feat(goal): add model-facing goal tools

2026-07-19 19:22:10 +08:00
parent e9940d35cf
commit 0129063ae7
24 changed files with 1388 additions and 1 deletions
@@ -0,0 +1,124 @@
+import { spawn, type ChildProcessWithoutNullStreams } from 'node:child_process'
+import { mkdtemp, readFile, readdir, rm } from 'node:fs/promises'
+import { tmpdir } from 'node:os'
+import { join } from 'node:path'
+import { fileURLToPath } from 'node:url'
+import { afterEach, describe, expect, it } from 'vitest'
+import { decodeGoalChange } from '@deepseek-ai/dsh-goal'
+import type { SessionEvent } from '@deepseek-ai/dsh-session'
+import { resolveExampleLaunch } from '@deepseek-ai/dsh-loader-smoke'
+
+const binScript = fileURLToPath(new URL('../../../examples/stdio-demo/src/bin.ts', import.meta.url))
+const configPath = fileURLToPath(new URL(
+  '../../../../examples/echo-agent/tests/fixtures/goal/tool-goal/cordis.yml',
+  import.meta.url,
+))
+const repoTsconfig = fileURLToPath(new URL('../../../../tsconfig.json', import.meta.url))
+const PROCESS_TIMEOUT_MS = 30_000
+const TEST_TIMEOUT_MS = PROCESS_TIMEOUT_MS + 15_000
+
+let child: ChildProcessWithoutNullStreams | undefined
+let workdir: string | undefined
+
+afterEach(async () => {
+  if (child !== undefined && child.exitCode === null) child.kill('SIGKILL')
+  child = undefined
+  if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
+  workdir = undefined
+})
+
+async function jsonlFiles(dir: string): Promise<string[]> {
+  const entries = await readdir(dir, { withFileTypes: true })
+  const paths = await Promise.all(entries.map(async (entry) => {
+    const path = join(dir, entry.name)
+    if (entry.isDirectory()) return jsonlFiles(path)
+    return entry.isFile() && entry.name.endsWith('.jsonl') ? [path] : []
+  }))
+  return paths.flat()
+}
+
+async function runComposition(): Promise<{ stdout: string; stderr: string }> {
+  workdir = await mkdtemp(join(tmpdir(), 'goal-tools-e2e-'))
+  const cwd = workdir
+  return new Promise((resolve, reject) => {
+    const launch = resolveExampleLaunch({
+      srcBin: binScript,
+      configArgs: [configPath],
+      tsconfigPath: repoTsconfig,
+      exposeInternals: true,
+      env: {
+        DSH_HOME: join(cwd, '.dsh'),
+        DSH_AGENTS_HOME: join(cwd, '.agents'),
+      },
+    })
+    const proc = spawn(launch.command, launch.args, {
+      cwd,
+      env: { ...process.env, ...launch.env },
+      stdio: ['pipe', 'pipe', 'pipe'],
+    })
+    child = proc
+    let stdout = ''
+    let stderr = ''
+    let pauseSent = false
+    let inputClosed = false
+    proc.stdout.setEncoding('utf8')
+    proc.stdout.on('data', (chunk: string) => {
+      stdout += chunk
+      if (!pauseSent && stdout.includes('GOAL CREATED') && stdout.includes('\n> ')) {
+        pauseSent = true
+        proc.stdin.write('pause\n')
+      }
+      if (!inputClosed && stdout.includes('GOAL PAUSED')) {
+        inputClosed = true
+        proc.stdin.end()
+      }
+    })
+    proc.stderr.setEncoding('utf8')
+    proc.stderr.on('data', (chunk: string) => { stderr += chunk })
+
+    const timer = setTimeout(() => {
+      proc.kill('SIGKILL')
+      reject(new Error(
+        `goal-tools e2e did not exit within ${PROCESS_TIMEOUT_MS / 1_000}s. stdout:\n${stdout}\nstderr:\n${stderr}`,
+      ))
+    }, PROCESS_TIMEOUT_MS)
+    proc.on('exit', (code) => {
+      clearTimeout(timer)
+      if (code === 0) resolve({ stdout, stderr })
+      else reject(new Error(`goal-tools e2e exited ${String(code)}. stdout:\n${stdout}\nstderr:\n${stderr}`))
+    })
+    proc.on('error', (error) => { clearTimeout(timer); reject(error) })
+    proc.stdin.write('start\n')
+  })
+}
+
+describe('goal tools through a real Loader, app, and stdio process', () => {
+  it('creates, reads, and pauses one root goal with durable tool and state records', async () => {
+    const { stdout, stderr } = await runComposition()
+    expect(stderr).not.toContain('UNHANDLED')
+    expect(stdout).toContain('goal-tools e2e ready.')
+    expect(stdout).toContain('GOAL CREATED')
+    expect(stdout).toContain('GOAL PAUSED')
+
+    const logs = await jsonlFiles(join(workdir as string, '.sessions'))
+    expect(logs).toHaveLength(1)
+    const lines = (await readFile(logs[0] as string, 'utf8')).trimEnd().split('\n')
+    const events = lines.slice(1).map(line => JSON.parse(line) as SessionEvent)
+    const calls = events.filter(event => event.type === 'tool/call')
+    expect(calls.map(event => event.data.name)).toEqual(['create_goal', 'get_goal', 'update_goal'])
+    const results = events.filter(event => event.type === 'tool/result')
+    expect(results).toHaveLength(3)
+    expect(results.every(event => !event.data.isError)).toBe(true)
+
+    const changes = events
+      .filter(event => event.type === 'context/message' && event.data.source.kind === 'goal')
+      .map(event => event.type === 'context/message' ? decodeGoalChange(event.data.meta) : undefined)
+    expect(changes.map(change => change?.operation)).toEqual(['create', 'pause'])
+    expect(changes[1]).toMatchObject({ goal: { phase: 'paused', revision: 2, maxGoalRounds: 7 } })
+    expect(JSON.stringify(changes)).not.toContain('activation')
+
+    const headers = events.filter(event => event.type === 'request/header')
+    expect(JSON.stringify(headers)).toContain('infer goal intent')
+    expect(JSON.stringify(headers)).toContain('at least 3 consecutive goal rounds')
+  }, TEST_TIMEOUT_MS)
+})
@@ -0,0 +1,374 @@
+import { describe, expect, it } from 'vitest'
+import { Context } from 'cordis'
+import Loader from '@cordisjs/plugin-loader'
+import AgentRegistry, { agentEvents } from '@deepseek-ai/dsh-agent'
+import type { Agent, AgentStatus, InjectOptions } from '@deepseek-ai/dsh-agent'
+import GoalService, { GoalId } from '@deepseek-ai/dsh-goal'
+import type { GoalRef } from '@deepseek-ai/dsh-goal'
+import { CallId } from '@deepseek-ai/dsh-llm'
+import type { ContentBlock, MessageSource } from '@deepseek-ai/dsh-llm'
+import { Session, SessionId } from '@deepseek-ai/dsh-session'
+import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
+import ToolRegistry from '@deepseek-ai/dsh-tools'
+import type { ToolExecutionResult } from '@deepseek-ai/dsh-tools'
+import * as toolGoal from '@deepseek-ai/dsh-tool-goal'
+
+interface StubAgent {
+  readonly agent: Agent
+  readonly session: Session
+  setStatus(status: AgentStatus): void
+}
+
+/** Build one registry-compatible live agent whose injections append in place. */
+function stubAgent(rawId: string): StubAgent {
+  const session = new Session(SessionId(rawId))
+  let status: AgentStatus = 'running'
+  const agent: Agent = {
+    id: session.id,
+    options: {},
+    session,
+    get status() { return status },
+    ctx: new Context(),
+    send() {},
+    steer() {},
+    inject(content: ContentBlock[], options?: InjectOptions) {
+      const source = options?.source ?? { kind: 'user' }
+      session.append('context/message', {
+        content,
+        source,
+        ...options?.envelope === undefined ? {} : { envelope: options.envelope },
+        ...options?.meta === undefined ? {} : { meta: options.meta },
+      }, { surfaceOp: 'append' })
+    },
+    cancel() {},
+    whenIdle() { return Promise.resolve() },
+  }
+  return { agent, session, setStatus(value) { status = value } }
+}
+
+/** Open one message-triggered turn with its accepted model-visible input. */
+function openTurn(stub: StubAgent, source: MessageSource, text = 'prompt'): number {
+  const turn = stub.session.events
+    .filter(event => event.type === 'turn/start')
+    .reduce((max, event) => Math.max(max, event.data.turn), 0) + 1
+  stub.session.append('turn/start', { turn, trigger: { kind: 'message', source } })
+  stub.session.append('user/message', {
+    content: [{ type: 'text', text }],
+    source,
+  }, { surfaceOp: 'append' })
+  return turn
+}
+
+/** Close the currently open test turn. */
+function closeTurn(stub: StubAgent, turn: number): void {
+  stub.session.append('turn/end', { turn, reason: { kind: 'completed' } })
+}
+
+async function harness(config: toolGoal.Config = {}) {
+  const ctx = new Context()
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(GoalService)
+  const fiber = await ctx.plugin(toolGoal, config)
+  const root = stubAgent(`goal-tool-root-${Math.random()}`)
+  ctx.agents.register(root.agent)
+  return { ctx, fiber, root }
+}
+
+/** Execute one registered tool under an optional driver initiator. */
+async function execute(
+  ctx: Context,
+  name: string,
+  args: unknown,
+  agent?: Agent,
+  initiator: Agent | undefined = agent,
+): Promise<ToolExecutionResult> {
+  const run = () => ctx.tools.execute({
+    callId: CallId(`call-${Math.random()}`),
+    name,
+    arguments: args,
+    ...agent === undefined ? {} : { agent },
+  })
+  return initiator === undefined ? run() : ctx.agents.withInitiator(initiator, run)
+}
+
+/** Parse the compact JSON returned by a successful goal tool. */
+function resultJson(result: ToolExecutionResult): Record<string, unknown> {
+  expect(result.isError).toBe(false)
+  const block = result.content[0]
+  if (block?.type !== 'text') throw new Error('expected text tool result')
+  return JSON.parse(block.text) as Record<string, unknown>
+}
+
+/** Read the returned goal sub-object. */
+function resultGoal(result: ToolExecutionResult): Record<string, unknown> {
+  const goal = resultJson(result)['goal']
+  if (typeof goal !== 'object' || goal === null) throw new Error('expected returned goal')
+  return goal as Record<string, unknown>
+}
+
+describe('goal tool registration and presentation', () => {
+  it('registers three exclusive tools plus configured guidance and disposes all contributions', async () => {
+    const { ctx, fiber } = await harness({ blockedAfterConsecutiveRounds: 5 })
+    expect(['create_goal', 'get_goal', 'update_goal'].map(name => ctx.tools.get(name)?.name))
+      .toEqual(['create_goal', 'get_goal', 'update_goal'])
+    for (const name of ['create_goal', 'get_goal', 'update_goal']) {
+      expect(ctx.tools.executionMode({ callId: CallId(name), name, arguments: {} }))
+        .toEqual({ kind: 'exclusive' })
+    }
+    const section = (await ctx.systemPrompt.assemble()).sections.find(item => item.name === 'tool:goal')
+    expect(section?.text).toContain('infer goal intent')
+    expect(section?.text).toContain('at least 5 consecutive goal rounds')
+
+    await fiber.dispose()
+    expect(ctx.tools.get('get_goal')).toBeUndefined()
+    expect((await ctx.systemPrompt.assemble()).sections.some(item => item.name === 'tool:goal')).toBe(false)
+  })
+
+  it('uses args-only generic render intent and soft-fails malformed replay args', async () => {
+    const { ctx } = await harness()
+    expect(ctx.tools.get('get_goal')?.presentCall?.({})).toEqual({
+      card: 'generic', title: 'Read current goal', kind: 'read',
+    })
+    expect(ctx.tools.get('create_goal')?.presentCall?.({ objective: 'ship' })).toEqual({
+      card: 'generic', title: 'Create goal', kind: 'other', rawInput: 'ship',
+    })
+    expect(ctx.tools.get('update_goal')?.presentCall?.({
+      goal_id: 'goal-1', revision: 2, action: 'blocked',
+    })).toEqual({ card: 'generic', title: 'Mark goal', kind: 'other', rawInput: 'goal-1' })
+    expect(ctx.tools.get('update_goal')?.presentCall?.({
+      goal_id: 'goal-1', revision: 2, action: 'resume',
+    })).toEqual({ card: 'generic', title: 'Resume goal', kind: 'other', rawInput: 'goal-1' })
+    expect(ctx.tools.get('update_goal')?.presentCall?.({ wrong: true })).toBeUndefined()
+  })
+
+  it('has the Loader-safe namespace export shape', () => {
+    expect('default' in toolGoal).toBe(false)
+    expect(toolGoal.name).toBe('tool-goal')
+    expect(toolGoal.inject).toEqual(['agents', 'goals', 'tools', 'systemPrompt'])
+    const loader = Object.create(Loader.prototype) as Loader
+    expect(loader.unwrapExports(toolGoal)).toBe(toolGoal)
+  })
+
+  it('fails invalid direct config before registering anything', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(GoalService)
+    expect(() => {
+      toolGoal.apply(ctx, { blockedAfterConsecutiveRounds: 1.5 })
+    }).toThrow(
+      'blockedAfterConsecutiveRounds must be a positive safe integer',
+    )
+    expect(ctx.tools.get('get_goal')).toBeUndefined()
+  })
+
+  it('resolves the direct-apply default before registration', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(GoalService)
+    toolGoal.apply(ctx, {})
+    const section = (await ctx.systemPrompt.assemble()).sections.find(item => item.name === 'tool:goal')
+    expect(section?.text).toContain('at least 3 consecutive goal rounds')
+  })
+})
+
+describe('goal tool execution authority', () => {
+  it('lets a root model infer create intent from its accepted human turn', async () => {
+    const { ctx, root } = await harness()
+    openTurn(root, { kind: 'user' }, '请持续工作直到这个功能完成')
+    const result = await execute(ctx, 'create_goal', {
+      objective: 'Finish the feature', max_goal_rounds: 9,
+    }, root.agent)
+    expect(resultGoal(result)).toMatchObject({
+      objective: 'Finish the feature', revision: 1, phase: 'active', maxGoalRounds: 9,
+    })
+    expect(resultJson(result)['activation']).toBe('armed')
+    expect(ctx.goals.get(root.agent)?.objective).toBe('Finish the feature')
+  })
+
+  it('rejects agentless, driverless, non-human, and live-child creation', async () => {
+    const { ctx, root } = await harness()
+    const agentless = await execute(ctx, 'get_goal', {})
+    expect(agentless.error?.code).toBe('GOAL_TOOL_AGENT_REQUIRED')
+
+    openTurn(root, { kind: 'user' })
+    const driverless = await ctx.tools.execute({
+      callId: CallId('call-driverless'),
+      name: 'get_goal',
+      arguments: {},
+      agent: root.agent,
+    })
+    expect(driverless.error?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED')
+    closeTurn(root, 1)
+
+    openTurn(root, { kind: 'plugin', plugin: 'test' })
+    const nonHuman = await execute(ctx, 'create_goal', { objective: 'forged' }, root.agent)
+    expect(nonHuman.error?.code).toBe('GOAL_TOOL_AUTHORITY_REQUIRED')
+    closeTurn(root, 2)
+
+    const child = stubAgent('goal-tool-child')
+    ctx.agents.enter(child.agent, root.agent)
+    ctx.agents.announce(child.agent)
+    openTurn(child, { kind: 'user' })
+    const childResult = await execute(ctx, 'create_goal', { objective: 'child goal' }, child.agent)
+    expect(childResult.error?.code).toBe('GOAL_TOOL_AUTHORITY_REQUIRED')
+  })
+
+  it('rejects calls before a turn and after its end boundary', async () => {
+    const { ctx, root } = await harness()
+    const before = await execute(ctx, 'get_goal', {}, root.agent)
+    expect(before.error?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED')
+
+    const turn = openTurn(root, { kind: 'user' })
+    closeTurn(root, turn)
+    const after = await execute(ctx, 'get_goal', {}, root.agent)
+    expect(after.error?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED')
+  })
+
+  it('rejects terminal reporting without human input or a current goal round', async () => {
+    const { ctx, root } = await harness()
+    openTurn(root, { kind: 'plugin', plugin: 'test' })
+    const result = await execute(ctx, 'update_goal', {
+      goal_id: 'goal-missing', revision: 1, action: 'complete',
+    }, root.agent)
+    expect(result.error?.code).toBe('GOAL_TOOL_AUTHORITY_REQUIRED')
+  })
+
+  it('accepts direct human steering in a goal-sourced root turn', async () => {
+    const { ctx, root } = await harness()
+    const humanTurn = openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'steer me' })
+    closeTurn(root, humanTurn)
+    const round = openTurn(root, {
+      kind: 'goal', goalId: created.id, revision: created.revision, round: 1,
+    })
+    root.session.append('steering/message', {
+      turn: round,
+      content: [{ type: 'text', text: 'pause now' }],
+      source: { kind: 'user' },
+    }, { surfaceOp: 'append' })
+    const paused = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'pause',
+    }, root.agent)
+    expect(resultGoal(paused)).toMatchObject({ phase: 'paused', revision: 2 })
+  })
+
+  it('rejects an initiator different from exec.agent', async () => {
+    const { ctx, root } = await harness()
+    const other = stubAgent('goal-tool-other')
+    ctx.agents.register(other.agent)
+    openTurn(other, { kind: 'user' })
+    const result = await execute(ctx, 'get_goal', {}, other.agent, root.agent)
+    expect(result.error?.code).toBe('GOAL_TOOL_DRIVER_REQUIRED')
+  })
+})
+
+describe('goal tool state transitions', () => {
+  it('reads null, then edits, pauses, and resumes by exact revision in one human turn', async () => {
+    const { ctx, root } = await harness()
+    openTurn(root, { kind: 'user' })
+    expect(resultJson(await execute(ctx, 'get_goal', {}, root.agent))).toEqual({ goal: null })
+    let goal = resultGoal(await execute(ctx, 'create_goal', { objective: 'old' }, root.agent))
+    goal = resultGoal(await execute(ctx, 'update_goal', {
+      goal_id: goal['id'], revision: goal['revision'], action: 'edit',
+      objective: 'new', max_goal_rounds: 8,
+    }, root.agent))
+    expect(goal).toMatchObject({ objective: 'new', revision: 2, maxGoalRounds: 8 })
+    goal = resultGoal(await execute(ctx, 'update_goal', {
+      goal_id: goal['id'], revision: goal['revision'], action: 'pause',
+    }, root.agent))
+    expect(goal).toMatchObject({ phase: 'paused', revision: 3 })
+    goal = resultGoal(await execute(ctx, 'update_goal', {
+      goal_id: goal['id'], revision: goal['revision'], action: 'resume',
+    }, root.agent))
+    expect(goal).toMatchObject({ phase: 'active', revision: 4 })
+  })
+
+  it('rearms a restored active goal only after a new direct human prompt', async () => {
+    const { ctx, root } = await harness()
+    let turn = openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'continue later' })
+    closeTurn(root, turn)
+    agentEvents(ctx, root.agent).emit('agent/session-start', 'resume')
+    expect(ctx.goals.get(root.agent)?.activation).toBe('disarmed')
+    turn = openTurn(root, { kind: 'user' }, '继续')
+    const resumed = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'resume',
+    }, root.agent)
+    expect(resultGoal(resumed)).toMatchObject({ phase: 'active', revision: 2 })
+    expect(resultJson(resumed)['activation']).toBe('armed')
+    closeTurn(root, turn)
+  })
+
+  it('returns structured domain and conditional-argument failures', async () => {
+    const { ctx, root } = await harness()
+    openTurn(root, { kind: 'user' })
+    const invalidCreate = await execute(ctx, 'create_goal', { objective: ' ' }, root.agent)
+    expect(invalidCreate.error?.code).toBe('GOAL_INVALID_OBJECTIVE')
+    const created = ctx.goals.create(root.agent, { objective: 'valid' })
+    const replacement = await execute(ctx, 'update_goal', {
+      goal_id: created.id,
+      revision: created.revision,
+      action: 'pause',
+      objective: 'not valid for pause',
+    }, root.agent)
+    expect(replacement.error?.code).toBe('GOAL_TOOL_INVALID_UPDATE')
+    const malformedRef = await execute(ctx, 'update_goal', {
+      goal_id: '', revision: 0, action: 'edit', objective: 'x',
+    }, root.agent)
+    expect(malformedRef.error?.code).toBe('GOAL_TOOL_INVALID_UPDATE')
+  })
+
+  it('allows exact goal rounds to complete but not edit or pause', async () => {
+    const { ctx, root } = await harness()
+    const humanTurn = openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'round-owned' })
+    closeTurn(root, humanTurn)
+    openTurn(root, { kind: 'goal', goalId: created.id, revision: created.revision, round: 1 })
+    const edit = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'edit', objective: 'forbidden',
+    }, root.agent)
+    expect(edit.error?.code).toBe('GOAL_TOOL_AUTHORITY_REQUIRED')
+    const complete = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'complete',
+    }, root.agent)
+    expect(resultGoal(complete)).toMatchObject({ phase: 'complete', revision: 2, roundsStarted: 1 })
+  })
+
+  it('enforces the configured model self-block lower bound across admitted rounds', async () => {
+    const { ctx, root } = await harness({ blockedAfterConsecutiveRounds: 3 })
+    let turn = openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'blocked eventually' })
+    closeTurn(root, turn)
+    const ref: GoalRef = { id: GoalId(created.id), revision: created.revision }
+
+    for (let round = 1; round <= 2; round += 1) {
+      turn = openTurn(root, { kind: 'goal', goalId: ref.id, revision: ref.revision, round })
+      const result = await execute(ctx, 'update_goal', {
+        goal_id: ref.id, revision: ref.revision, action: 'blocked',
+      }, root.agent)
+      expect(result.error?.code).toBe('GOAL_TOOL_BLOCK_THRESHOLD')
+      closeTurn(root, turn)
+    }
+    openTurn(root, { kind: 'goal', goalId: ref.id, revision: ref.revision, round: 3 })
+    const blocked = await execute(ctx, 'update_goal', {
+      goal_id: ref.id, revision: ref.revision, action: 'blocked',
+    }, root.agent)
+    expect(resultGoal(blocked)).toMatchObject({ phase: 'blocked', roundsStarted: 3 })
+  })
+
+  it('lets direct human authority block before the model threshold', async () => {
+    const { ctx, root } = await harness({ blockedAfterConsecutiveRounds: 9 })
+    openTurn(root, { kind: 'user' })
+    const created = ctx.goals.create(root.agent, { objective: 'human stop' })
+    const blocked = await execute(ctx, 'update_goal', {
+      goal_id: created.id, revision: created.revision, action: 'blocked',
+    }, root.agent)
+    expect(resultGoal(blocked)).toMatchObject({ phase: 'blocked', roundsStarted: 0 })
+  })
+})