recipe-maintainers/cc-ci-orchestrator
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Watchdog handoff signalling: ping the waiting loop on gate-claim / verdict (kill double-idle)

Browse Source 
launch.sh watchdog now runs a fast (~30s) handoff_check alongside the heavy (300s) restart/DONE
check: when the Builder writes a CLAIMED gate it pings the Adversary to verify now; when the
Adversary updates REVIEW.md it pings the Builder to proceed (edge-triggered, reads local clones).
So a pending handoff resolves in <~30s instead of a whole idle interval. Pacing revised: the
Adversary may idle freely when nothing's pending (no pointless re-verify/busy-poll) and is woken
by the watchdog; Builder waits on the ping + a fallback ~2-4m self-poll. kickoff documents the
new "handoff signalling" role.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
autonomic-bot
2026-05-27 06:15:25 +01:00
parent deca47d9c7
commit 239dfd8e26
5 changed files with 81 additions and 30 deletions
Download Patch File Download Diff File Expand all files Collapse all files

79
cc-ci-plan/launch.sh
View File

@ -44,7 +44,8 @@ LOG_DIR="${LOG_DIR:-/srv/cc-ci/.cc-ci-logs}"
CC_CI_REPO="${CC_CI_REPO:-https://git.autonomic.zone/recipe-maintainers/cc-ci.git}" # CI project repo (DONE detection); harmless until the Builder creates it
CC_CI_BRANCH="${CC_CI_BRANCH:-main}"
WATCH_INTERVAL="${WATCH_INTERVAL:-300}" # seconds between watchdog checks
WATCH_INTERVAL="${WATCH_INTERVAL:-300}" # seconds between HEAVY checks (restart dead loops, DONE)
SIGNAL_INTERVAL="${SIGNAL_INTERVAL:-30}" # seconds between HANDOFF checks (ping the waiting loop)
BUILDER_SESSION="cc-ci-builder"
ADV_SESSION="cc-ci-adv"
@ -108,26 +109,68 @@ is_done() {
grep -qE '^##[[:space:]]+DONE' "$WATCH_DIR/STATUS.md" 2>/dev/null
}
# Wake a loop by typing a one-line message into its tmux session (queues if mid-turn).
ping_session() {
local s="$1" msg="$2"
session_alive "$s" || return 0
tmux send-keys -t "$s" -l -- "$msg" 2>/dev/null && { sleep 0.3; tmux send-keys -t "$s" Enter 2>/dev/null; }
}
# Edge-triggered handoff signalling: the moment one loop produces the artifact the other is
# waiting on, ping the waiting loop so it wakes immediately instead of idling out its sleep.
# Reads the loops' local working clones (same host) for the fastest signal; the pinged loop
# still pulls the real state on wake. Edge-triggered (hash compare) so it pings once per change.
_wd_last_gate=""; _wd_last_review=""
handoff_check() {
local sf="$BUILDER_DIR/STATUS.md" rf="$ADV_DIR/REVIEW.md" cur
# Builder -> Adversary: a milestone gate is CLAIMED and awaiting verification.
if [[ -f "$sf" ]]; then
cur="$(grep -iE 'Gate:.*CLAIMED' "$sf" 2>/dev/null | sort -u | md5sum | awk '{print $1}')"
if grep -qiE 'Gate:.*CLAIMED' "$sf" 2>/dev/null && [[ "$cur" != "$_wd_last_gate" ]]; then
log "handoff: Builder CLAIMED a gate -> pinging Adversary"
ping_session "$ADV_SESSION" "watchdog ping: the Builder has CLAIMED a milestone gate in STATUS.md and is awaiting your verification. Pull and verify it now — don't idle."
fi
_wd_last_gate="$cur"
fi
# Adversary -> Builder: REVIEW.md changed (a verdict/PASS/FAIL or a new finding).
if [[ -f "$rf" ]]; then
cur="$(md5sum "$rf" 2>/dev/null | awk '{print $1}')"
if [[ -n "$cur" && "$cur" != "$_wd_last_review" ]]; then
[[ -n "$_wd_last_review" ]] && {
log "handoff: REVIEW.md changed -> pinging Builder"
ping_session "$BUILDER_SESSION" "watchdog ping: the Adversary updated REVIEW.md (a verdict or finding). Pull and act now — if it PASSes your gate, proceed; if it's a finding, address it. Don't idle."
}
_wd_last_review="$cur"
fi
fi
}
watchdog_loop() {
log "watchdog up (interval=${WATCH_INTERVAL}s, repo=${CC_CI_REPO:-<unset: DONE-detection disabled>})"
log "watchdog up (signal=${SIGNAL_INTERVAL}s, heavy=${WATCH_INTERVAL}s, repo=${CC_CI_REPO:-<unset: DONE-detection disabled>})"
local elapsed="$WATCH_INTERVAL" # run a heavy check on the first tick too
while true; do
# 1) DONE? then wind everything down.
if is_done; then
log "STATUS.md reports ## DONE — stopping loops."
stop_loops
log "watchdog exiting (project complete)."
exit 0
# Fast path every tick: ping a loop the moment its counterpart hands off.
handoff_check
# Heavy path every WATCH_INTERVAL: DONE detection + restart dead loops.
if (( elapsed >= WATCH_INTERVAL )); then
elapsed=0
if is_done; then
log "STATUS.md reports ## DONE — stopping loops."
stop_loops
log "watchdog exiting (project complete)."
exit 0
fi
if ! session_alive "$BUILDER_SESSION"; then
log "builder session gone — restarting"
start_agent "$BUILDER_SESSION" "$BUILDER_DIR" "$PLAN_DIR/prompts/builder.md"
fi
if ! session_alive "$ADV_SESSION"; then
log "adversary session gone — restarting"
start_agent "$ADV_SESSION" "$ADV_DIR" "$PLAN_DIR/prompts/adversary.md"
fi
fi
# 2) restart any dead loop (resilience the in-session /loop can't provide).
if ! session_alive "$BUILDER_SESSION"; then
log "builder session gone — restarting"
start_agent "$BUILDER_SESSION" "$BUILDER_DIR" "$PLAN_DIR/prompts/builder.md"
fi
if ! session_alive "$ADV_SESSION"; then
log "adversary session gone — restarting"
start_agent "$ADV_SESSION" "$ADV_DIR" "$PLAN_DIR/prompts/adversary.md"
fi
sleep "$WATCH_INTERVAL"
sleep "$SIGNAL_INTERVAL"
elapsed=$(( elapsed + SIGNAL_INTERVAL ))
done
}