mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-03 01:46:55 +02:00
* feat: add surface-aware exploratory QA and ship documentation gates * test: preserve delegated QA setup authority after main integration * fix(qa): clarify exploration order and preserve report artifacts * test(qa): follow the shared setup reference directly * refactor(ship): make verification and recovery routes explicit * test(ship): align evidence and review guards with explicit routes * fix(workflows): clarify ship recovery and functional QA evidence * fix(workflows): clarify approval recovery and full QA coverage * refactor(workflows): order review transactions and clarify ship state * fix(ship): clarify final verification and fail closed at publication * fix(evals): attribute native atomic documentation writes * fix(ship): clarify recovery and documentation lifecycle guidance * fix(test): preserve observed native placeholder styling in CI * fix(codex): report watchdog timeouts without a process-exit race * Checkpoint functional QA implementation and workflow validation repairs * Fix documentation and shared-review fixture contracts * docs: clarify judge reuse and evaluation supervision * test: align review evidence and selected case contracts * test: verify append-only documentation checkpoints and recovery * fix: qualify QA workflows and CI validation repairs * fix: launch shared-libs fixture scripts on Windows * fix: qualify QA deadlines, fixture isolation, and shard cleanup * fix: preserve qualified QA and cancellation repairs * fix: enforce functional fixture authority and share strict event decoding * fix: retain free-test evidence and explain recovery * fix: reject malformed native evidence after decoder consolidation * test: use reliable capture for telemetry privacy filters * test: refresh measured quick coverage and document validation costs * Fix native fixture receipts and preserve VM validation evidence * Align negative judge controls with upstream clarity policy * Fix report-only QA preparation and public evidence handling * Clarify QA-only preparation and current-report preservation * Stream Ship quality judgments with an explicit 64k response contract * Validate compact judge reasoning locally with supported wire schema * Align functional QA fixture instructions with evidence acceptance * Bind native browser diagnostics to execution evidence and align review verdicts * Preserve native diagnostic line boundaries * Serialize functional QA evidence from native captures * Keep large QA evidence fixture payload out of Windows argv
256 lines
11 KiB
TypeScript
256 lines
11 KiB
TypeScript
// /ship Step 12: VERSION ↔ package.json drift detection + repair.
|
|
// Mirrors the bash blocks in ship/SKILL.md.tmpl Step 12. When the template
|
|
// changes, update both sides together.
|
|
//
|
|
// Coverage gap: node-absent + bun-present path. Simulating "no node" in-process
|
|
// is flaky across dev machines; covered by manual spot-check + CI running on
|
|
// bun-only images if/when we add them.
|
|
|
|
import { test, expect, beforeEach, afterEach } from "bun:test";
|
|
import { execSync } from "node:child_process";
|
|
import { mkdtempSync, writeFileSync, readFileSync, rmSync, existsSync } from "node:fs";
|
|
import { tmpdir } from "node:os";
|
|
import { join } from "node:path";
|
|
|
|
let dir: string;
|
|
beforeEach(() => {
|
|
dir = mkdtempSync(join(tmpdir(), "ship-drift-"));
|
|
});
|
|
afterEach(() => {
|
|
rmSync(dir, { recursive: true, force: true });
|
|
});
|
|
|
|
const writeFiles = (files: Record<string, string>) => {
|
|
for (const [name, content] of Object.entries(files)) {
|
|
writeFileSync(join(dir, name), content);
|
|
}
|
|
};
|
|
|
|
const pkgJson = (version: string | null, extra: Record<string, unknown> = {}) =>
|
|
JSON.stringify(
|
|
version === null ? { name: "x", ...extra } : { name: "x", version, ...extra },
|
|
null,
|
|
2,
|
|
) + "\n";
|
|
|
|
const idempotency = (base: string): { stdout: string; code: number } => {
|
|
const script = `
|
|
cd "${dir}" || exit 2
|
|
BASE_VERSION="${base}"
|
|
CURRENT_VERSION=$(cat VERSION 2>/dev/null | tr -d '\\r\\n[:space:]' || echo "0.0.0.0")
|
|
[ -z "$CURRENT_VERSION" ] && CURRENT_VERSION="0.0.0.0"
|
|
PKG_VERSION=""
|
|
PKG_EXISTS=0
|
|
if [ -f package.json ]; then
|
|
PKG_EXISTS=1
|
|
if command -v node >/dev/null 2>&1; then
|
|
PKG_VERSION=$(node -e 'const p=require("./package.json");process.stdout.write(p.version||"")' 2>/dev/null)
|
|
PARSE_EXIT=$?
|
|
elif command -v bun >/dev/null 2>&1; then
|
|
PKG_VERSION=$(bun -e 'const p=require("./package.json");process.stdout.write(p.version||"")' 2>/dev/null)
|
|
PARSE_EXIT=$?
|
|
else
|
|
echo "ERROR: no parser"; exit 1
|
|
fi
|
|
if [ "$PARSE_EXIT" != "0" ]; then
|
|
echo "ERROR: invalid JSON"; exit 1
|
|
fi
|
|
fi
|
|
if [ "$CURRENT_VERSION" = "$BASE_VERSION" ]; then
|
|
if [ "$PKG_EXISTS" = "1" ] && [ -n "$PKG_VERSION" ] && [ "$PKG_VERSION" != "$CURRENT_VERSION" ]; then
|
|
echo "STATE: DRIFT_UNEXPECTED"; exit 1
|
|
fi
|
|
echo "STATE: FRESH"
|
|
else
|
|
if [ "$PKG_EXISTS" = "1" ] && [ -n "$PKG_VERSION" ] && [ "$PKG_VERSION" != "$CURRENT_VERSION" ]; then
|
|
echo "STATE: DRIFT_STALE_PKG"
|
|
else
|
|
echo "STATE: ALREADY_BUMPED"
|
|
fi
|
|
fi`;
|
|
try {
|
|
const stdout = execSync(script, { shell: "/bin/bash", encoding: "utf8", timeout: 30_000 });
|
|
return { stdout: stdout.trim(), code: 0 };
|
|
} catch (e: any) {
|
|
return { stdout: (e.stdout || "").toString().trim(), code: e.status ?? 1 };
|
|
}
|
|
};
|
|
|
|
const bump = (newVer: string): { code: number } => {
|
|
const script = `
|
|
cd "${dir}" || exit 2
|
|
NEW_VERSION="${newVer}"
|
|
if ! printf '%s' "$NEW_VERSION" | grep -qE '^[0-9]+\\.[0-9]+\\.[0-9]+\\.[0-9]+$'; then
|
|
echo "invalid semver" >&2; exit 1
|
|
fi
|
|
echo "$NEW_VERSION" > VERSION
|
|
if [ -f package.json ]; then
|
|
node -e 'const fs=require("fs"),p=require("./package.json");p.version=process.argv[1];fs.writeFileSync("package.json",JSON.stringify(p,null,2)+"\\n")' "$NEW_VERSION"
|
|
fi`;
|
|
try {
|
|
execSync(script, { shell: "/bin/bash", stdio: "pipe", timeout: 30_000 });
|
|
return { code: 0 };
|
|
} catch (e: any) {
|
|
return { code: e.status ?? 1 };
|
|
}
|
|
};
|
|
|
|
const syncRepair = (): { code: number } => {
|
|
const script = `
|
|
cd "${dir}" || exit 2
|
|
REPAIR_VERSION=$(cat VERSION | tr -d '\\r\\n[:space:]')
|
|
if ! printf '%s' "$REPAIR_VERSION" | grep -qE '^[0-9]+\\.[0-9]+\\.[0-9]+\\.[0-9]+$'; then
|
|
echo "invalid repair semver" >&2; exit 1
|
|
fi
|
|
node -e 'const fs=require("fs"),p=require("./package.json");p.version=process.argv[1];fs.writeFileSync("package.json",JSON.stringify(p,null,2)+"\\n")' "$REPAIR_VERSION"`;
|
|
try {
|
|
execSync(script, { shell: "/bin/bash", stdio: "pipe", timeout: 30_000 });
|
|
return { code: 0 };
|
|
} catch (e: any) {
|
|
return { code: e.status ?? 1 };
|
|
}
|
|
};
|
|
|
|
const pkgVersion = () =>
|
|
JSON.parse(readFileSync(join(dir, "package.json"), "utf8")).version;
|
|
|
|
test("rendered drift repair rejoins the existing-version queue check", () => {
|
|
const ship = readFileSync(join(import.meta.dir, '../ship/SKILL.md'), 'utf8');
|
|
const version = ship.slice(ship.indexOf('## Step 12:'), ship.indexOf('## Step 14:')).replace(/\s+/g, ' ');
|
|
expect(version).toMatch(/DRIFT_STALE_PKG[^\n]+repair[^\n]+reclassify[^\n]+ALREADY_BUMPED[^\n]+queue/);
|
|
expect(version).toContain('--current-version "$BASE_VERSION"');
|
|
expect(version).toContain('CANDIDATE_VERSION');
|
|
expect(version).toMatch(/keep[^\n]+NEW_VERSION[^\n]+currentVersion/);
|
|
});
|
|
|
|
test("rendered queue dispatch preserves offline git candidates without empty fallback fallthrough", () => {
|
|
const ship = readFileSync(join(import.meta.dir, '../ship/SKILL.md'), 'utf8');
|
|
const qualifyAt = ship.indexOf('**Qualify first:**');
|
|
const usableAt = ship.indexOf('**Usable candidate:**');
|
|
const missingAt = ship.indexOf('**No usable candidate:**');
|
|
expect(qualifyAt).toBeGreaterThanOrEqual(0);
|
|
expect(usableAt).toBeGreaterThan(qualifyAt);
|
|
expect(usableAt).toBeGreaterThanOrEqual(0);
|
|
expect(missingAt).toBeGreaterThan(usableAt);
|
|
const qualify = ship.slice(qualifyAt, usableAt).replace(/\s+/g, ' ');
|
|
const usable = ship.slice(usableAt, missingAt).replace(/\s+/g, ' ');
|
|
const missing = ship.slice(missingAt, ship.indexOf('4. **Write the bump**', missingAt)).replace(/\s+/g, ' ');
|
|
expect(qualify).toContain('require successful utility output and a nonempty valid version');
|
|
expect(qualify).toContain('`offline:false` qualifies; `offline:true` qualifies only with `fallback:"git"`');
|
|
expect(qualify).toContain('Offline output without that fallback, failure, malformed output or an empty version is unusable');
|
|
expect(usable).toContain('warnings and claimed queue');
|
|
expect(usable).toContain('CANDIDATE_VERSION');
|
|
expect(missing).toContain('local `BUMP_LEVEL` arithmetic');
|
|
expect(missing).toContain('ALREADY_BUMPED keeps `currentVersion`');
|
|
expect(missing).not.toContain('CANDIDATE_VERSION');
|
|
});
|
|
|
|
// --- Idempotency classification: 6 cases ---
|
|
|
|
test("FRESH: VERSION == base, pkg synced", () => {
|
|
writeFiles({ VERSION: "0.0.0.0\n", "package.json": pkgJson("0.0.0.0") });
|
|
expect(idempotency("0.0.0.0")).toEqual({ stdout: "STATE: FRESH", code: 0 });
|
|
});
|
|
|
|
test("FRESH: VERSION == base, no package.json", () => {
|
|
writeFiles({ VERSION: "0.0.0.0\n" });
|
|
expect(idempotency("0.0.0.0")).toEqual({ stdout: "STATE: FRESH", code: 0 });
|
|
});
|
|
|
|
test("ALREADY_BUMPED: VERSION ahead, pkg synced", () => {
|
|
writeFiles({ VERSION: "0.1.0.0\n", "package.json": pkgJson("0.1.0.0") });
|
|
expect(idempotency("0.0.0.0")).toEqual({ stdout: "STATE: ALREADY_BUMPED", code: 0 });
|
|
});
|
|
|
|
test("ALREADY_BUMPED: VERSION ahead, no package.json", () => {
|
|
writeFiles({ VERSION: "0.1.0.0\n" });
|
|
expect(idempotency("0.0.0.0")).toEqual({ stdout: "STATE: ALREADY_BUMPED", code: 0 });
|
|
});
|
|
|
|
test("DRIFT_STALE_PKG: VERSION ahead, pkg stale", () => {
|
|
writeFiles({ VERSION: "0.1.0.0\n", "package.json": pkgJson("0.0.0.0") });
|
|
expect(idempotency("0.0.0.0")).toEqual({ stdout: "STATE: DRIFT_STALE_PKG", code: 0 });
|
|
});
|
|
|
|
test("DRIFT_UNEXPECTED: VERSION == base, pkg edited (exits non-zero)", () => {
|
|
writeFiles({ VERSION: "0.0.0.0\n", "package.json": pkgJson("0.5.0.0") });
|
|
const r = idempotency("0.0.0.0");
|
|
expect(r.stdout.startsWith("STATE: DRIFT_UNEXPECTED")).toBe(true);
|
|
expect(r.code).toBe(1);
|
|
});
|
|
|
|
// --- Parse failures: 2 cases ---
|
|
|
|
test("idempotency: invalid JSON exits non-zero with clear error", () => {
|
|
writeFiles({ VERSION: "0.1.0.0\n", "package.json": "{ not valid" });
|
|
const r = idempotency("0.0.0.0");
|
|
expect(r.code).toBe(1);
|
|
expect(r.stdout).toContain("invalid JSON");
|
|
});
|
|
|
|
test("idempotency: package.json with no version field treated as <none>", () => {
|
|
writeFiles({ VERSION: "0.1.0.0\n", "package.json": pkgJson(null) });
|
|
// PKG_VERSION is empty → drift check skipped → ALREADY_BUMPED
|
|
expect(idempotency("0.0.0.0")).toEqual({ stdout: "STATE: ALREADY_BUMPED", code: 0 });
|
|
});
|
|
|
|
// --- Bump: 3 cases ---
|
|
|
|
test("bump: writes VERSION and package.json in sync", () => {
|
|
writeFiles({ VERSION: "0.0.0.0\n", "package.json": pkgJson("0.0.0.0") });
|
|
expect(bump("0.1.0.0").code).toBe(0);
|
|
expect(readFileSync(join(dir, "VERSION"), "utf8").trim()).toBe("0.1.0.0");
|
|
expect(pkgVersion()).toBe("0.1.0.0");
|
|
});
|
|
|
|
test("bump: rejects invalid NEW_VERSION", () => {
|
|
writeFiles({ VERSION: "0.0.0.0\n", "package.json": pkgJson("0.0.0.0") });
|
|
const r = bump("not-a-version");
|
|
expect(r.code).toBe(1);
|
|
// VERSION is unchanged — validation runs before any write.
|
|
expect(readFileSync(join(dir, "VERSION"), "utf8").trim()).toBe("0.0.0.0");
|
|
});
|
|
|
|
test("bump: no package.json is silent", () => {
|
|
writeFiles({ VERSION: "0.0.0.0\n" });
|
|
expect(bump("0.1.0.0").code).toBe(0);
|
|
expect(readFileSync(join(dir, "VERSION"), "utf8").trim()).toBe("0.1.0.0");
|
|
expect(existsSync(join(dir, "package.json"))).toBe(false);
|
|
});
|
|
|
|
// --- Adversarial review regressions: trailing whitespace + invalid REPAIR_VERSION ---
|
|
|
|
test("trailing CR in VERSION does not cause false DRIFT_STALE_PKG", () => {
|
|
// Before the tr-strip fix, VERSION="0.1.0.0\r" read via cat would mismatch
|
|
// pkg.version="0.1.0.0" and classify as DRIFT_STALE_PKG, then repair would
|
|
// write garbage \r into package.json. Now CURRENT_VERSION is stripped.
|
|
writeFileSync(join(dir, "VERSION"), "0.1.0.0\r\n");
|
|
writeFileSync(join(dir, "package.json"), pkgJson("0.1.0.0"));
|
|
expect(idempotency("0.0.0.0")).toEqual({ stdout: "STATE: ALREADY_BUMPED", code: 0 });
|
|
});
|
|
|
|
test("DRIFT REPAIR rejects invalid VERSION semver instead of propagating", () => {
|
|
// If VERSION is corrupted/manually-edited to something non-semver, the
|
|
// repair path must refuse rather than writing junk into package.json.
|
|
writeFileSync(join(dir, "VERSION"), "not-a-semver\n");
|
|
writeFileSync(join(dir, "package.json"), pkgJson("0.0.0.0"));
|
|
const r = syncRepair();
|
|
expect(r.code).toBe(1);
|
|
// package.json must NOT have been overwritten with the garbage.
|
|
expect(pkgVersion()).toBe("0.0.0.0");
|
|
});
|
|
|
|
// --- THE critical regression test: drift-repair does NOT double-bump ---
|
|
|
|
test("DRIFT REPAIR: sync path syncs pkg to VERSION without re-bumping", () => {
|
|
// Simulate a prior /ship that bumped VERSION but failed to touch package.json.
|
|
writeFiles({ VERSION: "0.1.0.0\n", "package.json": pkgJson("0.0.0.0") });
|
|
// Idempotency classifies as DRIFT_STALE_PKG.
|
|
expect(idempotency("0.0.0.0").stdout).toBe("STATE: DRIFT_STALE_PKG");
|
|
// Sync-only repair runs — no re-bump.
|
|
expect(syncRepair().code).toBe(0);
|
|
// VERSION is unchanged. package.json now matches VERSION. No 0.2.0.0.
|
|
expect(readFileSync(join(dir, "VERSION"), "utf8").trim()).toBe("0.1.0.0");
|
|
expect(pkgVersion()).toBe("0.1.0.0");
|
|
});
|