test(review): fix-range walk logs each pass's Step 4.8 attempt in /review's real order (#3339)

Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
This commit is contained in:
garrytanandcapy-ai[bot] committed 2026-10-25 11:33:20 +00:00
1 parent 1ea548bff4
commit ca2bc785e0
2 files changed
+9 -8

No files matched your search

+1 -1
View File
@@ -10,7 +10,7 @@
- Nearby prose was tightened to pay for the growth (the slop-scan note, the Step 4.7 probe-reuse rule, the search-before-recommending list, the version-compare note, the final-report and Greptile lines). Every host's review SKILL.md shrank by 36 characters, and its size pin was lowered to match. The Claude skeleton is 80,581 bytes against its 80,900 cap.
### Tests
- `test/review-fix-range.test.ts` adds five cases. Two check the rendered rules: the first pass's start block has no `--fix-range`, only the pass after an edited pass narrows, FIX_BASE replaces only DIFF_BASE outside Step 4.8, a refusal falls back to a full start, the edited pass is logged before the repeat and kept out of Step 5.0, and a fix-range pass is never final. Three run /review's real order (Step 4.8's attempt row, then start, fix in the working tree, log with the pass's own token, never commit) against the real logger. A committed first pass narrows the next repeat to the uncommitted fixes, and the following repeat is refused back to a full pass that is CURRENT. A zero-edit fix-range row is UNVERIFIED even if it were logged. A first pass over uncommitted work can't be narrowed.
- `test/review-fix-range.test.ts` adds five cases. Two check the rendered rules: the first pass's start block has no `--fix-range`, only the pass after an edited pass narrows, FIX_BASE replaces only DIFF_BASE outside Step 4.8, a refusal falls back to a full start, the edited pass is logged before the repeat and kept out of Step 5.0, and a fix-range pass is never final. Three run /review's real order on every pass against the real logger: core start, then the Step 4.8 attempt's start and finish, then fixes in the working tree, then the core finish with the pass's own token, and never a commit. A committed first pass narrows the next repeat to the uncommitted fixes, and the following repeat is refused back to a full pass that is CURRENT. A zero-edit fix-range row is UNVERIFIED even if it were logged. A first pass over uncommitted work can't be narrowed.
- `test/review-workflow-clarity.test.ts`: three expectations follow the new contract: the "No edits" marker, the edited pass saving its record with `converged:false`, and each pass finishing its own token instead of only the final one. The test formerly named "finish only the final core token without log-time capture" is now "each logged pass finishes its own core token without log-time capture". It still requires one `--finish REVIEW_START`, no `--start review` in Step 5.8 and no log-time token capture.
### Gate integrity
+8 -7
View File
@@ -241,12 +241,16 @@ describe('review Step 3 and Step 5.8 instructions', () => {
});
describe('review Step 3/5.8 order against the real logger', () => {
// /review never commits: each pass starts, applies fixes in the working tree and logs with its own token.
// /review's order on every pass: core start, Step 4.8 attempt start and finish, fixes in the working tree, core finish; never a commit.
const reviewRow = (fields: Record<string, unknown>) => JSON.stringify({ skill: 'review', status: 'clean', issues_found: 0, critical: 0, informational: 0, ...fields });
function reviewPass(fields: Record<string, unknown>, start: string[], fixes?: string) {
const started = bin('gstack-review-log', start);
expect(started.code).toBe(0);
const [token, base] = started.out.split('\n');
// Step 4.8: each pass's adversarial attempt saves its row before any fix and before the core row.
const attempt = bin('gstack-review-log', ['--start', 'adversarial-review']);
expect(attempt.code).toBe(0);
expect(bin('gstack-review-log', [JSON.stringify({ skill: 'adversarial-review', status: 'clean', source: 'claude', ...clean }), '--finish', attempt.out]).code).toBe(0);
if (fixes) edit(fixes);
expect(bin('gstack-review-log', [reviewRow(fields), '--finish', token!]).code).toBe(0);
return base;
@@ -254,9 +258,6 @@ describe('review Step 3/5.8 order against the real logger', () => {
test('a committed first pass narrows the next repeat to the uncommitted fixes, then the chain returns to a full pass', () => {
const reviewed = head();
// Step 4.8 saves its attempt row before fixes, so it precedes the core row and never blocks the narrowed start.
const attempt = bin('gstack-review-log', ['--start', 'adversarial-review']).out;
expect(bin('gstack-review-log', [JSON.stringify({ skill: 'adversarial-review', status: 'clean', source: 'claude', ...clean }), '--finish', attempt]).code).toBe(0);
reviewPass(fixing, ['--start', 'review'], 'export const a = 2;\n');
expect(reviewPass(fixing, ['--start', 'review', '--fix-range'], 'export const a = 3;\n')).toBe(`FIX_BASE=${reviewed}`);
expect(gitIn(repo, `diff --name-only ${reviewed}`).trim()).toBe('a.ts');
@@ -267,7 +268,7 @@ describe('review Step 3/5.8 order against the real logger', () => {
const last = rows().at(-1)!;
expect(last.scope).toBeUndefined();
expect(reviewFreshness(last, last.wtree)?.status).toBe('CURRENT');
});
}, 30_000);
test('a zero-edit fix-range pass is never CURRENT even if it were logged, so the final record needs a full pass', () => {
reviewPass(fixing, ['--start', 'review'], 'export const a = 2;\n');
@@ -275,7 +276,7 @@ describe('review Step 3/5.8 order against the real logger', () => {
const narrowed = rows().at(-1)!;
expect(narrowed.scope).toBe('fix-range');
expect(reviewFreshness(narrowed, narrowed.review_binding.range_end_wtree)?.status).toBe('UNVERIFIED');
});
}, 30_000);
test('a first pass over uncommitted work cannot be narrowed', () => {
edit('export const a = 1; // uncommitted\n');
@@ -283,5 +284,5 @@ describe('review Step 3/5.8 order against the real logger', () => {
const r = narrowStart();
expect(r.code).toBe(1);
expect(r.err).toContain('started from uncommitted content');
});
}, 30_000);
});