mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-10 21:18:47 +02:00
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.
This commit is contained in:
1 parent
53e7f3212f
commit
6415690a18
317 files changed
+315
-54111
No files matched your search
@@ -2,7 +2,6 @@ import { describe, expect, test } from 'bun:test';
|
||||
import actual from './fixtures/eng-devex-s-first-calls.json';
|
||||
import retry from './fixtures/eng-devex-s-retry-calls.json';
|
||||
import { nativePlanCallFingerprint, engFirstReviewAUQ, engStep0Boundary, engSetupAUQ, planCountQuestionPhase } from './helpers/claude-pty-runner';
|
||||
import { isDevexReviewIssue } from './helpers/devex-count-fixture';
|
||||
import type { NativePlanQuestionCall } from './helpers/plan-count-transcript';
|
||||
const fp = (call: NativePlanQuestionCall) => nativePlanCallFingerprint(call, 0, true);
|
||||
const copy = (call: unknown) => structuredClone(call) as NativePlanQuestionCall;
|
||||
@@ -12,14 +11,6 @@ function changeQuestion(call: NativePlanQuestionCall, transform: (s: string) =>
|
||||
}
|
||||
|
||||
describe('S completed native review accounting', () => {
|
||||
test('DX keeps all five real approvals including unnamed package file and CI/TTHW contradiction', () => {
|
||||
expect(actual.devex.calls.map(call => isDevexReviewIssue(fp(copy(call))))).toEqual([true, true, true, true, true]);
|
||||
});
|
||||
test('retry keeps empathy/scope setup and all distinct issues/TODOs', () => {
|
||||
expect(retry.devex.calls.map(call => isDevexReviewIssue(fp(copy(call))))).toEqual([false, true, true, true, true, true]);
|
||||
let started = false;
|
||||
expect(retry.eng.calls.map(call => { const phase = planCountQuestionPhase(fp(copy(call)), started, engStep0Boundary, engFirstReviewAUQ, engSetupAUQ); started = phase.reviewStarted; return phase.preReview; })).toEqual([true, false, false, false, false, false, false]);
|
||||
});
|
||||
test('Eng scope remains setup; first architecture remedy opens review including the later TODO', () => {
|
||||
let started = false;
|
||||
const phases = actual.eng.calls.map(call => {
|
||||
@@ -31,10 +22,7 @@ describe('S completed native review accounting', () => {
|
||||
expect(engFirstReviewAUQ(fp(copy(actual.eng.calls[1])))).toBe(true);
|
||||
});
|
||||
for (const [name, original, predicate] of [
|
||||
['DX quickstart', actual.devex.calls[0], isDevexReviewIssue],
|
||||
['DX CI/TTHW', actual.devex.calls[1], isDevexReviewIssue],
|
||||
['Eng architecture', actual.eng.calls[1], engFirstReviewAUQ],
|
||||
['DX retry CI repair', retry.devex.calls[2], isDevexReviewIssue],
|
||||
] as const) {
|
||||
test(`${name} requires complete native offered-answer identity`, () => {
|
||||
for (const mutate of [
|
||||
@@ -66,17 +54,6 @@ describe('S completed native review accounting', () => {
|
||||
expect(predicate(fp(c))).toBe(false);
|
||||
});
|
||||
}
|
||||
test('DX does not count resolved or generic benchmark recaps', () => {
|
||||
expect(isDevexReviewIssue(fp(changeQuestion(copy(actual.devex.calls[0]), s => s.replace("doesn't exist", 'already exists'))))).toBe(false);
|
||||
expect(isDevexReviewIssue(fp(changeQuestion(copy(actual.devex.calls[0]), s => s.replace('quickstart points to', 'quickstart no longer points to'))))).toBe(false);
|
||||
expect(isDevexReviewIssue(fp(changeQuestion(copy(actual.devex.calls[1]), s => s.replace('these are mutually exclusive', 'these are not mutually exclusive'))))).toBe(false);
|
||||
expect(isDevexReviewIssue(fp(changeQuestion(copy(actual.devex.calls[1]), s => s.replace('with no skip path', 'with a working skip path'))))).toBe(false);
|
||||
});
|
||||
test('retry benchmark confirmation or resolved target cannot count as a new repair', () => {
|
||||
expect(isDevexReviewIssue(fp(changeQuestion(copy(retry.devex.calls[2]), s => s.replace('target unreachable', 'target reachable'))))).toBe(false);
|
||||
const c = copy(retry.devex.calls[2]); c.questions[0]!.options[0]!.label = 'Keep the existing target (Recommended)'; c.answers = { [c.questions[0]!.question]: c.questions[0]!.options[0]!.label };
|
||||
expect(isDevexReviewIssue(fp(c))).toBe(false);
|
||||
});
|
||||
test('Eng requires a concrete asserted defect and a direct repair decision', () => {
|
||||
const c = copy(actual.eng.calls[1]); c.questions[0]!.header = 'Scope'; expect(engFirstReviewAUQ(fp(c))).toBe(false);
|
||||
expect(engFirstReviewAUQ(fp(changeQuestion(copy(actual.eng.calls[1]), s => s.replace('is a race condition', 'is not a race condition'))))).toBe(false);
|
||||
|
||||
Reference in new issue
Block a user