Files
deepseek-harness/packages/workflow/workflow-workerthread/tests/integration.spec.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

90 lines
4.0 KiB
TypeScript

import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import { SessionId } from '@deepseek-ai/dsh-session'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
import * as Invariants from '@deepseek-ai/dsh-invariants'
import SubagentService from '@deepseek-ai/dsh-subagent'
import * as spawn from '@deepseek-ai/dsh-subagent-spawn'
import { STRUCTURED_OUTPUT_TOOL } from '@deepseek-ai/dsh-subagent-inprocess'
import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
import WorkerWorkflowEngine from '../src/index.ts'
type Script = ConstructorParameters<typeof MockAdapter>[0]
/**
* The whole in-process stack, keyless, with the script in a REAL worker
* thread: the engine drives the REAL spawn backend (with its
* structured runtime) on a real agent loop; the scripted mock MODEL is the
* only mocked boundary. This is the guard the unit suites structurally
* cannot give — the MessageChannel suite fakes the host, and the host suite
* stubs the subagent seam.
*/
async function setup(script: Script) {
const ctx = new Context()
const adapter = new MockAdapter(script)
await mountAgentLoopTestDependencies(ctx)
await ctx.plugin(Invariants)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(SubagentService)
await ctx.plugin(spawn, { providerName: 'spawn' })
await ctx.plugin(WorkerWorkflowEngine, {})
ctx.llm.registerAdapter(['mock'], adapter)
const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock' })
return { ctx, parent, adapter }
}
describe('dsh-workflow-workerthread over the real in-process stack', () => {
it('runs a two-stage workflow: a plain child, then a schema child through the structured runtime', async () => {
const { ctx, parent } = await setup([
textResponse('the file list is a.ts'),
toolCallResponse('c1', STRUCTURED_OUTPUT_TOOL, { verdict: 'real', confidence: 0.9 }),
])
const childIds: string[] = []
ctx.on('workflow/agent-start', (_info, agent) => {
// The workflow bridge must await asynchronous provider start: an observer
// sees the real spawn child already published, never a reserved id.
expect(ctx.agents.get(agent.childId)).toBeDefined()
childIds.push(agent.childId)
})
const run = ctx.workflows.start({
meta: { name: 'integration', description: 'plain + structured children' },
script: `phase('Read')
const prose = await agent('read the repo')
phase('Judge')
const judged = await agent('judge: ' + prose, {
schema: { type: 'object', properties: { verdict: { type: 'string', enum: ['real', 'bogus'] }, confidence: { type: 'number' } }, required: ['verdict'] },
})
return { prose, verdict: judged.verdict, confidence: judged.confidence }`,
parent,
})
const result = await run.result
expect(result.stopReason).toBe('completed')
expect(result.value).toEqual({ prose: 'the file list is a.ts', verdict: 'real', confidence: 0.9 })
expect(result.agentsStarted).toBe(2)
await run.dispose()
// Both children were disposed to quiescence — no live child agents remain.
expect(childIds.length).toBe(2)
for (const childId of childIds) {
expect(ctx.agents.get(SessionId(childId))).toBeUndefined()
}
})
it('a child that fails against its schema (nudges exhausted) reaches the script as null', async () => {
const { ctx, parent } = await setup([
textResponse('prose only'),
textResponse('still prose after the nudge'),
])
const run = ctx.workflows.start({
meta: { name: 'null-path', description: 'schema failure maps to null' },
script: `const judged = await agent('judge it', { schema: { type: 'object', properties: { v: { type: 'string' } } } })
return { got: judged === null ? 'null' : 'value' }`,
parent,
})
const result = await run.result
expect(result.stopReason).toBe('completed')
expect(result.value).toEqual({ got: 'null' })
await run.dispose()
})
})