mirror of
https://github.com/garrytan/gstack.git
synced 2026-06-01 15:51:41 +02:00
46c1fae7f1
* feat(test): transcript-section-logger + ship-action fingerprint (T10) Pure-analysis module over a SkillTestResult/NDJSON transcript: - extractSectionReads(): which sections/*.md a run opened (post-carve check) - extractShipActions(): observable action fingerprint (merge/test/bump/ changelog/commit/push/pr) that works on the MONOLITH too, so a baseline captured before the carve can detect a sectioned-ship regression - baseline read/write + compareShipActions() for baseline-first dogf(T10) Baseline-first answers the Codex outside-voice critique that a logger in the same PR as the carve is post-failure telemetry without a pre-carve reference. 11 unit tests, all green. Paid monolith baseline capture runs separately. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(pipeline): section discovery + generation machinery (T9) - discover-skills.ts: discoverSectionTemplates() scans <skill>/sections/*.md.tmpl - gen-skill-docs.ts: extract resolvePlaceholders + applyHostRewrites + buildContext as shared helpers (processTemplate and the new processSectionTemplate both call them, so a sanitization/rewrite fix can't miss sections) [C1] - processSectionTemplate: body-fragment generation (no frontmatter/catalog/voice), parent-skill TemplateContext (skillName pinned to parent, not 'sections', so appliesTo gating + tier behave identically), per-host output routing - --host all now fails the build on ANY host failure, not just claude, so a stale external-host output can't slip the freshness gate [Codex outside-voice #9] Inert until a skill is carved (no sections/ dirs exist yet). Refactor is output-neutral: gen:skill-docs --dry-run --host all reports 0 STALE. 5 discovery unit tests + 389 gen-skill-docs tests green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(setup): install sections/ for cherry-pick targets (claude + kiro) (T9) Two install targets cherry-pick SKILL.md and would leave a carved skill's sections/ behind, 404ing a runtime 'Read sections/<name>.md': - link_claude_skill_dirs: link the sections/ subdir via _link_or_copy (windows gets a fresh copy on every ./setup) - kiro per-skill loop: sed-rewrite + copy each sections/* so paths resolve under ~/.kiro, not ~/.codex/~/.claude codex/factory/opencode link the whole generated dir, so sections ride free. Addresses Codex outside-voice #4/#6 (runtime pathing landmine). Inert until a skill is carved. Static-tripwire test + windows-fallback invariant green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * feat(ship): gstack-version-bump CLI — tested idempotency classify + write (T9) Hybrid CLI extraction (CM1): the deterministic core of ship Step 12 becomes a tested CLI instead of bash prose the agent re-derives each run. - classify: FRESH/ALREADY_BUMPED/DRIFT_STALE_PKG/DRIFT_UNEXPECTED from VERSION vs origin/<base>:VERSION vs package.json.version (pure reader) - write: validated dual-write to VERSION + package.json (FRESH bump) - repair: DRIFT_STALE_PKG sync, no re-bump Bump-LEVEL choice + queue collision stay agent judgment; slot pick stays bin/gstack-next-version. This removes the re-bump-a-shipped-branch footgun from skippable prose into code that can't be skipped or misread. 15 tests (exhaustive state matrix + write/repair fs + real-git classify). Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(parity): sectioned-skill parity capability — guards the carve (T9) Carved skills (skeleton + sections/*.md) need parity checks that see relocated content, or moving a phrase into a section reads as 'lost': - readSkillForParity(): union skeleton + all sections/*.md - checkSkillParity sectioned mode: content checks against the union; minBytes/ maxSizeRatio against union bytes (total behavior preserved); maxSkeletonBytes asserts the always-loaded skeleton actually shrank. Lowering minBytes to fit a small skeleton would otherwise make the size floor toothless [Codex #12]. Built + tested BEFORE the carve so ship's invariant can flip to sectioned in the same commit it lands. Monolith path byte-identical (verified: pre-existing investigate 1.053 ratio drift fails the same with this change stashed). 7 sectioned-parity tests + existing parity tests green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * refactor(ship): carve into skeleton + on-demand sections (Claude) (T9) ship/SKILL.md drops 167KB → 68.7KB (~59% of the always-loaded skill) by moving 8 prose-heavy steps into ship/sections/*.md, read on demand: tests, test-coverage, plan-completion, review-army, greptile, adversarial, changelog, pr-body. Step 12's version logic now calls the tested gstack-version-bump CLI instead of inline bash. Claude-first (S2): {{SECTION:id}} emits a STOP-Read pointer on Claude (skeleton + generated section files) and INLINES the content on every other host, so external hosts keep the full monolith — verified factory at 162KB with no sections dir. {{SECTION_INDEX:ship}} renders the situation→section table from the PASSIVE manifest (CM2 / v2_PLAN.md:663); required-reads live only in test fixtures. Multi-pass resolve expands inlined sections' own resolvers. Parity: ship invariant flipped to sectioned (union content checks + maxSkeletonBytes asserts the shrink). Carve-fallout fixed across gen-skill-docs/skill-validation/ golden/plan-completion/#1539/size-budget tests via skeleton+sections union reads. Free suite green except the pre-existing investigate parity drift. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(ship): manifest-consistency + context-parity + requiredReads helper (T9) Free deterministic guards for the carve: - required-reads.ts + unit test: assertRequiredReads(run, requiredFiles) — the mechanical layer-5 check that the agent Read the sections its situation needs (required set comes from the fixture, not the passive manifest) - section-manifest-consistency: 3-tier orphan classification (generated orphan + hand-edited generated file → FAIL; manifest orphan → WARN per v2_PLAN.md) and pins the PASSIVE-manifest contract (no applies_when/required_for) - template-context-parity: generated sections have zero unresolved placeholders and gated resolvers (ADVERSARIAL_STEP/CONFIDENCE_CALIBRATION/CHANGELOG_WORKFLOW) rendered — proving sections resolve with the parent skillName, not 'sections' 16 tests, all green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(ship): section-loading E2E + idempotency CLI detection (T9) - skill-e2e-ship-section-loading.test.ts (new, periodic): runs real /ship in plan mode against a fresh version-changing fixture and asserts the agent Read the required sections (review-army + changelog). Runs against the INSTALLED skill (~/.claude/skills/gstack/ship), not repo paths, so install-layout 404s surface [Codex outside-voice #5]. Layer-5 mechanical guard against silent section-skip. - skill-e2e-ship-idempotency.test.ts: detection updated for the carve — Step 12 now runs gstack-version-bump classify (JSON "state":"ALREADY_BUMPED") instead of the inline bash echo (STATE: ALREADY_BUMPED). Accept both; add a gstack-version-bump-write re-bump regression signal. - touchfiles: register ship-section-loading (periodic) + extend idempotency deps with bin/gstack-version-bump + scripts/resolvers/sections.ts. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * test(ship): union-read redaction wiring test for the carve (T9) main's PR-body redaction-at-sink lives in sections/pr-body.md.tmpl after the carve, not the skeleton template. Read skeleton + section templates union so the redaction-wiring assertions follow the relocated content. 9/9 green. Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> * v1.54.0.0 feat: carve /ship into skeleton + on-demand sections (-59% always-loaded) Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
213 lines
8.2 KiB
TypeScript
Executable File
213 lines
8.2 KiB
TypeScript
Executable File
#!/usr/bin/env bun
|
|
// gstack-version-bump — deterministic version-state classifier + writer for /ship.
|
|
//
|
|
// Extracted from ship Step 12 prose (v2 plan T9, hybrid CLI extraction). The
|
|
// idempotency classification and the dual-write to VERSION + package.json are
|
|
// pure deterministic logic; running them as tested code removes the single
|
|
// worst /ship footgun — re-bumping an already-shipped branch — from prose the
|
|
// agent could skip or misread when the step lives in a lazy-loaded section.
|
|
//
|
|
// What STAYS agent judgment (NOT here): the bump-LEVEL decision (micro/patch vs
|
|
// minor/major, which may AskUserQuestion on feature signals) and the queue
|
|
// collision prompt. The slot pick itself is bin/gstack-next-version. This CLI
|
|
// only answers "what state am I in?" and "write this exact version".
|
|
//
|
|
// Subcommands:
|
|
// classify --base <branch> [--version-path <p>]
|
|
// Compares VERSION vs origin/<base>:VERSION vs package.json.version.
|
|
// Emits JSON: { state, baseVersion, currentVersion, pkgVersion, pkgExists }
|
|
// state ∈ FRESH | ALREADY_BUMPED | DRIFT_STALE_PKG | DRIFT_UNEXPECTED
|
|
// Exit 0 on a decidable state (incl. DRIFT_UNEXPECTED — it's a real state
|
|
// the caller must handle), exit 2 on bad args / unresolvable base.
|
|
//
|
|
// write --version <X.Y.Z.W> [--version-path <p>]
|
|
// Validates the 4-digit pattern, writes VERSION + package.json.version.
|
|
// Use for the FRESH bump (or an approved queue rebump). Exit 3 on a
|
|
// half-write (VERSION written, package.json failed) so the caller knows
|
|
// drift exists; the next classify() will report DRIFT_STALE_PKG.
|
|
//
|
|
// repair [--version-path <p>]
|
|
// DRIFT_STALE_PKG path: sync package.json.version to the current VERSION
|
|
// file. No bump. Validates the VERSION pattern first.
|
|
//
|
|
// Contract: classify NEVER writes. write/repair mutate VERSION + package.json
|
|
// only. No git mutation, no network. Mirrors gstack-next-version's reader/writer
|
|
// split so /ship composes them.
|
|
|
|
import { existsSync, readFileSync, writeFileSync } from "node:fs";
|
|
import { execFileSync } from "node:child_process";
|
|
import { join } from "node:path";
|
|
|
|
const VERSION_RE = /^[0-9]+\.[0-9]+\.[0-9]+\.[0-9]+$/;
|
|
const DEFAULT = "0.0.0.0";
|
|
|
|
type State = "FRESH" | "ALREADY_BUMPED" | "DRIFT_STALE_PKG" | "DRIFT_UNEXPECTED";
|
|
|
|
function fail(msg: string, code = 2): never {
|
|
process.stderr.write(`gstack-version-bump: ${msg}\n`);
|
|
process.exit(code);
|
|
}
|
|
|
|
function argVal(args: string[], flag: string): string | undefined {
|
|
const i = args.indexOf(flag);
|
|
return i >= 0 && i + 1 < args.length ? args[i + 1] : undefined;
|
|
}
|
|
|
|
/** Resolve the VERSION file path: --version-path, else .gstack/version-path, else "VERSION". */
|
|
function resolveVersionPath(cwd: string, explicit?: string): string {
|
|
if (explicit) return join(cwd, explicit);
|
|
const pin = join(cwd, ".gstack", "version-path");
|
|
if (existsSync(pin)) {
|
|
const p = readFileSync(pin, "utf-8").trim();
|
|
if (p) return join(cwd, p);
|
|
}
|
|
return join(cwd, "VERSION");
|
|
}
|
|
|
|
function readVersionFile(p: string): string {
|
|
try {
|
|
const v = readFileSync(p, "utf-8").replace(/[\r\n\s]/g, "");
|
|
return v || DEFAULT;
|
|
} catch {
|
|
return DEFAULT;
|
|
}
|
|
}
|
|
|
|
/** package.json version + existence, parsed without spawning node. */
|
|
function readPkgVersion(cwd: string): { exists: boolean; version: string } {
|
|
const pkgPath = join(cwd, "package.json");
|
|
if (!existsSync(pkgPath)) return { exists: false, version: "" };
|
|
let raw: string;
|
|
try {
|
|
raw = readFileSync(pkgPath, "utf-8");
|
|
} catch {
|
|
return { exists: true, version: "" };
|
|
}
|
|
let parsed: unknown;
|
|
try {
|
|
parsed = JSON.parse(raw);
|
|
} catch {
|
|
fail("package.json is not valid JSON. Fix the file before re-running /ship.", 2);
|
|
}
|
|
const version = (parsed as { version?: unknown })?.version;
|
|
return { exists: true, version: typeof version === "string" ? version : "" };
|
|
}
|
|
|
|
function writePkgVersion(cwd: string, version: string): void {
|
|
const pkgPath = join(cwd, "package.json");
|
|
const raw = readFileSync(pkgPath, "utf-8");
|
|
const parsed = JSON.parse(raw) as Record<string, unknown>;
|
|
parsed.version = version;
|
|
writeFileSync(pkgPath, JSON.stringify(parsed, null, 2) + "\n");
|
|
}
|
|
|
|
function baseVersion(cwd: string, base: string, versionRel: string): string {
|
|
// Verify the base ref resolves, mirroring the Step 12 guard.
|
|
try {
|
|
execFileSync("git", ["rev-parse", "--verify", `origin/${base}`], { cwd, stdio: "ignore" });
|
|
} catch {
|
|
fail(`Unable to resolve origin/${base}. Run 'git fetch origin' or verify the base branch exists.`, 2);
|
|
}
|
|
try {
|
|
const out = execFileSync("git", ["show", `origin/${base}:${versionRel}`], { cwd }).toString();
|
|
const v = out.replace(/[\r\n\s]/g, "");
|
|
return v || DEFAULT;
|
|
} catch {
|
|
// VERSION absent on base (new repo / new file) → treat as 0.0.0.0.
|
|
return DEFAULT;
|
|
}
|
|
}
|
|
|
|
function classifyState(current: string, base: string, pkgExists: boolean, pkgVersion: string): State {
|
|
if (current === base) {
|
|
// VERSION unchanged vs base. A diverging package.json means someone hand-edited
|
|
// package.json bypassing /ship — unsafe to guess which is authoritative.
|
|
if (pkgExists && pkgVersion && pkgVersion !== current) return "DRIFT_UNEXPECTED";
|
|
return "FRESH";
|
|
}
|
|
// VERSION already moved past base.
|
|
if (pkgExists && pkgVersion && pkgVersion !== current) return "DRIFT_STALE_PKG";
|
|
return "ALREADY_BUMPED";
|
|
}
|
|
|
|
function cmdClassify(args: string[], cwd: string): void {
|
|
const base = argVal(args, "--base");
|
|
if (!base) fail("classify requires --base <branch>", 2);
|
|
const versionPath = resolveVersionPath(cwd, argVal(args, "--version-path"));
|
|
const versionRel = argVal(args, "--version-path") ?? "VERSION";
|
|
const current = readVersionFile(versionPath);
|
|
const baseV = baseVersion(cwd, base!, versionRel);
|
|
const pkg = readPkgVersion(cwd);
|
|
const state = classifyState(current, baseV, pkg.exists, pkg.version);
|
|
process.stdout.write(
|
|
JSON.stringify({
|
|
state,
|
|
baseVersion: baseV,
|
|
currentVersion: current,
|
|
pkgVersion: pkg.version || null,
|
|
pkgExists: pkg.exists,
|
|
}) + "\n",
|
|
);
|
|
// DRIFT_UNEXPECTED is a real, decidable state — the caller stops on it, but the
|
|
// classification itself succeeded, so exit 0. (Bad args / unresolvable base are
|
|
// the only exit-2 cases.)
|
|
}
|
|
|
|
function cmdWrite(args: string[], cwd: string): void {
|
|
const version = argVal(args, "--version");
|
|
if (!version) fail("write requires --version <X.Y.Z.W>", 2);
|
|
if (!VERSION_RE.test(version!)) {
|
|
fail(`NEW_VERSION (${version}) does not match MAJOR.MINOR.PATCH.MICRO. Aborting.`, 2);
|
|
}
|
|
const versionPath = resolveVersionPath(cwd, argVal(args, "--version-path"));
|
|
writeFileSync(versionPath, version + "\n");
|
|
if (existsSync(join(cwd, "package.json"))) {
|
|
try {
|
|
writePkgVersion(cwd, version!);
|
|
} catch {
|
|
fail(
|
|
"failed to update package.json. VERSION was written but package.json is now stale. " +
|
|
"Re-run — classify will report DRIFT_STALE_PKG and repair will sync it.",
|
|
3,
|
|
);
|
|
}
|
|
}
|
|
process.stdout.write(JSON.stringify({ wrote: version, packageJson: existsSync(join(cwd, "package.json")) }) + "\n");
|
|
}
|
|
|
|
function cmdRepair(args: string[], cwd: string): void {
|
|
const versionPath = resolveVersionPath(cwd, argVal(args, "--version-path"));
|
|
const current = readVersionFile(versionPath);
|
|
if (!VERSION_RE.test(current)) {
|
|
fail(
|
|
`VERSION file contents (${current}) do not match MAJOR.MINOR.PATCH.MICRO. ` +
|
|
"Refusing to propagate invalid semver into package.json. Fix VERSION, then re-run /ship.",
|
|
2,
|
|
);
|
|
}
|
|
if (!existsSync(join(cwd, "package.json"))) {
|
|
fail("repair: no package.json to sync.", 2);
|
|
}
|
|
try {
|
|
writePkgVersion(cwd, current);
|
|
} catch {
|
|
fail("drift repair failed — could not update package.json.", 3);
|
|
}
|
|
process.stdout.write(JSON.stringify({ repaired: current }) + "\n");
|
|
}
|
|
|
|
// Exported for unit tests (pure logic, no I/O).
|
|
export { classifyState, VERSION_RE, type State };
|
|
|
|
if (import.meta.main) {
|
|
const [sub, ...rest] = process.argv.slice(2);
|
|
const cwd = process.cwd();
|
|
switch (sub) {
|
|
case "classify": cmdClassify(rest, cwd); break;
|
|
case "write": cmdWrite(rest, cwd); break;
|
|
case "repair": cmdRepair(rest, cwd); break;
|
|
default:
|
|
fail("usage: gstack-version-bump <classify|write|repair> [flags]", 2);
|
|
}
|
|
}
|