watch.py admits heavy work only while PSI, swap-out rate and RAM forecast stay under the configured limits; config.default.json is the single default the install writes once (mode 600, no clobber) and every hook, admit and queue command falls back to. Browser runners and package-manager script forms count as heavy, preflight derives its probes from the light and heavy tool lists, and the shipped default carries no prune command, buildx path or host-specific key. Tests run once on unify/skills-20261114 after the merge (operator order 2026-11-14). 🎯 Fix: 85 % 💥 Break: 8 % 💸 Tokens: 99 % ⏱️ Velocity: – 🛡️ Security: 100 % 🏆 Score: 79 🚦 Gate: ⛔ fix 85 % < 90, break 8 % > 5 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
3.4 KiB
name, description
| name | description |
|---|---|
| kvb-org-queue | Queue every heavy job (gate, deploy, build, swarm), never ask the chair: hotfix first, then rank. |
${CLAUDE_SKILL_DIR}/scripts/queue.py replaces asking the chair for heavy
slots with one queue that every waiting agent evaluates by the same rules.
Run a heavy job
queue.py hold --kind <kind> --task <register task> -- <command>
Start it in the background (run_in_background or equivalent) and end the
turn: hold runs the command on its grant and exits with its code.
<kind>: a key ofslot_need_gbin~/.claude/agents-council/config.json.<register task>: your openkvb-org-rascitask; its rank places you.--hotfix <slug>: the job proves the register rowhotfix/<slug>(kvb-git-hotfix) and goes first.--need-gb <N>overrides the learned disk need.- Start hold in the job's worktree: its git toplevel is the workdir. Other
runtimes add
--session <id>. - In a worktree the command stays
gate.py run|hold(kvb-check-gate):queue.py hold ... -- python3 <gate.py> run ....
Light runs (kvb-org-organize Capacity) self-admit; anything else goes
through hold with kind test, and a light kind refuses it.
Order and grant
Every 20 s each waiting hold evaluates the queue under one lock:
- Hotfix jobs first, then the register rank (
rasci.py show), one place earlier per whole hour waited, then arrival; an openaftertask holds a job. - In that order, a job is blocked at disk stage stop or critical, at warn
when it needs disk, at memory stage stop, during a radio-silence mayday,
while its kind's slots are taken, or while its workdir runs another job;
exclusive_kindsrun only besidelight_kinds. - A job whose disk need would cut below the stop threshold, or whose
footprint would push the running ones past
budget_percent, reserves it against the jobs behind it butlight_kinds, which meet only running and granted jobs, so a stream of light jobs can delay a heavy head; a job alone always fits. - An unblocked job counts as granted for the jobs behind it.
- Every job, alone too, needs CPU, and RAM used plus what it and the
running jobs may still take, below
load_limits.
History and learning
Every finished job appends a row to queue-history.jsonl, from which disk
need, slot limits and footprints are learned; read learning.md next to this
file before changing a seed or a limit.
Inspect and cancel
queue.py list
queue.py history
queue.py cancel <id>
list shows each job's position, ETA and blocking reason, history the
learned values, cancel removes your own waiting job.
Rules
- Never ask the chair for a heavy slot or announce a grant; the chair handles
only exceptions such as a stuck queue or a hung job (
capacity.mdofkvb-org-organize). - A running job is never cut short for the queue; only the operator orders
one down, and
kvb-git-hotfixmay void a gate. Akvb-org-queue-cleanupround deletes only entries whose lock no living process holds. - With
queue_enforce: true, theblockhook (PreToolUse on Bash) refusesheavy_commands, image builds,make install|test*|quality*|verify-*, tests beyond one unit file andgate.py run|holdoutsidequeue.py hold. - Without the config, hold exits 2: tell the operator and ask the chair
(
kvb-org-organize) until it exists. A waiting hold rereads it every poll (a broken file keeps the last good one), so a limit change needs no re-hold.