mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-03 18:06:54 +02:00
* refactor(resolvers): split review.ts into MECE resolver modules (pure move) Move every function from scripts/resolvers/review.ts, unchanged, into: - review-dashboard.ts: review dashboard, plan-file review report - plan-gates.ts: approval check, exit-plan-mode gate, plan-file discovery, plan-completion audit/gate (ship + review), plan verification exec - spec-review.ts: both spec review loops, benefits-from, anti-shortcut clause - outside-voice-steps.ts: Codex second opinion, adversarial step, Codex plan review, Codex doc review, disabled-outside record - review-scope.ts: scope drift, cross-review dedup, shared-code reuse review.ts is deleted; index.ts imports the new modules. gen-skill-docs output is byte-identical for every host (--host all). Test imports and source-path references are re-pointed; the two source-text report/gate tests in gen-skill-docs.test.ts become behavioral renders across every consuming skill and host. All 46 touchfile entries that named review.ts now name all five modules, guarded by a recorded selection golden. * test(browse): black-box auth matrix for every server route and both surfaces Drives buildFetchHandler fetchLocal/fetchTunnel with no token, wrong token, root token, scoped token and the SSE cookie for all 33 routes, plus unmatched paths and wrong methods. Denials assert today's exact status, body and content type; allowed credentials assert the handler was reached. Written against the unchanged if-chain server so the W3 route-table refactor must keep it green. * refactor(shard-engine): move scripts/test-strict-output.ts to scripts/lib/shard-engine.ts The shared shard engine grows from the existing strict-output module (runShardChild, killProcessGroup, signal forwarding, strict classifier). scripts/test-strict-output.ts stays as a re-export so existing importers, mock.module paths and the strict-output/run-shard-child tests are unchanged. The engine inherits the global touchfile entry; the free runner's CLI-routing fixture copies the new module. * refactor(resolvers): decompose the three >150-line review resolvers (output-neutral) Split generateAdversarialStep, generateCodexPlanReview and generatePlanCompletionAuditInner into per-section helpers whose template literals are copied verbatim, so every function in the new modules is at or under 150 lines. gen-skill-docs output is byte-identical for every host (--host all, compared against96764e80with a fixed --link-root). * refactor(resolvers): one outside-voice failure policy (deliberate prose unification) outsideVoiceFailurePolicy(ctx, opts) in outside-voice.ts now renders the auth / timeout / empty-response bullets for all four call sites that hand-typed them (Codex second opinion, adversarial step, Codex plan review, design outside voices). Options are explicit per site (timeoutMinutes, onTimeout, stderrOnEmpty, fallback, escape) with no defaults. Deliberate generated-prose changes (every host): - office-hours: 'Fall back to <native> subagent.' becomes 'Fall back to the <native> subagent below.' - plan-devex-review: the plain 'Auth failure (stderr contains ...)' bullets become the canonical bold bullets; auth also triggers on 'API key'; 'auth failed' becomes 'authentication failed'. - review/ship adversarial: 'exceeded 9 minutes and was terminated' becomes 'timed out after 9 minutes and was terminated'; the timeout is still MISSING COVERAGE. - design outside voices: unchanged. Adds ratchet (d) (test/outside-voice-failure-policy.test.ts) with a reasoned allowlist for /codex's own CLI errors, the MISSING COVERAGE retention test, refreshed codex/factory ship goldens, and outside-voice.ts in every touchfile entry of review.ts and design.ts (selection golden extended). * test(pty): fake PTY session driver with an injectable clock through the runner launch seam The three plan-skill runners take an optional PtyDriver (launch, now, monotonic, sleep); omitted, they use the real launcher and clocks exactly as before. test/helpers/pty/fake-session.ts feeds scripted frames through that seam, and claude-pty-runner.runners.unit.test.ts runs observation, counting and floor for success, deadline timeout, permission prompt and plan-ready outcomes with no CLI or real timers. These cases must stay green unchanged through the W4 split and the runPtySession extraction. Touchfiles: every entry that lists claude-pty-runner.ts or pty-screen.ts now also lists test/helpers/pty/**. * refactor(shard-engine): run both lanes on the shared engine; lane policy injected Engine (scripts/lib/shard-engine.ts) gains the W2 primitives: per-shard tmp/Chromium sandbox + async cleanup backstop, log-path allocation and full-stream log capture, one duration-seed reader/writer with a lane predicate, LanePolicy (seed predicate + zero-execution verdict), strictShardStatus, and the shared CLI flag loop. runShardChild takes an optional companion (signal/settle) and waits a bounded 250ms to reap a wall-killed child. Free lane stops spawning shards itself: runFreeShard uses runShardChild with trackShardBrowser as the companion (win32 path unchanged: no process group, no negative-pid kill). Its sync state-dir removal stays lane policy. Paid lane uses the sandbox, log, seed, verdict and flag primitives; the hollow-shard guard applies PAID_LANE_POLICY. Lane outcomes are unchanged (free keeps >= 0 seeds and file-count zero-exec rule; paid keeps > 0 seeds, warning under selection and passed-empty under EVALS_ALL). paid-free-boundary's closure assertion now names the engine module, where the strict classifier lives. * test(shard-engine): engine unit tests, fixture-corpus equivalence, per-lane CLI parity - test/shard-engine.test.ts: failing/unhandled/module-load output fails both lanes, per-lane zero-execution and seed rules, whole-group kill on a wall timeout (both lanes), mocked-win32 path with no negative-pid kill, companion settle order, log capture, sandbox isolation, flag loop. - test/shard-engine-equivalence.test.ts + test/fixtures/shard-equivalence: seven outcome fixtures plus one real shard, run through both lanes and compared with classifications recorded from the base runners (96764e80). - test/shard-cli-parity.test.ts + test/fixtures/shard-cli-parity: flag set, defaults, validation errors and the Unknown argument error per lane match the base runners. * refactor(shard-engine): decompose runFreeShard and runPaidShard to <= 150 lines Output-neutral extraction under the fixture-corpus equivalence and runner tests: captureFreeStream, explainFreeVerdict and logFreeRecovery (free); paidShardCommand, settleShardSpool, settleBootstrapRetention and printLogTail (paid). The bootstrap scope-creation block that bootstrap-retention.test.ts evaluates stays verbatim. * refactor(pty): split claude-pty-runner.ts into test/helpers/pty/* behind a barrel Pure move: every line of the former 5,047-line runner lands verbatim in one module (four private helpers gain `export` for cross-module use): binary, screen (absorbs test/helpers/pty-screen.ts, which now re-exports it), launch, session (PtyDriver), judge, classify, auq, plan-native, boundaries, runners/{observation,counting,floor}. claude-pty-runner.ts re-exports the original public surface by name; pty/ modules import siblings directly. Tests that read the runner's source text: - rewritten as behavioral: the unit test's model-pin tripwire (fake CLI argv: fallback chain, --model before extraArgs, hermetic --strict-mcp-config), pty-skill-seeding-wiring (runners through the fake driver; launcher through a fake CLI reporting CLAUDE_CONFIG_DIR). The "three wrappers forward model" grep is replaced by the runners' fake-driver launch assertions. - pty-screen-session / pty-screen-supervision: stop copying runner source; they mock.module the real pty/screen.ts (and the fixture cleanup) instead. - re-pointed to the owning module (they execute a sliced runner body with injected boundaries; no seam exists for those boundaries yet): eng-seeded-completion-ai, plan-floor-permission, plan-create-prepublication, plan-count-completion; hermetic-wiring's source guard now reads pty/launch.ts and scans every pty/ module for raw process.env spreads. - plan-count-timeout and pty-output-wake mock the viewport at pty/screen.ts. * test(ratchet-c): enforcing module/function size ratchet and moved-code touchfile coverage Ratchet (c) ships enforcing: test/helpers/module-size.ts counts file and top-level function lengths by brace matching over masked source (strings, comments, regex literals and template text masked; ${} expressions kept), covering function declarations, arrow functions assigned to consts and route-table handler properties, with no parser dependency. Its self-test uses template literals and code-fence braces copied from scripts/resolvers/review.ts and design.ts. test/fixtures/module-size-ratchet.json binds scripts/lib/shard-engine.ts (<= 800 lines, <= 150 per function) and records the residual runner sizes (free 2352, paid 1921) as non-growth caps; allowlist entries are keyed on file plus matched text and need a reason. Failure output lists file:line, the rule, Fix: and the allowlist path. touchfiles.test.ts gains the moved-code superset check over test/fixtures/touchfile-move-goldens/ (W2 golden recorded at96764e80: test-strict-output.ts and test-paid-shards.ts global, test-free-shards.ts none). * refactor(browse): declared route table replaces the buildFetchHandler if-chain The ~1,300-line if-chain in buildFetchHandler becomes a route table: each entry declares method, path, auth kind and surfaces, and one auth gate in browse/src/routes/table.ts returns the per-kind denial (root-bearer, scoped, root-or-sse-cookie: 401 Unauthorized; root-token: 403 Root token required; extension-origin: 403 Forbidden). Unmatched requests take the declared fallthrough (root-bearer check, then plain-text 404). Handlers move to browse/src/routes/{core,pairing,pty,tokens,tunnel,activity,commands,files, inspector}.ts and receive a RouteContext with auth checks as functions instead of closing over factory locals. Dispatch order is unchanged: tunnel filter, beforeRoute overlay, gate, handler. TUNNEL_PATHS stays a literal in server.ts. Behavior-preserving: the black-box auth matrix from the previous commit passes unchanged. /memory and /inspector/events are declared root-bearer because the blanket check always ran before their SSE-cookie branch. Source-text route tests are rewritten as behavioral tests through buildFetchHandler or a route's real handler with a stub RouteContext (browse/test/route-test-harness.ts). Checks with no runtime seam are re-pointed to the route modules: Surface type, /inspector/events SSE helper, sanitizeReplacer imports, /pty-inject-scan sidecar-client import, and the ngrok config lookup and startTunnel wiring that stay in server.ts. * test(browse): stubbed-handler auth matrix and route inventory for the route table Every ROUTES entry runs through the real dispatcher and gate with stub handlers on each declared surface and six credentials; denials assert the exact status and body each auth kind returned at96764e8, admitted credentials assert the handler ran (with the gate's TokenInfo for scoped routes). Also pins the reviewed route inventory (method, path, auth kind, surfaces), that every entry declares auth and surfaces, that the table's tunnel paths equal the TUNNEL_PATHS literal with GET /connect admitted, the unmatched fallthrough, and that the root token is rejected on every tunnel route through buildFetchHandler. * test(browse): ratchet (b) keeps route dispatch inside the route table Scans browse/src/server.ts and browse/src/routes/*.ts for pathname comparisons; only the table matcher and the tunnel-surface filter are allowed, listed with reasons in browse/test/fixtures/route-dispatch-allowlist.json (keyed on file plus line text). Also checks every entry declares auth and surfaces and that gstack registers no beforeRoute overlay itself. Self-tests plant a violation and assert the file:line, Fix: and allowlist path in the message, that a shifted line stays allowlisted, and that a reasonless entry is rejected. * test: touchfile superset check for modules moved out of browse/src/server.ts Records the paid evals selected by touching browse/src/server.ts at96764e80(17 E2E, 1 LLM judge) and asserts every browse/src/routes/*.ts module selects a superset. The test reads every golden in test/fixtures/moved-module-selection/ so other moved-code goldens can sit beside it. * test(shard-engine): give non-timeout corpus fixtures CI headroom; keep the POSIX golden off the Windows lane Only the wall-timeout fixture keeps a 3s wall; the rest get 60s so a loaded host cannot turn a pass into a timeout. Base and branch runners still agree on every classification under the new walls. The Windows exclusion entry moves the free runner's ratchet (c) residual cap to 2356 lines. * refactor(pty): one runPtySession loop drives observation, counting and floor test/helpers/pty/session.ts owns launch -> start -> (poll -> tick)* -> timeout and the failure contract the three runners each hand-rolled: the run's own error wins over capture and close errors, close always runs, owned fixture cleanup runs last (also when launch fails). Each runner now supplies a PtySessionPlan: its boot/command step, poll cadence (2s observation/floor sleep; counting's output wake + 250ms coalesce), tick policy (permission handling, native identity, terminal rules stay per runner because they differ) and capture hooks. The runner bodies are decomposed into top-level steps so no function exceeds 150 lines; behavior is unchanged and the fake-driver cases from the first W4 commit pass unmodified. The counting capture step and the native completion-summary predicate are now named functions (countingCapture, isNativeCompletionSummary), so plan-create-prepublication and plan-count-completion call them directly instead of executing sliced source. The two harnesses that still execute a sliced runner body with injected boundaries (eng-seeded-completion-ai, plan-floor-permission) pass the PtyDriver seam instead of overriding Date/Bun.sleep. * test(ratchet-c): register route modules, review resolver modules and server.ts residual cap * refactor(pty): decompose launchClaudePty and engNumberedFindingAUQ under 150 lines launchClaudePty (349 lines) becomes launch preparation (args, hermetic child env, owned state roots), recorder creation, spawn, the trust-dialog watcher, close, and the session handle over one PtyProcess state object. The failure order is unchanged: abort the viewport, dispose any recorders created so far, dispose the viewport, rethrow. The --model / --strict-mcp-config ordering and seedSkills wiring stay pinned by the behavioral fake-CLI tests. engNumberedFindingAUQ (345 lines) keeps its guards and dispatch; each self-contained issue family (declared cache, library retry hooks, cache owner, injected singleton, shared writers, injected export) moves verbatim into its own function. Every pty/ module is now <= 800 lines and every top-level function <= 150 lines. * test(pty): split claude-pty-runner.unit.test.ts along the pty/ module seams The 188 unit tests move verbatim into claude-pty-runner.{screen,classify, auq,launch,plan-native,boundaries}.unit.test.ts (test names unchanged; each file imports only what it uses from the barrel). The five files that no longer read a SKILL.md template join the test-of-test ratchet baseline with a reason. * test(touchfiles): moved PTY modules keep their paid-eval selection test/fixtures/touchfile-selection/w4-pty.json records, at96764e8, the paid evals selected by touching test/helpers/claude-pty-runner.ts (20) and test/helpers/pty-screen.ts (20). touchfiles.test.ts now asserts every .ts file under test/helpers/pty/ (and pty/screen.ts for both sources) selects a superset, reading every golden in that directory so later moves can add one; a planted-violation case pins the report and its Fix line. * fix(browse): unexchanged pair setup keys no longer authenticate bearer requests validateToken accepted a gsk_setup_ key as a bearer on /command, /batch and /file (found while building the W3 auth matrix). A setup key now only authenticates the /connect exchange. * W1: one state-root owner (lib/state-root.ts + bin/gstack-state-root.sh), gstack-paths --explain and fail-stop, parity tests * W1: guarded migration of every executable state-root site; uninstall deletes only ~/.gstack Bins, careful/freeze hooks, setup, upgrade migrations, browse/src, design, ios-qa daemon, lib and scripts resolve the state root through bin/gstack-state-root.sh (bash) or lib/state-root.ts (TS). Bins source the twin and stop with a reinstall message when it is missing; hooks source it and never spawn gstack-paths. browse/src/config.ts and lib/cso/state.ts delegate to resolveStateRoot. Analytics writers and readers move together so the usage log stays one file. gstack-uninstall deletes state only at ~/.gstack, refuses (exit 2) when it resolves to /, $HOME or an ancestor, the checkout or the git root, and leaves any other resolved root in place with the removal command. Fixtures that copy single bins now copy the twin. * W1: privacy keys and trust-policy deny tiers merge across state roots; gstack-config reporting; test hermeticity readConfigKey / gstack_read_config_key return the most restrictive telemetry, memorable_recall, codex_reviews and update_check across the resolved root and ~/.gstack; other keys read the resolved root only. gstack-config set reports an overriding root with the exact override command, list shows the winning root and a root-variable disagreement line. gstack-gbrain-repo-policy get merges deny/read-only tiers. gstack-egress reads through readConfigKey. test-setup.ts strips inherited GSTACK_STATE_ROOT/GSTACK_STATE_DIR and redirects the legacy root. * W1: shared hook logging helper (hosts/claude/hooks/hook-log.ts) One hook-errors.log writer: root from resolveStateRoot, 0600 on every append, opt-in rate limit used only by memorable-user-prompt. The five hooks route through it. * W1: docs/state-root.md and README troubleshooting pointer Precedence table, a real --explain example, the move-your-state recipe, merged privacy keys, the uninstall rule, the resolver-failure fix, and the plugin-mode note (evidence gate: no official plugin distribution). * W1b: template and resolver prose resolve state through guarded gstack-paths; ratchet (a) Every gstack-paths eval in templates and resolvers carries the fail-stop guard; executable ~/.gstack paths in bash blocks (context recovery preamble, eureka log, analytics, project artifacts, upgrade snooze, setup-gbrain lock, retro snapshots, ship consent marker) use $GSTACK_STATE_ROOT, and the writer prose that pairs with them points at the printed PROJECT_DIR / RETRO_FILE. ship drops export GSTACK_STATE_ROOT. SKILL.md regenerated (claude + codex), ship goldens re-pinned, parity and context-budget caps raised to the measured sizes with notes. test/state-root-ratchet.test.ts enforces the rule with a reasoned allowlist; W1 touchfile entries plus a superset golden. * refactor: apply W1 state-root edits in W2/W3/W5-owned files; one moved-code touchfile golden for all workstreams * test: fold the moved-code touchfile golden into touchfiles.test.ts; fix integration fixture closure and caps * v1.91.11.0: CHANGELOG, TODOS, docs and conventions for the refactor wave * test: re-measure plan-ceo/design-consultation caps and ship goldens after the guarded plan-discovery and spec-review blocks; add the state-root twin to the workflow-boundaries fixture * fix(windows): migrations resolve their directory with either path separator; state-root parity compares under the HOME Git Bash actually sees * fix(review,ship): state plan-check timing after smoke expiry and test_stub Skip semantics (review workflow judge clarity) * test(qa-eval): webhook fix eval asks for the fix loop's post-repair probes; eight-scenario coverage stays in the report-only case and the harness recheck * test(qa-eval): re-pin the webhook prompt contract to the fix-loop stage; R29 coverage omissions stay bound by the report-only case * fix(review,ship): plan checks publish a checkpoint before each probe; only the smoke expiry stop is skipped * fix(qa): carry #2999's checkpoint receipt link, report-template line and full-revision placeholder (identical hunks) * test(qa-callers): disable git auto maintenance in the caller fixture Git 2.47+ runs auto maintenance detached after commit; on the CI runner's git 2.55 it rewrote .git/objects fan-out directories while the write observer was running, which surfaced as unauthorized mutations. Same gc.auto=0 / maintenance.auto=false guard the shared-libs fixture already uses. * test(plan-mode-no-op): require prose evidence for the prose-fallback members so a spinner-frame judge verdict cannot end the run as asked * test(ship-docsync): carry #2999's seeded-attempt docsync harness (identical files) The doc-sync fault cases replayed attempt 1 before reaching their gate and ran out of their 285s budget. The fixture now seeds attempt 1 and the parent starts at the gate under test. Taken byte-identical from origin/capy/audit-fix-wave (fb526898,e6ac813d,6ce10ff7,d0c53577,77cce3be). Local: stale-before, recovery and late-result 6/6 PASS (97-164s); the whole file 12/12 PASS.
316 lines
23 KiB
TypeScript
316 lines
23 KiB
TypeScript
import * as fs from 'node:fs';
|
||
import * as path from 'node:path';
|
||
import { createHash } from 'node:crypto';
|
||
import { observeQAWrites, type QAWriteObservation } from './qa-functional-observer';
|
||
import { nativeCalls } from './qa-checkpoint-evidence';
|
||
import type { SkillTestResult } from './session-runner';
|
||
import { DOC_PATH, type DocsScenario, type fixtureDocs } from './docsync-fixture';
|
||
import { sliceBetween } from './skill-fixture';
|
||
|
||
export async function observeDocsWrites(fixture: ReturnType<typeof fixtureDocs>) {
|
||
return observeQAWrites(fixture.repo, { atomicTargets: [DOC_PATH] });
|
||
}
|
||
|
||
type DocsWriteContext = {
|
||
result: SkillTestResult;
|
||
fixture: ReturnType<typeof fixtureDocs>;
|
||
scripts?: string[];
|
||
readOnly?: boolean;
|
||
};
|
||
|
||
function docsAtomicSources(observation: QAWriteObservation, allowed: string[], context?: DocsWriteContext): Set<string> {
|
||
const denied = new Set<string>();
|
||
if (!context || context.readOnly || !allowed.includes(DOC_PATH) || !observation.complete || observation.failures.length) return denied;
|
||
const { result, fixture, scripts = [] } = context;
|
||
if (result.exitReason !== 'success' || !Array.isArray(result.transcript) || docsToolFailures(result, fixture, scripts).length) return denied;
|
||
const failures: string[] = [];
|
||
const target = path.join(fixture.repo, DOC_PATH);
|
||
const native = nativeCalls(result.transcript, failures);
|
||
const calls = native.filter(call => ['Write', 'Edit'].includes(call.name)
|
||
&& typeof call.input.file_path === 'string' && path.resolve(fixture.repo, call.input.file_path) === target);
|
||
if (failures.length || !calls.length || calls.some((call, index) => call.failed || call.end <= call.start || (index > 0 && call.start <= calls[index - 1].end))) return denied;
|
||
const before = observation.before[DOC_PATH];
|
||
const after = observation.after[DOC_PATH];
|
||
if (!/^\d+:[a-f0-9]{64}$/.test(before ?? '') || !/^\d+:[a-f0-9]{64}$/.test(after ?? '') || before.split(':')[0] !== after.split(':')[0]) return denied;
|
||
const hash = (text: string) => createHash('sha256').update(text).digest('hex');
|
||
const encoded = fixture.before?.contents[DOC_PATH];
|
||
if (typeof encoded !== 'string') return denied;
|
||
const baseline = Buffer.from(encoded, 'base64');
|
||
let content = baseline.toString('utf8');
|
||
let contentHash = before.split(':')[1];
|
||
if (baseline.toString('base64') !== encoded || !Buffer.from(content).equals(baseline) || hash(content) !== contentHash) return denied;
|
||
const seen = new Set([contentHash]);
|
||
for (const call of calls) {
|
||
const event = result.transcript[call.end];
|
||
const payload = event.tool_use_result;
|
||
const results = event.message.content.filter((block: any) => block?.type === 'tool_result');
|
||
if (results.length !== 1 || (results[0].is_error !== undefined && results[0].is_error !== false)) return denied;
|
||
const omitted = !Object.hasOwn(event, 'tool_use_result');
|
||
if (omitted) {
|
||
if (call.parent === null) return denied;
|
||
let child = call;
|
||
const ancestors = new Set<typeof call>();
|
||
while (child.parent !== null) {
|
||
const parents = native.filter(candidate => {
|
||
const blocks = result.transcript[candidate.end]?.message?.content?.filter((block: any) => block?.type === 'tool_result');
|
||
return blocks?.length === 1 && blocks[0].tool_use_id === child.parent;
|
||
});
|
||
if (parents.length !== 1) return denied;
|
||
const parent = parents[0];
|
||
const completion = result.transcript[parent.end];
|
||
const block = completion.message.content.find((block: any) => block?.type === 'tool_result');
|
||
if (!['Agent', 'Task'].includes(parent.name) || parent.failed || parent.input.run_in_background === true
|
||
|| parent.start >= child.start || parent.end <= child.end || ancestors.has(parent)
|
||
|| (block.is_error !== undefined && block.is_error !== false)) return denied;
|
||
if (Object.hasOwn(completion, 'tool_use_result')) {
|
||
if (completion.tool_use_result?.status !== 'completed') return denied;
|
||
} else if (parent.parent === null) return denied;
|
||
ancestors.add(parent);
|
||
child = parent;
|
||
}
|
||
} else if (!payload || payload.filePath !== target || payload.userModified !== false || payload.originalFile !== content) return denied;
|
||
if (call.name === 'Write') {
|
||
if (typeof call.input.content !== 'string' || (!omitted && (payload.type !== 'update' || payload.content !== call.input.content))) return denied;
|
||
content = call.input.content;
|
||
} else {
|
||
const { old_string: old, new_string: replacement, replace_all: all = false } = call.input;
|
||
if (typeof old !== 'string' || !old || typeof replacement !== 'string' || typeof all !== 'boolean'
|
||
|| (!omitted && (payload.oldString !== old || payload.newString !== replacement || payload.replaceAll !== all))) return denied;
|
||
const parts = content.split(old);
|
||
if (parts.length < 2 || (!all && parts.length !== 2)) return denied;
|
||
content = parts.join(replacement);
|
||
}
|
||
contentHash = hash(content);
|
||
if (seen.has(contentHash)) return denied;
|
||
seen.add(contentHash);
|
||
}
|
||
if (contentHash !== after.split(':')[1]) return denied;
|
||
const events = observation.events;
|
||
const destinations = events.flatMap((event, index) => event.path === DOC_PATH && event.mask === 0x80 ? [index] : []);
|
||
if (destinations.length !== calls.length) return denied;
|
||
const sources = new Set<string>();
|
||
let previous = -1;
|
||
for (const destination of destinations) {
|
||
const move = events[destination];
|
||
if (!Number.isInteger(move.cookie) || move.cookie <= 0 || move.cookie > 0xffffffff) return denied;
|
||
const pair = events.flatMap((event, index) => event.cookie === move.cookie ? [index] : []);
|
||
if (pair.length !== 2 || pair[1] !== destination) return denied;
|
||
const source = events[pair[0]];
|
||
if (source.mask !== 0x40 || source.path === DOC_PATH || path.dirname(source.path) !== path.dirname(DOC_PATH)
|
||
|| Object.hasOwn(observation.before, source.path) || Object.hasOwn(observation.after, source.path) || sources.has(source.path)) return denied;
|
||
const lifecycle = events.flatMap((event, index) => event.path === source.path ? [{ event, index }] : []);
|
||
if (lifecycle[0]?.event.mask !== 0x100 || lifecycle[0].index <= previous || lifecycle.at(-1)?.index !== pair[0]) return denied;
|
||
let modified = false;
|
||
let closed = false;
|
||
for (const { event, index } of lifecycle) {
|
||
if (index === pair[0]) { if (!modified || !closed) return denied; continue; }
|
||
if (event.cookie !== 0) return denied;
|
||
if (index === lifecycle[0].index) continue;
|
||
if (event.mask === 0x2 && !closed) modified = true;
|
||
else if (event.mask === 0x4 && !closed) continue;
|
||
else if (event.mask === 0x8 && modified) closed = true;
|
||
else return denied;
|
||
}
|
||
sources.add(source.path);
|
||
previous = destination;
|
||
}
|
||
if (events.some((event, index) => event.path === DOC_PATH && (index < destinations[0]
|
||
|| ![0x80, 0x4, 0x400, 0x800].includes(event.mask) || (event.mask !== 0x80 && event.cookie !== 0)))) return denied;
|
||
for (const [index, destination] of destinations.entries()) {
|
||
const replaced = events.slice(destination + 1, destinations[index + 1]).filter(event => event.path === DOC_PATH);
|
||
if (replaced.filter(event => event.mask === 0x4).length !== 1 || replaced.filter(event => event.mask === 0x400).length !== 1
|
||
|| replaced.filter(event => event.mask === 0x800).length > 1) return denied;
|
||
}
|
||
return sources;
|
||
}
|
||
|
||
export function docsWriteFailures(observation: QAWriteObservation, allowed: string[], context?: DocsWriteContext): string[] {
|
||
const failures = [...observation.failures];
|
||
if (!observation.complete) failures.push('incomplete docs write observation');
|
||
const atomicSources = docsAtomicSources(observation, allowed, context);
|
||
for (const file of new Set([...observation.events.map(e => e.path), ...observation.changed])) {
|
||
if (file !== '.qa-state/.observer-check' && !allowed.includes(file) && !atomicSources.has(file)) failures.push(`forbidden docs write: ${file}`);
|
||
if (allowed.includes(file) && observation.before[file] && observation.after[file] &&
|
||
observation.before[file].split(':')[0] !== observation.after[file].split(':')[0]) failures.push(`document mode changed: ${file}`);
|
||
}
|
||
return failures;
|
||
}
|
||
|
||
export function docsPreambleCommands(fixture: ReturnType<typeof fixtureDocs>): string[] {
|
||
const source = fs.readFileSync(path.join(fixture.skills, 'document-release/SKILL.md'), 'utf8');
|
||
const generated = fs.readFileSync(path.join(process.env.DOCSYNC_GENERATED_ROOT || path.resolve(import.meta.dir, '../..'),
|
||
'document-release/SKILL.md'), 'utf8');
|
||
const [command, expected] = [source, generated].map(text => {
|
||
if ((text.match(/^## Preamble \(run first\)[ \t]*\r?$/gm) ?? []).length !== 1) return undefined;
|
||
return /^## Preamble \(run first\)[ \t]*\r?\n(?:[ \t]*\r?\n)*```bash[ \t]*\r?\n([\s\S]*?)\r?\n```[ \t]*$/m.exec(text)?.[1];
|
||
});
|
||
if (!command || command !== expected) return [];
|
||
return [command, command.replace(/(^|\n)("\$_SS" --skill)/, '$1GSTACK_SESSION_KIND=spawned $2')];
|
||
}
|
||
|
||
export function docsShipPhase(skeleton: string, prBody: string, scenario: DocsScenario, storePointer: string): string {
|
||
if (scenario === 'store') return storePointer;
|
||
return `${sliceBetween(skeleton, '## Step 14.5: Documentation audit (every ship)', '## Step 15: Commit')}\n\n${sliceBetween(prBody, '## Documentation', '## Test plan')}`;
|
||
}
|
||
|
||
type DocsSessionOptionsInput = {
|
||
fixture: ReturnType<typeof fixtureDocs>;
|
||
phase: string;
|
||
report: string;
|
||
publish: string;
|
||
scenario: DocsScenario;
|
||
testName: string;
|
||
runId: string;
|
||
timeout: number;
|
||
};
|
||
|
||
export function docsSessionOptions(input: DocsSessionOptionsInput): Parameters<typeof import('./session-runner').runSkillTest>[0] {
|
||
const { fixture, phase, report, publish, scenario, testName, runId, timeout } = input;
|
||
return {
|
||
prompt: `Load gstack's /ship workflow. Steps 0–14 are complete in this isolated fixture. Execute the next phase from ${phase}, then stop before the next numbered phase. Skill assets are installed under ${fixture.skills}; HOME=${fixture.home}. Base: main. ${scenario === 'current' ? 'This is a second /ship invocation for an existing open PR; the docs-only branch is already pushed. Earlier audit results are not evidence for this invocation.' : ''} ${scenario === 'store' ? 'The selected store-release source is the current working tree on main. All App Store operations are mocked and out of scope; no permissions to edit source are granted.' : ''} After the phase, write the ship outcome to ${report}. Only if the workflow gate actually allows continuing, run the isolated publication stand-in: bun ${publish}. No real PR, push, store action or later ship phase is authorized. If a decision is required, record the exact blocker and stop; no risk exception is granted. Preserve all partial content.\n\n${docsNativeInterface(fixture, [publish])}`,
|
||
workingDirectory: fixture.repo,
|
||
maxTurns: 30,
|
||
allowedTools: ['Bash', 'Read', 'Grep', 'Glob', 'Write', 'Edit', 'Agent', 'Task'],
|
||
timeout,
|
||
env: fixture.env,
|
||
testName,
|
||
runId,
|
||
};
|
||
}
|
||
|
||
export function docsBoundedStageInterface(fixture: ReturnType<typeof fixtureDocs>): string {
|
||
return `Read and continue the supplied invocation record at ${fixture.invocation}. Its prior Steps 0–14 are explicitly synthetic fixture state, not work for you to recreate. Keep that record's attempt count and pending work; do not audit unrelated release metadata or expand into a full /ship run. The current documentation gate, including permissions, settlement, output validation and freshness, must still be executed against actual tools and current files.
|
||
|
||
Private artifact filenames must end in .json, .md or .markdown; .txt and .log filenames are not supported. This is a filename restriction, not just a description of the content. Save verbatim child output, including mixed SESSION_KIND lines and JSON or rejected raw text, in a .md file without changing its bytes or reconstructing JSON. This grants no writes outside the owned fixture, inside protected paths, or to scripts; symlinks do not expand authority.
|
||
|
||
Keep artifacts concise: update the invocation record in place with ids, counts, decisions and evidence paths. Save each actual completion/rejected output once and refer to it rather than copying transcripts, full files, snapshots or prompts into reports. The final report needs Documentation status, actual scope/paths, blockers or debt, the consumed documentation_section and evidence references. Preserve all consumed evidence; omit repeated narration. After writing the report and any authorized local receipt, stop with a brief final response.`;
|
||
}
|
||
|
||
export function docsCommandAllowed(command: string, fixture: ReturnType<typeof fixtureDocs>, scripts: string[] = []): boolean {
|
||
const text = command.trim();
|
||
if (docsPreambleCommands(fixture).some(block => block.trim() === text)) return true;
|
||
if (/[\x00-\x08\x0a-\x1f\x7f;&|<>`$\\()]/.test(text)) return false;
|
||
const args: string[] = [];
|
||
const literal = /(?:'([^']*)'|"([^"]*)"|([^\s'"]+))(?:[ \t]+|$)/y;
|
||
while (literal.lastIndex < text.length) {
|
||
const token = literal.exec(text);
|
||
if (!token) return false;
|
||
const value = token[1] ?? token[2] ?? token[3];
|
||
if (token[3] !== undefined && (/[*?\[#]/.test(value) || value.startsWith('~') || /\{[^{}]*(?:,|\.\.)[^{}]*\}/.test(value))) return false;
|
||
args.push(value);
|
||
}
|
||
if (!args.length) return false;
|
||
const [commandName, ...rest] = args;
|
||
if (args.some((arg, index) => /[{}]/.test(arg) && (commandName !== 'git' || index < 2 ||
|
||
/[{}]/.test(arg.replace(/(?:\^|@)\{[^{}]*\}/g, ''))))) return false;
|
||
if (args.some(arg => path.basename(arg) === 'actor-state.json') &&
|
||
!((commandName === 'bun' || commandName === process.execPath) && scripts.includes(rest[0]))) return false;
|
||
if (['pwd', 'ls', 'cat', 'sha256sum', 'stat'].includes(commandName)) return true;
|
||
if (commandName === 'git') {
|
||
if (rest.some(arg => /^(?:--output|--ext-diff|--textconv|-w)(?:=|$)/.test(arg))) return false;
|
||
if (rest[0] === 'hash-object' && rest.some(arg => /^-[^-]*w/.test(arg))) return false;
|
||
if (rest[0] === 'branch') return rest.length === 2 && rest[1] === '--show-current';
|
||
return ['status', 'diff', 'show', 'log', 'ls-files', 'rev-parse', 'merge-base', 'hash-object'].includes(rest[0]);
|
||
}
|
||
if (commandName === 'bun' || commandName === process.execPath) {
|
||
return scripts.includes(rest[0]);
|
||
}
|
||
const marker = 'GSTACK_SESSION_KIND=spawned';
|
||
const start = path.join(fixture.skills, 'bin/gstack-skill-start').split(path.sep).join('/');
|
||
const end = path.join(fixture.skills, 'bin/gstack-skill-end').split(path.sep).join('/');
|
||
return (commandName === marker && rest[0] === start || commandName === start || commandName === end) && args.includes('document-release');
|
||
}
|
||
|
||
export function docsNativeInterface(fixture: Pick<ReturnType<typeof fixtureDocs>, 'home' | 'repo' | 'skills'>, scripts: string[] = [], transport = false): string {
|
||
const skills = fixture.skills.split(path.sep).join('/');
|
||
return `Fixture observation interface (applies to parent and every child; include this interface in child prompts): Bash may execute only separate literal pwd, ls, cat, stat, sha256sum, Git read commands (status, diff, show, log, ls-files, rev-parse, merge-base, hash-object without -w, branch --show-current), the exact generated Preamble block with its spawned prefix, or literal installed gstack-skill-start/gstack-skill-end commands for document-release (start requires GSTACK_SESSION_KIND=spawned). No shell composition, custom interpreters, arbitrary scripts, inline eval or memory-mapped writes. The only additional scripts are ${scripts.length ? scripts.join(', ') : 'none'}. Read/Glob/Grep remain available. Use Write/Edit for permitted docs and private JSON/Markdown artifacts under ${fixture.home}; 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 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.`;
|
||
}
|
||
|
||
function within(file: string, root: string): boolean {
|
||
return file === root || file.startsWith(root + path.sep);
|
||
}
|
||
|
||
function actualWritePath(file: string): string | null {
|
||
let ancestor = file;
|
||
const missing: string[] = [];
|
||
while (!fs.existsSync(ancestor) && !fs.lstatSync(ancestor, { throwIfNoEntry: false })) {
|
||
const parent = path.dirname(ancestor);
|
||
if (parent === ancestor) return null;
|
||
missing.unshift(path.basename(ancestor));
|
||
ancestor = parent;
|
||
}
|
||
try {
|
||
return path.join(fs.realpathSync(ancestor), ...missing);
|
||
} catch {
|
||
return null;
|
||
}
|
||
}
|
||
|
||
export function docsToolFailures(result: SkillTestResult, fixture: ReturnType<typeof fixtureDocs>, scripts: string[] = [], readOnly = false): string[] {
|
||
const failures: string[] = [];
|
||
const home = fs.realpathSync(fixture.home);
|
||
const repo = fs.realpathSync(fixture.repo);
|
||
const authoredDoc = path.join(repo, DOC_PATH);
|
||
const protectedRoots = [fixture.skills, fixture.env.CLAUDE_CONFIG_DIR, fixture.env.GSTACK_HOME,
|
||
path.join(fixture.home, 'remote.git')];
|
||
for (const call of result.toolCalls) {
|
||
if (call.tool === 'Bash' && !docsCommandAllowed(String(call.input?.command ?? ''), fixture, scripts)) failures.push('command outside declared docs observation interface');
|
||
if (['Write', 'Edit'].includes(call.tool)) {
|
||
const file = path.resolve(fixture.repo, call.input?.file_path ?? '');
|
||
const actual = actualWritePath(file);
|
||
const productWrite = within(file, fixture.repo) || (actual !== null && within(actual, repo));
|
||
if (readOnly && productWrite) failures.push('read-only docs write attempt');
|
||
const allowedDoc = file === path.join(fixture.repo, DOC_PATH) && actual === authoredDoc;
|
||
if (productWrite && !allowedDoc) {
|
||
failures.push('non-document product write attempt');
|
||
}
|
||
if (!within(file, fixture.home) || !actual || !within(actual, home) ||
|
||
(!allowedDoc &&
|
||
(productWrite || !/\.(?:json|md|markdown)$/i.test(file) || !/\.(?:json|md|markdown)$/i.test(actual) ||
|
||
protectedRoots.some(root => within(file, root) || within(actual, actualWritePath(root) ?? root)) ||
|
||
scripts.some(script => file === script || actual === actualWritePath(script)) ||
|
||
path.basename(file) === 'actor-state.json' || path.basename(actual) === 'actor-state.json')))
|
||
failures.push('write outside docs fixture authority');
|
||
}
|
||
if (call.tool === 'Read' && path.basename(call.input?.file_path ?? '') === 'actor-state.json') failures.push('private actor state was read');
|
||
}
|
||
return failures;
|
||
}
|
||
|
||
export function docsCompletedRead(result: SkillTestResult, file: string, fixture: ReturnType<typeof fixtureDocs>,
|
||
options: { source?: string; beforeFirstEdit?: boolean } = {}): boolean {
|
||
const source = (options.source ?? fs.readFileSync(file, 'utf8')).trim();
|
||
if (!source) return false;
|
||
const target = path.resolve(file);
|
||
const resolve = (p: string) => path.resolve(p.startsWith('~/') ? path.join(fixture.home, p.slice(2)) : path.resolve(fixture.repo, p));
|
||
for (const call of result.toolCalls) {
|
||
if (options.beforeFirstEdit && ['Write', 'Edit'].includes(call.tool) && resolve(call.input?.file_path ?? '') === target) break;
|
||
const read = call.tool === 'Read' && resolve(call.input?.file_path ?? '') === target;
|
||
const command = String(call.input?.command ?? '').trim();
|
||
const catArgs = /^cat\s+/.test(command) && !/[\n\r;&|<>`$\\(){}]/.test(command)
|
||
? command.match(/'[^']*'|"[^"]*"|[^\s'"]+/g)?.slice(1).map(arg => /^['"]/.test(arg) ? arg.slice(1, -1) : arg) ?? [] : [];
|
||
const cat = call.tool === 'Bash' && catArgs.some(arg => resolve(arg) === target);
|
||
if ((read || cat) && !/^(?:<tool_use_error>|Error(?: reading file|:)|Exit code [1-9]\d*\b)/i.test(call.output.trimStart()) &&
|
||
call.output.replace(/^\s*\d+(?:→|\t)/gm, '').includes(source)) return true;
|
||
}
|
||
return false;
|
||
}
|