mirror of
https://github.com/jackwener/OpenCLI.git
synced 2026-09-14 18:25:42 +08:00
jakevin
37f1b46a77
* feat: AutoResearch framework + V2EX test suite (40 tasks) AutoResearch framework (Karpathy-style autonomous iteration): - engine.ts: 8-phase loop (review → modify → commit → verify → guard → decide → log) - config.ts: typed config + CLI parser + metric extraction - logger.ts: TSV append-only results log - commands/run.ts: main loop spawning Claude Code per iteration - commands/plan.ts: interactive config wizard - commands/fix.ts: auto-detect broken state, iteratively fix - commands/debug.ts: hypothesis-driven debugging for failing tasks V2EX test suite (5 layers, 40 tasks): - L1 Atomic (10): open, state, click, scroll, eval, back, wait - L2 Single Page (10): hot topics, node list, topic meta, pagination - L3 Multi-Step (10): click-read, navigate-node, tab-then-topic, pagination - L4 Write Ops (5): reply typing, favorite detection, form detection - L5 Complex Chain (5): cross-page collect, multi-node compare, full workflow Presets: operate-reliability, skill-quality, v2ex-reliability * test: V2EX test suite 60/60 — fix selectors, add harder tasks - Fix v2ex-collect-hot-authors selector (pathname-based member link detection) - Fix v2ex-wait-text judge (accept "appeared") - Fix trailing commas in eval step strings - Add 20 harder tasks: state+click interaction + long chain workflows - Baseline: 60/60 across all layers * docs: optimize SKILL.md for efficiency — aggressive chaining, minimize turns - Add Rule #7: minimize total tool calls (3-5 per task, not 15-20) - Strengthen Rule #5: chain aggressively with && - Add explicit good/bad chaining examples - Add click+wait+state chaining pattern - Add type+verify chaining pattern Before: 21 turns for complex V2EX reply task After: 12 turns for same task (-43% turns, -28% cost)
70 lines
2.2 KiB
TypeScript
70 lines
2.2 KiB
TypeScript
/**
|
|
* AutoResearch TSV Logger — append-only results log with metadata header.
|
|
*/
|
|
|
|
import { writeFileSync, readFileSync, existsSync, appendFileSync } from 'node:fs';
|
|
import type { AutoResearchConfig, IterationResult } from './config.js';
|
|
|
|
const COLUMNS = ['iteration', 'commit', 'metric', 'delta', 'guard', 'status', 'description'];
|
|
|
|
export class Logger {
|
|
constructor(private path: string) {}
|
|
|
|
/** Create the TSV file with metadata header */
|
|
init(config: AutoResearchConfig): void {
|
|
const header = [
|
|
`# metric_direction: ${config.direction === 'higher' ? 'higher_is_better' : 'lower_is_better'}`,
|
|
`# goal: ${config.goal}`,
|
|
`# scope: ${config.scope.join(', ')}`,
|
|
`# verify: ${config.verify}`,
|
|
config.guard ? `# guard: ${config.guard}` : null,
|
|
COLUMNS.join('\t'),
|
|
].filter(Boolean).join('\n');
|
|
writeFileSync(this.path, header + '\n', 'utf-8');
|
|
}
|
|
|
|
/** Append one iteration result */
|
|
append(result: IterationResult): void {
|
|
const row = [
|
|
result.iteration,
|
|
result.commit,
|
|
result.metric,
|
|
result.delta >= 0 ? `+${result.delta}` : result.delta,
|
|
result.guard,
|
|
result.status,
|
|
result.description,
|
|
].join('\t');
|
|
appendFileSync(this.path, row + '\n', 'utf-8');
|
|
}
|
|
|
|
/** Read last N entries for pattern recognition */
|
|
readLast(n: number): IterationResult[] {
|
|
if (!existsSync(this.path)) return [];
|
|
const lines = readFileSync(this.path, 'utf-8').split('\n')
|
|
.filter(l => l && !l.startsWith('#') && !l.startsWith('iteration'));
|
|
return lines.slice(-n).map(line => {
|
|
const [iteration, commit, metric, delta, guard, status, ...desc] = line.split('\t');
|
|
return {
|
|
iteration: parseInt(iteration, 10),
|
|
commit,
|
|
metric: parseFloat(metric),
|
|
delta: parseFloat(delta),
|
|
guard: guard as 'pass' | 'fail' | '-',
|
|
status: status as IterationResult['status'],
|
|
description: desc.join('\t'),
|
|
};
|
|
});
|
|
}
|
|
|
|
/** Count consecutive discards from the end */
|
|
consecutiveDiscards(): number {
|
|
const entries = this.readLast(20);
|
|
let count = 0;
|
|
for (let i = entries.length - 1; i >= 0; i--) {
|
|
if (entries[i].status === 'discard') count++;
|
|
else break;
|
|
}
|
|
return count;
|
|
}
|
|
}
|