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>
197 lines
7.6 KiB
TypeScript
197 lines
7.6 KiB
TypeScript
/**
|
|
* Transcript section logger (v2 plan T10).
|
|
*
|
|
* Two jobs, both pure analysis over a SkillTestResult / NDJSON transcript:
|
|
*
|
|
* 1. extractSectionReads() — which `sections/*.md` files a run actually Read.
|
|
* Used by the sectioned world (post-carve) to verify the agent opened the
|
|
* chapters its situation required.
|
|
*
|
|
* 2. extractShipActions() — an observable ACTION fingerprint of a /ship run
|
|
* (ran tests, bumped VERSION, wrote CHANGELOG, created PR, ...). This works
|
|
* on BOTH the monolith and the sectioned skill, which is the whole point:
|
|
* capture a baseline on the current monolith ship FIRST, then assert the
|
|
* sectioned ship still performs the same actions. A section-read check alone
|
|
* can't catch "agent read the chapter but skipped the step"; the action
|
|
* fingerprint can.
|
|
*
|
|
* Why baseline-first (Codex outside-voice critique on the T9 plan): a logger
|
|
* shipped in the same PR as the carve is post-failure telemetry unless it has a
|
|
* pre-carve reference. captureShipBaseline() records the monolith's action
|
|
* fingerprint so compareShipActions() can flag a regression introduced by the
|
|
* carve.
|
|
*
|
|
* Pure functions, no I/O except the explicit read/write baseline helpers. The
|
|
* unit tests drive these with synthetic transcripts — no paid run needed to
|
|
* validate the logic.
|
|
*/
|
|
|
|
import * as fs from 'fs';
|
|
import * as path from 'path';
|
|
import * as os from 'os';
|
|
|
|
/** Minimal shape we need from SkillTestResult — kept structural so callers can
|
|
* pass a full SkillTestResult or a hand-built fixture in unit tests. */
|
|
export interface ToolCallLike {
|
|
tool: string;
|
|
input: unknown;
|
|
output?: string;
|
|
}
|
|
export interface TranscriptResultLike {
|
|
toolCalls: ToolCallLike[];
|
|
output?: string;
|
|
}
|
|
|
|
/** Pull the file_path off a tool-call input, tolerating unknown shapes. */
|
|
function readFilePath(input: unknown): string | null {
|
|
if (input && typeof input === 'object') {
|
|
const fp = (input as Record<string, unknown>).file_path;
|
|
if (typeof fp === 'string') return fp;
|
|
}
|
|
return null;
|
|
}
|
|
|
|
/** Pull the command string off a Bash tool-call input. */
|
|
function bashCommand(input: unknown): string | null {
|
|
if (input && typeof input === 'object') {
|
|
const cmd = (input as Record<string, unknown>).command;
|
|
if (typeof cmd === 'string') return cmd;
|
|
}
|
|
return null;
|
|
}
|
|
|
|
/**
|
|
* Every `sections/<name>.md` file the run Read, normalized to the section
|
|
* basename (e.g. "version-bump.md"). Deduped, in first-Read order. Matching is
|
|
* on the path segment `/sections/<file>.md` so it works regardless of whether
|
|
* the host resolved a relative, absolute, or prefixed install path.
|
|
*/
|
|
export function extractSectionReads(result: TranscriptResultLike): string[] {
|
|
const seen = new Set<string>();
|
|
const ordered: string[] = [];
|
|
for (const call of result.toolCalls) {
|
|
if (call.tool !== 'Read') continue;
|
|
const fp = readFilePath(call.input);
|
|
if (!fp) continue;
|
|
const m = fp.match(/(?:^|\/)sections\/([A-Za-z0-9._-]+\.md)$/);
|
|
if (!m) continue;
|
|
const name = m[1];
|
|
if (!seen.has(name)) {
|
|
seen.add(name);
|
|
ordered.push(name);
|
|
}
|
|
}
|
|
return ordered;
|
|
}
|
|
|
|
/**
|
|
* The canonical /ship action vocabulary. Each action is detected from the Bash
|
|
* commands the agent ran (plus a couple of Write/Edit signals). Order is the
|
|
* rough ship sequence; detection is order-independent.
|
|
*
|
|
* Keep this list aligned with the ship skeleton's numbered steps. The
|
|
* section-loading eval asserts the sectioned ship still triggers the same
|
|
* actions a monolith run did for the same fixture situation.
|
|
*/
|
|
export const SHIP_ACTIONS = [
|
|
'merged_base', // git merge <base>
|
|
'ran_tests', // bun test / npm test / the project test cmd
|
|
'bumped_version', // wrote VERSION / package.json version / ran gstack-version-bump
|
|
'wrote_changelog', // edited CHANGELOG.md
|
|
'committed', // git commit
|
|
'pushed', // git push
|
|
'opened_pr', // gh pr create / glab mr create
|
|
] as const;
|
|
export type ShipAction = (typeof SHIP_ACTIONS)[number];
|
|
|
|
const BASH_ACTION_PATTERNS: Array<{ action: ShipAction; re: RegExp }> = [
|
|
{ action: 'merged_base', re: /\bgit\s+merge\b/ },
|
|
{ action: 'ran_tests', re: /\b(bun\s+test|npm\s+(run\s+)?test|yarn\s+test|pytest|go\s+test|cargo\s+test|rspec)\b/ },
|
|
{ action: 'bumped_version', re: /gstack-version-bump\b|gstack-next-version\b|>\s*VERSION\b|npm\s+version\b/ },
|
|
{ action: 'wrote_changelog', re: /CHANGELOG\.md/ },
|
|
{ action: 'committed', re: /\bgit\s+commit\b/ },
|
|
{ action: 'pushed', re: /\bgit\s+push\b/ },
|
|
{ action: 'opened_pr', re: /\bgh\s+pr\s+create\b|\bglab\s+mr\s+create\b/ },
|
|
];
|
|
|
|
/**
|
|
* The observable action fingerprint of a ship run. Works on monolith AND
|
|
* sectioned skills because it reads what the agent DID (Bash + file writes),
|
|
* not which prose it loaded.
|
|
*/
|
|
export function extractShipActions(result: TranscriptResultLike): ShipAction[] {
|
|
const found = new Set<ShipAction>();
|
|
for (const call of result.toolCalls) {
|
|
if (call.tool === 'Bash') {
|
|
const cmd = bashCommand(call.input);
|
|
if (!cmd) continue;
|
|
for (const { action, re } of BASH_ACTION_PATTERNS) {
|
|
if (re.test(cmd)) found.add(action);
|
|
}
|
|
} else if (call.tool === 'Write' || call.tool === 'Edit') {
|
|
const fp = readFilePath(call.input);
|
|
if (fp && /CHANGELOG\.md$/.test(fp)) found.add('wrote_changelog');
|
|
if (fp && /(?:^|\/)VERSION$/.test(fp)) found.add('bumped_version');
|
|
}
|
|
}
|
|
// Preserve canonical order.
|
|
return SHIP_ACTIONS.filter(a => found.has(a));
|
|
}
|
|
|
|
export interface ShipBaseline {
|
|
tag: string;
|
|
/** Fixture/situation id this baseline was captured for. */
|
|
situation: string;
|
|
/** Action fingerprint observed on the monolith ship. */
|
|
actions: ShipAction[];
|
|
/** Section reads observed (empty on the monolith — present after carve). */
|
|
sectionReads: string[];
|
|
capturedAt: string;
|
|
}
|
|
|
|
const DEFAULT_BASELINE_DIR = path.join(os.homedir(), '.gstack-dev', 'ship-baselines');
|
|
|
|
/** Where a baseline for a given situation lives. */
|
|
export function baselinePath(situation: string, dir = DEFAULT_BASELINE_DIR): string {
|
|
return path.join(dir, `${situation}.json`);
|
|
}
|
|
|
|
/** Persist a ship baseline (used once on the monolith, before the carve). */
|
|
export function writeShipBaseline(baseline: ShipBaseline, dir = DEFAULT_BASELINE_DIR): string {
|
|
fs.mkdirSync(dir, { recursive: true });
|
|
const p = baselinePath(baseline.situation, dir);
|
|
fs.writeFileSync(p, JSON.stringify(baseline, null, 2) + '\n');
|
|
return p;
|
|
}
|
|
|
|
/** Read a previously-captured baseline, or null if none exists yet. */
|
|
export function readShipBaseline(situation: string, dir = DEFAULT_BASELINE_DIR): ShipBaseline | null {
|
|
try {
|
|
return JSON.parse(fs.readFileSync(baselinePath(situation, dir), 'utf-8')) as ShipBaseline;
|
|
} catch {
|
|
return null;
|
|
}
|
|
}
|
|
|
|
export interface ShipActionDiff {
|
|
/** Actions the baseline performed that the current run did NOT (the regression set). */
|
|
missing: ShipAction[];
|
|
/** Actions the current run performed that the baseline did not (usually fine). */
|
|
added: ShipAction[];
|
|
/** True when no baseline action was dropped. */
|
|
ok: boolean;
|
|
}
|
|
|
|
/**
|
|
* Compare a current sectioned-ship run against the monolith baseline. A dropped
|
|
* action (in baseline, not in current) is the carve regression we care about:
|
|
* the sectioned ship stopped doing something the monolith did.
|
|
*/
|
|
export function compareShipActions(baseline: ShipBaseline, current: ShipAction[]): ShipActionDiff {
|
|
const cur = new Set(current);
|
|
const base = new Set(baseline.actions);
|
|
const missing = baseline.actions.filter(a => !cur.has(a));
|
|
const added = current.filter(a => !base.has(a));
|
|
return { missing, added, ok: missing.length === 0 };
|
|
}
|