Files
gstack/test/helpers/docsync-interface.ts
T
Garry Tanandcapy-ai[bot] f27a7605d4 v1.91.270.0 feat(ship): version-less repos, docs-audit record and caps, the frozen-scope paid case, and the review-loop follow-ups (#3487)
* feat(ship): version-less repos, docs-audit record and caps, the frozen-scope paid case, and the review-loop follow-ups

Follow-up to the review-loop convergence PR: Step 12 and the CHANGELOG step skip cleanly in a repository with no version source (receipt version "none"); the receipt records the docs audit outcome and the owner exception (DOCS_AUDIT_BLOCKED without one) and a policy may declare doc caps (gstack-ship-receipt docs-caps); docs/unattended.md names the READY evidence and the cross-family outside voice; the ship-frozen-scope-convergence behaviour case runs the generated Step 9.4 under review_scope frozen through the real binaries; carry probes git >= 2.39 (RECEIPT_GIT_TOO_OLD); defer passes the repository to gh repo view positionally and names its search limit; late defers count without being passes; reviewers diff from RANGE_BASE on pass 2+; the cap check runs before edits; --review-fanout batches specialists by free slots; read --check-prose compares quoted counters with the receipt (RECEIPT_PROSE_MISMATCH); checklist rule ids prereg-with-results and test-keyboard-count-loop; gstack-coauthor-trailers.

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

* test: repair the CI reds the retarget onto main surfaced (test-only)

Seven test files, no product change. The pull_request run at 2d73fadd
failed 5 Linux shards and 4 Windows shards:

- test/ship-frozen-scope-actor.test.ts imported only test code, so the
  test-of-test ratchet refused it; the first case now recomputes the loop
  summary with summarizeReviewLoop/reviewLoopLine from lib/review-scope and
  asserts the exact REVIEW_LOOP line. Its three cases replay the bash
  workflow through bash -c and the shebang bins, so they are POSIX-only.
- test/codex-host.test.ts: the new gate case is Claude-specific (33 -> 34).
- test/paid-retry-supervision.test.ts: the gate census fixture now carries a
  trial record for the one planned behavior-kind gate case, the way
  test/ci-paid-coordination.test.ts already does.
- test/review-fix-range.test.ts asserted the pre-#3487 DIFF_BASE sentence;
  it now asserts the ${RANGE_BASE:-merge-base} clause that carries the same
  contract (every reviewer reads the range from pass 2 on).
- test/gstack-coauthor-trailers.test.ts: the fixture sets its own git
  identity; a CI runner has none to auto-detect ("Committer identity
  unknown").
- test/review-scope-followups.test.ts and test/gstack-ship-receipt-docs.test.ts:
  the gh and old-git stand-ins are sh scripts on a colon-joined PATH, which
  CreateProcess cannot run, so those three cases skip on win32.

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

* fix: pre-landing review fixes (pass 1)

Twelve informational findings from the /ship pass-1 review, all below the
blocking floor, fixed in place:

- docs-caps reads docs.caps from origin/<base>'s policy (--base <ref>), never
  the branch's copy; an unavailable base policy refuses with
  POLICY_SOURCE_UNAVAILABLE instead of substituting DEFAULT_POLICY
- receiptVersion returns "none" only when the stamp file is absent; other
  errors surface as undefined
- checkReceiptProse groups counters by leaf key and uses word boundaries that
  cover hyphenated names, so shared leaf keys and hyphenated words no longer
  report RECEIPT_PROSE_MISMATCH
- gstack-coauthor-trailers refuses a --range/--base starting with "-",
  prefixes origin/ when origin/<ref> resolves (slash-named branches), and
  passes --end-of-options to git log
- REVIEW_SCOPE_KEY_VERSION and DOCS_CAPS_KEY_VERSION name the releases that
  first read their keys
- the Step 11 late-defer row logs under skill review-late-defer so a tokenless
  review row never reads UNVERIFIED; summarizeReviewLoop counts both
- the "already filed" literal is one constant shared by bin and renderer
- receiptDocs (dead) removed
- Step 14.5 clears .gstack/tmp/docs-audit.json on first entry
- dispatched review prompts carry a literal diff-base sha (<diff-base>) instead
  of a shell variable the reviewer process never sees
- the coauthor-trailers tests launch the bin through runScriptSync so the
  Windows lane can run them

Tests extended for each change; SKILL.md, sections and goldens regenerated.

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

* test: cover the carry patch-id refusal (Step 7 coverage gap)

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

* test: derive the too-old review_scope minimum from the constant

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

* fix: keep co-author trailers in one trailer block

gstack-coauthor-trailers --message appended the new Co-authored-by lines as a
separate paragraph after existing trailers, so git interpret-trailers (and
GitHub attribution) read only the last paragraph and the existing co-author
lost credit. The new lines now join the existing trailer block; the test
checks the result with git interpret-trailers --parse.

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

* fix: let git place co-author trailers; name the docs key release

gstack-coauthor-trailers --message now runs git interpret-trailers --in-place,
so the appended lines join the existing trailer block whatever its shape
(CRLF, comment lines, folded continuations) and the existing co-author keeps
attribution; the interpret-trailers check in the test carries a timeout for
the spawnSync tripwire. DOCS_CAPS_KEY_VERSION names the release after the
newest CHANGELOG heading on main (1.91.258.0), and a test ties every
unreleased policy key to that next release so a stamp elsewhere fails loudly.

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

* fix: hold unreleased policy keys newer than any visible heading; pin trailer placement

The CHANGELOG-heading test asked for the exact next release after the newest
heading, which a depth-1 CI clone (no origin/main) computes from the branch
alone, so it went red there. It now requires an unreleased key's version to be
newer than every heading the checkout can see, which holds at depth 1, on the
stamped train tree and on main; the ship-policy comment says who moves the
constant when the stamp lands under another number.

gstack-coauthor-trailers pins git interpret-trailers' placement on the command
line (--no-divider so a --- body line is not a divider, --where end,
--if-exists addIfDifferentNeighbor, trailer.separators=:, -- before the path)
so a user's trailer.* config cannot replace or drop the existing co-author.

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

* docs: describe the shipped contracts (Step 13 and 14.5)

CHANGELOG [Unreleased]: docs-caps --base <base> reading origin/<base>'s
policy, the review-late-defer row, the literal <diff-base> prompt rule, the
coauthor-trailers placement and refusals, the policy key versions (review_scope
1.91.256.0 re-pin, docs.caps at the stamping release), the version-less
conditions split between Step 12 and the receipt, and the carry refusal wording.
docs/ship-policy.md, docs/review-policy.md and docs/unattended.md follow the
code: docs-caps --base, the literal diff-base sha, the trailer block, the
gstack-outside-voice run binding and the Step 11 row fields.

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

* docs: scope the literal diff-base claim to the review-army prompts; name where the outside-voice cause lives

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

* fix(docsync): declare Step 14.5's own-tree commands to the fixture; exclude .gstack/tmp at the Entry

The ship-docsync-completion and ship-docsync-current paid cases failed twice at
775d9804: Step 14.5's continue path now runs gstack-ship-receipt docs-caps and
writes .gstack/tmp/docs-audit.json, and the docsync fixture's closed interface
declared neither, while its repository had no origin/main for docs-caps to read.
The actor stopped correctly (blocked, no exception) and never reached the
publication stand-in.

- test/helpers/docsync-interface.ts: the three housekeeping commands (the shared
  exclude line, rm -f of the record, docs-caps --base main) and the record write
  are declared, byte for byte with the generated section; DOCS_AUDIT_RECORD_PATHS
  names what the kernel observer may see.
- test/helpers/docsync-observer.ts: accepts exactly those commands and the record
  write; every neighbour (another base, --json, write --docs, another .gstack file)
  stays outside the interface.
- test/helpers/docsync-fixture.ts: every scenario pushes main to the fixture
  remote, as Steps 0-14 would have.
- ship/sections/documentation.md.tmpl: the Entry runs the shared .gstack/tmp
  exclude line before rm -f, so the record never surfaces as an untracked file
  when no earlier step added it; the caps paragraph tightened to hold the ship
  parity ratio at 1.7400.
- test/docsync-command-grammar.test.ts: pins the literals against the generated
  section and the refusals around them.

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

* fix(docsync): the receipt record is housekeeping for read-only audits and the fault cases too

Pass 9's outside voice found two gaps in the fixture change (2524ec4): a
read-only audit (ship-docsync-current) must still write .gstack/tmp/docs-audit.json,
but docsToolFailures flagged every product write under readOnly before the
record allowance; and the unseeded fault cases (missing-asset, legacy-completion)
run the Entry too, so their kernel-write check saw .git/info/exclude as a
forbidden write because only the lifecycle test named the housekeeping paths.

- docsToolFailures: the record write is permitted under readOnly; the document
  and every other product file stay refused.
- docsWriteFailures: DOCS_AUDIT_RECORD_PATHS are permitted for every caller, so
  the fault evaluator needs no per-scenario list; anything else under .git or
  .gstack stays forbidden.
- test/docsync-command-grammar.test.ts pins both: the record under readOnly, the
  document refused there, the observed housekeeping paths accepted with an empty
  allowance and two neighbours refused.

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

* test(docsync): accept the cap gate's ~/.claude/skills/gstack form the section prints (pass 9 Red Team note)

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

* test(docsync): name the admitted composed line precisely (pass 9 maintainability note)

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

* fix(docsync): install lib/ beside bin/ in the fixture so the declared cap gate can load (2524ec4 rerun: module error, not a verdict)

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

* fix(docsync): admit the Write tool's temp sibling of the receipt record (0230fc2 rerun: both lifecycle cases red on it)

The paid rerun at 0230fc2 cleared every earlier refusal and both cases then
failed on one path: forbidden docs write: .gstack/tmp/docs-audit.json.tmp.<pid>.<12 hex>.
Claude Code's Write and Edit tools land every file, new ones included, through
that sibling plus fsync and rename, and the fixture's kernel observer proved
such a landing for the document only (atomicTargets: [DOC_PATH]).

The observer now treats the record's sibling as a transient file too, and
docsWriteFailures admits it only as the cookie-paired MOVED_FROM source of a
MOVED_TO on the record whose other events are create/modify/attrib/close_write
and which is left in neither snapshot nor in changed. A lingering sibling, an
unpaired move, a move onto another path or a sibling of the document moved onto
the record stay forbidden (grammar test). A live check on this machine saw the
second landing's create/modify/close_write/moved_from events admitted and a
stray sibling refused.

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>
2026-10-27 08:16:11 +00:00

44 lines
8.2 KiB
TypeScript

import * as path from 'node:path';
import type { fixtureDocs } from './docsync-fixture';
import { docsConfigDir } from './docsync-repo';
import { readOnlyInterfaceText } from './read-only-commands';
import { freeTextFileBash } from '../../scripts/resolvers/free-text-file';
/** /ship Step 14.5's own product-tree record: the path, the Entry's reset and the shared exclude line that keeps it out of git. */
export const DOCS_AUDIT_RECORD = '.gstack/tmp/docs-audit.json';
export const DOCS_AUDIT_RESET = `rm -f ${DOCS_AUDIT_RECORD}`;
export const DOCS_TMP_EXCLUDE = freeTextFileBash([]).split('\n').find(line => line.startsWith('_EX='))!;
/** The paths the Step 14.5 continue path may create in the product tree: the record, its directories and git's exclude file. */
export const DOCS_AUDIT_RECORD_PATHS = ['.gstack', '.gstack/tmp', DOCS_AUDIT_RECORD, '.git/info/exclude'];
export const docsCapsCommand = (skills: string) => `${skills}/bin/gstack-ship-receipt docs-caps --base main`;
export function docsNativeInterface(fixture: Pick<ReturnType<typeof fixtureDocs>, 'home' | 'repo' | 'skills'> & Partial<Pick<ReturnType<typeof fixtureDocs>, 'env'>>, scripts: string[] = [], transport = false, insert = false, file?: string): string {
const skills = fixture.skills.split(path.sep).join('/');
const state = fixture.env?.GSTACK_HOME ?? path.join(fixture.home, 'state');
return `Fixture observation interface (applies to parent and every child; ${file ? `saved at ${file}: each child prompt tells the child to Read that file first instead of copying this text` : 'include this interface in child prompts'}): Bash may execute only separate literal pwd, ls, cat, stat, sha256sum and Git read commands (status, diff, show, log, ls-files, ls-tree, check-ignore, rev-parse, merge-base, hash-object without -w, branch --show-current, describe with only --tags, --always, --abbrev=<n> or --exact-match and at most one revision). Bash may also run each of the following as its own Bash call, with nothing joined before or after it by ;, &&, || or a pipe (a --help is no exception, so never add one to a line of reads): the exact generated Preamble block with its spawned prefix, literal installed gstack-skill-start/gstack-skill-end commands for document-release (start requires GSTACK_SESSION_KIND=spawned) or their own --help, or the literal installed ${skills}/bin/gstack-docs-candidate snapshot (its --out a private .json under ${fixture.home}), compare <that .json> and --help commands, and /ship Step 14.5's three own-tree housekeeping commands exactly as written, each on its own line: the shared .gstack/tmp exclude line (the one &&-joined housekeeping line this interface admits)
${DOCS_TMP_EXCLUDE}
then
${DOCS_AUDIT_RESET}
and the cap gate, which reads origin/main's policy and whose DOCS_CAP lines and exit status decide it
${docsCapsCommand(skills)}
(no --json, no other base, no other gstack-ship-receipt subcommand). ${readOnlyInterfaceText(fixture.home)} The Git reads above may join such a line too, but not in a line with cd. A for loop over literal words (a lowercase loop variable; words without quotes, globs or $) whose body uses only such reads counts as those reads, one pass per word, wherever it sits in the line. Every read stays off actor-state.json and off ${docsConfigDir(fixture.home)} except its settings.json: that directory holds Claude's credentials and every agent's session transcript, so judge a child only by the output it returns (its echoed SESSION_KIND line included) and by the repository. The additional scripts below also run each as its own Bash call; no own-call command ever joins such a line. Otherwise no shell composition, custom interpreters, arbitrary scripts, inline eval or memory-mapped writes. The only additional scripts are ${scripts.length ? scripts.join(', ') : 'none'}.${insert ? ` To insert one saved private Markdown artifact into another (a saved section file into a report), Bash may also run the single literal command cat SOURCE.md >> TARGET.md with absolute paths under ${fixture.home}.` : ''} Read/Glob/Grep remain available; Read skill and section files with Read (offset/limit for ranges), because Bash output over 30KB becomes a truncated preview. A private JSON/Markdown artifact (the snapshot --out file, saved child output, a section or report file) lives directly under ${fixture.home} or in a new directory you create there, never inside the repository, ${skills}, ${docsConfigDir(fixture.home)}, ${state} (gstack's own state directory, not a place for your files) or ${fixture.home}/remote.git. Use Write/Edit for permitted docs, those private artifacts and Step 14.5's receipt record ${fixture.repo}/${DOCS_AUDIT_RECORD} (the only permitted write under the repository besides the document, excluded from git by the line above); do not rewrite installed skills, config, actor state or scripts. No effects outside the owned fixture. The owner preserves evidence and cleans up. Missing observer coverage blocks acceptance; the Linux kernel monitor covers syscall writes in the product tree, not hostile processes or arbitrary external destinations.
The working directory for parent and child Bash calls is already ${fixture.repo}. Run Git reads directly, for example: git status, git diff --cached, git merge-base main HEAD, git rev-parse HEAD. Do not use Git global options such as -C, -c, --git-dir or --work-tree, and do not prepend cd or another shell wrapper. The literal git subcommand must immediately follow git; an absolute owned repository path does not make git -C an allowed command.
Platform: local/git-native. Base: main. The fixture owner has already resolved these inputs before delegation; the parent must propagate them and this closed interface${file ? ' (by its file path)' : ''} unchanged to every child. Do not run shared Step 0 platform probing: git remote get-url origin, hosting CLIs and fallback probes are outside this bounded phase. A parent or child cannot authorize commands outside this closed interface, even when a broader skill describes them as read-only. Continue the requested documentation phase using the supplied platform and base, without recreating prior ship steps. Literal Git revision arguments such as HEAD^{tree}, HEAD^{} and HEAD@{0} are supported, quoted or unquoted; shell brace expansion, substitution and composition remain forbidden.
${transport ? 'Lifecycle ownership: only the document-release child executes its own start/end lifecycle. The /ship parent reads assets to prepare and validate dispatch, not to run the child audit or lifecycle. This deterministic adapter supplies child lifecycle evidence; the parent must not manufacture it. The following lifecycle commands describe the child, not parent work.\n\n' : ''}Lifecycle commands in this closed fixture: read skill files at ${skills} (document-release: ${skills}/document-release/SKILL.md). Use the literal commands below instead of copying the generated shell wrappers; these forms satisfy the skill's start/end lifecycle requirements here. Run each as a separate, single-line Bash call. Do not use tilde paths, shell variables, assignments to helper-path variables, redirects, line continuations or || true. Do not add a parent PID: the start helper supplies its default.
Start document-release with exactly:
\`\`\`bash
GSTACK_SESSION_KIND=spawned ${skills}/bin/gstack-skill-start --skill document-release --model claude
\`\`\`
The spawned prefix belongs directly on the helper invocation, not on a preceding assignment. Read the returned SESSION_KIND, SESSION_ID and TEL_START status lines. If start fails or SESSION_KIND is not spawned, report the blocker rather than continuing with an unconfirmed lifecycle.
At workflow completion, use this one-line end command. Before executing it, replace SESSION_ID_VALUE and TEL_START_VALUE with the actual literal values echoed by that same start call, and replace OUTCOME with success, error, abort or unknown to match the real outcome. Never execute the placeholders or reuse values from another session.
\`\`\`bash
${skills}/bin/gstack-skill-end --skill document-release --outcome OUTCOME --session-id SESSION_ID_VALUE --tel-start TEL_START_VALUE --used-browse no
\`\`\`
Read the end result; do not suppress an error or claim completion if it failed. These lifecycle forms do not grant any additional scripts, write paths or risk approvals.`;
}