AirCoding/packages/runtime/test/regression/release-critical-gates.test.ts

import { describe, it, expect } from 'bun:test'
import { mkdtempSync, writeFileSync, existsSync } from 'fs'
import { tmpdir } from 'os'
import { join } from 'path'
import { ToolRegistry } from '../../src/tools/ToolRegistry.js'
import { BuiltInToolRegistrar } from '../../src/tools/BuiltInToolRegistrar.js'
import { Scheduler } from '../../src/scheduler/Scheduler.js'
import { MainAgent } from '../../src/agents/main/MainAgent.js'
import { ContextAssembler } from '../../src/context/ContextAssembler.js'
import { createNullEventIngestor } from '../../src/events/EventIngestor.js'

function createRegistry(projectRoot: string): ToolRegistry {
  const registry = new ToolRegistry(projectRoot)
  new BuiltInToolRegistrar(registry).register_all(projectRoot)
  return registry
}

describe('Release critical gates', () => {
  it('built-in tool success envelopes use output, not content', async () => {
    const projectRoot = mkdtempSync(join(tmpdir(), 'air-tool-envelope-'))
    writeFileSync(join(projectRoot, 'sample.txt'), 'hello')
    const registry = createRegistry(projectRoot)
    const ctx = { session_id: 's', project_id: 'p', project_root: projectRoot, agent_id: 'a', agent_type: 'executor' as const }

    for (const [name, args] of [
      ['fs.stat', { path: 'sample.txt' }],
      ['project.scan', { root: '.' }],
      ['doctor.run', { scope: 'all' }],
    ] as Array<[string, Record<string, unknown>]>) {
      const result = await registry.call({ call_id: `call-${name}`, name, arguments: args }, ctx)
      expect(result.status).toBe('ok')
      expect(result.output).toBeDefined()
      expect((result as any).content).toBeUndefined()
    }
  })

  it('shell.run returns a final envelope through call and streaming APIs', async () => {
    const projectRoot = mkdtempSync(join(tmpdir(), 'air-shell-'))
    const registry = createRegistry(projectRoot)
    const ctx = { session_id: 's', project_id: 'p', project_root: projectRoot, agent_id: 'a', agent_type: 'executor' as const }

    const final = await registry.call({ call_id: 'shell-call', name: 'shell.run', arguments: { command: 'printf ok' } }, ctx)
    expect(final.status).toBe('ok')
    expect((final.output as any).exit_code).toBe(0)
    expect((final.output as any).stdout).toBe('ok')
    expect((final.metadata as any).is_final).toBe(true)

    const chunks = []
    for await (const chunk of registry.call_streaming({ call_id: 'shell-stream', name: 'shell.run', arguments: { command: 'printf ok' } }, ctx)) {
      chunks.push(chunk)
    }
    expect(chunks.length).toBeGreaterThanOrEqual(2)
    expect((chunks.at(-1)!.metadata as any).is_final).toBe(true)
  })

  it('scheduler does not mark running tasks completed without a worker result', async () => {
    const workerManager = {
      has_running: () => false,
      get_handle_for_task: () => undefined,
      get_result_for_task: () => undefined,
    }
    const scheduler = new Scheduler({ session_id: 's' as any, project_id: 'p' as any, project_root: process.cwd() }, workerManager as any, createNullEventIngestor())
    await scheduler.create_tasks([{ id: 'task-1' as any, type: 'execute', title: 'Task' }])
    scheduler.get_graph().update_status('task-1' as any, 'running')

    await scheduler.step()
    expect(scheduler.get_graph().get_tasks_by_status('running').length).toBe(1)
    expect(scheduler.get_graph().get_tasks_by_status('completed').length).toBe(0)
  })

  it('scheduler surfaces blocked worker results as BLOCKED, not COMPLETED', async () => {
    const workerManager = {
      has_running: () => false,
      get_handle_for_task: () => ({ worker_id: 'agent-task-1' }),
      get_result_for_task: () => ({
        task_id: 'task-1',
        agent_id: 'agent-task-1',
        agent_type: 'executor',
        status: 'blocked',
        summary: 'blocked by worker',
        changed_files: [],
        artifacts: [],
        verification: [],
        risks: [],
        follow_up_tasks: [],
        evidence_refs: [],
        result: {},
      }),
    }
    const scheduler = new Scheduler({ session_id: 's' as any, project_id: 'p' as any, project_root: process.cwd() }, workerManager as any, createNullEventIngestor())
    await scheduler.create_tasks([{ id: 'task-1' as any, type: 'execute', title: 'Task' }])
    scheduler.get_graph().update_status('task-1' as any, 'running')

    const finalState = await scheduler.run_until_idle()
    expect(finalState).toBe('BLOCKED')
    expect(scheduler.get_graph().get_tasks_by_status('blocked').length).toBe(1)
  })

  it('MainAgent answer mode uses assembled project context', async () => {
    const projectRoot = mkdtempSync(join(tmpdir(), 'air-context-'))
    writeFileSync(join(projectRoot, 'visible.txt'), 'visible')
    const assembler = new ContextAssembler()
    const provider = {
      async complete_text(messages: Array<{ role: string; content: string }>) {
        const joined = messages.map(m => m.content).join('\n')
        return { content: joined.includes('visible.txt') || joined.includes('Project') ? 'context seen' : 'missing context' }
      }
    }
    const agent = new MainAgent({
      session_id: 's' as any,
      project_id: 'p' as any,
      provider_manager: provider,
      context_assembler: assembler,
      project_root: projectRoot,
      agent_id: 'main-agent' as any,
    })

    const result = await agent.handle_user_message('what files are in this project?')
    expect(result.action).toBe('answer')
    expect(result.response).toBe('context seen')
  })

  it('destructive requests enter confirmation and rejection returns to idle', async () => {
    const agent = new MainAgent({ session_id: 's' as any, project_id: 'p' as any })
    const result = await agent.handle_user_message('delete hello.txt')
    expect(result.action).toBe('delegate')
    expect(agent.state).toBe('CONFIRMING')
    await agent.handle_confirmation(false)
    expect(agent.state).toBe('IDLE')
  })
})