Files
gstack/test/plan-count-prerequisite.test.ts
T
Garry Tan 943105f109 v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals (#2994)
* test: delete test-infrastructure dead code (G)

- exit-propagation drives the runner's real strict verdict
  (BunTestOutputClassifier + strictTestExitCode); delete the unused
  shardRunLooksTruncated predicate.
- delete skill-coverage-matrix registry + its gate (nothing reads it; the
  floor already iterates skillCensus()).
- delete touchfiles-facade export-parity tests (Bun fails missing imports
  at link time) and the duplicated E2E_TIERS tier-value test.
- delete brain-cache-spec TRANSPORT_DEFAULT_POLICY, SKILL_RUN_RETENTION_DAYS
  and the now-unused BrainTrustPolicy type with their literal tests.
  AUTOPLAN_PREFLIGHT_BUDGET_BYTES stays: skill-preflight-budget enforces it
  against real resolver output.
- delete audit-compliance's JSDoc-comment grep.

* test: replace product tests that fake the product with real-boundary tests (F)

- design: serve.test.ts drove an inline mirror server; now two tests run the
  real serve() on an ephemeral port (reload confinement, submit exit 0).
- setup-gbrain: rollback + voyage tests execute the template-extracted init
  blocks (3 sites) instead of drifted local bash copies.
- terminal-agent: internalHandler source greps replaced by a behavioral
  /internal/grant + /internal/revoke auth matrix (no/wrong/valid token).
- /health: server-security-surface and the server-auth / security-audit-r2 /
  sidebar-tabs source greps fold into one liveness-only check on the real
  body; the L4 sidecar wiring gets a behavioral /pty-inject-scan test.
- delete tautologies (browser-manager onDisconnect, memory-command #12),
  ios swiftui tap fixture self-check, memory-ingest put_page grep, detach
  source greps, sidebar-agent absence pins, dead-CSS pins + the dead CSS,
  security-audit-r2 Task 1 + the test-only meta-commands re-export,
  duplicate generated-SKILL.md checks.
- make-pdf coverage-gaps cases move into their owner test files.

* test: delete tests of dead eval code (A)

- A1: the retired Eng lexical oracle (evaluateEngSeedCoverage,
  isEngSeedDecisionAUQ), the completion-handoff detector and the retained
  corpus had no paid caller since v1.87.6; delete their 26 replay files,
  ~2.6k helper LOC and fixtures, and the dead blocks in 8 mixed files
  (live hasNativePlanTerminal / batching assertions stay).
- A2: dead viewport approvers in autoplan-artifact-permission and their 11
  replay files + fixtures; recorder/launcher cases stay.
- A3: never-wired oracles and seeders (autoplan-phase-order,
  eng-finding-fixture, ceo-paired-fixture, design-ui-scope,
  plan-skill-completion, pty-current-screen, required-reads,
  transcript-section-logger); plan-seed-submission now decodes through the
  production createPtyScreen; section manifests name their actual guard.
- A4: zero-reference helper exports, plus execGit and invokeAndObserve
  found by the reachability pass.
- 52 fixtures orphaned by the deletions; touchfile and selection-table
  entries for every deleted path.

* test: clean up the paid eval lane (B1-B4, B6, B7)

- B1: delete paid files that assert nothing or cannot pass meaningfully:
  skill-llm-eval-spec and skill-e2e-spec-execute (test.todo), gemini-e2e
  (+ gemini-session-runner; no gemini CLI in CI), ship-idempotency (red
  since v1.63), the two opus-4-7 *-sonnet overlay wrappers, conductor-prose
  (+ its source-evaluation replay), codex-e2e-plan-format; drop their keys,
  scripts and census rows.
- B2: skill-llm-eval grades browse/sections/command-list.md with one union
  judge that also carries the baseline score pin; regression-vs-baseline
  deleted (paid run: pass, c4/c4/a4).
- B3: memory-pipeline, ios-qa, ios-qa-swift-build and plan-tune-cathedral
  make no model calls; renamed out of the paid glob so they run on every
  PR. Swift builds need GSTACK_TEST_SWIFT=1; device stub deleted.
- B4: codex-e2e*, outside-voice, aside and ios-device cannot run in the CI
  image; excluded from the weekly lane with a tracked re-entry condition.
- B6: fold opus-47's negative routing controls into skill-routing-e2e
  journey-negatives (paid run: 3/3 unrouted) and delete the file.
- B7: delete the never-green brain-privacy-gate eval; a free
  gstack-skill-start test now proves consent precedes artifacts egress.

* test: retire the finding-count cluster and trim its helpers (C)

- C0/C1: the five never-green evals (skill-e2e-autoplan-chain and
  skill-e2e-plan-{ceo,eng,design,devex}-finding-count) failed on harness and
  budget, never on skill behavior; delete them, their touchfile/tier ids,
  AUTOPLAN_CHAIN_BUDGET and the dedicated eighth periodic slice (--slices 7).
- C2: delete the helper groups whose only paid consumers were those files
  (11 modules), trim claude-pty-runner and eng-seeded-coverage to the paid
  closure, and delete the free replay tests whose assertions exercised only
  that dead code (89 files, 135 orphaned fixtures). Blocks that used dead code
  only as input for a live subject keep their assertions: the multiSelect
  default moved to plan-review-decisions, runner PTY tests use inline caller
  policies, and the timer-safe budget checks moved to eng-finding-retry-budget.
- The eight production-touching files stay except ceo-current-decision-record
  (its template read only feeds the retired counter).
- CARVE_GUARDS.autoplan is behavioral 'none'; TODOS records the lost chain
  and per-finding cadence coverage with their re-entry tests.

* test: fold per-incident replay series into their detector owners (D)

Twelve detector families move into one owner test each: 73 incident files
become describe blocks in ceo-section-loading-fixture (stale-fill race),
model-overlays, coverage-audit-evidence, autoplan-phase-observer,
native-auto-decide, outside-voice-evidence, eng-first-review,
plan-count-completion, plan-count-file-permission, ceo-mode-option,
plan-scope-selection and plan-count-prerequisite. Each block keeps its original
code and fixture, so every case still runs; only tests asserting the incident
file's own touchfile registration are dropped (41). Touchfile lists that named
an incident now name its owner.

* test: start the plan-count history PTY on its readiness marker (H)

The fake CLI prints a startup marker and the runner waits for it instead of the
fixed 8 s startup sleep (8.6 s -> 0.9 s locally). eng-semantic-terminal's
sleeping registration cases went with C; plan-count-timeout keeps the fixed wait
because it asserts deadline behavior.

* test: derive paid touchfiles from each eval's static closure (E)

touchfiles.test.ts now checks, per key, that the paid file's static
test/helpers and test/fixtures closure (plus fixture paths it names in string
literals) is covered, and names the file, path, chain and key to fix when it is
not. Free *.test.ts files are no longer touchfiles, so editing a free replay
test stops selecting paid evals: 950 entries removed, 653 real closure paths
added. The hand-copied inventories go: periodic-fixture-selection,
fake-impeccable-touchfiles and 45 per-file selection examples. Selection for
the sample edits (plan-eng-review template, claude-pty-runner,
plan-count-fixture, gstack-config) loses no case under either profile.
CONTRIBUTING documents the rule and its lower bound.

* test: skip hollow tier shards and census judges in the paid planner (B5)

A paid file is now skipped for a tier lane only when every E2E id it registers
is known statically and none has that tier; ids come from the touchfile
registrations and literal testName/*IfSelected arguments, so a comment or
skill path that quotes another id cannot unschedule it, and computed names
keep today's scheduling. --list and the manifest show each skip as
"skipped: no E2E_TIERS id has tier <tier>". The weekly gate census drops the
LLM judges (--skip-judges); they still run in the periodic census and PR gate
lanes. Gate lane 52 -> 42 files, census 41; periodic 77 -> 69.

* test: run seven paid evals on the current default capture model (B8)

skill-e2e-{auq-matrix,plan-format,qa-bugs,retro,workflow} pinned
claude-opus-4-7 and skill-e2e-office-hours plus -brain-writeback pinned
claude-sonnet-4-6; none tests a historical model, so they now capture with
resolveEvalModel('capture'), and the free harness tests that execute these
registrations receive the same resolver. The paid re-pin run passed all of
them. skill-e2e-{design,office-hours-phase4,plan-prosons,plan} keep
claude-opus-4-7: six of their cases failed on the default model (three
timeouts, a missing report file, a format miss and a posture score of 3), so
per the plan's fallback they keep their pins with a TODOS entry. The pre-spend
estimate and drop threshold are in docs/test-audit-2026-09.md.

* test: guard the reduced suite against new test-of-test files

- test/test-of-test-ratchet.test.ts records the 228 free tests that import only
  test/ code and fails on a new one, naming the owner test to extend instead;
  a stale baseline entry fails with the remove instruction.
- test/helpers/resolve-repo-path.ts is the one specifier/literal resolver for
  the ratchet and the touchfile closure invariant, with its own unit tests.
- CONTRIBUTING "Test tiers" describes the paid-failure workflow (fix, then one
  row in the detector's owner test) and the ratchet; TEST_PORTFOLIO gains the
  detector -> owner-test table and no longer claims an Autoplan chain eval.
- TODOS: automatic exclusion policy for chronically red periodic files (P3),
  the deferred native-completion table collapse, the unused CEO payment
  seeder; the PTY readiness item is narrowed to the paid runner.
- docs/test-audit-2026-09.md collects the triage, security mapping, inventories,
  selection proof, behavior-commit decisions and retained false positives.

* v1.91.8.0 test: smaller suite, derived paid selection, retired never-green evals

Release metadata for the test-reduction branch: VERSION 1.91.8.0 (1.91.7.0 is
claimed by #2983), CHANGELOG with the measured before/after table and a
contributor section, durations re-recorded on Ubicloud standard-16 (857 files,
0 failures), the agents digest, CONTRIBUTING's after-measurement row, the B8
fallback TODOS entry, and the after metrics, kept-vs-plan notes, B8 run and
census estimate in docs/test-audit-2026-09.md.

* fix(ubicloud): skip retrieval globs that match nothing instead of reporting a failed pull

* test: count issue-numbered Design findings in the UI-scope gate eval
2026-09-29 08:58:49 -07:00

253 lines
16 KiB
TypeScript
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
/**
* Native prerequisite and navigation picks (planCountPrerequisitePick) over captured calls.
*/
import { describe } from 'bun:test';
import { expect } from 'bun:test';
import { test } from 'bun:test';
import { capturePlanCountQuestion } from './helpers/claude-pty-runner';
import { nativePlanCallFingerprint } from './helpers/claude-pty-runner';
import { planCountPrerequisitePick } from './helpers/claude-pty-runner';
import { planCountQuestionInput } from './helpers/claude-pty-runner';
import type { NativePlanQuestionCall } from './helpers/plan-count-transcript';
import prerequisite_plan_count_navigation_r from './fixtures/dx-prerequisite-r-call.json';
import callFixture_plan_count_prerequisite_n from './fixtures/ceo-prerequisite-n-call.json';
import engPrerequisite77_plan_count_prerequisite_n from './fixtures/eng-prerequisite-77.json';
describe('plan-count-navigation-r', () => {
const prerequisite = prerequisite_plan_count_navigation_r;
function pending(source: NativePlanQuestionCall): NativePlanQuestionCall {
const call = structuredClone(source);
call.answered = false;
delete call.answers;
delete call.unansweredQuestionIndices;
delete call.answeredAt;
return call;
}
function frame(call: NativePlanQuestionCall) {
const q = call.questions[0]!;
const visible = `☐ ${q.header}\n${q.question}\n${q.options.map((o, i) => `${i ? ' ' : '❯'} ${i + 1}. ${o.label}`).join('\n')}\nEnter to select · ↑/↓ to navigate · Esc to cancel`;
const active = capturePlanCountQuestion(visible, new Set(), 0, true, call)!;
return { visible, active, routing: nativePlanCallFingerprint(call, 0, true) };
}
describe('captured R planning navigation', () => {
test('DX declines its optional office-hours detour using the full native option meaning', () => {
const call = pending(prerequisite as NativePlanQuestionCall);
const { visible, active, routing } = frame(call);
expect(active.nativeCall).toBe(call);
expect(prerequisite.answers[prerequisite.questions[0]!.question]).toBe(prerequisite.questions[0]!.options[0]!.label);
const pick = planCountPrerequisitePick(routing, active) ?? 1;
expect(pick).toBe(2);
expect(planCountQuestionInput(visible, active, pick)).toBe('2');
});
test('short prerequisite labels require the current native question and affirmative review action', () => {
for (const change of [
(c: NativePlanQuestionCall) => { c.questions[0]!.options[1]!.description = ''; },
(c: NativePlanQuestionCall) => { c.questions[0]!.options[1]!.description = 'Do not proceed with standard DX POLISH review.'; },
(c: NativePlanQuestionCall) => { c.questions[0]!.options[1]!.description = 'Accept the finding and proceed with standard DX POLISH review.'; },
(c: NativePlanQuestionCall) => { c.questions[0]!.options[1]!.description = 'Accept this security finding. Proceed with standard DX POLISH review.'; },
(c: NativePlanQuestionCall) => { c.questions[0]!.options[1]!.description = 'Proceed with standard DX POLISH review after running /office-hours first.'; },
(c: NativePlanQuestionCall) => { c.questions[0]!.options[1]!.description = 'Proceed with standard DX POLISH review? No, run /office-hours first.'; },
(c: NativePlanQuestionCall) => { c.questions[0]!.options[1]!.description = 'Proceed with standard DX POLISH review. Accept the security risk.'; },
(c: NativePlanQuestionCall) => { c.questions[0]!.options[1]!.description = 'Plan scope is already precise. Proceed with standard DX POLISH review if the tests pass.'; },
(c: NativePlanQuestionCall) => { c.questions[0]!.options.push({ label: 'Accept this security finding' }); },
(c: NativePlanQuestionCall) => { c.questions[0]!.multiSelect = true; },
(c: NativePlanQuestionCall) => { c.questions.push(structuredClone(c.questions[0]!)); },
(c: NativePlanQuestionCall) => { c.answered = true; },
(c: NativePlanQuestionCall) => { c.failed = true; },
]) {
const call = pending(prerequisite as NativePlanQuestionCall);
change(call);
const fp = nativePlanCallFingerprint(call, 0, true);
expect(planCountPrerequisitePick(fp)).toBeNull();
}
const call = pending(prerequisite as NativePlanQuestionCall);
const { active, routing, visible } = frame(call);
expect(planCountPrerequisitePick(routing, { ...active, preReview: false })).toBeNull();
expect(planCountPrerequisitePick(routing, { ...active, signature: 'stale:question' })).toBeNull();
expect(planCountPrerequisitePick(routing, { ...active, nativeQuestionIndex: 1 })).toBeNull();
expect(planCountPrerequisitePick(routing, { ...active, options: active.options.slice().reverse() })).toBeNull();
const visibleOnly = capturePlanCountQuestion(visible, new Set(), 0, true)!;
expect(visibleOnly.nativeCall).toBeUndefined();
expect(planCountPrerequisitePick(routing, visibleOnly)).toBeNull();
call.questions[0]!.options.reverse();
const reordered = frame(call);
expect(planCountPrerequisitePick(reordered.routing, reordered.active)).toBe(1);
});
test('a bare short label uses its bound unconditional review meaning', () => {
const call = pending(prerequisite as NativePlanQuestionCall);call.questions[0]!.options[1]!.label='Skip';
const {active,routing}=frame(call);expect(planCountPrerequisitePick(routing,active)).toBe(2);
});
test('short labels allow only a benign plan-scope premise plus the unconditional review action', () => {
for (const description of ['Proceed with standard review.', 'Proceed with standard DX review', 'The plan is clear. Proceed with standard DX POLISH review.', 'Plan scope is already precise. Proceed with standard DX POLISH review.']) {
const call = pending(prerequisite as NativePlanQuestionCall);
call.questions[0]!.options[1]!.description = description;
const { active, routing } = frame(call);
expect(planCountPrerequisitePick(routing, active)).toBe(2);
}
});
});
});
describe('plan-count-prerequisite-n', () => {
const callFixture = callFixture_plan_count_prerequisite_n;
const engPrerequisite77 = engPrerequisite77_plan_count_prerequisite_n;
const call = () => structuredClone(callFixture);
describe('native prerequisite review-now offer', () => {
test('the captured CEO offer keeps the supplied plan instead of starting office hours', () => {
const fp = nativePlanCallFingerprint(call(), 0, true);
expect(planCountPrerequisitePick(fp)).toBe(2);
expect(planCountPrerequisitePick({ ...fp, preReview: false })).toBeNull();
});
test('the visible offer works before metadata arrives and follows reordered choices', () => {
for (const reverse of [false, true]) {
const native = call();
if (reverse) native.questions[0]!.options.reverse();
const q = native.questions[0]!;
const screen = ['☐ Prerequisite', q.question.split('\n\n')[0],
`❯ 1. ${q.options[0]!.label}`, ` 2. ${q.options[1]!.label}`,
' 3. Type something.', ' 4. Chat about this',
'Enter to select · ↑/↓ to navigate · Esc to cancel'].join('\n');
const fp = capturePlanCountQuestion(screen, new Set(), 0, true)!;
expect(fp).not.toBeNull();
expect(planCountPrerequisitePick(fp)).toBe(reverse ? 1 : 2);
}
});
test('the extra wording does not authorize skipping a finding or mixed decision', () => {
const fp = nativePlanCallFingerprint(call(), 0, true);
for (const skip of ['Skip', 'Skip — review now and ignore security', 'Skip — review now or delete the plan']) {
expect(planCountPrerequisitePick({ ...fp, options: [fp.options[0]!, { index: 2, label: skip }] })).toBeNull();
}
expect(planCountPrerequisitePick({ ...fp, promptSnippet: 'Should we skip this SQL injection finding?' })).toBeNull();
expect(planCountPrerequisitePick({ ...fp, options: [...fp.options, { index: 3, label: 'Fix SQL injection' }] })).toBeNull();
expect(planCountPrerequisitePick({ ...fp, options: [fp.options[0]!, { ...fp.options[1]!, index: 1 }] })).toBeNull();
expect(planCountPrerequisitePick({ ...fp, options: [{ index: 1, label: 'Run /office-hours first and rewrite the API' }, fp.options[1]!] })).toBeNull();
for (const mutate of [
(c: any) => { c.failed = true; },
(c: any) => { c.questions[0].multiSelect = true; },
(c: any) => { c.questions.push(structuredClone(c.questions[0])); },
]) {
const native = call(); mutate(native);
expect(planCountPrerequisitePick(nativePlanCallFingerprint(native, 0, true))).toBeNull();
}
});
});
function engPrerequisitePending(): NativePlanQuestionCall {
const native = structuredClone(engPrerequisite77.completedCall) as NativePlanQuestionCall;
native.answered = false;
delete native.answers;
delete native.answeredAt;
delete native.unansweredQuestionIndices;
return native;
}
// Exact public native question/options; the active pending viewport is synthetic.
function engPrerequisiteFrame(native: NativePlanQuestionCall, index = 0) {
const q = native.questions[index]!;
const screen = [native.questions.length > 1
? '← ' + native.questions.map((question, i) => `${i < index ? '☒' : '☐'} ${question.header}`).join(' ') + ' ✔ Submit →'
: `☐ ${q.header}`, q.question,
...q.options.map((option, i) => `${i ? ' ' : '❯'} ${i + 1}. ${option.label}`),
`Enter to select · ${native.questions.length > 1 ? 'Tab/Arrow keys' : '↑/↓'} to navigate · Esc to cancel`,
].join('\n');
const active = capturePlanCountQuestion(screen, new Set(), 0, true, native)!;
return { screen, active, routing: nativePlanCallFingerprint(native, 0, true) };
}
describe('optional Office Hours decision briefs', () => {
test('optional action is independent of header, numbering, recommendation and order', () => {
for (const reverse of [false, true]) for (const recommended of ['run', 'skip', 'neither']) {
const native = engPrerequisitePending(), q = native.questions[0]!;
q.header = 'Before review';
q.question = q.question.replace(/^D2 — /, 'D41: ').replace(/Recommendation: B[^\n]*/, recommended === 'run' ? 'Recommendation: A because deeper context helps.' : 'Recommendation: B because the supplied plan is reviewable.');
q.options[0]!.label = 'Run /office-hours first' + (recommended === 'run' ? ' (Recommended)' : '');
q.options[1]!.label = 'Skip, proceed with standard review' + (recommended === 'skip' ? ' (Recommended)' : '');
if (reverse) q.options.reverse();
const { active, routing } = engPrerequisiteFrame(native);
expect(planCountPrerequisitePick(routing, active)).toBe(reverse ? 1 : 2);
}
});
test('the complete native offer supports equivalent description structure and premise placement', () => {
for (const title of [
'Run /office-hours now, or proceed with standard review?\nNo design doc exists for this branch.',
'No design doc found: run /office-hours first, or proceed with the standard review?',
]) for (const bullet of ['✅', '- ✅', '* ✅']) {
const native = engPrerequisitePending(), q = native.questions[0]!;
q.question = title + '\nThe supplied plan is ready for review.';
q.options[0]!.description = `${bullet} Creates a design document with the problem and alternatives.\n❌ Delays the engineering review while the prerequisite runs.`;
q.options[1]!.description = `${bullet} Proceeds directly with standard review of the supplied plan.\n❌ The review has less background about the original premise.`;
const { active, routing } = engPrerequisiteFrame(native);
expect(planCountPrerequisitePick(routing, active)).toBe(2);
}
});
test('native pros and cons may be inline or multiline without changing the action', () => {
for (const separator of [' ', '\n', '\r\n']) {
const native = engPrerequisitePending();
for (const option of native.questions[0]!.options) option.description = option.description!.split('\n').join(separator);
const { active, routing } = engPrerequisiteFrame(native);
expect(planCountPrerequisitePick(routing, active)).toBe(2);
}
});
const invalid: Array<[string, (q: NativePlanQuestionCall['questions'][number]) => void]> = [
['quoted question', q => { q.question = '> ' + q.question; }],
['example question', q => { q.question = 'Example: ' + q.question; }],
['fenced question', q => { q.question = '```text\n' + q.question + '\n```'; }],
['unrelated current question', q => { q.question = 'Should we remove authorization?\n' + q.question; }],
['additional approval question', q => { q.question += '\nApprove deployment?'; }],
['mandatory prerequisite', q => { q.question += '\nYou must run /office-hours first.'; }],
['blocked review', q => { q.question += '\nStandard review is blocked until /office-hours completes.'; }],
['conditional skip label', q => { q.options[1]!.label += ' if the tests pass'; }],
['extra run action', q => { q.options[0]!.label += ' and rewrite the API'; }],
['missing skip meaning', q => { q.options[1]!.description = ''; }],
['negated review action', q => { q.options[1]!.description = '✅ Do not proceed with standard review.'; }],
['retracted review action', q => { q.options[1]!.description += '\n❌ No review will run.'; }],
['conditional review action', q => { q.options[1]!.description = '✅ Proceed with standard review after completing /office-hours.'; }],
['conditional corroboration', q => { q.options[1]!.description += '\n✅ First run /office-hours to establish the baseline.'; }],
['substantive action appended', q => { q.options[1]!.description += '\n✅ Remove CI.'; }],
['substantive action inline', q => { q.options[1]!.description = '✅ Proceed with standard review. Accept the security risk.'; }],
['additive skip action', q => { q.options[1]!.description = '✅ Proceed with standard review and deploy to production.\n❌ Less premise context.'; }],
['subordinate skip action', q => { q.options[1]!.description = '✅ Proceed with standard review while deleting the API.\n❌ Less premise context.'; }],
['additive run action', q => { q.options[0]!.description = '✅ Produces a design doc and deletes the API.\n❌ Delays the review.'; }],
['subordinate run action', q => { q.options[0]!.description = '✅ Produces a design doc while disabling CI.\n❌ Delays the review.'; }],
['unrelated run approval', q => { q.options[0]!.description += '\n✅ Deploy to production.'; }],
['run negated', q => { q.options[0]!.description = '✅ Do not run /office-hours.'; }],
['run retracted', q => { q.options[0]!.description += '\n❌ Do not produce a design doc.'; }],
['foreign premise', q => { q.question = q.question.replace('No design doc found.', 'The archived example had no design doc.'); }],
['extra choice', q => { q.options.push({ label: 'Approve deployment' }); }],
['checkbox', q => { q.multiSelect = true; }],
];
for (const [name, mutate] of invalid) test(`does not decline ${name}`, () => {
const native = engPrerequisitePending(); mutate(native.questions[0]!);
const { active, routing } = engPrerequisiteFrame(native);
expect(planCountPrerequisitePick(routing, active)).toBeNull();
});
test('only the pending owned active tab can supply the complete native brief', () => {
const native = engPrerequisitePending(), frame = engPrerequisiteFrame(native);
for (const active of [
{ ...frame.active, preReview: false }, { ...frame.active, signature: 'foreign:tool' },
{ ...frame.active, nativeQuestionIndex: 3 }, { ...frame.active, nativeCall: undefined },
{ ...frame.active, promptSnippet: 'A different current question' },
{ ...frame.active, options: [...frame.active.options].reverse() },
]) expect(planCountPrerequisitePick(frame.routing, active)).toBeNull();
for (const delta of [{ answered: true }, { failed: true }, { sessionId: '' }, { toolUseId: '' }]) {
const changed = { ...engPrerequisitePending(), ...delta }, f = engPrerequisiteFrame(changed);
expect(planCountPrerequisitePick(f.routing, f.active)).toBeNull();
}
expect(planCountPrerequisitePick({ ...frame.active, nativeCall: undefined })).toBeNull();
native.questions.unshift({ header: 'Unrelated', question: 'Should we deploy?', options: [{ label: 'Deploy' }, { label: 'Defer' }], multiSelect: false });
const own = engPrerequisiteFrame(native, 1), other = engPrerequisiteFrame(native, 0);
expect(planCountPrerequisitePick(own.routing, own.active)).toBe(2);
expect(planCountPrerequisitePick(other.routing, other.active)).toBeNull();
});
});
});