mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-04 18:36:54 +02:00
* test: delete test-infrastructure dead code (G) - exit-propagation drives the runner's real strict verdict (BunTestOutputClassifier + strictTestExitCode); delete the unused shardRunLooksTruncated predicate. - delete skill-coverage-matrix registry + its gate (nothing reads it; the floor already iterates skillCensus()). - delete touchfiles-facade export-parity tests (Bun fails missing imports at link time) and the duplicated E2E_TIERS tier-value test. - delete brain-cache-spec TRANSPORT_DEFAULT_POLICY, SKILL_RUN_RETENTION_DAYS and the now-unused BrainTrustPolicy type with their literal tests. AUTOPLAN_PREFLIGHT_BUDGET_BYTES stays: skill-preflight-budget enforces it against real resolver output. - delete audit-compliance's JSDoc-comment grep. * test: replace product tests that fake the product with real-boundary tests (F) - design: serve.test.ts drove an inline mirror server; now two tests run the real serve() on an ephemeral port (reload confinement, submit exit 0). - setup-gbrain: rollback + voyage tests execute the template-extracted init blocks (3 sites) instead of drifted local bash copies. - terminal-agent: internalHandler source greps replaced by a behavioral /internal/grant + /internal/revoke auth matrix (no/wrong/valid token). - /health: server-security-surface and the server-auth / security-audit-r2 / sidebar-tabs source greps fold into one liveness-only check on the real body; the L4 sidecar wiring gets a behavioral /pty-inject-scan test. - delete tautologies (browser-manager onDisconnect, memory-command #12), ios swiftui tap fixture self-check, memory-ingest put_page grep, detach source greps, sidebar-agent absence pins, dead-CSS pins + the dead CSS, security-audit-r2 Task 1 + the test-only meta-commands re-export, duplicate generated-SKILL.md checks. - make-pdf coverage-gaps cases move into their owner test files. * test: delete tests of dead eval code (A) - A1: the retired Eng lexical oracle (evaluateEngSeedCoverage, isEngSeedDecisionAUQ), the completion-handoff detector and the retained corpus had no paid caller since v1.87.6; delete their 26 replay files, ~2.6k helper LOC and fixtures, and the dead blocks in 8 mixed files (live hasNativePlanTerminal / batching assertions stay). - A2: dead viewport approvers in autoplan-artifact-permission and their 11 replay files + fixtures; recorder/launcher cases stay. - A3: never-wired oracles and seeders (autoplan-phase-order, eng-finding-fixture, ceo-paired-fixture, design-ui-scope, plan-skill-completion, pty-current-screen, required-reads, transcript-section-logger); plan-seed-submission now decodes through the production createPtyScreen; section manifests name their actual guard. - A4: zero-reference helper exports, plus execGit and invokeAndObserve found by the reachability pass. - 52 fixtures orphaned by the deletions; touchfile and selection-table entries for every deleted path. * test: clean up the paid eval lane (B1-B4, B6, B7) - B1: delete paid files that assert nothing or cannot pass meaningfully: skill-llm-eval-spec and skill-e2e-spec-execute (test.todo), gemini-e2e (+ gemini-session-runner; no gemini CLI in CI), ship-idempotency (red since v1.63), the two opus-4-7 *-sonnet overlay wrappers, conductor-prose (+ its source-evaluation replay), codex-e2e-plan-format; drop their keys, scripts and census rows. - B2: skill-llm-eval grades browse/sections/command-list.md with one union judge that also carries the baseline score pin; regression-vs-baseline deleted (paid run: pass, c4/c4/a4). - B3: memory-pipeline, ios-qa, ios-qa-swift-build and plan-tune-cathedral make no model calls; renamed out of the paid glob so they run on every PR. Swift builds need GSTACK_TEST_SWIFT=1; device stub deleted. - B4: codex-e2e*, outside-voice, aside and ios-device cannot run in the CI image; excluded from the weekly lane with a tracked re-entry condition. - B6: fold opus-47's negative routing controls into skill-routing-e2e journey-negatives (paid run: 3/3 unrouted) and delete the file. - B7: delete the never-green brain-privacy-gate eval; a free gstack-skill-start test now proves consent precedes artifacts egress. * test: retire the finding-count cluster and trim its helpers (C) - C0/C1: the five never-green evals (skill-e2e-autoplan-chain and skill-e2e-plan-{ceo,eng,design,devex}-finding-count) failed on harness and budget, never on skill behavior; delete them, their touchfile/tier ids, AUTOPLAN_CHAIN_BUDGET and the dedicated eighth periodic slice (--slices 7). - C2: delete the helper groups whose only paid consumers were those files (11 modules), trim claude-pty-runner and eng-seeded-coverage to the paid closure, and delete the free replay tests whose assertions exercised only that dead code (89 files, 135 orphaned fixtures). Blocks that used dead code only as input for a live subject keep their assertions: the multiSelect default moved to plan-review-decisions, runner PTY tests use inline caller policies, and the timer-safe budget checks moved to eng-finding-retry-budget. - The eight production-touching files stay except ceo-current-decision-record (its template read only feeds the retired counter). - CARVE_GUARDS.autoplan is behavioral 'none'; TODOS records the lost chain and per-finding cadence coverage with their re-entry tests. * test: fold per-incident replay series into their detector owners (D) Twelve detector families move into one owner test each: 73 incident files become describe blocks in ceo-section-loading-fixture (stale-fill race), model-overlays, coverage-audit-evidence, autoplan-phase-observer, native-auto-decide, outside-voice-evidence, eng-first-review, plan-count-completion, plan-count-file-permission, ceo-mode-option, plan-scope-selection and plan-count-prerequisite. Each block keeps its original code and fixture, so every case still runs; only tests asserting the incident file's own touchfile registration are dropped (41). Touchfile lists that named an incident now name its owner. * test: start the plan-count history PTY on its readiness marker (H) The fake CLI prints a startup marker and the runner waits for it instead of the fixed 8 s startup sleep (8.6 s -> 0.9 s locally). eng-semantic-terminal's sleeping registration cases went with C; plan-count-timeout keeps the fixed wait because it asserts deadline behavior. * test: derive paid touchfiles from each eval's static closure (E) touchfiles.test.ts now checks, per key, that the paid file's static test/helpers and test/fixtures closure (plus fixture paths it names in string literals) is covered, and names the file, path, chain and key to fix when it is not. Free *.test.ts files are no longer touchfiles, so editing a free replay test stops selecting paid evals: 950 entries removed, 653 real closure paths added. The hand-copied inventories go: periodic-fixture-selection, fake-impeccable-touchfiles and 45 per-file selection examples. Selection for the sample edits (plan-eng-review template, claude-pty-runner, plan-count-fixture, gstack-config) loses no case under either profile. CONTRIBUTING documents the rule and its lower bound. * test: skip hollow tier shards and census judges in the paid planner (B5) A paid file is now skipped for a tier lane only when every E2E id it registers is known statically and none has that tier; ids come from the touchfile registrations and literal testName/*IfSelected arguments, so a comment or skill path that quotes another id cannot unschedule it, and computed names keep today's scheduling. --list and the manifest show each skip as "skipped: no E2E_TIERS id has tier <tier>". The weekly gate census drops the LLM judges (--skip-judges); they still run in the periodic census and PR gate lanes. Gate lane 52 -> 42 files, census 41; periodic 77 -> 69. * test: run seven paid evals on the current default capture model (B8) skill-e2e-{auq-matrix,plan-format,qa-bugs,retro,workflow} pinned claude-opus-4-7 and skill-e2e-office-hours plus -brain-writeback pinned claude-sonnet-4-6; none tests a historical model, so they now capture with resolveEvalModel('capture'), and the free harness tests that execute these registrations receive the same resolver. The paid re-pin run passed all of them. skill-e2e-{design,office-hours-phase4,plan-prosons,plan} keep claude-opus-4-7: six of their cases failed on the default model (three timeouts, a missing report file, a format miss and a posture score of 3), so per the plan's fallback they keep their pins with a TODOS entry. The pre-spend estimate and drop threshold are in docs/test-audit-2026-09.md. * test: guard the reduced suite against new test-of-test files - test/test-of-test-ratchet.test.ts records the 228 free tests that import only test/ code and fails on a new one, naming the owner test to extend instead; a stale baseline entry fails with the remove instruction. - test/helpers/resolve-repo-path.ts is the one specifier/literal resolver for the ratchet and the touchfile closure invariant, with its own unit tests. - CONTRIBUTING "Test tiers" describes the paid-failure workflow (fix, then one row in the detector's owner test) and the ratchet; TEST_PORTFOLIO gains the detector -> owner-test table and no longer claims an Autoplan chain eval. - TODOS: automatic exclusion policy for chronically red periodic files (P3), the deferred native-completion table collapse, the unused CEO payment seeder; the PTY readiness item is narrowed to the paid runner. - docs/test-audit-2026-09.md collects the triage, security mapping, inventories, selection proof, behavior-commit decisions and retained false positives. * v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals Release metadata for the test-reduction branch: VERSION 1.91.8.0 (1.91.7.0 is claimed by #2983), CHANGELOG with the measured before/after table and a contributor section, durations re-recorded on Ubicloud standard-16 (857 files, 0 failures), the agents digest, CONTRIBUTING's after-measurement row, the B8 fallback TODOS entry, and the after metrics, kept-vs-plan notes, B8 run and census estimate in docs/test-audit-2026-09.md. * fix(ubicloud): skip retrieval globs that match nothing instead of reporting a failed pull * test: pin DISABLE_AUTOUPDATER in hermetic env and capture corrupt-seed warning Both EVALS_HERMETIC branches of buildHermeticEnv now carry DISABLE_AUTOUPDATER=1 (the allowlist scrubbed the workflow's copy, so every PTY screen showed the updater's npm-prefix failure). Per-test overrides still win. The corrupt durations-seed test now captures its expected warning and restores the console spy. * style(cso): format lib/cso TypeScript with pinned Prettier Mechanical reformat only. Minified transpile output is byte-identical for 21 of 22 files; witness.ts differs only in three regex flag orders (/mi -> /im), which JavaScript canonicalizes. Source-text assertions over lib/cso now compare whitespace-insensitively with the same tokens. * fix(cso): import join for compiled-launcher assertion witnesses Compiled installs always take the non-Bun branch, which called an unimported join and threw before any runtime-tested assertion could be witnessed. The child command selection is now a pure, platform-aware function; a missing sibling launcher fails with its expected path. * fix(browse): make connect --supervise actually respawn a crashed server The supervisor respawned with a block-scoped env that no longer existed, so every attempt threw and the loop gave up after five tries. The headed env is now one pure helper used by connect and respawn, the loop is an injectable runHeadedSupervisor with behavioral tests, failures name the daemon log and relaunch command, and connect's usage advertises --supervise. * test: one finite PR world for the shared-libs fixture; name dual-voice probe evidence The shared-libs shim served 2 PRs for pulls?state=all and endless full pages for state=open. gh pr list, pulls?state=open|all|closed (per_page/page, short last page, direction) and search/issues now page one deterministic table: PR 7, 600 older open PRs, PR 42 and 3 closed PRs, so five 100-item open-metadata pages still leave older open PRs unchecked. The Contents API lists pinned directories (the captured attempt got 404 for contents/ and contents/src while files resolved, then fell back to a raw host), unknown endpoints return 404 instead of repo metadata, and the read-only detector is unchanged. Free tests cover view agreement, the budget bound, gh/curl agreement and the empty world. Dual-voice outside-voice failures now report probeToolUseId, probeMode and the canonical-match result with the reason the probe output was rejected. * feat: require a zero-error product typecheck and a test type-debt ratchet Adds tsconfig.json (strict) over product code, fixes its remaining 90 diagnostics (type-only, interface corrections, and explicit narrowing), and adds a typecheck job to the required free-tests aggregate running bun run typecheck, the test-code ratchet (identity -> count baseline, fails on new, repeated, or unlocked fixed diagnostics), and the lib/cso format check. Reuses fixes from #2447 where they still applied. * test: follow the headed env helper and the typecheck gate in source-shape checks * fix(test): pin the package.json change kind in shared-input selection tests computePaidCaseSelection read the version-only exemption from git even when changed files were injected, so the shared-input test failed on main and on version-only branches. The exemption is now an optional input; the test pins a real package.json change and covers the version-only case. * test: judge plan-count completion on structured evidence, not wording Replaying run 36385945043's two Design attempts showed the existing routes rejected correct endings: attempt 1 at the typed-completion path field ('- Reviewed plan written to …' is not a 'Plan written to' line), attempt 2 at the leading-fence veto (its final message opens with the dashboard). nativePlanTerminalPreconditions is the structural prefix of hasNativePlanTerminal (behavior unchanged). structuredPlanCompletion adds, inside the existing nativeSummary branch: a complete report (Design binding for Design), a completed review-log row for the expected skill appended during this attempt under the child's GSTACK_HOME/project slug (resolved with bin/gstack-slug) and stamped with the fixture commit, timed between the report/last answer (second resolution) and the final native message, a final message with stop_reason end_turn (now carried on public transcript messages), and no visible question or permission prompt. Timeout summaries add idleFor and lastTerminalCandidate. Terminal and throw captures copy the plan file and review-log rows into the artifact directory; copies are best-effort and recorded in evidence-copy.json. Free regressions: both captured Design endings (trimmed fixture with provenance; report, row and end_turn reconstructed and labelled), the negative controls, and real-PTY completion/timeout runs through the real review logger. * test: structural Design count boundary; TODO proposals are not findings Replaying run 36385945043 through the Design count predicates: routing, focus and learnings setup was not recognized as setup, Issue 1 was counted pre-review in both attempts (the boundary fired on it), and attempt 2 counted the Font TODO proposal as a finding (review=4 and review=5 for five issues). The paid caller now starts review at the first answered native decision that is not setup (recognized packet, or setup header/question ID), a completion handoff, artifact rendering or a TODO proposal (the review's Add to TODOS.md / Skip / Build it now menu). TODO proposals are recorded as administrative extra decisions. The replay asserts each counted call: both attempts review=5 (Issues 1-5). isDesignCountFirstReview and its controls are unchanged. * test: CEO classifier throws name the question and matched predicates Replaying run 36385945043's FAN-1 and ERR-1 throws (ledger rows reconstructed from rendered diffs) through ceoPaymentFinding: the email obligation's row, subject, option and proposal predicates pass and the ELI10 explanation-defect predicate fails first ('lets that exception fly out', 'the error bubbles up'). Binding the defect to the named ledger row instead (the planned fix) was tried and reverted: scoped to the email seed it flips 30+ existing cf74 still-rejects replays, which require a vocabulary-free, ledger-bound email question to earn credit only through a complete saved comparison. With FAN-1's rendered currentDecision payload reconstructed, the recorded- decision path counts it, so the real saved plan (not uploaded) must have differed; failure artifacts now retain it. The classifier stays fail-closed and unchanged. Its throw now prints the header, the first 200 question characters and each obligation's predicate results. Free regressions with provenance and negative controls: an unrelated question, an email question whose row says it is already rescued, and a ledger ID whose row belongs to another seed. * chore: regenerate the test type-debt baseline on top of #2994 * fix(typecheck): strip the checkout root from ratchet diagnostic identities * fix(test): recognize ledger row-ID split candidates so collection stops at the last ACK Run 36385945043's split-overflow case asked all five candidate decisions by 8m55s, but the live candidate check required the question to open with "E1:" and every option to be a known disposition. The skill cited ledger row IDs ("D2.1 — R-E1: …") and offered "Hold, discuss first", so no candidate was recognized and the attempt ran the whole review (1302s). Identity now comes from the native header; the question must open with that candidate's ledger reference, name only that candidate, and offer exactly one include, defer and cut disposition. The selected answer must still be one of those three. The semantic evaluator and every existing negative control are unchanged; a trimmed capture from the run adds the positive case and four row-ID negative controls. * fix(test): stop the eng batching eval once its floor is proven The case's only verdict is reviewCount >= FLOOR (3). Run 36385945043 had three distinct acknowledged review decisions at 6m41s but kept answering until the ceiling (7) at 12m13s. The registration now passes the runner's existing isCollectionComplete stop once FLOOR non-setup, non-administrative review decisions are acknowledged; the floor check, ceiling, budget and counter are unchanged. A child-process registration test proves the stop predicate and that below-floor and timeout outcomes still fail. * test: add the non-blocking 'marathon' E2E tier Full start-to-finish flows move out of the blocking lanes. E2E_TIERS and E2ETier gain 'marathon'; describeE2ETier('marathon') is enabled only when EVALS_TIER=marathon, so the gate/PR and periodic lanes (and the gate census) never run those cases. The PR profile accepts marathon ids as scheduled elsewhere and defers them with their own reason, even on full fallback. * test: move the full office-hours workflow to marathon; add a periodic design-draft checkpoint The full startup workflow runs 1–3 real spec-review rounds (~280s each) and hit its 1200s capture in run 36385945043 at finalize. Review depth is the product's loop, so the case cannot fit a blocking lane without cutting rounds. It is now marathon tier with every assertion unchanged. skill-e2e-office-hours-design-draft.test.ts (periodic) runs the same fixed interview only through the Write that creates the design (269s in that run) and applies the full validator's design-draft checks, the required section reads and the launch/foreign-skill-read guards. validateOfficeHoursDesignDraft is extracted from validateOfficeHoursCompletion, which still applies it. Selection: office-hours-design-draft is registered periodic; the marathon-only file is already excluded from the gate and periodic plans by the B5 planner rule. Tier-alignment regexes and the valid-tier check accept 'marathon'. A type-only cast in plan-scope-selection.test.ts removes a diagnostic whose union print order made the ratchet identity unstable; baseline tightened. * test: supply the split-overflow fixture's HOLD SCOPE mode as a prerequisite The split actor always answered 0E's mode question with HOLD SCOPE. The skill skips that question on an explicit choice, so the fixture now states it and the attempt starts at the five candidate decisions (about 1.5 min earlier in run 36385945043). Candidates, actor policy, floor and semantic evaluation are unchanged; the fixture test pins the supplied choice. * test: start the eng batching eval with its setup prerequisites supplied Routing setup and cross-project learnings (D1/D2 in run 36385945043) are never counted and are not what the case measures. The registration now uses the runner's existing preconfiguredReviewActor so the attempt starts at the review; engSetupAUQ still vetoes any late setup question. The registration test pins the option. * test: count the design-draft paid file and defer marathon ids in PR selection pins The discovered paid-file census grows by one (skill-e2e-office-hours-design-draft). Full-fallback PR selection defers every non-gate id; the shared-input pins now expect periodic and marathon ids there. * fix(review): resolve the judged revalidation, setup-authority, plan-gate and findings-record ambiguities The census review workflow judge scored clarity/actionability 3 on both attempts: smoke-clock limits appeared to forbid post-repair revalidation, the caller deadline was undefined, 'ask for setup' conflicted with the report-only browser rule, fallback-sourced HIGH discrepancies had no gate decision, and the Step 5.8 record omitted adversarial findings. * fix(office-hours): load the builder section for every builder-mode reply Both census builder-wildness attempts answered a direct request for adjacent unlocks without reading phase-2b-builder-brainstorm.md, whose trigger read as applying only to the generative questions. * fix(sync-gbrain): define Step 4 helper args and one atomic write path Both census read-ready attempts spent turns reading the helper source to resolve <user-args>, inspecting fixture internals kept inside the repo, and reconciling 'Read + Edit' with the tmp+mv atomic write, then hit max turns before the verdict. * refactor(evals): share the import-closure walker and add the E2E shard reuse identity sourceDependencyClosure moves from the workflow-judge adapter into scripts/eval-input-cache.ts unchanged, so judge keys stay byte-identical. scripts/e2e-shard-reuse.ts builds the consumed-input identity of one PR-lane E2E shard (test import closure, every registered case's touchfiles, globals, runner/workflow/setup actions, child env pins, CI image, Claude CLI) and fails closed on anything unknown. Marathon joins the always-fresh purposes. * feat(evals): ~12-minute blocking paid lanes and a non-blocking marathon lane - Planner budget mode (--slice-budget S --jobs J): recorded per-tier wall times pack into as many ~9-minute executors as the work needs; the plan records per-slice estimates and the CI job timeout (supervised worst case + 20 min). evals.yml and evals-periodic.yml derive matrix size and timeout-minutes from it; max-parallel covers every slice at once. - Case shards: plan/design/review-army/shared-libs(-paths) run one registered case per process (<file>#<case id>, exact name pattern, exactly one case). - Retry rule: a timed-out attempt is a verdict. Only files whose every case budget is CAPTURE tier or shorter keep one retry; walls shrink to match. - Marathon tier: positive selection, excluded from gate/periodic planners, run by the new evals-marathon.yml (weekly + dispatch, fresh, own report). - PR-lane E2E reuse of verified first-attempt passes on identical inputs; the report rejects reuse outside the fast PR profile. - Duration seed from census run 36385945043, per tier and per case shard. * docs: blocking lane budget, marathon lane, retry policy and E2E reuse * chore(typecheck): lock in two fixed test diagnostics * fix(ci): drop a duplicated env/jobs block in evals-marathon.yml * test(ship-docsync): shard the doc-sync lifecycle by case and drop the duplicate dispatch-only case ship-docsync ran the same fixture and prompt as ship-docsync-completion and asserted a subset of it. The file now runs one case per process, so its lane wall is its longest case instead of half the sum of thirteen. * fix(evals): plan CI-unrunnable cases as excluded entries, not empty case shards design-review-fix drives the Aside browser and registers test.skip on Linux runners, so its case shard executed zero cases and failed the exact-one-case check in proof census 36597762183 (eval-slices 6). CASE_CI_EXCLUDE (reason + tracking, beside PERIODIC_CI_EXCLUDE) now turns such cases into excluded manifest entries that --list and the manifest surface; every planned case shard still must execute exactly its case. * docs(todos): list the case-level Aside exclusion with the CI-unrunnable evals * fix(plan-ceo-review): restore experience-first expansion framing, require the mode handoff, skip pacing menus Census 36597762183: both mode-routing runs logged provenance and moved on without the mandated handoff chat; the EXPANSION run asked an unauthorized batch/narrow pacing menu instead of the first per-addition question; the expansion-energy proposals led with the spec because v1.87.6.0 dropped 'lead with the felt experience'. The HOLD review detector also rejected a decision whose grounding line named no plan file although the owned source Read binds it. * test(outside-plan-disabled): bind quoted prior-record values by their sentence, not phrase order The parent obeyed the off switch and twice named the seeded completed record as pre-existing, once with the quotation after its owner and once with slash separators; the order-specific stripper counted both as current completion. Timestamp, location, current-claim and value-match controls still reject. * test(outside-plan-disabled): compare named record timestamps as instants; negated authorship is not a current claim The repair rerun named the seeded record by its ISO second (2026-09-29T16:58:52Z vs .727Z) and said 'I did not write'; both were misread as a foreign timestamp and a current write. * test(ceo-section-loading): recognize an arrow-ordered stale-fill execution by event roles The census review traced the seeded race as 'R1 miss -> R1 store read (v1) -> W commit v2 -> W cache.delete -> W fulfills -> R1 cache.set(v1) -> R2 (begun after W) hits v1', but the in-flight gate only accepted race vocabulary or fixed sentence shapes. Order, actor, version and dismissal mutations still fail. * test(design-floor): answer the seed-declared all-seven 0D focus menu while it is pending The actor declares 'Design: review all seven dimensions', but its picker reused designReviewSetupAUQ, which only matches already-answered calls (and a narrower header/label set), so the pending D1 focus menu was never answered and the case waited out its 609 s deadline. The skill's Step 0D requires asking; the fixture now answers it. * test(ceo-mode-routing): accept the skill-mandated Note form and Recommendation reason as HOLD posture HOLD Defer/Keep briefs must use 'Note: options differ in kind' (preamble), but the answered-HOLD path demanded a Completeness score, rejected a one-line Net with a semicolon, and read posture only from ELI10. The rerun's brief applied HOLD SCOPE in its Recommendation reason. Revert the ineffective 'always'/'handoff chat' wording: two runs still skipped the mode handoff. * test(qa-bugs): keep claude-opus-4-7 after qa-b6-static stalled on the default model qa-b6-static timed out on claude-fable-5-1 in census 36597762183 and in one of two targeted reruns. Both times the stream stopped mid-message with no pending tool, right after the model found the disabled submit button, and stayed silent until the 300 s deadline. Per the B8 fallback, re-pin with a TODOS entry; budgets and retries are unchanged. A rerun on opus-4-7 passed (125 s, 5/5 detected). * test(evals): add E2E_KINDS, BEHAVIOR_WHY, EVAL_POLICY and CASE_QUARANTINE skeletons Every E2E_TIERS and LLM_JUDGE_TOUCHFILES key starts as 'rule'; BEHAVIOR_WHY and CASE_QUARANTINE start empty. EVAL_POLICY pre-registers the approved panel (3, majority 2), quarantine entry 0.95/10 and exit 0.97/10, 10% cap, 8-weekly-run expiry, Fisher drift alarm and one INFRA re-dispatch. * test(evals): add trial records, panelVerdict, expectContract and trial-outcomes JSONL EvalTestEntry gains case_id, kind, trial, panel, failure_class and policy_version, stamped from the runner's TRIAL_ENV on isolated trial shards. panelVerdict() is the single verdict function (INCOMPLETE on missing or duplicate trials, contract veto at any count, quarantine hard-break rule, INFRA/INCOMPLETE machine classification). expectContract() records failure_class 'contract' on the collector entry and a sidecar before throwing. trial-outcomes JSONL has a fail-closed writer and a data-only reader. * test(evals): pin the fail-closed rule-shard gate through the real --report path Synthetic slice artifacts for rule fail, timeout, missing slice, unreported entry, hollow, never-started, collector failure and wrong-slice reports all exit red before the panel-verdict gate change lands. * test(evals): retire every paid automatic retry Paid evals never retry (approved 2026-09-29): delete SHORT_CASE_RETRY_FILES and retriesWithinCaseCap, drop the retry fields from the registered wall rows (walls now cover one run plus reserve), make retriesForFiles return 0, pass --retry 0 explicitly, and drop --retry 1 from the package.json paid scripts. Add the eval:pass-rates alias. Tests that pinned the old retry allowance are updated as a policy change; review-finalization-budget now proves late-result recording under the production zero-retry arguments. * test(llm-judge): sample every judge as a pre-registered 3-sample panel Each of the 24 skill-llm-eval judges now draws EVAL_POLICY.judge.samples independent samples of the same prompt concurrently inside the unchanged JUDGE_MS budget. Numeric dimensions gate on the per-dimension panel mean against the unchanged threshold; booleans (would_browse, consistent) on a strict majority. An erroring sample fails the whole panel and is never resampled; a refusal is an unscored panel only when every sample refused. callJudge's 429 backoff stays: it is transport before any model output. The workflow-judge cache stores and validates only complete panels, and its identity now records the panel and zero file retries. Harness tests that pinned one provider call per case now pin the panel size. * test(evals): classify every live case and re-select a case when its kind changes E2E_KINDS: rule by default (191 E2E ids), 22 behavior cases whose verdict is a live model choice with an acceptable sub-100% per-trial rate, each with a BEHAVIOR_WHY tolerance, and 25 judge entries (the 24 workflow judges plus the fixed-fixture llm-judge-recommendation rubric check). Contract-shaped cases (ask-before-decide, plan-mode no-writes, mandated steps, secrets, the batching floor) stay rule. Behavior requires a known literal registration and an exact Bun test name so the case runs as its own trial shard. Map-diff selection now diffs E2E_KINDS and BEHAVIOR_WHY per key, and a base revision without them selects every key, so a kind flip runs the panel it introduces. test/eval-kinds.test.ts enforces coverage, tolerances, isolatability and the reviewed counts, printing the literal to add. * feat(evals): per-case pass rates with Wilson intervals, identity series and quarantine policy scripts/eval-flake-rank.ts becomes eval:pass-rates (eval:flake-rank stays an alias, and the legacy aggregate stays exported). It reads eval-store's trial-outcomes JSONL from the last N completed evals-periodic runs on this branch and main (gh, downloading only the trial-outcomes artifact, cached and size-capped, parsed as data), plus local eval dirs, and prints per-case per-trial pass rates with 95% Wilson intervals. A series is a case's own touchfiles minus GLOBAL_TOUCHFILES (caseSeriesIdentities, for the report job to stamp), per model, CLI version and policy version. Labels: INCONCLUSIVE, BROKEN, FLAKY, FAILING, PASSING. --backfill imports legacy slice artifacts as pre-policy trials (first attempt only, attributed by registry id, never guessed) for display only. --gate fails with ACTION REQUIRED on post-policy evidence only: drift below the quarantine entry rule, a rule case behaving like behavior, a one-sided Fisher drop against the previous identity (Holm-controlled), and quarantine entries that met their exit rule, expired after 8 weekly runs, broke the 10% tier cap or are invalid. CASE_QUARANTINE entries now carry a failureClass (detector, harness or model-latency); a product defect has no class and is never quarantined. The policy test pins EVAL_POLICY's approved constants. * feat(eval-pass-rates): attribute legacy records by the exact slug of their display name * ci(image): pin Claude Code 2.1.284 so the eval model is recognized 2.1.251 logs [claude-code:unrecognized_model] for claude-fable-5-1, the eval capture/judge default. 2.1.284 does not. The gate PTY smoke subset (plan-ceo/plan-devex plan-mode, plan-mode-no-op) parses on the new TUI; plan-design-review-plan-mode passed at 293 s on 2.1.284 and timed out at 300 s on 2.1.251 on the same tree. * test(eng-batching): grade the floor once the review report is complete A completed GSTACK REVIEW REPORT ends the review, so the review-question count is final there. Run 36606688266 wrote its report at 1,248 s and closed the session at 1,318 s; the case now stops collection and applies the unchanged floor at the report instead of waiting out the session. No budget changes. * test(eng-batching): bind unsourced native briefs through the report's target Run 36606688266 asked ten separate native review questions (D1-D9 bound to ledger records R1-R9) and failed reviewCount=0 < FLOOR=3: its briefs named the plan by title instead of citing PLAN.md, its report declared 'Review target (fixed): PLAN.md' under '# Engineering review: <plan>', and it kept an unfenced copy of the plan's own H1. The named-source route now accepts those spellings and non-inline ledger briefs. The same replay rejects a foreign, mixed, duplicate or missing target, another plan's title or copied H1, a brief naming another plan or file, a mismatched saved brief, and re-asks. The run-36597762183 capture still counts 3. * fix(plan-design-review): treat a designer with no API key as unavailable Both proof runs (36597762183, 36606688266) printed DESIGN_READY, hit 'No OpenAI API key found' on the first $D variants call, then hand-built HTML/CSS wireframes, screenshots and a comparison board for ~195-245 s before the first review question; the second run timed out at 600 s. A failed first generation now takes the existing text-only path, and the skill forbids substituting hand-built mockups. * fix(deslop-shared-libs): read related sources together within the turn limit Run 36606688266's opportunity audit read sixteen sources one per turn and stopped at error_max_turns; the passing run 36597762183 read the same files in three batched commands. The skill now says turns are bounded and asks for parallel reads or one read-only command per step. * test(ceo-mode-routing): submit a mode review that scrolled past the viewport Run 36606688266 bundled routing, learnings and the mode choice into one native call. Its review panel was taller than the terminal, so the tab bar scrolled off, ceoModeSubmissionInput returned null for 240 s and HOLD SCOPE was never submitted ('no posture match'). With no bar on screen the viewport must still end at the focused Submit prompt, and the accumulated screen text supplies the one complete panel, authenticated exactly as before. Replay controls reject another mode, an unoffered answer, an altered question, a quoted panel, trailing output, a moved cursor and an answered or changed call. * docs(evals): document the pre-registered verdict policy, quarantine, pass-rate history and arithmetic AGENTS.md replaces the retry rule with the approved policy text (no retries; kind fixes trials; no added trials, samples or dispatches after a result; quarantine by CASE_QUARANTINE only; one INFRA/INCOMPLETE re-dispatch) and notes that a pre-registered fixed panel is not rejudging. CONTRIBUTING gains the kind rules, the judge panel, eval:pass-rates and an 'Add a paid eval' checklist. TESTING_INTERNALS describes verdicts, quarantine, history and the arithmetic, including the rule term: 1 trial vs 2-of-3 red rates at p = 0.99/0.95/0.90/0.70/0.30 and lane all-green probabilities for the current 191 rule / 22 behavior / 25 judge registry. * feat(evals): trial planner, slice exit split and panel-verdict report Planner: behavior and quarantined cases become panels of isolated trial shards (<file>#<id>~t<N>) bound by EVALS_SELECTION_JSON=[id] and the exact test name; the file shard excludes them by name. Trials of one case never share a slice, result slugs are unique, panels are validated whole, unknown registrations throw, and the planner prints a capacity preflight. Executor: each trial shard gets its TRIAL_ENV identity and a trial record (outcome, failure class, cause, cost); every shard writes a JUnit report. The slice exit now means execution completeness: a failed rule shard or a trial without a record reds the runner, a failed trial does not. Report: panelVerdict() decides every panel of the first run attempt (later attempts are reported, never replacing it); rule shards keep the unchanged fail-closed checks; collector records all count (no last-attempt wins); census runs enforce the quarantine cap and expiry. It writes collector-outcomes v2, trial-outcomes.jsonl (trials plus JUnit rule/judge cases), report-summary.md, and one headline + failure block with rerun commands, and flags INFRA/INCOMPLETE-only reds for the one re-dispatch. The fail-open suite gains the panel cases: behavior 1/3 red, 2/3 green with its failed trial shown, missing trial INCOMPLETE, contract at 2/3 red, quarantined 1/3 green, 0/3 and contract red, missing slice red, and a later attempt never replacing the first. * chore(evals): refresh paid duration seeds from proof runs 36597762183 and 36606688266 Both tiers, merged in run order (the later run wins). Notable: split-overflow 1332s -> 504s, section-loading 604s -> 342s, mode-routing 575s -> 444s; multi-finding-batching 734s -> 1318s (its red path in run 36606688266). * feat(evals): stamp trial series identities and fit panels to the live registry - scripts/eval-trial-series.ts stamps series_identity (eval-flake-rank's caseSeriesIdentities) on a report's trial-outcomes JSONL as its own step, keeping the history tool out of the paid runner's closure; TrialOutcomeRecord gains the optional series_identity field. - Slice-count plans let a registered trial spill into an ordinary lane when its siblings hold every long lane, so panels never share a runner. - Re-audited test-selection.ts (Stream B added the E2E_KINDS/BEHAVIOR_WHY map-diff; no new module loading) and repinned its hash. - Detach and release floors now count trial shards (66 periodic trials in 22 panels): periodic floor 33,821s, still under eval:bg:periodic's 67,380s. - Coordination fixtures supply the executor's trial records. * ci(evals): attempt-scoped artifacts, verdict-v2 PR comment, weekly pass-rate gate and one INFRA re-dispatch - Slice, census and marathon artifacts carry -a<run_attempt>; reports download them per artifact (no merge), so records never overwrite and a re-run never replaces the first attempt's verdict. - Planners pass --max-parallel for the capacity preflight (24/16 unchanged: the refreshed periodic plan needs 24 slices, the gate census 12). - PR comment: jq-only job reads collector-outcomes v2 (headline, sanitized failure block); the group_by(.name)|last recomputation is gone. - Reports stamp series identities, upload trial-outcomes-* for history, and shard logs upload always (a failed trial no longer reds its runner). - Weekly report: headline + failure block of both lanes in the issue body, the eval:pass-rates --gate step (fails closed without history), close the issue on a green run, and UC-E1: when every red is machine-classified INFRA/INCOMPLETE, one re-dispatch as a new run in its own concurrency group (redispatch_of), both runs reported. * feat(evals): planner-side whole-panel reuse and negative receipts The planner job restores this PR's receipt store once and ships a single filtered set with the plan: a pass or panel receipt with a same-or-newer FAIL for its input identity is dropped, and a panel receipt ships only as a whole PASS panel (re-verified with panelVerdict) from one run. Executors read only that set (no per-slice cache restore or save), so every trial of a panel sees the same receipts; a trial reuses its own record from the panel receipt, keeping a split PASS's failed trial. Trial identities drop the trial index (run-scoped) and bind the panel policy. Executed shards carry their input identity; the report turns a whole fresh PASS panel into a panel receipt and a FAIL panel or failed rule shard into a negative receipt, and marks a panel that mixes reused and fresh trials INCOMPLETE. The report job merges plan, slice and report receipts (newest per file) and saves one store per run. Also fixes two TS2352 casts in browse/test/dia-macos-qualification.test.ts whose diagnostic text drifted with program order (baseline locked, fix only). * feat(evals): --case/--trials local diagnosis and panels in local sharded runs bun run scripts/test-paid-shards.ts --case <id> [--trials N] runs N independent trials of one case through the CI panel runner (trial shards, TRIAL_ENV identity, name-pattern isolation) and prints its panelVerdict(); N defaults to the case's policy panel and CI never reads it. The local sharded path (test:gate:sharded, test:periodic:sharded) now plans the same trial shards and exclusions as CI and exits on execution completeness plus panel verdicts. * test(pty): grant an owned Create pane whose title row is cropped The targeted batching rerun on Claude Code 2.1.284 left its first report Write unanswered for 1,372 s and timed out: the viewport began at the pane's relative file row and rule, with the 'Create file' title cropped above, so the preview parser rejected the file row as foreign. That row must now resolve to the owned path and is skipped before the unchanged line-by-line preview match. Replay controls reject another file, another directory and an edited preview row. * fix(evals): tsx-safe generics in eval-flake-rank, legacy artifact names, no-retry wall docs * test(evals): record the read-only and detector-row invariants as contracts shared-libs-opportunity-judgment and review-design-lite are behavior cases: their recommendation and checklist judgments may vary, but the read-only invariant (commands, provider requests, fixture bytes, hooks, state) and the deterministic fake-engine detector rows are contracts. Both now go through expectContract, so any failure vetoes the panel. * test(judges): sample the recommendation rubric as a panel; never re-ask armJudge llm-judge-recommendation is a judge case: each fixture now draws a 3-sample judgePanel, gates reason_substance on the panel mean and the present/commits/has_because checks on a 2-of-3 majority, thresholds unchanged. armJudge no longer re-asks on a malformed verdict; it is a failed sample, as the judge policy requires. * test(evals): record a pre-turn API or CLI failure as infra recordE2E sets failure_class 'infra' on a failed session whose runner reports error_api, timeout_startup, error_output_stream or a non-zero CLI exit with zero turns and no assistant event. A model refusal, a timeout after model work, max turns, or an explicit caller pass/class keeps its ordinary classification. * test: pin every-record outcome counts and the twelve doc-sync callbacks * test(eng-batching): read the report target as a field, not a spelling The next targeted rerun (Claude Code 2.1.284) again asked eleven separate native questions and again counted zero: its briefs named no plan and its report declared '- **Review target (fixed):** `/abs/PLAN.md`' under '# Eng Review — PLAN.md: <plan>'. An unsourced brief now inherits the one current target field that names a PLAN.md file, whatever its list or emphasis markup; its ledger record still supplies the cited finding and must reproduce the brief exactly. A brief that names its plan must still match the report title. Replays of all three captures count 9, 9 and 3; controls reject a foreign, duplicate or missing target and an archived title. * fix(evals): --case list mode and name precheck; case-shard qa-callers; refresh batching and design-with-ui seeds * chore(release): v1.91.9.0 * test: settle the post-response composer before seeding; give the TPA recorder adapter its infra helper submitPlanSeed accepted a stale empty composer when the transcript recorded end_turn before the CLI repainted (late-repaint-typed-current fails 5/5 on the old helper, passes 5/5 now). The TPA recording fixture extracted recordE2E without isPreTurnInfraFailure, so every failed case threw before recording. * test(autoplan-dual-voice): unwrap Claude Code 2.1.284 subagent hand-back frames; accept read-only probe diagnostics; record before asserting Census run 36626737820: the native CEO report arrived framed and indented, so its INPUT line never matched, and the model's exact probe plus two variable echoes was not canonical. A column-zero line inside a frame, command substitution, backticks, redirects, assignments, CODEX_MODE echoes and output line-count mismatches stay rejected. The failure now records before asserting. * ci(image): keep Claude Code 2.1.251; test(ceo-mode-routing): keep HOLD's own deferrals in scope before assessing its rigor decision 2.1.284 enables per-turn effort for claude-fable-5-1: in gate census 36626737820, 66 of 84 sessions ran longer than on 2.1.251 (+20% session time, +32% thinking tokens) and 11 cases timed out on unchanged budgets. HOLD SCOPE's 0G step asks its own defer/keep menu; the actor answered it Defer and the assessment then judged that scope question as the rigor decision. The actor now answers that menu Keep and assesses the next one. * test: attribute quoted prior-record field lists, state the judge reason bound in its schema, move split-overflow to marathon Census 36629958451 reds: - outside-plan-disabled-no-fallback: the model quoted the pre-existing record as a parenthesized field list with its exact timestamp; attribution now requires that exact timestamp and the record's own field values. - plan-devex-peer-comparison-classification: the judge correctly returned missing but wrote a 1069-character reason, voiding the judgment; structured outputs cannot enforce maxLength, so the bound is stated on the field. - plan-ceo-split-overflow ran 504-1188 s as one PTY flow and set the periodic lane's wall clock; it now runs weekly in the marathon lane. * test: supply holdDeferKeepIndex to the CEO routing mocks and follow split-overflow into the marathon lane The registered-callback fixtures mock ceo-mode-option and lacked the new export; the split fixtures asserted the periodic tier; the registered-budget check looked for split-overflow only in the periodic manifest. * fix(qa): checkpoint receipts print the report link for their exploration file qa-functional-webhook-report failed in two of three censuses because the report linked .qa-evidence/NNN capture folders as "checkpoints" and never linked exploration-NNN.json. The checkpoint receipt now prints link: [checkpoint NNN](exploration-NNN.json), and the functional report template says capture folders are not checkpoints. * docs: final census numbers in the v1.91.9.0 entry; file the paid-eval follow-ups * ci(evals): name the PR-comment loop's unused fields so shellcheck passes (SC2034) * fix(plan-ceo-review): tighten expansion pacing wording to fit the skeleton cap after the main merge The merged skeleton measured 80,166 bytes against its unchanged 80,150 cap. Same instructions: ask separately for each addition, in turn, with no pacing menu; lead each proposal with the felt experience, then shape, effort and impact. * fix(eval-pass-rates): match trial-outcome files by basename so Windows backslash paths are read * fix(evals): repair proof-run reds in design-consultation, document-release, design and QA fixtures - design-consultation Phase 1 asks one brief that confirms context and decides research; the confirm-only first question scored substance 2. - document-release defines ship-owned inputs, exact steps and the JSON result, and drops stale spawned-from-/ship text (judge actionability 3.67 -> 4/4/4). - plan-design-with-ui accepts the Step 0D focus menu the same way the shared picker does ("focus on specific ones?"). - plan-design-review plan-mode saves in three Edits instead of one final Write. - QA functional annotations ask for the full 40-character revision. - Outside-disabled attribution judges quoted prior-record data by its exact timestamp or a dated, pre-existing-record sentence; four captured phrasings replay clean and current claims still fail. - --case can select autoplan-dual-voice by its literal test name. * test(design): revert the three-Edit plan-mode flow A focused paid run still timed out at 300 s: the first three passes alone took 150 s of thinking. The case stays a named timeout red rather than cutting review depth. * test: accept 'review mode = X' auto-decide declarations and parenthetical scope exclusions in the shared-libs actor auto-decide-preserved: the product auto-decided HOLD SCOPE and said "Decision: review mode = HOLD SCOPE"; the grammar knew only "is" and ":". shared-libs-plan-callers: the recommended option said "(no hardening)" and the actor read "hardening" as an expansion. Both replay the captured text, keep negative controls, and passed focused paid runs. * fix(review): pass Review Army checklists by path, run research alongside dispatch, always probe the design detector; state review-log invocation and statuses in the caller fixture - review-army-perf-n-plus-one: the parent copied full checklists into agent prompts and ran web research before dispatch (290 s on a 12-line diff); 212 s now. - review-design-lite: 5 of 6 captured trials reported the detector absent without probing; the probe is mandatory and its first line is reported, and the contract credits only fake-engine rule ids the checklist never names. - review-exploratory-small-cli: the fixture never gave review-log's direct invocation or status vocabulary; the model ran it through bun and wrote status "blocked". The prompt states both and the validator rejects out-of-vocabulary review statuses. Each case passed a focused paid run after repair. * docs(changelog): proof-run product fixes * fix(ship): always run the design-lite detector probe; test(shared-libs): credit a failed first file view and deferred-reuse Skip wording - /ship design-lite: the probe is mandatory and any non-ready first line is stated, matching /review (5 of 6 captured /review trials had skipped it). - shared-libs-pr-coverage: the first PR 42 page-1 read printed only a jq error, so the one refetch is a legitimate recovery, charged to the same budget. - shared-libs-review-prior-coverage: the Skip option said a future review can "reuse it once snapshot coverage holds"; a conditional tail on the recorded decision is not product work. Captured-text regressions and negative controls. * fix(ship,qa,document-release): repair proof-run regressions and fixture gaps - ship-docsync-completion: yesterday's audit-scope result dropped the section's status, so /ship spliced one in; the section now opens with **Status:**. - ship-docsync-missing-asset: a missing section or old Ship-owned mode blocks before launch. - ship-docsync-late-result: the invocation record says prepare already saves the candidate selection (no extra Read; budget unchanged). - qa exploratory: await the method Reads before the first probe. - qa-callers fixture: quote the real review-log record template; allow the git log command plan-completion prescribes. - qa functional observer: a receipt caught mid-link(2) is checked at stop instead of failing with ENOENT (reproduced from CI). Each repaired case passed a focused paid run. * ci(image): pin Claude Code 2.1.284, the version users run Request-body capture shows both 2.1.251 and 2.1.284 send effort "high" to claude-fable-5-1; 2.1.284 adds the model's own profile. The slower 2.1.284 census was mostly API latency: its SDK-only judges were 25% slower too. Nine previously slow cases pass on 2.1.284 within unchanged budgets. * test: one owner per case id, a structural devex 0B setup rule, and correct design/gbrain actors - plan-design-review-plan-mode was registered by two files; the PTY smoke is now plan-design-review-plan-mode-smoke, and a registry test requires one owner per case in case-sharded files. - plan-devex-finding-floor: the template's 0B narrative-confirmation question is classified as setup structurally instead of timing out a Haiku assessor. - setup-gbrain-remote: the actor accepted 'skip' on the MCP-registration question the test asserts; it now accepts that question and declines others. - design-review-plugin-handoff: the fake engine cited a file absent from the fixture repo and index.html linked a missing styles.css. Captured-question regressions with negative controls; each case passed a focused paid run. * test: PTY harness handles clipped reviews and bundled setup tabs; AUQ judge uses structured output; design-consultation carve declines optional outside voices - ceo mode routing: a Submit review taller than the viewport, a setup tab bundled after the mode tab, and a clip through the mode question each hung or misread the run; the native answer is still verified after Submit. - judgeRecommendation requests a 1-5 enum schema; a malformed Haiku reply had scored substance 0 for a 4/5 brief. Judge failures now propagate. - carve section-loading for design-consultation declines the optional outside voices (a supported path) and treats DESIGN.md as the report; timeout unchanged. The Step 0E handoff defect is not fixed (0/15 samples across four wordings, none shipped) and is filed in TODOS. * test: fold the design-consultation completion replay into carve-section-sharding (test-of-test ratchet) * docs(todos): record the pre-push hook shard-order hang * test(qa-callers): disable git auto maintenance in the fixture repo (same guard as shared-libs; from #3002) * test(office-hours-attempt): the fake judge SDK response carries stop_reason like the real API (structured judge requires end_turn) * fix(qa): the caller STOP line says to await the method Reads before any probe ship-exploratory-plan-checks: the model read exploratory.md and sent a capture in the same response, before seeing the section's own await rule. * fix(qa): number the qa value-bar questions from 1 and say reproduced bugs already answer the first two * fix(qa): define evidence.json where it is built, point the preparation gate at the next section, name measured command durations in the report template Recurring qa/qa-only workflow-judge complaints in CI (clarity/actionability 3.33). * fix(plan-eng-review,review): a disallowed question tool is not headless; report kept tests only when some were skipped * fix(plan-eng-review): keep the headless-rule contract phrases adjacent * fix(evals): cut path variance at its measured sources - gstack-qa-evidence capture prints startedAt/completedAt/durationMs and, for --deadline captures, remainingMs; the functional report takes durations from them. The section clock notice asks for one clock read up front instead of one after every checkpoint (QA runs spent 7-14% of tool calls on date -u). - ship plan-completion: skip the audit dispatch when discovery already found no plan (the dispatch-vs-skip conflict produced an optional 60-100 s subagent). - materialize/checkpoint validation errors state the expected schema, so a rejected annotations file is fixable in one call instead of blocking the phase. - session-runner counts turns from the transcript when a run times out, so timeouts stop reporting 'turn 0'. * fix(evals): count timeout turns only from object transcript events * test(qa-callers): deterministic child transport, completion-time handoff reads, compact phase report The exploratory caller cases exist to prove the caller starts and bounds exploratory QA. Their native adversarial reviewer (review) and plan audit (ship plan-checks) now come from recorded child outputs instead of a live subagent, handoff freshness reads are required before completion records rather than every bookkeeping log, and the phase report is compact. Measured: 194-257 s per case against 208-284 s before, no subagent calls. * test(ship-docsync): seed fault cases at their gate instead of replaying attempt 1 The post-dispatch fault cases (missing-marker, launch-failure, timeout-unsettled, late-result, stale-before, stale-after, recovery) now start from a fixture-owned attempt 1: the real actor prepares and dispatches it, its verbatim output is saved once, and the invocation journal carries its pre-dispatch entry with the child asset hashes. The model resumes at Parent processing with a trimmed read list, inspect named as the authoritative repository observation, and recovery's intermediate checkpoint folded into the next attempt's pre-dispatch entry. Assertions count only parent-issued transport events and require a read of the saved attempt-1 output; missing-asset and the legacy failure case keep the full model-driven first attempt, and their prompts are byte-identical. * test(ship-docsync): name the seeded read list and cap journal/report length The first seeded stale-before run spent calls locating documentation.md (two ls sweeps), reading through cat and re-Reading the record before Edit, and ~40 s composing 1.5-2.2 KB entries and report. Name every seeded read path, ask for native Read, and bound entry/report length. * test(ship-docsync): trim the seeded parent's measured model time Measured on the seeded runs: one read the 78 KB ship/SKILL.md, the post-child freshness comparison spent 18-32 s of thinking over full inspect contents, and the final response restated the report (~1.1 KB). Say the phase excerpt stands in for ship/SKILL.md, compare hashes first and read content only for changed paths, and end with one status line. * feat(qa-evidence): enforce the checkpoint sequence and fill report bookkeeping in code - capture refuses to run another probe until a checkpoint anchored on the latest complete capture names this capture as its next command, and every complete capture prints that requirement. - materialize fills revision, runtime, cwd and learning (checkpoints whose next native command differs) when omitted and prints the reportLinks the report must include; the QA section shrinks accordingly. * test(qa-callers): hand the caller phase its invocation-start observations and review token; fix(next-version): fetch without auto maintenance - Every caller case receives the diff, status, log, untracked list, HEAD and an already-captured review start token, so the phase spends its budget on the contract under test instead of re-running setup reads. - gstack-next-version's fetches pass --no-auto-maintenance. On git 2.55 a completed fetch forks detached maintenance in the caller's repository; the free suite's live smoke test ran it inside the CI checkout, and every shard-12 pre-push hook hang so far followed a completed smoke fetch. * feat(deslop-shared-libs): route every Git read through bin/gstack-safe-git The skill made the model retype a long safe-Git prefix on each call and a dropped flag failed shared-libs-read-only. bin/gstack-safe-git applies the fixed env + flag prefix, adds --no-ext-diff --no-textconv to log/show/diff, allows diff only between two explicit object IDs and ls-files only in the NUL-delimited overlay form, and refuses every other shape with one line naming the allowed forms. The template now points at the installed helper (host global runtime via {{SAFE_GIT}}) and drops the prose it enforces. Fixtures resolve the helper to this checkout, the git shim records the safety environment, and isGuardedGitRequest requires the complete prefix (env included) for every repository read. * test(shared-libs): tee to a discard device is not a file write Paid shared-libs-opportunity-judgment t1 on 1213b01 failed read-only on '... | tee /dev/null | sha256sum'. The detector flagged any tee operand while the same devices are allowed for redirection. tee now fails only when an operand is a real file; tee to a file, -a file and -- -a stay violations. * fix(qa-evidence,observer): reject placeholder metadata and replay-only learning; declare the docs atomic-write target - materialize measures revision, runtime and cwd itself and rejects supplied values that differ (CI run wrote revision "HEAD" and runtime "bun"), and refuses learning checkpoints that replay the same probe, naming the fix. - The docs write observer treats Claude Code's atomic temp for the authorized doc target as transient, so a temp renamed before its per-file watch no longer marks the observation incomplete (ship-docsync-completion flake). Per-file monitoring outside declared targets stays fail-closed. * test(qa-functional): fix mode requires only the happy scenario from the model (carried byte-identical from #3002 183b01f4..3e6074b4) verifyQANativeRegression already reruns all eight webhook scenarios on the repaired source, so the model-side eight-scenario requirement in fix mode duplicated harness coverage and pushed qa-functional-webhook-fix past its budget. qa-only still requires every scenario. * fix(deslop-shared-libs): probe the audited repository with -C <repo> A CI run probed safe-git from the session directory above the target repo, so the capability probe never touched the repository and the run fell back to the API without a local attempt. The probe (and any call from elsewhere) now names the audited repository. * test(qa-deadline): never attach a reader to the full-pipe fixture's stdout The full-pipe receipt test attached a 'data' listener (flowing mode) and then paused; on CI the reader could drain the 2 MB write before the pause, so the receipt write never blocked and the helper exited 0 in ~126 ms. The stdout pipe now stays unread until the assertion, which is what the test means to model. * feat(qa): helpers answer --help, and the QA eval interfaces declare it Approved by Garry: asking gstack-qa-evidence or gstack-qa-deadline for usage is read-only, so both helpers print usage and exit 0 on --help (the evidence usage now names the annotation shape), and the functional and caller command allowlists accept exactly 'bun <path>/bin/gstack-qa-{evidence,deadline} --help'. Two CI runs failed only on that call. * fix(qa): after an input change, a probe is affected unless shown otherwise CI late-input run finished in time but revalidated only the happy probe after the locale input changed and reported the stale adverse probe green. The revalidation step now treats any probe not shown to be unaffected as affected. * test(shared-libs): seed the lifecycle replay's first Step 3 pass instead of replaying it shared-libs-review-lifecycle ran ~88% of its 300 s session budget (12-run census median 265 s, 4/24 sessions timed out). The fixture now executes pass 1's Step 3 once with the real logger and Git: a real unused REVIEW_START, then the diff, inventories, attributes/config/index flags, gstack-review-read output and every file's bytes and sha256, saved to one observation. The model resumes at Step 4 with an exact four-file first read, the observation named as the authoritative pass-1 repository read, one post-fix verification, an explicit pass-2 read list and a twelve-line summary. Pass 2 still runs its own --start, diff, reads, fingerprint and stage actor before --finish. The actor scope now states that a current settled final-pass actor result supplies the replaced QA/adversarial prerequisites and that the no-credit disclosure is a reporting label: one r1 session persisted completed:false from that ambiguity. New assertions: the final binding never uses the seeded token's start or tree, and the observation was read; free controls finish the seeded token (binding changed) and omit the observation read, and both fail. * test(shared-libs): trim the resumed review replays' setup and report Every sibling review session (revalidation, path-eligibility, index-flags, prior-coverage) loaded qa/sections/exploratory.md and often scope.md although its QA and native adversarial results are supplied synthetic inputs, then spent a second request on shared-code-reuse.md and base metadata. The resumed scope now states that the supplied results replace Step 4's QA method loading; the revalidation contract names one first response (workflow, checklist, finding, prerequisites, shared-code-reuse.md, base metadata) and caps the summary at twelve lines. Receipt order, direct source reads, the checker, the question and final persistence are unchanged. * fix(review): define what a Step 5c Skip option says Step 5c named "B) Skip" without saying what its description may claim. Two CI captures (path-eligibility on131d43be, index-flags on4643cb85) offered a Skip whose description added effects beyond declining: "The extraction can be applied in a later editing review pass" and "replacing the invalidated prior Skip". Those read as change commitments, so the no-change actor refused both. Step 5c now says to describe Skip only as no code/index change with the Skip recorded; adjacent lines are compacted so the review parity caps hold unchanged. Both exact packets are kept as a free regression: still refused, and accepted once Skip follows the rule. The actor's classifier is unchanged. * fix(qa-evidence): every complete capture needs an evidence row; test(tpa): accept the hyphenated app-specific-password spelling - materialize refuses when a complete capture has no evidence row and is not named in limits (CI cli-report omitted capture 004), naming the missing IDs. - tpa-apple-ban's detector required 'app-specific password' with a space; the CI answer said 'app-specific-password path' and was otherwise correct. * test(qa-observer): fix mode treats atomic temps of authorized src/test writes as transient CI webhook-fix failed with 'Could not watch test/worker.regression-1.test.ts.tmp...': Claude Code's Write renamed its temp before the per-file watch was added. The functional eval now tells the observer its mode, and a temp whose target that mode may write is observed through its directory watch. Report-only mode and undeclared paths keep failing closed. * feat(qa-evidence): refuse evidence observed on an older input snapshot than the latest capture When native probe output declares a top-level input snapshot, materialize compares each evidence row with the latest capture's snapshot and refuses stale rows unless they are classified superseded, naming the captures to rerun. ship-exploratory-late-input kept reporting a pre-change adverse probe green after the input changed. * test(qa-functional): point the fixture at the helper's --help instead of its source A CI webhook-fix run spent three turns reading lib/qa-evidence.ts to learn the interface and timed out just before materialize (agreed with #3002's owner). * feat(qa-evidence): captures list the caller's declared-but-unrun required probes GSTACK_QA_REQUIRED_PROBES (a JSON array of native child commands) makes every capture print requiredRemaining; it never judges pass or fail. The functional eval passes the webhook list from QA_WEBHOOK_REQUIRED_SCENARIOS, which the verdict now reads too, so the nudge and the verdict share one source (agreed with #3002's owner). CI webhook-report kept stopping with scenarios unrun. * test(review-army): record N+1's pre-dispatch stages and scope the session to Step 4.5 review-army-perf-n-plus-one timed out in 7 of 13 CI runs on this branch (passing 245-280 s of 300). Each session spent ~95 s on setup (the full extracted SKILL, checklist, section greps, exploratory.md, diff-scope/stats/learnings, tooling checks), ran Step 4's core pass, a search-before-recommending WebSearch, and wrote a 10-16 KB report (~100 s after the Red Team returned). The fixture now stages only review/sections/review-army.md plus the performance and red-team checklists, and hands the session the recorded detect-scope, specialist-stats and learnings outputs and the diff. The caller passes --performance (every CI parent already treated the prompt as that force flag against the <50-line skip), declares the core pass, QA, adversarial review, web research, Fix-First and persistence out of scope, and caps the report at the selection line, the SPECIALIST REVIEW block and the Red Team result (30 lines). The Performance specialist and the conditional Red Team are still real foreground subagents, and the report still has to surface the N+1. New assertion: a foreground Performance specialist dispatch precedes the Red Team dispatch. Free controls omit the Performance dispatch or background it, and both fail; the budget lifecycle adapter supplies the current result shape. Touchfiles now include the .rb fixture the case reads. * test(review-army): share the recorded Step 4.5 staging with consensus and supply its Red Team review-army-consensus (periodic) timed out in 2 of 13 census sessions; passing runs took 213-297 s of 300. Like N+1 it spent ~30-50 s reading the whole extracted SKILL, checklist and every specialist file, sometimes dispatched an unrequested Maintainability specialist, then ran a Red Team (60-70 s) and a second merge before writing a 9-15 KB report. The N+1 staging and scope text move into stageReviewArmySession / reviewArmyScope / reviewArmyChecklists (the N+1 prompt renders byte-identical). Consensus now records its detect-scope, stats, learnings and diff, stages the Review Army section with the security and testing checklists, forces --security --testing, and caps the report like N+1. Its Red Team is outside the multi-specialist contract, so the fixture supplies a labeled synthetic NO FINDINGS result instead of a dispatch. The existing SQL-finding and browser-error assertions are unchanged; the lifecycle adapter's spawnSync now returns the git output the staging reads. * docs(changelog): v1.91.10.0 records the flake census and its repairs * test(strict-output): give the spool-prefix child time to finish before the pending stream times out windows-free-tests failed on9a7a7e54: the 150 ms shared deadline raced Bun startup on Windows, so the child was killed mid-write and the spool held a partial payload. Only the never-released extra stream should time out; the child now has 3 s. * fix(qa-evidence): accept a single limits string; test(qa-callers): read the handoff first when a probe snapshot changes CI late-input spent a turn rewriting limits as an array after materialize refused a string, and a ten-read sweep hunting for the changed input before it read reports/HANDOFF.md, then timed out at 300 s. * test(autoplan-dual-voice): unwrap the framed native report before Claude Code 2.1.284's agentId/usage trailer * test(section-loading): credit a Bash print that contains every line of the carved section * test(auto-decide): ask for the selected mode in the skill's mode handoff line, not a separate public decision * test(plan-ceo floor): scope preservation approves no premise, approach or remedy * test(autoplan-dual-voice): the fixture declares that delivered bash blocks run alone, diagnostics separately * test(coverage-audit): a fenced plain-word caption in a successful && read chain is display only Census 36776104571 plan-eng capture read both owned files with cat -n in one successful && chain; the caption 'echo "=== git diff main --stat ==="' fell outside the two-token caption grammar, so both reads lost credit. Accept a fenced caption of plain words; unfenced command strings, expansions, redirection, -e escapes and ; / || tails stay rejected. * test(office-hours): a fork whose outer options are the seeded shapes is the Phase 4 question Census trials 1-2 captured complete Phase 4 forks (A) Server-side B) Client-side C) Hybrid, recommendation with because) whose prose used none of the vocabulary words. Accept two seeded shapes as outer options as Phase 4 specificity; the earlier-phase, nested, fenced and single-shape controls still fail. * fix(review): design-lite rows keep the detector's [rule-id]; the e2e detector rows point at the diff The output template had no rule-id slot, so rows merged with checklist items dropped the detector id (census t2, local t1). Rows now carry [rule-id]. The fake engine's sample rows named a foreign fixture path at line 0; the e2e remaps them to landing.html/styles.css so trials stop spending turns reconciling it. * test(shared-libs): the plan actor reads scheduler parity and unchanged-scope lists Census 36776104571's question preserved the contract ('behaving exactly like the scheduler', 'scheduler parity holds by construction') and excluded work with 'Existing copies and helper hardening stay unchanged'. Accept exactly/parity as preservation (negated forms refuse) and a bare noun list that stays unchanged as an exclusion for the expansion scan only; verb-led clauses still refuse. * fix(qa-only,qa): name the exploratory read point and finalization order; judge qa with its browser assets qa-only judges cited 'next section' pointing at the wrong heading, an exploratory trigger that contradicted its read point, clock ownership in mixed runs and the unstated order of exploratory section 4 vs reporting. The qa judge penalized the absent qa-report-template and issue-taxonomy that qa-patterns loads; with them in, it found issue-taxonomy's dangling 'rule 13' (the consent rule is browser rule 3). * test(ship-docsync): seeded attempt 1 counts toward the limit; transport counts ignore calls that never reached the state file - CI launch-failure retried after the seeded attempt 1 as if that attempt were the fixture's; the seeded prompt now says attempt 1 is this invocation's and a further attempt needs what Blocked recovery requires. - A late-result run typo'd the state path once (ENOENT, the actor never ran), then repeated the call correctly; the per-action count compared both calls with one actor event. Only calls naming the real state file are counted. * fix(plan-eng-review): show the accepted dedicated read form for coverage-diagram sources CI plan-eng-coverage-audit mixed package/config and git diff into the source read; the review variant, whose prompt shows the && display form, does not. The plan trace step now shows it too, within the unchanged size cap. * test(sync-gbrain-readiness): a negation earlier in the claim clause is not a search/write readiness claim The census unknown actor wrote 'nothing about read, search, or write capability is confirmed either way' after a YELLOW/WARN verdict. The claim window started at 'write', so the leading 'nothing' was outside it. Check the clause subject for nothing/neither/none/no; keep the original in-claim negations. Replay of the captured output passes; positive controls still flag an unnegated claim. * fix(office-hours): a forcing question's recommendation takes the position the founder's words support auq-matrix office-hours asked D1 Demand as options about the founder's own evidence and, with no rule for that shape, recommended 'answer whichever is TRUE — A is marked recommended only because it is the strongest position' (substance 2). Say what such a recommendation is: the option the founder's own words support, why it matters for the next step, and what would change it. * fix(plan-ceo-review): name the mode preference command and the exact handoff line auto-decide-preserved at6fcb0981: the model never ran the preference check, read 'check ... through the preamble' as already done, auto-selected 'per your preference setting', and wrote 'Selected mode: HOLD SCOPE, auto-decided from your tuned preference' instead of the AUTO_DECIDE handoff line. At9a7a7e54it ran the check but wrote 'Decision: HOLD SCOPE is the review mode for ...'. Neither matched the handoff template the observer recognizes. Name gstack-question-preference --check at the point of use and say the handoff begins with the exact matching line. Collapse the audit block's comment padding to stay within the unchanged 80150-byte skeleton cap. * test(section-loading): record the CEO capture's report and transcript The6fcb0981census failed hasStaleFillRaceFinding (line 98), but the case records nothing beyond junit, so the report the detector judged is gone. Return the SkillTestResult from captureSectionReads and record it, with the full saved report, through the eval collector on pass and fail. * test(design): plan-mode names its read list and caps its additions and summary At6fcb0981plan-design-review-plan-mode timed out at 300 s (9 turns): 22 cat/sed chunk reads (~50 s), then a 28 KB plan Write (~150 s), before the read-back finished. The9a7a7e54pass took 240 s with a 24.6 KB Write. Read SKILL.md, review-sections.md and plan.md natively in one response, keep additions under 14,000 characters and the summary within ten lines. Budgets unchanged. * test(plan-mode-no-op): require prose evidence before a waiting verdict ends eng/design runs (carried byte-identical from #3002) With the prose fallback forced, the gate renders as a lettered menu; a judge 'waiting' verdict on a spinner-only frame ended the run as 'asked' before the menu rendered, so the scope-gate check failed on unchanged behavior. * feat(qa-evidence): materialize computes the phase verdict; callers must report it Approved by Garry: the helper, not the model, decides whether evidence can pass. materialize writes verdict {status, open} into evidence.json and prints it: fail or blocked from row classifications, inconclusive while any row is superseded, a complete capture is withheld, a declared required probe is unrun or there is no evidence, else pass. The caller fixture requires receipt.status to equal that verdict. CI late-input kept reporting pass with a superseded happy probe. * test(qa-callers): compare the receipt with the helper verdict only when evidence.json was materialized The producer free tests run captures without materialize; evidence.json is optional for callers, so its absence is not a verdict mismatch. * test(llm-judge): run the ship workflow judge at medium effort so its panel fits JUDGE_MS claude-fable-5-1 accepts only adaptive thinking (thinking.type.enabled with budget_tokens returns 400), so effort is the available thinking control. Measured on the exact ship judge request (105,301 input tokens): - default effort, 18 samples: thinking 5,086-10,881 tokens, 75.9-144.7 s; 3 of 18 passed the 120 s deadline (about 42% of 3-sample panels). - medium effort, 18 samples: thinking 2,749-5,762, output at most 6,144 tokens, 43.1-77.9 s; scores 4/4/4 in 16 of 18 (clarity 3 in two), versus 14 of 18 at default. callJudge gains an effort option sent as output_config.effort; only the ship judge sets it. Rubric, floors, panel size, deadline, model and max_tokens are unchanged. The cache identity records effort. * test(llm-judge): ask frontier workflow judges for 120-word reasoning under the unchanged 150-word check Told "under 150 words", the ship judge's reasoning landed at 130-156 words (3 of 18 probe samples at 152-156), so the structured-response check failed about one panel in three independent of effort. The prompt's frontier block and the response schema description now say under 120 words; the validator still rejects 150 words or more. The changed prompt bytes reach only the two frontier judges: ship/SKILL.md workflow (prompt and schema) and review/SKILL.md workflow (prompt). * test(llm-judge): type the stream transport mock call * test(plan-ceo floor): the request answers only the questions it names PR lane 36794871032 (head20d6e98f): the CEO floor ran 608 s without a question. Its Step 0 recorded the premise gap and approach choice as unresolved ledger rows, then said "this session supplies all answers up front, so no decision brief was dispatched" and wrote Sections 1-11.2734e203stopped scope preservation from approving the premise; this time the actor block (declined setup, recall, outside voices, HOLD SCOPE) and the fixture's "complete user request is available from the start" were read as pre-answering every review question. The CEO actor now states that the request answers only the routing, recall, outside-reviewer and review-mode questions it names. * test(plan-devex floor): a 'Partly wrong' 0B answer is the narrative confirmation PR lane 36794871032: the DX floor asked its D1 narrative confirmation (Accurate, proceed / Partly wrong, correct it / Way off, actual is...). The deterministic setup rule accepted only 'Some ... wrong', so the question went to the LLM assessor, which hit its 30 s spawnSync cap (ETIMEDOUT) and ended the case as assessment_error at 141 s, the same failure as census 36641820398. The rule now accepts 'partly' beside 'some'; the captured question is a free regression and the remedy-option controls still go to the assessor. * test(design-review plugin handoff): quoted report text is not an install command PR lane 36794871032: every behavioral check passed except noInstallOrOverride, which matched "no `npx impeccable`" inside the quoted heredoc that wrote detector-output.md. Nothing was installed or downloaded. The check now drops quoted-delimiter heredoc bodies (literal data) before matching; unquoted bodies, which can expand $(...), and unterminated bodies stay checked. Free controls cover the captured write, bare npx, an IMPECCABLE_BIN override, an unquoted $(npx ...), npx after the delimiter and an unterminated body. * test(review-army delivery audit): stage only the plan-completion section and record its git reads PR lane 36794871032: the case timed out at its 120 s budget after 7 turns (previous lane passed in 45 s). The session read the 46 KB extracted SKILL in three passes (cat to persisted output, grep, sed), ran its own git reads, wrote a 74-line report, then inspected and ran gstack-learnings-log and rewrote the report's Learnings section. As in the Step 4.5 cases (17ee2e54/2bd4651c), the fixture now stages only review/sections/plan-completion.md, hands the session the recorded git log and diff, declares the HIGH-impact question, its Scope Check, learnings logging and later steps outside the capture, and caps the report at the audit block and its DISCREPANCY entries (30 lines). The NOT DONE and email assertions are unchanged. * feat(qa-evidence): one capture call records the causal note for the previous capture capture R NNN [--public] (--deadline D|--timeout-ms MS) --after PREV --hypothesis 'TEXT' -- CMD publishes exploration-NNN.json {observationCapture, observationArgv, observed, hypothesis, nextCapture, nextArgv} before running CMD, refusing unless PREV is the latest complete capture. The receipt carries checkpoint/checkpointSha256; validators bind the note to the transcript's capture calls by capture ID and receipt hash instead of exact command strings. The separate checkpoint command and the capture guard keep working; materialize learning accepts both note shapes and still rejects same-probe replays. Prose and eval fixture prompts teach the merged form. * fix(qa-evidence): a superseded row stops holding the verdict open once its probe is rerun on current inputs materialize requires an old-snapshot row to be classified superseded, and its verdict kept every superseded row open, so rerunning the probe (what its own error tells the model to do) could never reach pass; late-input reran 3 and 9 on the new snapshot and still got inconclusive. A superseded row now closes only when a non-superseded row with the same captured argv observed the current snapshot. Re-materializing an already-published evidence.json names the cause instead of failing generically. * test(plan-eng batching): count saved decisions whose label drops the (recommended) marker or whose report is titled 'Eng Review Report — <plan>' * fix(qa): browser-only runs skip annotations/materialize; only Q captures can anchor evidence rows * test(design): plan-mode length is a drafting target, not a check to measure and trim * test(llm-judge): structured output for doc, outcome and posture judges so reasoning quotes cannot break JSON * test(ship-docsync): steer skill file reads to Read; large cat output becomes an unpageable preview * docs(changelog): browser-only QA evidence and structured judge output * test(qa-only cleanup): refusal scenarios get a 1 s budget and an absolute worker deadline; 300 ms starved under parallel load * fix(office-hours, design-consultation): ask the goal question and read the mode section first; ask the memorable-thing question on its own * test(outside-disabled): a record named by the retained record's own clock and then disowned owns its completed status * test(context-skills): install gstack-paths in the fixture bin; without it the model guessed the checkpoint root * test(ceo mode routing): SCOPE EXPANSION posture credits plural 'expansions' * test(ship-docsync): name the unmet atomic-replacement check on a forbidden temp-file write * fix(qa): browser-only runs materialize an empty evidence list with checkpoints in limits, matching /qa-only * test(qa callers): an accepted review-log record may cite checkpoints as finding evidence * fix(plan-eng-review): state that a disallowed question tool never qualifies as headless before the headless action * merge follow-up: re-record paid CLI parity for #2999's flags; trim merged review, qa-only and plan-eng wording toward the size caps * test(golden): refresh codex/factory ship goldens for the trimmed caller QA wording * test(coverage-audit fixture): disable git auto maintenance so cleanup is not racing a detached git writer * test(parity): raise review, qa and plan-eng caps to the measured merged size of #2999 and #3002 (each fit alone), documented per cap * fix(qa-evidence): materialize rejects an unrecognized classification before publishing, so the one-shot verdict cannot be locked inconclusive by a descriptive label
794 lines
61 KiB
TypeScript
794 lines
61 KiB
TypeScript
import { expect, test } from 'bun:test';
|
||
import { readFileSync } from 'node:fs';
|
||
import { ALL_HOST_CONFIGS } from '../hosts';
|
||
import { generateAdversarialStep } from '../scripts/resolvers/outside-voice-steps';
|
||
import { generatePlanCompletionGateShip } from '../scripts/resolvers/plan-gates';
|
||
import { generateQAReview } from '../scripts/resolvers/qa';
|
||
import { HOST_PATHS } from '../scripts/resolvers/types';
|
||
import { readWorkflowExcerpt } from './helpers/workflow-excerpt';
|
||
|
||
const readShip = () => readWorkflowExcerpt('ship/SKILL.md', '# Ship:', '## Important Rules');
|
||
|
||
test('Ship initializes and applies its smoke guard independently of required plan checks', () => {
|
||
for (const host of ALL_HOST_CONFIGS) {
|
||
const body = generateQAReview({ host: host.name, skillName: 'ship', tmplPath: '', paths: HOST_PATHS[host.name] });
|
||
expect(body).toContain('Run the shared preflight; start its smoke guard once. Guard every smoke probe.');
|
||
expect(body.indexOf('start its smoke guard once')).toBeLessThan(body.indexOf('**3. Run smoke and plan checks.**'));
|
||
expect(body).toContain('Required even for small diffs or missing plans/servers');
|
||
expect(body).toContain('Then run required plan checks and revalidation, even after smoke expires');
|
||
expect(body).toContain('using the same procedure but no smoke guard; never reset the clock');
|
||
}
|
||
});
|
||
|
||
test('ship uses the PR template headings instead of a competing combined QA report', () => {
|
||
const ship = readShip().replace(/\s+/g, ' ');
|
||
expect(ship).toContain('PR section `## Exploratory QA`');
|
||
expect(ship).toContain('plans in `## Verification Results`');
|
||
expect(ship).toContain('Read QA\'s `templates/functional-report-template.md`: PR section');
|
||
expect(ship).toContain('Link every checkpoint; no second report');
|
||
expect(ship).not.toContain('## Exploratory QA and Verification Results');
|
||
});
|
||
|
||
test('late adversarial fixes use the same bounded review cycle before release steps', () => {
|
||
const ship = readShip();
|
||
const controller = compact(ship.slice(ship.indexOf('### Ship control flow'), ship.indexOf('## Step 0:')));
|
||
const review = ship.slice(ship.indexOf('## Step 9:'), ship.indexOf('## Step 10:'));
|
||
const adversarial = compact(ship.slice(ship.indexOf('## Step 11:'), ship.indexOf('## Step 12:')));
|
||
expect(review).toContain('queued Steps 10–11 findings');
|
||
expect(compact(review)).toContain('do not run a fourth fixing cycle');
|
||
expect(controller).toContain('Keep the same attempt counts throughout the invocation');
|
||
expect(adversarial).toContain('queued for the parent; do not edit during Step 11');
|
||
expect(compact(review)).toContain("Every repeat starts before the checklist read and captures a fresh REVIEW_START. Finish the complete review and QA before applying any fix in Step 9.4");
|
||
expect(adversarial).toContain('**Required native review incomplete:** STOP');
|
||
expect(adversarial).toContain('Optional outside failures retain their own incomplete records');
|
||
expect(adversarial).toContain('Insert Steps 9, 10 and 11 before the pending Step 11.5 in the work list. Step 9 completes full review before fixes');
|
||
expect(adversarial).toContain('**Native complete with no queued fixes:**');
|
||
expect(adversarial).toContain('no queued fixes');
|
||
expect(adversarial).toContain('then continue to Step 11.5');
|
||
const greptile = ship.slice(ship.indexOf('## Step 10:'), ship.indexOf('## Step 11:'));
|
||
expect(greptile).toContain('queue the approved fix without editing here');
|
||
expect(compact(greptile)).toContain('Finish the saved replies without asking again about completed fixes');
|
||
});
|
||
|
||
test('late source changes repeat affected gates without resetting either allowance', () => {
|
||
const ship = readShip();
|
||
const gate = ship.slice(ship.indexOf('## Step 16:'), ship.indexOf('## Step 17:'));
|
||
const controller = ship.slice(ship.indexOf('### Ship control flow'), ship.indexOf('## Step 0:'));
|
||
const text = compact(controller + gate);
|
||
expect(text).toContain("**Behavior, tests or build inputs changed:** Prompts/templates count as behavior");
|
||
expect(text).toContain("Keep the same attempt counts throughout the invocation");
|
||
expect(text).toContain('Validate the outcome before Step 15');
|
||
const workflow = ship.replace(/\s+/g, ' ');
|
||
expect(workflow).toContain('Increment before each launch or inline takeover');
|
||
expect(workflow).toContain('Increment before each launch or inline takeover, including failed launches');
|
||
expect(workflow).toContain('A stale snapshot is neither a new attempt nor a current audit');
|
||
expect(workflow).toContain('never a third attempt, even after Step 16 changes');
|
||
});
|
||
|
||
const readTemplate = (name: string) => readFileSync(new URL(`../${name}`, import.meta.url), 'utf8');
|
||
const compact = (text: string) => text.replace(/\s+/g, ' ');
|
||
const reviewTemplate = readTemplate('ship/sections/review-army.md.tmpl');
|
||
const coverageTemplate = readTemplate('ship/sections/test-coverage.md.tmpl');
|
||
const entryTemplate = readTemplate('ship/SKILL.md.tmpl');
|
||
const controlTemplate = entryTemplate.slice(entryTemplate.indexOf('### Ship control flow'), entryTemplate.indexOf('{{SECTION_INDEX:ship}}'));
|
||
const control = compact(controlTemplate);
|
||
const reviewFlow = compact(reviewTemplate);
|
||
const nativeFlow = compact(generateAdversarialStep({ host: 'claude', skillName: 'ship', tmplPath: '', paths: HOST_PATHS.claude }));
|
||
const finalGate = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
const pushFlow = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 17:'), entryTemplate.indexOf('## Step 18:')));
|
||
const commentsFlow = compact(readTemplate('ship/sections/greptile.md.tmpl'));
|
||
const docsTemplate = readTemplate('ship/sections/documentation.md.tmpl');
|
||
const prTemplate = readTemplate('ship/sections/pr-body.md.tmpl');
|
||
|
||
test('ship r12 template: the invocation note locates release, attempts and receipts', () => {
|
||
const entry = compact(entryTemplate);
|
||
expect(entry).toContain('outside the product tree and save its absolute path');
|
||
for (const state of [
|
||
'versions, `BUMP_LEVEL`, reviewed tree and attempt counts',
|
||
'Reuse it only for that same scope; a repair never resets approvals or expands them',
|
||
'each approval\'s finding, files and authorized action',
|
||
'handles, original start tokens, terminal states, outputs and queued fixes',
|
||
'command/label, result/counts, timestamp, log and consumed inputs',
|
||
'candidate/id, attempts used, accepted hashes or named blocked exception',
|
||
]) {
|
||
expect(entry).toContain(state);
|
||
}
|
||
expect(entry).toContain('handles, original start tokens, terminal states, outputs and queued fixes');
|
||
expect(entry).toContain("reuse this invocation's saved level");
|
||
expect(entry).toContain('Otherwise FRESH chooses it in item 2 and ALREADY_BUMPED derives it in item 1');
|
||
});
|
||
|
||
test('ship r12 template: reuse compares recorded observations and actual inputs without resampling judges', () => {
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(gate).toContain('original command, result/counts, timestamp and log');
|
||
expect(gate).toContain('Compare hashes or complete bytes');
|
||
expect(gate).toContain('consumed files, fixtures, dependencies and execution parameters');
|
||
expect(gate).toContain('complete expanded request, rubric, parameters and builder/runtime dependencies');
|
||
expect(gate).toContain('never resample it');
|
||
expect(gate).toContain('Mandatory reviews still run');
|
||
expect(gate).toContain('Check each test lane\'s receipt as well');
|
||
});
|
||
|
||
test('ship r12 template: undeclared builds differ from unavailable declared prerequisites', () => {
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(gate).toContain('If none exists, record not applicable and the inspected sources');
|
||
expect(gate).toContain('A missing prerequisite or failed build stops shipping');
|
||
expect(gate).toContain('Confirm terminal completion or termination before another writer runs');
|
||
expect(gate).toContain('Timeout or cancellation acknowledgment alone means STOP until confirmed');
|
||
expect(gate).toContain("**No changes, or the docs-only checks still support the plan:** Continue to stage 3 without a new code review");
|
||
expect(gate).toContain("**Only authored docs or release metadata changed:** Keep Step 8's original child report and counts");
|
||
expect(gate).toContain("**Behavior, tests or build inputs changed:** Prompts/templates count as behavior");
|
||
});
|
||
|
||
test('ship r12 template: docs collection separates stopped work from acceptable coverage', () => {
|
||
const docs = compact(docsTemplate);
|
||
expect(docs).toContain('Terminal completion or confirmed termination is sufficient');
|
||
expect(docs).toContain('Require every field/type, exact audit id, schema, status invariant and actual spawned marker');
|
||
expect(docs).toContain('enforcing prompt/audit-scope permissions and protected-file exclusions');
|
||
expect(docs).toContain('Compare saved base and input hashes with current content');
|
||
expect(docs).toContain('An exited child with missing output is stopped, but its audit is blocked');
|
||
expect(docs).toContain('HEAD and index must be unchanged, existing dirty/untracked user content preserved, and changed paths exactly `files_updated`');
|
||
expect(docs).toContain('Otherwise save post-child hashes, status and `documentation_section` for Step 16');
|
||
expect(docs).toContain('A failed check or `blocked` result goes to recovery, even with valid JSON');
|
||
expect(docsTemplate).toContain('**Subagent prompt:**');
|
||
expect(docsTemplate).toContain('**Parent processing:**');
|
||
});
|
||
|
||
test('ship r12 template: review finalization precedes one prioritized return table', () => {
|
||
const persist = reviewTemplate.indexOf('6. Persist the review result');
|
||
const route = reviewTemplate.indexOf('### Decide whether to repeat Step 9');
|
||
expect(persist).toBeGreaterThanOrEqual(0);
|
||
expect(route).toBeGreaterThan(persist);
|
||
const exits = reviewFlow.slice(reviewFlow.indexOf("### Decide whether to repeat Step 9"));
|
||
const missing = exits.indexOf('**Dispatched reviewer output missing:** STOP');
|
||
const cap = exits.indexOf('**Third fixing cycle reached (`CYCLES >= 3`):** STOP');
|
||
const fixing = exits.indexOf('**Fixes applied below the cap:**');
|
||
const zeroFix = exits.indexOf('**No edits in this pass:** Resolve the required-probe gate below. Only after it clears may you continue to Step 10');
|
||
for (const position of [missing, cap, fixing, zeroFix]) expect(position).toBeGreaterThanOrEqual(0);
|
||
expect(missing).toBeLessThan(cap);
|
||
expect(cap).toBeLessThan(fixing);
|
||
expect(fixing).toBeLessThan(zeroFix);
|
||
expect(compact(reviewTemplate)).toContain('Finish and log this pass before choosing the next step');
|
||
expect(compact(reviewTemplate)).toContain('Complete items 5–6 exactly once with the original REVIEW_START');
|
||
});
|
||
|
||
test('ship r6 template: one progress note defines surviving state and per-pass content tokens', () => {
|
||
const entry = compact(entryTemplate);
|
||
expect(entry).toContain('one private Markdown **invocation record**');
|
||
expect(entry).toContain('**Next steps:** one ordered work list, with the current step marked');
|
||
expect(entry).toContain('tracked and non-ignored untracked files');
|
||
expect(entry).toContain('`gstack-wtree` prints a Git tree hash');
|
||
expect(entry).toContain('**start token** is the opaque value returned by `gstack-review-log --start` before it reads the diff');
|
||
expect(entry).toContain('Never borrow or replace a token');
|
||
expect(entry).toContain('each approval\'s finding, files and authorized action');
|
||
});
|
||
|
||
test('ship r6 template: plan obligations precede learnings and scope drift even without a plan', () => {
|
||
const plan = readTemplate('ship/sections/plan-completion.md.tmpl');
|
||
const route = compact(plan.slice(0, plan.indexOf('**Dispatch this step')));
|
||
const steps = ['1. Dispatch the audit, validate its result and resolve its Gate Logic',
|
||
"2. Collect the plan's executable checks in Step 8.1; do not run them yet",
|
||
'3. Run Step 8.2 Scope Drift',
|
||
'4. Run Prior Learnings, including its setting question when offered, then proceed to Step 9 for review and QA'];
|
||
const positions = steps.map(step => route.indexOf(step));
|
||
expect(positions.every(position => position >= 0)).toBe(true);
|
||
expect(positions).toEqual([...positions].sort((a, b) => a - b));
|
||
const noPlan = generatePlanCompletionGateShip({ host: 'claude', skillName: 'ship', tmplPath: '', paths: HOST_PATHS.claude });
|
||
expect(noPlan).toContain('Skip only the plan completion audit');
|
||
expect(noPlan).toContain('Continue with Step 8.1, Scope Drift and Prior Learnings; Step 9 QA still runs');
|
||
expect(noPlan).not.toContain('Skip entirely');
|
||
const sections = ['{{PLAN_COMPLETION_GATE_SHIP}}', '{{PLAN_VERIFICATION_EXEC}}',
|
||
'{{SCOPE_DRIFT}}', '{{LEARNINGS_SEARCH:query=release ship version changelog merge pr}}'];
|
||
const actual = sections.map(section => plan.indexOf(section));
|
||
expect(actual.every(position => position >= 0)).toBe(true);
|
||
expect(actual).toEqual([...actual].sort((a, b) => a - b));
|
||
expect(entryTemplate.indexOf('{{SECTION:plan-completion}}')).toBeLessThan(entryTemplate.indexOf('{{SECTION:review-army}}'));
|
||
});
|
||
|
||
test('ship r6 template: an approved rebump logs the written version rather than its initial state', () => {
|
||
const bump = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 12:'), entryTemplate.indexOf('{{SECTION:changelog}}')));
|
||
expect(bump).toContain('Record the release decision after a version was actually written');
|
||
expect(bump).toContain('including an approved ALREADY_BUMPED rebump');
|
||
expect(bump).toContain('Skip unchanged versions and manifest-only repairs');
|
||
expect(bump).not.toContain('skip if ALREADY_BUMPED');
|
||
expect(bump).toContain('Only approval changes the existing version');
|
||
expect(bump).toContain('Best-effort, non-interactive, non-blocking');
|
||
});
|
||
|
||
test('ship r6 template: late-change routing runs prerequisites before final evidence without a circular gate', () => {
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
const build = gate.indexOf('### 1. Finish writers and prepare outputs');
|
||
const route = gate.indexOf('### 2. Choose the change route');
|
||
const docs = gate.indexOf('### 3. Resolve documentation freshness');
|
||
const verify = gate.indexOf('### 4. Verify the frozen candidate');
|
||
expect(build).toBeGreaterThan(0);
|
||
expect(route).toBeGreaterThan(build);
|
||
expect(docs).toBeGreaterThan(route);
|
||
expect(verify).toBeGreaterThan(docs);
|
||
expect(gate).toContain('This repair excludes Step 14.5 because the rebuild can change generated docs. Step 16 restarts at stage 1');
|
||
expect(gate).toContain('Insert `5–11.5 → 12–14 → 16` before the pending Step 17, then stop this step. This repair excludes Step 14.5');
|
||
expect(gate).toContain('Compare hashes or complete bytes of its saved and current consumed files, fixtures, dependencies and execution parameters');
|
||
expect(gate).toContain('changed or unknown dependencies require a rerun');
|
||
expect(gate).toContain('Freeze inputs through verification and push');
|
||
expect(gate).toContain('If content changes during or after verification, restart at stage 1 and complete all five stages before Step 17');
|
||
});
|
||
|
||
test('ship r6 template: docs attempts count at launch and exhausted late changes never open a third attempt', () => {
|
||
const docs = compact(docsTemplate);
|
||
expect(docs).toContain('an initial audit plus ONE repair/re-audit in the invocation record');
|
||
expect(docs).toContain('an initial audit plus ONE repair/re-audit');
|
||
expect(docs).toContain('never a third attempt, even after Step 16 changes');
|
||
expect(docs).toContain('Increment before each launch or inline takeover');
|
||
expect(docs).toContain('Increment before each launch or inline takeover, including failed launches');
|
||
expect(docs).toContain('A stale snapshot is neither a new attempt nor a current audit');
|
||
expect(docs).toContain('Terminal completion or confirmed termination is sufficient');
|
||
expect(docs).toContain('the request alone is insufficient');
|
||
expect(docs).toContain('Unconfirmed writers, ownership violations, unauthorized Git mutation and redaction/security gates cannot be waived');
|
||
expect(docs).toContain('Only an actual user exception counts');
|
||
expect(docs).toContain('reports and PRs retain blocked status');
|
||
});
|
||
|
||
test('ship r6 template: evidence exemptions inspect metadata content rather than trusting filenames', () => {
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(gate).toContain('Inspect changes since the run; `--allow-paths` exempts only release metadata');
|
||
expect(gate).toContain('scripts, dependencies and runtime configuration require live tests');
|
||
expect(gate).toContain('A `package.json` version-only edit can qualify; scripts, dependencies and runtime configuration require live tests');
|
||
expect(gate).toContain('Docs, TODO edits, new/generated tests and fixes make evidence STALE');
|
||
expect(gate).toContain('Only receipt storage/readback failed | Independently prove unchanged final content, the same command and valid age from the successful run\'s evidence');
|
||
expect(gate).toContain('Only receipt storage/readback failed');
|
||
});
|
||
|
||
test('ship r6 template: linked spec discovery is ordered outside the body and cannot exit publication', () => {
|
||
const instructions = compact(prTemplate.slice(0, prTemplate.indexOf('The PR/MR body should contain')));
|
||
expect(instructions).toContain('Read archive frontmatter as data, never shell source');
|
||
expect(instructions).toContain('exact `spec_branch` match');
|
||
expect(instructions).toContain('newest `spec_filed_at`');
|
||
expect(instructions).toContain('positive integer `spec_issue_number`');
|
||
expect(instructions).toContain('omit only `## Linked Spec` and continue composing the PR');
|
||
expect(instructions).toContain('Only fully completed Step 8 plan scope permits `Closes #N`');
|
||
expect(instructions).toContain('Partial, deferred, failed, dropped or unverified scope uses `Linked to #N`');
|
||
const body = prTemplate.slice(prTemplate.indexOf('The PR/MR body should contain'), prTemplate.indexOf('#### Redaction scan'));
|
||
expect(body).not.toContain('CURRENT_BRANCH=');
|
||
expect(body).not.toContain('SPEC_ARCHIVES=');
|
||
expect(body).not.toContain('SPEC_FILE=$(grep');
|
||
expect(prTemplate).not.toContain('[ -z "$SPEC_FILE" ] && exit');
|
||
});
|
||
|
||
test('ship r6 template: Step 18 prepares the exact title Step 19 scans and publishes', () => {
|
||
const title = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 18:'), entryTemplate.indexOf('{{SECTION:pr-body}}')));
|
||
expect(title).toContain('Save the result as `NEW_TITLE` for Step 19');
|
||
expect(title).toContain('existing open PR/MR');
|
||
expect(title).toContain('For a new PR/MR, compose `v<NEW_VERSION> <type>: <summary>`');
|
||
expect(prTemplate).toContain('Use Step 18\'s `NEW_TITLE` unchanged; its version prefix is already present');
|
||
expect(prTemplate).not.toContain('`NEW_TITLE`, prefixed with');
|
||
expect(prTemplate).toContain('In a new shell, restore the saved literal title before this block');
|
||
expect(prTemplate).toContain(': "${NEW_TITLE:?Restore the saved Step 18 title before scanning}"');
|
||
expect(prTemplate).not.toContain('NEW_TITLE="<final vNEW_VERSION type: summary>"');
|
||
expect(prTemplate).toContain('Update the title with the same scanned `NEW_TITLE`');
|
||
expect(compact(prTemplate)).toContain('exit 3 blocks for HIGH findings');
|
||
});
|
||
|
||
test('ship template consolidation: initial, failed and inline generation attempts share one allowance', () => {
|
||
const allowance = compact(coverageTemplate.slice(0, coverageTemplate.indexOf('````text')));
|
||
expect(allowance).toContain('Maximum 2 generation passes total per invocation');
|
||
expect(allowance).toContain('Count each generation-authorized attempt before dispatch/inline execution');
|
||
expect(allowance).toContain('including the initial audit, failures and zero-test results');
|
||
expect(allowance).toContain('Re-entry never resets it');
|
||
expect(allowance).toContain('Two passes already used means no further generation');
|
||
expect(allowance).toContain('read-only reassessment uses no pass');
|
||
expect(allowance).toContain('30-path/5-tests-per-pass/2-minute per-test caps');
|
||
expect(allowance).toContain('missing permission is not approval');
|
||
expect(coverageTemplate).toContain("confirm it stopped before running the same audit inline");
|
||
});
|
||
|
||
test('ship template consolidation: audit-only authority reaches the actual coverage child prompt', () => {
|
||
const prompt = coverageTemplate.split('````text\n')[1]?.split('\n````')[0] ?? '';
|
||
expect(prompt).toContain('Generation: <allowed|audit-only>; passes used: <N> of 2.');
|
||
expect(prompt).toContain('Audit-only overrides every generation instruction below.');
|
||
expect(prompt.indexOf('Audit-only overrides')).toBeLessThan(prompt.indexOf('{{TEST_COVERAGE_AUDIT_SHIP}}'));
|
||
expect(prompt).toContain('Do not commit or push');
|
||
expect(prompt).toContain('return unresolved user decisions to the parent');
|
||
expect(prompt).toContain('"coverage_pct":N,"gaps":N');
|
||
expect(prompt).toContain('"tests_added":["path",...]');
|
||
});
|
||
|
||
test('ship template consolidation: duplicate design defects have one action without losing independent coverage', () => {
|
||
const design = compact(reviewTemplate.slice(reviewTemplate.indexOf('{{DESIGN_REVIEW_LITE}}'), reviewTemplate.indexOf('{{REVIEW_ARMY}}')));
|
||
expect(design).toContain('The parent owns design-lite; the Design specialist is an independent read');
|
||
expect(design).toContain('Before final counting/Fix-First');
|
||
expect(design).toContain('same evidenced design defect at the same path/line');
|
||
expect(design).toContain('one item with both sources and stricter ASK');
|
||
expect(design).toContain('Retain actual specialist stats');
|
||
expect(design).toContain('distinct defects stay separate');
|
||
expect(design).toContain('neither pass substitutes for the other');
|
||
expect(reviewTemplate).toContain('{{DESIGN_REVIEW_LITE}}');
|
||
expect(reviewTemplate).toContain('{{REVIEW_ARMY}}');
|
||
expect(reviewTemplate).toContain('"dispatched":true,"findings":N,"critical":N,"informational":N');
|
||
});
|
||
|
||
test('ship template consolidation: the parent owns one ordered review phase', () => {
|
||
const intro = compact(controlTemplate + reviewTemplate);
|
||
expect(intro).toContain("You, the **parent** running /ship, own advancement");
|
||
expect(intro).toContain('Set CYCLES to 0 on first entry only');
|
||
expect(intro).toContain('**No edits in this pass:**');
|
||
expect(intro).toContain('Start with Steps 1–21 in order, including 11.5 and 14.5');
|
||
expect(intro).toContain('Steps 10–11 queue findings without editing');
|
||
expect(intro).toContain("Finish the complete review and QA before applying any fix in Step 9.4");
|
||
expect(intro).toContain('Keep the same attempt counts throughout the invocation');
|
||
expect(intro).toContain('changed finding scope needs a new decision');
|
||
expect(intro).toContain('Gated/unsupported specialists skip only their dispatch, never QA or Step 11');
|
||
expect(intro).toContain("Apply these decisions in order");
|
||
for (const step of ['specialists (9.1)', 'exploratory QA (9.2.1)', 'fixes and logging (9.4)']) {
|
||
expect(intro.indexOf(step)).toBeGreaterThanOrEqual(0);
|
||
}
|
||
expect(intro.indexOf('specialists (9.1)')).toBeLessThan(intro.indexOf('exploratory QA (9.2.1)'));
|
||
expect(intro.indexOf('exploratory QA (9.2.1)')).toBeLessThan(intro.indexOf('fixes and logging (9.4)'));
|
||
});
|
||
|
||
test('ship template consolidation: every fixing pass persists once before looping or stopping at cycle three', () => {
|
||
const finalize = compact(reviewTemplate.slice(reviewTemplate.indexOf('4. **'), reviewTemplate.indexOf('5. Output summary:')));
|
||
expect(finalize).toContain('Increment CYCLES once if fixes were applied');
|
||
expect(finalize).toContain('Finish and log this pass before choosing the next step');
|
||
expect(finalize).toContain('Complete items 5–6 exactly once with the original REVIEW_START');
|
||
expect(reviewTemplate.indexOf('6. Persist the review result')).toBeLessThan(reviewTemplate.indexOf('### Decide whether to repeat Step 9'));
|
||
expect(finalize).toContain('Then commit named fixed files');
|
||
expect(finalize).toContain('fixes also require `converged:false`');
|
||
expect(reviewFlow).toContain('**Third fixing cycle reached (`CYCLES >= 3`):** STOP and report recurring findings with `converged:false`; do not run a fourth fixing cycle');
|
||
expect(control).toContain('Keep the same attempt counts throughout the invocation');
|
||
expect(reviewFlow).toContain('**Fixes applied below the cap:**');
|
||
expect(reviewFlow).toContain("Every repeat starts before the checklist read and captures a fresh REVIEW_START");
|
||
expect(compact(entryTemplate)).toContain('Reuse waivers only for the same verified pre-existing failures and approved scope');
|
||
expect(reviewTemplate).toContain('--finish REVIEW_START');
|
||
expect(compact(reviewTemplate)).toContain('never recapture at persistence to certify unreviewed fixes');
|
||
expect(reviewTemplate).toContain('`CONVERGED`: completed with zero fixes');
|
||
});
|
||
|
||
test('ship template consolidation: named QA risks remain failed or incomplete and cannot waive other gates', () => {
|
||
const intro = compact(reviewTemplate.slice(reviewTemplate.indexOf('**Required-probe parent gate:**')));
|
||
expect(intro).toContain('explicitly accept each named probe\'s concrete risk. Skipping a fix is not risk acceptance or a passing probe');
|
||
expect(intro).toContain('With completed checklist and dispatched reviewers, failed/unavailable required probes block continuation');
|
||
expect(intro).toContain('Keep actual outcomes and incomplete flags; VERIFY_RESULT stays fail');
|
||
expect(intro).toContain('VERIFY_RESULT stays fail for plan-check exceptions');
|
||
expect(compact(reviewTemplate)).toContain('Record accepted untested risk separately, not as passing verification');
|
||
expect(intro).toContain('cannot waive missing reviewer output, recurring fixes or independent test/security gates');
|
||
expect(compact(reviewTemplate)).toContain('Skipping a fix is not risk acceptance or a passing probe');
|
||
expect(compact(reviewTemplate)).toContain('all required probes pass');
|
||
expect(compact(reviewTemplate)).toContain('Failed, blocked, inconclusive or not-run required probes mean false, never clean');
|
||
expect(compact(reviewTemplate)).toContain('Record accepted untested risk separately, not as passing verification');
|
||
});
|
||
|
||
test('ship template consolidation: late behavioral inputs revisit named gates while docs still get freshness checks', () => {
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(gate).toContain('Insert `5–11.5 → 12–14 → 16` before the pending Step 17');
|
||
expect(gate).toContain('`5–11.5 → 12–14 → 16`');
|
||
expect(gate).toContain("**Behavior, tests or build inputs changed:** Prompts/templates count as behavior");
|
||
expect(gate).toContain('**Behavior, tests or build inputs changed:** Prompts/templates count as behavior. Insert `5–11.5 → 12–14 → 16` before the pending Step 17');
|
||
expect(gate).toContain('Explain why other changes cannot affect it; changed or unknown dependencies require a rerun');
|
||
expect(gate).toContain("**Only authored docs or release metadata changed:** Keep Step 8's original child report and counts");
|
||
expect(gate).toContain("**No changes, or the docs-only checks still support the plan:** Continue to stage 3 without a new code review");
|
||
expect(gate).toContain("Keep the same attempt counts throughout the invocation");
|
||
expect(gate).toContain('Validate the outcome before Step 15');
|
||
expect(gate).toContain("retain `Documentation: blocked`, its reason and incomplete scope");
|
||
expect(gate).toContain("Validate the outcome before Step 15, then restart Step 16 stage 1");
|
||
expect(gate).toContain('Inspect writer handles, including the docs child');
|
||
expect(gate).toContain('STOP until confirmed');
|
||
});
|
||
|
||
test('ship template consolidation: ledger recovery never waives stale content or failed verification', () => {
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(gate).toContain('Only receipt storage/readback failed | Independently prove unchanged final content, the same command and valid age from the successful run\'s evidence');
|
||
expect(gate).toContain('Only receipt storage/readback failed');
|
||
expect(gate).toContain('Independently prove unchanged final content, the same command and valid age');
|
||
expect(gate).toContain('Cite its exact command, exit, timestamp and log as **ledger unavailable**, never FRESH. Without that proof, use STALE/MISSING');
|
||
expect(gate).toContain('--allow-paths CHANGELOG.md,VERSION,package.json,agents-digest/gstack-AGENTS.md');
|
||
expect(gate).toContain('Docs, TODO edits, new/generated tests and fixes make evidence STALE');
|
||
expect(gate).toContain('Docs, TODO edits, new/generated tests and fixes make evidence STALE');
|
||
expect(gate).toContain("**New, changed or unwaived test failure:** STOP publication. Run Steps 5–15, starting with Step 5's triage");
|
||
expect(gate).toContain('**New, changed or unwaived test failure:** STOP publication');
|
||
});
|
||
|
||
test('ship has one invocation route and retains each independently bounded allowance', () => {
|
||
const entry = compact(entryTemplate);
|
||
expect(entry).toContain('Every new invocation repeats Steps 1–16, including both reviews and the docs audit');
|
||
expect(entry).toContain('prepare the release (12–15) → verify frozen content (16)');
|
||
expect(entry).toContain('## Step 16: Verification Gate');
|
||
expect(compact(coverageTemplate)).toContain('Maximum 2 generation passes total per invocation');
|
||
expect(reviewFlow).toContain('do not run a fourth fixing cycle');
|
||
expect(compact(docsTemplate)).toContain('an initial audit plus ONE repair/re-audit');
|
||
expect(entry).toContain('Keep the same attempt counts throughout the invocation');
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(gate).toContain('against the snapshot saved before Step 12');
|
||
expect(gate).toContain("Content-preserving commits keep valid evidence");
|
||
expect(gate).toContain('Use its actual Step 5 label/command');
|
||
expect(gate).toContain("--label <lane> --expect-cmd '<exact Step 5 command>'");
|
||
});
|
||
|
||
test('ship resolves threshold, branch and installed-asset references without competing instructions', () => {
|
||
expect(entryTemplate).toContain("When Step 7 coverage meets its target");
|
||
expect(entryTemplate).not.toContain('Test coverage gaps within target threshold');
|
||
expect(entryTemplate.indexOf('Save the current branch as `<branch-name>`')).toBeGreaterThan(0);
|
||
expect(entryTemplate.indexOf('Save the current branch as `<branch-name>`')).toBeLessThan(entryTemplate.indexOf('refs/heads/<branch-name>'));
|
||
expect(entryTemplate).toContain('~/.claude/skills/gstack/review/TODOS-format.md');
|
||
expect(entryTemplate).not.toContain('`.claude/skills/review/TODOS-format.md`');
|
||
const skeleton = readTemplate('ship/SKILL.md');
|
||
const row = skeleton.split('\n').find(line => line.startsWith('| exploratory QA before Fix-First'))!;
|
||
expect(row).toContain('`sections/review-army.md`');
|
||
expect(row).not.toContain('below');
|
||
});
|
||
|
||
test('ship distinguishes a changed verified tree from failed test-receipt storage', () => {
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(gate).toContain('declared generation/build commands in project instructions, manifests, build files and CI');
|
||
expect(gate).toContain("Run declared docs/link/generated-file checks");
|
||
expect(gate).toContain('Docs, TODO edits, new/generated tests and fixes make evidence STALE even without a new code review');
|
||
expect(gate).toContain('Docs, TODO edits, new/generated tests and fixes make evidence STALE');
|
||
expect(gate).toContain('| FRESH (exit 0) | Cite the label, exit, timestamp and log. |');
|
||
expect(gate).toContain('Only receipt storage/readback failed');
|
||
expect(gate).toContain('Without that proof, use STALE/MISSING');
|
||
expect(gate).toContain('Docs, TODO edits, new/generated tests and fixes make evidence STALE');
|
||
});
|
||
|
||
test('ship names the approval scope, probe-risk decision, and native-review recovery', () => {
|
||
const entry = compact(entryTemplate);
|
||
const review = compact(controlTemplate + reviewTemplate);
|
||
const adversarial = compact(generateAdversarialStep({ host: 'claude', skillName: 'ship', tmplPath: '', paths: HOST_PATHS.claude }));
|
||
expect(entry).toContain('one private Markdown **invocation record**');
|
||
expect(entry).toContain('each approval\'s finding, files and authorized action');
|
||
expect(entry).toContain('Never borrow or replace a token');
|
||
expect(review).toContain('Use AskUserQuestion: stop for repair (recommended), or explicitly accept each named probe\'s concrete risk');
|
||
expect(review).toContain('explicitly accept each named probe\'s concrete risk. Skipping a fix is not risk acceptance or a passing probe');
|
||
expect(nativeFlow).toContain("One recovery retry is allowed only after a concrete prerequisite correction and restored access");
|
||
expect(nativeFlow).toContain('count it in the invocation record before launch');
|
||
expect(control).toContain('Keep the same attempt counts throughout the invocation');
|
||
expect(nativeFlow).toContain('if the recovery fails, ask for repair and remain blocked');
|
||
expect(adversarial).toContain('Outside-provider output cannot replace this pass');
|
||
expect(entry).toContain('Only the final VERSION/CHANGELOG commit gets the release version and co-author trailer. Do not create a Git tag');
|
||
expect(entry).toContain('encode null/undetermined as -1');
|
||
});
|
||
|
||
test('native recovery has its own bounded retry without resetting fixing or documentation limits', () => {
|
||
const adversarial = compact(generateAdversarialStep({ host: 'claude', skillName: 'ship', tmplPath: '', paths: HOST_PATHS.claude }));
|
||
expect(nativeFlow).toContain('One recovery retry is allowed only after a concrete prerequisite correction and restored access');
|
||
expect(reviewFlow).toContain('do not run a fourth fixing cycle');
|
||
expect(compact(docsTemplate)).toContain('an initial audit plus ONE repair/re-audit');
|
||
expect(nativeFlow).toContain('**Required native review incomplete:** STOP');
|
||
expect(adversarial).toContain('STOP and confirm the native task stopped');
|
||
expect(adversarial).toContain('Capture a fresh PASS_START and persist the new attempt separately');
|
||
expect(nativeFlow).toContain('confirm the native task stopped');
|
||
expect(nativeFlow).toContain('One recovery retry is allowed only after a concrete prerequisite correction and restored access');
|
||
expect(nativeFlow).toContain('count it in the invocation record before launch');
|
||
expect(control).toContain('Keep the same attempt counts throughout the invocation');
|
||
expect(nativeFlow).toContain('Without that correction, or if the recovery fails, ask for repair and remain blocked');
|
||
expect(nativeFlow).toContain('if the recovery fails, ask for repair and remain blocked');
|
||
expect(nativeFlow).toContain('not recovery retries');
|
||
expect(reviewFlow).toContain("Finish the complete review and QA before applying any fix in Step 9.4");
|
||
});
|
||
|
||
test('late verified generated outputs are committed before publication without absorbing user files', () => {
|
||
const commit = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 15:'), entryTemplate.indexOf('## Step 16:')));
|
||
const finish = compact(entryTemplate.slice(entryTemplate.indexOf('### 5. Report, then push'), entryTemplate.indexOf('## Step 17:')));
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(commit).toContain('Group VERSION + CHANGELOG + TODOS.md after the feature commits');
|
||
expect(finish).toContain('Commit only approved, verified release changes left uncommitted after Step 15');
|
||
expect(finish).toContain('including generated outputs; use its grouping rules and never create an empty commit');
|
||
expect(finish).toContain('Preserve unrelated user files');
|
||
expect(gate).toContain('Content-preserving commits keep valid evidence');
|
||
expect(gate).toContain('If content changes during or after verification, restart at stage 1 and complete all five stages before Step 17');
|
||
const commitPosition = finish.indexOf('Commit only approved, verified');
|
||
const pushPosition = finish.indexOf('continue to Step 17');
|
||
expect(commitPosition).toBeGreaterThanOrEqual(0);
|
||
expect(pushPosition).toBeGreaterThan(commitPosition);
|
||
});
|
||
|
||
test('missing test suites need a named gap decision rather than a fabricated fresh receipt', () => {
|
||
const tests = compact(readTemplate('ship/sections/tests.md.tmpl'));
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(tests).toContain('If no applicable test suite exists');
|
||
expect(tests).toContain('A) Add tests (recommended), B) Ship with this named testing gap, or C) Stop');
|
||
expect(tests).toContain('Reuse an actual prior B answer only for the same scope and content');
|
||
expect(tests).toContain('declining bootstrap alone is not that approval');
|
||
expect(tests).toContain('Independent build, eval, review and QA gates still apply');
|
||
expect(tests).toContain('A declared but unavailable suite is a blocker, not an absent suite');
|
||
expect(gate).toContain('No test lanes: require Step 5\'s explicit untested-scope approval for final content');
|
||
expect(gate).toContain("or run Steps 5–15, including the no-tests decision, then return to Step 16 stage 1");
|
||
expect(gate).toContain('Report the gap, never FRESH');
|
||
});
|
||
|
||
test('ship template consolidation: remote integration retains all allowances and cannot bypass publication guards', () => {
|
||
const push = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 17:'), entryTemplate.indexOf('## Step 18:')));
|
||
const recovery = pushFlow;
|
||
expect(push).toContain('**If the push fails, STOP.** No Step 19 or publication claim');
|
||
expect(recovery).toContain('Run Steps 5–16 before returning to Step 17. Never rewrite history');
|
||
expect(control).toContain("Keep the same attempt counts throughout the invocation");
|
||
expect(recovery).toContain("fetch and inspect the remote, then merge under Step 3's conflict rules");
|
||
expect(push).toContain('Never force-push');
|
||
expect(recovery).toContain('repeat Step 16 even if content is unchanged before returning to Step 17');
|
||
expect(recovery).toContain('Never bypass failed guards');
|
||
expect(push).toContain('Only a successful push or verified `ALREADY_PUSHED` proceeds');
|
||
expect(push).toContain('No documentation writer runs after push');
|
||
});
|
||
|
||
test('missing dispatched coverage is persisted and stopped before any zero-fix completion', () => {
|
||
const review = compact(controlTemplate + reviewTemplate);
|
||
const branches = reviewFlow.slice(reviewFlow.indexOf("### Decide whether to repeat Step 9"));
|
||
expect(branches.indexOf('Dispatched reviewer output missing')).toBeGreaterThanOrEqual(0);
|
||
expect(branches.indexOf('**Dispatched reviewer output missing:** STOP')).toBeGreaterThanOrEqual(0);
|
||
expect(branches.indexOf('**Fixes applied below the cap:**')).toBeGreaterThanOrEqual(0);
|
||
expect(branches.indexOf('**No edits in this pass:** Resolve the required-probe gate below. Only after it clears may you continue to Step 10')).toBeGreaterThanOrEqual(0);
|
||
expect(branches.indexOf('**Fixes applied below the cap:**')).toBeGreaterThan(branches.indexOf('**Dispatched reviewer output missing:** STOP'));
|
||
expect(branches.indexOf('**No edits in this pass:** Resolve the required-probe gate below. Only after it clears may you continue to Step 10')).toBeGreaterThan(branches.indexOf('**Dispatched reviewer output missing:** STOP'));
|
||
expect(review).toContain('Missing dispatched output uses `status:"unavailable"`, `completed:false` and `converged:false`');
|
||
expect(review).toContain('Pre-Landing Review: INCOMPLETE');
|
||
expect(branches).toContain('Retain queued fixes');
|
||
expect(branches).toContain("If this pass made edits, resume at the next decision");
|
||
expect(branches).toContain("otherwise run a fresh complete Step 9");
|
||
expect(review).toContain('Undispatched host-unsupported/gated specialists do not block');
|
||
expect(review).toContain("Apply these decisions in order");
|
||
expect(review).toContain('**No edits in this pass:** Resolve the required-probe gate below. Only after it clears may you continue to Step 10');
|
||
expect(review).toContain('This cannot waive missing reviewer output');
|
||
expect(review).toContain('`STATUS`: `unavailable` for missing dispatched reviewer output');
|
||
const settlement = review.slice(review.indexOf('## Step 9.4:'), review.indexOf('1. **Classify'));
|
||
expect(settlement).toContain('every dispatched reader/writer\'s handle. Wait for return or confirm termination');
|
||
expect(settlement).toContain('log incomplete through items 5–6 and STOP without edits');
|
||
expect(settlement).toContain('After terminal failure, independent evidence may support fixes');
|
||
});
|
||
|
||
test('external-comment fixes refresh tests and mandatory review without repeating prior decisions', () => {
|
||
const section = compact(readTemplate('ship/sections/greptile.md.tmpl'));
|
||
const finish = section.slice(section.indexOf('**After triage:**'));
|
||
expect(section).toContain('queue the approved fix without editing here');
|
||
expect(finish).toContain('If fixes were approved, save their approvals and comment references');
|
||
expect(reviewFlow).toContain("Finish the complete review and QA before applying any fix in Step 9.4");
|
||
expect(commentsFlow).toContain("Run Step 9's full review/fix loop, then return here");
|
||
const repair = reviewFlow;
|
||
expect(repair).toContain('**Fixes applied below the cap:** Insert Step 5, affected Steps 6–8 and all of Step 9 before the pending Step 10 in the work list');
|
||
expect(repair).toContain('**No edits in this pass:** Resolve the required-probe gate below. Only after it clears may you continue to Step 10');
|
||
expect(finish).not.toContain('before continuing to Step 11');
|
||
expect(finish).toContain('Finish the saved replies without asking again about completed fixes');
|
||
expect(finish).toContain('With no queued fixes, continue to Step 11');
|
||
});
|
||
|
||
test('triage distinguishes absent PRs, successful empty fetches and unavailable evidence', () => {
|
||
const section = compact(readTemplate('ship/sections/greptile.md.tmpl'));
|
||
expect(section).toContain('"status":"complete|no_pr|unavailable"');
|
||
expect(section).toContain('Use `complete` only after a successful fetch, including zero comments');
|
||
expect(section).toContain('`no_pr` only after confirming no PR exists');
|
||
expect(section).toContain('`unavailable` for `gh`/API errors or incomplete classification');
|
||
expect(section).toContain('a nonnegative integer total matching the comments array');
|
||
expect(section).toContain('An unknown or missing status is unavailable, never an empty successful review');
|
||
expect(section).toContain('"Greptile: no PR exists"');
|
||
expect(section).toContain('"Greptile: fetched, zero comments"');
|
||
expect(section).toContain('Include `Greptile triage: UNAVAILABLE (dispatch failed)` and the actual reason');
|
||
expect(section).toContain('Stop a running child and confirm it stopped before continuing');
|
||
expect(section).not.toContain('If no PR exists, `gh` fails, the API errors, or there are zero comments');
|
||
});
|
||
|
||
test('late-change routing compares a saved reviewed snapshot without waiving probe outcomes', () => {
|
||
const receipt = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 11.5:'), entryTemplate.indexOf('## Step 12:')));
|
||
expect(receipt).toContain('~/.claude/skills/gstack/bin/gstack-review-read');
|
||
expect(receipt).toContain("Match each to its saved handle, original token and source");
|
||
expect(receipt).toContain('(`skill:"review"`, `via:"ship"`)');
|
||
expect(receipt).toContain('Step 11 native record (`skill:"adversarial-review"`)');
|
||
expect(receipt).toContain("reject outside-provider or older invocation records");
|
||
expect(receipt).toContain("Require the native record's `review_binding.state` to be `verified`");
|
||
expect(receipt).toContain("All three snapshots must match: its `wtree`, Step 9.4's `review_binding.start_wtree` and `review_binding.end_wtree`");
|
||
expect(receipt).toContain("A mismatch or missing record/field blocks release preparation: report **Review records missing or mismatched**");
|
||
expect(receipt).toContain('Never attach new tokens to old work');
|
||
expect(receipt).toContain("Keep Step 9.4's incomplete flags and the user's exception");
|
||
expect(receipt).toContain("Matching content does not mean the failed or unrun probes passed");
|
||
expect(receipt).toContain("A named probe-risk exception may leave Step 9.4's root `wtree` absent; item 2 still compares its start/end snapshots");
|
||
expect(receipt).not.toContain('phase:"core"');
|
||
expect(receipt).not.toContain('Step 9.5');
|
||
expect(receipt).not.toContain('source:"in-host"');
|
||
expect(receipt).not.toContain('status:"clean"');
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(gate).toContain('~/.claude/skills/gstack/bin/gstack-wtree');
|
||
expect(gate).toContain('git diff <reviewed-tree> <current-tree>');
|
||
expect(gate).toContain('against the snapshot saved before Step 12');
|
||
expect(gate).toContain('Missing snapshots block this comparison');
|
||
expect(gate).toContain('Missing snapshots block this comparison, regardless of HEAD equality');
|
||
expect(gate.indexOf('**Reuse a check when its inputs match.**')).toBeGreaterThan(gate.indexOf('### 4. Verify the frozen candidate'));
|
||
expect(gate).toContain('**Check each test lane\'s receipt as well.**');
|
||
});
|
||
|
||
test.each(ALL_HOST_CONFIGS.map(({ name }) => name))('%s: late adversarial fixes have a bounded return path and preserve approvals', host => {
|
||
const ctx = { host, skillName: 'ship', tmplPath: '', paths: HOST_PATHS[host] };
|
||
const text = generateAdversarialStep(ctx);
|
||
const finishPosition = text.indexOf('### Finish the adversarial phase');
|
||
expect(finishPosition).toBeGreaterThanOrEqual(0);
|
||
const finish = compact(text.slice(finishPosition));
|
||
const outcomes = [
|
||
'**Required native review incomplete:**',
|
||
'**Fixes queued after native completion:**',
|
||
'**Native complete with no queued fixes:**',
|
||
].map(outcome => finish.indexOf(outcome));
|
||
expect(outcomes.every(position => position >= 0)).toBe(true);
|
||
expect(outcomes).toEqual([...outcomes].sort((a, b) => a - b));
|
||
expect(text).toContain('queued for the parent; do not edit during Step 11');
|
||
expect(text).toContain('If A: queue the approved findings without editing here');
|
||
expect(reviewFlow).toContain("Every repeat starts before the checklist read and captures a fresh REVIEW_START");
|
||
expect(reviewFlow).toContain("Finish the complete review and QA before applying any fix in Step 9.4");
|
||
expect(control).toContain('Keep the same attempt counts throughout the invocation');
|
||
expect(finish).toContain('Insert Steps 9, 10 and 11 before the pending Step 11.5 in the work list. Step 9 completes full review before fixes');
|
||
expect(compact(entryTemplate)).toContain('each approval\'s finding, files and authorized action');
|
||
expect(reviewFlow).toContain('do not run a fourth fixing cycle');
|
||
expect(reviewFlow).toContain('**Third fixing cycle reached (`CYCLES >= 3`):** STOP and report recurring findings with `converged:false`; do not run a fourth fixing cycle');
|
||
expect(reviewFlow).toContain('**Fixes applied below the cap:** Insert Step 5, affected Steps 6–8 and all of Step 9 before the pending Step 10 in the work list');
|
||
expect(finish).toContain('**Native complete with no queued fixes:**');
|
||
expect(finish).toContain('**Native complete with no queued fixes:** Finish the memory updates below, then continue to Step 11.5');
|
||
expect(text).toContain('retain the acknowledged findings and failed gate');
|
||
expect(text).toContain('do not report a clean review');
|
||
expect(finish).toContain('**Required native review incomplete:** STOP');
|
||
expect(finish).toContain('Optional outside failures retain their own incomplete records');
|
||
expect(compact(text)).toContain('native completion never credits outside coverage');
|
||
const standalone = generateAdversarialStep({ ...ctx, skillName: 'review' });
|
||
expect(standalone).not.toContain('Before Step 12:');
|
||
expect(standalone).not.toContain('### Finish the adversarial phase');
|
||
expect(standalone).toContain("queue the findings and this approval for Step 5's Fix-First handling");
|
||
expect(standalone).toContain('After edits, the full re-review repeats this same structured invocation and diff scope');
|
||
expect(standalone).toContain('do not start an inner repair loop');
|
||
});
|
||
|
||
test('existing release levels have an explicit recovery rule, not implicit rebump approval', () => {
|
||
const root = entryTemplate;
|
||
const version = compact(root.slice(root.indexOf('## Step 12:'), root.indexOf('## Step 14:')));
|
||
expect(version).toContain('use the first changed component from `baseVersion` to `currentVersion` (major/minor/patch/micro');
|
||
expect(version).toContain('an absent fourth component is zero');
|
||
expect(version).toContain('Continue at item 3, not another automatic bump');
|
||
expect(version).toContain('Only approval changes the existing version');
|
||
});
|
||
|
||
test('distribution setup asks for unknown targets and cannot release before review', () => {
|
||
const root = entryTemplate;
|
||
const distribution = root.slice(root.indexOf('## Step 2:'), root.indexOf('## Step 3:'));
|
||
expect(distribution).toContain('git diff origin/<base> --diff-filter=A --name-only');
|
||
expect(distribution).toContain('a new `package.json` or `Cargo.toml` alone does not establish a publishable');
|
||
expect(distribution).toContain('Ask for unknown targets, registries or access first');
|
||
expect(distribution).toContain('never invent credentials');
|
||
expect(distribution).toContain('include the workflow in tests and review');
|
||
expect(distribution).toContain('Do not publish a release during `/ship`');
|
||
});
|
||
|
||
test('ship entry decisions identify Swift app products and wait on ambiguous merge resolutions', () => {
|
||
const apple = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 0.9:'), entryTemplate.indexOf('## Step 1:')));
|
||
expect(apple).toContain('If the ask is App Store/TestFlight distribution');
|
||
expect(apple).toContain("Read `Package.swift` and its entrypoint");
|
||
expect(apple).toContain('distinguish an app from a library/CLI');
|
||
expect(apple).toContain('If unclear, use AskUserQuestion');
|
||
expect(apple).toContain('AskUserQuestion to identify the target and wait before choosing a release path');
|
||
expect(apple).toContain('For a confirmed app, **STOP and Read');
|
||
const merge = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 3:'), entryTemplate.indexOf('{{SECTION:tests}}')));
|
||
expect(merge).toContain('Try to auto-resolve if they are simple');
|
||
expect(merge).toContain('For complex or ambiguous conflicts, **STOP**, show the conflicting choices');
|
||
expect(merge).toContain('use AskUserQuestion for the needed resolution decision');
|
||
expect(merge).toContain('wait for the answer before editing or continuing');
|
||
});
|
||
|
||
test('ship final preparation discovers declared commands and verifies the versioned digest output', () => {
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
expect(gate).toContain('declared generation/build commands in project instructions, manifests, build files and CI');
|
||
expect(gate).toContain('Run them and save results');
|
||
expect(gate).toContain('If none exists, record not applicable and the inspected sources');
|
||
expect(gate).toContain('A missing prerequisite or failed build stops shipping');
|
||
const version = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 12:'), entryTemplate.indexOf('{{SECTION:changelog}}')));
|
||
expect(version).toContain('only when it and committed `agents-digest/gstack-AGENTS.md` exist');
|
||
expect(version).toContain('If `agentsDigest` is false, run `bun scripts/gen-agents-digest.ts` and stage the digest with the bump');
|
||
expect(version).toContain("Before push, verify the committed digest matches generation for the selected VERSION");
|
||
});
|
||
|
||
test('ship publication metadata resolves open state before composing a title', () => {
|
||
const title = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 18:'), entryTemplate.indexOf('{{SECTION:pr-body}}')));
|
||
const query = title.indexOf('gh pr list --head <branch-name> --state open --json number,title,url');
|
||
const prepare = title.indexOf('Prepare the title from that result');
|
||
expect(query).toBeGreaterThanOrEqual(0);
|
||
expect(prepare).toBeGreaterThan(query);
|
||
expect(title).toContain('glab mr list --source-branch <branch-name> --output json` (defaults to open)');
|
||
expect(title).toContain('A successful empty array means new');
|
||
expect(title).toContain('one match supplies the existing title/identity');
|
||
expect(title).toContain('Lookup failure or ambiguous matches **STOP** for resolution, never mean no PR');
|
||
expect(title).toContain("Save the result for Step 19's recheck");
|
||
expect(title).toContain('Save the result as `NEW_TITLE` for Step 19');
|
||
expect(title).toContain('start with `v$NEW_VERSION `; never publish an unprefixed title');
|
||
});
|
||
|
||
test('ship explains receipts and genuine review tokens before selecting current invocation records', () => {
|
||
const state = compact(entryTemplate.slice(entryTemplate.indexOf('### Keep state'), entryTemplate.indexOf('{{SECTION_INDEX:ship}}')));
|
||
expect(state).toContain('A **receipt** is saved evidence of a check\'s command, result and consumed content');
|
||
expect(state).toContain('**start token** is the opaque value returned by `gstack-review-log --start` before it reads the diff');
|
||
expect(state).toContain('`REVIEW_START` for Step 9, a separate `PASS_START` for each Step 11 attempt, and `DESIGN_START` for design');
|
||
expect(state).toContain('Finish each pass with its original token');
|
||
expect(state).toContain('`gstack-wtree` prints a Git tree hash covering tracked and non-ignored untracked files');
|
||
});
|
||
|
||
test('ship documentation-only plan refresh preserves the original audit and routes unsupported classifications back to its gates', () => {
|
||
const route = compact(entryTemplate.slice(entryTemplate.indexOf('### 2. Choose the change route'), entryTemplate.indexOf('### 3. Resolve documentation freshness')));
|
||
expect(route).toContain("Keep Step 8's original child report and counts");
|
||
expect(route).toContain("Recheck affected plan items using their recorded verification");
|
||
expect(route).toContain("append current evidence to the invocation record");
|
||
expect(route).toContain("run Step 8's audit and decision gates only, then return to Step 16 stage 1. Never edit the child's counts yourself");
|
||
expect(route).toContain("**No changes, or the docs-only checks still support the plan:** Continue to stage 3 without a new code review");
|
||
});
|
||
|
||
test('ship recovery map preserves ordered review, build and push transitions without new allowances', () => {
|
||
const gate = compact(controlTemplate + entryTemplate.slice(entryTemplate.indexOf('## Step 16:'), entryTemplate.indexOf('## Step 17:')));
|
||
const rows = ['**Non-fast-forward push:**', '**Authentication, hook or network failure:**'].map(outcome => pushFlow.indexOf(outcome));
|
||
expect(rows.every(position => position >= 0)).toBe(true);
|
||
expect(rows).toEqual([...rows].sort((a, b) => a - b));
|
||
expect(reviewFlow).toContain("Every repeat starts before the checklist read and captures a fresh REVIEW_START. Finish the complete review and QA before applying any fix in Step 9.4");
|
||
expect(reviewFlow).toContain('Insert Step 5, affected Steps 6–8 and all of Step 9 before the pending Step 10 in the work list');
|
||
expect(commentsFlow).toContain("Run Step 9's full review/fix loop, then return here");
|
||
expect(gate).toContain('Insert `5–11.5 → 12–14 → 16` before the pending Step 17');
|
||
expect(gate).toContain('Insert `5–11.5 → 12–14 → 16` before the pending Step 17, then stop this step. This repair excludes Step 14.5');
|
||
expect(gate).toContain('A missing prerequisite or failed build stops shipping: report **Build failed or prerequisite missing**, with the command, error and needed repair');
|
||
expect(gate).toContain('Repair the prerequisite or build, then repeat stage 1');
|
||
expect(gate).toContain("After it passes, continue to stage 2; treat any content repair as a behavioral change there");
|
||
expect(gate).toContain('Never invent a substitute command');
|
||
expect(gate).toContain('A `package.json` version-only edit can qualify; scripts, dependencies and runtime configuration require live tests');
|
||
expect(gate).toContain('Uncertain edits cannot be exempted');
|
||
const commits = compact(entryTemplate.slice(entryTemplate.indexOf('## Step 15:'), entryTemplate.indexOf('## Step 16:')));
|
||
expect(commits).toContain('Only the final VERSION/CHANGELOG commit gets the release version and co-author trailer');
|
||
});
|
||
|
||
test('ship r22 routes each late change to one restart point before final checks', () => {
|
||
const route = compact(entryTemplate.slice(entryTemplate.indexOf('### 2. Choose the change route'), entryTemplate.indexOf('### 3. Resolve documentation freshness')));
|
||
const cases = ['**Behavior, tests or build inputs changed:**',
|
||
'**Only authored docs or release metadata changed:**', '**No changes, or the docs-only checks still support the plan:**'];
|
||
const positions = cases.map(label => route.indexOf(label));
|
||
expect(route).toContain("Classify the comparison in this order");
|
||
expect(positions.every(position => position >= 0)).toBe(true);
|
||
expect(positions).toEqual([...positions].sort((a, b) => a - b));
|
||
const behavior = route.slice(positions[0], positions[1]);
|
||
expect(behavior).toContain('Insert `5–11.5 → 12–14 → 16` before the pending Step 17');
|
||
expect(behavior).toContain('Insert `5–11.5 → 12–14 → 16` before the pending Step 17, then stop this step. This repair excludes Step 14.5');
|
||
expect(behavior).toContain('This repair excludes Step 14.5 because the rebuild can change generated docs. Step 16 restarts at stage 1');
|
||
expect(behavior).toContain('rebuild and compare again before stage 3 decides documentation freshness');
|
||
const docs = route.slice(positions[1], positions[2]);
|
||
expect(docs).toContain("run Step 8's audit and decision gates only, then return to Step 16 stage 1");
|
||
expect(docs).toContain('Never edit the child\'s counts');
|
||
expect(route.slice(positions[2])).toContain("**No changes, or the docs-only checks still support the plan:** Continue to stage 3 without a new code review");
|
||
});
|
||
|
||
test('ship r22 re-audits return through commit and regeneration rather than bypassing freshness', () => {
|
||
const docs = compact(entryTemplate.slice(entryTemplate.indexOf('### 3. Resolve documentation freshness'), entryTemplate.indexOf('### 4. Verify the frozen candidate')));
|
||
expect(docs).toContain("Compare the base and hashes of the selected release paths, generated outputs and docs/templates with Step 14.5\'s saved values");
|
||
expect(docs).toContain("accepted audit matches all inputs | Continue to stage 4");
|
||
const retryStart = docs.indexOf('**An attempt remains, with changed inputs or an available repair:**');
|
||
const retryEnd = docs.indexOf('**Otherwise:**');
|
||
expect(retryStart).toBeGreaterThanOrEqual(0);
|
||
expect(retryEnd).toBeGreaterThan(retryStart);
|
||
const retry = docs.slice(retryStart, retryEnd);
|
||
expect(retry).toContain('Validate the outcome before Step 15');
|
||
expect(compact(docsTemplate)).toContain('Only an actual user exception counts');
|
||
expect(compact(docsTemplate)).toContain('Reconcile those before proceeding');
|
||
expect(retry).toContain("Validate the outcome before Step 15, then restart Step 16 stage 1 to regenerate and compare again");
|
||
expect(retry).not.toContain('Continue to stage 4');
|
||
expect(finalGate).toContain("STOP unless the user accepts the specific named documentation risk and all unwaivable gates clear");
|
||
expect(docs).toContain("retain `Documentation: blocked`, its reason and incomplete scope");
|
||
expect(docs).toContain("covers the same approved scope and exact content");
|
||
expect(docs).toContain('Never run a third audit');
|
||
});
|
||
|
||
test('ship plan audit resolves scope drift before learnings and stops on an unverified N', () => {
|
||
const section = readTemplate('ship/sections/plan-completion.md');
|
||
expect(section.indexOf('## Step 8.1:')).toBeLessThan(section.indexOf('## Step 8.2:'));
|
||
expect(section.indexOf('## Step 8.2:')).toBeLessThan(section.indexOf('## Prior Learnings'));
|
||
expect(section).toContain('N) Not done — block ship and report the item as NOT DONE; do not offer a second deferral choice');
|
||
expect(section).toContain('Any N: STOP');
|
||
expect(section).not.toContain('re-enter the priority-1 gate');
|
||
});
|
||
|
||
test('outside challenge and documentation reruns preserve their actual blocking owners', () => {
|
||
const adversarial = readTemplate('ship/sections/adversarial.md');
|
||
expect(adversarial).toContain('An unavailable outside challenge does not block shipping by itself');
|
||
expect(adversarial).toContain('structured P1 and non-convergence gates still apply');
|
||
expect(adversarial).toContain("Returning here never resets Step 9's three-cycle fix limit");
|
||
const standaloneReview = readTemplate('review/sections/adversarial.md');
|
||
expect(standaloneReview).toContain('supported findings still enter Step 5 Fix-First');
|
||
expect(standaloneReview).not.toContain('supported findings still enter Step 11');
|
||
const docs = readTemplate('ship/sections/pr-body.md');
|
||
expect(docs).toContain('**Existing open PR/MR:** update');
|
||
expect(docs).toContain('do not run the create commands below');
|
||
expect(docs).not.toContain('no PR exists yet');
|
||
expect(entryTemplate.indexOf('## Step 14.5:')).toBeLessThan(entryTemplate.indexOf('## Step 17:'));
|
||
});
|