Files
deepseek-harness/packages/subagent/subagent-spawn/tests/spawn.e2e.ts
T
Tianyi Cui 59dc310bb5 Merge branch 'codex/simp-agent-entry-state' into codex/simp-unify-agent-session-id
# Conflicts:
#	docs/architecture.md
#	docs/config-catalog.md
#	docs/cordis-catalog/events.md
#	docs/cordis-catalog/services.md
#	docs/core-data-structures/core.md
#	docs/event-producer-consumer.md
#	docs/module-graph.md
#	examples/coding-agent/tests/code-mode.e2e.ts
#	examples/coding-agent/tests/coding-task.e2e.ts
#	examples/coding-agent/tests/compaction.e2e.ts
#	examples/coding-agent/tests/full-loop.e2e.ts
#	examples/coding-agent/tests/todo-write.e2e.ts
#	examples/cordis-agent/tests/cordis-tools.e2e.ts
#	packages/bash/tool-bash/tests/integration.spec.ts
#	packages/bash/tool-bash/tests/tools.spec.ts
#	packages/compact/compact-basic/tests/compact-loop-repro.spec.ts
#	packages/context/time-context/tests/time-context.spec.ts
#	packages/cordis/tool-cordis/src/api-catalog.ts
#	packages/cordis/tool-cordis/tests/integration.spec.ts
#	packages/core/agent-loop/README.md
#	packages/core/agent-loop/src/agent.ts
#	packages/core/agent-loop/src/index.ts
#	packages/core/agent-loop/tests/agent.spec.ts
#	packages/core/agent-loop/tests/cancel.spec.ts
#	packages/core/agent-loop/tests/config-session-id.spec.ts
#	packages/core/agent-loop/tests/contract-regressions.spec.ts
#	packages/core/agent-loop/tests/coverage-edges.spec.ts
#	packages/core/agent-loop/tests/interception.spec.ts
#	packages/core/agent-loop/tests/loop.spec.ts
#	packages/core/agent-loop/tests/properties.spec.ts
#	packages/core/agent-loop/tests/request-cache.e2e.ts
#	packages/core/agent-loop/tests/request-reconstruction.spec.ts
#	packages/core/agent-loop/tests/resume.spec.ts
#	packages/core/agent-loop/tests/scope-lifecycle.spec.ts
#	packages/core/agent-loop/tests/tool-order.spec.ts
#	packages/core/agent-loop/tests/turn-stop.spec.ts
#	packages/core/agent/src/types.ts
#	packages/examples/agent-spine-demo/README.md
#	packages/examples/agent-spine-demo/tests/agent-core.spec.ts
#	packages/examples/stdio-demo/README.md
#	packages/examples/stdio-demo/src/index.ts
#	packages/examples/stdio-demo/tests/stdio-agent.spec.ts
#	packages/fs/tool-fs/tests/fs-tools.e2e.ts
#	packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts
#	packages/hooks/hooks-claude/tests/bridge.spec.ts
#	packages/hooks/hooks-claude/tests/coverage.spec.ts
#	packages/hooks/hooks-codex/tests/bridge.spec.ts
#	packages/hooks/hooks-codex/tests/coverage.spec.ts
#	packages/subagent/subagent-fork/tests/multi-subagent.spec.ts
#	packages/subagent/subagent-fork/tests/subagent-fork.spec.ts
#	packages/subagent/subagent-inprocess/tests/structured.spec.ts
#	packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts
#	packages/subagent/subagent-spawn/tests/spawn.e2e.ts
#	packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts
#	packages/todo/tool-todo/tests/integration.spec.ts
#	packages/ui/acp/tests/dispose.spec.ts
#	packages/ui/acp/tests/edges.spec.ts
#	packages/workflow/workflow-workerthread/tests/integration.spec.ts
2026-07-18 12:21:15 +08:00

51 lines
2.2 KiB
TypeScript

import { mkdtemp, readFile, rm } from 'node:fs/promises'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import type { Context } from 'cordis'
import { spawnHarness, waitForIdle } from './harness.ts'
import { SessionId } from '@deepseek-ai/dsh-session'
/**
* With-key smoke for the in-process spawn backend: a REAL parent agent delegates
* to a REAL child (via the `subagent` tool → spawn backend) that uses the REAL
* bash tool to write a file, and we verify the WORLD (the file on disk) — not
* the agent's self-report. This is the "green units, broken product" guard:
* mocks prove the plumbing, only a real model proves a parent can actually drive
* a child to do real work. Key-gated (self-skips without DEEPSEEK_API_KEY).
*/
let ctx: Context | undefined
let workdir: string | undefined
afterEach(async () => {
await ctx?.fiber.dispose()
ctx = undefined
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
workdir = undefined
})
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('spawn backend with-key smoke', () => {
it('a parent delegates to a child that writes a file on disk', async () => {
workdir = await mkdtemp(join(tmpdir(), 'dsh-subagent-spawn-e2e-'))
ctx = await spawnHarness(workdir)
const parent = ctx.agentLoop.create(SessionId('e2e-parent'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
parent.send([{ type: 'text', text:
'Use the subagent tool to delegate this exact task: "Use the bash tool to write the text '
+ 'SUBAGENT_WAS_HERE into a file named proof.txt in the current directory." '
+ 'After the subagent finishes, tell me it is done.' }])
await waitForIdle(ctx, parent)
// Verify the WORLD: the child actually wrote the file.
const proof = await readFile(join(workdir, 'proof.txt'), 'utf8')
expect(proof).toContain('SUBAGENT_WAS_HERE')
// The parent's log records the subagent tool/call + its result (not the
// child's internal steps).
const events = [...parent.session.events]
const subagentCalls = events.filter(e => e.type === 'tool/call' && e.data.name === 'subagent')
expect(subagentCalls.length).toBeGreaterThan(0)
}, 180_000)
})