feat(subagent): add Codex product provider

packages/subagent/subagent-codex/tests/real-product.spec.ts

@@ -0,0 +1,230 @@
+import { execFile } from 'node:child_process'
+import {
+  existsSync,
+  mkdirSync,
+  mkdtempSync,
+  readFileSync,
+  rmSync,
+  writeFileSync,
+} from 'node:fs'
+import { tmpdir } from 'node:os'
+import { delimiter, join, resolve } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { promisify } from 'node:util'
+import { Context } from 'cordis'
+import { afterEach, describe, expect, it, vi } from 'vitest'
+import type { Agent } from '@deepseek-ai/dsh-agent'
+import SubagentService from '@deepseek-ai/dsh-subagent'
+import type { SubprocessHandle } from '@deepseek-ai/dsh-subprocess'
+import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local'
+import * as codex from '../src/index.ts'
+import {
+  startResponsesFixture,
+  type ResponsesBehavior,
+  type ResponsesFixture,
+} from './responses-fixture.ts'
+
+const execFileAsync = promisify(execFile)
+const packageRoot = resolve(fileURLToPath(new URL('..', import.meta.url)))
+const codexBinDir = join(packageRoot, 'node_modules', '.bin')
+const codexPackage = JSON.parse(readFileSync(
+  join(packageRoot, 'node_modules', '@openai', 'codex', 'package.json'),
+  'utf8',
+)) as { version: string }
+
+const roots: string[] = []
+const fixtures: ResponsesFixture[] = []
+const contexts: Context[] = []
+
+afterEach(async () => {
+  await Promise.all(contexts.splice(0).map(ctx => ctx.fiber.dispose()))
+  await Promise.all(fixtures.splice(0).map(fixture => fixture.close()))
+  for (const root of roots.splice(0)) {
+    rmSync(root, { recursive: true, force: true })
+  }
+})
+
+interface RealHarness {
+  readonly ctx: Context
+  readonly handles: SubprocessHandle[]
+  readonly parent: Agent
+  readonly env: Record<string, string>
+  readonly workspace: string
+}
+
+async function realHarness(script: readonly ResponsesBehavior[]): Promise<{
+  readonly harness: RealHarness
+  readonly fixture: ResponsesFixture
+}> {
+  const root = mkdtempSync(join(tmpdir(), 'dsh-codex-real-'))
+  roots.push(root)
+  const workspace = join(root, 'workspace')
+  const codexHome = join(root, 'codex-home')
+  const fixture = await startResponsesFixture(script)
+  fixtures.push(fixture)
+  mkdirSync(workspace)
+  mkdirSync(codexHome)
+  writeFileSync(join(codexHome, 'config.toml'), [
+    'model = "fixture-model"',
+    'model_provider = "fixture"',
+    'approval_policy = "on-request"',
+    'sandbox_mode = "read-only"',
+    'disable_response_storage = true',
+    'check_for_update_on_startup = false',
+    '',
+    '[model_providers.fixture]',
+    'name = "Fixture Responses"',
+    `base_url = "${fixture.baseUrl}"`,
+    'env_key = "OPENAI_API_KEY"',
+    'wire_api = "responses"',
+    'requires_openai_auth = false',
+    '',
+    '[analytics]',
+    'enabled = false',
+    '',
+  ].join('\n'))
+  const env = {
+    OPENAI_API_KEY: 'dsh-fake-openai-key',
+    CODEX_HOME: codexHome,
+    HOME: root,
+    XDG_CONFIG_HOME: join(root, 'xdg'),
+    PATH: `${codexBinDir}${delimiter}${process.env.PATH ?? ''}`,
+    HTTP_PROXY: '',
+    HTTPS_PROXY: '',
+    ALL_PROXY: '',
+    NO_PROXY: '127.0.0.1,localhost',
+  }
+  const ctx = new Context()
+  contexts.push(ctx)
+  await ctx.plugin(SubagentService)
+  await ctx.plugin(LocalSubprocessService)
+  const handles: SubprocessHandle[] = []
+  const spawn = ctx.subprocess.spawn.bind(ctx.subprocess)
+  vi.spyOn(ctx.subprocess, 'spawn').mockImplementation((spec) => {
+    const handle = spawn(spec)
+    handles.push(handle)
+    return handle
+  })
+  await ctx.plugin(codex, { env, disposeGraceMs: 2_000 })
+  const parent = {
+    id: 'real-parent',
+    session: { header: { cwd: workspace } },
+  } as unknown as Agent
+  return { harness: { ctx, handles, parent, env, workspace }, fixture }
+}
+
+async function expectQuiescent(handles: readonly SubprocessHandle[]): Promise<void> {
+  expect(handles.length).toBeGreaterThan(0)
+  for (const handle of handles) {
+    await expect(handle.waitForExit()).resolves.toBe(true)
+    const outcome = await handle.done
+    expect(outcome).toHaveProperty('exitCode')
+    expect(outcome).toHaveProperty('signal')
+  }
+}
+
+function responseInputTexts(body: Record<string, unknown>): string[] {
+  if (!Array.isArray(body.input)) return []
+  return body.input.flatMap((item): string[] => {
+    if (item === null || typeof item !== 'object') return []
+    const content = (item as Record<string, unknown>).content
+    if (!Array.isArray(content)) return []
+    return content.flatMap((part): string[] => (
+      part !== null
+      && typeof part === 'object'
+      && typeof (part as Record<string, unknown>).text === 'string'
+        ? [(part as Record<string, unknown>).text as string]
+        : []
+    ))
+  })
+}
+
+describe('real @openai/codex 0.146.0 product', () => {
+  it('passes the exact task and fake authentication to local Responses and returns exact text', async () => {
+    const sentinel = 'REAL_CODEX_SENTINEL_0_146_0'
+    const task = 'Return the fixture sentinel exactly.'
+    const { harness, fixture } = await realHarness([
+      { kind: 'complete', text: sentinel },
+    ])
+    expect(codexPackage.version).toBe('0.146.0')
+    const version = await execFileAsync(join(codexBinDir, 'codex'), ['--version'], {
+      env: { ...process.env, ...harness.env },
+    })
+    expect(version.stdout.trim()).toBe('codex-cli 0.146.0')
+
+    const run = await harness.ctx.subagents.start('codex', {
+      prompt: [{ type: 'text', text: task }],
+      parent: harness.parent,
+      signal: new AbortController().signal,
+    })
+    await expect(run.result).resolves.toEqual({
+      output: [{ type: 'text', text: sentinel }],
+      stopReason: 'completed',
+    })
+    await run.dispose()
+
+    expect(fixture.requests).toHaveLength(1)
+    const recorded = fixture.requests[0]!
+    expect(recorded.method).toBe('POST')
+    expect(recorded.path).toBe('/v1/responses')
+    expect(recorded.headers.authorization).toBe('Bearer dsh-fake-openai-key')
+    expect(responseInputTexts(recorded.body)).toContain(task)
+    await expectQuiescent(harness.handles)
+  }, 20_000)
+
+  it('declines a real app-server command approval without executing the command', async () => {
+    const sentinel = 'REAL_CODEX_APPROVAL_DECLINED'
+    const { harness, fixture } = await realHarness([
+      {
+        kind: 'functionCall',
+        name: 'exec_command',
+        arguments: {
+          cmd: 'touch approval-side-effect',
+          sandbox_permissions: 'require_escalated',
+          justification: 'exercise the unattended approval boundary',
+        },
+      },
+      { kind: 'complete', text: sentinel },
+    ])
+    const sideEffect = join(harness.workspace, 'approval-side-effect')
+    const run = await harness.ctx.subagents.start('codex', {
+      prompt: [{ type: 'text', text: 'Attempt the fixture command.' }],
+      parent: harness.parent,
+      signal: new AbortController().signal,
+    })
+    await expect(run.result).resolves.toEqual({
+      output: [{ type: 'text', text: sentinel }],
+      stopReason: 'completed',
+    })
+    await run.dispose()
+
+    expect(existsSync(sideEffect)).toBe(false)
+    expect(fixture.requests).toHaveLength(2)
+    const tools = fixture.requests[0]!.body.tools as Array<Record<string, unknown>>
+    expect(tools).toEqual(expect.arrayContaining([
+      expect.objectContaining({ type: 'function', name: 'exec_command' }),
+    ]))
+    const followup = JSON.stringify(fixture.requests[1]!.body)
+    expect(followup).toContain('call_fixture')
+    expect(followup).toContain('rejected by user')
+    expect(fixture.requests.every(requestEntry =>
+      requestEntry.headers.authorization === 'Bearer dsh-fake-openai-key',
+    )).toBe(true)
+    await expectQuiescent(harness.handles)
+  }, 20_000)
+
+  it('settles cancellation locally and leaves the real app-server tree quiescent', async () => {
+    const { harness, fixture } = await realHarness([{ kind: 'hold' }])
+    const controller = new AbortController()
+    const run = await harness.ctx.subagents.start('codex', {
+      prompt: [{ type: 'text', text: 'Wait for cancellation.' }],
+      parent: harness.parent,
+      signal: controller.signal,
+    })
+    await fixture.requestStarted
+    controller.abort(new Error('real product cancellation'))
+    await expect(run.result).resolves.toMatchObject({ stopReason: 'aborted' })
+    await run.dispose()
+    await expectQuiescent(harness.handles)
+  }, 20_000)
+})

packages/subagent/subagent-codex/tests/responses-fixture.ts

@@ -0,0 +1,283 @@
+import { createServer } from 'node:http'
+import type {
+  IncomingHttpHeaders,
+  IncomingMessage,
+  Server,
+  ServerResponse,
+} from 'node:http'
+
+/** One request observed by the package-private Responses fixture. */
+interface RecordedResponsesRequest {
+  readonly method: string | undefined
+  readonly path: string | undefined
+  readonly headers: IncomingHttpHeaders
+  readonly body: Record<string, unknown>
+}
+
+/** Behavior consumed by one Responses request. */
+export type ResponsesBehavior =
+  | { readonly kind: 'complete'; readonly text: string }
+  | {
+    readonly kind: 'functionCall'
+    readonly name: string
+    readonly arguments: Record<string, unknown>
+  }
+  | { readonly kind: 'hold' }
+
+/** Running package-private Responses fixture. */
+export interface ResponsesFixture {
+  readonly baseUrl: string
+  readonly requests: RecordedResponsesRequest[]
+  readonly requestStarted: Promise<void>
+  close(): Promise<void>
+}
+
+function responseObject(text: string): Record<string, unknown> {
+  const message = {
+    id: 'msg_fixture',
+    type: 'message',
+    status: 'completed',
+    role: 'assistant',
+    content: [{
+      type: 'output_text',
+      annotations: [],
+      logprobs: [],
+      text,
+    }],
+  }
+  return {
+    id: 'resp_fixture',
+    object: 'response',
+    created_at: 1,
+    status: 'completed',
+    background: false,
+    error: null,
+    incomplete_details: null,
+    instructions: null,
+    max_output_tokens: null,
+    max_tool_calls: null,
+    model: 'fixture-model',
+    output: [message],
+    parallel_tool_calls: true,
+    previous_response_id: null,
+    prompt_cache_key: null,
+    prompt_cache_retention: null,
+    reasoning: { effort: null, summary: null },
+    safety_identifier: null,
+    service_tier: 'default',
+    store: false,
+    temperature: null,
+    text: { format: { type: 'text' }, verbosity: 'medium' },
+    tool_choice: 'auto',
+    tools: [],
+    top_logprobs: 0,
+    top_p: null,
+    truncation: 'disabled',
+    usage: {
+      input_tokens: 10,
+      input_tokens_details: { cached_tokens: 0 },
+      output_tokens: 1,
+      output_tokens_details: { reasoning_tokens: 0 },
+      total_tokens: 11,
+    },
+    user: null,
+    metadata: {},
+  }
+}
+
+function completeEvents(text: string): Record<string, unknown>[] {
+  const completed = responseObject(text)
+  const message = (completed.output as Record<string, unknown>[])[0]!
+  const part = (message.content as Record<string, unknown>[])[0]!
+  return [
+    {
+      type: 'response.created',
+      response: { ...completed, status: 'in_progress', output: [] },
+    },
+    {
+      type: 'response.output_item.added',
+      output_index: 0,
+      item: { ...message, status: 'in_progress', content: [] },
+    },
+    {
+      type: 'response.content_part.added',
+      item_id: message.id,
+      output_index: 0,
+      content_index: 0,
+      part: { ...part, text: '' },
+    },
+    {
+      type: 'response.output_text.delta',
+      item_id: message.id,
+      output_index: 0,
+      content_index: 0,
+      delta: text,
+      logprobs: [],
+    },
+    {
+      type: 'response.output_text.done',
+      item_id: message.id,
+      output_index: 0,
+      content_index: 0,
+      text,
+      logprobs: [],
+    },
+    {
+      type: 'response.content_part.done',
+      item_id: message.id,
+      output_index: 0,
+      content_index: 0,
+      part,
+    },
+    {
+      type: 'response.output_item.done',
+      output_index: 0,
+      item: message,
+    },
+    { type: 'response.completed', response: completed },
+  ]
+}
+
+function functionCallEvents(
+  name: string,
+  argumentsValue: Record<string, unknown>,
+): Record<string, unknown>[] {
+  const argumentsText = JSON.stringify(argumentsValue)
+  const item = {
+    id: 'fc_fixture',
+    type: 'function_call',
+    status: 'completed',
+    name,
+    arguments: argumentsText,
+    call_id: 'call_fixture',
+  }
+  const completed = {
+    ...responseObject(''),
+    output: [item],
+    usage: {
+      input_tokens: 10,
+      input_tokens_details: { cached_tokens: 0 },
+      output_tokens: 5,
+      output_tokens_details: { reasoning_tokens: 0 },
+      total_tokens: 15,
+    },
+  }
+  return [
+    {
+      type: 'response.created',
+      response: { ...completed, status: 'in_progress', output: [] },
+    },
+    {
+      type: 'response.output_item.added',
+      output_index: 0,
+      item: { ...item, status: 'in_progress', arguments: '' },
+    },
+    {
+      type: 'response.function_call_arguments.delta',
+      item_id: item.id,
+      output_index: 0,
+      delta: argumentsText,
+    },
+    {
+      type: 'response.function_call_arguments.done',
+      item_id: item.id,
+      output_index: 0,
+      arguments: argumentsText,
+    },
+    {
+      type: 'response.output_item.done',
+      output_index: 0,
+      item,
+    },
+    { type: 'response.completed', response: completed },
+  ]
+}
+
+function readRequest(request: IncomingMessage): Promise<string> {
+  return new Promise((resolve, reject) => {
+    let body = ''
+    request.setEncoding('utf8')
+    request.on('data', (chunk: string) => { body += chunk })
+    request.on('end', () => { resolve(body) })
+    request.on('error', reject)
+  })
+}
+
+function closeServer(server: Server): Promise<void> {
+  return new Promise((resolve, reject) => {
+    server.close((error) => {
+      if (error !== undefined) reject(error)
+      else resolve()
+    })
+    server.closeAllConnections()
+  })
+}
+
+/**
+ * Start a loopback-only Responses SSE fixture.
+ * @param script - one behavior per expected Responses request.
+ * @returns the running fixture and its observed requests.
+ */
+export async function startResponsesFixture(
+  script: readonly ResponsesBehavior[],
+): Promise<ResponsesFixture> {
+  const behaviors = [...script]
+  const requests: RecordedResponsesRequest[] = []
+  const started = Promise.withResolvers<undefined>()
+  const openResponses = new Set<ServerResponse>()
+  const server = createServer((request, response) => {
+    openResponses.add(response)
+    response.on('close', () => { openResponses.delete(response) })
+    void readRequest(request).then((body) => {
+      requests.push({
+        method: request.method,
+        path: request.url,
+        headers: request.headers,
+        body: JSON.parse(body) as Record<string, unknown>,
+      })
+      started.resolve(undefined)
+      const behavior = behaviors.shift()
+      if (behavior === undefined) {
+        response.writeHead(500, { 'content-type': 'application/json' })
+        response.end(JSON.stringify({ error: { message: 'fixture script exhausted' } }))
+        return
+      }
+      response.writeHead(200, {
+        'content-type': 'text/event-stream',
+        'cache-control': 'no-cache',
+        connection: 'keep-alive',
+        'x-request-id': 'req_fixture',
+      })
+      if (behavior.kind === 'hold') return
+      const events = behavior.kind === 'complete'
+        ? completeEvents(behavior.text)
+        : functionCallEvents(behavior.name, behavior.arguments)
+      for (const event of events) {
+        response.write(`data: ${JSON.stringify(event)}\n\n`)
+      }
+      response.end('data: [DONE]\n\n')
+    }).catch((error: unknown) => {
+      response.destroy(error instanceof Error ? error : new Error(String(error)))
+    })
+  })
+  await new Promise<void>((resolve, reject) => {
+    server.once('error', reject)
+    server.listen(0, '127.0.0.1', () => {
+      server.off('error', reject)
+      resolve()
+    })
+  })
+  const address = server.address()
+  if (address === null || typeof address === 'string') {
+    throw new Error('responses fixture did not acquire a TCP port')
+  }
+  return {
+    baseUrl: `http://127.0.0.1:${address.port}/v1`,
+    requests,
+    requestStarted: started.promise,
+    async close(): Promise<void> {
+      for (const response of openResponses) response.destroy()
+      await closeServer(server)
+    },
+  }
+}