13bc948b1d
- Race condition: mv escalations.jsonl to a PID-stamped snapshot before processing so concurrent dev-poll appends go to a fresh file; rm snapshot after loop — no entries are ever silently dropped - SQL injection: validate ESC_PR_SHA is a 40-char hex string before interpolating into the wpdb query - sc_codes scope: compute per-file from file_errors (already filtered to that file) instead of the entire step log; also switch grep to -F so dots in filenames are not treated as regex wildcards - step_pid validation: reject non-integer values from Woodpecker API before passing as CLI argument - Fallback body now distinguishes "CI logs unavailable" from "logs found but issue creation API calls failed" - ESC_GENERIC_FAIL: avoid leading blank line by using conditional separator and fix code-block opening newline - is_escalated(): remove dead esc_file/done_file locals; add Python-level int() guard so empty/non-numeric issue or pr values fail cleanly instead of producing a syntax error suppressed by 2>/dev/null Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
771 lines
32 KiB
Bash
Executable file
771 lines
32 KiB
Bash
Executable file
#!/usr/bin/env bash
|
|
# supervisor-poll.sh — Supervisor agent: bash checks + claude -p for fixes
|
|
#
|
|
# Two-layer architecture:
|
|
# 1. Factory infrastructure (project-agnostic): RAM, disk, swap, docker, stale processes
|
|
# 2. Per-project checks (config-driven): CI, PRs, dev-agent, deps — iterated over projects/*.toml
|
|
#
|
|
# Runs every 10min via cron.
|
|
#
|
|
# Cron: */10 * * * * /path/to/disinto/supervisor/supervisor-poll.sh
|
|
#
|
|
# Peek: cat /tmp/supervisor-status
|
|
# Log: tail -f /path/to/disinto/supervisor/supervisor.log
|
|
|
|
source "$(dirname "$0")/../lib/env.sh"
|
|
|
|
LOGFILE="${FACTORY_ROOT}/supervisor/supervisor.log"
|
|
STATUSFILE="/tmp/supervisor-status"
|
|
LOCKFILE="/tmp/supervisor-poll.lock"
|
|
PROMPT_FILE="${FACTORY_ROOT}/supervisor/PROMPT.md"
|
|
PROJECTS_DIR="${FACTORY_ROOT}/projects"
|
|
|
|
METRICS_FILE="${FACTORY_ROOT}/metrics/supervisor-metrics.jsonl"
|
|
|
|
emit_metric() {
|
|
printf '%s\n' "$1" >> "$METRICS_FILE"
|
|
}
|
|
|
|
# Count all matching items from a paginated Codeberg API endpoint.
|
|
# Usage: codeberg_count_paginated "/issues?state=open&labels=backlog&type=issues"
|
|
# Returns total count across all pages (max 20 pages = 1000 items).
|
|
codeberg_count_paginated() {
|
|
local endpoint="$1" total=0 page=1 count
|
|
while true; do
|
|
count=$(codeberg_api GET "${endpoint}&limit=50&page=${page}" 2>/dev/null | jq 'length' 2>/dev/null || echo 0)
|
|
total=$((total + ${count:-0}))
|
|
[ "${count:-0}" -lt 50 ] && break
|
|
page=$((page + 1))
|
|
[ "$page" -gt 20 ] && break
|
|
done
|
|
echo "$total"
|
|
}
|
|
|
|
rotate_metrics() {
|
|
[ -f "$METRICS_FILE" ] || return 0
|
|
local cutoff tmpfile
|
|
cutoff=$(date -u -d '30 days ago' +%Y-%m-%dT%H:%M)
|
|
tmpfile="${METRICS_FILE}.tmp"
|
|
jq -c --arg cutoff "$cutoff" 'select(.ts >= $cutoff)' \
|
|
"$METRICS_FILE" > "$tmpfile" 2>/dev/null
|
|
# Only replace if jq produced output, or the source is already empty
|
|
if [ -s "$tmpfile" ] || [ ! -s "$METRICS_FILE" ]; then
|
|
mv "$tmpfile" "$METRICS_FILE"
|
|
else
|
|
rm -f "$tmpfile"
|
|
fi
|
|
}
|
|
|
|
# Prevent overlapping runs
|
|
if [ -f "$LOCKFILE" ]; then
|
|
LOCK_PID=$(cat "$LOCKFILE" 2>/dev/null)
|
|
if kill -0 "$LOCK_PID" 2>/dev/null; then
|
|
exit 0
|
|
fi
|
|
rm -f "$LOCKFILE"
|
|
fi
|
|
echo $$ > "$LOCKFILE"
|
|
trap 'rm -f "$LOCKFILE" "$STATUSFILE"' EXIT
|
|
mkdir -p "$(dirname "$METRICS_FILE")"
|
|
rotate_metrics
|
|
|
|
flog() {
|
|
printf '[%s] %s\n' "$(date -u '+%Y-%m-%d %H:%M:%S UTC')" "$*" >> "$LOGFILE"
|
|
}
|
|
|
|
status() {
|
|
printf '[%s] supervisor: %s\n' "$(date -u '+%Y-%m-%d %H:%M:%S UTC')" "$*" > "$STATUSFILE"
|
|
flog "$*"
|
|
}
|
|
|
|
# ── Check for escalation replies from Matrix ──────────────────────────────
|
|
ESCALATION_REPLY=""
|
|
if [ -s /tmp/supervisor-escalation-reply ]; then
|
|
ESCALATION_REPLY=$(cat /tmp/supervisor-escalation-reply)
|
|
rm -f /tmp/supervisor-escalation-reply
|
|
flog "Got escalation reply: $(echo "$ESCALATION_REPLY" | head -1)"
|
|
fi
|
|
|
|
# Alerts by priority
|
|
P0_ALERTS=""
|
|
P1_ALERTS=""
|
|
P2_ALERTS=""
|
|
P3_ALERTS=""
|
|
P4_ALERTS=""
|
|
|
|
p0() { P0_ALERTS="${P0_ALERTS}• [P0] $*\n"; flog "P0: $*"; }
|
|
p1() { P1_ALERTS="${P1_ALERTS}• [P1] $*\n"; flog "P1: $*"; }
|
|
p2() { P2_ALERTS="${P2_ALERTS}• [P2] $*\n"; flog "P2: $*"; }
|
|
p3() { P3_ALERTS="${P3_ALERTS}• [P3] $*\n"; flog "P3: $*"; }
|
|
p4() { P4_ALERTS="${P4_ALERTS}• [P4] $*\n"; flog "P4: $*"; }
|
|
|
|
FIXES=""
|
|
fixed() { FIXES="${FIXES}• ✅ $*\n"; flog "FIXED: $*"; }
|
|
|
|
# #############################################################################
|
|
# LAYER 1: FACTORY INFRASTRUCTURE
|
|
# (project-agnostic, runs once)
|
|
# #############################################################################
|
|
|
|
# =============================================================================
|
|
# P0: MEMORY — check first, fix first
|
|
# =============================================================================
|
|
status "P0: checking memory"
|
|
|
|
AVAIL_MB=$(free -m | awk '/Mem:/{print $7}')
|
|
SWAP_USED_MB=$(free -m | awk '/Swap:/{print $3}')
|
|
|
|
if [ "${AVAIL_MB:-9999}" -lt 500 ] || { [ "${SWAP_USED_MB:-0}" -gt 3000 ] && [ "${AVAIL_MB:-9999}" -lt 2000 ]; }; then
|
|
flog "MEMORY CRISIS: avail=${AVAIL_MB}MB swap_used=${SWAP_USED_MB}MB — auto-fixing"
|
|
|
|
# Kill stale agent-spawned claude processes (>3h old) — skip interactive sessions
|
|
STALE_CLAUDES=$(pgrep -f "claude -p" --older 10800 2>/dev/null || true)
|
|
if [ -n "$STALE_CLAUDES" ]; then
|
|
echo "$STALE_CLAUDES" | xargs kill 2>/dev/null || true
|
|
fixed "Killed stale claude processes: ${STALE_CLAUDES}"
|
|
fi
|
|
|
|
# Drop filesystem caches
|
|
sync && echo 3 | sudo tee /proc/sys/vm/drop_caches >/dev/null 2>&1
|
|
fixed "Dropped filesystem caches"
|
|
|
|
# Re-check after fixes
|
|
AVAIL_MB_AFTER=$(free -m | awk '/Mem:/{print $7}')
|
|
SWAP_AFTER=$(free -m | awk '/Swap:/{print $3}')
|
|
|
|
if [ "${AVAIL_MB_AFTER:-0}" -lt 500 ] || [ "${SWAP_AFTER:-0}" -gt 3000 ]; then
|
|
p0 "Memory still critical after auto-fix: avail=${AVAIL_MB_AFTER}MB swap=${SWAP_AFTER}MB"
|
|
else
|
|
flog "Memory recovered: avail=${AVAIL_MB_AFTER}MB swap=${SWAP_AFTER}MB"
|
|
fi
|
|
fi
|
|
|
|
# =============================================================================
|
|
# P1: DISK
|
|
# =============================================================================
|
|
status "P1: checking disk"
|
|
|
|
DISK_PERCENT=$(df -h / | awk 'NR==2{print $5}' | tr -d '%')
|
|
|
|
if [ "${DISK_PERCENT:-0}" -gt 80 ]; then
|
|
flog "DISK PRESSURE: ${DISK_PERCENT}% — auto-cleaning"
|
|
|
|
# Docker cleanup (safe — keeps images)
|
|
sudo docker system prune -f >/dev/null 2>&1 && fixed "Docker prune"
|
|
|
|
# Truncate logs >10MB
|
|
for logfile in "${FACTORY_ROOT}"/{dev,review,supervisor}/*.log; do
|
|
if [ -f "$logfile" ]; then
|
|
SIZE_KB=$(du -k "$logfile" 2>/dev/null | cut -f1)
|
|
if [ "${SIZE_KB:-0}" -gt 10240 ]; then
|
|
truncate -s 0 "$logfile"
|
|
fixed "Truncated $(basename "$logfile") (was ${SIZE_KB}KB)"
|
|
fi
|
|
fi
|
|
done
|
|
|
|
# Woodpecker log_entries cleanup
|
|
LOG_ENTRIES_MB=$(wpdb -c "SELECT pg_size_pretty(pg_total_relation_size('log_entries'));" 2>/dev/null | xargs)
|
|
if echo "$LOG_ENTRIES_MB" | grep -qP '\d+\s*(GB|MB)'; then
|
|
SIZE_NUM=$(echo "$LOG_ENTRIES_MB" | grep -oP '\d+')
|
|
SIZE_UNIT=$(echo "$LOG_ENTRIES_MB" | grep -oP '(GB|MB)')
|
|
if [ "$SIZE_UNIT" = "GB" ] || { [ "$SIZE_UNIT" = "MB" ] && [ "$SIZE_NUM" -gt 500 ]; }; then
|
|
wpdb -c "DELETE FROM log_entries WHERE id < (SELECT max(id) - 100000 FROM log_entries);" 2>/dev/null
|
|
fixed "Trimmed Woodpecker log_entries (was ${LOG_ENTRIES_MB})"
|
|
fi
|
|
fi
|
|
|
|
DISK_AFTER=$(df -h / | awk 'NR==2{print $5}' | tr -d '%')
|
|
if [ "${DISK_AFTER:-0}" -gt 80 ]; then
|
|
p1 "Disk still ${DISK_AFTER}% after auto-clean"
|
|
else
|
|
flog "Disk recovered: ${DISK_AFTER}%"
|
|
fi
|
|
fi
|
|
|
|
# Emit infra metric
|
|
_RAM_TOTAL_MB=$(free -m | awk '/Mem:/{print $2}')
|
|
_RAM_USED_PCT=$(( ${_RAM_TOTAL_MB:-0} > 0 ? (${_RAM_TOTAL_MB:-0} - ${AVAIL_MB:-0}) * 100 / ${_RAM_TOTAL_MB:-1} : 0 ))
|
|
emit_metric "$(jq -nc \
|
|
--arg ts "$(date -u +%Y-%m-%dT%H:%MZ)" \
|
|
--argjson ram "${_RAM_USED_PCT:-0}" \
|
|
--argjson disk "${DISK_PERCENT:-0}" \
|
|
--argjson swap "${SWAP_USED_MB:-0}" \
|
|
'{ts:$ts,type:"infra",ram_used_pct:$ram,disk_used_pct:$disk,swap_mb:$swap}' 2>/dev/null)" 2>/dev/null || true
|
|
|
|
# =============================================================================
|
|
# P4-INFRA: HOUSEKEEPING — stale processes, log rotation (project-agnostic)
|
|
# =============================================================================
|
|
status "P4: infra housekeeping"
|
|
|
|
# Stale agent-spawned claude processes (>3h) — skip interactive sessions
|
|
STALE_CLAUDES=$(pgrep -f "claude -p" --older 10800 2>/dev/null || true)
|
|
if [ -n "$STALE_CLAUDES" ]; then
|
|
echo "$STALE_CLAUDES" | xargs kill 2>/dev/null || true
|
|
fixed "Killed stale claude processes: $(echo $STALE_CLAUDES | wc -w) procs"
|
|
fi
|
|
|
|
# Rotate logs >5MB
|
|
for logfile in "${FACTORY_ROOT}"/{dev,review,supervisor}/*.log; do
|
|
if [ -f "$logfile" ]; then
|
|
SIZE_KB=$(du -k "$logfile" 2>/dev/null | cut -f1)
|
|
if [ "${SIZE_KB:-0}" -gt 5120 ]; then
|
|
mv "$logfile" "${logfile}.old" 2>/dev/null
|
|
fixed "Rotated $(basename "$logfile")"
|
|
fi
|
|
fi
|
|
done
|
|
|
|
# Process dev-agent escalations — create sub-issues for each CI failure
|
|
ESCALATION_FILE="${FACTORY_ROOT}/supervisor/escalations.jsonl"
|
|
ESCALATION_DONE="${FACTORY_ROOT}/supervisor/escalations.done.jsonl"
|
|
|
|
if [ -s "$ESCALATION_FILE" ]; then
|
|
# Atomically snapshot the file before processing to prevent race with
|
|
# concurrent dev-poll appends: new entries go to a fresh ESCALATION_FILE
|
|
# while we process the snapshot, so nothing is ever silently dropped.
|
|
ESCALATION_SNAP="${ESCALATION_FILE}.processing.$$"
|
|
mv "$ESCALATION_FILE" "$ESCALATION_SNAP"
|
|
|
|
ESCALATION_COUNT=$(wc -l < "$ESCALATION_SNAP")
|
|
flog "Processing ${ESCALATION_COUNT} escalation(s) from dev-agent"
|
|
|
|
while IFS= read -r esc_entry; do
|
|
[ -z "$esc_entry" ] && continue
|
|
|
|
ESC_ISSUE=$(echo "$esc_entry" | jq -r '.issue // empty')
|
|
ESC_PR=$(echo "$esc_entry" | jq -r '.pr // empty')
|
|
ESC_ATTEMPTS=$(echo "$esc_entry" | jq -r '.attempts // 3')
|
|
|
|
if [ -z "$ESC_ISSUE" ] || [ -z "$ESC_PR" ]; then
|
|
echo "$esc_entry" >> "$ESCALATION_DONE"
|
|
continue
|
|
fi
|
|
|
|
flog "Escalation: issue #${ESC_ISSUE} PR #${ESC_PR} (${ESC_ATTEMPTS} CI attempt(s))"
|
|
|
|
# Fetch the failing pipeline for this PR
|
|
ESC_PR_SHA=$(curl -sf -H "Authorization: token ${CODEBERG_TOKEN}" \
|
|
"${CODEBERG_API}/pulls/${ESC_PR}" 2>/dev/null | jq -r '.head.sha // ""') || true
|
|
|
|
ESC_PIPELINE=""
|
|
ESC_SUB_ISSUES_CREATED=0
|
|
ESC_GENERIC_FAIL=""
|
|
ESC_LOGS_AVAILABLE=0
|
|
|
|
if [ -n "$ESC_PR_SHA" ]; then
|
|
# Validate SHA is a 40-char hex string before interpolating into SQL
|
|
if [[ "$ESC_PR_SHA" =~ ^[0-9a-fA-F]{40}$ ]]; then
|
|
ESC_PIPELINE=$(wpdb -c "SELECT number FROM pipelines WHERE repo_id=${WOODPECKER_REPO_ID} AND commit='${ESC_PR_SHA}' ORDER BY created DESC LIMIT 1;" 2>/dev/null | xargs || true)
|
|
else
|
|
flog "WARNING: ESC_PR_SHA '${ESC_PR_SHA}' is not a valid hex SHA — skipping pipeline lookup"
|
|
fi
|
|
fi
|
|
|
|
if [ -n "$ESC_PIPELINE" ]; then
|
|
FAILED_STEPS=$(curl -sf \
|
|
-H "Authorization: Bearer ${WOODPECKER_TOKEN}" \
|
|
"${WOODPECKER_SERVER}/api/repos/${WOODPECKER_REPO_ID}/pipelines/${ESC_PIPELINE}" 2>/dev/null | \
|
|
jq -r '.workflows[]?.children[]? | select(.state=="failure") | "\(.pid)\t\(.name)"' 2>/dev/null || true)
|
|
|
|
while IFS=$'\t' read -r step_pid step_name; do
|
|
[ -z "$step_pid" ] && continue
|
|
[[ "$step_pid" =~ ^[0-9]+$ ]] || { flog "WARNING: invalid step_pid '${step_pid}' — skipping"; continue; }
|
|
step_logs=$(woodpecker-cli pipeline log show "${CODEBERG_REPO}" "${ESC_PIPELINE}" "${step_pid}" 2>/dev/null | tail -150 || true)
|
|
[ -z "$step_logs" ] && continue
|
|
ESC_LOGS_AVAILABLE=1
|
|
|
|
if echo "$step_name" | grep -qi "shellcheck"; then
|
|
# Create one sub-issue per file with ShellCheck errors
|
|
sc_files=$(echo "$step_logs" | grep -oP '(?<=In )\S+(?= line \d+:)' | sort -u || true)
|
|
|
|
while IFS= read -r sc_file; do
|
|
[ -z "$sc_file" ] && continue
|
|
# grep -F for literal filename match (dots in filenames are regex wildcards)
|
|
file_errors=$(echo "$step_logs" | grep -F -A3 "In ${sc_file} line" | head -30)
|
|
# SC codes only from this file's errors, not the whole step log
|
|
sc_codes=$(echo "$file_errors" | grep -oP 'SC\d+' | sort -u | tr '\n' ' ' | sed 's/ $//' || true)
|
|
|
|
sub_title="fix: ShellCheck errors in ${sc_file} (from PR #${ESC_PR})"
|
|
sub_body="## ShellCheck CI failure — \`${sc_file}\`
|
|
|
|
Spawned by supervisor from escalated issue #${ESC_ISSUE} (PR #${ESC_PR} failed CI after ${ESC_ATTEMPTS} attempt(s)).
|
|
|
|
### Errors
|
|
\`\`\`
|
|
${file_errors}
|
|
\`\`\`
|
|
|
|
Fix all ShellCheck errors${sc_codes:+ (${sc_codes})} in \`${sc_file}\` so PR #${ESC_PR} CI passes.
|
|
|
|
### Context
|
|
- Parent issue: #${ESC_ISSUE}
|
|
- PR: #${ESC_PR}
|
|
- Pipeline: #${ESC_PIPELINE} (step: ${step_name})"
|
|
|
|
new_issue=$(curl -sf -X POST \
|
|
-H "Authorization: token ${CODEBERG_TOKEN}" \
|
|
-H "Content-Type: application/json" \
|
|
"${CODEBERG_API}/issues" \
|
|
-d "$(jq -nc --arg t "$sub_title" --arg b "$sub_body" \
|
|
'{"title":$t,"body":$b,"labels":["backlog"]}')" 2>/dev/null | jq -r '.number // ""') || true
|
|
|
|
if [ -n "$new_issue" ]; then
|
|
flog "Created sub-issue #${new_issue}: ShellCheck in ${sc_file} (from #${ESC_ISSUE})"
|
|
fixed "Sub-issue #${new_issue}: ShellCheck errors in ${sc_file} (escalated from #${ESC_ISSUE})"
|
|
ESC_SUB_ISSUES_CREATED=$((ESC_SUB_ISSUES_CREATED + 1))
|
|
matrix_send "supervisor" "📋 Created sub-issue #${new_issue}: ShellCheck in ${sc_file} (from escalated #${ESC_ISSUE})" 2>/dev/null || true
|
|
fi
|
|
done <<< "$sc_files"
|
|
|
|
else
|
|
# Accumulate non-ShellCheck failures for one combined issue
|
|
esc_section="=== ${step_name} ===
|
|
$(echo "$step_logs" | tail -50)"
|
|
if [ -z "$ESC_GENERIC_FAIL" ]; then
|
|
ESC_GENERIC_FAIL="$esc_section"
|
|
else
|
|
ESC_GENERIC_FAIL="${ESC_GENERIC_FAIL}
|
|
${esc_section}"
|
|
fi
|
|
fi
|
|
done <<< "$FAILED_STEPS"
|
|
fi
|
|
|
|
# Create one sub-issue for all non-ShellCheck CI failures
|
|
if [ -n "$ESC_GENERIC_FAIL" ]; then
|
|
sub_title="fix: CI failures in PR #${ESC_PR} (from issue #${ESC_ISSUE})"
|
|
sub_body="## CI failure — fix required
|
|
|
|
Spawned by supervisor from escalated issue #${ESC_ISSUE} (PR #${ESC_PR} failed CI after ${ESC_ATTEMPTS} attempt(s)).
|
|
|
|
### Failed step output
|
|
\`\`\`
|
|
${ESC_GENERIC_FAIL}
|
|
\`\`\`
|
|
|
|
### Context
|
|
- Parent issue: #${ESC_ISSUE}
|
|
- PR: #${ESC_PR}${ESC_PIPELINE:+
|
|
- Pipeline: #${ESC_PIPELINE}}"
|
|
|
|
new_issue=$(curl -sf -X POST \
|
|
-H "Authorization: token ${CODEBERG_TOKEN}" \
|
|
-H "Content-Type: application/json" \
|
|
"${CODEBERG_API}/issues" \
|
|
-d "$(jq -nc --arg t "$sub_title" --arg b "$sub_body" \
|
|
'{"title":$t,"body":$b,"labels":["backlog"]}')" 2>/dev/null | jq -r '.number // ""') || true
|
|
|
|
if [ -n "$new_issue" ]; then
|
|
flog "Created sub-issue #${new_issue}: CI failures for PR #${ESC_PR} (from #${ESC_ISSUE})"
|
|
fixed "Sub-issue #${new_issue}: CI failures for PR #${ESC_PR} (escalated from #${ESC_ISSUE})"
|
|
ESC_SUB_ISSUES_CREATED=$((ESC_SUB_ISSUES_CREATED + 1))
|
|
matrix_send "supervisor" "📋 Created sub-issue #${new_issue}: CI failures for PR #${ESC_PR} (from escalated #${ESC_ISSUE})" 2>/dev/null || true
|
|
fi
|
|
fi
|
|
|
|
# Fallback: no sub-issues created — differentiate logs-unavailable from creation failure
|
|
if [ "$ESC_SUB_ISSUES_CREATED" -eq 0 ]; then
|
|
sub_title="fix: investigate CI failure for PR #${ESC_PR} (from issue #${ESC_ISSUE})"
|
|
if [ "$ESC_LOGS_AVAILABLE" -eq 1 ]; then
|
|
# Logs were fetched but all issue creation API calls failed
|
|
sub_body="## CI failure — investigation required
|
|
|
|
Spawned by supervisor from escalated issue #${ESC_ISSUE} (PR #${ESC_PR} failed CI after ${ESC_ATTEMPTS} attempt(s)). CI logs were retrieved but sub-issue creation failed (API error).
|
|
|
|
Check PR #${ESC_PR} CI output, identify the failing checks, and fix them so the PR can merge."
|
|
else
|
|
# Could not retrieve CI logs at all
|
|
sub_body="## CI failure — investigation required
|
|
|
|
Spawned by supervisor from escalated issue #${ESC_ISSUE} (PR #${ESC_PR} failed CI after ${ESC_ATTEMPTS} attempt(s)). CI logs were unavailable at escalation time.
|
|
|
|
Check PR #${ESC_PR} CI output, identify the failing checks, and fix them so the PR can merge."
|
|
fi
|
|
|
|
new_issue=$(curl -sf -X POST \
|
|
-H "Authorization: token ${CODEBERG_TOKEN}" \
|
|
-H "Content-Type: application/json" \
|
|
"${CODEBERG_API}/issues" \
|
|
-d "$(jq -nc --arg t "$sub_title" --arg b "$sub_body" \
|
|
'{"title":$t,"body":$b,"labels":["backlog"]}')" 2>/dev/null | jq -r '.number // ""') || true
|
|
|
|
if [ -n "$new_issue" ]; then
|
|
flog "Created fallback sub-issue #${new_issue} for escalated #${ESC_ISSUE}"
|
|
fixed "Fallback sub-issue #${new_issue}: investigate CI for PR #${ESC_PR} (escalated from #${ESC_ISSUE})"
|
|
matrix_send "supervisor" "📋 Created sub-issue #${new_issue}: investigate CI for PR #${ESC_PR} (from escalated #${ESC_ISSUE})" 2>/dev/null || true
|
|
fi
|
|
fi
|
|
|
|
# Mark as processed
|
|
echo "$esc_entry" >> "$ESCALATION_DONE"
|
|
done < "$ESCALATION_SNAP"
|
|
|
|
rm -f "$ESCALATION_SNAP"
|
|
flog "Escalations processed — moved to $(basename "$ESCALATION_DONE")"
|
|
fi
|
|
|
|
# #############################################################################
|
|
# LAYER 2: PER-PROJECT CHECKS
|
|
# (iterated over projects/*.toml, config-driven)
|
|
# #############################################################################
|
|
|
|
# Function: run all per-project checks for the currently loaded project config
|
|
check_project() {
|
|
local proj_name="${PROJECT_NAME:-unknown}"
|
|
flog "── checking project: ${proj_name} (${CODEBERG_REPO}) ──"
|
|
|
|
# ===========================================================================
|
|
# P2: FACTORY STOPPED — CI, dev-agent, git
|
|
# ===========================================================================
|
|
status "P2: ${proj_name}: checking pipeline"
|
|
|
|
# CI stuck
|
|
STUCK_CI=$(wpdb -c "SELECT count(*) FROM pipelines WHERE repo_id=${WOODPECKER_REPO_ID} AND status='running' AND EXTRACT(EPOCH FROM now() - to_timestamp(started)) > 1200;" 2>/dev/null | xargs || true)
|
|
[ "${STUCK_CI:-0}" -gt 0 ] 2>/dev/null && p2 "${proj_name}: CI: ${STUCK_CI} pipeline(s) running >20min"
|
|
|
|
PENDING_CI=$(wpdb -c "SELECT count(*) FROM pipelines WHERE repo_id=${WOODPECKER_REPO_ID} AND status='pending' AND EXTRACT(EPOCH FROM now() - to_timestamp(created)) > 1800;" 2>/dev/null | xargs || true)
|
|
[ "${PENDING_CI:-0}" -gt 0 ] && p2 "${proj_name}: CI: ${PENDING_CI} pipeline(s) pending >30min"
|
|
|
|
# Emit CI metric (last completed pipeline within 24h — skip if project has no recent CI)
|
|
_CI_ROW=$(wpdb -A -F ',' -c "SELECT id, COALESCE(ROUND(EXTRACT(EPOCH FROM (to_timestamp(finished) - to_timestamp(started)))/60)::int, 0), status FROM pipelines WHERE repo_id=${WOODPECKER_REPO_ID} AND status IN ('success','failure','error') AND finished > 0 AND to_timestamp(finished) > now() - interval '24 hours' ORDER BY id DESC LIMIT 1;" 2>/dev/null | grep -E '^[0-9]' | head -1 || true)
|
|
if [ -n "$_CI_ROW" ]; then
|
|
_CI_ID=$(echo "$_CI_ROW" | cut -d',' -f1 | tr -d ' ')
|
|
_CI_DUR=$(echo "$_CI_ROW" | cut -d',' -f2 | tr -d ' ')
|
|
_CI_STAT=$(echo "$_CI_ROW" | cut -d',' -f3 | tr -d ' ')
|
|
emit_metric "$(jq -nc \
|
|
--arg ts "$(date -u +%Y-%m-%dT%H:%MZ)" \
|
|
--arg proj "$proj_name" \
|
|
--argjson pipeline "${_CI_ID:-0}" \
|
|
--argjson duration "${_CI_DUR:-0}" \
|
|
--arg status "${_CI_STAT:-unknown}" \
|
|
'{ts:$ts,type:"ci",project:$proj,pipeline:$pipeline,duration_min:$duration,status:$status}' 2>/dev/null)" 2>/dev/null || true
|
|
fi
|
|
|
|
# Dev-agent health (only if monitoring enabled)
|
|
if [ "${CHECK_DEV_AGENT:-true}" = "true" ]; then
|
|
DEV_LOCK="/tmp/dev-agent.lock"
|
|
if [ -f "$DEV_LOCK" ]; then
|
|
DEV_PID=$(cat "$DEV_LOCK" 2>/dev/null)
|
|
if ! kill -0 "$DEV_PID" 2>/dev/null; then
|
|
rm -f "$DEV_LOCK"
|
|
fixed "${proj_name}: Removed stale dev-agent lock (PID ${DEV_PID} dead)"
|
|
else
|
|
DEV_STATUS_AGE=$(stat -c %Y /tmp/dev-agent-status 2>/dev/null || echo 0)
|
|
NOW_EPOCH=$(date +%s)
|
|
STATUS_AGE_MIN=$(( (NOW_EPOCH - DEV_STATUS_AGE) / 60 ))
|
|
if [ "$STATUS_AGE_MIN" -gt 30 ]; then
|
|
p2 "${proj_name}: Dev-agent: status unchanged for ${STATUS_AGE_MIN}min"
|
|
fi
|
|
fi
|
|
fi
|
|
fi
|
|
|
|
# Git repo health
|
|
if [ -d "${PROJECT_REPO_ROOT}" ]; then
|
|
cd "${PROJECT_REPO_ROOT}" 2>/dev/null || true
|
|
GIT_BRANCH=$(git branch --show-current 2>/dev/null || echo "unknown")
|
|
GIT_REBASE=$([ -d .git/rebase-merge ] || [ -d .git/rebase-apply ] && echo "yes" || echo "no")
|
|
|
|
if [ "$GIT_REBASE" = "yes" ]; then
|
|
git rebase --abort 2>/dev/null && git checkout "${PRIMARY_BRANCH}" 2>/dev/null && \
|
|
fixed "${proj_name}: Aborted stale rebase, switched to ${PRIMARY_BRANCH}" || \
|
|
p2 "${proj_name}: Git: stale rebase, auto-abort failed"
|
|
fi
|
|
if [ "$GIT_BRANCH" != "${PRIMARY_BRANCH}" ] && [ "$GIT_BRANCH" != "unknown" ]; then
|
|
git checkout "${PRIMARY_BRANCH}" 2>/dev/null && \
|
|
fixed "${proj_name}: Switched repo from '${GIT_BRANCH}' to ${PRIMARY_BRANCH}" || \
|
|
p2 "${proj_name}: Git: on '${GIT_BRANCH}' instead of ${PRIMARY_BRANCH}"
|
|
fi
|
|
fi
|
|
|
|
# ===========================================================================
|
|
# P2b: FACTORY STALLED — backlog exists but no agent running
|
|
# ===========================================================================
|
|
if [ "${CHECK_PIPELINE_STALL:-true}" = "true" ]; then
|
|
status "P2: ${proj_name}: checking pipeline stall"
|
|
|
|
BACKLOG_COUNT=$(codeberg_api GET "/issues?state=open&labels=backlog&type=issues&limit=1" 2>/dev/null | jq -r 'length' 2>/dev/null || echo "0")
|
|
IN_PROGRESS=$(codeberg_api GET "/issues?state=open&labels=in-progress&type=issues&limit=1" 2>/dev/null | jq -r 'length' 2>/dev/null || echo "0")
|
|
|
|
if [ "${BACKLOG_COUNT:-0}" -gt 0 ] && [ "${IN_PROGRESS:-0}" -eq 0 ]; then
|
|
DEV_LOG="${FACTORY_ROOT}/dev/dev-agent.log"
|
|
if [ -f "$DEV_LOG" ]; then
|
|
LAST_LOG_EPOCH=$(stat -c %Y "$DEV_LOG" 2>/dev/null || echo 0)
|
|
else
|
|
LAST_LOG_EPOCH=0
|
|
fi
|
|
NOW_EPOCH=$(date +%s)
|
|
IDLE_MIN=$(( (NOW_EPOCH - LAST_LOG_EPOCH) / 60 ))
|
|
|
|
if [ "$IDLE_MIN" -gt 20 ]; then
|
|
p2 "${proj_name}: Pipeline stalled: ${BACKLOG_COUNT} backlog issue(s), no agent ran for ${IDLE_MIN}min"
|
|
fi
|
|
fi
|
|
fi
|
|
|
|
# ===========================================================================
|
|
# P2c: DEV-AGENT PRODUCTIVITY — all backlog blocked for too long
|
|
# ===========================================================================
|
|
if [ "${CHECK_DEV_AGENT:-true}" = "true" ]; then
|
|
status "P2: ${proj_name}: checking dev-agent productivity"
|
|
|
|
DEV_LOG_FILE="${FACTORY_ROOT}/dev/dev-agent.log"
|
|
if [ -f "$DEV_LOG_FILE" ]; then
|
|
RECENT_POLLS=$(tail -100 "$DEV_LOG_FILE" | grep "poll:" | tail -6)
|
|
TOTAL_RECENT=$(echo "$RECENT_POLLS" | grep -c "." || true)
|
|
BLOCKED_IN_RECENT=$(echo "$RECENT_POLLS" | grep -c "no ready issues" || true)
|
|
if [ "$TOTAL_RECENT" -ge 6 ] && [ "$BLOCKED_IN_RECENT" -eq "$TOTAL_RECENT" ]; then
|
|
p2 "${proj_name}: Dev-agent blocked: last ${BLOCKED_IN_RECENT} polls all report 'no ready issues'"
|
|
fi
|
|
fi
|
|
fi
|
|
|
|
# ===========================================================================
|
|
# P3: FACTORY DEGRADED — derailed PRs, unreviewed PRs
|
|
# ===========================================================================
|
|
if [ "${CHECK_PRS:-true}" = "true" ]; then
|
|
status "P3: ${proj_name}: checking PRs"
|
|
|
|
OPEN_PRS=$(codeberg_api GET "/pulls?state=open&limit=10" 2>/dev/null | jq -r '.[].number' 2>/dev/null || true)
|
|
for pr in $OPEN_PRS; do
|
|
PR_JSON=$(codeberg_api GET "/pulls/${pr}" 2>/dev/null || true)
|
|
[ -z "$PR_JSON" ] && continue
|
|
PR_SHA=$(echo "$PR_JSON" | jq -r '.head.sha // ""')
|
|
[ -z "$PR_SHA" ] && continue
|
|
|
|
CI_STATE=$(codeberg_api GET "/commits/${PR_SHA}/status" 2>/dev/null | jq -r '.state // "unknown"' 2>/dev/null || true)
|
|
|
|
MERGEABLE=$(echo "$PR_JSON" | jq -r '.mergeable // true')
|
|
if [ "$MERGEABLE" = "false" ] && [ "$CI_STATE" = "success" ]; then
|
|
p3 "${proj_name}: PR #${pr}: CI pass but merge conflict — needs rebase"
|
|
elif [ "$CI_STATE" = "failure" ] || [ "$CI_STATE" = "error" ]; then
|
|
UPDATED=$(echo "$PR_JSON" | jq -r '.updated_at // ""')
|
|
if [ -n "$UPDATED" ]; then
|
|
UPDATED_EPOCH=$(date -d "$UPDATED" +%s 2>/dev/null || echo 0)
|
|
NOW_EPOCH=$(date +%s)
|
|
AGE_MIN=$(( (NOW_EPOCH - UPDATED_EPOCH) / 60 ))
|
|
[ "$AGE_MIN" -gt 30 ] && p3 "${proj_name}: PR #${pr}: CI=${CI_STATE}, stale ${AGE_MIN}min"
|
|
fi
|
|
elif [ "$CI_STATE" = "success" ]; then
|
|
HAS_REVIEW=$(codeberg_api GET "/issues/${pr}/comments?limit=50" 2>/dev/null | \
|
|
jq -r --arg sha "$PR_SHA" '[.[] | select(.body | contains("<!-- reviewed: " + $sha))] | length' 2>/dev/null || echo "0")
|
|
|
|
if [ "${HAS_REVIEW:-0}" -eq 0 ]; then
|
|
UPDATED=$(echo "$PR_JSON" | jq -r '.updated_at // ""')
|
|
if [ -n "$UPDATED" ]; then
|
|
UPDATED_EPOCH=$(date -d "$UPDATED" +%s 2>/dev/null || echo 0)
|
|
NOW_EPOCH=$(date +%s)
|
|
AGE_MIN=$(( (NOW_EPOCH - UPDATED_EPOCH) / 60 ))
|
|
if [ "$AGE_MIN" -gt 60 ]; then
|
|
p3 "${proj_name}: PR #${pr}: CI passed, no review for ${AGE_MIN}min"
|
|
bash "${FACTORY_ROOT}/review/review-pr.sh" "$pr" >> "${FACTORY_ROOT}/review/review.log" 2>&1 &
|
|
fixed "${proj_name}: Auto-triggered review for PR #${pr}"
|
|
fi
|
|
fi
|
|
fi
|
|
fi
|
|
done
|
|
fi
|
|
|
|
# ===========================================================================
|
|
# P3b: CIRCULAR DEPENDENCIES — deadlock detection
|
|
# ===========================================================================
|
|
status "P3: ${proj_name}: checking for circular dependencies"
|
|
|
|
BACKLOG_FOR_DEPS=$(codeberg_api GET "/issues?state=open&labels=backlog&type=issues&limit=50" 2>/dev/null || true)
|
|
if [ -n "$BACKLOG_FOR_DEPS" ] && [ "$BACKLOG_FOR_DEPS" != "null" ] && [ "$(echo "$BACKLOG_FOR_DEPS" | jq 'length' 2>/dev/null || echo 0)" -gt 0 ]; then
|
|
|
|
PARSE_DEPS="${FACTORY_ROOT}/lib/parse-deps.sh"
|
|
ISSUE_COUNT=$(echo "$BACKLOG_FOR_DEPS" | jq 'length')
|
|
|
|
declare -A DEPS_OF
|
|
declare -A BACKLOG_NUMS
|
|
for i in $(seq 0 $((ISSUE_COUNT - 1))); do
|
|
NUM=$(echo "$BACKLOG_FOR_DEPS" | jq -r ".[$i].number")
|
|
BODY=$(echo "$BACKLOG_FOR_DEPS" | jq -r ".[$i].body // \"\"")
|
|
ISSUE_DEPS=$(echo "$BODY" | bash "$PARSE_DEPS" | grep -v "^${NUM}$" || true)
|
|
[ -n "$ISSUE_DEPS" ] && DEPS_OF[$NUM]="$ISSUE_DEPS"
|
|
BACKLOG_NUMS[$NUM]=1
|
|
done
|
|
|
|
declare -A NODE_COLOR
|
|
for node in "${!DEPS_OF[@]}"; do NODE_COLOR[$node]=0; done
|
|
|
|
FOUND_CYCLES=""
|
|
declare -A SEEN_CYCLES
|
|
|
|
dfs_detect_cycle() {
|
|
local node="$1" path="$2"
|
|
NODE_COLOR[$node]=1
|
|
for dep in ${DEPS_OF[$node]:-}; do
|
|
[ -z "${NODE_COLOR[$dep]+x}" ] && continue
|
|
if [ "${NODE_COLOR[$dep]}" = "1" ]; then
|
|
local cycle_key=$(echo "$path $dep" | tr ' ' '\n' | sort -n | tr '\n' ' ')
|
|
if [ -z "${SEEN_CYCLES[$cycle_key]+x}" ]; then
|
|
SEEN_CYCLES[$cycle_key]=1
|
|
local in_cycle=0 cycle_str=""
|
|
for p in $path $dep; do
|
|
[ "$p" = "$dep" ] && in_cycle=1
|
|
[ "$in_cycle" = "1" ] && cycle_str="${cycle_str:+$cycle_str -> }#${p}"
|
|
done
|
|
FOUND_CYCLES="${FOUND_CYCLES}${cycle_str}\n"
|
|
fi
|
|
elif [ "${NODE_COLOR[$dep]}" = "0" ]; then
|
|
dfs_detect_cycle "$dep" "$path $dep"
|
|
fi
|
|
done
|
|
NODE_COLOR[$node]=2
|
|
}
|
|
|
|
for node in "${!DEPS_OF[@]}"; do
|
|
[ "${NODE_COLOR[$node]:-2}" = "0" ] && dfs_detect_cycle "$node" "$node"
|
|
done
|
|
|
|
if [ -n "$FOUND_CYCLES" ]; then
|
|
echo -e "$FOUND_CYCLES" | while IFS= read -r cycle; do
|
|
[ -z "$cycle" ] && continue
|
|
p3 "${proj_name}: Circular dependency deadlock: ${cycle}"
|
|
done
|
|
fi
|
|
|
|
# =========================================================================
|
|
# P3c: STALE DEPENDENCIES — blocked by old open issues (>30 days)
|
|
# =========================================================================
|
|
status "P3: ${proj_name}: checking for stale dependencies"
|
|
|
|
NOW_EPOCH=$(date +%s)
|
|
declare -A DEP_CACHE
|
|
|
|
for issue_num in "${!DEPS_OF[@]}"; do
|
|
for dep in ${DEPS_OF[$issue_num]}; do
|
|
if [ -n "${DEP_CACHE[$dep]+x}" ]; then
|
|
DEP_INFO="${DEP_CACHE[$dep]}"
|
|
else
|
|
DEP_JSON=$(codeberg_api GET "/issues/${dep}" 2>/dev/null || true)
|
|
[ -z "$DEP_JSON" ] && continue
|
|
DEP_STATE=$(echo "$DEP_JSON" | jq -r '.state // "unknown"')
|
|
DEP_CREATED=$(echo "$DEP_JSON" | jq -r '.created_at // ""')
|
|
DEP_TITLE=$(echo "$DEP_JSON" | jq -r '.title // ""' | head -c 50)
|
|
DEP_INFO="${DEP_STATE}|${DEP_CREATED}|${DEP_TITLE}"
|
|
DEP_CACHE[$dep]="$DEP_INFO"
|
|
fi
|
|
|
|
DEP_STATE="${DEP_INFO%%|*}"
|
|
[ "$DEP_STATE" != "open" ] && continue
|
|
|
|
DEP_REST="${DEP_INFO#*|}"
|
|
DEP_CREATED="${DEP_REST%%|*}"
|
|
DEP_TITLE="${DEP_REST#*|}"
|
|
|
|
[ -z "$DEP_CREATED" ] && continue
|
|
CREATED_EPOCH=$(date -d "$DEP_CREATED" +%s 2>/dev/null || echo 0)
|
|
AGE_DAYS=$(( (NOW_EPOCH - CREATED_EPOCH) / 86400 ))
|
|
if [ "$AGE_DAYS" -gt 30 ]; then
|
|
p3 "${proj_name}: Stale dependency: #${issue_num} blocked by #${dep} \"${DEP_TITLE}\" (open ${AGE_DAYS} days)"
|
|
fi
|
|
done
|
|
done
|
|
|
|
unset DEPS_OF BACKLOG_NUMS NODE_COLOR SEEN_CYCLES DEP_CACHE
|
|
fi
|
|
|
|
# Emit dev metric (paginated to avoid silent cap at 50)
|
|
_BACKLOG_COUNT=$(codeberg_count_paginated "/issues?state=open&labels=backlog&type=issues")
|
|
_BLOCKED_COUNT=$(codeberg_count_paginated "/issues?state=open&labels=blocked&type=issues")
|
|
_PR_COUNT=$(codeberg_count_paginated "/pulls?state=open")
|
|
emit_metric "$(jq -nc \
|
|
--arg ts "$(date -u +%Y-%m-%dT%H:%MZ)" \
|
|
--arg proj "$proj_name" \
|
|
--argjson backlog "${_BACKLOG_COUNT:-0}" \
|
|
--argjson blocked "${_BLOCKED_COUNT:-0}" \
|
|
--argjson prs "${_PR_COUNT:-0}" \
|
|
'{ts:$ts,type:"dev",project:$proj,issues_in_backlog:$backlog,issues_blocked:$blocked,pr_open:$prs}' 2>/dev/null)" 2>/dev/null || true
|
|
|
|
# ===========================================================================
|
|
# P4-PROJECT: Clean stale worktrees for this project
|
|
# ===========================================================================
|
|
NOW_TS=$(date +%s)
|
|
for wt in /tmp/${PROJECT_NAME}-worktree-* /tmp/${PROJECT_NAME}-review-*; do
|
|
[ -d "$wt" ] || continue
|
|
WT_AGE_MIN=$(( (NOW_TS - $(stat -c %Y "$wt")) / 60 ))
|
|
if [ "$WT_AGE_MIN" -gt 120 ]; then
|
|
WT_BASE=$(basename "$wt")
|
|
if ! pgrep -f "$WT_BASE" >/dev/null 2>&1; then
|
|
git -C "$PROJECT_REPO_ROOT" worktree remove --force "$wt" 2>/dev/null && \
|
|
fixed "${proj_name}: Removed stale worktree: $wt (${WT_AGE_MIN}min old)" || true
|
|
fi
|
|
fi
|
|
done
|
|
git -C "$PROJECT_REPO_ROOT" worktree prune 2>/dev/null || true
|
|
}
|
|
|
|
# =============================================================================
|
|
# Iterate over all registered projects
|
|
# =============================================================================
|
|
status "checking projects"
|
|
|
|
PROJECT_COUNT=0
|
|
if [ -d "$PROJECTS_DIR" ]; then
|
|
for project_toml in "${PROJECTS_DIR}"/*.toml; do
|
|
[ -f "$project_toml" ] || continue
|
|
PROJECT_COUNT=$((PROJECT_COUNT + 1))
|
|
|
|
# Load project config (overrides CODEBERG_REPO, PROJECT_REPO_ROOT, etc.)
|
|
source "${FACTORY_ROOT}/lib/load-project.sh" "$project_toml"
|
|
|
|
check_project
|
|
done
|
|
fi
|
|
|
|
if [ "$PROJECT_COUNT" -eq 0 ]; then
|
|
# Fallback: no project TOML files, use .env config (backwards compatible)
|
|
flog "No projects/*.toml found, using .env defaults"
|
|
check_project
|
|
fi
|
|
|
|
# #############################################################################
|
|
# RESULT
|
|
# #############################################################################
|
|
|
|
ALL_ALERTS="${P0_ALERTS}${P1_ALERTS}${P2_ALERTS}${P3_ALERTS}${P4_ALERTS}"
|
|
|
|
if [ -n "$ALL_ALERTS" ]; then
|
|
ALERT_TEXT=$(echo -e "$ALL_ALERTS")
|
|
|
|
# Notify Matrix
|
|
matrix_send "supervisor" "⚠️ Supervisor alerts:
|
|
${ALERT_TEXT}" 2>/dev/null || true
|
|
|
|
flog "Invoking claude -p for alerts"
|
|
|
|
CLAUDE_PROMPT="$(cat "$PROMPT_FILE" 2>/dev/null || echo "You are a supervisor agent. Fix the issue below.")
|
|
|
|
## Current Alerts
|
|
${ALERT_TEXT}
|
|
|
|
## Auto-fixes already applied by bash
|
|
$(echo -e "${FIXES:-None}")
|
|
|
|
## System State
|
|
RAM: $(free -m | awk '/Mem:/{printf "avail=%sMB", $7}') $(free -m | awk '/Swap:/{printf "swap=%sMB", $3}')
|
|
Disk: $(df -h / | awk 'NR==2{printf "%s used of %s (%s)", $3, $2, $5}')
|
|
Docker: $(sudo docker ps --format '{{.Names}}' 2>/dev/null | wc -l) containers running
|
|
Claude procs: $(pgrep -f "claude" 2>/dev/null | wc -l)
|
|
|
|
$(if [ -n "$ESCALATION_REPLY" ]; then echo "
|
|
## Human Response to Previous Escalation
|
|
${ESCALATION_REPLY}
|
|
|
|
Act on this response."; fi)
|
|
|
|
Fix what you can. Escalate what you can't. Read the relevant best-practices file first."
|
|
|
|
CLAUDE_OUTPUT=$(timeout 300 claude -p --model sonnet --dangerously-skip-permissions \
|
|
"$CLAUDE_PROMPT" 2>&1) || true
|
|
flog "claude output: $(echo "$CLAUDE_OUTPUT" | tail -20)"
|
|
status "claude responded"
|
|
else
|
|
[ -n "$FIXES" ] && flog "Housekeeping: $(echo -e "$FIXES")"
|
|
status "all clear"
|
|
fi
|