deepseek-harness/apps/cli/src/headless.ts

/**
 * `dsh -p "task"` — headless over the one shared composition: AppCLIEntry
 * boots the same base plus Web overlay as `dsh web` (port 0, so parallel runs never
 * collide), then in-process isomorphic injection (InProcessApiClient over
 * toFetchHandler(ctx.apiProxy), so the full carrier chain — wire
 * serialization, zod, SSE framing — really runs). The printed URL opens the
 * live session in a browser while the task runs. Runs one task turn, prints
 * the final assistant text, exits (completed → 0, else 1).
 */

import { fileURLToPath } from 'node:url'
import { InProcessApiClient, toFetchHandler } from '@deepseek-ai/dsh-host-apiproxy'
import type { MuxFrame } from '@deepseek-ai/dsh-host-apiproxy/api'
import type { RpcRequest, RpcResponse } from '@deepseek-ai/dsh-host-apiproxy/api/rpc'
import type { SessionId } from '@deepseek-ai/dsh-session'
import { AppCLIEntry } from './app-cli-entry.ts'

/** Outcome of one headless turn: aggregated final text plus the turn-end reason kind. */
interface TurnOutcome {
  text: string
  reason: string
}

/** Unwrap an RpcResponse or fail loud: business errors print and exit 1 (dispose first). */
async function unwrap<T>(response: RpcResponse<T>, dispose: () => Promise<void>): Promise<T> {
  if (response.result.ok) return response.result.value
  const { code, message } = response.result.error
  process.stderr.write(`dsh: ${code}: ${message}\n`)
  await dispose()
  process.exit(1)
}

/**
 * Consume mux frames until the agent reaches idle, per the one-shot CLI
 * idle-to-idle contract: the stream opens immediately before the prompt, and
 * its first observed turn/start begins the task. Text is the last committed
 * assistant message of the whole interval (steering or injected work may run
 * further turns before quiescence), and the outcome reason is the final
 * turn/end's kind. Idleness is signalled out of band by the caller's
 * `agent/status` subscription; the stream itself carries no status frame.
 * @param frames - the mux stream opened before the prompt.
 * @param sessionId - the headless session.
 * @param idle - resolves when the agent reaches quiescence.
 * @returns the aggregated outcome.
 */
async function consumeUntilIdle(
  frames: AsyncIterable<RpcRequest<MuxFrame>>,
  sessionId: SessionId,
  idle: Promise<void>,
): Promise<TurnOutcome> {
  let started = false
  let text = ''
  let reason: string = 'error'
  void (async () => {
    try {
      for await (const frame of frames) {
        const payload = frame.payload
        if (payload.type === 'stream/error') return
        if (payload.type !== 'session/event' || payload.sessionId !== sessionId) continue
        const event = payload.event
        if (event.type === 'turn/start') {
          started = true
          continue
        }
        if (!started) continue
        if (event.type === 'assistant/message') {
          const joined = event.data.message.content.filter(block => block.type === 'text').map(block => block.text).join('')
          if (joined !== '') text = joined
        }
        if (event.type === 'turn/end') reason = event.data.reason.kind
      }
    } catch (error: unknown) {
      process.stderr.write(`dsh: event stream failed: ${String(error)}\n`)
    }
  })()
  await idle
  return { text, reason }
}

/**
 * Run one headless turn for `task` and exit (completed → 0, else 1). The task
 * is the non-empty prompt the argument adapter parsed from `-p`/`--prompt`
 * (the adapter rejects an empty task, so no guard is needed here).
 * @param task - the prompt text for the single turn.
 */
export async function runHeadless(task: string): Promise<void> {
  // A missing DEEPSEEK_API_KEY throws here (plugin load is fail-loud, uncaught by design).
  const entry = new AppCLIEntry({
    configPath: fileURLToPath(new URL('../config/base.cordis.yml', import.meta.url)),
    overlayPath: fileURLToPath(new URL('../config/web.cordis.yml', import.meta.url)),
    dev: false,
    watchPersonalConfig: false,
    port: 0,
  })
  const { ctx, port } = await entry.run()
  const dispose = async (): Promise<void> => { await ctx.fiber.dispose() }
  // Signal exits must still dispose the tree: the composition mounts
  // exit-drained plugins (telemetry's queued tail and shutdown marker would
  // otherwise be lost), and Node's default signal exit skips disposal.
  let signalled = false
  const disposeAndExit = (code: number): void => {
    if (signalled) return
    signalled = true
    void dispose().finally(() => { process.exit(code) })
  }
  process.on('SIGTERM', () => { disposeAndExit(143) })
  process.on('SIGINT', () => { disposeAndExit(130) })
  // The headless session is web-observable while it runs (same composition).
  process.stderr.write(`dsh: observing at http://127.0.0.1:${String(port)}\n`)
  const api = new InProcessApiClient(toFetchHandler(ctx.apiProxy))

  const created = await unwrap(await api.sessions.create({}), dispose)

  // Open the stream before prompting so no frame is lost — kept in this order
  // even though in-process delivery has no race, so the code survives a move
  // to a remote HTTP carrier unchanged.
  const abort = new AbortController()
  const frames = api.events.mux({}, abort.signal)
  const idle = new Promise<void>((resolve) => {
    ctx.on('agent/status', (agent, status) => {
      if (agent.id === created.sessionId && status === 'idle') resolve()
    })
  })
  const done = consumeUntilIdle(frames, created.sessionId, idle)

  await unwrap(await api.sessions.prompt({
    sessionId: created.sessionId,
    mode: 'queue',
    content: [{ type: 'text', text: task }],
  }), dispose)

  const outcome = await done
  process.stdout.write(outcome.text + '\n')
  abort.abort()
  await dispose()
  process.exit(outcome.reason === 'completed' ? 0 : 1)
}