johba/disinto
1
0
Fork 0
Code Issues 4 Pull requests Projects Releases Packages Wiki Activity Actions

feat: add Matrix coordination channel, replace openclaw (Closes #8)

Browse source 
Add matrix_send() to lib/env.sh and matrix_listener.sh daemon for
real-time notifications, threaded escalations, and human-in-the-loop
replies. All agents now notify via Matrix instead of openclaw.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
johba 2026-03-14 16:25:33 +01:00
parent 90ef03a304
commit f215fbe3cf
11 changed files with 266 additions and 23 deletions
Download patch file Download diff file Expand all files Collapse all files

24
factory/factory-poll.sh
View file

@ -36,6 +36,14 @@ status() {
flog "$*"
}
# ── Check for escalation replies from Matrix ──────────────────────────────
ESCALATION_REPLY=""
if [ -s /tmp/factory-escalation-reply ]; then
ESCALATION_REPLY=$(cat /tmp/factory-escalation-reply)
rm -f /tmp/factory-escalation-reply
flog "Got escalation reply: $(echo "$ESCALATION_REPLY" | head -1)"
fi
# Alerts by priority
P0_ALERTS=""
P1_ALERTS=""
@ -154,10 +162,10 @@ fi
status "P2: checking factory"
# 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)
[ "${STUCK_CI:-0}" -gt 0 ] && p2 "CI: ${STUCK_CI} pipeline(s) running >20min"
STUCK_CI=$(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 "CI: ${STUCK_CI} pipeline(s) running >20min"
PENDING_CI=$(wpdb -c "SELECT count(*) FROM pipelines WHERE repo_id=${WOODPECKER_REPO_ID} AND status='pending' AND EXTRACT(EPOCH FROM now() - to_timestamp(created)) > 1800;" 2>/dev/null | xargs)
PENDING_CI=$(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 "CI: ${PENDING_CI} pipeline(s) pending >30min"
# Dev-agent health
@ -304,6 +312,10 @@ ALL_ALERTS="${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" "⚠️ Factory 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 factory supervisor. Fix the issue below.")
@ -320,6 +332,12 @@ 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 \