From daf661374fb9ab73f8a4ac891de228c13a714339 Mon Sep 17 00:00:00 2001 From: Garry Tan Date: Mon, 2 Nov 2026 09:44:00 -0800 Subject: [PATCH] v1.93.10.0 wave(docs): #3590 #3591 #3819 #3618 #3824 #3828 (#3847) * Attribute every paid trial's cost: bind label-named records by testName, price aborted SDK sessions from streamed usage, model-free cases cost $0 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: case cost adds streamed sessions to record sums and keeps record cost_known Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: the paid report headline counts ledger-only session cost once Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: a cost-only record never sets the trial model Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: recordE2E writes cost_case_id only for a registered label-named case Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CHANGELOG for paid-report cost attribution (Unreleased) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: the headline adds only streamed session cost; cache writes without a 5m key Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: how the paid report prices a trial and what stays cost-unknown Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * Price PTY sessions from their transcripts: pin a session id, sum the session's and its subagents' usage into the ledger's streamed_cost_usd Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: transcript pricing never throws from a PTY ledger writer Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: pin transcript-cost.ts as non-behavioral at HARNESS_VERSION 6 Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: recognise --session-id= and --resume= forms Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: CHANGELOG for PTY transcript pricing (Unreleased) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: PTY sessions priced from their transcripts Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: price PTY transcripts without adding a launch argument; native AUQ capture opts out Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: harness notes and CHANGELOG match the transcript claim Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(flaky): gstack-flaky run reruns a failed JUnit test once and ledgers the flake (GSTA-158) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(flaky): stream output, keep unreported runner failures red, fail-closed duplicates and nonzero reruns Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: pre-landing review fixes gstack-flaky never greens an incomplete run: a targeted rerun needs the runner's summary proving the first run complete, otherwise (and always for generic runners) the rerun repeats the whole command. A rerun clears a test only when it exits 0 and the test passes once on its first attempt. Killed runners exit 3 (FLAKY_COMMAND_KILLED) and signals are forwarded. The first report is restored at --junit with reruns kept beside it; ids are redacted at every output; the ledger gets its own GSTACK_FLAKE_LEDGER_JUNIT; fixtures are registered in FREE_FIXTURES. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: latch cancellation and check whole-command rerun reports A cancel forwarded to a runner that traps the signal now counts as killed for every later attempt, so a cancelled job is never rerun or greened. A whole-command rerun clears nothing when its report has a failed test, misses a first-run test, or its runner counted failures outside the report. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix: whole-command rerun when coverage or runner-flaky tests can fail the run A coverage threshold or a fail-on-flaky policy fails a run for a reason a narrowed rerun cannot reproduce, so either forces a whole-command rerun. --junit refuses an existing file that is not a JUnit report instead of deleting it. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(flaky): rerun the whole command by default; targeted rerun is opt-in A rerun counts only on the runner's own full green verdict: exit 0, no failed or missing test, nothing counted outside the report. That covers every way a run can fail, which a narrowed rerun cannot (a coverage threshold with an lcov reporter, a fail-on-flaky policy, a test never reached). --rerun-scope test reruns the failed test alone, with its preconditions documented and the complete-run checks kept as a safety net. An unreadable existing --junit file is a usage error, not a crash. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: gstack-flaky CHANGELOG entry and standalone-binaries row (GSTA-158) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(flaky): quarantine registry for repeat flakes (GSTA-158 P2) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(flaky): bound renewal dates; match non-ASCII paths in check --base Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(flaky): reword the FLAKY_QUARANTINE_BASE hint so the egress scanner does not read it as a network op Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(agent-sdk): every SDK caller passes the claude_code preset or names why not The SDK's default system prompt is a bare stub that drops the line telling the model to run /skill through the Skill tool. runAgentSdkTest now refuses a missing, empty or bare-string prompt; non-preset callers name a reason; a free tripwire scans test/ and scripts/ for the same mistake. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test: record the SDK prompt guard as a non-behavioral harness change and baseline its tripwire harness-version: runAgentSdkTest validates systemPrompt before starting; every live caller already passed the claude_code preset, so no verdict can change. test-of-test ratchet: the tripwire's subject is the eval harness by design. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs: name the preset literal callers pass and the unnamed-prompt refusal Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * feat(eval-plan): frontier models under test (R54) Haiku and Sonnet are not models under test. dry-run refuses a plan whose every arm is Haiku or Sonnet unless --tier-question names what it asks about that tier, warns on a mix, and re-costs the plan on Opus 5.5 and GPT-6.1 Sol. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(eval-plan): trim R54 skill prose and raise the eval-plan context ceiling The R54 paragraph and CHECK: frontier bullet were cut to the minimum; the exemptions and verdict rule stay in docs/TESTING_INTERNALS.md. The remaining growth is the feature, so only the eval-plan eager ceiling moves (4887 -> 5458, the capture helper's value); other skills' ceilings are left as they were. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(eval-plan): pilot start keeps the R54 refusal; --tier-question rejects a flag Review pass 1 (full depth) found the frontier refusal could be skipped by starting a pilot on Haiku or Sonnet arms behind a dry run made on other arms, or behind a dry-run.json written before the check existed. startPilot now refuses a pilot whose every arm is Haiku or Sonnet unless its dry run recorded a tier question. dry-run --tier-question no longer takes the next flag as its answer. The testing doc now says the frontier re-cost is printed for comparison with the brief cap, not enforced. Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(support-tiers): Windows CI in the present tense now that windows-smoke is required (#3806) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * chore: empty commit for a clean check set at the same tree (cancelled orphan free-suite check at 97487df) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(skills): /eval-plan entry names the R54 frontier check Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --- CHANGELOG.md | 40 ++ VERSION | 2 +- agents-digest/gstack-AGENTS.md | 2 +- bin/gstack-eval-plan | 14 +- bin/gstack-flaky | 44 +- captain/templates/automation-flaky-pass.md | 9 +- docs/TESTING_INTERNALS.md | 128 ++++- docs/captain.md | 4 +- docs/evals/census-red.md | 2 +- docs/flaky.md | 125 ++++- docs/skills.md | 5 +- docs/standalone-binaries.md | 2 +- docs/support-tiers.md | 7 +- docs/troubleshooting.md | 24 +- eval-plan/SKILL.md | 5 + eval-plan/SKILL.md.tmpl | 5 + lib/eval-plan.ts | 24 +- lib/flaky-run.ts | 130 ++++- lib/junit.ts | 8 + lib/pricing.ts | 63 +++ lib/quarantine.ts | 447 ++++++++++++++++++ package.json | 2 +- scripts/harness-version.json | 17 +- scripts/lib/paid-report.ts | 41 +- scripts/preflight-agent-sdk.ts | 3 +- test/agent-sdk-runner.test.ts | 7 +- test/fixtures/context-budget.json | 2 +- test/flaky-run.test.ts | 2 +- test/helpers/agent-sdk-runner.ts | 23 +- test/helpers/auq-native-capture.ts | 2 +- .../claude-pty-runner.launch.unit.test.ts | 40 ++ test/helpers/e2e-helpers.ts | 1 + test/helpers/eval-store.ts | 3 + test/helpers/pty/launch.ts | 25 +- test/helpers/pty/session.ts | 3 +- test/helpers/pty/transcript-cost.ts | 74 +++ test/helpers/sdk-system-prompt.ts | 32 ++ test/helpers/session-ledger.ts | 2 + test/helpers/session-runner.ts | 4 +- test/helpers/touchfiles-data.ts | 106 ++--- test/overlay-lifecycle.test.ts | 2 +- test/overlay-sdk-cancel-eof.test.ts | 2 +- test/paid-report-census.test.ts | 23 + test/paid-report-cost.test.ts | 203 ++++++++ test/pricing-eval-plan.test.ts | 48 +- test/quarantine.test.ts | 442 +++++++++++++++++ test/sdk-system-prompt-tripwire.test.ts | 135 ++++++ test/setup-gbrain-fixture.test.ts | 6 +- test/test-of-test-ratchet.test.ts | 1 + test/trial-cause.test.ts | 2 +- 50 files changed, 2168 insertions(+), 175 deletions(-) create mode 100644 lib/quarantine.ts create mode 100644 test/helpers/pty/transcript-cost.ts create mode 100644 test/helpers/sdk-system-prompt.ts create mode 100644 test/paid-report-cost.test.ts create mode 100644 test/quarantine.test.ts create mode 100644 test/sdk-system-prompt-tripwire.test.ts diff --git a/CHANGELOG.md b/CHANGELOG.md index 9375dc182..fabef13e5 100644 --- a/CHANGELOG.md +++ b/CHANGELOG.md @@ -1,5 +1,45 @@ # Changelog +## [1.93.10.0] - 2026-11-02 + +### Changed + +- Evals test frontier models (R54). /eval-plan and docs/TESTING_INTERNALS.md#frontier-models-under-test now say that models under test are Opus 5.5 and GPT-6.1 Sol, plus at most one named low-cost primary. Haiku and Sonnet aren't stand-ins for a frontier model, and a Haiku- or Sonnet-only result can't carry a KEEP, FIX-METHOD or CUT-CANDIDATE verdict. Judges, review voices and housekeeping models keep their models. `gstack-eval-plan dry-run` refuses a plan whose every arm is Haiku or Sonnet unless `--tier-question` names what it asks about that tier, warns on a mixed plan, and prices the whole plan on frontier models. `pilot start` refuses a Haiku- or Sonnet-only pilot unless its dry run recorded that tier question. + +### Fixed + +- Agent SDK evals can no longer run on the SDK's bare stub prompt by accident. Every `runAgentSdkTest` and direct SDK `query()` caller now passes Claude Code's preset or names why it doesn't. The runner refuses a missing, empty or bare-string prompt, and a free tripwire test scans test/ and scripts/ for the same mistake. docs/TESTING_INTERNALS.md#agent-sdk-system-prompt says to record which prompt each arm used, and to treat a null result from an arm on the stub as FIX-METHOD. + +**A test that keeps flaking while someone fixes it can be quarantined instead of skipped, and it still can't turn a red run green.** `gstack-flaky quarantine add` puts the test in `.gstack/quarantine.json` with an owner, a ledger link and an expiry. The test keeps running on every run and is never counted as a pass. When every test an attempt failed is quarantined, the whole command may run again, up to 3 attempts, and the run is green only when an attempt gets the runner's own full green verdict, so a coverage threshold or another failure outside the report stays red. Before this, a test that flaked every few runs either went red on every PR or got skipped and forgotten. + +### Added +- **Quarantine registry, `gstack-flaky quarantine add|renew|release|check|report`** (`.gstack/quarantine.json`, GSTA-158 P2): a quarantined test that fails all 3 attempts is a `hard-break` (red), a quarantined id missing from a run that included its file is red, and quarantined tests are listed (`FLAKY_RESULT … quarantined=`) and ledgered (`quarantined-pass`, `quarantined-fail`, `hard-break`) on every run. Tests that are not quarantined keep their one rerun. +- **Entries are owned and expire**: owner, ledger link, class (`detector`, `harness`, `timing`, `model-latency`; `product` and `infra` refused), evidence, 7 days by default and 14 at most, one renewal of up to 7 days with new evidence and the owner named again. An expired entry stops applying with no edit and prints the renew and release commands. Live entries are capped at 10% of the suite (at least 1, and 5 under 50 tests). +- **`run --base `** reads the registry from the base branch, so a change cannot quarantine the test it breaks. **`check --base`** refuses an entry added in the change that edits its test's file, an entry removed without a release record, a removed release record and rewritten history. **`report --ledger `** lists entries soonest-expiring first and marks those with 10 consecutive clean passes ready to release. gstack's own `CASE_QUARANTINE` / `EVAL_POLICY` is unchanged and shares no schema with it. + +### Docs +- `docs/flaky.md#quarantine`: commands, rules, expiry, cap, classes, the `CASE_QUARANTINE` separation and the daily-pass `gh run download` + `report` loop. `captain/templates/automation-flaky-pass.md` and `docs/captain.md` run `report` and fix expiring entries first. + +### Tests +- `test/quarantine.test.ts`: add refusals (cap, more than 14 days, no evidence, product or infra class, unknown id), one renewal and future-dated renewals, release, `check --base` against git fixtures (non-ASCII paths included), expiry, a hard break across 3 attempts, the false-green regression (exit 1 from outside the report while only a quarantined test fails stays red), missing ids with their file present or absent, and the registry read from the base branch. + +### Gate integrity +- `test/flaky-run.test.ts`: the exact `FLAKY_RESULT` line it expects gains the new `quarantined=0` field. No other assertion, threshold or skip changed. + +- `docs/support-tiers.md` describes Windows CI as it works now. `windows-smoke` is the required Windows check on pull requests, and the six-shard `windows-free-tests` suite runs nightly on main or by hand and never blocks a pull request. The page was written before #3806 landed, so it still said these changes were coming. + +**The train gate's paid report now prices the trials it used to call "cost unknown".** 32 of 139 gate trials had no cost on every gate since Oct 26, so the report's total understated a gate by about $7.50 (GSTA-150 audit). All four causes are fixed. + +### Fixed +- **Label-named records in multi-case shards** (`test/helpers/e2e-helpers.ts`, `scripts/lib/paid-report.ts`): a `claude -p` record named by its display label ("browse basic commands") carries `cost_case_id` from `runSkillTest`'s registered test name, and the report binds its cost to that case. The failed record, failure class and model still come from the records named by case id, so no verdict, class or pass-rate series changes (22 trials: bws, session-intelligence, workflow, skillify, review-attribution, review, gate-integrity, diagram). +- **Aborted Agent SDK sessions** (`test/helpers/agent-sdk-runner.ts`, `lib/pricing.ts`): a session that ends without a result event logs its streamed usage as `streamed_cost_usd` in the session ledger, priced once per message id at its largest output, subagent turns included, with 5-minute cache writes at 1.25x and 1-hour writes at 2x input. An unpriced model leaves the cost unknown (auq-format-gate). +- **Model-free cases**: `timeline-event-flow` runs no model, so with no record and no session it is a known $0. A test checks every listed case's body starts no model session. +- **PTY sessions** (`test/helpers/pty/launch.ts`, `test/helpers/pty/session.ts`, `test/helpers/pty/transcript-cost.ts`): each PTY ledger row prices the session's transcript (`projects/*/.jsonl` plus its `subagents/` files) as `streamed_cost_usd`. The session is the caller's `--session-id`, else the one transcript that appeared during the launch for its cwd, so the launcher adds no argument and concurrent tests sharing a config dir never price each other. No transcript, two new transcripts for one cwd, no usage or an unpriced model leaves the cost unknown, never $0, and a read error never reaches the test. The native AskUserQuestion capture, which never reads model transcripts, opts out (`priceTranscript: false`). This covers 8 cases and 14 sessions per gate: plan-mode-no-op, plan-design-with-ui-scope, the plan-ceo and plan-devex finding-floor and plan-mode cases, autoplan-guard-pty and office-hours-auto-mode. Checked live, a `claude -p` session with one subagent priced $0.090376 from its transcripts, equal to its `total_cost_usd`. +- **The headline total** adds session cost that no collector record carries, so newly priced trials reach the gate's `cost $X` line exactly once. + +### Tests +- `test/paid-report-cost.test.ts`: pricing arithmetic, streamed dedupe, `caseCost`, `recordE2E`'s `cost_case_id`, a two-case shard whose label-named records bind by cost without changing the failed record, class or model. `test/paid-report-census.test.ts`: a record-less trial's streamed cost reaches the trial and the verdict total once. `test/paid-report-cost.test.ts` also prices a PTY session, its inline sidechains and subagent files once per message id, leaves a foreign session, a missing or unreadable transcript or an unpriced model unknown, and claims only the one new transcript for a launch's cwd. `test/helpers/claude-pty-runner.launch.unit.test.ts`: a real launch prices the transcript it created without adding an argument, and an opted-out launch prices nothing. + ## [1.93.9.0] - 2026-11-02 **`gstack-ship-receipt read --check-prose` no longer reads the required Review-loop exception line as counter claims (GST-977).** `write --review-loop-exception` requires the PR body to carry the whole `Review-loop exception: …` line word for word, but the prose check read that line as prose. On gstack-evals #139 the owner's reason "outside 1 and 2 skip detector" was read as a `2 skip` claim against the receipt's 70 skips, so no body could pass both checks. diff --git a/VERSION b/VERSION index 7ab5f1da9..40f3543d0 100644 --- a/VERSION +++ b/VERSION @@ -1 +1 @@ -1.93.9.0 +1.93.10.0 diff --git a/agents-digest/gstack-AGENTS.md b/agents-digest/gstack-AGENTS.md index f55349cf4..7a37f602b 100644 --- a/agents-digest/gstack-AGENTS.md +++ b/agents-digest/gstack-AGENTS.md @@ -1,4 +1,4 @@ -# gstack digest v1.93.9.0 — regenerate/re-copy after upgrading gstack +# gstack digest v1.93.10.0 — regenerate/re-copy after upgrading gstack Behavioral rules from gstack (https://github.com/garrytan/gstack), compressed for agent hosts without a full skill install. The full skills add workflows, diff --git a/bin/gstack-eval-plan b/bin/gstack-eval-plan index 8a52cc109..4826b83e0 100755 --- a/bin/gstack-eval-plan +++ b/bin/gstack-eval-plan @@ -5,7 +5,7 @@ * gstack-eval-plan prereg --check [--allow-repo-commands] [--json] | --init [--title ] * gstack-eval-plan arms [--arms ] [--policy-doc ] [--input-tokens N] [--output-tokens N] [--json] * gstack-eval-plan dry-run --input --arms [--fields a,b] [--output-budget N] - * [--retry-prompt ] [--max-rows N] [--out ] [--json] + * [--retry-prompt ] [--max-rows N] [--tier-question ] [--out ] [--json] * gstack-eval-plan pilot start --out --cap --arms --dry-run [--n 3] [--seat-metered ] * gstack-eval-plan pilot settle --out --attempt --usd * gstack-eval-plan pilot release --out --attempt @@ -50,9 +50,11 @@ const HELP = `gstack-eval-plan — preregistration, priced arms, $0 dry run, pri prereg --init [--title ] write the template arms [--arms m,m] [--policy-doc f] [--input-tokens N] [--output-tokens N] [--json] arms from \`gstack-models resolve --role eval-arms\`, else the repo policy doc, each priced per item - dry-run --input rows.jsonl --arms m,m [--fields a,b] [--output-budget N] [--retry-prompt f] [--max-rows N] [--cap usd] [--out dir] [--json] + dry-run --input rows.jsonl --arms m,m [--fields a,b] [--output-budget N] [--retry-prompt f] [--max-rows N] [--cap usd] [--tier-question ""] [--out dir] [--json] stub model over the real rows; checklist: price table, output budget, retry prompt text, - and with --cap reservation-fits-cap (one call: largest row + output budget, priced) + and with --cap reservation-fits-cap (one call: largest row + output budget, priced); + frontier: refuses a plan whose every arm is Haiku or Sonnet unless --tier-question + names what it asks about that tier, and re-costs the plan on frontier prices (R54) pilot start --out dir --cap usd --arms m,m#no-gstack --dry-run dry-run.json [--n 3] [--seat-metered arm,...] --seat-metered: arms on a subscription with no incremental charge; they reserve $0, settle unknown, and sit outside the cap and the projection until one settles a charge @@ -165,13 +167,15 @@ function doDryRun(rest: string[]): number { if (!arms.length) return usage('dry-run needs --arms '); const scope = scopeOf(rest); const modelRules = lintModels(rest, arms.map(model => ({ model, scope, where: 'dry-run --arms' })), 'dry-run'); - const r = dryRun({ input, arms, fields: csv(flag(rest, '--fields')), outputBudget: num(rest, '--output-budget'), retryPrompt: flag(rest, '--retry-prompt'), maxRows: num(rest, '--max-rows'), cap: num(rest, '--cap'), modelRules }); + const tierQuestion = flag(rest, '--tier-question'); + if (tierQuestion?.startsWith('--')) return usage('--tier-question needs the question the preregistration asks about that tier, not another flag'); + const r = dryRun({ input, arms, fields: csv(flag(rest, '--fields')), outputBudget: num(rest, '--output-budget'), retryPrompt: flag(rest, '--retry-prompt'), maxRows: num(rest, '--max-rows'), cap: num(rest, '--cap'), modelRules, tierQuestion }); const out = flag(rest, '--out'); if (out) { fs.mkdirSync(out, { recursive: true }); fs.writeFileSync(path.join(out, 'dry-run.json'), JSON.stringify(r, null, 2) + '\n'); } if (rest.includes('--json')) process.stdout.write(JSON.stringify(r) + '\n'); else process.stdout.write(renderDryRun(r)); if (out) process.stdout.write(`DRY_RUN_RECORD: ${path.join(out, 'dry-run.json')}\n`); if (!r.pass) { - const why = [r.rows === 0 ? 'no rows' : '', r.bad_rows.length ? `${r.bad_rows.length} bad rows` : '', !r.checks.price_table.ok ? `price missing: ${r.checks.price_table.missing.join(',') || 'no arms'}` : '', !r.checks.output_budget.ok ? 'output budget below the reasoning floor' : '', !r.checks.retry_prompt.ok ? 'retry prompt missing' : '', r.checks.reservation_fits_cap && !r.checks.reservation_fits_cap.ok ? `one call exceeds --cap $${r.checks.reservation_fits_cap.cap}` : '', r.checks.model_rules && !r.checks.model_rules.ok ? 'model rules refused an arm (EVAL_MODEL lines above)' : ''].filter(Boolean).join('; '); + const why = [r.rows === 0 ? 'no rows' : '', r.bad_rows.length ? `${r.bad_rows.length} bad rows` : '', !r.checks.price_table.ok ? `price missing: ${r.checks.price_table.missing.join(',') || 'no arms'}` : '', !r.checks.output_budget.ok ? 'output budget below the reasoning floor' : '', !r.checks.retry_prompt.ok ? 'retry prompt missing' : '', r.checks.reservation_fits_cap && !r.checks.reservation_fits_cap.ok ? `one call exceeds --cap $${r.checks.reservation_fits_cap.cap}` : '', r.checks.model_rules && !r.checks.model_rules.ok ? 'model rules refused an arm (EVAL_MODEL lines above)' : '', !r.checks.frontier.ok ? 'every arm is Haiku or Sonnet (R54; CHECK: frontier above)' : ''].filter(Boolean).join('; '); process.stderr.write(resultLine('gstack-eval-plan dry-run', r.checks.price_table.ok ? 'EVAL_DRY_RUN_FAILED' : 'EVAL_PRICE_MISSING', why) + '\n'); return EXIT.fail; } diff --git a/bin/gstack-flaky b/bin/gstack-flaky index 40239d156..6baf43ed4 100755 --- a/bin/gstack-flaky +++ b/bin/gstack-flaky @@ -9,11 +9,13 @@ import * as fs from 'fs'; import { DEFAULT_MAX_RERUNS, appendLedger, ledgerPath, renderResult, runFlaky, safeText, stepSummary, workflowEscape } from '../lib/flaky-run'; import { JunitError, readJunit, type JunitRunner } from '../lib/junit'; +import { liveQuarantine, QuarantineError, quarantineMain, readRegistry } from '../lib/quarantine'; const USAGE = `Usage: gstack-flaky run --junit [--runner playwright|bun|generic] [--max-reruns ] - [--rerun-scope command|test] [--ledger ] -- + [--rerun-scope command|test] [--ledger ] [--base ] -- gstack-flaky ids --junit [--runner playwright|bun|generic] + gstack-flaky quarantine add|renew|release|check|report ... (gstack-flaky quarantine --help) gstack-flaky --help run: runs the command (an argv, no shell), reads the JUnit report it writes at @@ -31,11 +33,18 @@ holds the first run's report afterwards; reruns' reports sit beside it as .rerun-.xml. The command runs with PLAYWRIGHT_JUNIT_INCLUDE_RETRIES=1 so Playwright's own retries are reported. +Quarantine: tests listed in .gstack/quarantine.json (read from --base when +given, so PR CI passes its target branch) still run and never count as passes. +When every test an attempt failed is a live quarantined test, the whole command +may run again, up to 3 attempts; the run is green only on an attempt with the +runner's full green verdict, and a quarantined test that fails all 3 is a hard +break (red). A quarantined id missing from a run that included its file is red. + ids: prints the id of every test in a report (::::). Output: one FLAKY: line per test that failed at least once, FLAKY_RERUN: scope=command (<why>) when the rerun repeated the whole command, then -FLAKY_RESULT: tests=<n> failed=<n> flaky=<n> reruns=<n> command_exit=<n> verdict=pass|fail ledger=<file|none> +FLAKY_RESULT: tests=<n> failed=<n> flaky=<n> quarantined=<n> reruns=<n> command_exit=<n> verdict=pass|fail ledger=<file|none> Exit: 0 pass (flaky passes included), 1 a test failed, 2 usage, 3 no usable report, a crash or a killed runner (FLAKY_<CODE> and a fix: line on stderr). `; @@ -48,6 +57,10 @@ const FIX: Record<string, string> = { FLAKY_COMMAND_KILLED: 'the runner was killed by a signal (a cancelled job, an OOM kill); nothing was rerun, rerun the job', FLAKY_COMMAND_NOT_STARTED: 'check the command after -- (it runs without a shell; wrap it as bash -c \'<script> "$@"\' _ when it needs one)', FLAKY_UNREPORTED_FAILURES: 'the runner counted failures its JUnit omits (a test file that failed to load, an error outside any test); fix that first, it is a real red', + FLAKY_QUARANTINE_INVALID: 'fix .gstack/quarantine.json: it must be {"schema":1,"entries":{...},"released":[...]} (gstack-flaky quarantine check names the problem)', + FLAKY_QUARANTINE_BASE: 'the base branch is not in this clone: fetch it before the run (in Actions, actions/checkout with fetch-depth: 0) and pass it as --base origin/<branch>', + FLAKY_QUARANTINE_REFUSED: 'read the reason above; docs/flaky.md#quarantine lists the rules', + FLAKY_QUARANTINE_USAGE: 'gstack-flaky quarantine --help', }; function die(msg: string, code = 2): never { @@ -60,8 +73,13 @@ function coded(e: JunitError): never { process.exit(3); } +function quarantineFailed(e: QuarantineError): never { + process.stderr.write(`gstack-flaky: ${e.message} (${e.code})\nfix: ${FIX[e.code] ?? 'see docs/flaky.md#quarantine'}\n`); + process.exit(e.exitCode); +} + function parse(argv: string[]) { - const o: { junit?: string; runner?: JunitRunner; maxReruns: number; rerunScope: 'command' | 'test'; ledger?: string; command: string[] } = { maxReruns: DEFAULT_MAX_RERUNS, rerunScope: 'command', command: [] }; + const o: { junit?: string; runner?: JunitRunner; maxReruns: number; rerunScope: 'command' | 'test'; ledger?: string; base?: string; command: string[] } = { maxReruns: DEFAULT_MAX_RERUNS, rerunScope: 'command', command: [] }; for (let i = 0; i < argv.length; i++) { const a = argv[i]!; const val = () => { const v = argv[++i]; if (v === undefined) die(`${a} needs a value`); return v; }; @@ -80,6 +98,7 @@ function parse(argv: string[]) { if (v !== 'command' && v !== 'test') die(`--rerun-scope must be command or test, got ${JSON.stringify(v)}`); o.rerunScope = v; } else if (a === '--ledger') o.ledger = val(); + else if (a === '--base') o.base = val(); else die(`unknown option ${a}\n${USAGE}`); } return o; @@ -88,6 +107,16 @@ function parse(argv: string[]) { const [sub, ...rest] = process.argv.slice(2); if (!sub || sub === '--help' || sub === '-h') { process.stdout.write(USAGE); process.exit(sub ? 0 : 2); } +if (sub === 'quarantine') { + try { + process.exit(quarantineMain(rest, { cwd: process.cwd(), out: s => process.stdout.write(s), now: new Date() })); + } catch (e) { + if (e instanceof QuarantineError) quarantineFailed(e); + if (e instanceof JunitError) coded(e); + throw e; + } +} + if (sub === 'ids') { const o = parse(rest); if (!o.junit) die('ids needs --junit <file>'); @@ -107,9 +136,15 @@ try { existing = fs.statSync(o.junit, { throwIfNoEntry: false }) && fs.readFileS } if (existing && existing.trim() && !/<testsuites?[\s>/]/.test(existing)) die(`--junit ${JSON.stringify(o.junit)} exists and is not a JUnit report; gstack-flaky deletes that path before every attempt, so it refuses to touch it`); if (!o.command.length) die('run needs the test command after --'); +let quarantined: Set<string>; +try { + const live = liveQuarantine(readRegistry(process.cwd(), o.base), new Date()); + for (const n of live.notices) process.stdout.write(`${n}\n`); + quarantined = live.ids; +} catch (e) { if (e instanceof QuarantineError) quarantineFailed(e); throw e; } let result; try { - result = await runFlaky({ command: o.command, junit: o.junit, runner: o.runner, maxReruns: o.maxReruns, rerunScope: o.rerunScope }); + result = await runFlaky({ command: o.command, junit: o.junit, runner: o.runner, maxReruns: o.maxReruns, rerunScope: o.rerunScope, quarantined }); } catch (e) { if (e instanceof JunitError) coded(e); throw e; } const ledger = ledgerPath(o.ledger); appendLedger(result.ledger, ledger, s => process.stderr.write(`gstack-flaky: ${s}\n`)); @@ -118,6 +153,7 @@ const summary = process.env.GITHUB_STEP_SUMMARY && stepSummary(result); if (summary) { try { fs.appendFileSync(process.env.GITHUB_STEP_SUMMARY!, summary); } catch { /* a summary is a convenience, never the verdict */ } } if (process.env.GITHUB_ACTIONS === 'true') { for (const f of result.outcomes.filter(x => x.status === 'flaky-pass')) process.stdout.write(`::warning title=flaky test::${workflowEscape(safeText(f.test.id))} passed on attempt ${f.attempts.length}\n`); + for (const f of result.outcomes.filter(x => x.status === 'hard-break')) process.stdout.write(`::error title=quarantined test hard break::${workflowEscape(safeText(f.test.id))} failed all ${f.attempts.length} attempts\n`); } if (result.code) { process.stderr.write(`gstack-flaky: ${result.message} (${result.code})\nfix: ${FIX[result.code] ?? 'see docs/flaky.md'}\n`); diff --git a/captain/templates/automation-flaky-pass.md b/captain/templates/automation-flaky-pass.md index c51b78944..7afbd5f26 100644 --- a/captain/templates/automation-flaky-pass.md +++ b/captain/templates/automation-flaky-pass.md @@ -16,6 +16,13 @@ ledger's Open section: in-run rerun turned green (date, case, tier, PR and head, failing attempt, passing attempt, one-line symptom from the failure log). 2. The free suites' retried cases in the same window, from the runners' retry output. +3. For repositories that run `gstack-flaky`: download the window's `flaky-junit-ledger-*` + artifacts (`gh run download <run-id> --pattern 'flaky-junit-ledger-*' --dir ledgers/<run-id>`) + and run `gstack-flaky quarantine report --ledger ledgers`. Fix its expired and EXPIRING + entries first: fix the test, or renew once with new evidence and the owner named, never + a second time. Release each READY_TO_RELEASE entry with + `gstack-flaky quarantine release <id> --reason <why> --pr <url>` in a PR of its own. + A hard-break line is a real red, not a flake: fix it like any failing test. Never add a case that failed twice (that is a real failure, not a flake), and never a harness, infra or incomplete red. Then group the Open section by case, worst repeat @@ -33,5 +40,5 @@ spend of every paid run you made. ``` What it reads: the ledger, the gate runs' flake-records artifacts, the free suites' -retry output, the crew rules file. What it starts: one fix PR per cause, each READY'd to +retry output, the `gstack-flaky` ledgers and quarantine report, the crew rules file. What it starts: one fix PR per cause, each READY'd to the controller. What it never does: rerun a gate, change a threshold, or merge. diff --git a/docs/TESTING_INTERNALS.md b/docs/TESTING_INTERNALS.md index 441525762..bc3451c68 100644 --- a/docs/TESTING_INTERNALS.md +++ b/docs/TESTING_INTERNALS.md @@ -651,15 +651,37 @@ this checkout to read it)`. samples, rationale}` entry per failing dimension (since EVAL_POLICY v3 `mean` holds the panel's gating median), each part capped at 200 characters. `sessions[]` (at most 32) summarizes the trial's session-ledger -rows. `cost_known: false` marks a record or trial whose harness captured no -billing: PTY and Codex sessions never bill, and an SDK session bills only with a -terminal `total_cost_usd`. It also marks a trial no result record could be -attributed to: a record named by the case id or carrying `case_id` is that -case's, and a record named by a display label (`/qa fix loop`) is the shard's -only case's when the shard ran one case, so a multi-case shard whose records -carry display labels leaves those trials cost-unknown rather than guessing -which case paid (`junitCensus` in `scripts/lib/paid-report.ts`). An absent -field means known. Census and marathon cost lines print the known sum and +rows. `cost_known: false` marks a record or trial whose cost is not fully +known; an absent field means known. A record carries it when its harness +captured no billing (a Codex session that completed no turn or whose model has +no price row). A rule case's trial in the JUnit census (`caseCost` in +`scripts/lib/paid-report.ts`) costs its records' sum plus what no record +carries: each ledger session without a terminal result (`billed: false`) adds +its `streamed_cost_usd`, and a trial with no record adds each billed session's +own `cost_usd` (Codex). The trial is cost-unknown when any record says +`cost_known: false`, when any of those sessions has no priced cost (a PTY +session whose transcript does not price, a `claude -p` session that ended +without a result, an aborted Agent SDK session with no usage or an unpriced +model), or when it has neither records +nor sessions. A case in `MODEL_FREE_CASES` (`timeline-event-flow`, which runs +no model) with neither is a known $0. A panel trial (`behavior`, `judge`) from +an isolated trial shard keeps the older rule (`trialCostKnown` in +`test/helpers/eval-store.ts`): known only with at least one record and every +session billed, and streamed cost is not added. + +Records are attributed to a case this way: a record named by the case id or +carrying `case_id` is that case's, and a record named by a display label +(`/qa fix loop`) is the shard's only case's when the shard ran one case. In a +multi-case shard, a display-label record whose `runSkillTest` test name is a +registered case id carries `cost_case_id` (`recordE2E`), and the census adds +its cost to that case only: the failed record, failure class and model still +come from the records named by case id, so no verdict changes. A display-label +record without `cost_case_id` in a multi-case shard is not attributed rather +than guessed, and its case is cost-unknown when nothing else prices it +(`junitCensus`). The report's headline `cost $<x>` adds the streamed session +cost no collector record carries, so a newly priced trial counts once. + +Census and marathon cost lines print the known sum and `N of M trial(s) cost unknown`, and a train verdict's `ATTEMPT:` line prints `cost=$<known> known + <n> of <m> case(s) cost unknown` when some but not every case in the train record has a cost (a record with no priced case prints @@ -671,13 +693,33 @@ including `runSharedInteractive`, the PTY session and `runRecordedCodexEval`) appends one best-effort line per armed session to `$GSTACK_EVAL_DIR/session-ledger.jsonl` (`test/helpers/session-ledger.ts`): a stable key `<runner>:<label>#n`, the exact `budget_ms` it armed, monotonic -`elapsed_ms`, the `end` reason, sanitized evidence, `billed`, and a compact +`elapsed_ms`, the `end` reason, sanitized evidence, `billed`, the billed +`model`, `cost_usd` and token classes of a Codex session, and a compact liveness summary (longest in-request silence, the last event kind, any tool open at the end). `claude -p` sessions stream partial messages for this summary; transcripts keep their shape and size (full stream diagnostics only with `publicStreamDiagnostics`). A failed ledger write never fails a trial; a trial without ledger rows has no `sessions` and its headroom is `unknown`, never -scored. The ledger rides in each slice artifact beside the shard results. +scored. An Agent SDK session that ends without a terminal result (aborted, +thrown) also records `streamed_cost_usd`: its streamed assistant usage priced +by `streamedUsageCostUsd` (`lib/pricing.ts`), each message id once at its +largest output, subagent turns included, `<synthetic>` messages skipped, +5-minute cache writes at 1.25x and 1-hour writes at 2x the input rate. The +field is absent when no message carries usage or any message's model has no +price row, so an unpriced session stays cost-unknown, never $0. A PTY session +records `streamed_cost_usd` from its transcript the same way. Both PTY ledger +writers price `<CLAUDE_CONFIG_DIR>/projects/*/<id>.jsonl` plus +`<id>/subagents/*.jsonl` (`test/helpers/pty/transcript-cost.ts`), where the +id is the caller's `--session-id`, else the one transcript that appeared +during this launch for its cwd. The launcher adds no argument. Pricing never +takes the whole directory, because concurrent PTY tests in one process share +one hermetic config dir; two new transcripts for one cwd are ambiguous and stay +unknown. A non-hermetic or resumed launch, a caller that opts out +(`priceTranscript: false`, the native AskUserQuestion capture, which never +reads model transcripts), a missing transcript, no usage, an unpriced model or +a read error leaves the field absent (cost-unknown), and a pricing failure +never fails the test. The row keeps `billed: false`. The ledger rides in each slice +artifact beside the shard results. **Quarantine** (`CASE_QUARANTINE`, same file). An entry needs: a per-trial rate below 95% over at least 10 post-policy trials of the case's current input @@ -1232,9 +1274,11 @@ observation never removes a command and a missing or empty artifact never erases one; removing a command is a reviewed edit. While the map is in shadow mode it changes no selection, so a PR that changes only the map selects no paid case. -Dollar figures are lower bounds. Known cost excludes PTY trials, whose cost is -unknown: about 39% of observed case runs in the committed map. The shadow block -and `test:health` both say so. +Dollar figures are lower bounds. Known cost excludes trials whose cost is +unknown: about 39% of observed case runs in the committed map, mostly PTY +trials recorded before PTY sessions were priced from their transcripts +([Failure causes and details](#failure-causes)). The shadow block and +`test:health` both say so. - **Shadow block:** `prCoverage.shadow` in the paid-plan manifest lists the gate cases the map would select, would drop and would add, a provenance line per @@ -1750,6 +1794,32 @@ lower-case words in path components under `test/fixtures/`; a substring match separate change with its own touchfile updates; the list is here so that change can be scoped. +## Agent SDK system prompt + +An Agent SDK caller that leaves out `systemPrompt` doesn't get Claude Code's +prompt. It gets the SDK's bare stub, and the stub drops the line that tells the +model to run `/skill` through the Skill tool. A skill arm then never loads its +skill, so a "no difference" result says nothing about the skill (FOUN-32 found +this in another crew's null result). + +**Every caller says which prompt it uses.** `runAgentSdkTest` and every direct +SDK `query()` call pass the Claude Code preset, +`{ type: 'preset', preset: 'claude_code' }` (also exported as +`CLAUDE_CODE_PRESET` from `test/helpers/sdk-system-prompt.ts`; an overlay arm +adds `append`), or name why not: `{ type: 'sdk-default', reason }` for a stub +provider or a connectivity probe, `{ type: 'custom', text, reason }` for an arm +that replaces the prompt. The runner refuses a missing, empty, bare-string or +unnamed prompt before it starts, and +`test/sdk-system-prompt-tripwire.test.ts` scans test/ and scripts/ for the same +mistake in free CI. Arms that compare loadouts, the no-gstack arm included, +keep the same preset and differ only in what the arm loads. + +**Record it, and treat a null on the stub as a method bug.** Every eval report +and results table names the prompt each arm ran under (`claude_code`, +`claude_code + append`, or the named reason). A null or negative result from an +arm that ran on the SDK default is FIX-METHOD under R48 ("Why null?"): fix the +prompt and rerun before reading it as KEEP or CUT-CANDIDATE. + ## No-gstack arm Garry, 2026-10-31: "all of our head to head tests have to test no gstack from @@ -1843,6 +1913,36 @@ it as the diagnostic. Candidate folders and git identity name a project, never the arm. The model panel (`test/skill-e2e-model-panel.test.ts`) runs a `<model>#no-gstack` arm beside each model (GST-468, GST-469). +## Frontier models under test + +Garry, 2026-11-01 (R54): "I think you are spending too much time with Haiku and +Sonnet, whereas GBrain and GStack are really designed to be used with frontier +models like Opus and 6.1 Sol... just transfer from Haiku to Sonnet, who gives a +shit about that, man?" + +**Models under test are frontier models.** Today that's `claude-opus-5-5` and +`gpt-6.1-sol`, plus at most one low-cost primary the preregistration names. Haiku +and Sonnet are not models under test. They aren't stand-ins for a frontier model, +and an eval has no tier-transfer arms (Haiku against Sonnet, say) unless its +preregistration says it is asking about that tier. + +**Verdicts need a frontier result.** A result measured only on Haiku or Sonnet +can't carry a KEEP, FIX-METHOD or CUT-CANDIDATE verdict under R48. Rerun it on a +frontier model first. + +**What the rule leaves alone.** Judges, cross-family review voices and a +harness's shipped housekeeping model aren't models under test, so they keep the +model they already use. + +**The check.** `gstack-eval-plan dry-run` prints `CHECK: frontier` whenever an arm +is Haiku or Sonnet. When every arm is one, the dry run fails unless +`--tier-question "<what the preregistration asks about that tier>"` is passed. +When only some arms are, it warns. Either way it prints the whole plan's price +on `claude-opus-5-5` and `gpt-6.1-sol`. The dry run doesn't enforce that number: +compare it with the brief cap before any arm is swapped. `pilot start` refuses a +pilot whose every arm is Haiku or Sonnet unless its dry run recorded a tier +question. + ## Running evals as an agent: detach Moved verbatim from CLAUDE.md (#2096 size limit). The short rule stays in diff --git a/docs/captain.md b/docs/captain.md index cdc83da98..b09778c50 100644 --- a/docs/captain.md +++ b/docs/captain.md @@ -434,7 +434,9 @@ A scheduled automation starts one lane a day with the runs' flake-records artifacts and the free suites' retried cases, writes one ledger line per event, groups by case, and fixes the worst repeat first with a PR that shows the failure red before green. It never reruns a gate and never touches a threshold, trial -count or case kind. On Capy, create it with the automation tool, scheduled in the owner's +count or case kind. Where a repository runs `gstack-flaky`, the lane also reads +`gstack-flaky quarantine report --ledger <downloaded ledgers>` and fixes expiring quarantine +entries before anything else ([flaky.md](flaky.md#the-daily-flaky-pass)). On Capy, create it with the automation tool, scheduled in the owner's timezone, running as a thread in the crew so its report lands in `reports/`. The lane's side of the same rule: in CI the gate reruns a case that failed on its own diff --git a/docs/evals/census-red.md b/docs/evals/census-red.md index f3503b625..e3bb69991 100644 --- a/docs/evals/census-red.md +++ b/docs/evals/census-red.md @@ -93,7 +93,7 @@ What incomplete data means: | headroom `censored` | a sample timed out, so its real duration is at least the budget | | cause `unrecorded` | the trial was written before `failure_cause` existed | | cause `unknown` | the trial failed with no evidence for any other cause | -| `cost unknown` | the harness (PTY, Codex) records no billing, or the trial sits in a multi-case shard whose records are named by display label and cannot be attributed to it; only the known sum is shown | +| `cost unknown` | a session's cost was not captured (a PTY session without a priced transcript, an unbilled Codex session, a `claude -p` session without a result, an aborted Agent SDK session with no priced streamed usage), or no record or session can be attributed to the trial (a multi-case shard's display-label record without `cost_case_id`); only the known sum is shown | | `history unavailable (...)` | the GitHub history could not be read; `--gate` fails closed | ## 4. Replay and repair (free) diff --git a/docs/flaky.md b/docs/flaky.md index 1a56b798e..eeea3e8ab 100644 --- a/docs/flaky.md +++ b/docs/flaky.md @@ -6,7 +6,9 @@ rerun is a **flaky pass**: the job stays green and the flake is recorded on a le the daily flaky pass can fix it at the source. A test that fails twice is red. This is CREW rule 16 ("run the failed test again and note that it is flaky") for any runner that writes JUnit: Playwright, `bun test`, jest, vitest and -pytest. gstack's own free suite keeps its file-level retry +pytest. A test that keeps flaking while it is fixed can be +[quarantined](#quarantine): it still runs, with up to 3 attempts, and never counts +as a pass. gstack's own free suite keeps its file-level retry (`GSTACK_FREE_RETRY_FLAKY`, [Flake ledger](TESTING_INTERNALS.md#flake-ledger)). ## Get started in GitHub Actions @@ -74,6 +76,104 @@ It cannot see a coverage threshold configured without console output (for example `coverageReporter = ["lcov"]` in `bunfig.toml`), which is why this scope is opt-in. +## Quarantine + +A test that keeps flaking while someone fixes it can be **quarantined** in +`.gstack/quarantine.json` at the repository root. Quarantine is a larger +attempt budget, never a skip: the test still runs on every run, is listed as +quarantined in the output, and never counts as a pass. + +**How a quarantined test is judged.** The verdict rule from +[Rerun scope](#rerun-scope) does not change: an attempt counts only when the +runner itself reports a full green run. When every test an attempt failed is a +live quarantined test, and nothing else is wrong with that attempt (no kill, no +failure outside the report, no first-run test missing), the whole command may +run again, up to 3 attempts in total. The run is green only when one of those +attempts is fully green. A quarantined test that fails all 3 is a **hard +break**, and the run is red. A test that is not quarantined keeps its one +rerun. A red attempt never turns green because its only reported failure is a +quarantined test, because the runner's exit status can come from things the +report does not show (a coverage threshold, a fail-on-flaky policy, a global +setup). With `--rerun-scope test` the quarantined test gets the same 3 +attempts on the targeted path, with the same fallback to the whole command. +When the runner retries on its own (Playwright `retries`), its attempts are +the budget and nothing is rerun again. + +**Missing results.** A quarantined id missing from a run that included its +file (and, for Playwright, its project) is red. A run that did not include the +file, such as a shard or a diff selection, is not. + +**Read from the base branch.** `run --base <ref>` reads the registry from +that commit instead of the working tree. Pull-request CI passes its target +branch, so a change cannot quarantine the test it breaks. `check --base` +compares against the merge base, so check out full history for it: + +```yaml +- uses: actions/checkout@v4 + with: { fetch-depth: 0 } +- name: Quarantine registry + run: '"$RUNNER_TEMP/gstack/bin/gstack-flaky" quarantine check --base "origin/${{ github.base_ref }}"' +- name: E2E + run: | + "$RUNNER_TEMP/gstack/bin/gstack-flaky" run --base "origin/${{ github.base_ref }}" --junit results/junit.xml -- npx playwright test --reporter=line,junit +``` + +### Commands + +| Command | What it does | +|---|---| +| `gstack-flaky quarantine add <id> --owner <who> --ledger <url> --class <class> --reason <text> --evidence <url>… --junit <file> [--days <n>]` | Adds an entry that expires in `--days` (default 7, at most 14). `--junit` counts the suite for the cap and confirms the id exists; `gstack-flaky ids` prints the ids. | +| `gstack-flaky quarantine renew <id> --owner <who> --evidence <url> [--days <n>]` | One renewal of up to 7 days from the later of now and the current expiry, with evidence not already on the entry and the owner named again. A second renewal is refused. | +| `gstack-flaky quarantine release <id> --reason <text> --pr <url>` | Moves the entry to `released` with the date, the reason and the PR. | +| `gstack-flaky quarantine check [--base <ref>] [--junit <file>]` | Validates every entry and the cap; with `--base`, also what this change did since the merge base. Exits 1 with one `QUARANTINE_REFUSED:` line per problem. | +| `gstack-flaky quarantine report [--ledger <file\|dir>…] [--base <ref>]` | Lists expired entries, then live entries soonest-expiring first with days left. With downloaded ledgers it adds recent outcomes and marks entries with 10 consecutive clean passes `READY_TO_RELEASE`; without `--ledger` it says the exit rule was not checked. | + +### Rules + +- **Every entry is owned and expires.** An entry holds `owner`, `ledger` + (the ledger line or issue tracking the fix), `failureClass`, `reason`, + `evidence`, `enteredAt`, `expiresAt`, `renewals` and `suiteTests` (the + suite size `add` counted). It lasts 7 days by default and at most 14 from + entry, plus one renewal of at most 7 days. +- **Expired means not quarantined.** An expired entry stops applying without + an edit: `run` treats the test as an ordinary test and prints + `FLAKY_QUARANTINE_EXPIRED` with the renew and release commands. An entry + that breaks a rule (for example one that lasts 30 days) is ignored the same + way, with `FLAKY_QUARANTINE_IGNORED`. +- **Cap.** Live entries are capped at 10% of the suite's tests, at least 1, + and 5 for a suite under 50 tests. `add` refuses past the cap; `check` + enforces it against `--junit` when given, else against the smallest + `suiteTests` on a live entry. +- **Classes.** `detector`, `harness`, `timing` and `model-latency`. + `product` is refused (a product defect is fixed, not quarantined), and so is + `infra` (an infrastructure red is rerun or fixed as infrastructure). +- **`check --base` refuses** an entry added in the same change that edits its + test's file, an entry that disappears without a release record, a release + record that was removed, and a changed `enteredAt` or rewritten renewal + history. +- **Exit rule.** 10 consecutive clean passes (`quarantined-pass` with no + failed attempt) on the ledgers since the entry was added. Release the entry + with the fix PR. +- **Separate from `CASE_QUARANTINE`.** gstack's own paid-eval quarantine + (`CASE_QUARANTINE` and `EVAL_POLICY`, + [TESTING_INTERNALS.md](TESTING_INTERNALS.md)) is a different registry with + its own rules for eval cases. The two share no schema, and `gstack-flaky` + neither reads nor writes it. + +### The daily flaky pass + +Download the ledger artifacts of the last week's runs and read them with +`report`; fix expired and `EXPIRING` entries first (fix the test, or renew +once with new evidence), release `READY_TO_RELEASE` entries, then fix the +worst repeat on the ledger: + +```bash +for id in $(gh run list --workflow e2e.yml --limit 50 --json databaseId -q '.[].databaseId'); do + gh run download "$id" --pattern 'flaky-junit-ledger-*' --dir "ledgers/$id" || true +done +gstack-flaky quarantine report --ledger ledgers +``` + ## Rules - **One rerun, small failures only.** A failed test gets one rerun when the @@ -101,8 +201,9 @@ scope is opt-in. - **Ids.** A test is `<file>::<project>::<describe > title>`, with the project empty outside Playwright, so a test in two browser projects is two tests. `gstack-flaky ids --junit <file>` prints them. -- **Ledger.** One JSON line per flaky pass (`kind: flaky-pass`) and per test - that failed its rerun (`rerun-fail`), with the tree, commit, branch, run URL, +- **Ledger.** One JSON line per flaky pass (`kind: flaky-pass`), per test + that failed its rerun (`rerun-fail`) and per quarantined test on every run + (`quarantined-pass`, `quarantined-fail`, `hard-break`), with the tree, commit, branch, run URL, attempts, the rerun's scope (`test` or `command`) and the first lines of the error. Ids, paths and failure text go through gstack's redaction engine first; when the scan cannot run, they are withheld. The path is `--ledger`, @@ -113,15 +214,17 @@ scope is opt-in. ## Output and exit codes -One `FLAKY: <flaky-pass|fail|rerun-fail> <id> attempts=<…> (<reason>)` line per -test that failed at least once, `FLAKY_RERUN: scope=command (<why>)` when the -rerun repeated the whole command, then -`FLAKY_RESULT: tests=<n> failed=<n> flaky=<n> reruns=<n> command_exit=<n> verdict=pass|fail ledger=<file|none>`. +One `FLAKY: <flaky-pass|fail|rerun-fail|quarantined-pass|quarantined-fail|hard-break> <id> attempts=<…> (<reason>)` +line per test that failed at least once and per quarantined test, +`FLAKY_RERUN: scope=command (<why>)` when the rerun repeated the whole command, then +`FLAKY_RESULT: tests=<n> failed=<n> flaky=<n> quarantined=<n> reruns=<n> command_exit=<n> verdict=pass|fail ledger=<file|none>`. +`failed` counts every outcome but `flaky-pass` and `quarantined-pass`; `quarantined` +counts the quarantined tests' outcomes, which are never counted as passes. | Exit | Meaning | |---|---| | 0 | Every test passed, flaky passes included | -| 1 | A test failed (after its rerun, or with no rerun), including `FLAKY_UNREPORTED_FAILURES` | +| 1 | A test failed (after its rerun, or with no rerun), including `FLAKY_UNREPORTED_FAILURES`, a quarantined test's hard break or missing result, and a refused `quarantine` command | | 2 | Usage error, including a `--junit` path that is not a `.xml` file, or an existing file there that is not a readable JUnit report | | 3 | No usable report, a crash, or a killed runner (a code below on stderr) | @@ -135,3 +238,9 @@ rerun repeated the whole command, then | `FLAKY_COMMAND_NOT_STARTED` | 3 | The command could not be started | Check the argv after `--` | | `FLAKY_UNREPORTED_FAILURES` | 1 | The runner counted failures or errors its JUnit omits | Fix the load error or the error outside any test: a real red | | `FLAKY_LEDGER_WRITE_FAILED` | — | The ledger could not be appended (warning) | Check the path; the verdict stands | +| `FLAKY_QUARANTINE_INVALID` | 3 | `.gstack/quarantine.json` is not valid JSON or not a schema 1 registry | Fix the file; `quarantine check` names the problem | +| `FLAKY_QUARANTINE_BASE` | 3 | `--base` does not resolve to a commit (exit 2 for a value starting with `-`), or `check` finds no merge base | Fetch the base branch; `check --base` needs `fetch-depth: 0` | +| `FLAKY_QUARANTINE_REFUSED` | 1 | `add`, `renew` or `release` broke a rule | Read the reason; [Quarantine](#quarantine) lists the rules | +| `FLAKY_QUARANTINE_USAGE` | 2 | An unknown `quarantine` command or option, or a missing value | `gstack-flaky quarantine --help` | +| `FLAKY_QUARANTINE_EXPIRED` | — | Notice: an expired entry no longer applies | Fix the test, renew once, or release; the line prints both commands | +| `FLAKY_QUARANTINE_IGNORED` | — | Notice: an entry breaks a rule and does not apply | Fix the entry; `quarantine check` names the rule | diff --git a/docs/skills.md b/docs/skills.md index 3185d1822..d5315e262 100644 --- a/docs/skills.md +++ b/docs/skills.md @@ -961,7 +961,10 @@ arms, decoys, stop rules, cap) and `--check` refuses to continue while a field i blank (`PREREG_INCOMPLETE`). `arms` resolves the `eval-arms` model role against `lib/pricing.ts` and stops on an unpriced model (`EVAL_PRICE_MISSING`); `dry-run` runs every row through the stub model for $0 and flags malformed rows -(`EVAL_DRY_RUN_FAILED`); `pilot start|settle|release|report` runs three priced +(`EVAL_DRY_RUN_FAILED`), and refuses a plan whose every arm is Haiku or Sonnet +unless `--tier-question` names what it asks about that tier, re-costing it on +frontier models ([frontier models under test](TESTING_INTERNALS.md#frontier-models-under-test)); +`pilot start|settle|release|report` runs three priced items, records actual spend, extrapolates each priced arm to the full set against the cap (`EVAL_BUDGET_EXHAUSTED`) and prints the spend table the approval question shows. An arm on a subscription with no extra charge is declared with diff --git a/docs/standalone-binaries.md b/docs/standalone-binaries.md index 40074838d..8518318d6 100644 --- a/docs/standalone-binaries.md +++ b/docs/standalone-binaries.md @@ -19,7 +19,7 @@ Beyond the slash-command skills, gstack ships standalone CLIs for workflows that | `gstack-review-log` | **Review-pass receipts** — `--start <skill>` captures the working-tree fingerprint before a diff review; `'<JSON>' --finish <token>` consumes that single-use, repository/branch/skill-scoped receipt. Binding requires matching start/end content and reviewer-reported `completed:true` and `converged:true`; it is not independent proof that a model read the source. `--check-shared-libs <token>` reads a current finding as JSON on stdin and checks prior Skip decisions against the actual branch, capture and eligible raw source blobs. It returns `reusable:false` when proof is missing or unsafe, including older records without logger-versioned coverage. Final review logging computes shared-code fingerprints and coverage rather than trusting supplied proof. | | `gstack-review-read` | **Review freshness** — emits review records with computed `review_freshness.status` and `reason`: CURRENT, STALE, or UNVERIFIED for diff reviews. `/ship` and `/land-and-deploy` use the same grade; a matching commit alone never certifies a diff review. [Dashboard rules](skills.md#review-readiness-dashboard). | | `gstack-evidence` | **Verification-evidence ledger** — `run --label <lane> -- <cmd>` transparently wraps any test command (the child's exit code always passes through) and records what ran against which working-tree fingerprint (tracked and untracked files that are not gitignored, minus an untracked `.bun/` folder at the repo root, which Bun can create during a run); a run whose files changed while it ran is recorded without a fingerprint and with up to five of the changed paths, which `check` names in its STALE reason. `check` grades each label FRESH/STALE/MISSING with `--expect-cmd`, `--max-age`, and `--allow-paths` binding. /ship and /land-and-deploy cite fresh evidence instead of re-running suites. Per-run logs are 0600, capped at 2MB, pruned after 30 days; the ledger and logs stay machine-local by design. | -| `gstack-flaky` | **Flaky-test rerun for any JUnit runner** — `run --junit <file.xml> -- <command>` runs your test command (Playwright, `bun test`, jest, vitest, pytest) and, when at most `--max-reruns` (3) tests failed and the runner made no retries of its own, reruns the whole command once (`--rerun-scope test` opts in to rerunning only the failed tests). A test that fails and then passes on that rerun is a flaky pass: the run stays green and one redacted line per flaky pass or failed rerun goes on a ledger (`GSTACK_FLAKE_LEDGER_JUNIT`, default `<state root>/flake-ledger-junit.jsonl`). A missing or malformed report, a crash or a killed runner never passes. `ids --junit <file>` prints a report's test ids. Exit 0 pass, 1 a test failed, 2 usage, 3 no usable report. [Guide](flaky.md). | +| `gstack-flaky` | **Flaky-test rerun for any JUnit runner** — `run --junit <file.xml> -- <command>` runs your test command (Playwright, `bun test`, jest, vitest, pytest) and, when at most `--max-reruns` (3) tests failed and the runner made no retries of its own, reruns the whole command once (`--rerun-scope test` opts in to rerunning only the failed tests). A test that fails and then passes on that rerun is a flaky pass: the run stays green and one redacted line per flaky pass or failed rerun goes on a ledger (`GSTACK_FLAKE_LEDGER_JUNIT`, default `<state root>/flake-ledger-junit.jsonl`). A missing or malformed report, a crash or a killed runner never passes. `quarantine add|renew|release|check|report` keeps `.gstack/quarantine.json`: a quarantined test still runs, gets up to 3 attempts of the whole command, passes only on a full green attempt and is never counted as a pass (`run --base <ref>` reads the registry from the base branch). `ids --junit <file>` prints a report's test ids. Exit 0 pass, 1 a test failed, 2 usage, 3 no usable report. [Guide](flaky.md). | | `gstack-pr-wait` | **PR event watcher** — `gstack-pr-wait <pr> [--repo owner/name] [--until green\|ready\|any-change] [--interval 20] [--timeout 60] [--exclude CHECK,...]` polls one pull request through `gh` and prints one stdout line per real event (a check failed with its link, all checks finished, a comment or review from someone other than the author, a review bot finished on the head, the base moved and its new commits touch this PR's files, BEHIND or DIRTY, merged or closed), with progress on stderr, so a monitor wakes the agent once per event instead of on a timer. `green` gates on every check on the head (an advisory bot's review is never waited for, its checks gate like any other), as `gstack-ci-gate` does; a check the base branch requires (rulesets and classic branch protection) is pending until it appears, never green by omission; two identical polls confirm a check set is complete; `--exclude` leaves a named non-required check out of the verdict as `gstack-ci-gate --exclude` does (a required name is refused and gates). Exit 0 when the condition is met, 1 when it needs action or `--timeout` passes (`PR_WAIT_BLOCKED`), 2 on bad input, a second watcher for the same PR or a local error (`PR_WAIT_REFUSED`). State under `<state root>/pr-wait/`, baseline discarded after 6 hours. Review bots are configuration: `gstack-config set pr_wait_gating_bots greptile,macroscope`, `pr_wait_advisory_bots coderabbit` (advisory bots are reported, never waited on). `/land-and-deploy` Step 3 is one call of it. Design ported from tstack's pr-wait (MIT, Theo Browne; NOTICE.md). [Exit codes](troubleshooting.md#gstack-pr-wait). | | `gstack-issue-guard` | **Tracker-text trust envelope** — fetches GitHub issue/PR text (`issue <n>`, `pr-body`, `pr-comments`, or `--stdin`) and wraps it in a labeled envelope so agents treat it as data: injection-shaped lines get labeled even through fullwidth and invisible-character evasion, and forged envelope banners are defused. Every tracker-text ingress in gstack routes through it, enforced by a CI scanner. | | `gstack-ios-qa-daemon` | **iOS QA daemon** — Mac-side broker between an agent and a connected iPhone or iPad over USB CoreDevice. Loopback by default; `--tailnet` opens a Tailscale-facing listener with identity-gated capability tiers. Single-instance via flock on `~/.gstack/ios-qa-daemon.pid`. See [docs/howto-ios-testing-with-gstack.md](howto-ios-testing-with-gstack.md). | diff --git a/docs/support-tiers.md b/docs/support-tiers.md index e919aaf4d..05b01b4aa 100644 --- a/docs/support-tiers.md +++ b/docs/support-tiers.md @@ -10,7 +10,7 @@ gstack has two support tiers. Full support gets the whole test suite, paid evals ## Minimal support -- **Windows** (Git Bash or MSYS): with a default Git for Windows install, `./setup` installs, and the core skills start without errors. The core skills are `/ship`, `/review`, `/qa-only`, `/investigate` and `/browse` on gstack's own browser. Once the `windows-smoke` CI job lands, it checks this on every pull request (see Windows CI below). +- **Windows** (Git Bash or MSYS): with a default Git for Windows install, `./setup` installs, and the core skills start without errors. The core skills are `/ship`, `/review`, `/qa-only`, `/investigate` and `/browse` on gstack's own browser. One required CI job, `windows-smoke`, checks this on every pull request (see Windows CI below). - **Gemini models:** the core workflows run to the end without errors when Gemini is the host agent or a reviewer. We check this by hand or with one cheap smoke run, not with an eval cell. That is the whole promise. Other skills, optional parts such as `/cso`'s native helper, non-default shell settings and speed are not covered. @@ -23,8 +23,9 @@ That is the whole promise. Other skills, optional parts such as `/cso`'s native ## Windows CI -- **Today:** the six-shard Windows free suite (the `Windows Free Tests` workflow, `windows-free-tests`) runs on every pull request and every push to main, and it is a required check. -- **Once `windows-smoke` lands:** `windows-smoke` becomes the required Windows check on pull requests. The six-shard suite then runs nightly on main, or when someone starts it by hand, and never blocks a pull request. A red nightly run gets a fix only when it shows an install, startup or core-workflow break. +- `windows-smoke` is the required Windows check on pull requests. +- The six-shard Windows free suite (the `Windows Free Tests` workflow, `windows-free-tests`) runs nightly on main, or when someone starts it by hand, and never blocks a pull request. +- A red nightly run gets a fix only when it shows an install, startup or core-workflow break. ## What doesn't change diff --git a/docs/troubleshooting.md b/docs/troubleshooting.md index 473a6572a..e7db68e52 100644 --- a/docs/troubleshooting.md +++ b/docs/troubleshooting.md @@ -2592,12 +2592,24 @@ case with `bun run eval:pass-rates --headroom --case <id>`. <a id="cost-unknown"></a> ### `cost unknown (no billing captured for any of <N> trial(s))` / `cost $<x> known + <N> of <M> trial(s) cost unknown` -**Meaning.** PTY and Codex sessions record no billing, so their cost is -unknown. So is a trial in a multi-case shard whose result records are named by -a display label rather than the case id, because no record can be attributed -to it (a one-case shard's records are its case's). Only the known sum is -shown. A train verdict's `ATTEMPT:` line reports the same as `cost=$<x> known -+ <n> of <m> case(s) cost unknown`, a bare `cost=$<x>` only when every case +**Meaning.** Some trials' cost was not captured, so only the known sum is +shown. A trial is cost-unknown when it ran a PTY session whose transcript +could not be priced (a non-hermetic or resumed launch, the native +AskUserQuestion capture, two new transcripts for one cwd, no transcript or +usage, or a model with no price row), a +Codex session that completed no turn or whose model has no price row, a +`claude -p` session that ended without a result, or an aborted Agent SDK +session whose streamed usage could not be priced (no usage, or a model with no +price row). A PTY or aborted Agent SDK session that does price counts its +`streamed_cost_usd` instead. A trial is also unknown when no record and no +session can be attributed to it, for example a multi-case shard's +display-label record without `cost_case_id` (a one-case shard's records are +its case's); a model-free case (`timeline-event-flow`) is a known $0. A panel +trial (`behavior`, `judge`) is unknown whenever any of its sessions billed +nothing, even one with a priced `streamed_cost_usd`. The rules are in +[Failure causes and details](TESTING_INTERNALS.md#failure-causes). A train +verdict's `ATTEMPT:` line reports the same as `cost=$<x> known + <n> of <m> +case(s) cost unknown`, a bare `cost=$<x>` only when every case in the train record is priced, and no cost at all when none is. **Fix.** None needed; this is informational. diff --git a/eval-plan/SKILL.md b/eval-plan/SKILL.md index 8e82deb3f..fa6a0f479 100644 --- a/eval-plan/SKILL.md +++ b/eval-plan/SKILL.md @@ -185,6 +185,10 @@ page or drop the arm. Copy the priced arms into the Arms section. An arm identit `<model>#<loadout>` (for example `claude-opus-5-5#no-gstack`) is priced by its model and gets its own pilot attempts; naming one identity twice is `EVAL_ARM_DUPLICATE`. +Models under test are frontier models (`claude-opus-5-5`, `gpt-6.1-sol`, at most one named +low-cost primary); a Haiku or Sonnet arm only with a stated tier question +(docs/TESTING_INTERNALS.md#frontier-models-under-test). + When the repo commits `.gstack/eval-models.json` (allow, deny, per-scope lists, families newest first; `docs/eval-models.md` in gstack), `arms`, `dry-run`, `pilot start` and `price-gate` print one `EVAL_MODEL:` line per arm. Pass `--scope smoke` for a smoke run; @@ -239,6 +243,7 @@ the budget the run will use. The checklist printed must be all `ok`: with no text is a repeat of the same failure at the same price. - `CHECK: reservation-fits-cap` (with `--cap <cap-usd>`) — one call, the largest row plus the output budget, priced, fits under the cap; a provider refuses a reservation the cap cannot hold. +- `CHECK: frontier` — Haiku/Sonnet arms: `refused` if all (pass `--tier-question "<why>"`), `warn` if some; re-costs on frontier prices. - `DRY_RUN_ROW:` lines name rows missing a field; fix the rows, not the prompt. `DRY_RUN_RESULT: pass` writes `dry-run.json` to `--out`; the pilot refuses to start on diff --git a/eval-plan/SKILL.md.tmpl b/eval-plan/SKILL.md.tmpl index 1029b4053..6083aa0ba 100644 --- a/eval-plan/SKILL.md.tmpl +++ b/eval-plan/SKILL.md.tmpl @@ -107,6 +107,10 @@ page or drop the arm. Copy the priced arms into the Arms section. An arm identit `<model>#<loadout>` (for example `claude-opus-5-5#no-gstack`) is priced by its model and gets its own pilot attempts; naming one identity twice is `EVAL_ARM_DUPLICATE`. +Models under test are frontier models (`claude-opus-5-5`, `gpt-6.1-sol`, at most one named +low-cost primary); a Haiku or Sonnet arm only with a stated tier question +(docs/TESTING_INTERNALS.md#frontier-models-under-test). + When the repo commits `.gstack/eval-models.json` (allow, deny, per-scope lists, families newest first; `docs/eval-models.md` in gstack), `arms`, `dry-run`, `pilot start` and `price-gate` print one `EVAL_MODEL:` line per arm. Pass `--scope smoke` for a smoke run; @@ -161,6 +165,7 @@ the budget the run will use. The checklist printed must be all `ok`: with no text is a repeat of the same failure at the same price. - `CHECK: reservation-fits-cap` (with `--cap <cap-usd>`) — one call, the largest row plus the output budget, priced, fits under the cap; a provider refuses a reservation the cap cannot hold. +- `CHECK: frontier` — Haiku/Sonnet arms: `refused` if all (pass `--tier-question "<why>"`), `warn` if some; re-costs on frontier prices. - `DRY_RUN_ROW:` lines name rows missing a field; fix the rows, not the prompt. `DRY_RUN_RESULT: pass` writes `dry-run.json` to `--out`; the pilot refuses to start on diff --git a/lib/eval-plan.ts b/lib/eval-plan.ts index 21ae8b6e5..084038514 100644 --- a/lib/eval-plan.ts +++ b/lib/eval-plan.ts @@ -39,7 +39,7 @@ export function preregTemplate(title = 'Eval preregistration'): string { <!-- One line per metric: name, the pass bar, the direction, and what a miss means for the decision. --> ## Arms -<!-- One line per arm: the arm identity first (\`<model>\` or \`<model>#<loadout>\`, the model in lib/pricing.ts, e.g. \`claude-opus-5-5#no-gstack\`), settings, and the per-item cost from \`gstack-eval-plan arms\`. --> +<!-- One line per arm: the arm identity first (\`<model>\` or \`<model>#<loadout>\`, the model in lib/pricing.ts, e.g. \`claude-opus-5-5#no-gstack\`), settings, and the per-item cost from \`gstack-eval-plan arms\`. Models under test are frontier models (today \`claude-opus-5-5\`, \`gpt-6.1-sol\`) plus at most one named low-cost primary; a Haiku or Sonnet arm only with a stated tier question. --> ## Comparison <!-- \`stack: loaded\` when any arm loads gstack or another skill stack (review variants, preamble loadouts, skill diets, a model panel under a stack); otherwise \`stack: none\` and a \`why:\` line. --> @@ -292,10 +292,16 @@ export interface DryRunResult { reservation_fits_cap?: { ok: boolean; cap: number; max_input_tokens: number; per_arm: Record<string, number | null> }; /** Present when the caller linted the arms against .gstack/eval-models.json (lib/eval-models.ts). */ model_rules?: { ok: boolean; source: string; refused: string[] }; + /** R54: Haiku and Sonnet are not models under test; arms on them alone are refused unless the plan asks about that tier. */ + frontier: { ok: boolean; small_tier: string[]; tier_question: string | null; recost_usd: Record<string, number> }; }; per_item_usd: Record<string, number | null>; excluded_billing: readonly string[]; pass: boolean; stub: 'stub-model (no network, $0)'; } -export interface DryRunOptions { input: string; arms: string[]; fields?: string[]; outputBudget?: number; retryPrompt?: string; maxRows?: number; cap?: number; modelRules?: ModelRulesCheck } +export interface DryRunOptions { input: string; arms: string[]; fields?: string[]; outputBudget?: number; retryPrompt?: string; maxRows?: number; cap?: number; modelRules?: ModelRulesCheck; tierQuestion?: string } + +/** Today's frontier models under test (R54, docs/TESTING_INTERNALS.md#frontier-models-under-test); a small-tier plan is re-costed on these. */ +export const FRONTIER_MODELS = ['claude-opus-5-5', 'gpt-6.1-sol'] as const; +export const isSmallTierModel = (model: string) => /(^|[-/])(haiku|sonnet)(-|$)/i.test(model); /** Four bytes per token, the estimator every gstack admission uses. */ export const estimateTokens = (text: string) => Math.ceil(Buffer.byteLength(text, 'utf8') / 4); @@ -335,9 +341,12 @@ export function dryRun(o: DryRunOptions): DryRunResult { checks.reservation_fits_cap = { ok: Object.values(perArm).every(v => v === null || v <= o.cap!), cap: o.cap, max_input_tokens: maxInput, per_arm: perArm }; } if (o.modelRules) checks.model_rules = { ok: o.modelRules.ok, source: o.modelRules.source, refused: o.modelRules.errors.map(e => e.message) }; + const smallTier = o.arms.filter(a => isSmallTierModel(armModel(a))); + const recost = Object.fromEntries(FRONTIER_MODELS.map(m => [m, rows * o.arms.length * estimateCostUsd({ input: avgIn, output: budget }, m)])); + checks.frontier = { ok: smallTier.length < o.arms.length || !!o.tierQuestion?.trim(), small_tier: smallTier, tier_question: o.tierQuestion?.trim() || null, recost_usd: recost }; return { schema_version: 1, input: o.input, rows, bad_rows: bad, est_input_tokens: inputTokens, est_output_tokens: rows * budget, arms: o.arms, checks, per_item_usd: perItem, - excluded_billing: EXCLUDED_BILLING_CATEGORIES, pass: rows > 0 && bad.length === 0 && checks.price_table.ok && checks.output_budget.ok && checks.retry_prompt.ok && (checks.reservation_fits_cap?.ok ?? true) && (checks.model_rules?.ok ?? true), stub: 'stub-model (no network, $0)', + excluded_billing: EXCLUDED_BILLING_CATEGORIES, pass: rows > 0 && bad.length === 0 && checks.price_table.ok && checks.output_budget.ok && checks.retry_prompt.ok && (checks.reservation_fits_cap?.ok ?? true) && (checks.model_rules?.ok ?? true) && checks.frontier.ok, stub: 'stub-model (no network, $0)', }; } @@ -349,6 +358,7 @@ export function renderDryRun(r: DryRunResult): string { `CHECK: output-budget ${r.checks.output_budget.ok ? 'ok' : 'too small'} (${r.checks.output_budget.budget} tokens; reasoning floor ${r.checks.output_budget.floor})`, `CHECK: retry-prompt ${r.checks.retry_prompt.ok ? `ok — ${JSON.stringify(r.checks.retry_prompt.text)}` : 'missing (pass --retry-prompt <file> with the exact text the run will send)'}`, ...(r.checks.reservation_fits_cap ? [renderReservationCheck(r.checks.reservation_fits_cap, r.checks.output_budget.budget)] : []), + ...(r.checks.frontier.small_tier.length ? [renderFrontierCheck(r.checks.frontier, r.arms.length)] : []), ...(r.checks.model_rules ? [`CHECK: model-rules ${r.checks.model_rules.ok ? 'ok' : `refused ${r.checks.model_rules.refused.join('; ') || 'invalid rules'}`} (source ${r.checks.model_rules.source})`] : []), ...Object.entries(r.per_item_usd).map(([m, usd]) => `ESTIMATE: ${m} per_item=${usd === null ? 'unknown (no price)' : `$${usd.toFixed(4)}`} (estimate: excludes ${r.excluded_billing.length} billing categories, see lib/pricing.ts)`), `DRY_RUN_RESULT: ${r.pass ? 'pass' : 'fail'}`, @@ -356,6 +366,13 @@ export function renderDryRun(r: DryRunResult): string { return lines.join('\n') + '\n'; } +function renderFrontierCheck(c: DryRunResult['checks']['frontier'], arms: number): string { + const verdict = !c.ok ? 'refused (every arm is Haiku or Sonnet; pass --tier-question "<what the preregistration asks about that tier>" or test a frontier model)' + : c.tier_question ? `ok (tier question: ${JSON.stringify(c.tier_question)})` : 'warn (Haiku or Sonnet arms are not models under test)'; + const recost = Object.entries(c.recost_usd).map(([m, usd]) => `${m} $${usd.toFixed(2)}`).join(', '); + return `CHECK: frontier ${verdict} small_tier=${c.small_tier.join(',')}; all ${arms} arm(s) re-costed on frontier prices: ${recost} (docs/TESTING_INTERNALS.md#frontier-models-under-test)`; +} + function renderReservationCheck(c: NonNullable<DryRunResult['checks']['reservation_fits_cap']>, budget: number): string { const worst = Math.max(0, ...Object.values(c.per_arm).filter((v): v is number => v !== null)); return `CHECK: reservation-fits-cap ${c.ok ? 'ok' : 'exceeds'} ($${worst.toFixed(4)} ${c.ok ? '<=' : '>'} cap $${c.cap.toFixed(2)}) one call = ${c.max_input_tokens} in + ${budget} out tokens`; @@ -376,6 +393,7 @@ export interface PilotStartOptions { out: string; cap: number; n: number; arms: export function startPilot(o: PilotStartOptions): { record: PilotRecord; error?: { code: ResultCodeName; message: string } } { const dry = JSON.parse(fs.readFileSync(o.dryRun, 'utf8')) as DryRunResult; if (!dry.pass) return { record: null as unknown as PilotRecord, error: { code: 'EVAL_DRY_RUN_FAILED', message: `${o.dryRun} did not pass; the pilot never starts on a failed dry run` } }; + if (o.arms.length && o.arms.every(a => isSmallTierModel(armModel(a))) && !dry.checks.frontier?.tier_question) return { record: null as unknown as PilotRecord, error: { code: 'EVAL_DRY_RUN_FAILED', message: `every pilot arm is Haiku or Sonnet and ${o.dryRun} records no --tier-question (R54, docs/TESTING_INTERNALS.md#frontier-models-under-test)` } }; const tokens = o.tokens ?? { input: dry.rows ? Math.ceil(dry.est_input_tokens / dry.rows) : DEFAULT_TOKENS.input, output: dry.checks.output_budget.budget }; const seat = o.seatMetered ?? []; const stray = seat.filter(a => !o.arms.includes(a)); diff --git a/lib/flaky-run.ts b/lib/flaky-run.ts index 4c2f0d65e..a92ba91d8 100644 --- a/lib/flaky-run.ts +++ b/lib/flaky-run.ts @@ -29,15 +29,23 @@ * omits (bun files that fail to load), the run is red and nothing is rerun. * The first report is restored at the --junit path when the run ends; each * rerun's report is kept beside it as <name>.rerun-<n>.xml. + * - Quarantine (lib/quarantine.ts) is a larger attempt budget, never a skip: + * a live quarantined test is listed and ledgered on every run and never + * counts as a pass. When every test a whole-command attempt failed is + * quarantined and nothing else is wrong, the command may run again, up to + * QUARANTINE_ATTEMPTS in total; the run is green only on an attempt with the + * runner's full green verdict, so a quarantined failure never turns a red + * attempt green. One that fails every attempt is a hard break. A quarantined + * id missing from a run that included its file is red. */ import * as fs from 'fs'; import * as path from 'path'; import { spawn as spawnChild, spawnSync } from 'child_process'; -import { finalAttempt, JunitError, readJunit, type JunitReport, type JunitRunner, type JunitTest } from './junit'; +import { finalAttempt, JunitError, parseTestId, readJunit, type Attempt, type JunitReport, type JunitRunner, type JunitTest } from './junit'; import { redactFindingSpans } from './redact-engine'; import { resolveStateRoot } from './state-root'; -export type LedgerKind = 'flaky-pass' | 'rerun-fail'; +export type LedgerKind = 'flaky-pass' | 'rerun-fail' | 'quarantined-pass' | 'quarantined-fail' | 'hard-break'; export interface LedgerLine { ts: string; @@ -64,6 +72,8 @@ export interface RunOptions { maxReruns: number; /** 'command' (default): rerun the whole command. 'test': rerun the failed test alone when the first run is proven complete. */ rerunScope?: 'command' | 'test'; + /** Live quarantined test ids (lib/quarantine.ts liveQuarantine): up to QUARANTINE_ATTEMPTS attempts, never a skip. */ + quarantined?: ReadonlySet<string>; cwd?: string; env?: NodeJS.ProcessEnv; /** Runs one attempt; resolves with its exit status and the tail of its combined output. */ @@ -73,7 +83,7 @@ export interface RunOptions { export interface TestOutcome { test: JunitTest; - status: 'flaky-pass' | 'fail' | 'rerun-fail'; + status: 'flaky-pass' | 'fail' | 'rerun-fail' | 'quarantined-pass' | 'quarantined-fail' | 'hard-break'; attempts: string[]; reason?: string; } @@ -88,6 +98,8 @@ export interface RunResult { commandExit: number; outcomes: TestOutcome[]; reruns: number; + /** Outcomes of quarantined tests (listed, never counted as passes). */ + quarantined: number; /** Why the rerun was the whole command (the default, or why a requested targeted rerun was refused); absent for targeted reruns. */ wholeRerun?: string; ledger: LedgerLine[]; @@ -243,7 +255,7 @@ function rerunProblem(again: Attempted & { report?: JunitReport }, first: JunitR } /** A rerun clears a test only when its command exited 0 and the test ran once and passed on its first attempt. */ -function rerunVerdict(again: Attempted & { report?: JunitReport; error?: JunitError }, t: JunitTest, problem?: string): { status: 'flaky-pass' | 'rerun-fail'; attempts: string[]; reason?: string } { +function rerunVerdict(again: Attempted & { report?: JunitReport; error?: JunitError }, t: JunitTest, problem?: string): { status: 'flaky-pass' | 'rerun-fail'; attempts: Attempt[]; reason?: string } { const match = again.report?.tests.find(x => x.id === t.id); if (!match) return { status: 'rerun-fail', attempts: [...t.attempts, 'fail'], reason: again.error ? `rerun: ${again.error.message}` : 'rerun: the report does not contain this test' }; const attempts = [...t.attempts, ...match.attempts]; @@ -254,11 +266,47 @@ function rerunVerdict(again: Attempted & { report?: JunitReport; error?: JunitEr return { status: 'flaky-pass', attempts }; } +export const QUARANTINE_ATTEMPTS = 3; + +const PASSING: ReadonlySet<TestOutcome['status']> = new Set(['flaky-pass', 'quarantined-pass']); + +type Ran = Attempted & { report?: JunitReport; error?: JunitError }; + +/** The runner's own full green verdict for a whole-command attempt: exit 0, no failed or missing test, nothing counted outside the report. */ +function fullGreen(again: Ran, first: JunitReport): boolean { + return !!again.report && !again.signal && again.exit === 0 && !rerunProblem(again, first, true); +} + +/** + * Whether a red whole-command attempt may be followed by another: only within + * the quarantine budget, and only when every test it failed is a live + * quarantined test that ran once and nothing else is wrong (a kill, a missing + * report, failures outside the report, a first-run test missing). + */ +function mayRunAgain(again: Ran, first: JunitReport, quarantined: ReadonlySet<string>, attemptsSoFar: number): boolean { + if (attemptsSoFar >= QUARANTINE_ATTEMPTS || again.signal || !again.report) return false; + const failedNow = again.report.tests.filter(x => finalAttempt(x) === 'fail'); + if (!failedNow.length || !failedNow.every(x => quarantined.has(x.id) && x.executions === 1 && x.attempts.length === 1)) return false; + if (unreportedFailures(first.runner, again.output, failedNow.length)) return false; + const seen = new Set(again.report.tests.map(x => x.id)); + return first.tests.every(x => seen.has(x.id)); +} + +/** A test's attempts over the first run and the given whole-command reruns; a rerun that did not report it counts as a failure. */ +const history = (t: JunitTest, runs: Ran[]): Attempt[] => + [...t.attempts, ...runs.flatMap(r => r.report?.tests.find(x => x.id === t.id)?.attempts ?? ['fail' as const])]; + +/** A quarantined test passes only when it never failed or an attempt with the runner's full verdict cleared it. */ +const quarantinedStatus = (attempts: string[], cleared: boolean): 'quarantined-pass' | 'quarantined-fail' | 'hard-break' => + cleared || !attempts.includes('fail') ? 'quarantined-pass' + : attempts.length >= QUARANTINE_ATTEMPTS && attempts.every(a => a === 'fail') ? 'hard-break' : 'quarantined-fail'; + export async function runFlaky(opts: RunOptions): Promise<RunResult> { const cwd = opts.cwd ?? process.cwd(); const env = { ...(opts.env ?? process.env), PLAYWRIGHT_JUNIT_INCLUDE_RETRIES: '1' }; const now = opts.now ?? (() => new Date()); - const empty = { tests: 0, outcomes: [], reruns: 0, ledger: [] }; + const quarantined = opts.quarantined ?? new Set<string>(); + const empty = { tests: 0, outcomes: [], reruns: 0, quarantined: 0, ledger: [] }; const first = await attempt(opts, opts.command, cwd, env); if (first.signal) return { exitCode: 3, code: 'FLAKY_COMMAND_KILLED', message: `the command was killed by ${first.signal}`, commandExit: first.exit, ...empty }; if (!first.report) return { exitCode: 3, code: first.error!.code, message: first.error!.message, commandExit: first.exit, ...empty }; @@ -282,15 +330,39 @@ export async function runFlaky(opts: RunOptions): Promise<RunResult> { const prov = provenance(cwd, env); const line = (t: JunitTest, kind: LedgerKind, by: LedgerLine['rerun_by'], attempts: string[], scope?: LedgerLine['rerun_scope']): LedgerLine => ({ ts: now().toISOString(), runner: 'junit', kind, id: safeText(t.id), file: safeText(t.file), rerun_by: by, ...(scope ? { rerun_scope: scope } : {}), attempts, ...prov, excerpt: safeExcerpt(t.excerpt) }); - const ledger: LedgerLine[] = runnerFlaky.map(t => line(t, 'flaky-pass', 'runner', t.attempts)); - const outcomes: TestOutcome[] = runnerFlaky.map(t => ({ test: t, status: 'flaky-pass' as const, attempts: t.attempts })); + const isQ = (t: JunitTest) => quarantined.has(t.id); + const outcomes: TestOutcome[] = []; + const ledger: LedgerLine[] = []; + for (const t of runnerFlaky.filter(x => !isQ(x))) { + outcomes.push({ test: t, status: 'flaky-pass', attempts: t.attempts }); + ledger.push(line(t, 'flaky-pass', 'runner', t.attempts)); + } + const settleQ = (t: JunitTest, attempts: string[], cleared: boolean, reason?: string, scope?: LedgerLine['rerun_scope']) => { + const status = quarantinedStatus(attempts, cleared); + const why = status === 'hard-break' ? `failed all ${attempts.length} attempts: a hard break, not a flake` : status === 'quarantined-fail' ? reason : undefined; + outcomes.push({ test: t, status, attempts, ...(why ? { reason: why } : {}) }); + ledger.push(line(t, status, 'gstack-flaky', attempts, scope)); + }; + const settle = (t: JunitTest, attempts: string[], reason: string) => isQ(t) ? settleQ(t, attempts, false, reason) : outcomes.push({ test: t, status: 'fail', attempts, reason }); + const present = new Set(report.tests.map(t => t.id)); + const included = new Set(report.tests.map(t => `${t.file}::${t.project}`)); + for (const id of quarantined) { + const p = parseTestId(id); + if (!p || present.has(id) || !included.has(`${p.file}::${p.project}`)) continue; + const t: JunitTest = { id, file: p.file, project: p.project, path: p.title.split(' > '), attempts: [], executions: 0, excerpt: [] }; + outcomes.push({ test: t, status: 'quarantined-fail', attempts: [], reason: 'quarantined, and missing from a run that included its file' }); + ledger.push(line(t, 'quarantined-fail', 'gstack-flaky', [])); + } + const others = failed.filter(t => !isQ(t)).length; const eligible: JunitTest[] = []; for (const t of failed) { - if (t.executions > 1) outcomes.push({ test: t, status: 'fail', attempts: t.attempts, reason: `it ran ${t.executions} times in this report and one failed; not rerun` }); - else if (t.attempts.length > 1) outcomes.push({ test: t, status: 'fail', attempts: t.attempts, reason: `the runner already retried (${t.attempts.length} attempts)` }); - else if (failed.length > opts.maxReruns) outcomes.push({ test: t, status: 'fail', attempts: t.attempts, reason: `${failed.length} tests failed, more than --max-reruns ${opts.maxReruns}; not rerun` }); + const why = t.executions > 1 ? `it ran ${t.executions} times in this report and one failed; not rerun` + : t.attempts.length > 1 ? `the runner already retried (${t.attempts.length} attempts)` + : !isQ(t) && others > opts.maxReruns ? `${others} tests failed, more than --max-reruns ${opts.maxReruns}; not rerun` : undefined; + if (why) settle(t, t.attempts, why); else eligible.push(t); } + const passedQ = report.tests.filter(t => isQ(t) && finalAttempt(t) !== 'fail' && t.attempts.some(a => a !== 'skip')); const wholeRerun = !eligible.length ? undefined : opts.rerunScope !== 'test' ? 'the default; --rerun-scope test reruns the failed test alone' : incompleteRun(report.runner, first.output, first.exit, opts.command, runnerFlaky.length) ?? undefined; @@ -304,30 +376,42 @@ export async function runFlaky(opts: RunOptions): Promise<RunResult> { return again; }; const record = (t: JunitTest, v: ReturnType<typeof rerunVerdict>, scope: 'test' | 'command') => { + if (isQ(t)) return settleQ(t, v.attempts, v.status === 'flaky-pass', v.reason, scope); outcomes.push({ test: t, status: v.status, attempts: v.attempts, ...(v.reason ? { reason: v.reason } : {}) }); ledger.push(line(t, v.status, 'gstack-flaky', v.attempts, scope)); }; + const runs: Ran[] = []; try { - if (wholeRerun && outcomes.some(o => o.status === 'fail')) { - for (const t of eligible) outcomes.push({ test: t, status: 'fail', attempts: t.attempts, reason: `not rerun: the run is already red, and a rerun would repeat the whole command (${wholeRerun})` }); + if (wholeRerun && outcomes.some(o => !PASSING.has(o.status))) { + for (const t of eligible) settle(t, t.attempts, `not rerun: the run is already red, and a rerun would repeat the whole command (${wholeRerun})`); } else if (wholeRerun) { - const again = await rerun(opts.command); - const problem = rerunProblem(again, report, true); - for (const t of eligible) record(t, rerunVerdict(again, t, problem), 'command'); + do { + runs.push(await rerun(opts.command)); + } while (!fullGreen(runs.at(-1)!, report) && mayRunAgain(runs.at(-1)!, report, quarantined, 1 + runs.length)); + const decider = runs.at(-1)!; + const problem = rerunProblem(decider, report, true); + for (const t of eligible) record(t, rerunVerdict(decider, { ...t, attempts: history(t, runs.slice(0, -1)) }, problem), 'command'); } else if (eligible.length) { let interrupted = false; for (const t of eligible) { - if (interrupted) { outcomes.push({ test: t, status: 'fail', attempts: t.attempts, reason: 'not rerun: an earlier rerun was killed' }); continue; } - const again = await rerun([...opts.command, ...rerunSelection(report.runner as 'playwright' | 'bun', t)]); - interrupted = !!again.signal; - record(t, rerunVerdict(again, t, rerunProblem(again, report, false)), 'test'); + if (interrupted) { settle(t, t.attempts, 'not rerun: an earlier rerun was killed'); continue; } + let v: ReturnType<typeof rerunVerdict> = { status: 'rerun-fail', attempts: t.attempts }; + for (let budget = isQ(t) ? QUARANTINE_ATTEMPTS - t.attempts.length : 1; budget > 0 && v.status !== 'flaky-pass' && !interrupted; budget--) { + const again = await rerun([...opts.command, ...rerunSelection(report.runner as 'playwright' | 'bun', t)]); + interrupted = !!again.signal; + v = rerunVerdict(again, { ...t, attempts: v.attempts }, rerunProblem(again, report, false)); + } + record(t, v, 'test'); } } } finally { if (reruns) fs.writeFileSync(junit, firstXml); } - const red = outcomes.some(o => o.status !== 'flaky-pass'); - return { exitCode: red ? 1 : 0, tests: report.tests.length, commandExit: first.exit, outcomes, reruns, ...(wholeRerun && reruns ? { wholeRerun } : {}), ledger }; + const green = runs.length ? fullGreen(runs.at(-1)!, report) : reruns > 0 || first.exit === 0; + for (const t of passedQ) settleQ(t, history(t, runs), green, 'the attempt that decided the run was not a full green run', runs.length ? 'command' : undefined); + const red = !green || outcomes.some(o => !PASSING.has(o.status)); + const q = outcomes.filter(o => o.status === 'quarantined-pass' || o.status === 'quarantined-fail' || o.status === 'hard-break').length; + return { exitCode: red ? 1 : 0, tests: report.tests.length, commandExit: first.exit, outcomes, reruns, quarantined: q, ...(wholeRerun && reruns ? { wholeRerun } : {}), ledger }; } export function ledgerPath(flag: string | undefined, env: NodeJS.ProcessEnv = process.env): string { @@ -352,9 +436,9 @@ export function renderResult(r: RunResult, ledger: string): string[] { const out: string[] = []; for (const o of r.outcomes) out.push(`FLAKY: ${o.status} ${safeText(o.test.id)} attempts=${o.attempts.join(',')}${o.reason ? ` (${o.reason})` : ''}`); const flaky = r.outcomes.filter(o => o.status === 'flaky-pass').length; - const failed = r.outcomes.length - flaky; + const failed = r.outcomes.filter(o => !PASSING.has(o.status)).length; if (r.wholeRerun) out.push(`FLAKY_RERUN: scope=command (${r.wholeRerun})`); - out.push(`FLAKY_RESULT: tests=${r.tests} failed=${failed} flaky=${flaky} reruns=${r.reruns} command_exit=${r.commandExit} verdict=${r.exitCode === 0 ? 'pass' : 'fail'} ledger=${r.ledger.length ? ledger : 'none'}`); + out.push(`FLAKY_RESULT: tests=${r.tests} failed=${failed} flaky=${flaky} quarantined=${r.quarantined} reruns=${r.reruns} command_exit=${r.commandExit} verdict=${r.exitCode === 0 ? 'pass' : 'fail'} ledger=${r.ledger.length ? ledger : 'none'}`); return out; } diff --git a/lib/junit.ts b/lib/junit.ts index 0f4d504d3..5440f4b48 100644 --- a/lib/junit.ts +++ b/lib/junit.ts @@ -137,6 +137,14 @@ function excerptOf(node: XmlNode | undefined): string[] { export const testId = (file: string, project: string, path: string[]) => `${file}::${project}::${path.join(' > ')}`; +/** The parts of a test id, or null when it is not `<file>::<project>::<title>`. */ +export function parseTestId(id: string): { file: string; project: string; title: string } | null { + const i = id.indexOf('::'); + const j = i < 0 ? -1 : id.indexOf('::', i + 2); + if (i <= 0 || j < 0 || j + 2 >= id.length) return null; + return { file: id.slice(0, i), project: id.slice(i + 2, j), title: id.slice(j + 2) }; +} + function readCase(tc: XmlNode, runner: JunitRunner): Omit<JunitTest, 'id' | 'executions'> & { hidden: boolean } { const suite = tc.parent!; let file: string, project = '', path: string[]; diff --git a/lib/pricing.ts b/lib/pricing.ts index 9d867e442..fc97c8df4 100644 --- a/lib/pricing.ts +++ b/lib/pricing.ts @@ -149,3 +149,66 @@ export function estimateCostUsd( const outputCost = tokens.output * row.output_per_mtok / 1_000_000; return +(inputCost + cachedCost + outputCost).toFixed(6); } + +/** Token classes of one Anthropic Messages usage block, as Claude Code's stream-json and session transcripts carry it. */ +export interface AnthropicUsage { + input_tokens?: number; + output_tokens?: number; + cache_read_input_tokens?: number; + cache_creation_input_tokens?: number; + cache_creation?: { ephemeral_5m_input_tokens?: number; ephemeral_1h_input_tokens?: number }; +} + +/** Anthropic bills a prompt-cache write at 1.25x input for the 5-minute TTL and 2x for the 1-hour TTL. */ +export const CACHE_WRITE_MULTIPLIER = { ephemeral_5m: 1.25, ephemeral_1h: 2 } as const; + +/** + * Cost of one usage block at its model's row, prompt-cache writes included + * (unlike estimateCostUsd). Undefined when the model has no price row: an + * unpriced model's usage is unknown cost, never zero. + */ +export function anthropicUsageCostUsd(usage: AnthropicUsage, model: string | undefined): number | undefined { + const row = pricingRow(model); + if (!row) return undefined; + const count = (value: unknown) => typeof value === 'number' && Number.isFinite(value) && value > 0 ? value : 0; + const oneHour = count(usage.cache_creation?.ephemeral_1h_input_tokens); + const fiveMinute = typeof usage.cache_creation?.ephemeral_5m_input_tokens === 'number' + ? count(usage.cache_creation.ephemeral_5m_input_tokens) : Math.max(0, count(usage.cache_creation_input_tokens) - oneHour); + const cachedRate = row.cached_input_per_mtok ?? row.input_per_mtok * 0.1; + return (count(usage.input_tokens) * row.input_per_mtok + + count(usage.cache_read_input_tokens) * cachedRate + + fiveMinute * row.input_per_mtok * CACHE_WRITE_MULTIPLIER.ephemeral_5m + + oneHour * row.input_per_mtok * CACHE_WRITE_MULTIPLIER.ephemeral_1h + + count(usage.output_tokens) * row.output_per_mtok) / 1_000_000; +} + +/** + * Billed cost of a session's assistant messages, subagent (sidechain) turns + * included. A message streams as several events sharing one message id whose + * usage grows, so each id counts once at its largest output. Each message is + * priced at its own model, else `fallbackModel`. Undefined when no message + * carries usage or any message's model has no price row. + */ +export function streamedUsageCostUsd( + events: ReadonlyArray<{ message?: { id?: unknown; model?: unknown; usage?: unknown } } | null | undefined>, + fallbackModel?: string, +): number | undefined { + const byId = new Map<string, { model?: string; usage: AnthropicUsage }>(); + for (const event of events) { + const message = event?.message; + const usage = message?.usage as AnthropicUsage | undefined; + if (!usage || typeof usage !== 'object' || typeof message!.id !== 'string' || message!.model === '<synthetic>') continue; + const seen = byId.get(message!.id); + if (!seen || (usage.output_tokens ?? 0) >= (seen.usage.output_tokens ?? 0)) { + byId.set(message!.id, { model: typeof message!.model === 'string' ? message!.model : fallbackModel, usage }); + } + } + if (byId.size === 0) return undefined; + let total = 0; + for (const { model, usage } of byId.values()) { + const cost = anthropicUsageCostUsd(usage, model); + if (cost === undefined) return undefined; + total += cost; + } + return +total.toFixed(6); +} diff --git a/lib/quarantine.ts b/lib/quarantine.ts new file mode 100644 index 000000000..2b4c619e9 --- /dev/null +++ b/lib/quarantine.ts @@ -0,0 +1,447 @@ +/** + * gstack-flaky quarantine (GSTA-158 P2): a registry of known-flaky tests at + * `.gstack/quarantine.json`. A quarantined test still runs; it gets a larger + * attempt budget (lib/flaky-run.ts, QUARANTINE_ATTEMPTS) under the same full + * green verdict, and it is never counted as a pass. This file holds the + * registry: schema, validation, add/renew/release, `check` against the base + * branch, and `report` over downloaded ledgers. + * + * Rules (docs/flaky.md § Quarantine): + * - Every entry has an owner, a ledger link, a failure class (detector, + * harness, timing, model-latency; product defects and infra are refused), + * evidence and an expiry: 7 days by default, at most 14 from entry, and one + * renewal of at most 7 days with new evidence and the owner named again. + * - An expired or invalid entry is not quarantined; nothing needs editing. + * - Live entries are capped at max(1, 10% of the suite's tests), and 5 for a + * suite under 50 tests. + * - `run --base` reads the registry from the base branch so a change cannot + * quarantine the test it breaks; `check --base` refuses an entry added in + * the change that edits its test's file, an entry that disappears without a + * release record, a release record that was removed, and rewritten history. + * - gstack's own CASE_QUARANTINE / EVAL_POLICY (paid evals) is a separate + * registry; the two share no schema. + */ +import * as fs from 'fs'; +import * as path from 'path'; +import { spawnSync } from 'child_process'; +import { parseTestId, readJunit, type JunitRunner } from './junit'; +import { safeText } from './flaky-run'; + +export const REGISTRY_PATH = '.gstack/quarantine.json'; +export const FAILURE_CLASSES = ['detector', 'harness', 'timing', 'model-latency'] as const; +export type FailureClass = typeof FAILURE_CLASSES[number]; +export const DEFAULT_DAYS = 7; +export const MAX_DAYS = 14; +export const RENEW_MAX_DAYS = 7; +export const EXIT_RULE_PASSES = 10; +const DAY = 86_400_000; + +export interface Renewal { renewedAt: string; previousExpiresAt: string; expiresAt: string; owner: string; evidence: string[] } + +export interface QuarantineEntry { + owner: string; + /** Link to the flaky ledger line or issue that tracks the fix. */ + ledger: string; + failureClass: FailureClass; + reason: string; + evidence: string[]; + enteredAt: string; + expiresAt: string; + renewals: Renewal[]; + /** The suite's test count when the entry was added (`add --junit`), the base of the cap. */ + suiteTests: number; +} + +export type ReleasedEntry = Omit<QuarantineEntry, 'reason'> & { id: string; releasedAt: string; reason: string; pr: string }; + +export interface Registry { schema: 1; entries: Record<string, QuarantineEntry>; released: ReleasedEntry[] } + +export class QuarantineError extends Error { + constructor(readonly code: string, message: string, readonly exitCode: 1 | 2 | 3 = 3) { super(message); } +} + +export const emptyRegistry = (): Registry => ({ schema: 1, entries: {}, released: [] }); + +/** Live entries allowed for a suite of `tests` tests. */ +export const suiteCap = (tests: number) => tests < 50 ? 5 : Math.max(1, Math.floor(tests / 10)); + +function git(args: string[], cwd: string): { ok: boolean; out: string } { + const r = spawnSync('git', args, { cwd, encoding: 'utf-8', timeout: 15_000 }); + return { ok: r.status === 0, out: r.stdout ?? '' }; +} + +export function repoRoot(cwd: string): string { + const r = git(['rev-parse', '--show-toplevel'], cwd); + return r.ok && r.out.trim() ? r.out.trim() : cwd; +} + +export function parseRegistry(text: string, source: string): Registry { + let data: unknown; + try { data = JSON.parse(text); } catch (e) { + throw new QuarantineError('FLAKY_QUARANTINE_INVALID', `${source} is not valid JSON (${(e as Error).message})`); + } + const r = data as Partial<Registry> | null; + if (!r || typeof r !== 'object' || r.schema !== 1 || !r.entries || typeof r.entries !== 'object' || Array.isArray(r.entries) || !Array.isArray(r.released)) { + throw new QuarantineError('FLAKY_QUARANTINE_INVALID', `${source} is not a schema 1 quarantine registry ({"schema":1,"entries":{},"released":[]})`); + } + return r as Registry; +} + +function resolveCommit(ref: string, cwd: string): string { + if (!ref || ref.startsWith('-')) throw new QuarantineError('FLAKY_QUARANTINE_BASE', `--base ${JSON.stringify(ref)} is not a git ref`, 2); + const r = git(['rev-parse', '--verify', '--quiet', `${ref}^{commit}`], cwd); + if (!r.ok) throw new QuarantineError('FLAKY_QUARANTINE_BASE', `--base ${ref} does not resolve to a commit in ${cwd}`); + return r.out.trim(); +} + +function registryAt(commit: string, root: string, label: string): Registry { + if (!git(['cat-file', '-e', `${commit}:${REGISTRY_PATH}`], root).ok) return emptyRegistry(); + const shown = git(['show', `${commit}:${REGISTRY_PATH}`], root); + if (!shown.ok) throw new QuarantineError('FLAKY_QUARANTINE_BASE', `cannot read ${REGISTRY_PATH} at ${label}`); + return parseRegistry(shown.out, `${REGISTRY_PATH} at ${label}`); +} + +/** The registry in the working tree, or at `base` when given; a missing file is an empty registry. */ +export function readRegistry(cwd: string, base?: string): Registry { + const root = repoRoot(cwd); + if (base !== undefined) return registryAt(resolveCommit(base, root), root, base); + const file = path.join(root, REGISTRY_PATH); + if (!fs.existsSync(file)) return emptyRegistry(); + return parseRegistry(fs.readFileSync(file, 'utf-8'), REGISTRY_PATH); +} + +export function writeRegistry(cwd: string, reg: Registry): string { + const file = path.join(repoRoot(cwd), REGISTRY_PATH); + const entries = Object.fromEntries(Object.keys(reg.entries).sort().map(id => [id, reg.entries[id]!])); + fs.mkdirSync(path.dirname(file), { recursive: true }); + fs.writeFileSync(file, JSON.stringify({ schema: 1, entries, released: reg.released }, null, 2) + '\n'); + return file; +} + +const filled = (s: unknown): s is string => typeof s === 'string' && s.trim().length > 0; +const filledList = (l: unknown): l is string[] => Array.isArray(l) && l.length > 0 && l.every(filled); + +export function classRefusal(c: unknown): string | undefined { + if (FAILURE_CLASSES.includes(c as FailureClass)) return undefined; + if (c === 'product') return 'class product is refused: a product defect is a real red; fix it instead of quarantining it'; + if (c === 'infra') return 'class infra is refused: an infrastructure red is rerun or fixed as infra, never quarantined'; + return `class ${JSON.stringify(c)} is not one of ${FAILURE_CLASSES.join(', ')}`; +} + +/** What makes one entry invalid; an invalid entry is never quarantined and `check` refuses it. */ +export function entryProblems(id: string, e: QuarantineEntry, now: Date): string[] { + if (!e || typeof e !== 'object') return ['not an object']; + const p: string[] = []; + if (!parseTestId(id)) p.push('not a test id (<file>::<project>::<title>; gstack-flaky ids prints them)'); + if (!filled(e.owner)) p.push('no owner'); + if (!filled(e.ledger)) p.push('no ledger link'); + if (!filled(e.reason)) p.push('no reason'); + const cls = classRefusal(e.failureClass); + if (cls) p.push(cls); + if (!filledList(e.evidence)) p.push('no evidence'); + if (!(Number.isInteger(e.suiteTests) && e.suiteTests > 0)) p.push('no suiteTests (add records the suite size from --junit)'); + const entered = Date.parse(e.enteredAt); + const expires = Date.parse(e.expiresAt); + if (Number.isNaN(entered) || Number.isNaN(expires)) return [...p, 'enteredAt or expiresAt is not a date']; + if (entered > now.getTime() + DAY) p.push('enteredAt is in the future'); + if (!Array.isArray(e.renewals)) return [...p, 'renewals is not a list']; + if (e.renewals.length > 1) p.push(`renewed ${e.renewals.length} times; one renewal is allowed, then fix the test or release it`); + const firstExpiry = e.renewals.length ? Date.parse(e.renewals[0]?.previousExpiresAt) : expires; + if (!(firstExpiry > entered)) p.push('expires before it entered'); + if (firstExpiry - entered > MAX_DAYS * DAY) p.push(`expires more than ${MAX_DAYS} days after it entered`); + for (const r of e.renewals) { + if (!r || typeof r !== 'object') { p.push('a renewal is not an object'); continue; } + const renewed = Date.parse(r.renewedAt); + if (!(renewed >= entered && renewed <= now.getTime() + DAY)) p.push('a renewal is dated before the entry or in the future'); + if (!filled(r?.owner)) p.push('a renewal names no owner'); + if (!filledList(r?.evidence) || r.evidence.every(x => filledList(e.evidence) && e.evidence.includes(x))) p.push('a renewal carries no new evidence'); + const from = Math.max(Date.parse(r?.renewedAt), Date.parse(r?.previousExpiresAt)); + const until = Date.parse(r?.expiresAt); + if (Number.isNaN(from) || Number.isNaN(until) || until - from > RENEW_MAX_DAYS * DAY) p.push(`a renewal is not a date range of at most ${RENEW_MAX_DAYS} days`); + } + const last = e.renewals.at(-1); + if (last && last.expiresAt !== e.expiresAt) p.push('expiresAt differs from the last renewal'); + return p; +} + +export const isLive = (e: QuarantineEntry, now: Date) => Date.parse(e.expiresAt) > now.getTime(); + +/** Ids `run` gives the quarantine budget, plus one notice per entry it ignores (expired or invalid). */ +export function liveQuarantine(reg: Registry, now: Date): { ids: Set<string>; notices: string[] } { + const ids = new Set<string>(); + const notices: string[] = []; + for (const [id, e] of Object.entries(reg.entries)) { + const problems = entryProblems(id, e, now); + if (problems.length) notices.push(`FLAKY_QUARANTINE_IGNORED: ${safeText(id)} is not quarantined: ${problems.join('; ')}`); + else if (!isLive(e, now)) notices.push(expiredNotice(id, e)); + else ids.add(id); + } + return { ids, notices }; +} + +const shq = (s: string) => "'" + s.split("'").join(`'"'"'`) + "'"; +export const renewCommand = (id: string) => `gstack-flaky quarantine renew ${shq(safeText(id))} --owner <you> --evidence <new evidence url>`; +export const releaseCommand = (id: string) => `gstack-flaky quarantine release ${shq(safeText(id))} --reason <why> --pr <fix pr url>`; + +export function expiredNotice(id: string, e: QuarantineEntry): string { + return `FLAKY_QUARANTINE_EXPIRED: ${safeText(id)} expired ${e.expiresAt.slice(0, 10)} and is not quarantined; renew: ${renewCommand(id)} | release: ${releaseCommand(id)}`; +} + +export interface AddInput { owner?: string; ledger?: string; failureClass?: string; reason?: string; evidence: string[]; days?: number; suiteIds: string[] } + +const refuse = (msg: string): never => { throw new QuarantineError('FLAKY_QUARANTINE_REFUSED', msg, 1); }; + +export function addEntry(reg: Registry, id: string, a: AddInput, now: Date): QuarantineEntry { + const days = a.days ?? DEFAULT_DAYS; + if (!Number.isInteger(days) || days < 1 || days > MAX_DAYS) refuse(`--days must be a whole number from 1 to ${MAX_DAYS}, got ${a.days}`); + const cls = classRefusal(a.failureClass); + if (cls) refuse(cls); + if (!a.evidence.length) refuse('no evidence: pass --evidence <url> (a failing run, a ledger line) at least once'); + if (!a.suiteIds.includes(id)) refuse(`${safeText(id)} is not a test in the --junit report (gstack-flaky ids --junit <file> prints the ids)`); + if (reg.entries[id]) refuse(`${safeText(id)} already has an entry; renew or release it`); + const live = Object.values(reg.entries).filter(e => isLive(e, now)).length; + const cap = suiteCap(a.suiteIds.length); + if (live + 1 > cap) refuse(`the registry holds ${live} live entries and the cap for a ${a.suiteIds.length}-test suite is ${cap}; fix or release one first`); + const entry: QuarantineEntry = { + owner: a.owner ?? '', ledger: a.ledger ?? '', failureClass: a.failureClass as FailureClass, reason: a.reason ?? '', evidence: a.evidence, + enteredAt: now.toISOString(), expiresAt: new Date(now.getTime() + days * DAY).toISOString(), renewals: [], suiteTests: a.suiteIds.length, + }; + const problems = entryProblems(id, entry, now); + if (problems.length) refuse(problems.join('; ')); + reg.entries[id] = entry; + return entry; +} + +export function renewEntry(reg: Registry, id: string, r: { owner?: string; evidence: string[]; days?: number }, now: Date): QuarantineEntry { + const e = reg.entries[id] ?? refuse(`${safeText(id)} has no entry to renew`); + if (e.renewals.length) refuse(`${safeText(id)} was renewed once already; a second renewal is refused: fix the test or release it`); + if (!filled(r.owner)) refuse('renew names the owner again: pass --owner'); + if (!r.evidence.some(x => filled(x) && !e.evidence.includes(x))) refuse('renew needs new evidence: pass --evidence <url> not already on the entry'); + const days = r.days ?? RENEW_MAX_DAYS; + if (!Number.isInteger(days) || days < 1 || days > RENEW_MAX_DAYS) refuse(`a renewal is 1 to ${RENEW_MAX_DAYS} days, got ${r.days}`); + const from = Math.max(now.getTime(), Date.parse(e.expiresAt)); + const expiresAt = new Date(from + days * DAY).toISOString(); + e.renewals.push({ renewedAt: now.toISOString(), previousExpiresAt: e.expiresAt, expiresAt, owner: r.owner!, evidence: r.evidence }); + e.expiresAt = expiresAt; + return e; +} + +export function releaseEntry(reg: Registry, id: string, r: { reason?: string; pr?: string }, now: Date): ReleasedEntry { + const e = reg.entries[id] ?? refuse(`${safeText(id)} has no entry to release`); + if (!filled(r.reason) || !filled(r.pr)) refuse('release needs --reason and --pr (the fix, or the decision to stop quarantining)'); + const record: ReleasedEntry = { id, ...e, releasedAt: now.toISOString(), reason: r.reason!, pr: r.pr! }; + reg.released.push(record); + delete reg.entries[id]; + return record; +} + +const liveEntries = (reg: Registry, now: Date) => Object.values(reg.entries).filter(e => e && typeof e === 'object' && isLive(e, now)); +const smallestSuite = (live: QuarantineEntry[]) => Math.min(...live.map(e => e.suiteTests).filter(n => Number.isInteger(n) && n > 0)); + +/** Structural problems of a whole registry plus the cap, for `check`. */ +export function registryProblems(reg: Registry, now: Date, suiteTests?: number): string[] { + const p: string[] = []; + for (const [id, e] of Object.entries(reg.entries)) for (const x of entryProblems(id, e, now)) p.push(`${safeText(id)}: ${x}`); + for (const r of reg.released) { + if (!r || !filled(r.id) || Number.isNaN(Date.parse(r.releasedAt)) || !filled(r.reason) || !filled(r.pr)) p.push(`released record ${JSON.stringify(r?.id)}: needs id, releasedAt, reason and pr`); + } + const live = liveEntries(reg, now); + const tests = suiteTests ?? smallestSuite(live); + if (live.length && Number.isFinite(tests) && live.length > suiteCap(tests)) p.push(`${live.length} live entries, over the cap of ${suiteCap(tests)} for a ${tests}-test suite`); + return p; +} + +const editsFile = (changed: string[], file: string) => changed.some(f => f === file || f.endsWith(`/${file}`)); + +/** What a change did to the registry that `check --base` refuses. */ +export function baseProblems(base: Registry, head: Registry, changed: string[]): string[] { + const p: string[] = []; + for (const [id, e] of Object.entries(head.entries)) { + const was = base.entries[id]; + const t = parseTestId(id); + if (!was) { + if (t && editsFile(changed, t.file)) p.push(`${safeText(id)}: added in the same change that edits ${t.file}; a change cannot quarantine the test it touches (land the entry on its own, or fix the test)`); + continue; + } + if (was.enteredAt !== e?.enteredAt) p.push(`${safeText(id)}: enteredAt changed from ${was.enteredAt}; release the entry instead of restarting it`); + if (JSON.stringify((e?.renewals ?? []).slice(0, was.renewals.length)) !== JSON.stringify(was.renewals)) p.push(`${safeText(id)}: its renewal history was rewritten`); + } + for (const [id, was] of Object.entries(base.entries)) { + if (!(id in head.entries) && !head.released.some(r => r?.id === id && r.enteredAt === was.enteredAt)) p.push(`${safeText(id)}: removed without a release record (use: ${releaseCommand(id)})`); + } + for (const r of base.released) { + if (!head.released.some(h => h?.id === r.id && h.releasedAt === r.releasedAt)) p.push(`${safeText(r.id)}: its release record of ${r.releasedAt} was removed`); + } + return p; +} + +/** `check`: the working-tree registry alone, and with `base` against what this change did since the merge base. */ +export function checkRegistry(cwd: string, o: { base?: string; suiteTests?: number }, now: Date): { problems: string[]; live: number; cap?: number } { + const head = readRegistry(cwd); + const problems = registryProblems(head, now, o.suiteTests); + if (o.base !== undefined) { + const root = repoRoot(cwd); + const commit = resolveCommit(o.base, root); + const mb = git(['merge-base', commit, 'HEAD'], root); + if (!mb.ok) throw new QuarantineError('FLAKY_QUARANTINE_BASE', `no merge base between ${o.base} and HEAD (a shallow clone?)`); + const changed = git(['-c', 'core.quotePath=false', 'diff', '--name-only', '-z', mb.out.trim()], root); + if (!changed.ok) throw new QuarantineError('FLAKY_QUARANTINE_BASE', `cannot diff against the merge base of ${o.base}`); + problems.push(...baseProblems(registryAt(mb.out.trim(), root, `the merge base of ${o.base}`), head, changed.out.split('\0').filter(Boolean))); + } + const live = liveEntries(head, now); + const tests = o.suiteTests ?? smallestSuite(live); + return { problems, live: live.length, ...(Number.isFinite(tests) ? { cap: suiteCap(tests) } : {}) }; +} + +export interface LedgerRecord { ts: string; kind: string; id: string; attempts?: string[] } + +/** Read every JSON line of the given ledger files, and of every .jsonl file under the given directories. */ +export function readLedgers(paths: string[]): { records: LedgerRecord[]; skipped: number } { + const files: string[] = []; + const walk = (p: string) => { + const st = fs.statSync(p, { throwIfNoEntry: false }); + if (!st) throw new QuarantineError('FLAKY_QUARANTINE_USAGE', `--ledger ${p} does not exist`, 2); + if (!st.isDirectory()) { files.push(p); return; } + for (const n of fs.readdirSync(p).sort()) { + const c = path.join(p, n); + if (fs.statSync(c).isDirectory() || n.endsWith('.jsonl')) walk(c); + } + }; + paths.forEach(walk); + const records: LedgerRecord[] = []; + let skipped = 0; + for (const f of files) { + for (const l of fs.readFileSync(f, 'utf-8').split('\n')) { + if (!l.trim()) continue; + try { + const r = JSON.parse(l) as LedgerRecord; + if (filled(r?.id) && filled(r.kind) && filled(r.ts)) records.push(r); else skipped++; + } catch { skipped++; } + } + } + return { records, skipped }; +} + +const cleanPass = (r: LedgerRecord) => r.kind === 'quarantined-pass' && !(r.attempts ?? []).includes('fail'); +const shortKind = (r: LedgerRecord) => cleanPass(r) ? 'pass' : r.kind === 'quarantined-pass' ? 'flaky' : r.kind === 'quarantined-fail' ? 'fail' : r.kind; + +/** `report`: expired entries first, then live entries soonest-expiring first, with ledger history when given. */ +export function reportLines(reg: Registry, now: Date, ledgers?: LedgerRecord[]): string[] { + const out: string[] = []; + const all = Object.entries(reg.entries).sort((a, b) => Date.parse(a[1].expiresAt) - Date.parse(b[1].expiresAt)); + const expired = all.filter(([, e]) => !isLive(e, now)); + const live = all.filter(([, e]) => isLive(e, now)); + for (const [id, e] of expired) out.push(expiredNotice(id, e)); + let expiring = 0, ready = 0; + for (const [id, e] of live) { + const daysLeft = Math.ceil((Date.parse(e.expiresAt) - now.getTime()) / DAY); + if (daysLeft <= 2) expiring++; + let history = ''; + if (ledgers) { + const sid = safeText(id); + const mine = ledgers.filter(r => r.id === sid && Date.parse(r.ts) >= Date.parse(e.enteredAt)).sort((a, b) => Date.parse(a.ts) - Date.parse(b.ts)); + let streak = 0; + for (let i = mine.length - 1; i >= 0 && cleanPass(mine[i]!); i--) streak++; + const isReady = streak >= EXIT_RULE_PASSES; + if (isReady) ready++; + history = ` recent=${mine.slice(-5).map(shortKind).join(',') || 'none'} clean_streak=${streak}${isReady ? ` READY_TO_RELEASE: ${releaseCommand(id)}` : ''}`; + } + const renewal = e.renewals.length ? 'renewed once; fix or release' : `renew: ${renewCommand(id)}`; + out.push(`QUARANTINE: ${safeText(id)} owner=${safeText(e.owner)} class=${e.failureClass} days_left=${daysLeft} expires=${e.expiresAt.slice(0, 10)} ledger=${safeText(e.ledger)}${history}${daysLeft <= 2 ? ` EXPIRING (${renewal})` : ''}`); + } + out.push(`QUARANTINE_REPORT: live=${live.length} expired=${expired.length} expiring=${expiring} ready=${ledgers ? ready : 'unchecked'} exit_rule=${ledgers ? `checked (${EXIT_RULE_PASSES} consecutive clean passes)` : 'not checked (no --ledger given)'}`); + return out; +} + +export const QUARANTINE_USAGE = `Usage: + gstack-flaky quarantine add <id> --owner <who> --ledger <url> --class detector|harness|timing|model-latency + --reason <text> --evidence <url> [--evidence <url>...] --junit <file> [--runner <r>] [--days <1-${MAX_DAYS}>] + gstack-flaky quarantine renew <id> --owner <who> --evidence <new url> [--days <1-${RENEW_MAX_DAYS}>] + gstack-flaky quarantine release <id> --reason <text> --pr <url> + gstack-flaky quarantine check [--base <ref>] [--junit <file>] + gstack-flaky quarantine report [--ledger <file|dir>...] [--base <ref>] + +add/renew/release edit ${REGISTRY_PATH} at the repository root. check validates it +(owner, ledger, class, evidence, expiry, one renewal, the cap) and, with --base, +refuses an entry added in the change that edits its test's file, an entry removed +without a release record, and a removed release record. report lists expired and +live entries, soonest-expiring first; with --ledger (files or directories of +downloaded ledgers) it shows recent outcomes and marks entries with ${EXIT_RULE_PASSES} +consecutive clean passes READY_TO_RELEASE. +Exit: 0 ok, 1 refused, 2 usage, 3 unreadable registry or base. +`; + +interface CliIO { cwd: string; out: (s: string) => void; now: Date } + +const usage = (msg: string): never => { throw new QuarantineError('FLAKY_QUARANTINE_USAGE', msg, 2); }; + +function parseArgs(argv: string[]) { + const flags: Record<string, string[]> = {}; + const positional: string[] = []; + for (let i = 0; i < argv.length; i++) { + const a = argv[i]!; + if (!a.startsWith('--')) { positional.push(a); continue; } + const v = argv[++i]; + if (v === undefined) usage(`${a} needs a value`); + (flags[a.slice(2)] ??= []).push(v!); + } + return { flags, positional }; +} + +function intFlag(v: string | undefined, name: string): number | undefined { + if (v === undefined) return undefined; + const n = Number(v); + if (!Number.isInteger(n)) usage(`--${name} must be a whole number`); + return n; +} + +const ALLOWED: Record<string, string[]> = { + add: ['owner', 'ledger', 'class', 'reason', 'evidence', 'junit', 'runner', 'days'], renew: ['owner', 'evidence', 'days'], + release: ['reason', 'pr'], check: ['base', 'junit', 'runner'], report: ['ledger', 'base'], +}; + +/** The `gstack-flaky quarantine` subcommands; returns the exit code. A JunitError from --junit propagates to the bin. */ +export function quarantineMain(argv: string[], io: CliIO): number { + const [sub, ...rest] = argv; + if (!sub || sub === '--help' || sub === '-h') { io.out(QUARANTINE_USAGE); return sub ? 0 : 2; } + if (!ALLOWED[sub]) usage(`unknown quarantine command ${sub}\n${QUARANTINE_USAGE}`); + const { flags, positional } = parseArgs(rest); + const unknown = Object.keys(flags).find(f => !ALLOWED[sub]!.includes(f)); + if (unknown) usage(`${sub} does not take --${unknown}`); + const one = (f: string) => flags[f]?.at(-1); + const runner = one('runner') as JunitRunner | undefined; + if (runner !== undefined && !['playwright', 'bun', 'generic'].includes(runner)) usage('--runner must be playwright, bun or generic'); + const needsId = sub === 'add' || sub === 'renew' || sub === 'release'; + if (needsId !== (positional.length === 1) || positional.length > 1) usage(needsId ? `${sub} takes one test id` : `${sub} takes no test id`); + if (sub === 'check') { + const junit = one('junit'); + const r = checkRegistry(io.cwd, { base: one('base'), suiteTests: junit ? readJunit(junit, runner).tests.length : undefined }, io.now); + for (const p of r.problems) io.out(`QUARANTINE_REFUSED: ${p}\n`); + io.out(`QUARANTINE_CHECK: live=${r.live} cap=${r.cap ?? 'none'} base=${one('base') ?? 'none'} verdict=${r.problems.length ? 'fail' : 'pass'}\n`); + return r.problems.length ? 1 : 0; + } + if (sub === 'report') { + const ledgers = flags.ledger ? readLedgers(flags.ledger) : undefined; + if (ledgers?.skipped) io.out(`QUARANTINE_LEDGER: skipped ${ledgers.skipped} unreadable line(s)\n`); + for (const l of reportLines(readRegistry(io.cwd, one('base')), io.now, ledgers?.records)) io.out(`${l}\n`); + return 0; + } + const id = positional[0]!; + const reg = readRegistry(io.cwd); + let line: string; + if (sub === 'add') { + const junit = one('junit') ?? refuse('add needs --junit <file> to count the suite and confirm the id exists'); + const suiteIds = readJunit(junit, runner).tests.map(t => t.id); + const e = addEntry(reg, id, { owner: one('owner'), ledger: one('ledger'), failureClass: one('class'), reason: one('reason'), evidence: flags.evidence ?? [], days: intFlag(one('days'), 'days'), suiteIds }, io.now); + line = `QUARANTINE_ADDED: ${safeText(id)} owner=${safeText(e.owner)} class=${e.failureClass} expires=${e.expiresAt}`; + } else if (sub === 'renew') { + const e = renewEntry(reg, id, { owner: one('owner'), evidence: flags.evidence ?? [], days: intFlag(one('days'), 'days') }, io.now); + line = `QUARANTINE_RENEWED: ${safeText(id)} owner=${safeText(e.renewals[0]!.owner)} expires=${e.expiresAt} (no further renewal)`; + } else { + const r = releaseEntry(reg, id, { reason: one('reason'), pr: one('pr') }, io.now); + line = `QUARANTINE_RELEASED: ${safeText(id)} pr=${safeText(r.pr)}`; + } + writeRegistry(io.cwd, reg); + io.out(`${line} registry=${REGISTRY_PATH}\n`); + return 0; +} diff --git a/package.json b/package.json index 60880d218..312e37851 100644 --- a/package.json +++ b/package.json @@ -1,6 +1,6 @@ { "name": "gstack", - "version": "1.93.9", + "version": "1.93.10", "description": "Garry's Stack — Claude Code skills + fast headless browser. One repo, one install, entire AI engineering workflow.", "license": "MIT", "type": "module", diff --git a/scripts/harness-version.json b/scripts/harness-version.json index 8385511f3..a4bbf78c8 100644 --- a/scripts/harness-version.json +++ b/scripts/harness-version.json @@ -13,21 +13,21 @@ "files": { "scripts/lib/paid-cases.ts": {"blob":"f862cf5241580c7593b9ee62eacf5ef046248d26","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"}, "scripts/lib/paid-plan.ts": {"blob":"e8ce3cb98474dded38c5128a631d283b0ca35b63","since":6,"nonBehavioral":"F1 rule-16 flaky rerun: report aggregation, rerun planning and the gate slice exit code; no case's execution, trial outcome, trial record or panel verdict changes, so no pass-rate series resets"}, - "scripts/lib/paid-report.ts": {"blob":"224dc5e8ba23a3589a37bad94db72ed1ca3c7c77","since":6,"nonBehavioral":"a case shard's result records are attributed to its one case: the trial's cost_usd and cost_known come from them, and a failed trial's failure_class, exit_reason and error come from its record instead of a bare assertion with the JUnit message, so a red whose record says infra or timeout is classed by that record (INFRA instead of VERDICT: rerun and bisect eligibility, not a pass rate); no case's outcome or selection changes and pass rates count outcomes only, so no pass-rate series resets"}, + "scripts/lib/paid-report.ts": {"blob":"e0d18da4ea02ac443835a68992abeea2b47f22fc","since":6,"nonBehavioral":"the headline adds only streamed session cost; a billed session's cost is already in its collector total; cache writes without a 5m key fall back to the total minus 1h; cost fields only"}, "scripts/lib/published-text.ts": {"blob":"3f2e4d616b5dd0204035710c66b64d49055c5714","since":6}, "scripts/lib/shard-engine.ts": {"blob":"dc714d7d897aed185c0ec3d2c92ad22d954039e5","since":6,"nonBehavioral":"createShardSandbox drops the Capy launch markers (GSTACK_SESSION_KIND, GSTACK_CAPY, GSTACK_EPHEMERAL, GSTACK_INSTALL_VERDICT) from shard environments; CI never sets them, so no case's input or verdict changes there, and on a Capy machine fixtures now see the session kind they set themselves instead of the installer's"}, "scripts/test-paid-shards.ts": {"blob":"5439d0a8f6e1569fa7c924af20d67c30c81d5d30","since":6,"nonBehavioral":"credential rejections are classed infra instead of assertion: no case's pass or fail changes; only failed trials whose provider rejected the run's key move class, so no rerun spends on a rejected key"}, "scripts/test-pr-profile.ts": {"blob":"44ae88bebf8f716f70a3bd836c8bedb03e6653e8","since":6,"nonBehavioral":"FREE_ONLY_PR_FILES gains scripts/lib/shard-jobs.ts (free-runner module) and .github/workflows/windows-smoke.yml (a workflow no paid case reads); both change only which PR paths select paid cases, never how a case runs or is judged"}, "scripts/test-strict-output.ts": {"blob":"01185d20dc9761b04b9b2f751ec98664fe0eaf93","since":6}, - "test/helpers/agent-sdk-runner.ts": {"blob":"210bba92d241a90df578b2c7fc943ac5755d0025","since":6}, + "test/helpers/agent-sdk-runner.ts": {"blob":"d66dac458b8c13250973e550edf8087d4044cd0b","since":6,"nonBehavioral":"Cost attribution only (GSTA-150 PR 2): a display-label record carries cost_case_id from runSkillTest's testName and the report binds its cost by it while the failed record and failure class still come from the named records (test/paid-report-cost.test.ts pins both); an aborted Agent SDK session logs its streamed usage as streamed_cost_usd, used only when a case has no record; a listed model-free case with no record or session is a known $0. No case's execution, outcome, failure class, rerun eligibility or panel verdict changes, so no pass-rate series resets. Also: runAgentSdkTest now validates systemPrompt before starting; every live caller already passed the claude_code preset, so the prompt the model sees is unchanged and no verdict can change"}, "test/helpers/auq-substance-panel.ts": {"blob":"4881260ef793668e4963a062db6d06a5e1f7a40f","since":6}, "test/helpers/claude-pty-runner.ts": {"blob":"ce7a5eaa66e502a052ea9c53348dd2ab25db6148","since":6,"nonBehavioral":"Removes the plan-design 0D focus picker from the shared harness; floor.ts gains an optional pickSetupChoice hook that no other caller passes, so no other case's input or verdict can change. plan-design-finding-floor, the only case whose seed raises that menu, passes the picker from its owned fixture test/fixtures/design-floor-focus-picker.ts, so its owned bytes start its own new series."}, "test/helpers/codex-host-runner.ts": {"blob":"bff225017e235f0be6ece29f04971ac04b95b544","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"}, "test/helpers/codex-session-runner.ts": {"blob":"c040ebbfa815b8cce19ef80c6133bd5a5474149a","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"}, "test/helpers/e2e-gate.ts": {"blob":"efb7e197dd5f66c3ad0e34074b14e640754f7a45","since":6}, - "test/helpers/e2e-helpers.ts": {"blob":"6ee6937e6c3ca081c77131b5a755278c7b714834","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"}, + "test/helpers/e2e-helpers.ts": {"blob":"91996ff2bc303ee29f4e6f1705d1468b2536b32e","since":6,"nonBehavioral":"Cost attribution only (GSTA-150 PR 2): a display-label record carries cost_case_id from runSkillTest's testName and the report binds its cost by it while the failed record and failure class still come from the named records (test/paid-report-cost.test.ts pins both); an aborted Agent SDK session logs its streamed usage as streamed_cost_usd, used only when a case has no record; a listed model-free case with no record or session is a known $0. No case's execution, outcome, failure class, rerun eligibility or panel verdict changes, so no pass-rate series resets"}, "test/helpers/eval-budgets.ts": {"blob":"667d0e09b20fe5d7366f57b77b5fb9b04baa37ef","since":6}, - "test/helpers/eval-store.ts": {"blob":"a50ea2c28f508ad9f35ea9353dd2f502ee0dcfc2","since":6,"nonBehavioral":"credential rejections are classed infra instead of assertion: no case's pass or fail changes; only failed trials whose provider rejected the run's key move class, so no rerun spends on a rejected key"}, + "test/helpers/eval-store.ts": {"blob":"4085ad18cd99698f675deadad2a76a796427b693","since":6,"nonBehavioral":"Cost attribution only (GSTA-150 PR 2): a display-label record carries cost_case_id from runSkillTest's testName and the report binds its cost by it while the failed record and failure class still come from the named records (test/paid-report-cost.test.ts pins both); an aborted Agent SDK session logs its streamed usage as streamed_cost_usd, used only when a case has no record; a listed model-free case with no record or session is a known $0. No case's execution, outcome, failure class, rerun eligibility or panel verdict changes, so no pass-rate series resets"}, "test/helpers/hermetic-env.ts": {"blob":"cc072895461dc52ea317d1beff72121342420d30","since":6}, "test/helpers/llm-judge.ts": {"blob":"f14ca0db6504480698acd662351b6f0d6ef31a7b","since":6,"nonBehavioral":"llm-judge.ts adds a pass-through byte counter (bytesReceived, lastByteMs) to the aborted-judge diagnostic; the request, response bytes, deadline and scoring are unchanged"}, "test/helpers/paid-test-set.ts": {"blob":"ff9bfe43c43ec2bdd11114f7b8ec7c5736116f75","since":6}, @@ -38,16 +38,17 @@ "test/helpers/pty/classify.ts": {"blob":"3f2daa12ff6484f96b8d28d910a50231c4bb3ae8","since":6}, "test/helpers/pty/fake-session.ts": {"blob":"554e064ef259b8444280eddfe9b0db93c66a8202","since":6}, "test/helpers/pty/judge.ts": {"blob":"81c5bb4c48ab928aca2f186a1ade9df7169d7fbe","since":6}, - "test/helpers/pty/launch.ts": {"blob":"e4413de380b799659170e7da248d51afda3b0e3f","since":6,"nonBehavioral":"credential rejections are classed infra instead of assertion: no case's pass or fail changes; only failed trials whose provider rejected the run's key move class, so no rerun spends on a rejected key"}, + "test/helpers/pty/launch.ts": {"blob":"4f0731ef39bc3a6a7c5c592ce98690a24cb1ed7f","since":6,"nonBehavioral":"PTY transcript pricing finds the session by the caller's --session-id or the one new transcript for the launch cwd; the launcher adds no argument; native AUQ capture opts out; ledger cost fields only, no prompt, argv, answer, timeout or verdict changes"}, "test/helpers/pty/plan-native.ts": {"blob":"ddba9cb68c7c0da935cff7c1cea258dee2dff740","since":6}, "test/helpers/pty/runners/counting.ts": {"blob":"8c5c05e54abf961259d34d9c3d77db67138d7794","since":6}, "test/helpers/pty/runners/floor.ts": {"blob":"a9938cb98f285474ebc4860cd61012504a36466e","since":6,"nonBehavioral":"The PTY floor and observation runners end a plan-mode turn at an idle prompt (the plan-mode footer without its running 'esc to interrupt' segment, after a 10 s settle) instead of waiting out the deadline. The floor runner exits as api_error only after the idle screen with its error panel held still for 10 s and every tick's question and assessment steps found nothing to credit (the transcript is re-read each tick), so a native or prose question already on screen is credited as before, even when its transcript line lands after the screen draws done (test/helpers/claude-pty-runner.runners.unit.test.ts, the prose-question-before-panel case). With no qualifying question an idle turn stays idle, so a trial that failed at the deadline as observer_timeout now fails earlier as api_error. An observation returns what the deadline would have returned. A running footer, extra footer text and a cut footer still wait for the deadline. No pass becomes a fail or a fail a pass. The session ledger may now record failure_cause api_error or refusal instead of observer_timeout or session_timeout for a plan-mode session whose last idle turn shows a panel; failure_class, the gate red class and pass rates are unchanged, so no pass-rate series resets"}, "test/helpers/pty/runners/observation.ts": {"blob":"1c2b75fbb984708725abaa8939125f7cab969f9f","since":6}, "test/helpers/pty/screen.ts": {"blob":"1384f765e48e511d5f843df2660b2ec70bbcb6b2","since":6,"nonBehavioral":"The PTY floor and observation runners end a plan-mode turn at an idle prompt (the plan-mode footer without its running 'esc to interrupt' segment, after a 10 s settle) instead of waiting out the deadline. The floor runner exits as api_error only after the idle screen with its error panel held still for 10 s and every tick's question and assessment steps found nothing to credit (the transcript is re-read each tick), so a native or prose question already on screen is credited as before, even when its transcript line lands after the screen draws done (test/helpers/claude-pty-runner.runners.unit.test.ts, the prose-question-before-panel case). With no qualifying question an idle turn stays idle, so a trial that failed at the deadline as observer_timeout now fails earlier as api_error. An observation returns what the deadline would have returned. A running footer, extra footer text and a cut footer still wait for the deadline. No pass becomes a fail or a fail a pass. The session ledger may now record failure_cause api_error or refusal instead of observer_timeout or session_timeout for a plan-mode session whose last idle turn shows a panel; failure_class, the gate red class and pass rates are unchanged, so no pass-rate series resets"}, - "test/helpers/pty/session.ts": {"blob":"54fe04b61d953e4e55e2fc251532c04a49fab66f","since":6,"nonBehavioral":"credential rejections are classed infra instead of assertion: no case's pass or fail changes; only failed trials whose provider rejected the run's key move class, so no rerun spends on a rejected key"}, + "test/helpers/pty/session.ts": {"blob":"8fd1749a62f24dc37ae186c8a21c2165f7f7645e","since":6,"nonBehavioral":"PTY sessions price their ledger row (streamed_cost_usd) from the session transcript found by the caller's --session-id or the one new transcript for the launch cwd; ledger cost fields only, no prompt, argv, answer, timeout or verdict changes"}, + "test/helpers/pty/transcript-cost.ts": {"blob":"08f7ccbdbd9d71a5dc86edd2f8fced423a78ad9a","since":6,"nonBehavioral":"PTY transcript pricing finds the session by the caller's --session-id or the one new transcript for the launch cwd; the launcher adds no argument; native AUQ capture opts out; ledger cost fields only, no prompt, argv, answer, timeout or verdict changes"}, "test/helpers/session-drain-policy.ts": {"blob":"6211239dd0485e6495a700b824a7e0e61d1bcd97","since":6}, - "test/helpers/session-ledger.ts": {"blob":"a10bf28bf100f135b93c73818670dd147253cdd3","since":6,"nonBehavioral":"credential rejections are classed infra instead of assertion: no case's pass or fail changes; only failed trials whose provider rejected the run's key move class, so no rerun spends on a rejected key"}, - "test/helpers/session-runner.ts": {"blob":"cc65a66adafa9c053e3da3c6f17b5ac86c0eade7","since":6,"nonBehavioral":"Claude-host verdicts are unchanged: the Codex host (EVALS_HOST=codex, codex-host-runner) runs only when selected and records its own per-model series; the Codex runner refactor (execCodex extraction, onSpawn hook) keeps its events and verdicts and adds token cost accounting; host fields on the plan/report are absent for claude"}, + "test/helpers/session-ledger.ts": {"blob":"c99baaaa0a77a5a72384493fd8a85a4253ecb05d","since":6,"nonBehavioral":"PTY sessions price their ledger row (streamed_cost_usd) from the session transcript found by the caller's --session-id or the one new transcript for the launch cwd; ledger cost fields only, no prompt, argv, answer, timeout or verdict changes"}, + "test/helpers/session-runner.ts": {"blob":"c73b2596d9eb5377530a6bf1d284e0b6ea1556a0","since":6,"nonBehavioral":"Cost attribution only (GSTA-150 PR 2): a display-label record carries cost_case_id from runSkillTest's testName and the report binds its cost by it while the failed record and failure class still come from the named records (test/paid-report-cost.test.ts pins both); an aborted Agent SDK session logs its streamed usage as streamed_cost_usd, used only when a case has no record; a listed model-free case with no record or session is a known $0. No case's execution, outcome, failure class, rerun eligibility or panel verdict changes, so no pass-rate series resets"}, "test/helpers/skill-fixture.ts": {"blob":"8a654dae6b0a396d839b02179119ae3e3bb13f69","since":6,"nonBehavioral":"extractSkillBody and extractSkillSections follow the shared-preamble hoist (pointer plus sections/preamble.md); every fixture they build is byte-identical to the pre-hoist output (compared for 8 body and 4 section extractions), so no case's input or verdict changes; the /ship review then reworded only comments and two error messages, so no fixture byte changes"}, "test/helpers/skill-startup.ts": {"blob":"a8d21e3817c3f35a1d06af325c92fde7d420e377","since":6,"nonBehavioral":"readSkillEffective also appends a variant's added ### subsections (office-hours' Open-ended questions); readSkillStartup, readSharedSections and readSkillEffective return bytes identical to the pinned helper for every tier 2+ render without added subsections (735 across all hosts) and for office-hours' SKILL.md before this PR, so office-hours' fixture input changes only because its prompt changed in this PR, not because the helper did"}, "test/helpers/test-selection.ts": {"blob":"e1b54ad5e3d3eadd8027de1b44e57554d6d99a41","since":6,"nonBehavioral":"selection only: fragment exemption narrowed to .md files directly in the fragments dir; changed-file lists include a rename's old path; no case prompt, fixture, judge or verdict logic changes (GST-400)"}, diff --git a/scripts/lib/paid-report.ts b/scripts/lib/paid-report.ts index 224dc5e8b..e0d18da4e 100644 --- a/scripts/lib/paid-report.ts +++ b/scripts/lib/paid-report.ts @@ -9,7 +9,7 @@ import { STALL_WINDOW_MS } from '../../test/helpers/eval-budgets'; import { isFinalizedEvalResultFile, credentialRejection, failureClassOf, panelVerdict, sanitizeTrialError, formatTrialOutcomes, TRIAL_OUTCOME_SCHEMA, TRIAL_OUTCOMES_FILE, type EvalCaseKind, type PanelVerdict, type TrialFailureClass, type TrialOutcome, type TrialOutcomeRecord, - trialCostKnown, trialFailureFields, trialSessions, type TrialFailureDetail, + trialFailureFields, trialSessions, type TrialFailureDetail, } from '../../test/helpers/eval-store'; import { readSessionLedger, type SessionLedgerRow } from '../../test/helpers/session-ledger'; import { publishedFence, sanitizeFixedFenceLine } from './published-text'; @@ -230,6 +230,8 @@ export interface JUnitCensus { deselected: Map<string, number>; /** Per shard key: skip reason -> skipped testcase count. */ shardSkipReasons: Map<string, Map<string, number>>; + /** Streamed session cost (sessions without a terminal result), which no collector record carries; the headline adds it to the collectors' total_cost_usd. */ + ledgerCostUsd: number; /** `<shard key> :: <test name> (<outcome>)` for every testcase no rule attributes. */ unattributed: string[]; } @@ -241,6 +243,24 @@ function caseSessions(rows: SessionLedgerRow[], id: string, onlyCase: boolean): return rows.filter(row => row.case === id || (!row.case && (onlyCase || row.test_name === id || row.test_name === CASE_TEST_NAMES[id]))); } +/** Cases that run no model (a binary data flow): with no record and no session they cost a known $0. test/paid-report-cost.test.ts pins each body model-free. */ +export const MODEL_FREE_CASES: ReadonlySet<string> = new Set(['timeline-event-flow']); + +/** + * A trial's cost: its records' sum plus what no record carries, a session without a terminal result priced from its + * streamed usage (streamed_cost_usd). With no record, a billed session counts its own cost_usd (Codex). Unknown when any + * record or session cost is; a listed model-free case with neither record nor session is a known $0. + */ +export function caseCost(id: string, records: any[], sessions: SessionLedgerRow[]): { cost_usd: number; cost_known?: false } { + if (!records.length && !sessions.length) return MODEL_FREE_CASES.has(id) ? { cost_usd: 0 } : { cost_usd: 0, cost_known: false }; + const unrecorded = sessions.map(s => s.billed !== false ? (records.length ? 0 : s.cost_usd) : s.streamed_cost_usd); + const known = records.every(r => r?.cost_known !== false) && unrecorded.every(c => typeof c === 'number' && Number.isFinite(c)); + const total = records.reduce((sum, r) => sum + (Number(r?.cost_usd) || 0), 0) + knownSum(unrecorded); + return { cost_usd: Math.round(total * 100) / 100, ...(known ? {} : { cost_known: false as const }) }; +} + +const knownSum = (costs: Array<number | undefined>) => costs.reduce<number>((sum, c) => sum + (typeof c === 'number' && Number.isFinite(c) ? c : 0), 0); + /** The artifact holding a slice's shards: the downloaded directory's own name when it is one. */ /** The red-census guide the report and every eval:pass-rates view link. */ export const CENSUS_RED_GUIDE = 'docs/evals/census-red.md'; @@ -252,7 +272,8 @@ export function sliceArtifactName(root: string, slice: number, attempt: number): export function junitCensus(manifest: PaidRunManifest, artifacts: ReportArtifact[], recordsByShard: Map<string, any[]>, base: Record<string, unknown>, cliVersion?: string): JUnitCensus { - const census: JUnitCensus = { ruleCases: [], history: [], failedShards: new Set(), skipped: [], deselected: new Map(), shardSkipReasons: new Map(), unattributed: [] }; + const census: JUnitCensus = { ruleCases: [], history: [], failedShards: new Set(), skipped: [], deselected: new Map(), shardSkipReasons: new Map(), unattributed: [], + ledgerCostUsd: 0 }; const entries = new Map(manifest.entries.map(entry => [normalizeRelativePath(entry.file), entry])); for (const { root, result } of artifacts) { for (const outcome of result.outcomes) { @@ -277,11 +298,15 @@ export function junitCensus(manifest: PaidRunManifest, artifacts: ReportArtifact const caseOutcome: TrialOutcome = failed ? 'failed' : cases.some(tc => tc.outcome === 'passed') ? 'passed' : 'skipped'; // A record is named by its case id or carries case_id; an E2E record named by its display label ("/qa fix loop") is // the shard's only case's when the shard ran one case, else it stays unattributed and the trial's cost unknown. - const mine = records.filter((r: any) => r?.name === id || r?.case_id === id || (byCase.size === 1 && !r?.case_id)); - const failedRecord = mine.find((r: any) => r.passed === false); + // A display-label record whose runSkillTest testName is this case (cost_case_id) adds its cost only: the failed record stays the named one. + const named = records.filter((r: any) => r?.name === id || r?.case_id === id || (byCase.size === 1 && !r?.case_id)); + const mine = [...named, ...records.filter((r: any) => r?.cost_case_id === id && !named.includes(r) && !byCase.has(r?.name))]; + const failedRecord = named.find((r: any) => r.passed === false); const recorded: TrialFailureClass | undefined = !failed ? undefined : failed.failureType === 'TimeoutError' ? 'timeout' : failedRecord ? failureClassOf(failedRecord) : 'assertion'; const sessions = caseSessions(ledger, id, byCase.size === 1); + const cost = caseCost(id, mine, sessions); + census.ledgerCostUsd += knownSum(sessions.map(s => s.billed === false ? s.streamed_cost_usd : 0)); const credentials = failed && recorded !== 'contract' ? credentialRejection({ error: `${failedRecord?.error ?? ''}\n${failed.message ?? ''}`, sessions }) : undefined; const failureClass = credentials ? 'infra' : recorded; const rawError = credentials ? `credentials rejected: ${credentials}` : failedRecord?.error ?? failed?.message; @@ -295,7 +320,7 @@ export function junitCensus(manifest: PaidRunManifest, artifacts: ReportArtifact census.skipped.push(`◌ ${id} ${key} (${cases.map(tc => tc.name).join('; ')}): ${RUNTIME_SKIP_REASON}`); } census.ruleCases.push({ id, kind, outcome: caseOutcome, key, slice: result.sliceIndex, ...(failureClass ? { failureClass } : {}), ...(error && failed ? { error } : {}), - costUsd: Math.round(mine.reduce((sum: number, r: any) => sum + (Number(r.cost_usd) || 0), 0) * 100) / 100, costKnown: trialCostKnown(mine, sessions).cost_known !== false, + costUsd: cost.cost_usd, costKnown: cost.cost_known !== false, ...(failed ? { line: `✗ ${id} ${kind} FAIL ${failureClass}${failedRecord?.exit_reason === 'timeout' && failedRecord?.timeout_at_turn !== undefined ? ` at turn ${failedRecord.timeout_at_turn}` : ''}${error ? ` — ${error}` : ''}` + `${diagnosisText(diagnosis, error)} [slice ${result.sliceIndex}, attempt ${result.attempt ?? 1}]` + `${evidencePointer(sliceArtifactName(root, result.sliceIndex, result.attempt ?? 1), key, typeof base.run_id === 'string' ? base.run_id : undefined, id)}` @@ -303,8 +328,8 @@ export function junitCensus(manifest: PaidRunManifest, artifacts: ReportArtifact census.history.push({ ...base, case: id, file: shardFile(key), kind, trial: 1, panel: { n: 1, k: 1 }, outcome: caseOutcome, ...(failureClass ? { failure_class: failureClass } : {}), ...(failedRecord?.exit_reason ? { exit_reason: String(failedRecord.exit_reason) } : {}), ...(error && failed ? { error } : {}), ...diagnosis, ...trialSessions(sessions), duration_ms: Math.min(cases.reduce((sum, tc) => sum + tc.timeMs, 0), outcome.elapsedMs), - cost_usd: Math.round(mine.reduce((sum: number, r: any) => sum + (Number(r.cost_usd) || 0), 0) * 100) / 100, ...trialCostKnown(mine, sessions), - ...(typeof mine[0]?.model === 'string' ? { model: mine[0].model } : {}), ...(cliVersion ? { cli_version: cliVersion } : {}), + ...cost, + ...(typeof named[0]?.model === 'string' ? { model: named[0].model } : {}), ...(cliVersion ? { cli_version: cliVersion } : {}), quarantined: false, execution: outcome.reused ? 'reused' : 'executed', source: 'junit' } as TrialOutcomeRecord); } census.shardSkipReasons.set(key, reasons); @@ -776,7 +801,7 @@ export function runPaidReport(reportDir: string, options: { writeDurations?: boo ...(spend.executions ? { reruns: spend } : {}), actionRequired: verdict.problems.length, wallMs: wall.length ? Math.max(...wall.map(r => r.finishedAt!)) - Math.min(...wall.map(r => r.startedAt!)) : null, - costUsd: Math.round(costUsd * 100) / 100, + costUsd: Math.round((costUsd + census.ledgerCostUsd) * 100) / 100, redispatchEligible: red && infraOnly(verdict.problems), }; const executed = history.filter(r => r.attempt === primary && r.execution === 'executed' && r.outcome !== 'skipped'); diff --git a/scripts/preflight-agent-sdk.ts b/scripts/preflight-agent-sdk.ts index a62ee6ddd..b530532c8 100644 --- a/scripts/preflight-agent-sdk.ts +++ b/scripts/preflight-agent-sdk.ts @@ -21,6 +21,7 @@ import '../lib/conductor-env-shim'; import { query, type SDKMessage } from '@anthropic-ai/claude-agent-sdk'; import { readOverlay } from './resolvers/model-overlay'; import { resolveClaudeBinary } from '../lib/claude-bin'; +import { sdkSystemPrompt } from '../test/helpers/sdk-system-prompt'; const USAGE = `Usage: bun run scripts/preflight-agent-sdk.ts [--live] @@ -94,7 +95,7 @@ async function main() { prompt: 'say pong', options: { model: 'claude-opus-4-7', - systemPrompt: '', + ...sdkSystemPrompt({ type: 'sdk-default', reason: 'connectivity probe with no tools: checks the event stream shape, not skill behavior' }), tools: [], permissionMode: 'bypassPermissions', allowDangerouslySkipPermissions: true, diff --git a/test/agent-sdk-runner.test.ts b/test/agent-sdk-runner.test.ts index 78e2ea675..f3937dd5d 100644 --- a/test/agent-sdk-runner.test.ts +++ b/test/agent-sdk-runner.test.ts @@ -213,7 +213,7 @@ function makeStubProvider(config: StubConfig): QueryProvider { } const BASE_OPTS = { - systemPrompt: '', + systemPrompt: { type: 'sdk-default', reason: 'stub queryProvider: no model reads the prompt' } as const, userPrompt: 'test prompt', workingDirectory: '/tmp/test-dir', maxRetries: 3, @@ -416,7 +416,7 @@ describe('runAgentSdkTest — options propagation', () => { calls: [], }; await runAgentSdkTest({ - systemPrompt: 'you are a test overlay', + systemPrompt: { type: 'custom', text: 'you are a test overlay', reason: 'checks that custom text reaches query()' }, userPrompt: 'go', workingDirectory: '/tmp/spec-dir', model: 'claude-opus-4-7', @@ -451,7 +451,7 @@ describe('runAgentSdkTest — options propagation', () => { expect(opts.pathToClaudeCodeExecutable).toBe('/fake/path/claude'); }); - test('empty systemPrompt means no systemPrompt option passed', async () => { + test('an sdk-default systemPrompt passes no systemPrompt option', async () => { freshSem(); const stub: StubConfig = { streams: [[systemInit(), assistantTurn([{ type: 'text', text: 'ok' }]), resultSuccess()]], @@ -461,7 +461,6 @@ describe('runAgentSdkTest — options propagation', () => { ...BASE_OPTS, queryProvider: makeStubProvider(stub), }); - // systemPrompt is undefined when empty string passed (so SDK uses no override) expect(stub.calls[0]!.options!.systemPrompt).toBeUndefined(); }); }); diff --git a/test/fixtures/context-budget.json b/test/fixtures/context-budget.json index 619885589..48a84e702 100644 --- a/test/fixtures/context-budget.json +++ b/test/fixtures/context-budget.json @@ -25,7 +25,7 @@ "diagram": 4286, "document-generate": 6013, "document-release": 4454, - "eval-plan": 5021, + "eval-plan": 5107, "freeze": 1115, "gstack": 5350, "gstack-upgrade": 6297, diff --git a/test/flaky-run.test.ts b/test/flaky-run.test.ts index c890b5883..cd8f2e5b8 100644 --- a/test/flaky-run.test.ts +++ b/test/flaky-run.test.ts @@ -160,7 +160,7 @@ describe('runFlaky', () => { expect(r.outcomes.map(o => [o.status, o.attempts.join(',')])).toEqual([['flaky-pass', 'fail,pass']]); expect(r.ledger).toHaveLength(1); expect(r.ledger[0]).toMatchObject({ kind: 'flaky-pass', id: 'a.test.ts::::b', rerun_by: 'gstack-flaky', attempts: ['fail', 'pass'], excerpt: ['boom'] }); - expect(renderResult(r, '/l.jsonl').at(-1)).toBe('FLAKY_RESULT: tests=2 failed=0 flaky=1 reruns=1 command_exit=1 verdict=pass ledger=/l.jsonl'); + expect(renderResult(r, '/l.jsonl').at(-1)).toBe('FLAKY_RESULT: tests=2 failed=0 flaky=1 quarantined=0 reruns=1 command_exit=1 verdict=pass ledger=/l.jsonl'); expect(stepSummary(r)).toContain('a.test.ts::::b'); }); diff --git a/test/helpers/agent-sdk-runner.ts b/test/helpers/agent-sdk-runner.ts index 210bba92d..d66dac458 100644 --- a/test/helpers/agent-sdk-runner.ts +++ b/test/helpers/agent-sdk-runner.ts @@ -37,6 +37,8 @@ import * as fs from 'fs'; import * as path from 'path'; import { resolveClaudeBinary as resolveClaudeBinaryShared } from '../../lib/claude-bin'; import { resolveEvalModel } from '../../lib/eval-model'; +import { streamedUsageCostUsd } from '../../lib/pricing'; +import { sdkSystemPrompt, type SystemPromptOption } from './sdk-system-prompt'; import { SessionObserver, appendSessionLedger, sessionKey, type SessionEnd } from './session-ledger'; import { hermeticChildEnv } from './hermetic-env'; import type { SkillTestResult } from './session-runner'; @@ -74,18 +76,15 @@ export interface AgentSdkResult { /** Signature matching `query()` from the SDK. DI hook for unit tests. */ export type QueryProvider = typeof query; -/** Subset of SDK Options['systemPrompt'] we support. */ -export type SystemPromptOption = - | string - | { type: 'preset'; preset: 'claude_code'; append?: string; excludeDynamicSections?: boolean }; +export type { SystemPromptOption }; export interface RunAgentSdkOptions { /** - * System prompt surface. - * - bare string "" -> omit entirely (SDK default: no system prompt) - * - bare string "...text..." -> REPLACE default with given text (use sparingly) + * System prompt surface (test/helpers/sdk-system-prompt.ts). * - { type:'preset', preset:'claude_code' } -> use Claude Code default * - { type:'preset', preset:'claude_code', append: "..." } -> default + append + * - { type:'sdk-default', reason } -> omit; the SDK runs its bare stub + * - { type:'custom', text, reason } -> REPLACE default with given text * * For overlay-efficacy measurement, the preset+append pattern is the right * one: it measures "does adding overlay text to the REAL Claude Code system @@ -316,6 +315,7 @@ export async function runAgentSdkTest( opts: RunAgentSdkOptions, ): Promise<AgentSdkResult> { const sem = getApiSemaphore(); + const systemPrompt = sdkSystemPrompt(opts.systemPrompt); const maxRetries = opts.maxRetries ?? 3; const queryImpl: QueryProvider = opts.queryProvider ?? query; // Default matches session-runner's frontier eval fallback. Tests that need a @@ -353,11 +353,12 @@ export async function runAgentSdkTest( const budget = typeof opts.sessionBudgetMs === 'function' ? opts.sessionBudgetMs() : opts.sessionBudgetMs; const aborted = controller.signal.aborted || opts.signal?.aborted === true; const structured = observer.verdict(); + const streamed = observer.billed ? undefined : streamedUsageCostUsd(assistantTurns, model); const end: SessionEnd = aborted ? (budget !== undefined && elapsed + 1000 >= budget ? 'session_timeout' : 'aborted') : structured?.end ?? fallback; appendSessionLedger({ key: sessionKey('agent-sdk', opts.testName), ...(opts.testName ? { test_name: opts.testName } : {}), runner: 'agent-sdk', started_at: startedAt, ...(budget !== undefined ? { budget_ms: budget } : {}), elapsed_ms: elapsed, end, ...(end === 'session_timeout' ? { evidence: `armed ${budget}ms session timeout fired` } : structured && !aborted ? { evidence: structured.evidence } : {}), - liveness: observer.summary(performance.now()), billed: observer.billed }); + liveness: observer.summary(performance.now()), billed: observer.billed, ...(streamed !== undefined ? { streamed_cost_usd: streamed } : {}) }); }; const controller = new AbortController(); let activeQuery: ReturnType<QueryProvider> | undefined; @@ -444,11 +445,7 @@ export async function runAgentSdkTest( try { return await opts.canUseTool!(...args); } finally { observer.permission(-1); } } } : {}), }; - // Empty bare string means "omit entirely" (SDK runs with no override). - // Any object or non-empty string is passed through. - if (typeof opts.systemPrompt === 'object' || opts.systemPrompt !== '') { - sdkOpts.systemPrompt = opts.systemPrompt; - } + Object.assign(sdkOpts, systemPrompt); opts.signal?.throwIfAborted(); const q = queryImpl({ diff --git a/test/helpers/auq-native-capture.ts b/test/helpers/auq-native-capture.ts index ba70bb8c4..27b1cee56 100644 --- a/test/helpers/auq-native-capture.ts +++ b/test/helpers/auq-native-capture.ts @@ -313,7 +313,7 @@ Skip any system-audit / environment-setup / codebase-exploration steps. At the f session = await launchClaudePty({ // Explicit tool approvals suffice. Bypass mode introduces a separate // safety-consent screen in a fresh CLI config; never accept that screen. - cwd, model, seedSkills: false, permissionMode: 'default', + cwd, model, seedSkills: false, permissionMode: 'default', priceTranscript: false, observeScreen: true, observeSetupQuestions: true, timeoutMs: Math.max(1, deadline - Date.now()), // Explicit availability as well as approval: no Bash/Agent/Skill or MCP. diff --git a/test/helpers/claude-pty-runner.launch.unit.test.ts b/test/helpers/claude-pty-runner.launch.unit.test.ts index 0f6123afe..5abbb8e05 100644 --- a/test/helpers/claude-pty-runner.launch.unit.test.ts +++ b/test/helpers/claude-pty-runner.launch.unit.test.ts @@ -76,3 +76,43 @@ process.stdout.write(JSON.stringify({ capture: resolveEvalModel('capture'), } finally { rmSync(dir, { recursive: true, force: true }); } }, 60_000); }); + +describe('launchClaudePty transcript pricing (GSTA-150 PR 3)', () => { + test.skipIf(process.platform === 'win32')('prices the transcript this launch created for its cwd, without adding a launch argument; opting out prices nothing', () => { + const dir = mkdtempSync(join(tmpdir(), 'pty-transcript-cost-')); + try { + const fake = join(dir, 'fake-claude'); + writeFileSync(fake, `#!${process.execPath} +const fs = require('node:fs'), path = require('node:path'), crypto = require('node:crypto'); +const project = path.join(process.env.CLAUDE_CONFIG_DIR, 'projects', 'fake-project'); +fs.mkdirSync(project, { recursive: true }); +fs.writeFileSync(path.join(project, crypto.randomUUID() + '.jsonl'), JSON.stringify({ type: 'assistant', cwd: process.cwd(), + message: { id: 'msg_' + crypto.randomUUID(), model: 'claude-opus-5-5', usage: { input_tokens: 0, output_tokens: 1000 } } }) + '\\n'); +process.stdout.write('ARGV=' + JSON.stringify(process.argv.slice(2)) + '\\n'); +setInterval(() => {}, 1000); +`, { mode: 0o755 }); + const runner = pathToFileURL(join(import.meta.dir, 'claude-pty-runner.ts')).href; + const worker = join(dir, 'worker.ts'); + writeFileSync(worker, `import { launchClaudePty } from ${JSON.stringify(runner)}; +import * as fs from 'node:fs'; +const run = async (opts) => { + const cwd = fs.mkdtempSync(${JSON.stringify(join(dir, 'cwd-'))}); + const session = await launchClaudePty({ cwd, timeoutMs: 5000, ...opts }); + try { + await session.waitFor(/ARGV=\\[.*\\]/, { timeoutMs: 4000, pollMs: 20 }); + return { argv: JSON.parse(/ARGV=(\\[.*\\])/.exec(session.visibleText())[1]), cost: session.transcriptCostUsd?.() ?? null }; + } finally { await session.close(); } +}; +const [priced, optedOut] = await Promise.all([run({}), run({ priceTranscript: false })]); +process.stdout.write(JSON.stringify({ priced, optedOut })); +`); + const result = spawnSync(process.execPath, [worker], { cwd: join(import.meta.dir, '../..'), encoding: 'utf8', timeout: 30_000, + env: { ...process.env, BROWSE_TERMINAL_BINARY: fake, EVALS_HERMETIC: '1' } }); + expect(result.status, result.stderr).toBe(0); + const { priced, optedOut } = JSON.parse(result.stdout.trim().split('\n').at(-1)!); + expect(priced.cost).toBeCloseTo(0.02, 6); + expect(optedOut.cost).toBeNull(); + expect(priced.argv).not.toContain('--session-id'); + } finally { rmSync(dir, { recursive: true, force: true }); } + }, 60_000); +}); diff --git a/test/helpers/e2e-helpers.ts b/test/helpers/e2e-helpers.ts index 6ee6937e6..91996ff2b 100644 --- a/test/helpers/e2e-helpers.ts +++ b/test/helpers/e2e-helpers.ts @@ -274,6 +274,7 @@ export function recordE2E( duration_ms: result.duration, cost_usd: result.costEstimate.estimatedCost, ...(result.costKnown === false ? { cost_known: false } : {}), + ...(result.testName && result.testName !== name && result.testName in E2E_TIERS ? { cost_case_id: result.testName } : {}), ...(result.tokenUsage ? { token_usage: result.tokenUsage } : {}), transcript: result.transcript, output: result.output?.slice(0, 2000), diff --git a/test/helpers/eval-store.ts b/test/helpers/eval-store.ts index a50ea2c28..4085ad18c 100644 --- a/test/helpers/eval-store.ts +++ b/test/helpers/eval-store.ts @@ -86,6 +86,9 @@ export interface EvalTestEntry { // TRIAL_ENV variables the paid runner sets on an isolated trial shard. /** Registry id (E2E_TIERS / LLM_JUDGE_TOUCHFILES key) this record belongs to. */ case_id?: string; + /** Registry id whose cost this record carries (runSkillTest's testName) when its name is a display label; + * the report binds cost by it, never the failed record or its failure class. */ + cost_case_id?: string; kind?: EvalCaseKind; /** 1-based trial index within the case's panel. */ trial?: number; diff --git a/test/helpers/pty/launch.ts b/test/helpers/pty/launch.ts index e4413de38..4f0731ef3 100644 --- a/test/helpers/pty/launch.ts +++ b/test/helpers/pty/launch.ts @@ -15,8 +15,12 @@ import { trustDialogInput } from '../pty-trust-dialog'; import { resolveClaudeBinary } from './binary'; import { createPtyScreen, screenPanelEnd, stripAnsi } from './screen'; import { appendSessionLedger, sessionKey } from '../session-ledger'; +import { newTranscriptSessionId, pricedTranscript, ptyTranscriptCostUsd, transcriptFiles } from './transcript-cost'; export interface ClaudePtyOptions { + /** Price this session's ledger row from the transcript Claude writes under the hermetic config dir (default true). + * false for a caller that must never read model transcripts, such as the native AskUserQuestion capture. */ + priceTranscript?: boolean; /** Register the repo's shipped skills in the child's user scope via * hermeticSkillsConfigDir(). Required by any test that types a /skill * slash command; without it hermetic claude rejects the command as @@ -129,6 +133,9 @@ export interface ClaudePtySession { * the dir name ends in `/.claude` by contract). */ hermeticConfigDir: string | null; + /** This session's cost from its transcript (the caller's --session-id, else the one transcript this launch created + * for its cwd); undefined when unpriced, ambiguous or opted out. Never throws. */ + transcriptCostUsd?(): number | undefined; /** Owned HOME/.gstack created by the seeded launcher; absent for caller overrides. */ hermeticSkillStateRoot?: string; /** Owned pre-tool identity record, removed by close(). */ @@ -249,7 +256,8 @@ export async function launchClaudePty( recorded = true; const elapsed = performance.now() - startedMono; appendSessionLedger({ key: sessionKey('pty', undefined), runner: 'pty', started_at: startedAt, budget_ms: timeoutMs, - elapsed_ms: elapsed, end: elapsed >= timeoutMs ? 'session_timeout' : 'completed', ...screenPanelEnd(handle.visibleText()), billed: false }); + elapsed_ms: elapsed, end: elapsed >= timeoutMs ? 'session_timeout' : 'completed', ...screenPanelEnd(handle.visibleText()), billed: false, + ...pricedTranscript(handle) }); } return close(); } }); @@ -263,6 +271,8 @@ interface LaunchSetup { hermeticSkillStateRoot: string | undefined; autoplanArtifactStateRoot: string | undefined; autoplanEngTestPlanStateRoot: string | undefined; + /** What prices the transcript: the caller's session id, else the transcripts present before spawn. */ + transcript: { sessionId: string | undefined; before: Set<string>; cwd: string } | undefined; } function prepareLaunch(opts: ClaudePtyOptions): LaunchSetup { @@ -319,7 +329,13 @@ function prepareLaunch(opts: ClaudePtyOptions): LaunchSetup { const autoplanEngTestPlanStateRoot = opts.approveAutoplanArtifactEdits && opts.autoplanArtifactState !== undefined ? hermeticSkillStateRoot : undefined; - return { args, childEnv, hermetic, hermeticSkillStateRoot, autoplanArtifactStateRoot, autoplanEngTestPlanStateRoot }; + const extra = opts.extraArgs ?? []; + const pinned = extra.findIndex(arg => /^--session-id(=|$)/.test(arg)); + const sessionId = pinned < 0 ? undefined : extra[pinned].startsWith('--session-id=') ? extra[pinned].slice('--session-id='.length) : extra[pinned + 1]; + const resumes = extra.some(arg => /^(--resume|--continue|-r|-c)(=|$)/.test(arg)); + const transcript = hermetic && childEnv.CLAUDE_CONFIG_DIR && opts.priceTranscript !== false && !resumes + ? { sessionId, before: transcriptFiles(childEnv.CLAUDE_CONFIG_DIR), cwd: opts.cwd ?? process.cwd() } : undefined; + return { args, childEnv, hermetic, hermeticSkillStateRoot, autoplanArtifactStateRoot, autoplanEngTestPlanStateRoot, transcript }; } interface LaunchRecorders { @@ -568,6 +584,11 @@ function sessionHandle(pty: PtyProcess, launch: LaunchSetup, wallTimer: ReturnTy exited: () => pty.exited, exitCode: () => pty.exitCode, hermeticConfigDir: launch.hermetic ? launch.childEnv.CLAUDE_CONFIG_DIR ?? null : null, + transcriptCostUsd: () => { + const { transcript, childEnv } = launch; + return transcript && ptyTranscriptCostUsd(childEnv.CLAUDE_CONFIG_DIR, + transcript.sessionId ?? newTranscriptSessionId(childEnv.CLAUDE_CONFIG_DIR, transcript.before, transcript.cwd)); + }, hermeticSkillStateRoot: launch.hermeticSkillStateRoot, pendingPlanReadyFile: pendingExit?.file, pendingQuestionFile: pendingQuestion?.file, diff --git a/test/helpers/pty/session.ts b/test/helpers/pty/session.ts index 54fe04b61..8fd1749a6 100644 --- a/test/helpers/pty/session.ts +++ b/test/helpers/pty/session.ts @@ -10,6 +10,7 @@ import { launchClaudePty, type ClaudePtyOptions, type ClaudePtySession } from './launch'; import { screenPanelEnd } from './screen'; import { appendSessionLedger, sessionKey, type SessionEnd } from '../session-ledger'; +import { pricedTranscript } from './transcript-cost'; /** * The runners' launch seam: how a session starts, and the clock the runner @@ -97,7 +98,7 @@ export async function runPtySession<R>(plan: PtySessionPlan<R>): Promise<R> { } finally { appendSessionLedger({ key: sessionKey('pty', undefined), runner: 'pty', started_at: startedAt, budget_ms: plan.budgetMs ?? plan.launch.timeoutMs ?? 240_000, elapsed_ms: plan.driver.monotonic() - started, - end, ...safePanelEnd(session), billed: false }); + end, ...safePanelEnd(session), billed: false, ...pricedTranscript(session) }); try { try { plan.beforeClose?.(session, failure); } catch (error) { if (!failure) { failure = { error }; throw error; } } diff --git a/test/helpers/pty/transcript-cost.ts b/test/helpers/pty/transcript-cost.ts new file mode 100644 index 000000000..08f7ccbdb --- /dev/null +++ b/test/helpers/pty/transcript-cost.ts @@ -0,0 +1,74 @@ +import * as fs from 'node:fs'; +import * as path from 'node:path'; +import { streamedUsageCostUsd } from '../../../lib/pricing'; + +/** The session ledger's cost field for a PTY session: present only when its transcript prices. */ +export function pricedTranscript(session: { transcriptCostUsd?(): number | undefined } | undefined): { streamed_cost_usd?: number } { + const cost = session?.transcriptCostUsd?.(); + return cost === undefined ? {} : { streamed_cost_usd: cost }; +} + +/** Top-level session transcripts (`projects/<dir>/<id>.jsonl`) under a config dir; empty when unreadable. */ +export function transcriptFiles(configDir: string | undefined): Set<string> { + if (!configDir) return new Set(); + try { + const projects = path.join(configDir, 'projects'); + return new Set(fs.readdirSync(projects, { withFileTypes: true }).filter(dir => dir.isDirectory()) + .flatMap(dir => fs.readdirSync(path.join(projects, dir.name)).filter(f => f.endsWith('.jsonl')).map(f => path.join(projects, dir.name, f)))); + } catch { + return new Set(); + } +} + +/** + * The session id of the one transcript that appeared since `before` and was written for `cwd`. Concurrent PTY tests in + * one process share a hermetic config dir, so a launch claims only a new transcript for its own cwd; none or several + * (two sessions in one cwd) is undefined, which leaves the cost unknown. + */ +export function newTranscriptSessionId(configDir: string | undefined, before: ReadonlySet<string>, cwd: string): string | undefined { + try { + const cwds = new Set([cwd, fs.realpathSync(cwd)]); + const mine = [...transcriptFiles(configDir)].filter(file => !before.has(file) && fs.readFileSync(file, 'utf8').split('\n').some(line => { + try { + return cwds.has(JSON.parse(line)?.cwd); + } catch { + return false; + } + })); + return mine.length === 1 ? path.basename(mine[0], '.jsonl') : undefined; + } catch { + return undefined; + } +} + +/** + * Price one PTY session from the transcripts Claude Code wrote under its owned config dir: + * `projects/<dir>/<sessionId>.jsonl` (inline sidechains included) and `projects/<dir>/<sessionId>/subagents/*.jsonl`, + * rows deduplicated by message id. Undefined (cost-unknown, never $0) without a config dir, session id, transcript or + * usage, when a message's model has no price row, or when any read fails: it runs in ledger writers before close and + * cleanup, so it never throws. + */ +export function ptyTranscriptCostUsd(configDir: string | null | undefined, sessionId: string | undefined): number | undefined { + if (!configDir || !sessionId) return undefined; + try { + const projects = path.join(configDir, 'projects'); + const files: string[] = []; + for (const dir of fs.readdirSync(projects, { withFileTypes: true })) { + if (!dir.isDirectory()) continue; + const main = path.join(projects, dir.name, `${sessionId}.jsonl`); + if (fs.existsSync(main)) files.push(main); + const subagents = path.join(projects, dir.name, sessionId, 'subagents'); + if (fs.existsSync(subagents)) files.push(...fs.readdirSync(subagents).filter(f => f.endsWith('.jsonl')).map(f => path.join(subagents, f))); + } + const rows = files.flatMap(file => fs.readFileSync(file, 'utf8').split('\n').flatMap(line => { + try { + return [JSON.parse(line)]; + } catch { + return []; + } + })); + return streamedUsageCostUsd(rows); + } catch { + return undefined; + } +} diff --git a/test/helpers/sdk-system-prompt.ts b/test/helpers/sdk-system-prompt.ts new file mode 100644 index 000000000..95749138f --- /dev/null +++ b/test/helpers/sdk-system-prompt.ts @@ -0,0 +1,32 @@ +/** + * The system prompt every Agent SDK caller hands to Claude Code. + * + * Without `systemPrompt`, the SDK runs a bare stub instead of Claude Code's + * own prompt, and the stub drops the "run /skill via Skill" line, so a skill + * arm never learns how to load its skill. Callers pass the Claude Code preset, + * or name why they don't: docs/TESTING_INTERNALS.md#agent-sdk-system-prompt. + * test/sdk-system-prompt-tripwire.test.ts holds every caller to this. + */ + +export const CLAUDE_CODE_PRESET = { type: 'preset', preset: 'claude_code' } as const; + +export type SystemPromptOption = + | { type: 'preset'; preset: 'claude_code'; append?: string; excludeDynamicSections?: boolean } + | { type: 'sdk-default'; reason: string } + | { type: 'custom'; text: string; reason: string }; + +type SdkSystemPrompt = string | { type: 'preset'; preset: 'claude_code'; append?: string; excludeDynamicSections?: boolean }; + +/** The SDK options a caller's choice becomes; throws on a bare, unnamed or unknown prompt. */ +export function sdkSystemPrompt(option: SystemPromptOption): { systemPrompt?: SdkSystemPrompt } { + const fix = 'pass CLAUDE_CODE_PRESET, or { type: "sdk-default" | "custom", reason } naming why not (docs/TESTING_INTERNALS.md#agent-sdk-system-prompt)'; + const o = option as unknown; + if (!o || typeof o !== 'object') throw new Error(`systemPrompt must be an object, got ${JSON.stringify(o)}: ${fix}`); + const p = o as Record<string, unknown>; + if (p.type === 'preset' && p.preset === 'claude_code') return { systemPrompt: option as SdkSystemPrompt }; + if (p.type !== 'sdk-default' && p.type !== 'custom') throw new Error(`unknown systemPrompt ${JSON.stringify(o)}: ${fix}`); + if (typeof p.reason !== 'string' || !p.reason.trim()) throw new Error(`systemPrompt type "${p.type}" needs a non-empty reason: ${fix}`); + if (p.type === 'sdk-default') return {}; + if (typeof p.text !== 'string' || !p.text) throw new Error(`systemPrompt type "custom" needs its text: ${fix}`); + return { systemPrompt: p.text }; +} diff --git a/test/helpers/session-ledger.ts b/test/helpers/session-ledger.ts index a10bf28bf..c99baaaa0 100644 --- a/test/helpers/session-ledger.ts +++ b/test/helpers/session-ledger.ts @@ -52,6 +52,8 @@ export interface SessionLedgerRow { liveness?: LivenessSummary; /** Whether the runner captured this session's billing (a terminal result with total_cost_usd). */ billed?: boolean; + /** A session without a terminal result (an aborted Agent SDK session, a PTY session): its assistant messages' usage at lib/pricing.ts rates, from the stream or the PTY transcript; absent when unpriced. */ + streamed_cost_usd?: number; /** Codex sessions: the model, its billed cost and token classes. */ model?: string; cost_usd?: number; diff --git a/test/helpers/session-runner.ts b/test/helpers/session-runner.ts index cc65a66ad..c73b2596d 100644 --- a/test/helpers/session-runner.ts +++ b/test/helpers/session-runner.ts @@ -61,6 +61,8 @@ export interface SkillTestResult { tokenUsage?: CodexTokenUsage; /** Codex host: false when the session completed no turn or its model has no price row. */ costKnown?: boolean; + /** runSkillTest's testName: the registered case id the session ledger names, which recordE2E binds the record's cost to. */ + testName?: string; } /** Local default startup grace: 90s covers observed API queue latency @@ -741,5 +743,5 @@ Before source Reads, use Bash to run exactly \`date -u +%Y-%m-%dT%H:%M:%SZ\`. Af turnsUsed, }; - return { toolCalls, browseErrors, exitReason, duration, output: resultLine?.result || '', costEstimate, transcript, model, firstResponseMs, maxInterTurnMs }; + return { toolCalls, browseErrors, exitReason, duration, output: resultLine?.result || '', costEstimate, transcript, model, firstResponseMs, maxInterTurnMs, ...(testName ? { testName } : {}) }; } diff --git a/test/helpers/touchfiles-data.ts b/test/helpers/touchfiles-data.ts index 7b7eaee35..55a925406 100644 --- a/test/helpers/touchfiles-data.ts +++ b/test/helpers/touchfiles-data.ts @@ -36,7 +36,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = { 'test/helpers/ship-skip-actor.ts', 'test/helpers/scratch-repo.ts', 'test/skill-e2e-ship-skip.test.ts', 'test/helpers/shared-libs-eval-fixture.ts', - 'test/helpers/agent-sdk-runner.ts', 'test/helpers/hermetic-env.ts', + 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eval-budgets.ts' ], // The frozen review scope's two-pass convergence: the generated Step 9.4 + repeat decision, the real @@ -50,24 +50,24 @@ export const E2E_TOUCHFILES: Record<string, string[]> = { 'lib/review-evidence.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/helpers/ship-frozen-scope-actor.ts', 'test/helpers/scratch-repo.ts', 'test/skill-e2e-ship-frozen-scope.test.ts', 'test/helpers/shared-libs-eval-fixture.ts', - 'test/helpers/agent-sdk-runner.ts', 'test/helpers/hermetic-env.ts', + 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eval-budgets.ts' ], - 'investigate-owned-completion': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'investigate/**', 'freeze/**', 'guard/**', 'unfreeze/**', 'careful/bin/hook-extract.sh', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/workflow-boundaries-fixture.ts', 'test/skill-e2e-investigate-owned-completion.test.ts', 'test/helpers/e2e-gate.ts'], - 'investigate-owned-abort': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'investigate/**', 'freeze/**', 'guard/**', 'unfreeze/**', 'careful/bin/hook-extract.sh', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/workflow-boundaries-fixture.ts', 'test/skill-e2e-investigate-owned-termination.test.ts', 'test/helpers/e2e-gate.ts'], - 'investigate-owned-ending-error': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'investigate/**', 'freeze/**', 'guard/**', 'unfreeze/**', 'careful/bin/hook-extract.sh', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/workflow-boundaries-fixture.ts', 'test/skill-e2e-investigate-owned-termination.test.ts', 'test/helpers/e2e-gate.ts'], - 'shared-libs-review-path-eligibility': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'review/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/review-army.ts', 'lib/review-evidence.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'bin/gstack-wtree', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs-paths.test.ts', 'test/helpers/shared-libs-path-fixture.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-index-flags-*.json', 'test/fixtures/shared-libs-resolved-reads-public.json', 'test/helpers/shared-libs-review-start-evidence.ts'], - 'shared-libs-review-index-flags': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'review/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/review-army.ts', 'lib/review-evidence.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'bin/gstack-wtree', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs-paths.test.ts', 'test/helpers/shared-libs-path-fixture.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-index-flags-*.json', 'test/fixtures/shared-libs-paths-max-turns-public.json', 'test/fixtures/shared-libs-resolved-reads-public.json', 'test/helpers/shared-libs-review-start-evidence.ts'], - 'shared-libs-review-prior-coverage': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'review/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/review-army.ts', 'lib/review-evidence.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'bin/gstack-wtree', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs-paths.test.ts', 'test/helpers/shared-libs-path-fixture.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-index-flags-*.json', 'test/fixtures/shared-libs-resolved-reads-public.json', 'test/helpers/shared-libs-review-start-evidence.ts'], - 'shared-libs-codex-read-only': [ 'lib/outside-review-result.ts', 'lib/gate-outcomes.ts','deslop-shared-libs/**', 'bin/gstack-safe-git', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'test/helpers/codex-session-runner.ts', 'test/helpers/skill-fixture.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/eval-budgets.ts', 'test/codex-e2e-shared-libs.test.ts', 'test/helpers/e2e-gate.ts', 'hosts/codex.ts', 'hosts/define-host.ts', 'scripts/resolvers/constants.ts', 'test/fixtures/shared-libs-readonly-substitution-ci16358.json', 'test/helpers/agent-sdk-runner.ts', 'bin/gstack-codex-probe', 'scripts/resolve-codex-generation-model.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/outside-voice-steps.ts'], + 'investigate-owned-completion': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'investigate/**', 'freeze/**', 'guard/**', 'unfreeze/**', 'careful/bin/hook-extract.sh', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/workflow-boundaries-fixture.ts', 'test/skill-e2e-investigate-owned-completion.test.ts', 'test/helpers/e2e-gate.ts'], + 'investigate-owned-abort': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'investigate/**', 'freeze/**', 'guard/**', 'unfreeze/**', 'careful/bin/hook-extract.sh', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/workflow-boundaries-fixture.ts', 'test/skill-e2e-investigate-owned-termination.test.ts', 'test/helpers/e2e-gate.ts'], + 'investigate-owned-ending-error': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'investigate/**', 'freeze/**', 'guard/**', 'unfreeze/**', 'careful/bin/hook-extract.sh', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/workflow-boundaries-fixture.ts', 'test/skill-e2e-investigate-owned-termination.test.ts', 'test/helpers/e2e-gate.ts'], + 'shared-libs-review-path-eligibility': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'review/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/review-army.ts', 'lib/review-evidence.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'bin/gstack-wtree', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs-paths.test.ts', 'test/helpers/shared-libs-path-fixture.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-index-flags-*.json', 'test/fixtures/shared-libs-resolved-reads-public.json', 'test/helpers/shared-libs-review-start-evidence.ts'], + 'shared-libs-review-index-flags': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'review/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/review-army.ts', 'lib/review-evidence.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'bin/gstack-wtree', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs-paths.test.ts', 'test/helpers/shared-libs-path-fixture.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-index-flags-*.json', 'test/fixtures/shared-libs-paths-max-turns-public.json', 'test/fixtures/shared-libs-resolved-reads-public.json', 'test/helpers/shared-libs-review-start-evidence.ts'], + 'shared-libs-review-prior-coverage': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'review/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/review-army.ts', 'lib/review-evidence.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'bin/gstack-wtree', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs-paths.test.ts', 'test/helpers/shared-libs-path-fixture.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-index-flags-*.json', 'test/fixtures/shared-libs-resolved-reads-public.json', 'test/helpers/shared-libs-review-start-evidence.ts'], + 'shared-libs-codex-read-only': [ 'lib/outside-review-result.ts', 'lib/gate-outcomes.ts','deslop-shared-libs/**', 'bin/gstack-safe-git', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'test/helpers/codex-session-runner.ts', 'test/helpers/skill-fixture.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/eval-budgets.ts', 'test/codex-e2e-shared-libs.test.ts', 'test/helpers/e2e-gate.ts', 'hosts/codex.ts', 'hosts/define-host.ts', 'scripts/resolvers/constants.ts', 'test/fixtures/shared-libs-readonly-substitution-ci16358.json', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'bin/gstack-codex-probe', 'scripts/resolve-codex-generation-model.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/outside-voice-steps.ts'], // Shared-code audit and scoped review lifecycle - 'shared-libs-read-only': ['deslop-shared-libs/**', 'bin/gstack-safe-git', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-readonly-substitution-ci16358.json', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/shared-libs-review-start-evidence.ts', 'test/helpers/shared-libs-path-fixture.ts'], - 'shared-libs-unsupported-git': ['deslop-shared-libs/**', 'bin/gstack-safe-git', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-readonly-substitution-ci16358.json', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/shared-libs-review-start-evidence.ts', 'test/helpers/shared-libs-path-fixture.ts'], - 'shared-libs-review-lifecycle': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'deslop-shared-libs/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'review/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/review-army.ts', 'lib/review-evidence.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'bin/gstack-wtree', 'test/skill-e2e-shared-libs.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-index-flags-*.json', 'test/helpers/shared-libs-path-fixture.ts', 'test/fixtures/shared-libs-lifecycle-r59-stage-scope-public.json', 'test/helpers/shared-libs-review-start-evidence.ts'], - 'shared-libs-review-revalidation': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'deslop-shared-libs/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'review/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/review-army.ts', 'lib/review-evidence.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'bin/gstack-wtree', 'test/skill-e2e-shared-libs.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/helpers/shared-libs-review-start-evidence.ts', 'test/fixtures/shared-libs-review-start-public.json', 'test/fixtures/shared-libs-revalidation-max-turns-public.json', 'test/fixtures/shared-libs-index-flags-*.json', 'test/helpers/shared-libs-path-fixture.ts' ], - 'shared-libs-opportunity-judgment': ['deslop-shared-libs/**', 'bin/gstack-safe-git', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs-periodic.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-readonly-substitution-ci16358.json', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/shared-libs-plan-actor.ts', 'test/helpers/shared-libs-plan-excerpt.ts', 'test/helpers/skill-startup.ts'], - 'shared-libs-pr-coverage': ['deslop-shared-libs/**', 'bin/gstack-safe-git', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs-periodic.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-readonly-substitution-ci16358.json', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/shared-libs-plan-actor.ts', 'test/helpers/shared-libs-plan-excerpt.ts', 'test/helpers/skill-startup.ts'], - 'shared-libs-plan-callers': ['test/helpers/shared-libs-plan-actor.ts', 'scripts/resolvers/confidence.ts', 'test/helpers/shared-libs-plan-excerpt.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'deslop-shared-libs/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'plan-eng-review/**', 'test/skill-e2e-shared-libs-periodic.test.ts', 'test/fixtures/plan-scope-recovery-av.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/llm-judge.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/helpers/skill-startup.ts'], + 'shared-libs-read-only': ['deslop-shared-libs/**', 'bin/gstack-safe-git', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-readonly-substitution-ci16358.json', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/shared-libs-review-start-evidence.ts', 'test/helpers/shared-libs-path-fixture.ts'], + 'shared-libs-unsupported-git': ['deslop-shared-libs/**', 'bin/gstack-safe-git', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-readonly-substitution-ci16358.json', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/shared-libs-review-start-evidence.ts', 'test/helpers/shared-libs-path-fixture.ts'], + 'shared-libs-review-lifecycle': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'deslop-shared-libs/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'review/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/review-army.ts', 'lib/review-evidence.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'bin/gstack-wtree', 'test/skill-e2e-shared-libs.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-index-flags-*.json', 'test/helpers/shared-libs-path-fixture.ts', 'test/fixtures/shared-libs-lifecycle-r59-stage-scope-public.json', 'test/helpers/shared-libs-review-start-evidence.ts'], + 'shared-libs-review-revalidation': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'deslop-shared-libs/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'review/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/review-army.ts', 'lib/review-evidence.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'bin/gstack-wtree', 'test/skill-e2e-shared-libs.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/helpers/shared-libs-review-start-evidence.ts', 'test/fixtures/shared-libs-review-start-public.json', 'test/fixtures/shared-libs-revalidation-max-turns-public.json', 'test/fixtures/shared-libs-index-flags-*.json', 'test/helpers/shared-libs-path-fixture.ts' ], + 'shared-libs-opportunity-judgment': ['deslop-shared-libs/**', 'bin/gstack-safe-git', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs-periodic.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-readonly-substitution-ci16358.json', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/shared-libs-plan-actor.ts', 'test/helpers/shared-libs-plan-excerpt.ts', 'test/helpers/skill-startup.ts'], + 'shared-libs-pr-coverage': ['deslop-shared-libs/**', 'bin/gstack-safe-git', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'test/skill-e2e-shared-libs-periodic.test.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/fixtures/shared-libs-readonly-substitution-ci16358.json', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/shared-libs-plan-actor.ts', 'test/helpers/shared-libs-plan-excerpt.ts', 'test/helpers/skill-startup.ts'], + 'shared-libs-plan-callers': ['test/helpers/shared-libs-plan-actor.ts', 'scripts/resolvers/confidence.ts', 'test/helpers/shared-libs-plan-excerpt.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'deslop-shared-libs/**', 'scripts/resolvers/shared-libs.ts', 'scripts/resolvers/index.ts', 'test/helpers/shared-libs-eval-fixture.ts', 'plan-eng-review/**', 'test/skill-e2e-shared-libs-periodic.test.ts', 'test/fixtures/plan-scope-recovery-av.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/helpers/e2e-gate.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/llm-judge.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'test/helpers/skill-startup.ts'], 'ship-docsync-missing-marker': ['bin/gstack-docs-candidate', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'document-release/**', 'scripts/resolvers/sections.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble-hoist.ts', 'scripts/resolvers/testing.ts', 'scripts/gen-skill-docs.ts', 'bin/gstack-skill-start', 'bin/gstack-session-kind', 'test/helpers/docsync-*.ts', 'test/helpers/read-only-commands.ts', 'test/helpers/qa-functional-*.ts', 'test/helpers/session-runner.ts', 'test/helpers/hermetic-env.ts', 'test/skill-e2e-ship-docsync.test.ts', 'test/helpers/qa-checkpoint-evidence.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/qa-evidence-producer.ts', 'bin/gstack-context-recovery'], 'ship-docsync-missing-asset': ['bin/gstack-docs-candidate', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'document-release/**', 'scripts/resolvers/sections.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble-hoist.ts', 'scripts/resolvers/testing.ts', 'scripts/gen-skill-docs.ts', 'bin/gstack-skill-start', 'bin/gstack-session-kind', 'test/helpers/docsync-*.ts', 'test/helpers/read-only-commands.ts', 'test/helpers/qa-functional-*.ts', 'test/helpers/session-runner.ts', 'test/helpers/hermetic-env.ts', 'test/skill-e2e-ship-docsync.test.ts', 'test/helpers/qa-checkpoint-evidence.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/qa-evidence-producer.ts', 'bin/gstack-context-recovery'], 'ship-docsync-launch-failure': ['bin/gstack-docs-candidate', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'document-release/**', 'scripts/resolvers/sections.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble-hoist.ts', 'scripts/resolvers/testing.ts', 'scripts/gen-skill-docs.ts', 'bin/gstack-skill-start', 'bin/gstack-session-kind', 'test/helpers/docsync-*.ts', 'test/helpers/read-only-commands.ts', 'test/helpers/qa-functional-*.ts', 'test/helpers/session-runner.ts', 'test/helpers/hermetic-env.ts', 'test/skill-e2e-ship-docsync.test.ts', 'test/helpers/qa-checkpoint-evidence.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/qa-evidence-producer.ts', 'bin/gstack-context-recovery'], @@ -366,7 +366,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = { // Native question capture and interactive workflow probes. 'auq-format-gate': [ 'ETHOS.md', 'plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble-hoist.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-ask-user-question-format-compliance.test.ts', - 'test/helpers/agent-sdk-runner.ts', + 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/hermetic-env.ts', 'test/helpers/eval-store.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', @@ -417,35 +417,35 @@ export const E2E_TOUCHFILES: Record<string, string[]> = { 'tpa-apple-ban': [ 'scripts/resolvers/third-party-actions.ts', 'ship/SKILL.md.tmpl', 'ship/sections/apple-release.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-third-party-actions.test.ts', 'test/helpers/third-party-actions.ts', 'lib/eval-model.ts' ], - 'ship-measure-seeded-flake': ['ship/**', 'scripts/ship-measure.ts', 'scripts/lib/measure-bar.ts', 'scripts/test-free-shards.ts', 'scripts/lib/shard-engine.ts', 'scripts/lib/paid-select.ts', 'scripts/lib/free-home-guard.ts', 'scripts/lib/shard-jobs.ts', 'bin/gstack-config', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/testing.ts', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-ship-measure-loop.test.ts', 'test/helpers/ship-measure-seeded-fixture.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/skill-fixture.ts'], + 'ship-measure-seeded-flake': ['ship/**', 'scripts/ship-measure.ts', 'scripts/lib/measure-bar.ts', 'scripts/test-free-shards.ts', 'scripts/lib/shard-engine.ts', 'scripts/lib/paid-select.ts', 'scripts/lib/free-home-guard.ts', 'scripts/lib/shard-jobs.ts', 'bin/gstack-config', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/testing.ts', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-ship-measure-loop.test.ts', 'test/helpers/ship-measure-seeded-fixture.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/skill-fixture.ts'], 'ship-section-loading': [ 'ship/**', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-ship-section-loading.test.ts', - 'scripts/resolvers/testing.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'scripts/resolvers/testing.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], 'plan-ceo-section-loading': [ 'ETHOS.md', 'test/fixtures/ceo-fill-lifetime.json', 'plan-ceo-review/**', 'ETHOS.md', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'test/helpers/ceo-section-loading-fixture.ts', 'test/helpers/ceo-stale-fill-decision.ts', 'test/skill-e2e-plan-ceo-review-section-loading.test.ts', 'test/fixtures/ceo-section-loading-l-report.md', 'test/fixtures/ceo-section-loading-q-report.md', 'test/fixtures/ceo-section-r-rejected-report.md', 'test/fixtures/ceo-section-s-trace-report.md', 'test/fixtures/ceo-section-u-report.md', 'test/fixtures/ceo-section-y-report.md', 'test/fixtures/ceo-section-aa-report.md', 'test/fixtures/sdk-stale-table-ad-v3.json', 'test/fixtures/sdk-ordering-ae.json', 'test/fixtures/sdk-columnar-af.json', 'test/fixtures/sdk-order-b-ag.json', 'test/fixtures/sdk-schedule-continuation-ah.json', 'test/fixtures/sdk-original-order-ai.json', 'test/fixtures/sdk-compact-sequence-aj.json', "test/fixtures/sdk-reported-coordination-ar.md", "test/fixtures/sdk-ordered-schedule-ar.md", - 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/tasks-section.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/tasks-section.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], // Data-driven behavioral guard for the 'plan'/'prompt' carves: one case per // skill in test/carve-section-loading.test.ts (case-sharded, W5a). Each case // selects on its own skill directory; the registry, helper, harness and // sections.ts select every case. - 'carve-section-loading-browse': ['browse/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-codex': ['codex/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-design-consultation': ['design-consultation/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-design-html': ['design-html/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-design-shotgun': ['design-shotgun/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-document-release': ['document-release/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-benchmark': ['benchmark/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-context-restore': ['context-restore/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-investigate': ['investigate/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-land-and-deploy': ['land-and-deploy/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-plan-design-review': ['plan-design-review/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-plan-devex-review': ['plan-devex-review/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-plan-eng-review': ['plan-eng-review/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'scripts/resolvers/learnings.ts', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'scripts/resolvers/testing.ts', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-qa': ['qa/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-retro': ['retro/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-review': ['review/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-setup-gbrain': ['setup-gbrain/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'carve-section-loading-spec': ['spec/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-browse': ['browse/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-codex': ['codex/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-design-consultation': ['design-consultation/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-design-html': ['design-html/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-design-shotgun': ['design-shotgun/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-document-release': ['document-release/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-benchmark': ['benchmark/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-context-restore': ['context-restore/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-investigate': ['investigate/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-land-and-deploy': ['land-and-deploy/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-plan-design-review': ['plan-design-review/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-plan-devex-review': ['plan-devex-review/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-plan-eng-review': ['plan-eng-review/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'scripts/resolvers/learnings.ts', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'scripts/resolvers/testing.ts', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-qa': ['qa/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-retro': ['retro/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-review': ['review/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-setup-gbrain': ['setup-gbrain/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'carve-section-loading-spec': ['spec/**', 'setup', 'bin/gstack-bun-version.sh', 'bin/gstack-state-root.sh', 'lib/state-root.ts', 'bin/gstack-review-log', 'bin/gstack-review-read', 'lib/review-evidence.ts', 'bin/gstack-slug', 'bin/gstack-remote-identity.sh', 'bin/gstack-wtree', 'bin/gstack-config', 'bin/gstack-brain-enqueue', 'test/fixtures/autoplan-amend-input-77.json', 'test/fixtures/autoplan-phase-handoff-6714.json', 'test/fixtures/plan-scope-recovery-av.json', 'test/fixtures/design-scope-checkpoint-at.json', 'scripts/resolvers/composition.ts', 'autoplan/**', 'test/helpers/carve-guards.ts', 'scripts/resolvers/sections.ts', 'scripts/resolvers/redact-doc.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/session-runner.ts', 'bin/gstack-autoplan-snapshot.ts', 'test/fixtures/autoplan/t-ceo-omitted-obligations.json', 'test/fixtures/autoplan/u-ceo-original-loss.json', 'test/fixtures/autoplan/v-ceo-dangling-references.json', 'scripts/resolvers/preamble/generate-preamble-bash.ts', 'scripts/resolvers/preamble/generate-completion-status.ts', 'test/carve-section-loading.test.ts', 'test/helpers/carve-section-case.ts', 'test/fixtures/design-html-section-complete.md', 'test/helpers/carve-plan-fixture.ts', 'test/fixtures/carve-existing-repository/**', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/llm-judge.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], // Per-finding AskUserQuestion count + review-report-at-bottom assertion. // Each test drives its skill end-to-end; touchfiles include preamble + @@ -582,15 +582,15 @@ export const E2E_TOUCHFILES: Record<string, string[]> = { // Agent SDK. Gate-tier (deterministic stub server, fixed inputs); fires // when the skill template, the verify helper, the artifacts-init helper, // or the detect script changes. - 'setup-gbrain-remote': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'test/helpers/setup-gbrain-sandbox.ts', 'test/helpers/office-hours-attempt.ts', 'test/helpers/eval-store.ts', 'test/helpers/e2e-helpers.ts', 'lib/redact-engine.ts', 'lib/redact-patterns.ts', 'lib/eval-model.ts','setup-gbrain/sections/brain-init.md.tmpl', 'setup-gbrain/sections/claude-md-persist.md.tmpl', 'setup-gbrain/sections/manifest.json', 'test/helpers/setup-gbrain-fixture.ts', 'setup-gbrain/SKILL.md.tmpl', 'bin/gstack-gbrain-mcp-verify', 'bin/gstack-artifacts-init', 'bin/gstack-gbrain-detect', 'test/helpers/agent-sdk-runner.ts', 'test/skill-e2e-setup-gbrain-remote.test.ts', + 'setup-gbrain-remote': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'test/helpers/setup-gbrain-sandbox.ts', 'test/helpers/office-hours-attempt.ts', 'test/helpers/eval-store.ts', 'test/helpers/e2e-helpers.ts', 'lib/redact-engine.ts', 'lib/redact-patterns.ts', 'lib/eval-model.ts','setup-gbrain/sections/brain-init.md.tmpl', 'setup-gbrain/sections/claude-md-persist.md.tmpl', 'setup-gbrain/sections/manifest.json', 'test/helpers/setup-gbrain-fixture.ts', 'setup-gbrain/SKILL.md.tmpl', 'bin/gstack-gbrain-mcp-verify', 'bin/gstack-artifacts-init', 'bin/gstack-gbrain-detect', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/skill-e2e-setup-gbrain-remote.test.ts', 'test/helpers/e2e-gate.ts'], - 'setup-gbrain-bad-token': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'setup-gbrain/sections/brain-init.md.tmpl', 'setup-gbrain/sections/manifest.json', 'test/helpers/setup-gbrain-fixture.ts', 'setup-gbrain/SKILL.md.tmpl', 'bin/gstack-gbrain-mcp-verify', 'test/helpers/agent-sdk-runner.ts', 'test/skill-e2e-setup-gbrain-bad-token.test.ts', + 'setup-gbrain-bad-token': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'setup-gbrain/sections/brain-init.md.tmpl', 'setup-gbrain/sections/manifest.json', 'test/helpers/setup-gbrain-fixture.ts', 'setup-gbrain/SKILL.md.tmpl', 'bin/gstack-gbrain-mcp-verify', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/skill-e2e-setup-gbrain-bad-token.test.ts', 'test/helpers/setup-gbrain-sandbox.ts', 'lib/redact-engine.ts', 'lib/redact-patterns.ts', 'test/helpers/setup-gbrain-fixture-command.ts', 'bin/gstack-gbrain-detect', 'lib/gbrain-local-status.ts', 'lib/gbrain-exec.ts', 'bin/gstack-gbrain-lib.sh', 'bin/gstack-egress-lib.sh', 'bin/gstack-egress-receipt', 'test/helpers/office-hours-attempt.ts', 'test/helpers/e2e-gate.ts'], // v1.34.0.0 split-engine Path 4 + Step 4.5 Yes (local PGLite for code). // Periodic-tier per codex #12 (AgentSDK harness is non-deterministic). // Fires when the setup-gbrain template, install/verify/init helpers, or // the agent-sdk-runner harness changes. - 'setup-gbrain-path4-local-pglite': [ 'lib/memory-ingest-landing.ts', 'bin/gstack-memory-ingest.ts', 'bin/gstack-gbrain-sync.ts','bin/gstack-state-root.sh', 'lib/state-root.ts', 'setup-gbrain/sections/brain-init.md.tmpl', 'setup-gbrain/sections/claude-md-persist.md.tmpl', 'setup-gbrain/sections/manifest.json', 'test/helpers/setup-gbrain-fixture.ts', 'setup-gbrain/SKILL.md.tmpl', 'bin/gstack-gbrain-mcp-verify', 'bin/gstack-gbrain-install', 'bin/gstack-gbrain-detect', 'lib/gbrain-local-status.ts', 'test/helpers/agent-sdk-runner.ts', 'test/skill-e2e-setup-gbrain-path4-local-pglite.test.ts', + 'setup-gbrain-path4-local-pglite': [ 'lib/memory-ingest-landing.ts', 'bin/gstack-memory-ingest.ts', 'bin/gstack-gbrain-sync.ts','bin/gstack-state-root.sh', 'lib/state-root.ts', 'setup-gbrain/sections/brain-init.md.tmpl', 'setup-gbrain/sections/claude-md-persist.md.tmpl', 'setup-gbrain/sections/manifest.json', 'test/helpers/setup-gbrain-fixture.ts', 'setup-gbrain/SKILL.md.tmpl', 'bin/gstack-gbrain-mcp-verify', 'bin/gstack-gbrain-install', 'bin/gstack-gbrain-detect', 'lib/gbrain-local-status.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/skill-e2e-setup-gbrain-path4-local-pglite.test.ts', 'test/helpers/setup-gbrain-sandbox.ts', 'lib/redact-engine.ts', 'lib/redact-patterns.ts', 'test/helpers/setup-gbrain-fixture-command.ts', 'lib/gbrain-exec.ts', 'bin/gstack-gbrain-lib.sh', 'bin/gstack-egress-lib.sh', 'bin/gstack-egress-receipt', 'test/helpers/office-hours-attempt.ts', 'test/helpers/e2e-gate.ts'], // AskUserQuestion format regression (RECOMMENDATION + Completeness: N/10) @@ -654,15 +654,15 @@ export const E2E_TOUCHFILES: Record<string, string[]> = { // Ship 'ship-managed-hook-refresh': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'bin/gstack-redact', 'bin/gstack-config', 'scripts/gen-skill-docs.ts', 'test/helpers/ship-hook-actor.ts', - 'test/helpers/workflow-excerpt.ts', 'test/helpers/agent-sdk-runner.ts', 'test/skill-e2e-ship-hook-refresh.test.ts', + 'test/helpers/workflow-excerpt.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/skill-e2e-ship-hook-refresh.test.ts', 'test/helpers/e2e-gate.ts'], 'ship-unmanaged-hook-consent': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'bin/gstack-redact', 'bin/gstack-config', 'scripts/gen-skill-docs.ts', 'test/helpers/ship-hook-actor.ts', - 'test/helpers/workflow-excerpt.ts', 'test/helpers/agent-sdk-runner.ts', 'test/skill-e2e-ship-hook-consent.test.ts', + 'test/helpers/workflow-excerpt.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/skill-e2e-ship-hook-consent.test.ts', 'test/helpers/e2e-gate.ts'], 'ship-local-hook-preservation': ['bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'bin/gstack-redact', 'bin/gstack-config', 'scripts/gen-skill-docs.ts', 'test/helpers/ship-hook-actor.ts', - 'test/helpers/workflow-excerpt.ts', 'test/helpers/agent-sdk-runner.ts', 'test/skill-e2e-ship-hook-consent.test.ts', + 'test/helpers/workflow-excerpt.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/skill-e2e-ship-hook-consent.test.ts', 'test/helpers/e2e-gate.ts'], 'ship-base-branch': [ 'bin/gstack-version-bump','bin/gstack-state-root.sh', 'lib/state-root.ts', 'ship/**', 'bin/gstack-repo-mode', 'test/skill-e2e-review-attribution.test.ts', 'scripts/resolvers/testing.ts' @@ -741,11 +741,11 @@ export const E2E_TOUCHFILES: Record<string, string[]> = { ], // Formerly keyless periodic files (W1b): registered so an edit selects its own case instead of restoring the full PR gate. 'auq-consistency': [ 'ETHOS.md', 'test/skill-e2e-auq-consistency.test.ts', 'plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble-hoist.ts', - 'test/helpers/auq-sdk-capture.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/llm-judge.ts', 'test/helpers/e2e-gate.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', + 'test/helpers/auq-sdk-capture.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/llm-judge.ts', 'test/helpers/e2e-gate.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'scripts/resolvers/tasks-section.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts', ], 'auq-verbose-vs-carved-ab': [ 'ETHOS.md', 'test/skill-e2e-auq-verbose-vs-carved-ab.test.ts', 'test/fixtures/auq-pre-cut-plan-ceo-review-SKILL.md', 'plan-ceo-review/**', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'scripts/resolvers/preamble/generate-completeness-section.ts', 'scripts/resolvers/preamble.ts', 'scripts/resolvers/preamble-hoist.ts', - 'test/helpers/auq-sdk-capture.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/llm-judge.ts', 'test/helpers/e2e-gate.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', + 'test/helpers/auq-sdk-capture.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/llm-judge.ts', 'test/helpers/e2e-gate.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts', 'scripts/resolvers/tasks-section.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts', ], 'codex-recommendation-substance': [ 'test/codex-e2e-recommendation-substance.test.ts', 'codex/**', 'test/helpers/codex-session-runner.ts', 'test/helpers/llm-judge.ts', 'test/helpers/e2e-gate.ts', @@ -1208,8 +1208,8 @@ export const E2E_TOUCHFILES: Record<string, string[]> = { 'test/skill-e2e-model-panel.test.ts', 'ship/SKILL.md', 'test/helpers/e2e-gate.ts'], - 'office-hours-section-loading': [ 'ETHOS.md', 'office-hours/**', 'bin/gstack-office-hours-review', 'lib/office-hours-review.ts', 'lib/fs-atomic.ts', 'lib/spec-review-cap.ts', 'test/helpers/office-hours-formatter-fixture.ts', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/carve-guards.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/office-hours-completion.ts', 'test/helpers/llm-judge.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-office-hours-section-loading.test.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], - 'office-hours-design-draft': [ 'ETHOS.md', 'office-hours/**', 'lib/office-hours-review.ts', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/carve-guards.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/office-hours-completion.ts', 'test/helpers/llm-judge.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-office-hours-design-draft.test.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'office-hours-section-loading': [ 'ETHOS.md', 'office-hours/**', 'bin/gstack-office-hours-review', 'lib/office-hours-review.ts', 'lib/fs-atomic.ts', 'lib/spec-review-cap.ts', 'test/helpers/office-hours-formatter-fixture.ts', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/carve-guards.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/office-hours-completion.ts', 'test/helpers/llm-judge.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-office-hours-section-loading.test.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], + 'office-hours-design-draft': [ 'ETHOS.md', 'office-hours/**', 'lib/office-hours-review.ts', 'scripts/resolvers/review-dashboard.ts', 'scripts/resolvers/plan-gates.ts', 'scripts/resolvers/spec-review.ts', 'scripts/resolvers/outside-voice-steps.ts', 'scripts/resolvers/review-scope.ts', 'scripts/resolvers/outside-voice.ts', 'scripts/resolvers/sections.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/carve-guards.ts', 'test/helpers/auq-sdk-capture.ts', 'test/helpers/office-hours-completion.ts', 'test/helpers/llm-judge.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-office-hours-design-draft.test.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'test/helpers/auq-native-capture.ts', 'test/helpers/auto-decision-state.ts', 'test/helpers/autoplan-artifact-digest.ts', 'test/helpers/autoplan-artifact-permission.ts', 'test/helpers/autoplan-artifact-recorder.ts', 'test/helpers/capture-parity-baseline.ts', 'test/helpers/claude-pty-runner.ts', 'test/helpers/pty/**', 'test/helpers/dx-selected-navigation.ts', 'test/helpers/e2e-gate.ts', 'test/helpers/eng-cache-writer-decision.ts', 'test/helpers/hermetic-skill-runtime.ts', 'test/helpers/native-auto-decide.ts', 'test/helpers/owned-claude-transcript.ts', 'test/helpers/parity-harness.ts', 'test/helpers/size-ledger.ts', 'test/size-ledger/**', 'test/helpers/plan-count-artifacts.ts', 'test/helpers/plan-count-file-permission.ts', 'test/helpers/plan-count-fixture.ts', 'test/helpers/plan-count-pending-exit.ts', 'test/helpers/plan-count-pending-question.ts', 'test/helpers/plan-count-transcript.ts', 'test/helpers/plan-floor-review.ts', 'test/helpers/plan-floor-target.ts', 'test/helpers/plan-scope-selection.ts', 'test/helpers/plan-seed-submission.ts', 'test/helpers/plan-skill-question-events.ts', 'test/helpers/plan-skill-question-hook-scope.ts', 'test/helpers/plan-skill-questions.ts', 'test/helpers/pty-screen.ts', 'test/helpers/pty-trust-dialog.ts', 'test/helpers/skill-census.ts'], 'dx-error-contract-review': ['test/skill-e2e-dx-error-contract.test.ts', 'test/fixtures/dx-error-contract-case.ts', 'lib/dx-error-contract.ts', 'scripts/resolvers/dx.ts', 'scripts/resolvers/index.ts', 'scripts/gen-skill-docs.ts', 'plan-devex-review/**', 'bin/gstack-autoplan-snapshot.ts', 'lib/autoplan-prompts.ts', 'lib/autoplan-reconcile.ts', 'lib/coordinator-contract.ts', 'test/helpers/session-runner.ts', 'test/helpers/eval-store.ts', 'test/helpers/eval-budgets.ts', 'lib/claude-bin.ts', 'lib/eval-model.ts'], 'plan-devex-peer-comparison-classification': [ @@ -1220,11 +1220,11 @@ export const E2E_TOUCHFILES: Record<string, string[]> = { 'test/skill-e2e-plan-decision-classification.test.ts', 'test/fixtures/plan-decision-classification.ts', 'test/helpers/plan-review-decisions.ts', 'test/helpers/plan-review-cases.ts', 'test/helpers/llm-judge.ts', 'lib/eval-model.ts', 'test/helpers/e2e-helpers.ts', 'test/helpers/eval-store.ts', 'test/helpers/eval-budgets.ts', 'scripts/resolvers/preamble/generate-ask-user-format.ts', 'docs/askuserquestion-split.md', 'plan-ceo-review/SKILL.md.tmpl', 'plan-ceo-review/sections/review-sections.md.tmpl', 'scripts/resolvers/tasks-section.ts'], 'health-reporting': ['health/**', 'test/skill-e2e-health.test.ts', 'test/helpers/health-eval-fixture.ts', 'test/helpers/e2e-gate.ts'], - 'overlay-harness-claude-dedicated-tools-vs-bash': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts', 'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts', 'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'], - 'overlay-harness-opus-4-7-effort-match-trivial': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-opus-4-7-effort-match-trivial.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts', 'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts', 'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'], - 'overlay-harness-opus-4-7-literal-interpretation': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-opus-4-7-literal-interpretation.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts', 'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts', 'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'], - 'overlay-harness-claude-dedicated-tools-vs-bash-sonnet': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-sonnet.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts', 'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts', 'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'], - 'overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts', 'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts', 'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'], + 'overlay-harness-claude-dedicated-tools-vs-bash': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts', 'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts', 'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'], + 'overlay-harness-opus-4-7-effort-match-trivial': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-opus-4-7-effort-match-trivial.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts', 'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts', 'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'], + 'overlay-harness-opus-4-7-literal-interpretation': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-opus-4-7-literal-interpretation.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts', 'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts', 'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'], + 'overlay-harness-claude-dedicated-tools-vs-bash-sonnet': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-sonnet.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts', 'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts', 'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'], + 'overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5': ['model-overlays/**', 'test/fixtures/overlay-nudges.ts', 'test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts', 'scripts/resolvers/model-overlay.ts', 'test/skill-e2e-overlay-harness-claude-dedicated-tools-vs-bash-opus-5-5.test.ts', 'test/helpers/overlay-measurement.ts', 'test/helpers/overlay-workspace.ts', 'test/helpers/overlay-attempt.ts', 'test/helpers/overlay-case.ts', 'test/helpers/overlay-case-policy.ts', 'test/helpers/overlay-lifecycle.ts', 'test/fixtures/overlay-admission-child.ts', 'test/helpers/e2e-gate.ts'], 'journey-negatives': [ 'ETHOS.md', diff --git a/test/overlay-lifecycle.test.ts b/test/overlay-lifecycle.test.ts index 66232ce59..ef5addbec 100644 --- a/test/overlay-lifecycle.test.ts +++ b/test/overlay-lifecycle.test.ts @@ -15,7 +15,7 @@ const sample = (metric = 3): OverlayTrialOutcome => ({ passed: true, taskCorrect const sdkResult = (): AgentSdkResult => ({ events: [{ type: 'result', subtype: 'success' }] as AgentSdkResult['events'], assistantTurns: [], toolCalls: [], output: 'done', exitReason: 'success', turnsUsed: 1, durationMs: 1, firstResponseMs: 1, maxInterTurnMs: 0, costUsd: .01, model: 'test', sdkVersion: 'test', sdkClaudeCodeVersion: 'test', resolvedBinaryPath: 'test', browseErrors: [] }); function roots() { return fs.mkdtempSync(path.join(os.tmpdir(), 'overlay-lifecycle-free-')); } -function opts(dir: string, provider: QueryProvider, signal: AbortSignal) { return { systemPrompt: '', userPrompt: 'test', workingDirectory: dir, queryProvider: provider, signal }; } +function opts(dir: string, provider: QueryProvider, signal: AbortSignal) { return { systemPrompt: { type: 'sdk-default', reason: 'stub queryProvider: no model reads the prompt' } as const, userPrompt: 'test', workingDirectory: dir, queryProvider: provider, signal }; } test('every fixture owns one paid wrapper; public models/trials/concurrency/turn caps and walls are preserved', () => { expect(Object.values(OVERLAY_CASE_FILES).sort()).toEqual(OVERLAY_FIXTURES.map(f => f.id).sort()); diff --git a/test/overlay-sdk-cancel-eof.test.ts b/test/overlay-sdk-cancel-eof.test.ts index 6cd4614b0..f17be5425 100644 --- a/test/overlay-sdk-cancel-eof.test.ts +++ b/test/overlay-sdk-cancel-eof.test.ts @@ -9,7 +9,7 @@ import { captureOverlayQueryAttempts } from './helpers/overlay-attempt'; const terminal = { type: 'result', subtype: 'success', is_error: false, num_turns: 1, total_cost_usd: 0 }; const assistant = { type: 'assistant', message: { id: 'owned', content: [{ type: 'text', text: 'owned fake result' }] } }; -const options = (directory: string, signal: AbortSignal, queryProvider: QueryProvider) => ({ workingDirectory: directory, signal, queryProvider, systemPrompt: '', userPrompt: 'owned free probe', settingSources: [], env: { ANTHROPIC_API_KEY: '', HOME: directory, GSTACK_HOME: path.join(directory, '.gstack') } }); +const options = (directory: string, signal: AbortSignal, queryProvider: QueryProvider) => ({ workingDirectory: directory, signal, queryProvider, systemPrompt: { type: 'sdk-default', reason: 'fake Claude Code child script: no model reads the prompt' } as const, userPrompt: 'owned free probe', settingSources: [], env: { ANTHROPIC_API_KEY: '', HOME: directory, GSTACK_HOME: path.join(directory, '.gstack') } }); test('SDK cancellation after the terminal event but before EOF rejects and releases its permit', async () => { __resetSemaphoreForTests(1); diff --git a/test/paid-report-census.test.ts b/test/paid-report-census.test.ts index ff9dbf168..103e1c8d2 100644 --- a/test/paid-report-census.test.ts +++ b/test/paid-report-census.test.ts @@ -123,6 +123,29 @@ describe('a case shard\'s result records are its one case\'s cost (2026-10-26 tr expect(collector(r.dir).verdict.costUsd).toBe(0.75); }); + test('a record-less trial\'s streamed session cost reaches the trial and the verdict total once (GSTA-150 outside voice: $0.65 known, headline $0.00)', () => { + const ledger = (dir: string, slug: string, costs: number[]) => fs.writeFileSync(path.join(shard(dir, slug), 'session-ledger.jsonl'), + costs.map(cost => JSON.stringify({ key: 'k', runner: 'agent-sdk', started_at: 't', elapsed_ms: 1, end: 'aborted', billed: false, streamed_cost_usd: cost })).join('\n') + '\n'); + const r = report('periodic', dir => { + ledger(dir, 'skill-e2e-qa-workflow--qa-fix-loop', [0.4, 0.25]); + results(dir, 'skill-e2e-benchmark-providers', [{ name: 'benchmark-providers-live', suite: 's', tier: 'e2e', passed: true, duration_ms: 1, cost_usd: 0.1 }]); + ledger(dir, 'skill-e2e-benchmark-providers', [0.5]); + }); + expect(r.history.find(record => record.case === 'qa-fix-loop')).toMatchObject({ outcome: 'passed', cost_usd: 0.65 }); + expect(r.history.find(record => record.case === 'benchmark-providers-live')).toMatchObject({ cost_usd: 0.6 }); + expect(collector(r.dir).verdict.costUsd).toBe(1.25); + expect(r.out).toContain('cost $1.25 known + 5 of 7 trial(s) cost unknown'); + }); + + test('a billed session\'s cost is already in its collector total, so the verdict never adds it again (Codex host, unbound label record)', () => { + const r = report('periodic', dir => { + results(dir, 'skill-e2e-cso', [{ name: '/cso full audit', suite: 'cso', tier: 'e2e', passed: true, duration_ms: 1, cost_usd: 0.5 }]); + fs.writeFileSync(path.join(shard(dir, 'skill-e2e-cso'), 'session-ledger.jsonl'), + JSON.stringify({ key: 'k', runner: 'codex', started_at: 't', elapsed_ms: 1, end: 'completed', billed: true, cost_usd: 0.5 }) + '\n'); + }); + expect(collector(r.dir).verdict.costUsd).toBe(0.5); + }); + // Value: protects=a failed case shard's trial reads its failure class, exit reason, error and cost from the display-labelled record the shard // wrote, not a generic 'assertion' with the JUnit message (the same attribution the cost fix made; train-gate's INFRA/VERDICT class follows failure_class); // fails_when=failedRecord is looked up through the old name/case_id-only filter again so the record's class and error are dropped; diff --git a/test/paid-report-cost.test.ts b/test/paid-report-cost.test.ts new file mode 100644 index 000000000..fcfc2dd30 --- /dev/null +++ b/test/paid-report-cost.test.ts @@ -0,0 +1,203 @@ +/** + * PR 2 of GSTA-150: every trial's cost is attributed. A display-label record binds its cost by + * runSkillTest's testName (cost_case_id) without changing the failed record or failure class; a case + * with no record takes its sessions' streamed cost; a listed model-free case costs a known $0. + */ +import { describe, expect, test } from 'bun:test'; +import * as fs from 'node:fs'; +import * as os from 'node:os'; +import * as path from 'node:path'; +import { MODEL_FREE_CASES, caseCost, junitCensus } from '../scripts/lib/paid-report'; +import { anthropicUsageCostUsd, streamedUsageCostUsd } from '../lib/pricing'; +import { E2E_TOUCHFILES } from './helpers/touchfiles-data'; +import type { SessionLedgerRow } from './helpers/session-ledger'; +import { recordE2E } from './helpers/e2e-helpers'; +import { newTranscriptSessionId, pricedTranscript, ptyTranscriptCostUsd, transcriptFiles } from './helpers/pty/transcript-cost'; + +const ROOT = path.resolve(import.meta.dir, '..'); +const session = (over: Partial<SessionLedgerRow>): SessionLedgerRow => ({ key: 'k', runner: 'agent-sdk', started_at: 't', elapsed_ms: 1, end: 'aborted', ...over }); + +describe('pricing usage', () => { + test('cache writes bill 1.25x input (5-minute) and 2x (1-hour); reads at the cached rate', () => { + // claude-opus-5-5: input $4, output $20, cache read $0.20 per Mtok. + expect(anthropicUsageCostUsd({ input_tokens: 1_000_000, output_tokens: 1_000_000, cache_read_input_tokens: 1_000_000, cache_creation_input_tokens: 1_000_000 }, 'claude-opus-5-5')) + .toBeCloseTo(4 + 20 + 0.2 + 5, 6); + expect(anthropicUsageCostUsd({ cache_creation_input_tokens: 3_000_000, cache_creation: { ephemeral_5m_input_tokens: 1_000_000, ephemeral_1h_input_tokens: 2_000_000 } }, 'claude-opus-5-5')) + .toBeCloseTo(5 + 16, 6); + expect(anthropicUsageCostUsd({ cache_creation_input_tokens: 3_000_000, cache_creation: { ephemeral_1h_input_tokens: 2_000_000 } }, 'claude-opus-5-5')) + .toBeCloseTo(5 + 16, 6); + expect(anthropicUsageCostUsd({ input_tokens: 10 }, 'no-such-model')).toBeUndefined(); + }); + + test('streamed messages count once per id at their largest output, sidechains included; an unpriced model is unknown', () => { + const msg = (id: string, output: number, extra: Record<string, unknown> = {}) => ({ message: { id, model: 'claude-opus-5-5', usage: { input_tokens: 0, output_tokens: output } }, ...extra }); + expect(streamedUsageCostUsd([msg('a', 10), msg('a', 1_000_000), msg('b', 500_000, { parent_tool_use_id: 'tool-1' })])).toBeCloseTo(30, 6); + expect(streamedUsageCostUsd([{ message: { id: 'a', model: '<synthetic>', usage: { output_tokens: 5 } } }])).toBeUndefined(); + expect(streamedUsageCostUsd([{ message: { id: 'a', model: 'no-such-model', usage: { output_tokens: 5 } } }, msg('b', 5)])).toBeUndefined(); + expect(streamedUsageCostUsd([{ message: { id: 'a', usage: { output_tokens: 1_000_000 } } }], 'claude-opus-5-5')).toBeCloseTo(20, 6); + }); +}); + +describe('caseCost', () => { + test('a billed session\'s cost is already in the records; a streamed session adds what no record carries', () => { + expect(caseCost('x', [{ cost_usd: 0.25 }, { cost_usd: 0.1 }], [session({ billed: true, cost_usd: 9 })])).toEqual({ cost_usd: 0.35 }); + expect(caseCost('x', [{ cost_usd: 0 }], [session({ billed: false, streamed_cost_usd: 0.4 })])).toEqual({ cost_usd: 0.4 }); + expect(caseCost('x', [{ cost_usd: 0.2 }], [session({ runner: 'pty', billed: false })])).toEqual({ cost_usd: 0.2, cost_known: false }); + expect(caseCost('x', [{ cost_usd: 0.2, cost_known: false }], [])).toEqual({ cost_usd: 0.2, cost_known: false }); + }); + + test('a case with no record takes its sessions\' billed or streamed cost, else stays unknown', () => { + expect(caseCost('auq', [], [session({ billed: false, streamed_cost_usd: 0.123 })])).toEqual({ cost_usd: 0.12 }); + expect(caseCost('auq', [], [session({ billed: false })])).toEqual({ cost_usd: 0, cost_known: false }); + expect(caseCost('auq', [], [session({ runner: 'claude-p', billed: true })])).toEqual({ cost_usd: 0, cost_known: false }); + }); + + test('only a listed model-free case with neither record nor session costs a known $0', () => { + expect(caseCost('timeline-event-flow', [], [])).toEqual({ cost_usd: 0 }); + expect(caseCost('some-other-case', [], [])).toEqual({ cost_usd: 0, cost_known: false }); + }); + + test('every listed model-free case body starts no model session', () => { + for (const id of MODEL_FREE_CASES) { + const file = E2E_TOUCHFILES[id]?.find(entry => /^test\/[^/]+\.test\.ts$/.test(entry)); + expect(file, id).toBeTruthy(); + const source = fs.readFileSync(path.join(ROOT, file!), 'utf8'); + const start = source.search(new RegExp(`IfSelected\\(\\s*['"\`]${id}['"\`]`)); + expect(start, id).toBeGreaterThan(-1); + const rest = source.slice(start + 1); + const end = rest.search(/IfSelected\(/); + const body = end === -1 ? rest : rest.slice(0, end); + expect(body, id).not.toMatch(/runSkillTest|runAgentSdkTest|runCodex|launchClaudePty|runPtySession|claude-pty|callJudge|judge\w*\(/); + } + }); +}); + +describe('recordE2E cost_case_id', () => { + const entry = (name: string, testName?: string) => { + const tests: any[] = []; + const result: any = { toolCalls: [], browseErrors: [], exitReason: 'success', duration: 1, output: '', transcript: [], model: 'claude-opus-5-5', + costEstimate: { estimatedCost: 0.05, turnsUsed: 1, estimatedTokens: 1 }, ...(testName ? { testName } : {}) }; + recordE2E({ addTest: (t: any) => tests.push(t) } as any, name, 'suite', result); + return tests[0]; + }; + + test('a display-label record carries its registered runSkillTest testName as cost_case_id, and nothing else does', () => { + expect(entry('browse basic commands', 'browse-basic')).toMatchObject({ name: 'browse basic commands', cost_case_id: 'browse-basic' }); + expect(entry('browse-basic', 'browse-basic').cost_case_id).toBeUndefined(); + expect(entry('browse basic commands', 'not-a-registered-case').cost_case_id).toBeUndefined(); + expect(entry('browse basic commands').cost_case_id).toBeUndefined(); + }); +}); + +describe('junitCensus cost binding', () => { + const key = 'test/skill-e2e-bws.test.ts'; + const census = (records: any[], ledger: SessionLedgerRow[] = []) => { + const root = fs.mkdtempSync(path.join(os.tmpdir(), 'paid-report-cost-')); + const shard = path.join(root, 'shards', 'skill-e2e-bws'); + fs.mkdirSync(shard, { recursive: true }); + fs.writeFileSync(path.join(shard, 'junit.xml'), `<testsuites><testsuite name="${key}"> +<testcase name="browse-basic" classname="${key}" time="1"></testcase> +<testcase name="browse-snapshot" classname="${key}" time="1"><failure type="AssertionError" message="expected snapshot"/></testcase> +</testsuite></testsuites>`); + fs.writeFileSync(path.join(shard, 'session-ledger.jsonl'), ledger.map(row => JSON.stringify(row)).join('\n')); + const manifest: any = { version: 1, tier: 'gate', evalsAll: true, sliceCount: 1, profile: 'full', selection: { e2e: null, judges: null }, entries: [{ file: key, slice: 1, status: 'planned', estimatedMs: 1 }] }; + const result: any = { version: 1, tier: 'gate', profile: 'full', selection: { e2e: null, judges: null }, sliceIndex: 1, sliceCount: 1, attempt: 1, + outcomes: [{ files: [key], status: 'failed', exitCode: 1, elapsedMs: 10, executedTests: 2, skippedTests: 0 }] }; + try { return junitCensus(manifest, [{ root, result }], new Map([[key, records]]), {}); } finally { fs.rmSync(root, { recursive: true, force: true }); } + }; + const labelled = [ + { name: 'browse basic commands', passed: true, cost_usd: 0.05, cost_case_id: 'browse-basic' }, + { name: 'browse snapshot flags', passed: false, cost_usd: 0.06, cost_case_id: 'browse-snapshot', exit_reason: 'timeout', failure_class: 'infra', error: 'record error' }, + ]; + + test('display-label records bind their cost by cost_case_id in a multi-case shard', () => { + const cases = census(labelled).ruleCases; + expect(cases.map(c => [c.id, c.costUsd, c.costKnown])).toEqual([['browse-basic', 0.05, true], ['browse-snapshot', 0.06, true]]); + }); + + test('the failed record and failure class stay what the named records give, as without cost_case_id', () => { + const bound = census(labelled).ruleCases.find(c => c.id === 'browse-snapshot')!; + const unbound = census(labelled.map(({ cost_case_id, ...rest }) => rest)).ruleCases.find(c => c.id === 'browse-snapshot')!; + expect(unbound).toMatchObject({ costUsd: 0, costKnown: false }); + expect({ failureClass: bound.failureClass, error: bound.error, line: bound.line?.replace(/ {2}\[slice.*$/, '') }) + .toEqual({ failureClass: unbound.failureClass, error: unbound.error, line: unbound.line?.replace(/ {2}\[slice.*$/, '') }); + expect(bound.failureClass).toBe('assertion'); + }); + + test('a cost-only record never sets the trial\'s model, which keys its pass-rate series', () => { + const history = census(labelled.map(r => ({ ...r, model: 'claude-opus-5-5' }))).history; + expect(history.map(h => [h.case, h.model])).toEqual([['browse-basic', undefined], ['browse-snapshot', undefined]]); + }); +}); + +describe('PTY transcript pricing (GSTA-150 PR 3)', () => { + const SID = '11111111-2222-4333-8444-555555555555'; + const OTHER = '99999999-2222-4333-8444-555555555555'; + const assistant = (sid: string, id: string, model: string, usage: object, extra: object = {}) => + JSON.stringify({ type: 'assistant', sessionId: sid, cwd: '/fixture/cwd', message: { id, model, role: 'assistant', usage }, ...extra }); + const fixture = (write: (project: string) => void) => { + const config = fs.mkdtempSync(path.join(os.tmpdir(), 'pty-cost-')); + const project = path.join(config, 'projects', '-fixture-cwd'); + fs.mkdirSync(project, { recursive: true }); + write(project); + return config; + }; + + test('prices the session, its inline sidechains and subagent files, each message id once at its largest output', () => { + const config = fixture(project => { + fs.writeFileSync(path.join(project, `${SID}.jsonl`), [ + JSON.stringify({ type: 'user', sessionId: SID, message: { role: 'user', content: 'hi' } }), + assistant(SID, 'msg_a', 'claude-opus-5-5', { input_tokens: 1000, output_tokens: 10 }), + assistant(SID, 'msg_a', 'claude-opus-5-5', { input_tokens: 1000, output_tokens: 500 }), + assistant(SID, 'msg_side', 'claude-opus-5-5', { input_tokens: 0, output_tokens: 1000 }, { isSidechain: true }), + assistant(SID, 'msg_syn', '<synthetic>', { input_tokens: 0, output_tokens: 0 }), + '{"partial":', + ].join('\n')); + fs.mkdirSync(path.join(project, SID, 'subagents'), { recursive: true }); + fs.writeFileSync(path.join(project, SID, 'subagents', 'agent-x.jsonl'), + assistant(SID, 'msg_sub', 'claude-opus-5-5', { input_tokens: 0, cache_read_input_tokens: 10000, output_tokens: 0 }) + '\n'); + fs.writeFileSync(path.join(project, `${OTHER}.jsonl`), assistant(OTHER, 'msg_foreign', 'claude-opus-5-5', { input_tokens: 1_000_000 }) + '\n'); + }); + try { + // opus-5-5: $4 in, $20 out, $0.20 cached per MTok. + const expected = (1000 * 4 + 500 * 20 + 1000 * 20 + 10000 * 0.2) / 1_000_000; + expect(ptyTranscriptCostUsd(config, SID)).toBeCloseTo(expected, 6); + expect(pricedTranscript({ transcriptCostUsd: () => ptyTranscriptCostUsd(config, SID) }).streamed_cost_usd).toBeCloseTo(expected, 6); + } finally { fs.rmSync(config, { recursive: true, force: true }); } + }); + + test('stays cost-unknown without a transcript, a session id, usage, a priced model or a readable file, and never throws', () => { + const unpriced = fixture(project => fs.writeFileSync(path.join(project, `${SID}.jsonl`), + assistant(SID, 'msg_a', 'claude-opus-5-5', { output_tokens: 1 }) + '\n' + assistant(SID, 'msg_b', 'some-unpriced-model', { output_tokens: 1 }) + '\n')); + const empty = fixture(project => fs.writeFileSync(path.join(project, `${SID}.jsonl`), JSON.stringify({ type: 'user', sessionId: SID }) + '\n')); + const unreadable = fixture(project => fs.mkdirSync(path.join(project, `${SID}.jsonl`))); + try { + expect(ptyTranscriptCostUsd(unpriced, SID)).toBeUndefined(); + expect(ptyTranscriptCostUsd(empty, SID)).toBeUndefined(); + expect(ptyTranscriptCostUsd(empty, OTHER)).toBeUndefined(); + expect(ptyTranscriptCostUsd(unpriced, undefined)).toBeUndefined(); + expect(ptyTranscriptCostUsd(null, SID)).toBeUndefined(); + expect(ptyTranscriptCostUsd(path.join(empty, 'missing'), SID)).toBeUndefined(); + expect(ptyTranscriptCostUsd(unreadable, SID)).toBeUndefined(); + expect(newTranscriptSessionId(unreadable, new Set(), '/fixture/cwd')).toBeUndefined(); + expect(pricedTranscript(undefined)).toEqual({}); + expect(pricedTranscript({})).toEqual({}); + } finally { for (const dir of [unpriced, empty, unreadable]) fs.rmSync(dir, { recursive: true, force: true }); } + }); + + test('a launch claims only the one transcript it created for its own cwd', () => { + const cwd = fs.realpathSync(fs.mkdtempSync(path.join(os.tmpdir(), 'pty-cost-cwd-'))); + const line = (sid: string, at: string) => JSON.stringify({ type: 'user', sessionId: sid, cwd: at }) + '\n'; + const config = fixture(project => fs.writeFileSync(path.join(project, `${OTHER}.jsonl`), line(OTHER, cwd))); + try { + const before = transcriptFiles(config); + const project = path.join(config, 'projects', '-fixture-cwd'); + fs.writeFileSync(path.join(project, '22222222-2222-4333-8444-555555555555.jsonl'), line('22222222-2222-4333-8444-555555555555', '/a/concurrent/test')); + expect(newTranscriptSessionId(config, before, cwd)).toBeUndefined(); + fs.writeFileSync(path.join(project, `${SID}.jsonl`), line(SID, cwd)); + expect(newTranscriptSessionId(config, before, cwd)).toBe(SID); + fs.writeFileSync(path.join(project, '33333333-2222-4333-8444-555555555555.jsonl'), line('33333333-2222-4333-8444-555555555555', cwd)); + expect(newTranscriptSessionId(config, before, cwd)).toBeUndefined(); + } finally { fs.rmSync(config, { recursive: true, force: true }); fs.rmSync(cwd, { recursive: true, force: true }); } + }); +}); diff --git a/test/pricing-eval-plan.test.ts b/test/pricing-eval-plan.test.ts index 5f78c45d0..6b5478edb 100644 --- a/test/pricing-eval-plan.test.ts +++ b/test/pricing-eval-plan.test.ts @@ -13,7 +13,7 @@ import { EXCLUDED_BILLING_CATEGORIES, PRICING, estimateCostUsd, hasPricing, pric import * as helperPricing from './helpers/pricing'; import { PREREG_SECTIONS, checkPrereg, dryRun, formatEvalCalls, parseEvalCalls, pilotReport, preregTemplate, renderArms, renderDryRun, renderPilotReport, renderSpendTable, - resolveArms, settlePilot, startPilot, + resolveArms, settlePilot, startPilot, estimateTokens, REASONING_OUTPUT_FLOOR, isSmallTierModel, } from '../lib/eval-plan'; import { capyHost, type CapyHost } from './helpers/capy-host'; @@ -110,6 +110,52 @@ describe('dry run', () => { expect(dryRun({ input: rows, arms: ['gpt-6-astra'], retryPrompt: retry, outputBudget: 100 }).checks.output_budget.ok).toBe(false); expect(dryRun({ input: rows, arms: ['made-up'], retryPrompt: retry }).checks.price_table.missing).toEqual(['made-up']); }); + + test('R54: refuses a Haiku- or Sonnet-only plan unless it names a tier question, warns on a mix, and re-costs on frontier prices', () => { + const d = tmp(); + const rows = path.join(d, 'rows.jsonl'); + fs.writeFileSync(rows, [JSON.stringify({ prompt: 'hello world' }), JSON.stringify({ prompt: 'second row' })].join('\n') + '\n'); + const retry = path.join(d, 'retry.txt'); fs.writeFileSync(retry, 'retry\n'); + const small = dryRun({ input: rows, arms: ['claude-haiku-4-5', 'claude-sonnet-5-5#no-gstack'], retryPrompt: retry }); + expect(small.pass).toBe(false); + expect(small.checks.frontier).toMatchObject({ ok: false, small_tier: ['claude-haiku-4-5', 'claude-sonnet-5-5#no-gstack'], tier_question: null }); + const avgIn = Math.ceil((estimateTokens('hello world') + estimateTokens('second row')) / 2); + expect(small.checks.frontier.recost_usd['claude-opus-5-5']).toBe(2 * 2 * estimateCostUsd({ input: avgIn, output: REASONING_OUTPUT_FLOOR }, 'claude-opus-5-5')); + expect(small.checks.frontier.recost_usd['gpt-6.1-sol']).toBeGreaterThan(0); + expect(renderDryRun(small)).toContain('CHECK: frontier refused'); + const asked = dryRun({ input: rows, arms: ['claude-haiku-4-5'], retryPrompt: retry, tierQuestion: 'does the diet hold on Haiku' }); + expect(asked.pass).toBe(true); + expect(renderDryRun(asked)).toContain('CHECK: frontier ok (tier question'); + const mixed = dryRun({ input: rows, arms: ['claude-opus-5-5', 'claude-sonnet-5-5'], retryPrompt: retry }); + expect(mixed.pass).toBe(true); + expect(renderDryRun(mixed)).toContain('CHECK: frontier warn'); + const frontier = dryRun({ input: rows, arms: ['claude-opus-5-5', 'gpt-6.1-sol#no-gstack'], retryPrompt: retry }); + expect(frontier.checks.frontier).toMatchObject({ ok: true, small_tier: [] }); + expect(renderDryRun(frontier)).not.toContain('CHECK: frontier'); + expect(['claude-opus-5-5', 'gpt-6.1-sol', 'gpt-6-luna', 'gemini-3.8-flash'].some(isSmallTierModel)).toBe(false); + const dryFile = (name: string, r: unknown) => { const f = path.join(d, name); fs.writeFileSync(f, JSON.stringify(r)); return f; }; + const swapped = startPilot({ out: path.join(d, 'swapped'), cap: 5, n: 1, arms: ['claude-haiku-4-5'], dryRun: dryFile('frontier.json', frontier) }); + expect(swapped.error?.code).toBe('EVAL_DRY_RUN_FAILED'); + expect(fs.existsSync(path.join(d, 'swapped'))).toBe(false); + expect(startPilot({ out: path.join(d, 'asked'), cap: 5, n: 1, arms: ['claude-haiku-4-5'], dryRun: dryFile('asked.json', asked) }).error).toBeUndefined(); + expect(startPilot({ out: path.join(d, 'mixed'), cap: 5, n: 1, arms: ['claude-opus-5-5', 'claude-sonnet-5-5'], dryRun: dryFile('frontier2.json', frontier) }).error).toBeUndefined(); + }); + + test('R54 CLI: --tier-question refuses another flag as its answer', () => { + const host = capyHost(); + try { + const rows = path.join(host.base, 'rows.jsonl'); fs.writeFileSync(rows, JSON.stringify({ prompt: 'hello world' }) + '\n'); + const retry = path.join(host.base, 'retry.txt'); fs.writeFileSync(retry, 'retry\n'); + const run = (...extra: string[]) => spawnSync(BIN, ['dry-run', '--input', rows, '--arms', 'claude-haiku-4-5', '--retry-prompt', retry, ...extra], { cwd: host.base, env: host.env, encoding: 'utf8', timeout: 30_000 }); + const flagAnswer = run('--tier-question', '--json'); + expect(flagAnswer.status).not.toBe(0); + expect(flagAnswer.stderr).toContain('--tier-question needs the question'); + const refused = run(); + expect(refused.status).not.toBe(0); + expect(refused.stderr).toContain('R54'); + expect(run('--tier-question', 'does the diet hold on Haiku').status).toBe(0); + } finally { host.cleanup(); } + }); }); describe('priced pilot', () => { diff --git a/test/quarantine.test.ts b/test/quarantine.test.ts new file mode 100644 index 000000000..6d4b2ff20 --- /dev/null +++ b/test/quarantine.test.ts @@ -0,0 +1,442 @@ +/** + * gstack-flaky quarantine (GSTA-158 P2): registry refusals, renew and release, + * `check --base` against git fixtures, expiry, the quarantine attempt budget + * under the runner's full green verdict (never a false green), missing ids, + * the registry read from the base branch, and `report` over ledgers. + */ +import { afterAll, describe, expect, test } from 'bun:test'; +import * as fs from 'fs'; +import * as os from 'os'; +import * as path from 'path'; +import { spawnSync } from 'child_process'; +import { addEntry, checkRegistry, emptyRegistry, entryProblems, liveQuarantine, readLedgers, readRegistry, registryProblems, releaseEntry, renewEntry, reportLines, suiteCap, writeRegistry, type AddInput, type Registry } from '../lib/quarantine'; +import { renderResult, runFlaky } from '../lib/flaky-run'; + +const ROOT = path.resolve(import.meta.dir, '..'); +const BIN = path.join(ROOT, 'bin', 'gstack-flaky'); +const TMP = fs.mkdtempSync(path.join(os.tmpdir(), 'gstack-quarantine-')); +const tmp = () => fs.mkdtempSync(path.join(TMP, 't-')); +afterAll(() => fs.rmSync(TMP, { recursive: true, force: true })); + +const NOW = new Date('2026-10-29T00:00:00Z'); +const DAY = 86_400_000; +const at = (days: number) => new Date(NOW.getTime() + days * DAY); +const ids = (n: number, file = 'a.test.ts') => Array.from({ length: n }, (_, i) => `${file}::::t${i}`); +const add = (reg: Registry, id: string, over: Partial<AddInput> = {}, now = NOW) => + addEntry(reg, id, { owner: 'garry', ledger: 'https://ledger/1', failureClass: 'timing', reason: 'slow CI disk', evidence: ['https://run/1'], suiteIds: ids(100), ...over }, now); +const refusal = (fn: () => unknown) => { try { fn(); return 'ok'; } catch (e) { return (e as Error).message; } }; + +describe('registry: add, renew, release', () => { + test('add refuses more than 14 days, no evidence, product or infra class, an unknown id, a duplicate and the cap', () => { + const reg = emptyRegistry(); + expect(refusal(() => add(reg, 'a.test.ts::::t0', { days: 15 }))).toContain('from 1 to 14'); + expect(refusal(() => add(reg, 'a.test.ts::::t0', { evidence: [] }))).toContain('no evidence'); + expect(refusal(() => add(reg, 'a.test.ts::::t0', { failureClass: 'product' }))).toContain('class product is refused'); + expect(refusal(() => add(reg, 'a.test.ts::::t0', { failureClass: 'infra' }))).toContain('class infra is refused'); + expect(refusal(() => add(reg, 'a.test.ts::::t0', { failureClass: 'flaky' }))).toContain('is not one of detector, harness, timing, model-latency'); + expect(refusal(() => add(reg, 'a.test.ts::::nope'))).toContain('is not a test in the --junit report'); + expect(refusal(() => add(reg, 'a.test.ts::::t0', { owner: ' ' }))).toContain('no owner'); + expect(Object.keys(reg.entries)).toEqual([]); + const e = add(reg, 'a.test.ts::::t0'); + expect(e).toMatchObject({ enteredAt: NOW.toISOString(), expiresAt: at(7).toISOString(), renewals: [], suiteTests: 100 }); + expect(add(reg, 'a.test.ts::::t1', { days: 14 }).expiresAt).toBe(at(14).toISOString()); + expect(refusal(() => add(reg, 'a.test.ts::::t0'))).toContain('already has an entry'); + const small = emptyRegistry(); + for (let i = 0; i < 5; i++) add(small, `a.test.ts::::t${i}`, { suiteIds: ids(10) }); + expect(refusal(() => add(small, 'a.test.ts::::t5', { suiteIds: ids(10) }))).toContain('the cap for a 10-test suite is 5'); + expect(refusal(() => add(small, 'a.test.ts::::t5', { suiteIds: ids(10) }, at(8)))).toBe('ok'); + }); + + test('the cap is 10% of the suite, at least 1, and 5 under 50 tests', () => { + expect([1, 10, 49, 50, 99, 100, 1000].map(suiteCap)).toEqual([5, 5, 5, 5, 9, 10, 100]); + }); + + test('renew once, with new evidence and the owner named again; a second renewal is refused', () => { + const reg = emptyRegistry(); + add(reg, 'a.test.ts::::t0'); + const id = 'a.test.ts::::t0'; + expect(refusal(() => renewEntry(reg, id, { evidence: ['https://run/2'] }, at(6)))).toContain('names the owner again'); + expect(refusal(() => renewEntry(reg, id, { owner: 'garry', evidence: ['https://run/1'] }, at(6)))).toContain('new evidence'); + expect(refusal(() => renewEntry(reg, id, { owner: 'garry', evidence: ['https://run/2'], days: 8 }, at(6)))).toContain('1 to 7 days'); + const e = renewEntry(reg, id, { owner: 'garry', evidence: ['https://run/2'] }, at(6)); + expect(e.expiresAt).toBe(at(14).toISOString()); + expect(entryProblems(id, e, at(6))).toEqual([]); + expect(refusal(() => renewEntry(reg, id, { owner: 'garry', evidence: ['https://run/3'] }, at(13)))).toContain('a second renewal is refused'); + const expired = emptyRegistry(); + add(expired, id); + expect(renewEntry(expired, id, { owner: 'sam', evidence: ['https://run/9'], days: 3 }, at(10)).expiresAt).toBe(at(13).toISOString()); + const twice = { ...e, renewals: [...e.renewals, { ...e.renewals[0]!, evidence: ['https://run/3'] }] }; + expect(entryProblems(id, twice, at(6)).join()).toContain('one renewal is allowed'); + const farFuture = { ...e, expiresAt: at(400).toISOString(), renewals: [{ ...e.renewals[0]!, renewedAt: at(393).toISOString(), expiresAt: at(400).toISOString() }] }; + expect(entryProblems(id, farFuture, at(6)).join()).toContain('a renewal is dated before the entry or in the future'); + expect(liveQuarantine({ schema: 1, entries: { [id]: farFuture }, released: [] }, at(6)).ids.size).toBe(0); + expect(entryProblems(id, { ...e, renewals: [null as never] }, at(6)).join()).toContain('a renewal is not an object'); + }); + + test('release moves the entry to released with its reason and PR', () => { + const reg = emptyRegistry(); + add(reg, 'a.test.ts::::t0'); + expect(refusal(() => releaseEntry(reg, 'a.test.ts::::t0', { reason: 'fixed' }, at(2)))).toContain('--reason and --pr'); + const r = releaseEntry(reg, 'a.test.ts::::t0', { reason: 'fixed the wait', pr: 'https://github.com/o/r/pull/9' }, at(2)); + expect(reg.entries).toEqual({}); + expect(reg.released).toEqual([r]); + expect(r).toMatchObject({ id: 'a.test.ts::::t0', owner: 'garry', reason: 'fixed the wait', releasedAt: at(2).toISOString(), enteredAt: NOW.toISOString() }); + expect(refusal(() => releaseEntry(reg, 'a.test.ts::::t0', { reason: 'x', pr: 'y' }, at(2)))).toContain('no entry to release'); + }); + + test('expired and invalid entries are not quarantined; expiry prints the renew and release commands', () => { + const reg = emptyRegistry(); + add(reg, 'a.test.ts::::t0'); + expect([...liveQuarantine(reg, at(6)).ids]).toEqual(['a.test.ts::::t0']); + const later = liveQuarantine(reg, at(7)); + expect(later.ids.size).toBe(0); + expect(later.notices[0]).toContain('FLAKY_QUARANTINE_EXPIRED: a.test.ts::::t0 expired 2026-11-05 and is not quarantined'); + expect(later.notices[0]).toContain("renew: gstack-flaky quarantine renew 'a.test.ts::::t0' --owner"); + expect(later.notices[0]).toContain("release: gstack-flaky quarantine release 'a.test.ts::::t0' --reason"); + reg.entries['a.test.ts::::t1'] = { ...reg.entries['a.test.ts::::t0']!, expiresAt: at(30).toISOString() }; + reg.entries['a.test.ts::::t2'] = { ...reg.entries['a.test.ts::::t0']!, failureClass: 'infra' as never }; + const live = liveQuarantine(reg, at(1)); + expect([...live.ids]).toEqual(['a.test.ts::::t0']); + expect(live.notices.join('\n')).toContain('a.test.ts::::t1 is not quarantined: expires more than 14 days after it entered'); + expect(live.notices.join('\n')).toContain('a.test.ts::::t2 is not quarantined: class infra is refused'); + }); + + test('check enforces the cap and the entry rules on the whole registry', () => { + const reg = emptyRegistry(); + for (let i = 0; i < 5; i++) add(reg, `a.test.ts::::t${i}`, { suiteIds: ids(10) }); + expect(registryProblems(reg, NOW)).toEqual([]); + reg.entries['a.test.ts::::t5'] = { ...reg.entries['a.test.ts::::t0']! }; + expect(registryProblems(reg, NOW)).toEqual(['6 live entries, over the cap of 5 for a 10-test suite']); + expect(registryProblems(reg, NOW, 60)).toEqual([]); + expect(registryProblems(reg, at(8))).toEqual([]); + }); +}); + +const git = (dir: string, ...args: string[]) => { + const r = spawnSync('git', ['-c', 'user.name=t', '-c', 'user.email=t@example.com', '-c', 'commit.gpgsign=false', ...args], { cwd: dir, encoding: 'utf-8', timeout: 30_000 }); + if (r.status !== 0) throw new Error(`git ${args.join(' ')}: ${r.stderr}`); + return r.stdout; +}; + +/** A repository whose main branch quarantines test/a.test.ts::::slow and has released test/a.test.ts::::old; HEAD is a change branch. */ +function fixtureRepo(now = NOW) { + const dir = tmp(); + git(dir, 'init', '-q', '-b', 'main'); + fs.mkdirSync(path.join(dir, 'test')); + fs.writeFileSync(path.join(dir, 'test', 'a.test.ts'), '// a\n'); + fs.writeFileSync(path.join(dir, 'test', 'b.test.ts'), '// b\n'); + const reg = emptyRegistry(); + const suiteIds = ['test/a.test.ts::::slow', 'test/a.test.ts::::old', 'test/b.test.ts::::other']; + add(reg, 'test/a.test.ts::::old', { suiteIds }, now); + releaseEntry(reg, 'test/a.test.ts::::old', { reason: 'fixed', pr: '#1' }, now); + add(reg, 'test/a.test.ts::::slow', { suiteIds }, now); + writeRegistry(dir, reg); + git(dir, 'add', '-A'); + git(dir, 'commit', '-qm', 'seed'); + git(dir, 'checkout', '-qb', 'change'); + return { dir, reg, suiteIds }; +} + +const clone = (r: Registry): Registry => JSON.parse(JSON.stringify(r)); + +describe('check --base against a git fixture', () => { + test('an unchanged registry and a proper release pass', () => { + const { dir, reg } = fixtureRepo(); + expect(checkRegistry(dir, { base: 'main' }, NOW).problems).toEqual([]); + const next = clone(reg); + releaseEntry(next, 'test/a.test.ts::::slow', { reason: 'fixed', pr: '#2' }, at(1)); + writeRegistry(dir, next); + expect(checkRegistry(dir, { base: 'main' }, at(1)).problems).toEqual([]); + }); + + test('a deleted entry, a removed release record and rewritten history are refused', () => { + const { dir, reg } = fixtureRepo(); + const deleted = clone(reg); + delete deleted.entries['test/a.test.ts::::slow']; + writeRegistry(dir, deleted); + expect(checkRegistry(dir, { base: 'main' }, NOW).problems.join('\n')).toContain('test/a.test.ts::::slow: removed without a release record'); + const unreleased = clone(reg); + unreleased.released = []; + writeRegistry(dir, unreleased); + expect(checkRegistry(dir, { base: 'main' }, NOW).problems.join('\n')).toContain('test/a.test.ts::::old: its release record of'); + const restarted = clone(reg); + restarted.entries['test/a.test.ts::::slow']!.enteredAt = at(1).toISOString(); + writeRegistry(dir, restarted); + expect(checkRegistry(dir, { base: 'main' }, at(1)).problems.join('\n')).toContain('enteredAt changed'); + }); + + test('an entry added in the same change that edits its test file is refused; without the edit it passes', () => { + const { dir, reg, suiteIds } = fixtureRepo(); + const next = clone(reg); + add(next, 'test/b.test.ts::::other', { suiteIds }); + writeRegistry(dir, next); + expect(checkRegistry(dir, { base: 'main' }, NOW).problems).toEqual([]); + fs.writeFileSync(path.join(dir, 'test', 'b.test.ts'), '// b, now broken\n'); + git(dir, 'commit', '-qam', 'break b and quarantine it'); + expect(checkRegistry(dir, { base: 'main' }, NOW).problems).toEqual([ + 'test/b.test.ts::::other: added in the same change that edits test/b.test.ts; a change cannot quarantine the test it touches (land the entry on its own, or fix the test)', + ]); + }); + + test('a non-ASCII test path is matched too (git would quote it by default)', () => { + const { dir, reg } = fixtureRepo(); + fs.writeFileSync(path.join(dir, 'test', 'über.test.ts'), '// ü\n'); + git(dir, 'add', '-A'); + git(dir, 'commit', '-qm', 'add über'); + const next = clone(reg); + add(next, 'test/über.test.ts::::t', { suiteIds: ['test/über.test.ts::::t', 'test/a.test.ts::::slow'] }); + writeRegistry(dir, next); + expect(checkRegistry(dir, { base: 'main' }, NOW).problems.join('\n')).toContain('test/über.test.ts::::t: added in the same change that edits test/über.test.ts'); + }); + + test('the bin: check exits 1 with QUARANTINE_REFUSED lines, and an unknown base exits 3', () => { + const { dir, reg } = fixtureRepo(new Date()); + const deleted = clone(reg); + delete deleted.entries['test/a.test.ts::::slow']; + writeRegistry(dir, deleted); + const r = spawnSync(BIN, ['quarantine', 'check', '--base', 'main'], { cwd: dir, encoding: 'utf-8', timeout: 30_000 }); + expect(r.status).toBe(1); + expect(r.stdout).toContain('QUARANTINE_REFUSED: test/a.test.ts::::slow: removed without a release record'); + expect(r.stdout).toContain('verdict=fail'); + const missing = spawnSync(BIN, ['quarantine', 'check', '--base', 'no-such-branch'], { cwd: dir, encoding: 'utf-8', timeout: 30_000 }); + expect([missing.status, missing.stderr.includes('(FLAKY_QUARANTINE_BASE)')]).toEqual([3, true]); + }); +}); + +/** A fake runner: the attempt number decides the report, exit status, output and signal. */ +function fakeRun(reports: (n: number, argv: string[]) => string | null, exits: (n: number) => number, outputs: (n: number) => string = () => 'Ran 3 tests across 1 file. [3ms]\n', signals: (n: number) => string | undefined = () => undefined) { + const calls: string[][] = []; + const spawn = async (argv: string[], _env: NodeJS.ProcessEnv, cwd: string) => { + calls.push(argv); + const xml = reports(calls.length, argv); + if (xml !== null) fs.writeFileSync(path.join(cwd, 'r.xml'), xml); + const signal = signals(calls.length); + return { exit: exits(calls.length), output: outputs(calls.length), ...(signal ? { signal } : {}) }; + }; + return { calls, spawn }; +} + +const suite = (cases: string, file = 'a.test.ts') => `<testsuites name="bun test"><testsuite name="${file}" file="${file}">${cases}</testsuite></testsuites>`; +const pass = (name: string) => `<testcase name="${name}" classname="" file="a.test.ts"/>`; +const fail = (name: string) => `<testcase name="${name}" classname="" file="a.test.ts"><failure message="boom"/></testcase>`; +const Q = new Set(['a.test.ts::::q']); +const run = (f: ReturnType<typeof fakeRun>, extra: Partial<Parameters<typeof runFlaky>[0]> = {}) => + runFlaky({ command: ['bun', 'test'], junit: 'r.xml', maxReruns: 3, cwd: tmp(), spawn: f.spawn, env: {}, now: () => NOW, quarantined: Q, ...extra }); + +describe('the quarantine attempt budget under the full green verdict', () => { + test('a quarantined test that fails all 3 attempts is a hard break', async () => { + const f = fakeRun(() => suite(pass('a') + fail('q')), () => 1); + const r = await run(f); + expect(f.calls).toHaveLength(3); + expect(r.exitCode).toBe(1); + expect(r.outcomes).toMatchObject([{ status: 'hard-break', attempts: ['fail', 'fail', 'fail'], reason: 'failed all 3 attempts: a hard break, not a flake' }]); + expect(r.ledger.map(l => [l.kind, l.id, l.rerun_scope])).toEqual([['hard-break', 'a.test.ts::::q', 'command']]); + expect(renderResult(r, '/l').at(-1)).toBe('FLAKY_RESULT: tests=2 failed=1 flaky=0 quarantined=1 reruns=2 command_exit=1 verdict=fail ledger=/l'); + }); + + test('it passes on attempt 3 only on the runner\'s full green verdict, listed as quarantined and not as a pass', async () => { + const f = fakeRun(n => suite(pass('a') + (n < 3 ? fail('q') : pass('q'))), n => n < 3 ? 1 : 0); + const r = await run(f); + expect(f.calls).toHaveLength(3); + expect(r.exitCode).toBe(0); + expect(r.outcomes).toMatchObject([{ status: 'quarantined-pass', attempts: ['fail', 'fail', 'pass'] }]); + expect(r.ledger[0]).toMatchObject({ kind: 'quarantined-pass', attempts: ['fail', 'fail', 'pass'] }); + expect(renderResult(r, '/l')).toEqual(['FLAKY: quarantined-pass a.test.ts::::q attempts=fail,fail,pass', 'FLAKY_RERUN: scope=command (the default; --rerun-scope test reruns the failed test alone)', + 'FLAKY_RESULT: tests=2 failed=0 flaky=0 quarantined=1 reruns=2 command_exit=1 verdict=pass ledger=/l']); + }); + + test('false-green regression: exit 1 from outside the report never turns green because only a quarantined test failed', async () => { + const greenReportLaterExit1 = fakeRun(n => suite(pass('a') + (n === 1 ? fail('q') : pass('q'))), () => 1); + const a = await run(greenReportLaterExit1); + expect(greenReportLaterExit1.calls).toHaveLength(2); + expect(a.exitCode).toBe(1); + expect(a.outcomes).toMatchObject([{ status: 'quarantined-fail', attempts: ['fail', 'pass'], reason: 'rerun: the command exited 1' }]); + const alwaysExit1 = fakeRun(() => suite(pass('a') + fail('q')), () => 1, () => 'All files | % Funcs | % Lines |\nRan 2 tests across 1 file.\n'); + const b = await run(alwaysExit1, { rerunScope: 'test' }); + expect(alwaysExit1.calls.every(c => c.join(' ') === 'bun test')).toBe(true); + expect([b.exitCode, b.outcomes[0]!.status]).toEqual([1, 'hard-break']); + }); + + test('the bin keeps a coverage-style exit 1 red while the only reported failure is quarantined', () => { + const dir = tmp(); + git(dir, 'init', '-q', '-b', 'main'); + const reg = emptyRegistry(); + add(reg, 'a.test.ts::::q', { suiteIds: ['a.test.ts::::a', 'a.test.ts::::q'] }, new Date()); + writeRegistry(dir, reg); + const runner = path.join(dir, 'runner.sh'); + fs.writeFileSync(runner, ['#!/usr/bin/env bash', 'echo x >> count', `printf '%s' '${suite(pass('a') + fail('q'))}' > r.xml`, 'exit 1'].join('\n'), { mode: 0o755 }); + const r = spawnSync(BIN, ['run', '--junit', 'r.xml', '--ledger', path.join(dir, 'l.jsonl'), '--', runner], { cwd: dir, encoding: 'utf-8', timeout: 30_000, env: { ...process.env, GITHUB_ACTIONS: '', GITHUB_STEP_SUMMARY: '' } }); + expect(r.status).toBe(1); + expect(r.stdout).toContain('FLAKY: hard-break a.test.ts::::q attempts=fail,fail,fail'); + expect(r.stdout).toContain('quarantined=1 reruns=2 command_exit=1 verdict=fail'); + expect(fs.readFileSync(path.join(dir, 'count'), 'utf-8').trim().split('\n')).toHaveLength(3); + }); + + test('non-quarantined failures keep one rerun; a new non-quarantined failure ends the budget', async () => { + const both = fakeRun(n => suite((n === 1 ? fail('a') : fail('a')) + (n === 1 ? fail('q') : pass('q'))), () => 1); + const r = await run(both); + expect(both.calls).toHaveLength(2); + expect(r.outcomes.map(o => [o.test.id, o.status])).toEqual([['a.test.ts::::a', 'rerun-fail'], ['a.test.ts::::q', 'quarantined-fail']]); + const newFailure = fakeRun(n => suite((n === 1 ? pass('a') : fail('a')) + fail('q')), () => 1); + const s = await run(newFailure); + expect(newFailure.calls).toHaveLength(2); + expect([s.exitCode, s.outcomes[0]!.status]).toEqual([1, 'quarantined-fail']); + }); + + test('a flaky test and a quarantined test both clear on the attempt that is fully green', async () => { + const f = fakeRun(n => suite((n === 1 ? fail('a') : pass('a')) + (n < 3 ? fail('q') : pass('q'))), n => n < 3 ? 1 : 0); + const r = await run(f); + expect(f.calls).toHaveLength(3); + expect(r.exitCode).toBe(0); + expect(r.outcomes.map(o => [o.status, o.attempts.join(',')])).toEqual([['flaky-pass', 'fail,pass,pass'], ['quarantined-pass', 'fail,fail,pass']]); + }); + + test('a killed attempt or a missing first-run test ends the budget red', async () => { + const killed = fakeRun(() => suite(pass('a') + fail('q')), n => n === 1 ? 1 : 128, undefined, n => n === 2 ? 'SIGTERM' : undefined); + expect((await run(killed)).exitCode).toBe(1); + expect(killed.calls).toHaveLength(2); + const shrunk = fakeRun(n => n === 1 ? suite(pass('a') + fail('q')) : suite(fail('q')), () => 1); + expect((await run(shrunk)).exitCode).toBe(1); + expect(shrunk.calls).toHaveLength(2); + }); + + test('a quarantined test that passes is listed, ledgered for the exit rule, and the run is green', async () => { + const r = await run(fakeRun(() => suite(pass('a') + pass('q')), () => 0)); + expect(r).toMatchObject({ exitCode: 0, reruns: 0, quarantined: 1 }); + expect(r.ledger.map(l => [l.kind, l.attempts])).toEqual([['quarantined-pass', ['pass']]]); + expect(renderResult(r, '/l').at(-1)).toContain('failed=0 flaky=0 quarantined=1'); + }); + + test('quarantined failures do not count against --max-reruns', async () => { + const f = fakeRun(n => suite(pass('a') + (n === 1 ? fail('q') : pass('q'))), n => n === 1 ? 1 : 0); + expect((await run(f, { maxReruns: 0 })).exitCode).toBe(0); + }); + + test('--rerun-scope test gives the quarantined test the same budget on the targeted path', async () => { + const f = fakeRun((n, argv) => argv.length === 2 ? suite(pass('a') + fail('q')) : suite(n < 3 ? fail('q') : pass('q')), n => n < 3 ? 1 : 0); + const r = await run(f, { rerunScope: 'test' }); + expect(f.calls.slice(1)).toEqual([['bun', 'test', 'a.test.ts', '--test-name-pattern', '^q$'], ['bun', 'test', 'a.test.ts', '--test-name-pattern', '^q$']]); + expect(r.exitCode).toBe(0); + expect(r.outcomes).toMatchObject([{ status: 'quarantined-pass', attempts: ['fail', 'fail', 'pass'] }]); + const notQ = fakeRun((n, argv) => argv.length === 2 ? suite(pass('q') + fail('a')) : suite(fail('a')), () => 1); + expect((await run(notQ, { rerunScope: 'test' })).exitCode).toBe(1); + expect(notQ.calls).toHaveLength(2); + }); + + test('an expired entry gives no budget: one rerun, as for any test', async () => { + const reg = emptyRegistry(); + add(reg, 'a.test.ts::::q', { suiteIds: ['a.test.ts::::q'] }); + const f = fakeRun(n => suite(pass('a') + (n < 3 ? fail('q') : pass('q'))), n => n < 3 ? 1 : 0); + const r = await run(f, { quarantined: liveQuarantine(reg, at(8)).ids }); + expect(f.calls).toHaveLength(2); + expect([r.exitCode, r.outcomes[0]!.status, r.quarantined]).toEqual([1, 'rerun-fail', 0]); + }); +}); + +describe('missing quarantined ids', () => { + test('a quarantined id missing from a run that included its file blocks', async () => { + const f = fakeRun(() => suite(pass('a') + pass('b')), () => 0); + const r = await run(f, { quarantined: new Set(['a.test.ts::::gone']) }); + expect(f.calls).toHaveLength(1); + expect(r.exitCode).toBe(1); + expect(r.outcomes).toMatchObject([{ status: 'quarantined-fail', reason: 'quarantined, and missing from a run that included its file' }]); + expect(r.ledger[0]).toMatchObject({ kind: 'quarantined-fail', id: 'a.test.ts::::gone' }); + }); + + test('a run that did not include its file (a shard, a diff selection) does not block', async () => { + const r = await run(fakeRun(() => suite(pass('a')), () => 0), { quarantined: new Set(['b.test.ts::::gone', 'a.test.ts:: chromium ::x']) }); + expect(r).toMatchObject({ exitCode: 0, outcomes: [], quarantined: 0 }); + }); +}); + +describe('the registry read from the base branch', () => { + test('readRegistry --base sees the base copy, not the change\'s own entry', () => { + const { dir, reg, suiteIds } = fixtureRepo(); + const next = clone(reg); + add(next, 'test/b.test.ts::::other', { suiteIds }); + writeRegistry(dir, next); + expect(Object.keys(readRegistry(dir).entries).sort()).toEqual(['test/a.test.ts::::slow', 'test/b.test.ts::::other']); + expect(Object.keys(readRegistry(dir, 'main').entries)).toEqual(['test/a.test.ts::::slow']); + }); + + test('the bin: a change that quarantines its own failing test gets no budget with --base', () => { + const dir = tmp(); + git(dir, 'init', '-q', '-b', 'main'); + git(dir, 'commit', '-q', '--allow-empty', '-m', 'seed'); + git(dir, 'checkout', '-qb', 'change'); + fs.writeFileSync(path.join(dir, 'seed.xml'), suite(pass('a') + pass('b'))); + const addRun = spawnSync(BIN, ['quarantine', 'add', 'a.test.ts::::b', '--owner', 'garry', '--ledger', 'https://l/1', '--class', 'timing', '--reason', 'slow', '--evidence', 'https://run/1', '--junit', 'seed.xml'], { cwd: dir, encoding: 'utf-8', timeout: 30_000 }); + expect([addRun.status, addRun.stdout.startsWith('QUARANTINE_ADDED: a.test.ts::::b owner=garry class=timing')]).toEqual([0, true]); + const runner = path.join(dir, 'runner.sh'); + fs.writeFileSync(runner, [ + '#!/usr/bin/env bash', + 'n=$(cat count 2>/dev/null || echo 0); echo $((n+1)) > count', + `if [ "$n" -lt 2 ]; then printf '%s' '${suite(pass('a') + fail('b'))}' > r.xml; exit 1; fi`, + `printf '%s' '${suite(pass('a') + pass('b'))}' > r.xml`, + ].join('\n'), { mode: 0o755 }); + const flaky = (extra: string[]) => { + fs.rmSync(path.join(dir, 'count'), { force: true }); + return spawnSync(BIN, ['run', '--junit', 'r.xml', '--ledger', path.join(dir, 'l.jsonl'), ...extra, '--', runner], { cwd: dir, encoding: 'utf-8', timeout: 30_000, env: { ...process.env, GITHUB_ACTIONS: '', GITHUB_STEP_SUMMARY: '' } }); + }; + const own = flaky([]); + expect([own.status, own.stdout.includes('FLAKY: quarantined-pass a.test.ts::::b attempts=fail,fail,pass')]).toEqual([0, true]); + const fromBase = flaky(['--base', 'main']); + expect([fromBase.status, fromBase.stdout.includes('FLAKY: rerun-fail a.test.ts::::b')]).toEqual([1, true]); + expect(fs.readFileSync(path.join(dir, 'count'), 'utf-8').trim()).toBe('2'); + const badBase = flaky(['--base', 'no-such-branch']); + expect([badBase.status, badBase.stderr.includes('(FLAKY_QUARANTINE_BASE)')]).toEqual([3, true]); + }); +}); + +describe('quarantine CLI and report', () => { + test('add, renew, release through the bin; refusals exit 1 and usage exits 2', () => { + const dir = tmp(); + fs.writeFileSync(path.join(dir, 'seed.xml'), suite(pass('a') + pass('b'))); + const q = (...args: string[]) => spawnSync(BIN, ['quarantine', ...args], { cwd: dir, encoding: 'utf-8', timeout: 30_000 }); + const base = ['--owner', 'garry', '--ledger', 'https://l/1', '--reason', 'slow', '--evidence', 'https://run/1', '--junit', 'seed.xml']; + const product = q('add', 'a.test.ts::::b', ...base, '--class', 'product'); + expect([product.status, product.stderr.includes('class product is refused'), product.stderr.includes('(FLAKY_QUARANTINE_REFUSED)')]).toEqual([1, true, true]); + expect(q('add', 'a.test.ts::::b', ...base, '--class', 'harness').status).toBe(0); + expect(q('renew', 'a.test.ts::::b', '--owner', 'garry', '--evidence', 'https://run/2').status).toBe(0); + expect(q('renew', 'a.test.ts::::b', '--owner', 'garry', '--evidence', 'https://run/3').status).toBe(1); + expect(q('check').stdout).toContain('QUARANTINE_CHECK: live=1 cap=5 base=none verdict=pass'); + expect(q('release', 'a.test.ts::::b', '--reason', 'fixed', '--pr', '#7').status).toBe(0); + const saved = JSON.parse(fs.readFileSync(path.join(dir, '.gstack', 'quarantine.json'), 'utf-8')) as Registry; + expect([Object.keys(saved.entries), saved.released.map(r => [r.id, r.pr, r.renewals.length])]).toEqual([[], [['a.test.ts::::b', '#7', 1]]]); + expect(q('add', 'a.test.ts::::b', '--bogus', 'x').status).toBe(2); + expect(q('frobnicate').status).toBe(2); + }); + + test('report: expired first, then soonest-expiring; the exit rule needs 10 consecutive clean passes from the ledgers', () => { + const reg = emptyRegistry(); + add(reg, 'a.test.ts::::t0', { days: 14 }); + add(reg, 'a.test.ts::::t1', { days: 2 }); + add(reg, 'a.test.ts::::t2', { days: 1 }, at(-5)); + const without = reportLines(reg, NOW); + expect(without.map(l => l.split(' ').slice(0, 2).join(' '))).toEqual(['FLAKY_QUARANTINE_EXPIRED: a.test.ts::::t2', 'QUARANTINE: a.test.ts::::t1', 'QUARANTINE: a.test.ts::::t0', 'QUARANTINE_REPORT: live=2']); + expect(without[1]).toContain('days_left=2'); + expect(without[1]).toContain("EXPIRING (renew: gstack-flaky quarantine renew 'a.test.ts::::t1'"); + expect(without.at(-1)).toBe('QUARANTINE_REPORT: live=2 expired=1 expiring=1 ready=unchecked exit_rule=not checked (no --ledger given)'); + const dir = tmp(); + fs.mkdirSync(path.join(dir, 'run-1', 'flaky-junit-ledger-e2e'), { recursive: true }); + const lineFor = (id: string, i: number, kind = 'quarantined-pass', attempts = ['pass']) => JSON.stringify({ ts: new Date(NOW.getTime() + i * 1000).toISOString(), kind, id, attempts }); + const t0 = [lineFor('a.test.ts::::t0', 0, 'hard-break', ['fail', 'fail', 'fail']), ...Array.from({ length: 10 }, (_, i) => lineFor('a.test.ts::::t0', i + 1))]; + const t1 = [...Array.from({ length: 9 }, (_, i) => lineFor('a.test.ts::::t1', i)), lineFor('a.test.ts::::t1', 9, 'quarantined-pass', ['fail', 'pass'])]; + fs.writeFileSync(path.join(dir, 'run-1', 'flaky-junit-ledger-e2e', 'flaky-junit-ledger.jsonl'), [...t0, ...t1, 'not json'].join('\n') + '\n'); + const ledgers = readLedgers([dir]); + expect([ledgers.records.length, ledgers.skipped]).toEqual([21, 1]); + const withLedger = reportLines(reg, NOW, ledgers.records); + expect(withLedger.find(l => l.includes('t0 '))).toContain("recent=pass,pass,pass,pass,pass clean_streak=10 READY_TO_RELEASE: gstack-flaky quarantine release 'a.test.ts::::t0'"); + expect(withLedger.find(l => l.includes('t1 '))).toContain('recent=pass,pass,pass,pass,flaky clean_streak=0'); + expect(withLedger.at(-1)).toBe('QUARANTINE_REPORT: live=2 expired=1 expiring=1 ready=1 exit_rule=checked (10 consecutive clean passes)'); + }); + + test('every FLAKY_QUARANTINE_ code is in the docs table, and the docs say the registries share no schema with CASE_QUARANTINE', () => { + const doc = fs.readFileSync(path.join(ROOT, 'docs', 'flaky.md'), 'utf-8'); + const src = fs.readFileSync(path.join(ROOT, 'lib', 'quarantine.ts'), 'utf-8') + fs.readFileSync(path.join(ROOT, 'bin', 'gstack-flaky'), 'utf-8'); + const codes = [...new Set(src.match(/FLAKY_QUARANTINE_[A-Z_]+/g))]; + expect(codes.length).toBeGreaterThan(4); + expect(codes.filter(c => !doc.includes(`| \`${c}\` |`))).toEqual([]); + expect(doc).toContain('CASE_QUARANTINE'); + }); +}); diff --git a/test/sdk-system-prompt-tripwire.test.ts b/test/sdk-system-prompt-tripwire.test.ts new file mode 100644 index 000000000..953019b77 --- /dev/null +++ b/test/sdk-system-prompt-tripwire.test.ts @@ -0,0 +1,135 @@ +/** + * Every Agent SDK caller hands Claude Code its real system prompt, or names + * why not. Without systemPrompt the SDK runs a bare stub that drops the "run + * /skill via Skill" line, so a skill arm never learns to load its skill and a + * null result means nothing (docs/TESTING_INTERNALS.md#agent-sdk-system-prompt). + */ +import { describe, test, expect } from 'bun:test'; +import * as fs from 'fs'; +import * as path from 'path'; +import { CLAUDE_CODE_PRESET, sdkSystemPrompt } from './helpers/sdk-system-prompt'; +import { runAgentSdkTest } from './helpers/agent-sdk-runner'; + +const ROOT = path.resolve(import.meta.dir, '..'); +const SELF = 'test/sdk-system-prompt-tripwire.test.ts'; +const DEFINERS = new Set(['test/helpers/agent-sdk-runner.ts', 'test/helpers/sdk-system-prompt.ts']); + +/** Index just past the bracket that closes the one opened at text[open]. */ +function closeOf(text: string, open: number): number { + const pairs: Record<string, string> = { '(': ')', '{': '}', '[': ']' }; + const stack: string[] = []; + for (let i = open; i < text.length; i++) { + const c = text[i]!; + if (c === '/' && text[i + 1] === '/') { i = text.indexOf('\n', i); if (i < 0) return text.length; continue; } + if (c === '/' && text[i + 1] === '*') { i = text.indexOf('*/', i + 2) + 1; continue; } + if (c === "'" || c === '"' || c === '\x60') { + for (i++; i < text.length && text[i] !== c; i++) if (text[i] === '\\') i++; + continue; + } + if (pairs[c]) stack.push(pairs[c]!); + else if (c === stack[stack.length - 1]) { stack.pop(); if (!stack.length) return i + 1; } + } + return text.length; +} + +/** Text of one property value: from after "key:" to the next top-level , } or ). */ +function valueAt(text: string, start: number): string { + let i = start; + while (i < text.length && !',})'.includes(text[i]!)) { + const c = text[i]!; + if ('({['.includes(c)) { i = closeOf(text, i); continue; } + if (c === "'" || c === '"' || c === '\x60') { for (i++; i < text.length && text[i] !== c; i++) if (text[i] === '\\') i++; } + i++; + } + return text.slice(start, i).trim(); +} + +/** Why a systemPrompt value is refused, or null when it is the preset, names its reason, or forwards a caller's value. */ +export function promptValueProblem(value: string): string | null { + if (/^['"\x60]/.test(value)) return 'a bare string prompt (empty runs the SDK stub); pass CLAUDE_CODE_PRESET or name a reason'; + if (/^[\w$.?]+$/.test(value)) return null; + const objects = [...value.matchAll(/\{[^{}]*\}/g)].map(m => m[0]); + if (!objects.length) return null; + for (const o of objects) { + if (/type:\s*'preset'/.test(o) && /preset:\s*'claude_code'/.test(o)) continue; + if (/type:\s*'(sdk-default|custom)'/.test(o) && /reason:\s*(['"\x60])\s*[^'"\x60\s][^'"\x60]*\1/.test(o)) continue; + return 'a prompt that is neither the Claude Code preset nor a named sdk-default/custom reason'; + } + return null; +} + +/** Every refused systemPrompt and every SDK call that omits one, in one file's source. */ +export function scanSource(file: string, source: string): string[] { + const problems: string[] = []; + const line = (i: number) => source.slice(0, i).split('\n').length; + if (!DEFINERS.has(file)) { + for (const m of source.matchAll(/\bsystemPrompt\s*:/g)) { + const problem = promptValueProblem(valueAt(source, m.index! + m[0].length)); + if (problem) problems.push(file + ':' + line(m.index!) + ': ' + problem); + } + } + const sdk = /import\s*\{[^}]*\bquery\b[^}]*\}\s*from\s*'@anthropic-ai\/claude-agent-sdk'|\(await import\('@anthropic-ai\/claude-agent-sdk'\)\)\.query|const\s*\{\s*query\s*\}\s*=\s*await import\('@anthropic-ai\/claude-agent-sdk'\)/.test(source); + const calls = [...source.matchAll(/(?<![\w.])runAgentSdkTest\(/g)].map(m => m.index! + m[0].length - 1); + if (sdk && !DEFINERS.has(file)) calls.push(...[...source.matchAll(/(?<![\w.])query\(/g)].map(m => m.index! + m[0].length - 1)); + for (const open of calls) { + if (/function\s+runAgentSdkTest\($/.test(source.slice(Math.max(0, open - 40), open + 1))) continue; + const arg = source.slice(open + 1, closeOf(source, open) - 1).trim(); + if (!arg.startsWith('{')) continue; + if (/\bsystemPrompt\b|\.\.\.\s*sdkSystemPrompt\(/.test(arg)) continue; + if (/\.\.\./.test(arg)) continue; + problems.push(file + ':' + line(open) + ': SDK call without systemPrompt; pass CLAUDE_CODE_PRESET or name a reason'); + } + return problems; +} + +function trackedSources(): string[] { + const out: string[] = []; + const walk = (dir: string) => { + for (const entry of fs.readdirSync(path.join(ROOT, dir), { withFileTypes: true })) { + const rel = path.posix.join(dir, entry.name); + if (entry.isDirectory()) { if (entry.name !== 'node_modules' && rel !== 'test/fixtures') walk(rel); } + else if (/\.tsx?$/.test(entry.name) && rel !== SELF) out.push(rel); + } + }; + walk('test'); walk('scripts'); + return out; +} + +describe('Agent SDK system prompt tripwire', () => { + test('every runAgentSdkTest and SDK query caller passes the preset or names its reason', () => { + const files = trackedSources(); + const problems = files.flatMap(file => scanSource(file, fs.readFileSync(path.join(ROOT, file), 'utf8'))); + expect(problems).toEqual([]); + const callers = files.filter(file => /(?<![\w.])runAgentSdkTest\(/.test(fs.readFileSync(path.join(ROOT, file), 'utf8'))); + expect(callers).toContain('test/helpers/ship-hook-actor.ts'); + expect(callers.length).toBeGreaterThan(10); + }); + + test('the scanner refuses a missing, empty, bare or unnamed prompt and accepts the preset, a named reason or a forward', () => { + const scan = (body: string) => scanSource('x.ts', body); + expect(scan("runAgentSdkTest({ userPrompt: 'go', workingDirectory: d })")).toHaveLength(1); + expect(scan("runAgentSdkTest({ systemPrompt: '', userPrompt: 'go' })")).toHaveLength(1); + expect(scan("runAgentSdkTest({ systemPrompt: 'be terse', userPrompt: 'go' })")).toHaveLength(1); + expect(scan("runAgentSdkTest({ systemPrompt: { type: 'sdk-default', reason: '' }, userPrompt: 'go' })")).toHaveLength(1); + expect(scan("import { query } from '@anthropic-ai/claude-agent-sdk';\nquery({ prompt: 'p', options: { tools: [] } })")).toHaveLength(1); + expect(scan("runAgentSdkTest({ systemPrompt: { type: 'preset', preset: 'claude_code' }, userPrompt: 'go' })")).toEqual([]); + expect(scan("runAgentSdkTest({ systemPrompt: a ? { type: 'preset', preset: 'claude_code', append: x } : { type: 'preset', preset: 'claude_code' } })")).toEqual([]); + expect(scan("runAgentSdkTest({ systemPrompt: { type: 'sdk-default', reason: 'stub provider' }, userPrompt: 'go' })")).toEqual([]); + expect(scan("runAgentSdkTest({ systemPrompt: CLAUDE_CODE_PRESET, userPrompt: 'go' })")).toEqual([]); + expect(scan("runAgentSdkTest({ ...options, signal })")).toEqual([]); + expect(scan("const o = { systemPrompt: options.systemPrompt };")).toEqual([]); + expect(scan("import { query } from '@anthropic-ai/claude-agent-sdk';\nquery({ prompt: 'p', options: { ...sdkSystemPrompt({ type: 'sdk-default', reason: 'probe' }) } })")).toEqual([]); + expect(scan("import { query } from '@anthropic-ai/claude-agent-sdk';\nquery({ ...args, options: { ...args.options, cwd } })")).toEqual([]); + }); + + test('the runner refuses a bare or unnamed prompt before it starts', async () => { + const queryProvider = (() => { throw new Error('query must not run'); }) as never; + for (const systemPrompt of ['', 'be terse', undefined, { type: 'sdk-default', reason: ' ' }, { type: 'custom', reason: 'x' }]) { + await expect(runAgentSdkTest({ systemPrompt: systemPrompt as never, userPrompt: 'go', workingDirectory: ROOT, queryProvider, maxRetries: 0 })) + .rejects.toThrow('docs/TESTING_INTERNALS.md#agent-sdk-system-prompt'); + } + expect(sdkSystemPrompt(CLAUDE_CODE_PRESET)).toEqual({ systemPrompt: CLAUDE_CODE_PRESET }); + expect(sdkSystemPrompt({ type: 'sdk-default', reason: 'stub provider' })).toEqual({}); + expect(sdkSystemPrompt({ type: 'custom', text: 'be terse', reason: 'overlay-only arm' })).toEqual({ systemPrompt: 'be terse' }); + }); +}); diff --git a/test/setup-gbrain-fixture.test.ts b/test/setup-gbrain-fixture.test.ts index 5594e17a1..1165cfc80 100644 --- a/test/setup-gbrain-fixture.test.ts +++ b/test/setup-gbrain-fixture.test.ts @@ -170,7 +170,7 @@ describe('setup-gbrain owned Path 4 fixture', () => { let failure = ''; try { await runSetupGbrainAttempt(fixture, { - systemPrompt: '', userPrompt: 'free deadline probe', queryProvider, + systemPrompt: { type: 'sdk-default', reason: 'stub queryProvider: no model reads the prompt' }, userPrompt: 'free deadline probe', queryProvider, pathToClaudeCodeExecutable: '/nonexistent/free-test-never-spawn-claude', signal: controller.signal, }, () => { validated = true; }, mode === 'deadline' ? 250 : 1000, { @@ -213,7 +213,7 @@ describe('setup-gbrain owned Path 4 fixture', () => { })() as ReturnType<QueryProvider>; try { await expect(runSetupGbrainAttempt(fixture, { - systemPrompt: '', userPrompt: 'free validation cancellation probe', queryProvider, + systemPrompt: { type: 'sdk-default', reason: 'stub queryProvider: no model reads the prompt' }, userPrompt: 'free validation cancellation probe', queryProvider, pathToClaudeCodeExecutable: '/nonexistent/free-test-never-spawn-claude', signal: controller.signal, }, async () => { await Promise.resolve(); @@ -276,7 +276,7 @@ describe('setup-gbrain owned Path 4 fixture', () => { let thrown = ''; try { await runSetupGbrainAttempt(fixture, { - systemPrompt: '', userPrompt: 'free fixture probe', queryProvider, + systemPrompt: { type: 'sdk-default', reason: 'stub queryProvider: no model reads the prompt' }, userPrompt: 'free fixture probe', queryProvider, canUseTool: async (_tool, input) => ({ behavior: 'allow', updatedInput: { ...input, answers: { 'Want symbol-aware code search?': 'Yes, local PGLite' }, } }), diff --git a/test/test-of-test-ratchet.test.ts b/test/test-of-test-ratchet.test.ts index 4a0b48977..119b7b775 100644 --- a/test/test-of-test-ratchet.test.ts +++ b/test/test-of-test-ratchet.test.ts @@ -209,6 +209,7 @@ const BASELINE = [ 'test/review-enum-lifecycle.test.ts', 'test/review-n-plus-one-contract.test.ts', 'test/review-quality-provenance.test.ts', // landed in v1.91.7.0 before this ratchet: harness owner for its functional-QA/docsync paid evals + 'test/sdk-system-prompt-tripwire.test.ts', // the Agent SDK prompt tripwire: its subject is the eval harness (test/helpers/sdk-system-prompt.ts, agent-sdk-runner.ts) and every SDK caller under test/ 'test/session-runner-browse-errors.test.ts', // slices test/skill-e2e-review.test.ts source (recorded 2026-10 when the ratchet learned paid-source slicing) 'test/session-runner-stream-lifecycle.test.ts', 'test/session-runner-timeout.test.ts', diff --git a/test/trial-cause.test.ts b/test/trial-cause.test.ts index 1dbd9226a..95c511111 100644 --- a/test/trial-cause.test.ts +++ b/test/trial-cause.test.ts @@ -227,7 +227,7 @@ describe('one fixture per runner writes the ledger the classifier reads', () => setTimeout(() => args.options.abortController.abort(), 400); return Object.assign(iterator, { close: () => {} }); }) as unknown as QueryProvider; - const run = (events: any[]) => withEvalDir(() => runAgentSdkTest({ systemPrompt: '', userPrompt: 'x', workingDirectory: os.tmpdir(), maxRetries: 0, + const run = (events: any[]) => withEvalDir(() => runAgentSdkTest({ systemPrompt: { type: 'sdk-default', reason: 'stub queryProvider: no model reads the prompt' }, userPrompt: 'x', workingDirectory: os.tmpdir(), maxRetries: 0, testName: 'sdk-fixture', sessionBudgetMs: 400, streamLiveness: true, queryProvider: hangingQuery(events) }).catch(error => error)); const quiet = await run([{ type: 'system', subtype: 'init' }]); expect(quiet.rows).toEqual([expect.objectContaining({ key: 'agent-sdk:sdk-fixture#1', runner: 'agent-sdk', budget_ms: 400, end: 'session_timeout',