mirror of
https://github.com/garrytan/gstack.git
synced 2026-06-08 11:03:54 +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>
119 lines
4.6 KiB
TypeScript
119 lines
4.6 KiB
TypeScript
/**
|
|
* Regression tests for #1539 — /review false positive rate on mature
|
|
* frameworks (Django, 4/8 FPs).
|
|
*
|
|
* The fix extends the Confidence Calibration resolver with a Pre-emit
|
|
* verification gate: every finding must quote the specific code line that
|
|
* motivates it; unverified findings are forced to confidence 4-5 so the
|
|
* existing suppression rule auto-fires.
|
|
*
|
|
* Tests pin:
|
|
* - The resolver emits the gate text
|
|
* - The regenerated SKILL.md files for all consumers carry the gate
|
|
* - The framework-meta nudge is present
|
|
* - The deferred-design-doc reference is present (T-Codex-2 split)
|
|
* - Each named FP class from the issue has an explicit row in the gate
|
|
*
|
|
* No paid eval. The static invariants are the durable guarantees that the
|
|
* FP-killing mechanism doesn't regress — the LLM behavior under it is
|
|
* separately measured via E2E review evals when this branch is run with
|
|
* EVALS=1.
|
|
*/
|
|
import { describe, expect, test } from "bun:test";
|
|
import * as fs from "node:fs";
|
|
import * as path from "node:path";
|
|
|
|
import { generateConfidenceCalibration } from "../scripts/resolvers/confidence";
|
|
|
|
const ROOT = path.resolve(import.meta.dir, "..");
|
|
|
|
describe("#1539 confidence resolver — pre-emit verification gate present", () => {
|
|
test("resolver text includes the gate header", () => {
|
|
const out = generateConfidenceCalibration({} as never);
|
|
expect(out).toMatch(/Pre-emit verification gate/);
|
|
expect(out).toMatch(/#1539/);
|
|
});
|
|
|
|
test("gate requires quoted code snippet (file:line + verbatim text)", () => {
|
|
const out = generateConfidenceCalibration({} as never);
|
|
expect(out).toMatch(/Quote the specific code line/);
|
|
expect(out).toMatch(/file:line/);
|
|
expect(out).toMatch(/verbatim text/);
|
|
});
|
|
|
|
test("unverified findings auto-suppressed via existing confidence rule", () => {
|
|
const out = generateConfidenceCalibration({} as never);
|
|
// The gate must hook the existing "<7 -> suppress" rule rather than
|
|
// invent new mechanism. Look for both forcing-to-4-5 AND a reference
|
|
// to suppression.
|
|
expect(out).toMatch(/Force its confidence to 4-5/);
|
|
expect(out).toMatch(/suppress/i);
|
|
});
|
|
|
|
test("framework-meta nudge present for Django/Rails/SQLAlchemy/TypeORM/Sequelize/Prisma", () => {
|
|
const out = generateConfidenceCalibration({} as never);
|
|
expect(out).toMatch(/Framework-meta nudge/);
|
|
expect(out).toMatch(/Django/);
|
|
expect(out).toMatch(/Rails/);
|
|
expect(out).toMatch(/SQLAlchemy/);
|
|
expect(out).toMatch(/TypeORM/);
|
|
expect(out).toMatch(/Sequelize/);
|
|
expect(out).toMatch(/Prisma/);
|
|
});
|
|
|
|
test("references the deferred design doc for framework-aware verification (T-Codex-2)", () => {
|
|
const out = generateConfidenceCalibration({} as never);
|
|
expect(out).toMatch(/1539-framework-aware-review\.md/);
|
|
});
|
|
|
|
test("enumerates the four FP classes the gate kills (#1539 named cases)", () => {
|
|
const out = generateConfidenceCalibration({} as never);
|
|
expect(out).toMatch(/field doesn't exist on model/);
|
|
expect(out).toMatch(/dict\.get\(\) might be None/);
|
|
expect(out).toMatch(/save\(\) might lose fields/);
|
|
expect(out).toMatch(/update_fields might miss/);
|
|
});
|
|
});
|
|
|
|
describe("#1539 generated SKILL.md files — gate propagated to all consumers", () => {
|
|
const consumers = [
|
|
"review/SKILL.md",
|
|
"cso/SKILL.md",
|
|
"plan-eng-review/SKILL.md",
|
|
"ship/SKILL.md",
|
|
];
|
|
|
|
// ship's confidence-calibration gate moved into sections/review-army.md (T9 carve);
|
|
// read the skeleton+sections union so the gate is still found.
|
|
const readUnion = (rel: string): string => {
|
|
let body = fs.readFileSync(path.join(ROOT, rel), "utf-8");
|
|
const secDir = path.join(ROOT, path.dirname(rel), "sections");
|
|
if (fs.existsSync(secDir)) {
|
|
for (const f of fs.readdirSync(secDir).sort()) {
|
|
if (f.endsWith(".md")) body += "\n" + fs.readFileSync(path.join(secDir, f), "utf-8");
|
|
}
|
|
}
|
|
return body;
|
|
};
|
|
|
|
for (const rel of consumers) {
|
|
test(`${rel} carries the Pre-emit verification gate`, () => {
|
|
const body = readUnion(rel);
|
|
expect(body).toMatch(/Pre-emit verification gate/);
|
|
expect(body).toMatch(/Quote the specific code line/);
|
|
});
|
|
}
|
|
});
|
|
|
|
describe("#1539 confidence suppression rule unchanged (regression on existing behavior)", () => {
|
|
test("confidence 3-4 row still says 'Suppress from main report'", () => {
|
|
const out = generateConfidenceCalibration({} as never);
|
|
expect(out).toMatch(/3-4[\s\S]{0,200}Suppress from main report/);
|
|
});
|
|
|
|
test("confidence 9-10 row preserves 'Show normally' behavior", () => {
|
|
const out = generateConfidenceCalibration({} as never);
|
|
expect(out).toMatch(/9-10[\s\S]{0,200}Show normally/);
|
|
});
|
|
});
|