deepseek-harness/packages/subagent/subagent-fork/tests/subagent-fork.spec.ts

import { describe, expect, it } from 'vitest'
import { Context } from 'cordis'
import Loader from '@cordisjs/plugin-loader'
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 { MockAdapter, textResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
import type { StreamChunk } from '@deepseek-ai/dsh-llm'
import * as fork from '../src/index.ts'
import { completedTurnPrefix } from '../src/index.ts'

type Script = ConstructorParameters<typeof MockAdapter>[0]

/** A bare `stop` finish that streams no content → the turn ends `completed`
 * with NO `assistant/message` of its own. */
const emptyStop: StreamChunk[] = [{ type: 'finish', reason: { kind: 'stop' } }]

/**
 * Drives the REAL fork backend with a real loop + scripted mock MODEL + the
 * real dsh-invariants plugin. The invariants plugin re-replays a seeded child
 * log on `session/created` (its freeze-check), so a malformed (unbalanced) fork
 * seed makes these tests THROW — that is the regression guard for the
 * completed-turn-prefix boundary.
 */
async function setup(script: Script) {
  const ctx = new Context()
  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(fork, { providerName: 'fork', structuredNudgeRetries: 1 })
  ctx.llm.registerAdapter(['mock'], new MockAdapter(script))
  const parent = ctx.agentLoop.create(AgentId('parent'), { model: 'mock' })
  return { ctx, parent }
}

function text(blocks: { type: string; text?: string }[]): string {
  return blocks.filter(b => b.type === 'text').map(b => b.text).join('')
}

describe('completedTurnPrefix', () => {
  it('returns an empty prefix for a parent that has never completed a turn', async () => {
    const { parent } = await setup([])
    expect(completedTurnPrefix(parent)).toEqual([])
  })

  it('returns the balanced prefix up to and including the last turn/end', async () => {
    const { parent } = await setup([textResponse('first'), textResponse('second')])
    parent.send([{ type: 'text', text: 'q1' }])
    await parent.whenIdle()
    parent.send([{ type: 'text', text: 'q2' }])
    await parent.whenIdle()

    const prefix = completedTurnPrefix(parent)
    // Ends exactly at the last turn/end; seq is contiguous from 0.
    expect(prefix.at(-1)?.type).toBe('turn/end')
    expect(prefix.map(e => e.seq)).toEqual(prefix.map((_, i) => i))
    // Both completed turns are present.
    expect(prefix.filter(e => e.type === 'turn/end')).toHaveLength(2)
  })
})

describe('dsh-subagent-fork', () => {
  it('forks an UNSEEDED (fresh) child when the parent has no completed turn', async () => {
    // The parent has never completed a turn → empty prefix → the provider omits
    // the seed → the child runs fresh. Exercises the `seed.length > 0` false arm.
    const { ctx, parent } = await setup([textResponse('fresh child')])
    expect(completedTurnPrefix(parent)).toEqual([])
    const run = ctx.subagents.start('fork', { prompt: [{ type: 'text', text: 'child q' }], parent })
    const result = await run.result
    expect(result.stopReason).toBe('completed')
    expect(text(result.output)).toBe('fresh child')
    const child = ctx.agents.get(run.id)!
    // Only the child's own turn — no seeded parent turns.
    expect(child.session.events.filter(e => e.type === 'turn/end')).toHaveLength(1)
    await run.dispose()
  })

  it('seeds the child with the parent\'s completed-turn prefix (child inherits context)', async () => {
    // Parent runs one turn, then we fork. The child's seeded log should contain
    // the parent's first turn, and the child should run its own new turn on top.
    const { ctx, parent } = await setup([textResponse('parent answer'), textResponse('child answer')])
    parent.send([{ type: 'text', text: 'parent question' }])
    await parent.whenIdle()
    const parentPrefixLen = parent.session.events.length

    const run = ctx.subagents.start('fork', { prompt: [{ type: 'text', text: 'child question' }], parent })
    const result = await run.result
    expect(result.stopReason).toBe('completed')
    expect(text(result.output)).toBe('child answer')

    const child = ctx.agents.get(run.id)!
    // The child's log STARTS with the parent's prefix (seeded), then its own turn.
    expect(child.session.events.length).toBeGreaterThan(parentPrefixLen)
    // The seeded prefix carried the parent's user message.
    const seededUser = child.session.events.slice(0, parentPrefixLen).find(e => e.type === 'user/message')
    expect(seededUser).toBeDefined()
    // Lineage stamped.
    expect(child.session.header.parentSession).toBe(parent.session.header.id)
    // The seed boundary is recorded on the header (= the seeded prefix length),
    // so a reload / replay harness can tell the inherited prefix from the
    // child's own events.
    expect(child.session.header.seedLength).toBe(parentPrefixLen)
    await run.dispose()
  })

  it('produces an invariant-CLEAN seed: forking mid-turn excludes the open turn', async () => {
    // Drive the parent so it has ONE completed turn, then start a SECOND turn
    // that is still open (a hanging model call), and fork while it's in flight.
    // The fork must seed only the completed first turn — an unbalanced seed
    // would make the invariants replay throw inside ctx.subagents.start.
    const { ctx, parent } = await setup([textResponse('done'), 'hang', textResponse('child')])
    parent.send([{ type: 'text', text: 'q1' }])
    await parent.whenIdle()
    // Start a second turn that hangs (open turn/start + open step, never ends).
    parent.send([{ type: 'text', text: 'q2' }])
    await new Promise(r => setTimeout(r, 20)) // let the hanging turn open

    // Forking now must NOT throw (the open second turn is excluded from the seed).
    const run = ctx.subagents.start('fork', { prompt: [{ type: 'text', text: 'child q' }], parent })
    const result = await run.result
    expect(result.stopReason).toBe('completed')
    expect(text(result.output)).toBe('child')

    const child = ctx.agents.get(run.id)!
    // The child's seed has exactly the ONE completed parent turn (the open one excluded).
    const seedTurnEnds = child.session.events.filter(e => e.type === 'turn/end')
    // 1 from the seeded parent turn + 1 from the child's own completed turn.
    expect(seedTurnEnds.length).toBe(2)

    parent.cancel()
    await run.dispose()
  })

  it('does NOT return the seeded parent output when the child produces no message of its own', async () => {
    // Regression: readResult must scope to the child's OWN events (after the
    // seed). The parent completes a turn with a distinctive assistant message,
    // then the fork child's own turn finishes with a bare `stop` and NO
    // assistant/message. Scanning the whole (seeded) log would return the
    // parent's "parent stale" message with stopReason 'completed'; scoped to the
    // child's own events the output is empty.
    const { ctx, parent } = await setup([textResponse('parent stale'), emptyStop])
    parent.send([{ type: 'text', text: 'parent question' }])
    await parent.whenIdle()

    const run = ctx.subagents.start('fork', { prompt: [{ type: 'text', text: 'child question' }], parent })
    const result = await run.result
    // The child completed its own (empty) turn — completed, but with NO output
    // borrowed from the seeded parent prefix.
    expect(result.stopReason).toBe('completed')
    expect(result.output).toEqual([])
    await run.dispose()
  })

  it('advertises depthLimit and outputSchema but not toolFilter', async () => {
    const { ctx } = await setup([])
    expect(ctx.subagents.getProvider('fork')!.capabilities).toEqual({ outputSchema: true, depthLimit: true, toolFilter: false })
  })

  it('unregisters the provider when its fiber is disposed (HMR safety)', async () => {
    const ctx = new Context()
    await ctx.plugin(SubagentService)
    await ctx.plugin(AgentRegistry)
    // The backend injects 'tools' for the structured runtime, so the registry
    // (and its systemPrompt dependency) must be live for the fiber to activate.
    await ctx.plugin(SystemPrompt)
    await ctx.plugin(ToolRegistry)
    const fiber = await ctx.plugin(fork, { providerName: 'fork', structuredNudgeRetries: 1 })
    expect(ctx.subagents.list()).toEqual(['fork'])
    await fiber.dispose()
    expect(ctx.subagents.list()).toEqual([])
  })

  it('has the namespace-plugin export shape (no stray default)', () => {
    expect('default' in fork).toBe(false)
    expect(fork.name).toBe('subagent-fork')
    expect(fork.inject).toEqual(['subagents', 'agents', 'tools'])
    const loader = Object.create(Loader.prototype) as Loader
    const unwrapped = loader.unwrapExports(fork) as Record<string, unknown>
    expect(unwrapped).toBe(fork)
    expect(unwrapped.name).toBe('subagent-fork')
    expect(unwrapped.inject).toEqual(['subagents', 'agents', 'tools'])
    expect(typeof unwrapped.apply).toBe('function')
  })
})