"
git fetch forgejo main --quiet 2>/dev/null || true
git fetch origin main --quiet 2>/dev/null || true
GH_MAIN_FINAL=$(git rev-parse refs/remotes/origin/main 2>/dev/null || true)
FG_MAIN_FINAL=$(git rev-parse refs/remotes/forgejo/main 2>/dev/null || true)
if [ -n "$GH_MAIN_FINAL" ] && [ -n "$FG_MAIN_FINAL" ] && [ "$GH_MAIN_FINAL" != "$FG_MAIN_FINAL" ]; then
PREV=$(cat "$DIVERGENCE_FILE" 2>/dev/null || echo "0")
if [ "$PREV" = "alerted" ]; then
log "DIVERGENCE: still diverged (already alerted)"
else
COUNT=$((PREV + 1))
echo "$COUNT" > "$DIVERGENCE_FILE"
log "DIVERGENCE: cycle $COUNT — GitHub=$GH_MAIN_FINAL Forgejo=$FG_MAIN_FINAL"
if [ "$COUNT" -ge 2 ]; then
BOT_TOKEN=$(cat /opt/teleo-eval/secrets/telegram-bot-token 2>/dev/null || true)
ADMIN_CHAT=$(cat /opt/teleo-eval/secrets/admin-chat-id 2>/dev/null || true)
if [ -n "$BOT_TOKEN" ] && [ -n "$ADMIN_CHAT" ]; then
ALERT_MSG=$(python3 -c "
import json, sys
msg = '⚠️ Mirror divergence detected\\n\\n'
msg += f'GitHub main: {sys.argv[1][:8]}\\n'
msg += f'Forgejo main: {sys.argv[2][:8]}\\n'
msg += f'Diverged for {sys.argv[3]} consecutive cycles ({int(sys.argv[3])*2} min)\\n\\n'
msg += 'Check sync-mirror.sh logs: /opt/teleo-eval/logs/sync.log'
print(json.dumps({'chat_id': sys.argv[4], 'text': msg, 'parse_mode': 'HTML'}))
" "$GH_MAIN_FINAL" "$FG_MAIN_FINAL" "$COUNT" "$ADMIN_CHAT")
if curl -sf -X POST "https://api.telegram.org/bot${BOT_TOKEN}/sendMessage" \
-H "Content-Type: application/json" \
-d "$ALERT_MSG" >> "$LOG" 2>&1; then
log "DIVERGENCE: alert sent to admin"
echo "alerted" > "$DIVERGENCE_FILE"
else
log "WARN: Failed to send divergence alert (will retry next cycle)"
fi
else
log "WARN: Cannot send divergence alert — missing bot token or admin chat ID"
fi
fi
fi
else
if [ -f "$DIVERGENCE_FILE" ]; then
PREV=$(cat "$DIVERGENCE_FILE" 2>/dev/null || echo "0")
if [ "$PREV" != "0" ]; then
log "DIVERGENCE: resolved — repos back in sync"
fi
rm -f "$DIVERGENCE_FILE"
fi
fi
log "Sync complete"