宜博 / lemonboss

#!/usr/bin/env node
/**
 * scripts/phase3-verify.js
 *
 * P3 L1 + L2 联动验收 (mock 模式 · 4 类分支):
 *   ① contract_mismatch  → shipped · sdd_rev=2 · l2_rounds=1 · sdd.updated SSE · changelog sdd_rev 条
 *   ② impl_bug           → shipped · sdd_rev=1 · l2_rounds=0 · 仅 reset Unit
 *   ③ spec_ambiguous     → l2_blocked · human_intervention_needed SSE
 *   ④ infra_flake        → shipped · l2_rounds=0 · rerun 无 reset
 *  ⑤ Observability       → bugs.ndjson · timeline.ndjson · stream.log SSE replay
 *
 * 用法: node scripts/phase3-verify.js
 */

process.env.LEMONBOSS_CLAUDE_MODE = 'mock';

const fs = require('fs');
const path = require('path');

const serverNodeModules = path.resolve(__dirname, '../server/node_modules');
require('module').globalPaths.push(serverNodeModules);
const express = (() => {
  try { return require('express'); }
  catch {
    return require(require.resolve('express', { paths: [path.resolve(__dirname, '../server')] }));
  }
})();

const pathResolver = require('../server/services/devloop/path-resolver');
const sseBroker = require('../server/services/devloop/sse-broker');
const bugTracker = require('../server/services/devloop/bug-tracker');
const lc = require('../server/src/core/devloop/loop-controller');

const SCENARIO_BASE = path.resolve(__dirname, '../fixtures/devloop-mock-scenarios');

const results = [];
function step(name, fn) {
  return (async () => {
    try {
      const r = await fn();
      results.push({ name, ok: true, detail: r?.detail || '' });
      return r;
    } catch (e) {
      results.push({ name, ok: false, reason: e.message });
      throw e;
    }
  })();
}

function makeFakeRes(events) {
  return {
    setHeader() {}, flushHeaders() {}, end() {},
    on() {},
    write(line) {
      const m = line.match(/^event: (.+)$/m);
      if (m) events.push(m[1]);
    },
  };
}

async function runScenario(scenario) {
  pathResolver._resetForTesting();
  sseBroker._resetForTesting();
  const cid = 'c-phase3-' + scenario + '-' + Date.now().toString(36);
  const dir = path.join(SCENARIO_BASE, scenario);
  const proj = await lc.createProject({ company_id: cid, mode: 'sandbox', idea: 'phase3 ' + scenario });
  await lc.runDocsPhase(proj.pid, 'TODO demo', { mockFixtureDir: dir });

  const events = [];
  sseBroker.subscribe(proj.pid, makeFakeRes(events), {});

  const result = await lc.runProject(proj.pid, { mockFixtureDir: dir });
  sseBroker.close(proj.pid);
  return { pid: proj.pid, cid, result, events };
}

function cleanup(cid) {
  try {
    fs.rmSync(path.join(pathResolver.DATA_DIR, 'companies', cid), { recursive: true, force: true });
  } catch { /* ignore */ }
}

async function main() {
  const cidsToClean = [];

  // ① contract_mismatch
  let cm;
  try {
    await step('① contract_mismatch → shipped (sdd_rev=2, l2_rounds=1)', async () => {
      cm = await runScenario('contract_mismatch');
      cidsToClean.push(cm.cid);
      if (cm.result.final_state !== 'shipped') throw new Error('not shipped: ' + cm.result.final_state);
      const u = JSON.parse(fs.readFileSync(pathResolver.resolveUnitsJson(cm.pid), 'utf8'));
      if (u.l2_rounds !== 1) throw new Error('l2_rounds=' + u.l2_rounds);
      if (u.sdd_rev !== '2') throw new Error('sdd_rev=' + u.sdd_rev);
      return { detail: `pid=${cm.pid} sdd_rev=2 l2_rounds=1` };
    });

    await step('   sdd.updated SSE event', () => {
      if (!cm.events.includes('sdd.updated')) throw new Error('no sdd.updated in: ' + cm.events.join(','));
      return { detail: 'sdd.updated emitted' };
    });

    await step('   changelog has sdd_rev=2 entry', () => {
      const cl = pathResolver.resolveChangelog(cm.pid);
      if (!fs.existsSync(cl)) throw new Error('changelog missing');
      const lines = fs.readFileSync(cl, 'utf8').trim().split('\n').filter(Boolean).map(JSON.parse);
      if (!lines.some(l => l.kind === 'sdd_rev' && l.rev === 2)) throw new Error('no sdd_rev=2 in changelog');
      return { detail: `${lines.length} changelog entries` };
    });

    await step('   bug opened → fixed', () => {
      const bugs = bugTracker.list(cm.pid, {});
      if (bugs.length !== 1) throw new Error('want 1 bug, got ' + bugs.length);
      if (bugs[0].status !== 'fixed') throw new Error('bug.status=' + bugs[0].status);
      return { detail: `${bugs[0].id} (${bugs[0].status})` };
    });
  } catch { /* errors recorded by step */ }

  // ② impl_bug
  let ib;
  try {
    await step('② impl_bug → shipped · SDD unchanged · l2_rounds=0', async () => {
      ib = await runScenario('impl_bug');
      cidsToClean.push(ib.cid);
      if (ib.result.final_state !== 'shipped') throw new Error('state=' + ib.result.final_state);
      const u = JSON.parse(fs.readFileSync(pathResolver.resolveUnitsJson(ib.pid), 'utf8'));
      if (u.l2_rounds !== 0) throw new Error('l2_rounds=' + u.l2_rounds + ' (impl_bug should not burn)');
      if (u.sdd_rev !== '1') throw new Error('sdd_rev=' + u.sdd_rev + ' (should remain 1)');
      return { detail: `sdd_rev=1 l2_rounds=0` };
    });
  } catch {}

  // ③ spec_ambiguous
  let sa;
  try {
    await step('③ spec_ambiguous → l2_blocked + human_intervention_needed SSE', async () => {
      sa = await runScenario('spec_ambiguous');
      cidsToClean.push(sa.cid);
      if (sa.result.final_state !== 'l2_blocked') throw new Error('state=' + sa.result.final_state);
      if (!sa.events.includes('human_intervention_needed')) throw new Error('no human_intervention_needed SSE');
      return { detail: 'l2_blocked · SSE fired' };
    });
  } catch {}

  // ④ infra_flake
  let inf;
  try {
    await step('④ infra_flake → shipped · l2_rounds=0 · rerun_integrator', async () => {
      inf = await runScenario('infra_flake');
      cidsToClean.push(inf.cid);
      if (inf.result.final_state !== 'shipped') throw new Error('state=' + inf.result.final_state);
      const u = JSON.parse(fs.readFileSync(pathResolver.resolveUnitsJson(inf.pid), 'utf8'));
      if (u.l2_rounds !== 0) throw new Error('l2_rounds=' + u.l2_rounds);
      const actions = inf.result.history.filter(h => h.phase === 'L2.dispatch').map(h => h.action);
      if (!actions.some(a => /rerun_integrator/.test(a))) throw new Error('no rerun_integrator action');
      return { detail: 'shipped without budget burn' };
    });
  } catch {}

  // ⑤ Observability cross-check
  try {
    await step('⑤ Observability — timeline / bugs / changelog / stream.log', () => {
      // 用 contract_mismatch 项目验
      if (!cm) throw new Error('cm scenario did not run');
      const tl = pathResolver.resolveTimelineLog(cm.pid);
      const bg = pathResolver.resolveBugsLog(cm.pid);
      const cl = pathResolver.resolveChangelog(cm.pid);
      const sl = pathResolver.resolveStreamLog(cm.pid);
      for (const [name, p] of [['timeline', tl], ['bugs', bg], ['changelog', cl], ['stream.log', sl]]) {
        if (!fs.existsSync(p)) throw new Error(`${name} missing`);
      }
      const tlKinds = fs.readFileSync(tl, 'utf8').trim().split('\n').filter(Boolean)
        .map(l => { try { return JSON.parse(l).kind; } catch { return ''; }});
      for (const must of ['unit.state', 'integration.result', 'triage.result', 'sdd.updated']) {
        // unit.state is via sseBroker.emit not timeline; but we should at least have integration.result + sdd.updated as timeline kinds — actually those go via sseBroker.emit too. Check timeline has agent.call entries.
      }
      // 至少: project.created + agent.call (PM + Architect + L1 coder/tester + integrator + triager + architect-patch) + project.shipped
      const expectedTimelineKinds = ['project.created', 'agent.call', 'project.shipped'];
      const missing = expectedTimelineKinds.filter(k => !tlKinds.includes(k));
      if (missing.length) throw new Error('timeline missing kinds: ' + missing.join(','));
      return { detail: `timeline=${tlKinds.length}ev · bugs+changelog+stream.log present` };
    });

    await step('⑥ SSE replay via Last-Event-ID', async () => {
      if (!cm) throw new Error('cm scenario did not run');
      const replayed = [];
      sseBroker.subscribe(cm.pid, makeFakeRes(replayed), { replayFromOffset: 3 });
      sseBroker.close(cm.pid);
      // 至少应回放出 sdd.updated / project.shipped 之类
      if (replayed.length < 2) throw new Error('replay too few events: ' + replayed.length);
      return { detail: `replayed ${replayed.length} events from id=3` };
    });
  } catch {}

  for (const c of cidsToClean) cleanup(c);

  let pass = 0, fail = 0;
  console.log('\n┌─ DevLoop Phase 3 — L1+L2 联动 Acceptance ────────');
  for (const r of results) {
    const tag = r.ok ? '✓' : '✗';
    console.log(`│ ${tag} ${r.name.padEnd(62)} ${r.ok ? r.detail : '— ' + r.reason}`);
    r.ok ? pass++ : fail++;
  }
  console.log(`└─ ${pass}/${pass + fail} steps passed${fail ? ' · ' + fail + ' failed' : ''}\n`);
  process.exit(fail ? 1 : 0);
}

main().catch(e => {
  console.error('\n[phase3-verify] fatal:', e);
  for (const r of results) console.log(' ', r.ok ? '✓' : '✗', r.name, r.ok ? r.detail : '— ' + r.reason);
  process.exit(1);
});