Files
gstack/captain/templates/READY.md
T
Garry Tanandcapy-ai[bot] 4d48d39e51 v1.91.253.0 feat(captain): /captain skill (also /crew), crew templates and docs/captain.md for running a crew from one controller (#3473)
* feat(captain): /captain skill (also /crew), crew templates and docs/captain.md for running a crew from one controller

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* chore(captain): regenerate SKILL.md at main's version

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(captain): AGENTS.md and NOTES.md templates, roles, ship lane sequence, owner device and lessons loop in docs/captain.md; owner-brief closes with the do-it reply

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(captain): review pass 1: 'do it' parses as rec, READY template matches the tool's lines, slot-2 and freeze wording, mergeChangelogs named, parameter lists and doc numbers aligned

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* fix(captain): align the slot-call BASE merge, freeze repair and severe-race wording across skill, CREW.md and docs; router routes on phrases; receipt head width as printed

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

* feat(captain): CREW.md template becomes pointers plus parameters; every crew rule gets a canonical home in gstack (lane discipline, outside contributions, stale READYs, standing spend, the lane side of flaky reruns in docs/captain.md; the rule-to-home map)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>

---------

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
2026-10-26 18:04:22 +00:00

2.0 KiB

READY block

Sent by the lane: first the block exactly as gstack-ship-queue ready --pr <n> --no-screen|--screen prints it, then the lane's own lines. The controller validates every field before the pin enters train build. A missing or wrong field goes back to the lane, never into a train.

The tool's lines (shapes as printed; screen: is inserted as the second line under a train policy):

READY #<n> <sha40> STAMP_VERSION=unstamped
screen: <screen|no-screen> policy=<selection> nonce=<nonce> run=<run id or ->
pr: <PR url>
head: <sha40>
version: unstamped
base: origin/<BASE>@<base sha40>
ci: green at <sha12> (passed=<k> failed=0 pending=0 skipped=<s>)
PREGATE: pass tree=<tree12> head=<sha12> checks=<c>
gate: command=<"…"|none> full_e2e=<yes|no> gate-ahead=<…>
SHIP_RECEIPT: pr=<n> head=<sha12> version=- base=<BASE> tree=<tree> session_kind=unattended …
READY_RECEIPT: <path the tool wrote> (<local and notes-ref detail>)

The lane's own lines, after the block:

pin: <sha40>                      # the full head SHA, restated
screen choice: <--no-screen: cases <ids> ran focused and passed | --screen: <reason>>
flaky: <none | case, both run ids, logged in the ledger on <date>>
review passes: <n> (deferred: <items filed as issues, or none>)
Head frozen from now on; a push drops this PR from any train and I will READY again.

Optional lines a crew's rules file may require:

gate_run: <run id> tree=<tree12>        # when lanes gate on their own machines
closes: #<issue>
image: <URL of the key before/after image>

Refuse (send back) when: the SHA is short or a fork head; SHIP_RECEIPT reads none or invalid, or its head is not the pin; ci: is not green at the pin; PREGATE: is not pass for the pin's tree; --no-screen names no cases; a flaky case is not in the ledger; the PR page is "green" but no block was sent; the evidence offered is a cheap tier.

After the slot call the lane answers with the stamped head:

READY #<n> <stamped sha40> STAMP_VERSION=<X>