Function main

agents/browser-use/browser-use.test.ts:147–191

()

}

async function main() {
  fs.mkdirSync(TRACE_DIR, { recursive: true })

  const taskIndexArg = process.argv[2]
  const tasksToRun =
    taskIndexArg !== undefined
      ? [{ task: TASKS[parseInt(taskIndexArg, 10)], index: parseInt(taskIndexArg, 10) }]
      : TASKS.map((task, index) => ({ task, index }))

  if (tasksToRun.some((t) => !t.task)) {
    console.error(`Invalid task index: ${taskIndexArg}. Available: 0-${TASKS.length - 1}`)
    process.exit(1)
  }

  const agents = await loadLocalAgents({ agentsPath: path.join(process.cwd(), 'agents'), verbose: true })
  const agentDefinitions = Object.values(agents) as AgentDefinition[]

  const browserAgent = agentDefinitions.find((a) => a.id === 'browser-use')
  if (!browserAgent) {
    console.error('browser-use agent not found in agents/ directory')
    process.exit(1)
  }
  console.log(`Loaded browser-use agent (model: ${browserAgent.model})`)

  const client = new CodebuffClient({
    apiKey: process.env.CODEBUFF_API_KEY,
    cwd: process.cwd(),
  })

  const results: Array<{ name: string; success: boolean; traceFile: string }> = []

  for (const { task, index } of tasksToRun) {
    const result = await runTask(client, task, agentDefinitions, index)
    results.push({ name: task.name, success: result.success, traceFile: result.traceFile })
  }

  console.log(`\n${'='.repeat(60)}`)
  console.log('SUMMARY')
  console.log(`${'='.repeat(60)}`)
  for (const r of results) {
    console.log(`  ${r.success ? '✅' : '❌'} ${r.name} → ${r.traceFile}`)
  }
  const passed = results.filter((r) => r.success).length
  console.log(`\n${passed}/${results.length} tasks passed`)
}

if (import.meta.main) {
  main().catch((err) => {