gstack/ship/DRIVER.md

/ship driver: run /ship from a parent agent

Read this instead of ship/SKILL.md when a parent agent on any host runs /ship (SESSION_KIND: unattended). Commands live in <root>/bin/ (<root> holds ship/); run each with the GSTACK_LAUNCH assignments your installer printed (. <the GSTACK_LAUNCH_FILE it printed>), never export $(...), env, printenv or a bare set in a tool fence.

Rules. Each phase below is one call: one program (Capy: an execute program; else a script) that runs the bins, reads, dispatches and waits, returning only result lines and reader outputs; print them verbatim. The model keeps only lead judgment, fixes, CHANGELOG and PR prose, the gates and the report. STOP: (exit 3) means nothing after it ran; NEXT: names the next act. Read a section only when a phase or the list at the end sends you, never up front. A STOP or decision this file does not cover: read ship/SKILL.md at that step, finish it there, come back. Unattended, a question with a recommended option takes it (log it); a gate disposition and every approval stay pending and end the run. Keep a private invocation record (the --record file): write its six headings at Phase 1, then fill each as its phase ends: Checks (Phases 2-4: lanes, pregate, evals, Coverage:, the plan checks, Scope Check:), Decisions (any phase: each answered or auto-taken question, in its words), Reviews (Phases 3-5: the plan line, start tokens, Pre-Landing Review:, Gate edits:, the reviewed tree), Release (Phases 5-7: version, CHANGELOG, commits), Documentation (Step 14.5) and Next steps (every phase: the next act).

Reviewers are the sections' own. Every audit, specialist, Red Team, QA, fix-check, adversarial, outside-voice and documentation brief, its severity and confidence rules and its gates come from its section verbatim, with only its placeholders filled; this file never shortens a reviewer's brief. A blocking reader's prompt is its gstack-review-dispatch render file, unchanged; its findings reach merged.jsonl only via collect; judge refuses a drop or downgrade. Audit readers (Steps 7, 8, 9.2.1, 14.5) cannot block, so each runs on a small model at low effort; their findings go to the PR body.

Calls. One pass with no fixes is 9 calls: Phases 1-8 and the report; at most 12 with a STOP's section read or a fix-check, plus a keep-alive per 200 s waited. A fix repeats Phases 3-4.

Budget: observe. gstack-ship-budget start --mode observe records, never admits: each program ends with gstack-ship-budget note --step <last step> --reading R --credits C --record <rec>, R and C read in that program (Capy: your jam's cost.tokens, cost.credits). No check per step, no reservation, no meter-only call, no handoff; under --token-cap a note past the cap prints verdict=stop, the one stop check. A dispatching program takes BEFORE (R and C) as its readers start and passes --dispatched-at <R> --dispatched-credits <C> --readers <n> with the reading after the last settles.

Waits. No call waits past 200 s: a program returns what still runs 200 s after its first line; the next call resumes the poll. Lanes, pregate and finish run in background. Never end the turn while readers run (each wakes it). A small waiting child saves nothing. Past 100 minutes, stop. Returns: ≤32 KB per program; split longer reads at headings, each byte once, before first use.

One program per pass. Each review pass, Step 11 and the Step 14.5 audit is one program, and the parent makes no other call while it runs: (1) gstack-review-dispatch pass: gstack-review-plan --base <base> with the pass's flags, then its staged manifest (Step 14.5 has one reader, docs); (2) gstack-review-log --start <skill> once per row the step logs (Step 14.5 takes none); (3) BEFORE; (4) sent (BRIEF_MISMATCH voids it), then one subagent per reader on its rendered file; (5) a poll until every reader settles (status done or failed, or a final summary; a fresh idle has not run); (6) note with the reading pair; a later batch (the Red Team, given the specialists' collected lines) repeats (3)-(6); (7) the collect: return only each reader's final output and status, via collect; it never walks the dispatch steps call by call.

1. Load: Step 0

The install check and this file.

2. Preflight, tests, evals and reads: Steps 0.9, 1, 2, 3, 4, 5, 6, 6.5, 10

gstack-ship-budget start --record <rec> --mode observe [--token-cap <n>] --reading R --credits C, then gstack-ship-preflight --base <base> --lane <label>=<command>... (the test commands AGENTS.md or CLAUDE.md names). CARRY: carried ends the run on its GSTACK_RESULT: line. A lane passes on tests_ran: N with exit 0; tests_ran: 0 is ZERO-RUN, a failed lane; unknown is count unavailable. In-branch failures stop the ship; after a repair rerun with --tests-only. requires-remote needs gstack-pregate clear before Step 18. When prompts, templates, judges or eval harness changed, start the eval selector and pre-merge command (detached past 30 min); else record evals: none affected. Steps 6.5 and 10 run only if gstack-greptile-early detect finds Greptile. Then gstack-ship-preflight --audit --base <base> --out <run dir> writes the diff once (CONTEXT:) and the TODOS.md items naming touched paths (TODOS:), and prints the coverage map, the plan candidates and READER: coverage=<needed|none> plan=<needed|none>. Programs read sections/review-army.md, sections/adversarial.md, sections/documentation.md, the todos and commits files, and sections/test-coverage.md or sections/plan-completion.md only when its reader is needed. Never read TODOS.md or the full diff into the parent. A PERSIST: hint never replaces Step 9.

3. Audits and review: Steps 7, 8, 9, 9.1, 9.2, 9.2.1

One program: the audit readers READER: names (Step 7 from sections/test-coverage.md, Step 8 from sections/plan-completion.md, each run as written; Step 7 may write tests, so it settles first), Step 9.2.1's QA reader (that step of sections/review-army.md as its brief) and the pass (above): Step 9's plan and start, Step 9.1's specialists and Step 9.2's Red Team as written. Coverage: and Step 8's line come from --audit when no reader ran.

4. Judgment: Steps 8.1, 8.2, 9.3, 9.4 and Step 11

Steps 8.1 and 8.2 (Scope Check:) on the todos and commits files, then the core checklist, Steps 9.3, 9.4 and the repeat decision as written (gstack-review-plan included; JUDGMENT: ok before any fix), fixes and persistence in one program. Prints Pre-Landing Review:, Gate edits:. NEXT: stop stops; full or scoped: one program runs the failing test, fix, --tests-only and Phase 3, each gated; done: the same program runs Step 11 from sections/adversarial.md as written (above), only the voices the last full-pass plan lists (neither prints ADVERSARIAL: skipped (review plan)).

5. Voices, bind and version: Steps 11, 11.5, 12

Judge the voices; missing outside coverage is unavailable, never clean; queued fixes rerun Phases 3-4. Then gstack-review-dispatch verify (VERIFY: clean) and gstack-review-read: the final Step 9 row and Step 11 native row (or CURRENT freshness after a planned skip) agree on wtree, start_wtree, end_wtree; save that reviewed tree. Then gstack-ship-release version --base <base> [--bump micro|patch] --why '<line>'; MINOR, MAJOR, BUMP_ANSWER_REQUIRED: approvals; VERSION: skipped|kept: no write.

6. Notes and documentation: Steps 13, 14, 14.5

Step 13: one user-facing entry from the commits file, where NEXT: says; gstack-prose-lint <it> --base origin/<base> --gate until PROSE_LINT: ok. Step 14: TODOS.md deferrals and completions, edited from the todos file. Step 14.5, every ship: read sections/documentation.md and run its audit as written, as one program (above), then gstack-ship-receipt docs-caps --base <base>; print Documentation:. One re-audit at most.

7. Release: Steps 15, 16, 17

Commit in bisectable chunks, then gstack-ship-release finish --base <base> --reviewed-tree <t> --docs-post <post> --lane ... [--build <cmd>] --trailer '<t>': ROUTE:, DOCS:, EVIDENCE: (FRESH; STALE or MISSING reruns once), PREGATE:; print them, the last Gate edits: and each tests_ran. Then gstack-ship-release push --branch <branch> [--gate-open <n>]: REDACT_PREPUSH:, SEALED:, PUSH: (pushed or ALREADY_PUSHED). Unattended, push defers the pre-push offer; else its STOP runs Step 17's guard block (HOOK_STATE:, HOOKS_IN_GIT_DIR:, PREPUSH_PROMPTED:). Never force-push.

8. Publish: Steps 18, 19, 19-C, 20, 21, 22

• Step 18: the open-PR lookup; a title file starting v<NEW_VERSION> . UNATTENDED_SHIP: with no open PR at HEAD takes Step 18-H.
• Step 19 body: the receipt block, then the sections sections/pr-body.md lists (Pre-Landing Review: REVIEW_LOOP:, Gate edits:, deferred, notes), led under CAPY_PR: on (Step 19-C) by What changed, Why, Blast radius and Approvals (gstack-approvals render). gstack-prose-lint <top> --sections 'Why,Summary,Blast radius' --gate; gstack-issue-links; gstack-review-scope summary --since "$REVIEW_SINCE" && gstack-ship-receipt write --pr <n> --base <base> --gate @<f> --pregate <f> --issues @<f> --review-loop @<f> --docs @<f> --body <body>; gstack-post pr-body and pr-title (a new PR via the host's PR tool; a draft while a gate finding is open). SHIP_RECEIPT: opens your report.
• Step 20: the ship metrics row via gstack-review-log.
• Step 22: gstack-ship-budget close --reading R --credits C (BUDGET_FINAL: and BUDGET_TIMELINE: carry tokens and credits; put both in the report), then gstack-ship-receipt result --pr <n>: GSTACK_RESULT: skill=ship status=complete run=<dir>. Under a merge queue, gstack-ship-queue ready --pr <n> [--screen|--no-screen] at the pushed head; paste its output.

Where each STOP sends you (paths under <root>/ship/)

• merge conflicts: SKILL.md#step-3-merge-the-base-branch-before-tests
• NEXT: carry route: SKILL.md#step-1-pre-flight
• DISTRIBUTION: candidates=: SKILL.md#step-2-distribution-pipeline-check
• APPLE: with a store ask: sections/apple-release.md#apple-app-store-release
• pregate fail or incomplete: sections/tests.md#step-5-run-tests-on-merged-code
• a failed or zero-run lane: sections/tests.md#test-failure-ownership-triage
• a red eval or a failed free-suite shard: sections/measure.md#measure-then-fix-loop-a-red-paid-eval-or-a-failed-free-suite-shard
• Greptile found: sections/greptile-early.md#step-65-early-greptile-pr-after-the-free-tests-pass
• coverage below target, a failed audit: sections/test-coverage.md#step-7-test-coverage-audit
• plan items NOT DONE or UNVERIFIABLE: sections/plan-completion.md#gate-logic
• NEXT: stop: sections/review-army.md#decide-whether-to-repeat-step-9
• a REVIEW_SCOPE_* refusal, the review-log row: sections/review-army.md#step-94-fix-first-and-persistence
• a required probe not passed: sections/review-army.md#step-921-exploratory-qa-before-fix-first
• native adversarial incomplete, queued fixes: sections/adversarial.md#finish-the-adversarial-phase
• Step 11.5 mismatch: SKILL.md#step-115-bind-the-reviews
• a version STOP: SKILL.md#step-12-version-bump-auto-decide
• Documentation: blocked or a DOCS_CAP: over: sections/documentation.md#blocked-recovery
• finish: changed since review: SKILL.md#2-choose-the-change-route
• finish: documentation inputs changed: SKILL.md#3-resolve-documentation-freshness
• finish: build, lane or pregate STOP: SKILL.md#4-verify-the-frozen-candidate
• a push STOP: SKILL.md#step-17-push
• unattended, no open PR at HEAD: sections/handoff.md#step-18-h-handoff-without-a-pr-automation-lanes
• a receipt write or gstack-post refusal: sections/pr-body.md#compose-the-body-then-publish-through-gstack-post
• verdict=stop or DELEGATE:: sections/budget-handoff.md#budget-and-context-handoff-read-when-a-cap-is-set-or-verdictdelegate-prints
• QUEUE_RECEIPT_STALE: ../docs/ship-policy.md#ship-before-ready