Function selftest

scripts/agent-eval/parse-run.mjs:952–1354

()

// answers. It lives here rather than in a test file on purpose — a new
// scripts/agent-eval/*.mjs scores into the self-query eval fixture's corpus.
function selftest() {
  const { writeFileSync, mkdtempSync } = require0('fs');
  const { join } = require0('path');
  const { tmpdir } = require0('os');
  const dir = mkdtempSync(join(tmpdir(), 'cg-occ-'));
  let n = 0, failures = 0;
  const check = (name, got, want, tol) => {
    n++;
    const ok = Math.abs(got - want) <= tol;
    if (!ok) failures++;
    console.log(`${ok ? '  ok  ' : '  FAIL'} ${name}: got ${Math.round(got)}, want ${want} ±${tol}`);
  };
  // Builders for the event shapes Claude Code actually emits.
  const req = (ctx, id, blocks) => blocks.map((b) => JSON.stringify({
    type: 'assistant',
    message: { id, content: [b], usage: { input_tokens: ctx, cache_read_input_tokens: 0, cache_creation_input_tokens: 0, output_tokens: 2 } },
  }));
  const use = (id, name, input = {}) => ({ type: 'tool_use', id, name, input });
  const res = (id, chars) => JSON.stringify({
    type: 'user', message: { content: [{ type: 'tool_result', tool_use_id: id, content: [{ type: 'text', text: 'x'.repeat(chars) }] }] },
  });
  const done = () => JSON.stringify({ type: 'result', subtype: 'success', duration_ms: 1000, total_cost_usd: 0.1, usage: {} });
  const write = (name, lines) => { const f = join(dir, name); writeFileSync(f, lines.join('\n') + '\n'); return f; };

  // 1. Attribution: ratio 2.5 chars/tok, two families, no shedding.
  //    10,000 explore chars over a 4,000-tok gap; 5,000 Read chars over 2,000.
  let f = write('basic.jsonl', [
    ...req(10000, 'm1', [use('t1', 'mcp__codegraph__codegraph_explore')]),
    res('t1', 10000),
    ...req(14000, 'm2', [use('t2', 'Read')]),
    res('t2', 5000),
    ...req(16000, 'm3', [{ type: 'text', text: 'done' }]),
    done(),
  ]);
  let o = parseSession([f]).occupancy;
  check('chars/token', o.charsPerToken * 1000, 2500, 30);
  check('codegraph residual', o.residual.codegraph, 4000, 60);
  check('Read residual', o.residual.read, 2000, 40);
  check('file-access residual', o.residualFileAccess, 2000, 40);
  check('final context', o.ctxFinal, 16000, 0);
  check('fixed base', o.ctxBase, 10000, 0);
  check('nothing evicted', o.evicted, 0, 1);

  // 2. Dedupe: thinking + tool_use are two events sharing one id and one usage.
  //    Counting usage per event would report 5 requests instead of 3.
  f = write('dupe.jsonl', [
    ...req(10000, 'm1', [{ type: 'thinking', thinking: '' }, use('t1', 'mcp__codegraph__codegraph_explore')]),
    res('t1', 10000),
    ...req(14000, 'm2', [{ type: 'thinking', thinking: '' }, use('t2', 'Read')]),
    res('t2', 5000),
    ...req(16000, 'm3', [{ type: 'text', text: 'done' }]),
    done(),
  ]);
  let s = parseSession([f]);
  check('turns deduped by message.id', s.turns, 3, 0);
  check('codegraph residual (deduped)', s.occupancy.residual.codegraph, 4000, 60);

  // 3. Compaction: the boundary clears everything resident before it.