mirror of
https://github.com/pbakaus/impeccable.git
synced 2026-09-12 22:26:38 +03:00
Addresses the review findings on #371, plus several the bots did not catch. All fixes have regression coverage that fails on the prior code. Source corruption: - Vue accept dropped valueless root attrs (disabled, v-cloak) and, worse, rewrote @click="x" as a literal click="x" DOM attribute, because the attr parser was name-anchored and skipped the sigil. Tokenize the whole Vue attr grammar and normalize shorthands so accept round-trips directives. - --variant was interpolated unescaped into a RegExp, so --variant '.*' matched the original block first and reported a successful accept while silently restoring the original. Validate against the digits pattern the browser and the /events schema already enforce. - --id reached path.join unvalidated, so --id ../../../../etc/evil wrote and read receipts outside the project. Hoist the existing safeSessionId check into impeccable-paths and apply it at every id-to-path sink. Accept/lock correctness: - Plain HTML/JSX accept and discard did not catch SOURCE_LOCKED, so contention exited non-zero with empty stdout and the agent got no JSON to retry on. - Lock staleness was mtime-only and never read the pid it records: a holder whose critical section outran 60s had its live lock swept, admitting a second writer to the same file, while a crashed holder blocked accepts for a full 60s. Decide staleness by owner liveness, and release only our own lock. Detector: - isNeutralColor only parses computed color forms, so routing authored CSS through it reported inset 4px 0 0 #000 / black / #e5e7eb as chromatic side-tab stripes. Add an authored-color neutrality test covering hex and named neutrals; the fixture had no literal-color cases at all. - Rule line numbers were off by one for every rule after the first, and commented-out CSS was scanned as live rules. Server: - An error reply carries no sourceEventType, and inferSourceEventType returned undefined, which acknowledgePendingEvent treats as a wildcard: a stale generate worker's failure consumed the user's queued Accept, which then reached no agent and left the browser in SAVING forever. - The generate preflight spawned live-wrap.mjs synchronously inside the request handler, freezing the single-threaded server for the whole scaffold (~7.6s measured on this repo, 15s ceiling) and stalling Accept/Discard/SSE. Make it async, claiming the lease before the first await so no event double-delivers. - Every browser checkpoint was echoed back as variant_progress, so a Tune slider drag remounted the preview under the user's cursor and latched the *_reviewable phases from the wrong trigger. Gate on the reason. Cleanup: - Collapse four divergent benchmark argv parsers into scripts/lib/cli-args.mjs. Three silently misread flags: --iterations 20 benchmarked 5, --agent llm ran the fake agent, --median-target=0.4 used the default threshold. - Drop a snapshot cache this branch made write-only (it grew per session for the server's lifetime and was never read), a dead exported reconcile helper, and the unused deferReply branch. Prepared with AI assistance under maintainer direction. Co-Authored-By: Claude <noreply@anthropic.com>
102 lines
3.5 KiB
JavaScript
102 lines
3.5 KiB
JavaScript
/**
|
|
* Tests for scripts/lib/cli-args.mjs — the shared argv parser for the Live
|
|
* benchmark / judging scripts.
|
|
* Run with: node --test tests/cli-args.test.mjs
|
|
*/
|
|
|
|
import { describe, it } from 'node:test';
|
|
import assert from 'node:assert/strict';
|
|
|
|
import { boolFlag, parseArgs, positiveIntFlag, toCamel } from '../scripts/lib/cli-args.mjs';
|
|
|
|
describe('parseArgs', () => {
|
|
it('reads space-separated values', () => {
|
|
// The regression: without the argv[i+1] lookahead this yielded
|
|
// {fixture: true, iterations: true}, silently benchmarking the defaults.
|
|
assert.deepEqual(
|
|
parseArgs(['--fixture', 'vite8-react-modal', '--iterations', '20']),
|
|
{ fixture: 'vite8-react-modal', iterations: '20' },
|
|
);
|
|
});
|
|
|
|
it('reads --flag=value values', () => {
|
|
assert.deepEqual(parseArgs(['--fixture=vite8-react-plain']), { fixture: 'vite8-react-plain' });
|
|
});
|
|
|
|
it('treats a flag followed by another flag as boolean', () => {
|
|
assert.deepEqual(parseArgs(['--headed', '--quiet']), { headed: true, quiet: true });
|
|
});
|
|
|
|
it('treats a trailing flag as boolean', () => {
|
|
assert.deepEqual(parseArgs(['--append']), { append: true });
|
|
});
|
|
|
|
it('camel-cases kebab keys so both spellings land on one key', () => {
|
|
assert.deepEqual(parseArgs(['--simulated-tail-ms=250']), { simulatedTailMs: '250' });
|
|
assert.deepEqual(parseArgs(['--simulatedTailMs=250']), { simulatedTailMs: '250' });
|
|
assert.deepEqual(parseArgs(['--median-target', '0.4']), { medianTarget: '0.4' });
|
|
});
|
|
|
|
it('keeps a value that contains an equals sign intact', () => {
|
|
assert.deepEqual(parseArgs(['--model=claude-sonnet-4-6=x']), { model: 'claude-sonnet-4-6=x' });
|
|
});
|
|
|
|
it('ignores positional args and a bare --', () => {
|
|
assert.deepEqual(parseArgs(['positional', '--', '--real', 'v']), { real: 'v' });
|
|
});
|
|
|
|
it('lets a later occurrence win', () => {
|
|
assert.deepEqual(parseArgs(['--agent', 'fake', '--agent', 'llm']), { agent: 'llm' });
|
|
});
|
|
});
|
|
|
|
describe('toCamel', () => {
|
|
it('upcases after hyphens only', () => {
|
|
assert.equal(toCamel('simulated-tail-ms'), 'simulatedTailMs');
|
|
assert.equal(toCamel('p95-target'), 'p95Target');
|
|
assert.equal(toCamel('already'), 'already');
|
|
});
|
|
});
|
|
|
|
describe('boolFlag', () => {
|
|
it('accepts the bare-flag sentinel and the explicit spellings alike', () => {
|
|
// --headed and --headed=true must not diverge.
|
|
assert.equal(boolFlag(true), true);
|
|
assert.equal(boolFlag('true'), true);
|
|
assert.equal(boolFlag('1'), true);
|
|
assert.equal(boolFlag('yes'), true);
|
|
assert.equal(boolFlag(''), true);
|
|
});
|
|
|
|
it('recognizes negative spellings', () => {
|
|
assert.equal(boolFlag('false'), false);
|
|
assert.equal(boolFlag('0'), false);
|
|
assert.equal(boolFlag('no'), false);
|
|
});
|
|
|
|
it('falls back when absent or unrecognized', () => {
|
|
assert.equal(boolFlag(undefined), false);
|
|
assert.equal(boolFlag(undefined, true), true);
|
|
assert.equal(boolFlag('maybe', true), true);
|
|
});
|
|
});
|
|
|
|
describe('positiveIntFlag', () => {
|
|
it('parses positive integers', () => {
|
|
assert.equal(positiveIntFlag('20', 5), 20);
|
|
});
|
|
|
|
it('falls back when absent or given as a bare flag', () => {
|
|
assert.equal(positiveIntFlag(undefined, 5), 5);
|
|
assert.equal(positiveIntFlag(true, 5), 5);
|
|
});
|
|
|
|
it('throws rather than silently using the default', () => {
|
|
// Quietly benchmarking 5 iterations when 20 were asked for is the failure
|
|
// this replaces.
|
|
for (const bad of ['abc', '0', '-3', '2.5', '20x']) {
|
|
assert.throws(() => positiveIntFlag(bad, 5), /positive integer/, `accepted ${bad}`);
|
|
}
|
|
});
|
|
});
|