gdkbox 0.1.20 → 0.1.21

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 6a5d8a8a1fbb33083f8cfb0b306ee0d6fc4efaffad04a110ef9f1a55141baae5
-  data.tar.gz: f4ec5a9b60bf6ab209ced26b1c0ec9c6b95503ae6a65484844506553055ea900
+  metadata.gz: ed8db8e33eb456eab81c33ec420fccbb86294d1569373da95d4eab9aebf1ee79
+  data.tar.gz: 23812d9d52938ddbdbd5613f412bdb5e35ed588ec177c5f1ad8acfbfa76fe214
 SHA512:
-  metadata.gz: 596f76ed57ea61c0fc0a00a7e0cd72a917a076aa9fcf022127d8b3ac7e5303c6ccb2c60e30c24727dcedb402f14065da1776be58832d1d28446b070850b09145
-  data.tar.gz: 1e4e94bc489cfc712b5e7a7386cad211e5cdf26b826eddeb43fa5e2bf47cacfde8c945677d896c5a21e97deef8dae99458133ebb4a3253a2530142c66404ff77
+  metadata.gz: 588e9c4a5beaa9f7ddcfd0cdfe3c897de80b230646a24b1c580bdb1cf008ec9aa86531d5f5a03d2234bf128918dd821f02dba7b41a79470b172d5607b2abd8c2
+  data.tar.gz: d1369eb4dadb712a8e2cacef481c55475e4239f447daad5ef952bdb956d5651ca13ac7fe80a29e8390ac609228514ed3bbcac3cf659f1c050bcc22ce8d679ca5

data/lib/gdkbox/version.rb

@@ -1,5 +1,5 @@
 # frozen_string_literal: true
 
 module GDKBox
-  VERSION = "0.1.20"
+  VERSION = "0.1.21"
 end

data/skills/gdkbox-fleet/SKILL.md

@@ -1,5 +1,6 @@
 ---
 name: gdkbox-fleet
+version: 1.0.0
 description: >-
   Orchestrate a fleet of GDK-in-a-box environments with the `gdkbox` CLI:
   provision a reusable pool of GitLab Development Kit boxes, then dispatch
@@ -190,8 +191,10 @@ can parse per task.
    ```
 
    When a dispatch returns, that box is idle again — assign it the next task
-   from the queue. Never run two dispatches against the same box at once,
-   and never dispatch into a box whose `claimed_by` is not your owner id.
+   from the queue, or **stop it immediately if nothing is queued for it**
+   (`gdkbox stop <box>`; see the "never leave a box running idle" guardrail).
+   Never run two dispatches against the same box at once, and never dispatch
+   into a box whose `claimed_by` is not your owner id.
 
    **Delegating to subagents:** the renewal in `run_task` above is for when
    *you* run the loop. If you hand a task to a subagent instead, do the
@@ -214,14 +217,20 @@ can parse per task.
    and summarize per task: success/failure (exit status), what the agent did,
    and any follow-ups. Surface failures explicitly.
 
-6. **Wind down — release every box you claimed.** When the batch is done,
-   release **all** your boxes so the pool is usable by others (a lease would
-   expire eventually, but do not rely on it for normal completion). Then keep
-   them warm (`gdkbox stop`, later `gdkbox start`) or `gdkbox rm --force` to
-   discard:
+6. **Stop idle boxes as you go; release everything at wind-down.** A box with
+   no task running right now must not be left running — `gdkbox stop <box>`
+   it the moment it goes idle (stopping keeps the claim, license and seeded
+   data; `gdkbox start <box>` brings it straight back). Do this throughout the
+   batch, not only at the end — especially whenever you pause to wait on the
+   user, on a review, or on another box. See the guardrail below.
+
+   When the **whole batch is done**, stop every box, then release **all** of
+   them so the pool is usable by others (a lease would expire eventually, but
+   do not rely on it for normal completion), or `gdkbox rm --force` to discard:
 
    ```sh
    for b in $(gdkbox ls --json | jq -r ".[] | select(.claimed_by==\"$OWNER\") | .name"); do
+     gdkbox stop "$b"                      # no box left running once its work is done
      gdkbox release "$b" --owner "$OWNER"
    done
    ```
@@ -245,7 +254,8 @@ for i in 1 2 3; do
   gdkbox dispatch "pool-$i" --task-file "tasks/$i.md" --json > "out/$i.json" 2>&1 &
 done
 wait
-for i in 1 2 3; do gdkbox release "pool-$i" --owner "$OWNER"; done
+# batch done: stop each box so none is left running, then release the pool
+for i in 1 2 3; do gdkbox stop "pool-$i"; gdkbox release "pool-$i" --owner "$OWNER"; done
 ```
 
 Adopt one more existing free box when the queue outgrows the pool (each call
@@ -303,6 +313,15 @@ rest of the pool accordingly, and give the claim a generous `--ttl`.
   heavy. Prefer reusing the pool over creating more boxes.
 - **One dispatch per box at a time.** Serialize tasks on a box; parallelize
   *across* boxes.
+- **Never leave a box running idle.** A box is expensive (a full GDK
+  container); it must be running *only* while a dispatch is actually using it.
+  The moment a box has no task queued for it — including whenever the
+  orchestration pauses to wait on the user, on a review, or on another box —
+  `gdkbox stop <box>` it. Stopping frees the host's memory and CPU but **keeps
+  the claim, license and seeded data**, so `gdkbox start <box>` resumes it in
+  seconds. Keep the claim while the box is yours and only *release* at session
+  wind-down; stopping is for idleness, releasing is for "done with it". If you
+  stopped boxes mid-session, `gdkbox start` them again before dispatching.
 - **Own every box you touch, for the whole batch.** Provision with
   `up --owner`, adopt with `claim`, and hold the claims until wind-down —
   then release them all. Claims are advisory: `dispatch` will not stop you

metadata

@@ -1,7 +1,7 @@
 --- !ruby/object:Gem::Specification
 name: gdkbox
 version: !ruby/object:Gem::Version
-  version: 0.1.20
+  version: 0.1.21
 platform: ruby
 authors:
 - jotolo