mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
b5f618bcfb
In-place port of dsh-workflow-vm from the in-process node:vm execution to one worker thread per run (the workflow-workerthread engine of PR #215, adopted as THE engine): the script's vm context moves inside the worker, agent() bridges to ctx.subagents over the message port (host.ts/protocol.ts/session.ts/worker.ts are new; runtime.ts loses the abandon channel — the host's grace timer force-settles and TERMINATES instead), start() pre-parses the body host-side to keep the seam's synchronous SCRIPT_PARSE throw, and a ready→go handshake keeps a run cancelled before start from ever executing the body. start() no longer blocks the host, termination is real, and the value boundary is serialization by construction. The package keeps its name until the follow-up rename commit; scripts see the identical hook surface, and the seam-contract tests hardened ahead of this swap pass unchanged. The run and child-RPC surfaces are class-shaped rather than literal bundles: WorkerRun IMPLEMENTS the seam's WorkflowRun (id/meta are its own clone, separate from event payloads') and start() returns the instance directly — interface parity with the seam is compiler-checked; worker-side, ChildRpcBridge (implements ChildPort; callId allocation + pending book-keeping settled by onChild* entry points) and RpcChildHandle (every member an RPC keyed by its callId) carry names in stacks. ChildPort's method is startAgent — it names what it starts, matching the script-side agent() hook and the agentsStarted / workflow/agent-* vocabulary; the Child* type names deliberately stay (the worker side is cordis- and subagent-free; these are reduced JSON projections, not the seam's types). Review findings from the reference PR are folded in rather than re-introduced: - cancel() drives BOTH child-cancel channels host-side: the request signal aborts AND each registered child's explicit cancel() is called — a worker wedged in a synchronous spin cannot relay its own ChildCancel RPCs (regression: cancel-only provider + wedged worker). - All host warn paths render through the total renderThrown; a child dispose() rejecting a value whose coercion throws still acks ChildDisposed instead of wedging the script's finally (regression). - built-worker.e2e.ts is wired into builtBinSmokeGate and the AGENTS.md CI sequence — the built lib/worker.js resolution contract now runs in an automated gate. - workflow/end payload pinned on the worker-death path (with the cancelled and grace-force-settle pins riding the ported spec). - Real-Worker scripted timing budgets widened (50-300ms → 150-1000ms) for starved CI hosts. Workspace plumbing: the "./worker" subpath export sanctions the second runtime bundle (check-workspace-constraints), tsdown builds two single-entry passes, tsx becomes a devDependency for the unbuilt worker spawn.
92 lines
4.0 KiB
TypeScript
92 lines
4.0 KiB
TypeScript
import { describe, expect, it } from 'vitest'
|
|
import { Context } from 'cordis'
|
|
import LlmService from '@deepseek-ai/dsh-llm'
|
|
import SessionStore from '@deepseek-ai/dsh-session'
|
|
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
|
import ToolRegistry from '@deepseek-ai/dsh-tools'
|
|
import AgentRegistry, { AgentId } from '@deepseek-ai/dsh-agent'
|
|
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
|
|
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 ctx.plugin(LlmService)
|
|
await ctx.plugin(SessionStore)
|
|
await ctx.plugin(SystemPrompt)
|
|
await ctx.plugin(ToolRegistry)
|
|
await ctx.plugin(AgentRegistry)
|
|
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(AgentId('parent'), { model: 'mock' })
|
|
return { ctx, parent, adapter }
|
|
}
|
|
|
|
describe('dsh-workflow-vm 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) => { childIds.push(agent.childId) })
|
|
const run = ctx.workflows.start({
|
|
script: `export const meta = { name: 'integration', description: 'plain + structured children' }
|
|
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(AgentId(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({
|
|
script: `export const meta = { name: 'null-path', description: 'schema failure maps to null' }
|
|
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()
|
|
})
|
|
})
|