Files
gstack/test/skill-e2e-plan-mode-no-op.test.ts
T
d078622b73 v1.62.0.0 feat: plan-mode auto-select at the review scope gate (#2533)
* fix(evals): align plan-eng/design plan-mode + finding-floor smokes to their declared periodic tier

The #2077 demotion of these four stochastic tests to 'periodic' was inert:
E2E_TIERS declared periodic but the files self-gated on EVALS_TIER === 'gate',
so they kept running in the blocking gate lane and never in the weekly lane.

Flip the four self-gates to 'periodic' (headers/describe labels updated), add
a free static tier-alignment invariant test (dep-list filename mapping;
unmapped self-gated files are reported, never silently skipped), and name the
two plan-mode test files in their own touchfiles dep lists so the invariant
binds for them.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(pty-runner): scope-gate question/auto-select detectors + observation flags

Two render-shape-anchored detectors (whitespace-squished, like the Pattern-4/5
collapsed-form handling): isScopeGateQuestionVisible requires the question text
PLUS option-body text (native AskUserQuestion renders numbered options, prose
fallback renders lettered — the option body appears in both; narration doesn't),
and isScopeGateAutoSelectVisible requires the announcement prefix PLUS the
selected-B token.

runPlanSkillObservation gains scopeGateQuestionObserved /
scopeGateAutoSelectObserved high-water flags (attached at every return path) so
paid smokes can assert gate behavior across the whole run instead of the lossy
2KB evidence tail. runPlanSkillFloorCheck no longer counts a scope-gate render
toward auqObserved (tail-scoped exclusion) — the floor measures FINDING-driven
questions, and the gate could fire inside the 3s pre-target window.

Unit fixtures pin clean/native/collapsed positives, narration negatives, and
the verbatim template announcement string (template rewording fails here first,
before the paid smokes degrade to vacuous asserts).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* feat(plan-eng/design-review): auto-select B in plan mode at the scope gate

In plan mode the scope gate's "What should I review? A/B/C" question is pure
friction: there is no branch diff and the target is the plan being drafted.
Both gates gain an ordered exceptions block, checked BEFORE asking:

1. Plan mode → auto-select B: review the active plan (in context or pasted),
   announce it in one line ("Scope gate: plan mode — auto-selected B
   (reviewing <target>)") so the user can interrupt; an explicitly different
   user-named target still wins; no plan drafted yet → ask as normal.
2. User-named target (outside plan mode): explicit-only — a path, a pasted
   doc, or the literal words "branch diff". A passing mention is not naming;
   when in doubt, ask.

Outside plan mode with no explicitly-named target, nothing changes. Plan-mode
is checked FIRST because the PTY harness seeds drafts as pasted user messages
(claude-pty-runner.ts:1600) — ordering makes the seeded smokes deterministic.

Pinning: seeded plan-mode smokes assert no gate render + announcement rendered
(eng test 2; new design seeded test); plan-mode-no-op extends to eng/design
(bypass must not misfire outside plan mode; first question must be the gate)
plus a named-target case proving the pasted target is consumed; a drift-guard
asserts the two hand-duplicated exceptions blocks stay identical modulo the
two variant slots and carry the announcement string the detectors pin.

Skeleton ceilings ratcheted with comments (eng 68k, design 89k; eng union
ratio 1.08→1.09) — measured 67,006 B / 88,226 B after regen.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(autoplan): skip the scope gate when following loaded review skills

autoplan Step 3 reads plan-eng-review / plan-design-review SKILL.md verbatim,
and its section skip list omitted the scope gate — so autoplan ingested a
hard-STOP AskUserQuestion that contradicts its every-question-auto-decides
contract. One skip-list line fixes it; a static toContain pin in
skill-validation keeps the entry load-bearing.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: file scope-gate resolver-extraction TODO (eng-review D5 follow-up)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(pty-runner): positional floor exclusion, flag builder, outcome union, token tracking

Review-army + adversarial findings on the scope-gate observability work,
all verified before fixing:

- Floor check: acceptance scanned the CUMULATIVE buffer while the scope-gate
  exclusion scanned only the 1500-byte tail, so an early gate render satisfied
  the floor vacuously once ~1.5KB of output accumulated (found independently
  by 4 review passes; predicate reproduced). Acceptance now scans only content
  APPENDED after the first gate render (positional anchor), and the LLM-judge
  'waiting' shortcut no longer fires while the gate menu is the pending render.
- High-water flags are built once and spread at every return path — the
  hand-spread pattern had already drifted (judge-waiting return omitted two
  flags), which made must-stay-false asserts vacuous on those paths.
- isScopeGateAutoSelectVisible: tense-tolerant selected/selecting/selects
  token (must-be-TRUE asserts shouldn't fail semantically-perfect paraphrases)
  and quoted-occurrence rejection (a model verbatim-quoting the announcement
  while declining must not trip must-stay-FALSE asserts). Fixtures added for
  both directions.
- PlanSkillObservation outcome union gains 'wrote_findings_before_asking'
  (returned at runtime via classifyVisible but missing from the type).
- trackTokens/tokensObserved: cumulative-buffer token high-water for
  consumption asserts (the 2KB evidence tail is lossy and the plan-file
  fallback is unreachable outside plan mode).
- New scope-gate-floor unit pins (from the ship coverage audit): both gate
  render forms trip acceptance and exclusion; a genuine finding AUQ is not
  excluded; tail-scoping semantics pinned.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* test(evals): harden no-op asserts, close tier-invariant fail-open holes, pin gate question strings

- no-op regression: gate-must-ask is now UNCONDITIONAL for eng/design (the
  outcome==='asked' conditional let a silent-bypass plan_ready run sail
  through); eng/design cases force --disallowedTools so the pinned prose
  shape is contractual rather than hoping native AUQ renders match; the
  named-target case uses trackTokens for consumption and lists
  wrote_findings_before_asking in its diagnostic throw branch.
- tier-alignment invariant: both quote styles matched; zero-self-gate,
  mixed-tier, and owning-keys-without-E2E_TIERS-entries are all REPORTED
  instead of silently skipped (the fail-open holes three reviewers found).
- drift-guard: the generated gate menus must carry the exact question/option
  strings the PTY question detector anchors on — free CI fails before the
  paid smokes can go vacuous on a menu reword.
- touchfiles: corrected the no-op cost note for CI concurrency + retry
  semantics.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ci): register plan-eng/design-review skills in PTY eval containers

The extended plan-mode-no-op smoke invokes /plan-eng-review and
/plan-design-review, but the fresh CI containers registered only
office-hours and plan-ceo-review — both new runs would return
'Unknown command' and fail every PR's gate job (Codex structured
review P1, verified against evals.yml). Registration loops, the
dangling-target fail-fast list, and the frontmatter checks (now a
loop over the same skill list, so the lists can't drift) all cover
the two skills.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(plan-eng/design-review): harden scope-gate exceptions against injection and ambiguity

Adversarial-review wording fixes (Claude adversarial F1-F8 + Codex
cross-confirmation), applied to both gate templates + regen:

- Host-anchored mode signal: only the host's own system messages (plan-mode
  reminder or active plan file path) arm the auto-select; plan-shaped text
  inside pasted documents, tool results, or fetched pages does NOT count —
  injected content can't disarm the consent gate or nominate the target.
- Multiple plan candidates: the host-referenced plan file wins; still
  ambiguous means ask.
- The DIFFERENT-target override carries the passing-mention guard.
- Plan mode + explicitly named target + no drafted plan resolves to the
  named target instead of a contradictory re-ask.
- The numbered ask-path rules are qualified ('When no exception above
  applied:') so they no longer restate an unconditional MUST-ask that
  contradicts the exceptions.
- 'Whenever this gate does ask — in any mode — it is a hard STOP.'
- Shared preamble: 'any AskUserQuestion the skill fires is the workflow
  operating within plan mode' (was 'the first AskUserQuestion is the
  workflow entering plan mode', which framed the opposite of the bypass);
  regenerates every skill.
- Ceilings ratcheted with attribution: plan-eng union ratio 1.10,
  investigate 1.10 (the ~250B shared-preamble reword lands the
  closest-to-ceiling skill at 1.092).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* chore: bump version and changelog (v1.62.0.0)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(pty-runner): active-render gate veto in the floor check + honest periodic-wiring docs

Codex re-review P2s on the fix wave, both verified:

- A finding AUQ rendering within TAIL_SCAN_BYTES of the gate (model waiting,
  no further output) was vetoed by the blanket tail exclusion until timeout.
  The veto is now ACTIVE-RENDER-aware: parseNumberedOptions anchors the last
  cursor menu, so only a pending GATE menu vetoes; the judge fallback shares
  the same check. Residual (documented): prose gate + prose finding inside
  one tail — floors run the native-menu path in practice.
- The four demoted periodic tests are not in evals-periodic.yml's explicit
  matrix (a named instance of the pre-existing periodic-orphans TODO), so
  they run locally/manually until the PTY-capable periodic job lands.
  CHANGELOG claim softened accordingly; TODO filed with the wiring recipe.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: update project documentation for v1.62.0.0

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: apply codex doc-review fixes for v1.62.0.0

- CLAUDE.md: scope the tier-alignment invariant claim (mapped files
  enforced, unmapped files reported)
- docs/skills.md: document the plan-mode auto-select scope gate for
  /plan-eng-review and /plan-design-review
- evals.yml: fix stale comment (PTY smokes register four skills, not two)

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* test: refresh ship golden baselines for the plan-mode preamble reword

The generate-completion-status.ts wording change ('any AskUserQuestion the
skill fires…') intentionally regenerates every SKILL.md; the byte-compare
goldens carry the generator's output and refresh with it.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(ship): custom-hooks-path detection false-negatives on git worktrees

The pre-push guard's HOOKS_IN_GIT_DIR check compared the hooks dir against
--absolute-git-dir, which in a linked worktree is .git/worktrees/<name>
while hooks resolve to the COMMON .git/hooks — so every Conductor worktree
read as a 'custom hooks path' and the consented guard install was skipped.
Match against the resolved --git-common-dir too (with a /nonexistent
fallback so a failed resolution can't collapse the case pattern into
match-everything). Verified live: this worktree now reports yes (was no),
and the main checkout still reports yes. Goldens refreshed (--host all).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* docs: changelog bullet for the worktree hooks-detection fix

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(evals): give the plan-ceo plan-mode smoke real budget headroom

Measured 2026-08-11: a clean isolated pass took 295.7s against the 300s
inner budget (4s of margin) and the same test timed out at ~308s three
times under concurrent eval load — a budget-edge flake in the gate lane,
not a behavior regression (it passed isolated on both this branch and
main). Inner budget 300s -> 420s, outer bun timeout 360s -> 480s, and the
test file is now named in its own touchfiles dep list so the tier-alignment
invariant binds for it.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

* fix(evals): 300s budget floor for the two 90s design-consultation SDK tests

Root cause of PR #2533's e2e-design CI failure: design-consultation-preview
failed 3 attempts at 0 turns/$0.00/93s — the session was up but the model's
first completion queued past the 90s inner budget under concurrent API load
(11 matrix jobs; the sibling research test booted its first tool at 4s, so
this is API-side queuing, not CPU boot contention). The test was selected
only because touchfiles.ts is a global touchfile; the tested behavior is
untouched by this branch.

90s budgets cannot absorb one slow first completion. Both 90s tests in the
file move to the repo's saturated-runner standard (300s inner / 360s outer,
matching review-dashboard-via and retro-base-branch). Deliberately NOT
re-arming the runner's inner timer on first stream event: an audit found
~100 outer bun-timeout literals sized inner+30-60s that a re-arm would
silently break — the structural options are written up in TODOS.md.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
2026-08-12 11:12:28 -07:00

150 lines
6.8 KiB
TypeScript

/**
* Plan-mode-info no-op regression (gate tier, paid, real-PTY).
*
* Asserts: when a plan-review skill is invoked OUTSIDE plan mode (no
* --permission-mode plan flag, no plan-mode reminder injected), the skill
* still reaches a terminal outcome ('asked' or 'plan_ready'). This is the
* negative coverage to the per-skill plan-mode smokes — if plan-mode-keyed
* behavior ever starts misfiring for non-plan-mode sessions (e.g., gating
* questions on a phrase that isn't there, or the plan-eng/plan-design
* scope-gate auto-select-B bypass firing without plan mode), this test
* catches it.
*
* Why this matters: outside plan mode, claude doesn't render a native
* confirmation UI. The skill must drive its own AskUserQuestion. Same
* runner, same outcome contract — just `inPlanMode: false`.
*
* Coverage grew with the scope-gate bypass (plan-mode auto-select B):
* - plan-ceo-review: original preamble-misfire regression.
* - plan-eng-review / plan-design-review: the bypass must NOT fire outside
* plan mode (scopeGateAutoSelectObserved stays false), and when the run
* ends in 'asked', the question that fired must be the scope gate itself
* (outside plan mode with no named target, the gate is the FIRST
* question by contract).
* - named-target case: a pasted draft (initialPlanContent) IS an
* explicitly-named target, so the gate must NOT ask — and the review
* must actually consume the pasted content.
*
* Cost note: 4 sequential PTY runs (~3-5 min each) in the gate lane, up
* from 1 pre-bypass. Selected only when plan-ceo/eng/design or the runner
* change (see 'plan-mode-no-op' in touchfiles.ts).
*/
import { describe, test, expect } from 'bun:test';
import { runPlanSkillObservation } from './helpers/claude-pty-runner';
const shouldRun = !!process.env.EVALS && process.env.EVALS_TIER === 'gate';
const describeE2E = shouldRun ? describe : describe.skip;
const PLAN_MODE_REMINDER =
'Plan mode is active. The user indicated that they do not want you to execute yet';
// Distinctive token proves the pasted target was consumed by the review —
// not just that no question fired. Nonsense-unique so it can't appear by
// coincidence in skill output.
const SEED_TOKEN = 'ZephyrLedgerWidget';
const NAMED_TARGET_SEED = `
# Plan: ${SEED_TOKEN} settings panel
## Scope
Add a ${SEED_TOKEN} settings panel with a single toggle that enables
weekly export emails. One new component, one route, one test file.
## Files
- src/components/${SEED_TOKEN}.tsx (new)
- src/routes/settings.tsx (add panel)
- test/${SEED_TOKEN}.test.tsx (new)
`;
describeE2E('plan-mode-info no-op outside plan mode (gate regression)', () => {
for (const skillName of ['plan-ceo-review', 'plan-eng-review', 'plan-design-review'] as const) {
test(`${skillName} reaches a terminal outcome outside plan mode`, async () => {
const obs = await runPlanSkillObservation({
skillName,
inPlanMode: false,
timeoutMs: 300_000,
// eng/design: force the prose-fallback path. The unconditional
// gate-must-ask assert below pins the render shape the detector
// anchors on, and only the --disallowedTools prose fallback makes
// that shape CONTRACTUAL ("use exactly this shape" in the template);
// native AskUserQuestion could render terse option labels that a
// correct run would fail on (red-team finding).
...(skillName === 'plan-ceo-review'
? {}
: { extraArgs: ['--disallowedTools', 'AskUserQuestion'] }),
});
if (obs.outcome === 'silent_write' || obs.outcome === 'exited' || obs.outcome === 'timeout') {
throw new Error(
`plan-mode no-op regression FAILED (${skillName}): outcome=${obs.outcome}\n` +
`summary: ${obs.summary}\n` +
`elapsed: ${obs.elapsedMs}ms\n` +
`--- evidence (last 2KB visible) ---\n${obs.evidence}`,
);
}
expect(['asked', 'plan_ready']).toContain(obs.outcome);
// Negative regression: the rendered output must NOT echo the plan-mode
// distinctive reminder phrase. If it does, the plan-mode preamble
// section is leaking outside plan mode.
expect(obs.evidence).not.toContain(PLAN_MODE_REMINDER);
if (skillName !== 'plan-ceo-review') {
// Scope-gate bypass must not misfire: no auto-select announcement
// outside plan mode.
expect(obs.scopeGateAutoSelectObserved ?? false).toBe(false);
// UNCONDITIONAL: outside plan mode with no named target, the gate is
// a hard STOP before any tool call, so the gate question must have
// rendered no matter which terminal outcome fired. Gating this on
// outcome === 'asked' would let a silent-bypass run that reaches
// plan_ready (isPlanReadyVisible also matches common prose) sail
// through — the exact regression this test exists to catch.
expect(obs.scopeGateQuestionObserved ?? false).toBe(true);
}
}, 360_000);
}
// Named-target exception (outside plan mode): a pasted draft IS an
// explicitly-named target, so the scope gate must NOT ask — and the
// review must consume the pasted content (seed token visible in the
// review output), proving the target was used rather than the question
// merely skipped. Also the over-trigger guard for the tightened
// "explicit-only" exception wording.
test('plan-eng-review skips the scope gate for an explicitly-pasted target', async () => {
const obs = await runPlanSkillObservation({
skillName: 'plan-eng-review',
inPlanMode: false,
initialPlanContent: NAMED_TARGET_SEED,
trackTokens: [SEED_TOKEN],
timeoutMs: 300_000,
});
if (
obs.outcome === 'wrote_findings_before_asking' ||
obs.outcome === 'silent_write' ||
obs.outcome === 'exited' ||
obs.outcome === 'timeout'
) {
throw new Error(
`named-target no-op FAILED: outcome=${obs.outcome}\n` +
`summary: ${obs.summary}\n` +
`elapsed: ${obs.elapsedMs}ms\n` +
`--- evidence (last 2KB visible) ---\n${obs.evidence}`,
);
}
expect(['asked', 'plan_ready']).toContain(obs.outcome);
expect(obs.evidence).not.toContain(PLAN_MODE_REMINDER);
// The pasted doc is the named target: gate question must not render,
// no plan-mode announcement either (we are NOT in plan mode).
expect(obs.scopeGateQuestionObserved ?? false).toBe(false);
expect(obs.scopeGateAutoSelectObserved ?? false).toBe(false);
// Target consumption via high-water token tracking over the CUMULATIVE
// buffer — the 2KB evidence tail is lossy and the plan-file fallback is
// unreachable outside plan mode (extractPlanFilePath only matches
// plan-mode save renders).
expect(obs.tokensObserved?.[SEED_TOKEN] ?? false).toBe(true);
}, 360_000);
});