Files
gstack/test/ship-document-release-dispatch.test.ts
T
Garry TanandClaude Fable 5 a3749bfa4b v1.70.1.0 fix: ship names the /document-release subagent at every decision point (tripwire + gate E2E) (#2700)
* fix(ship): name the /document-release subagent at every Step 18 decision point

The v1.54.0.0 carve moved Step 18 (documentation sync) into
ship/sections/pr-body.md and the Claude-host skeleton stopped saying
"document-release" anywhere in the workflow body — the dispatch became
invisible at exactly the moments an agent decides whether to open the
section. Restore visibility at three touchpoints, all subagent-framed
(never bare-slash-framed, which would invite an inline Skill invocation
that bypasses the fresh-context subagent + JSON contract):

- manifest trigger (renders into the section-index row AND the STOP
  pointer): "dispatching the /document-release subagent to sync docs
  (Step 18) and then creating or updating the PR/MR (Step 19)"
- Step 17 handoff line names Step 18's dispatch explicitly
- new hoisted doc-sync invariant beside the PR-title invariant: the
  dispatch itself is never skipped; only a failed subagent is
  non-blocking

Pin it in carve-guards: 'the /document-release subagent' (all three
touchpoints) + 'dispatches the /document-release subagent' (invariant)
must stay in the skeleton; the carved imperative 'Dispatch
/document-release as a subagent' must stay carved. Skeleton cap
91,600 → 92,300 (measured 91,764; trigger renders twice). Goldens
regenerated for all three hosts.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* test: pin the ship→document-release Step 18 wiring with a free tripwire

Five substring/structure asserts across the carved section, the Claude
skeleton's three touchpoints, the manifest trigger, and the codex/factory
goldens (inlined Step 18 ordered before Step 19). Claude-golden asserts
deliberately omitted: host-config.test.ts already enforces golden ==
generated byte-for-byte.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* test: gate-tier E2E proving /ship dispatches the document-release subagent

New skill-e2e-ship-docsync: a live agent gets the sliced Step 17→19 tail
of the generated ship skeleton in a bare-remote git fixture (Steps 0-16
"done"), under a fake HOME so the STOP pointer and the Step 18 subagent
prompt resolve to planted copies, with a stub document-release skill that
returns the empty-result JSON contract. Hard assert: an Agent/Task
tool-call matching /document-release/i exists in result.toolCalls and
precedes any `gh pr create`. Neutral prompt (no STOP-Read priming, no
document-release mention — the prompt echoes into the transcript, so
asserts read toolCalls only).

Hardening from review: throw-on-marker-drift fixture slice; per-test
GSTACK_HOME + .redact-prepush-prompted marker (routes Step 17's
credential guard to its silent branch — the hermetic GSTACK_HOME pin
defeats a HOME-only override); 480s/540s timeouts (nested subagent adds
wall clock the 300s sibling never carried); 'timeout' accepted in
exitReason only because the dispatch assert is independently hard;
whole-file describeE2ETier('gate') composed with diff selection (keeps
the file out of the periodic shard census, which sits at its ceiling,
and under the hard tier-alignment invariant).

Registered as 'ship-docsync' in E2E_TOUCHFILES + E2E_TIERS (gate) in the
same commit — touchfiles.test.ts rejects either half landing first.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: fix stale document-release TODOS entry + three review-deferred items

The SHIPPED entry still described the deleted Step 8.5 post-PR cat-delegation
design from v0.8.4; replace with the current Step 18 subagent design and its
test pins. Add the three P3 items deferred from the v1.69 plan review:
dispatch receipt enforcement, land-and-deploy→canary dispatch-pin pattern,
and the periodic shard-census boundary.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix: pre-landing review fixes

Testing-specialist findings, all mechanical: (1) pin the E2E fixture's git
branch (-b main / init.defaultBranch=main) and assert every setup command's
exit status so operator git config can't silently corrupt a paid run;
(2) tighten the dispatch matcher to Step 18-prompt-specific markers
(document-release/SKILL.md | executing the /document-release workflow) so a
subagent merely quoting section text can't false-pass the regression assert
(verified against recorded burn-in transcripts); (3) replace the subsumed
carve-guards anchor with three non-overlapping per-touchpoint anchors
(gerund/imperative/3rd-person) so each touchpoint is independently enforced.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix: red-team review fixes

Five informational findings: TODOS shard-census arithmetic corrected (census
is 67 with one free ungated slot; the SECOND ungated file trips the floor)
and version pointer fixed (v0.18.2.0, not v0.18.1.0); the free tripwire now
pins the two dispatch-matcher marker strings so a pr-body prompt reword
fails the free suite instead of surfacing as a paid-tier mystery; the E2E
matcher gains a section-paste exclusion (scaffold strings disqualify) —
verified against all recorded runs; the E2E header documents the tierless
test:evals invisibility tradeoff.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix: adversarial review fixes

Pin the E2E matcher's two EXCLUSION markers in the free tripwire (an
unpinned 'Parent processing:' reword would silently deaden the
section-paste guard while every test stayed green); add an ordering pin
(the hoisted doc-sync invariant must sit above the pr-body STOP pointer —
presence-only anchors can't catch drift below it); plant a third
cwd-relative pr-body copy inside the fixture repo, gitignored so the agent
never tries to commit test scaffolding.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* chore: bump version and changelog (v1.70.1.0)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: CHANGELOG accuracy fixes from the doc-release review

Three factual corrections the Step 18 doc subagent caught in the fresh
v1.70.1.0 entry: 5 tripwire tests (not 6), cost floor $0.63 per the cited
eval store (not $0.59), and the visibility claim scoped to decision points
(the re-run checklist mention survived the carve). Plus the E2E header's
stale pending-burn-in note replaced with the observed numbers.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix: raise bun-polyfill subprocess budget to 60s for degraded Windows runners

The 50ms-sleep test blew the 20s budget on BOTH bun retry attempts on PR
#2700's windows-latest runner (run 32989821401) — sustained AV/runner
pressure, not just the documented cold-start. Same flake passed-on-rerun on
the prompt-token-load-reduction branch yesterday. Budget only; every
assertion still checks exact output.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ci): run the ship-docsync gate E2E in the evals matrix + silent-skip tripwire

The evals.yml matrix is hand-enumerated and the Run step never exported
EVALS_TIER, so the new whole-file-gated ship-docsync E2E would have
self-skipped even with a row — a hollow green one layer deeper than the
documented rehomed-monolith incident. Add the e2e-ship-docsync row with a
row-level `tier: gate` property, exported as EVALS_TIER by the Run step
(empty = unset for every existing row: all readers are `=== '<tier>'` or
truthiness).

New free tripwire test/evals-workflow-matrix.test.ts ratchets the class:
matrix files must exist; gate-hosting files must have a row; whole-file-gated
matrix files must carry a matching row tier; and the burn-down lists enforce
their own cleanup. It enumerates the PRE-EXISTING holes found while wiring
this (8 gate-hosting files with no row; codex/gemini rows running zero tests;
the pty-plan-smoke row hollow since its files adopted describeE2ETier) —
tracked in TODOS as the CI gate-lane hollow-coverage burn-down.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-27 08:46:41 -07:00

136 lines
6.2 KiB
TypeScript

/**
* /ship → /document-release Step 18 dispatch stays wired AND visible.
*
* The v1.54.0.0 carve (46c1fae7) moved Step 18 (documentation sync) out of
* the ship skeleton into sections/pr-body.md. The wiring survived, but on
* the Claude host the skeleton stopped saying "document-release" anywhere
* in the workflow body — the dispatch became invisible at the decision
* points and "the idea of running document-release as part of ship got
* lost". This tripwire pins both halves so neither can silently regress:
*
* - the carved section keeps the full dispatch contract (imperative,
* subagent_type, JSON return keys, non-blocking failure), and
* - the Claude skeleton names "the /document-release subagent" at its
* three touchpoints (manifest trigger via section-index + STOP pointer,
* Step 17 handoff, hoisted doc-sync invariant) while the imperative
* itself stays carved.
*
* Structural backstop lives in test/helpers/carve-guards.ts (ship entry);
* this named test documents the regression story. Behavioral proof is the
* ship-docsync E2E (test/skill-e2e-ship-docsync.test.ts).
*/
import { describe, test, expect } from 'bun:test';
import * as fs from 'fs';
import * as path from 'path';
const ROOT = path.join(import.meta.dir, '..');
const SECTION_SITES = [
path.join(ROOT, 'ship', 'sections', 'pr-body.md'),
path.join(ROOT, 'ship', 'sections', 'pr-body.md.tmpl'),
];
// ship/SKILL.md only — NOT the claude golden: test/host-config.test.ts
// already enforces golden == generated byte-for-byte, so substring asserts
// on the golden would be pure duplication. The codex/factory goldens ARE
// asserted below because for them the check is content (the inlined
// section survived generation), which byte-equality alone doesn't prove.
const CLAUDE_SKELETON = path.join(ROOT, 'ship', 'SKILL.md');
const INLINED_GOLDENS = [
path.join(ROOT, 'test', 'fixtures', 'golden', 'codex-ship-SKILL.md'),
path.join(ROOT, 'test', 'fixtures', 'golden', 'factory-ship-SKILL.md'),
];
const CARVED_IMPERATIVE = 'Dispatch /document-release as a subagent';
describe('/ship Step 18 dispatches /document-release (carve visibility)', () => {
test('carved section carries the full dispatch contract', () => {
for (const file of SECTION_SITES) {
const content = fs.readFileSync(file, 'utf-8');
expect(content).toContain(
'## Step 18: Documentation sync (via subagent, before PR creation)'
);
expect(content).toContain(CARVED_IMPERATIVE);
expect(content).toContain('subagent_type: "general-purpose"');
// The JSON return contract Step 19 bakes into the PR body.
expect(content).toContain('"files_updated"');
expect(content).toContain('"commit_sha"');
expect(content).toContain('"pushed"');
expect(content).toContain('"documentation_section"');
// Deliberate design: docs sync never holds a ship hostage.
expect(content).toContain('Do not block /ship on subagent failure');
// These four strings are the ship-docsync E2E's dispatch-matcher markers
// (test/skill-e2e-ship-docsync.test.ts): the first two are INCLUSION
// markers (verbatim from the dictated Step 18 subagent prompt); the last
// two are EXCLUSION markers (section scaffolding that disqualifies a
// whole-section paste). Rewording any of them in pr-body.md.tmpl silently
// deadens the paid matcher; update all four in lockstep.
expect(content).toContain('You are executing the /document-release workflow');
expect(content).toContain('.claude/skills/gstack/document-release/SKILL.md');
expect(content).toContain('## Step 19: Create PR/MR');
expect(content).toContain('Parent processing:');
}
});
test('claude skeleton names the subagent at all three touchpoints', () => {
const content = fs.readFileSync(CLAUDE_SKELETON, 'utf-8');
// Manifest trigger — renders into the section-index row AND the STOP
// pointer, so it must appear at least twice.
const trigger =
'dispatching the /document-release subagent to sync docs (Step 18) and then creating or updating the PR/MR (Step 19)';
expect(content.split(trigger).length - 1).toBeGreaterThanOrEqual(2);
// Step 17 handoff.
expect(content).toContain(
'Step 18 (dispatch the /document-release subagent to sync docs)'
);
// Hoisted doc-sync invariant (beside the PR-title invariant).
expect(content).toContain('**Doc-sync invariant');
expect(content).toContain('dispatches the /document-release subagent');
// The STOP-Read pointer still routes to the carved section.
expect(content).toMatch(
/> \*\*STOP\.\*\*[^\n]*Read `[^`]*ship\/sections\/pr-body\.md`/
);
// Ordering pin: the hoisted invariant must sit ABOVE the pr-body STOP
// pointer (mustStayInSkeleton asserts presence only — a future edit could
// drift the paragraph below the STOP with every registry check green).
const invariantIdx = content.indexOf('**Doc-sync invariant');
const stopIdx = content.indexOf(
'> **STOP.** Before dispatching the /document-release subagent'
);
expect(invariantIdx).toBeGreaterThan(-1);
expect(stopIdx).toBeGreaterThan(invariantIdx);
});
test('the dispatch imperative stays carved out of the claude skeleton', () => {
const content = fs.readFileSync(CLAUDE_SKELETON, 'utf-8');
expect(content).not.toContain(CARVED_IMPERATIVE);
});
test('manifest trigger names the subagent', () => {
const manifest = JSON.parse(
fs.readFileSync(
path.join(ROOT, 'ship', 'sections', 'manifest.json'),
'utf-8'
)
);
const prBody = manifest.sections.find(
(s: { id: string }) => s.id === 'pr-body'
);
expect(prBody).toBeDefined();
expect(prBody.trigger).toContain('the /document-release subagent');
});
test('codex + factory goldens inline Step 18 before Step 19', () => {
for (const file of INLINED_GOLDENS) {
const content = fs.readFileSync(file, 'utf-8');
const step18 = content.indexOf(
'## Step 18: Documentation sync (via subagent, before PR creation)'
);
const step19 = content.indexOf('## Step 19: Create PR/MR');
expect(step18).toBeGreaterThan(-1);
expect(step19).toBeGreaterThan(step18);
expect(content).toContain(CARVED_IMPERATIVE);
}
});
});