Merge refreshed schema DSL into canonical tool output
# Conflicts: # docs/config-catalog.md # examples/headless-agent/tests/snapshots/advanced-toolchain/session.1.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.2.jsonl # examples/headless-agent/tests/snapshots/advanced-toolchain/session.jsonl # packages/context/workspace-context/tests/workspace-context.spec.ts # packages/core/tools/tests/tools.spec.ts # packages/ui/tui/src/index.ts # packages/ui/tui/tests/tui.snapshot.ts
This commit is contained in:
Tianyi Cui
170
packages/plan/plan-mode/tests/integration.spec.ts
Normal file
170
packages/plan/plan-mode/tests/integration.spec.ts
Normal file
@@ -0,0 +1,170 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import LlmService, { type StreamChunk } from '@deepseek-ai/dsh-llm'
|
||||
import SessionStore, { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, { defineContentToolFixture } from '@deepseek-ai/dsh-tools'
|
||||
import AgentRegistry, { type Agent } from '@deepseek-ai/dsh-agent'
|
||||
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
|
||||
import PlanModeService, { foldPlanMode } from '@deepseek-ai/dsh-plan-mode'
|
||||
import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
|
||||
|
||||
const PLAN_CONFIG = { section: 'Test plan mode instructions.' }
|
||||
|
||||
/**
|
||||
* Full-loop integration: a scripted mock model drives the REAL plan-mode plugin
|
||||
* through the agent loop — the pending-intent flush at the turn boundary, the
|
||||
* assembly the soft layer shapes (the exit tool + mode section), and the
|
||||
* `request/header` snapshots every transition leaves.
|
||||
* Only the model is mocked; the loop, the session log, and the plugin are
|
||||
* real.
|
||||
*/
|
||||
async function harness(adapter: MockAdapter): Promise<Context> {
|
||||
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(AgentLoop, { agents: [] })
|
||||
await ctx.plugin(PlanModeService, PLAN_CONFIG)
|
||||
ctx.llm.registerAdapter(['mock'], adapter)
|
||||
for (const name of ['read', 'write']) {
|
||||
ctx.tools.register(defineContentToolFixture({
|
||||
name,
|
||||
description: `test tool ${name}`,
|
||||
parameters: {},
|
||||
execute: () => Promise.resolve([{ type: 'text', text: `ran ${name}` }]),
|
||||
}))
|
||||
}
|
||||
return ctx
|
||||
}
|
||||
|
||||
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
const dispose = ctx.on('agent/status', (subject, status) => {
|
||||
if (subject === agent && status === 'idle') {
|
||||
dispose()
|
||||
resolve()
|
||||
}
|
||||
})
|
||||
})
|
||||
}
|
||||
|
||||
function findEvent<T extends SessionEvent['type']>(
|
||||
log: readonly SessionEvent[],
|
||||
type: T,
|
||||
position: 'first' | 'last' = 'first',
|
||||
): Extract<SessionEvent, { type: T }> {
|
||||
const found = position === 'first'
|
||||
? log.find(event => event.type === type)
|
||||
: log.findLast(event => event.type === type)
|
||||
if (!found) throw new Error(`no ${type} event in the session log`)
|
||||
return found as Extract<SessionEvent, { type: T }>
|
||||
}
|
||||
|
||||
describe('plan mode through the agent loop', () => {
|
||||
it('a pre-turn set() makes the FIRST header plan-shaped, and a non-shell call is guidance-constrained only', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
toolCallResponse('call-1', 'write', {}, 'Writing during plan.'),
|
||||
textResponse('Noted in the plan.'),
|
||||
])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(SessionId('it-plan-seed'), { provider: 'mock', model: 'mock' })
|
||||
// Selected while idle (the ACP picker shape): the pending intent flushes at
|
||||
// the first prompt-submit, BEFORE the first assembly.
|
||||
ctx.planMode.set(agent, true)
|
||||
|
||||
agent.send([{ type: 'text', text: 'explore the repo' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const log = agent.session.events
|
||||
const planMode = findEvent(log, 'plan/mode')
|
||||
const header = findEvent(log, 'request/header')
|
||||
expect(planMode.seq).toBeLessThan(header.seq)
|
||||
expect(header.data.reason).toBe('initial')
|
||||
expect(header.data.header.tools?.map(tool => tool.name)).toEqual(['exit_plan_mode', 'read', 'write'])
|
||||
expect(header.data.header.system).toContain('plan mode')
|
||||
|
||||
// No tool gate: the write RUNS — plan restrains by the section's
|
||||
// guidance alone (enforcement lives on the independent sandbox/approval
|
||||
// axes). The mode itself stays plan throughout.
|
||||
const result = findEvent(log, 'tool/result')
|
||||
expect(result.data.isError).toBe(false)
|
||||
expect(foldPlanMode(log)).toBe(true)
|
||||
expect(log.some(event => event.type === 'context/message')).toBe(false)
|
||||
})
|
||||
|
||||
it('a user flip between turns lands at the boundary: one notice and a changed header with stable tool schemas', async () => {
|
||||
const adapter = new MockAdapter([
|
||||
textResponse('First turn, default mode.'),
|
||||
textResponse('Second turn, plan mode.'),
|
||||
])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(SessionId('it-plan-flip'), { provider: 'mock', model: 'mock' })
|
||||
|
||||
agent.send([{ type: 'text', text: 'hello' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
expect(foldPlanMode(agent.session.events)).toBe(false)
|
||||
const first = findEvent(agent.session.events, 'request/header')
|
||||
expect(first.data.header.tools?.map(tool => tool.name)).toEqual(['exit_plan_mode', 'read', 'write'])
|
||||
|
||||
ctx.planMode.set(agent, true)
|
||||
agent.send([{ type: 'text', text: 'now plan' }])
|
||||
await waitForIdle(ctx, agent)
|
||||
|
||||
const log = agent.session.events
|
||||
expect(foldPlanMode(log)).toBe(true)
|
||||
const notices = log.filter(event => event.type === 'context/message')
|
||||
expect(notices).toHaveLength(1)
|
||||
expect(findEvent(log, 'context/message').data.content).toEqual([
|
||||
{ type: 'text', text: 'The user switched this session to plan mode.' },
|
||||
])
|
||||
// The changed request is logged as a complete snapshot.
|
||||
const second = findEvent(log, 'request/header', 'last')
|
||||
expect(second.data.reason).toBe('change')
|
||||
expect(second.data.header.tools?.map(tool => tool.name)).toEqual(['exit_plan_mode', 'read', 'write'])
|
||||
expect(second.data.header.tools).toEqual(first.data.header.tools)
|
||||
expect(second.data.header.system).toContain('plan mode')
|
||||
})
|
||||
|
||||
it('a mode flip during request recovery shapes the retry before its assembly', async () => {
|
||||
const failedRequest = [{
|
||||
type: 'finish',
|
||||
reason: { kind: 'error', failure: { message: 'temporarily unavailable', code: 'SERVER', status: 503 } },
|
||||
}] satisfies StreamChunk[]
|
||||
const adapter = new MockAdapter([failedRequest, textResponse('Recovered in plan mode.')])
|
||||
const ctx = await harness(adapter)
|
||||
const agent = ctx.agentLoop.create(SessionId('it-plan-retry-flip'), { provider: 'mock', model: 'mock' })
|
||||
const recoveryEntered = Promise.withResolvers<true>()
|
||||
const releaseRecovery = Promise.withResolvers<true>()
|
||||
ctx.on('agent/request-error', async (subject, _turn, _step, _error, _failure, _history, _signal, next) => {
|
||||
if (subject !== agent) return next()
|
||||
recoveryEntered.resolve(true)
|
||||
await releaseRecovery.promise
|
||||
return { action: 'retry' }
|
||||
})
|
||||
|
||||
const idle = waitForIdle(ctx, agent)
|
||||
agent.send([{ type: 'text', text: 'plan after the transient failure' }])
|
||||
await recoveryEntered.promise
|
||||
ctx.planMode.set(agent, true)
|
||||
releaseRecovery.resolve(true)
|
||||
await idle
|
||||
|
||||
expect(adapter.requests).toHaveLength(2)
|
||||
expect(adapter.requests[0]?.system).not.toContain(PLAN_CONFIG.section)
|
||||
expect(adapter.requests[1]?.system).toContain(PLAN_CONFIG.section)
|
||||
expect(adapter.requests[1]?.tools).toEqual(adapter.requests[0]?.tools)
|
||||
const log = agent.session.events
|
||||
const planMode = findEvent(log, 'plan/mode')
|
||||
const firstEnd = log.find(event => event.type === 'step/end' && event.data.step === 1)
|
||||
const retryStart = log.find(event => event.type === 'step/start' && event.data.step === 2)
|
||||
expect(firstEnd?.seq).toBeLessThan(planMode.seq)
|
||||
expect(planMode.seq).toBeLessThan(retryStart?.seq ?? 0)
|
||||
expect(findEvent(log, 'request/header', 'last').data.header.system).toContain(PLAN_CONFIG.section)
|
||||
expect(findEvent(log, 'context/message').data.content).toEqual([
|
||||
{ type: 'text', text: 'The user switched this session to plan mode.' },
|
||||
])
|
||||
})
|
||||
})
|
||||
50
packages/plan/plan-mode/tests/invariant.spec.ts
Normal file
50
packages/plan/plan-mode/tests/invariant.spec.ts
Normal file
@@ -0,0 +1,50 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import SessionStore, { type Session, type SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import * as PlanModeInvariant from '@deepseek-ai/dsh-plan-mode/invariant'
|
||||
import InvariantService from '@deepseek-ai/dsh-invariants'
|
||||
|
||||
async function setup(): Promise<Context> {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
await ctx.plugin(InvariantService, { enabled: true })
|
||||
await ctx.plugin(PlanModeInvariant)
|
||||
return ctx
|
||||
}
|
||||
|
||||
function event(active: unknown): SessionEvent {
|
||||
return { type: 'plan/mode', seq: 0, time: 0, data: { active } } as SessionEvent
|
||||
}
|
||||
|
||||
describe('plan-mode stream invariants', () => {
|
||||
it('accepts either boolean state', async () => {
|
||||
const ctx = await setup()
|
||||
expect(() => { ctx.emit('session/event', {} as Session, event(true)) }).not.toThrow()
|
||||
expect(() => { ctx.emit('session/event', {} as Session, event(false)) }).not.toThrow()
|
||||
})
|
||||
|
||||
it.each([42, 'plan', undefined])('rejects invalid durable plan state %j', async (active) => {
|
||||
const ctx = await setup()
|
||||
expect(() => { ctx.emit('session/event', {} as Session, event(active)) })
|
||||
.toThrow(/expected a boolean/)
|
||||
})
|
||||
|
||||
it('ignores unrelated dispatches and session events', async () => {
|
||||
const ctx = await setup()
|
||||
expect(() => {
|
||||
ctx.emit('tools/change')
|
||||
ctx.emit('session/event', {} as Session, {
|
||||
type: 'turn/start', seq: 0, time: 0, data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } },
|
||||
})
|
||||
}).not.toThrow()
|
||||
})
|
||||
|
||||
it('rejects invalid existing state on late registration', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SessionStore)
|
||||
ctx.sessions.create().append('plan/mode', { active: 'plan' as unknown as boolean })
|
||||
await ctx.plugin(InvariantService, { enabled: true })
|
||||
|
||||
await expect(ctx.plugin(PlanModeInvariant).then(() => undefined)).rejects.toThrow(/expected a boolean/)
|
||||
})
|
||||
})
|
||||
936
packages/plan/plan-mode/tests/plan-mode.spec.ts
Normal file
936
packages/plan/plan-mode/tests/plan-mode.spec.ts
Normal file
@@ -0,0 +1,936 @@
|
||||
import { describe, expect, it, vi } from 'vitest'
|
||||
import { Context } from 'cordis'
|
||||
import { CallId } from '@deepseek-ai/dsh-llm'
|
||||
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
|
||||
import ToolRegistry, { RUN_CODE_NAME, defineContentToolFixture } from '@deepseek-ai/dsh-tools'
|
||||
import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import { agentEvents, type Agent, type RequestErrorDecision } from '@deepseek-ai/dsh-agent'
|
||||
import { createScope } from '@deepseek-ai/dsh-scope'
|
||||
import UserInteractionService, { type AskUserQuestionRequest } from '@deepseek-ai/dsh-user-interaction'
|
||||
import CommandService from '@deepseek-ai/dsh-commands'
|
||||
import { CodeRuntime, type CodeRunRequest, type CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
|
||||
import PlanModeService, { EXIT_PLAN_MODE, foldPlanMode, resolveConfig } from '../src/index.ts'
|
||||
import type { PlanModeConfig } from '../src/index.ts'
|
||||
|
||||
const TEST_PLAN_SECTION = 'Test plan mode instructions.'
|
||||
const PLAN_CONFIG = { section: TEST_PLAN_SECTION } satisfies PlanModeConfig
|
||||
|
||||
/**
|
||||
* Drives the REAL plugin: mounts `dsh-plan-mode` beside real `SystemPrompt` and
|
||||
* `ToolRegistry` services, with fake Agents carrying real `Session`s and a
|
||||
* real scoped `agent.ctx` minted through `createScope`.
|
||||
* Turn boundaries are simulated by appending the real boundary events and
|
||||
* dispatching the interception seams the loop fires there. Recovery retries
|
||||
* exercise the separate `agent/request-error` wrapper.
|
||||
*/
|
||||
|
||||
async function agentWithSession(ctx: Context, id = 'agent-1', { active }: { active?: boolean } = {}): Promise<Agent & { session: Session }> {
|
||||
const session = new Session(SessionId(id))
|
||||
const agent = { id: SessionId(id), session, options: {} } as unknown as Agent & { session: Session }
|
||||
let scoped!: Context
|
||||
await ctx.plugin(Object.assign((inner: Context) => { scoped = createScope(inner, agent).ctx }, {
|
||||
inject: ['tools'],
|
||||
}))
|
||||
;(agent as { ctx?: Context }).ctx = scoped
|
||||
// Seeded plan state lands before the creation announcement, matching resume.
|
||||
if (active !== undefined) session.append('plan/mode', { active })
|
||||
// The loop announces creation after publication.
|
||||
ctx.emit('agent/created', agent)
|
||||
return agent
|
||||
}
|
||||
|
||||
/** Assemble exactly as the loop does: the agent is both subject and scope. */
|
||||
function assembleFor(ctx: Context, agent: Agent) {
|
||||
return ctx.systemPrompt.assemble({ agent, scope: agent })
|
||||
}
|
||||
|
||||
async function setup(config: PlanModeConfig = PLAN_CONFIG): Promise<Context> {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(PlanModeService, config)
|
||||
return ctx
|
||||
}
|
||||
|
||||
/**
|
||||
* Append a boundary event and dispatch the interception seam the loop fires
|
||||
* there — `agent/prompt-submit` inside the just-opened turn,
|
||||
* `agent/turn-continuation` after the step closed. Recovery retries use the
|
||||
* separately covered `agent/request-error` wrapper; post-commit
|
||||
* `session/event` observers remain observe-only.
|
||||
*/
|
||||
async function boundary(ctx: Context, agent: Agent & { session: Session }, type: 'turn/start' | 'step/end'): Promise<void> {
|
||||
const events = agentEvents(ctx, agent)
|
||||
if (type === 'turn/start') {
|
||||
agent.session.append('turn/start', { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } })
|
||||
await events.waterfall('agent/prompt-submit', [{ type: 'text', text: 'boundary probe' }], { kind: 'user' }, new AbortController().signal, () => Promise.resolve({ kind: 'allow' }))
|
||||
return
|
||||
}
|
||||
agent.session.append('step/end', { turn: 1, step: 1 })
|
||||
await events.waterfall('agent/turn-continuation', 1, { action: 'stop' }, new AbortController().signal, () => Promise.resolve({ action: 'stop' }))
|
||||
}
|
||||
|
||||
/** Dispatch the closed-step recovery seam with one terminal decision. */
|
||||
function recoveryBoundary(
|
||||
ctx: Context,
|
||||
agent: Agent & { session: Session },
|
||||
decision: RequestErrorDecision,
|
||||
): Promise<RequestErrorDecision> {
|
||||
return agentEvents(ctx, agent).waterfall(
|
||||
'agent/request-error',
|
||||
1,
|
||||
1,
|
||||
new Error('request failed'),
|
||||
{ message: 'request failed', code: 'SERVER' },
|
||||
[],
|
||||
new AbortController().signal,
|
||||
() => Promise.resolve(decision),
|
||||
)
|
||||
}
|
||||
|
||||
/** Append a minimal `request/header` snapshot so the log has a "what the model was told" anchor. */
|
||||
function header(session: Session): void {
|
||||
session.append('request/header', { header: { config: { provider: 'test', model: 'test-model' } }, reason: 'initial' })
|
||||
}
|
||||
|
||||
function noticeTexts(session: Session): string[] {
|
||||
return session.events
|
||||
.filter(event => event.type === 'context/message')
|
||||
.map(event => (event.data as { content: { type: string; text?: string }[] }).content.map(block => block.text ?? '').join(''))
|
||||
}
|
||||
|
||||
function registerNamedTools(ctx: Context, names: string[]): void {
|
||||
for (const name of names) {
|
||||
ctx.tools.register(defineContentToolFixture({
|
||||
name,
|
||||
description: `test tool ${name}`,
|
||||
parameters: {},
|
||||
execute: () => Promise.resolve([{ type: 'text', text: `ran ${name}` }]),
|
||||
}))
|
||||
}
|
||||
}
|
||||
|
||||
let callCounter = 0
|
||||
function execute(ctx: Context, name: string, agent?: Agent) {
|
||||
return ctx.tools.execute({
|
||||
callId: CallId(`call-${++callCounter}`),
|
||||
name,
|
||||
arguments: {},
|
||||
signal: new AbortController().signal,
|
||||
...agent ? { agent } : {},
|
||||
})
|
||||
}
|
||||
|
||||
describe('resolveConfig', () => {
|
||||
it('requires string, non-empty plan instructions', () => {
|
||||
expect(() => resolveConfig({} as PlanModeConfig))
|
||||
.toThrow('needs a string `section`')
|
||||
expect(() => resolveConfig({ section: 5 } as unknown as PlanModeConfig))
|
||||
.toThrow('needs a string `section`')
|
||||
expect(() => resolveConfig({ section: ' ' }))
|
||||
.toThrow('needs a non-empty `section`')
|
||||
})
|
||||
|
||||
it('returns a detached plan config', () => {
|
||||
const config = { section: TEST_PLAN_SECTION }
|
||||
const resolved = resolveConfig(config)
|
||||
expect(resolved).toEqual(config)
|
||||
expect(resolved).not.toBe(config)
|
||||
})
|
||||
|
||||
it('rejects fields outside the plan policy config', () => {
|
||||
expect(() => resolveConfig({ section: TEST_PLAN_SECTION, tools: ['read'] } as unknown as PlanModeConfig))
|
||||
.toThrow('unknown key(s) tools — config is { section }')
|
||||
})
|
||||
})
|
||||
|
||||
describe('foldPlanMode', () => {
|
||||
it('folds an empty log to inactive and takes the last plan/mode otherwise', () => {
|
||||
const session = new Session(SessionId('fold'))
|
||||
expect(foldPlanMode(session.events)).toBe(false)
|
||||
session.append('plan/mode', { active: true })
|
||||
session.append('plan/mode', { active: false })
|
||||
session.append('plan/mode', { active: true })
|
||||
expect(foldPlanMode(session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('folds a prefix when `end` is given', () => {
|
||||
const session = new Session(SessionId('fold-prefix'))
|
||||
session.append('plan/mode', { active: true })
|
||||
session.append('plan/mode', { active: false })
|
||||
expect(foldPlanMode(session.events, 1)).toBe(true)
|
||||
expect(foldPlanMode(session.events, 0)).toBe(false)
|
||||
})
|
||||
})
|
||||
|
||||
describe('ctx.planMode: get/set', () => {
|
||||
it('reads the folded state', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: false })
|
||||
agent.session.append('plan/mode', { active: true })
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: true })
|
||||
})
|
||||
|
||||
it('selects inactive as the plan exit target', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
agent.session.append('plan/mode', { active: true })
|
||||
ctx.planMode.set(agent, false)
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: true, pending: false })
|
||||
})
|
||||
|
||||
it('drops a no-op set (target equals pending, else the current fold)', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
ctx.planMode.set(agent, false)
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: false })
|
||||
ctx.planMode.set(agent, true)
|
||||
ctx.planMode.set(agent, true)
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: false, pending: true })
|
||||
})
|
||||
})
|
||||
|
||||
describe('the boundary flush', () => {
|
||||
it('flushes the pending intent as a plan/mode at turn/start', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
ctx.planMode.set(agent, true)
|
||||
await boundary(ctx, agent, 'turn/start')
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: true })
|
||||
})
|
||||
|
||||
it('flushes a set() that arrives while a downstream listener is still awaiting (post-next ordering)', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
// A downstream async listener (the shipped hooks listeners' shape): the
|
||||
// selection lands DURING its await — after this boundary began, before it
|
||||
// returns. The prepended flush runs after next(), so the plan/mode still
|
||||
// precedes the request this boundary gates.
|
||||
ctx.on('agent/turn-continuation', async (_agent, _turn, decision, _signal, next) => {
|
||||
await new Promise(resolve => setTimeout(resolve, 5))
|
||||
ctx.planMode.set(agent, true)
|
||||
await next()
|
||||
return decision
|
||||
})
|
||||
agent.session.append('step/end', { turn: 1, step: 1 })
|
||||
await agentEvents(ctx, agent).waterfall(
|
||||
'agent/turn-continuation', 1, { action: 'stop' }, new AbortController().signal,
|
||||
() => Promise.resolve({ action: 'stop' }),
|
||||
)
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: true })
|
||||
})
|
||||
|
||||
it('skips the flush after the plugin fiber is disposed (a captured wrapper must not write into a dead service)', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
const fiber = await ctx.plugin(PlanModeService, PLAN_CONFIG)
|
||||
const agent = await agentWithSession(ctx)
|
||||
ctx.planMode.set(agent, true)
|
||||
// A downstream listener captured before disposal keeps the waterfall
|
||||
// continuation alive across the unload; the resumed wrapper must not
|
||||
// append through the disposed service.
|
||||
ctx.on('agent/turn-continuation', async (_agent, _turn, decision, _signal, next) => {
|
||||
await fiber.dispose()
|
||||
await next()
|
||||
return decision
|
||||
})
|
||||
agent.session.append('step/end', { turn: 1, step: 1 })
|
||||
await agentEvents(ctx, agent).waterfall(
|
||||
'agent/turn-continuation', 1, { action: 'stop' }, new AbortController().signal,
|
||||
() => Promise.resolve({ action: 'stop' }),
|
||||
)
|
||||
expect(agent.session.events.some(event => event.type === 'plan/mode')).toBe(false)
|
||||
})
|
||||
|
||||
it('flushes at step/end too (a mid-turn flip lands on the following step)', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
ctx.planMode.set(agent, true)
|
||||
await boundary(ctx, agent, 'step/end')
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('keeps the pending intent parked when recovery does not retry', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
ctx.planMode.set(agent, true)
|
||||
expect(await recoveryBoundary(ctx, agent, { action: 'fail' })).toEqual({ action: 'fail' })
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: false, pending: true })
|
||||
})
|
||||
|
||||
it('contains an append failure at the retry boundary without changing its decision', async () => {
|
||||
const ctx = await setup()
|
||||
const warn = vi.fn()
|
||||
ctx.logger.warn = warn as never
|
||||
const agent = await agentWithSession(ctx)
|
||||
ctx.planMode.set(agent, true)
|
||||
const original = agent.session.append.bind(agent.session)
|
||||
agent.session.append = (((type: string, ...rest: unknown[]) => {
|
||||
if (type === 'plan/mode') throw new Error('backend gone')
|
||||
return (original as (...args: unknown[]) => unknown)(type, ...rest)
|
||||
}) as unknown) as typeof agent.session.append
|
||||
|
||||
expect(await recoveryBoundary(ctx, agent, { action: 'retry' })).toEqual({ action: 'retry' })
|
||||
expect(warn).toHaveBeenCalledOnce()
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: false, pending: true })
|
||||
})
|
||||
|
||||
it('nets out a flip sequence that returns to the folded mode (no append, no notice)', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
ctx.planMode.set(agent, true)
|
||||
ctx.planMode.set(agent, false)
|
||||
await boundary(ctx, agent, 'turn/start')
|
||||
expect(agent.session.events.some(event => event.type === 'plan/mode')).toBe(false)
|
||||
expect(noticeTexts(agent.session)).toEqual([])
|
||||
})
|
||||
|
||||
it('narrates nothing before the first request header (the section is the state statement)', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
ctx.planMode.set(agent, true)
|
||||
await boundary(ctx, agent, 'turn/start')
|
||||
expect(noticeTexts(agent.session)).toEqual([])
|
||||
})
|
||||
|
||||
it('narrates once when the flushed mode differs from what the last header told the model', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
header(agent.session)
|
||||
ctx.planMode.set(agent, true)
|
||||
await boundary(ctx, agent, 'turn/start')
|
||||
expect(noticeTexts(agent.session)).toEqual(['The user switched this session to plan mode.'])
|
||||
await boundary(ctx, agent, 'step/end')
|
||||
expect(noticeTexts(agent.session)).toEqual(['The user switched this session to plan mode.'])
|
||||
})
|
||||
|
||||
it('narrates a switch back to the default mode with the default wording', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
agent.session.append('plan/mode', { active: true })
|
||||
header(agent.session)
|
||||
ctx.planMode.set(agent, false)
|
||||
await boundary(ctx, agent, 'step/end')
|
||||
expect(noticeTexts(agent.session)).toEqual(['The user switched this session back to the default mode.'])
|
||||
})
|
||||
|
||||
it('stays silent when the header already reflects the flushed mode', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
agent.session.append('plan/mode', { active: true })
|
||||
header(agent.session)
|
||||
agent.session.append('plan/mode', { active: false })
|
||||
ctx.planMode.set(agent, true)
|
||||
await boundary(ctx, agent, 'step/end')
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
expect(noticeTexts(agent.session)).toEqual([])
|
||||
})
|
||||
|
||||
|
||||
it('contains an append failure instead of blocking the prompt or the turn', async () => {
|
||||
const ctx = await setup()
|
||||
const warn = vi.fn()
|
||||
ctx.logger.warn = warn as never
|
||||
const agent = await agentWithSession(ctx)
|
||||
ctx.planMode.set(agent, true)
|
||||
const original = agent.session.append.bind(agent.session)
|
||||
// Only the flush's own plan/mode append fails; the boundary event itself
|
||||
// lands (the loop appended it before the seam fires).
|
||||
agent.session.append = (((type: string, ...rest: unknown[]) => {
|
||||
if (type === 'plan/mode') throw new Error('backend gone')
|
||||
return (original as (...args: unknown[]) => unknown)(type, ...rest)
|
||||
}) as unknown) as typeof agent.session.append
|
||||
await boundary(ctx, agent, 'step/end')
|
||||
expect(warn).toHaveBeenCalledOnce()
|
||||
// The failed flush re-parks the intent (cleared only after a landed
|
||||
// append), so the next healthy boundary converges the log with the
|
||||
// picker's optimistic state instead of dropping the switch forever.
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: false, pending: true })
|
||||
agent.session.append = original
|
||||
await boundary(ctx, agent, 'step/end')
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
expect(ctx.planMode.get(agent).pending).toBeUndefined()
|
||||
})
|
||||
|
||||
it('contains an append failure on the prompt-submit seam the same way', async () => {
|
||||
const ctx = await setup()
|
||||
const warn = vi.fn()
|
||||
ctx.logger.warn = warn as never
|
||||
const agent = await agentWithSession(ctx)
|
||||
ctx.planMode.set(agent, true)
|
||||
const original = agent.session.append.bind(agent.session)
|
||||
agent.session.append = (((type: string, ...rest: unknown[]) => {
|
||||
if (type === 'plan/mode') throw new Error('backend gone')
|
||||
return (original as (...args: unknown[]) => unknown)(type, ...rest)
|
||||
}) as unknown) as typeof agent.session.append
|
||||
await boundary(ctx, agent, 'turn/start')
|
||||
expect(warn).toHaveBeenCalledOnce()
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: false, pending: true })
|
||||
})
|
||||
})
|
||||
|
||||
describe('the soft layer', () => {
|
||||
it('keeps the tool schemas identical across default and plan mode', async () => {
|
||||
const ctx = await setup()
|
||||
registerNamedTools(ctx, ['read', 'write'])
|
||||
const agent = await agentWithSession(ctx)
|
||||
const defaultAssembly = await assembleFor(ctx, agent)
|
||||
expect(defaultAssembly.tools.map(tool => tool.name)).toEqual([EXIT_PLAN_MODE, 'read', 'write'])
|
||||
expect(defaultAssembly.sections.find(section => section.name === 'plan:policy')?.text).toBe('')
|
||||
|
||||
agent.session.append('plan/mode', { active: true })
|
||||
const planAssembly = await assembleFor(ctx, agent)
|
||||
expect(planAssembly.tools).toEqual(defaultAssembly.tools)
|
||||
expect(planAssembly.sections.find(section => section.name === 'plan:policy')?.text).toBe(TEST_PLAN_SECTION)
|
||||
})
|
||||
|
||||
it('leaves an agent-less assembly untouched', async () => {
|
||||
const ctx = await setup()
|
||||
registerNamedTools(ctx, ['read'])
|
||||
const assembly = await ctx.systemPrompt.assemble()
|
||||
expect(assembly.tools.map(tool => tool.name)).toEqual([EXIT_PLAN_MODE, 'read'])
|
||||
expect(assembly.sections.find(section => section.name === 'plan:policy')?.text).toBe('')
|
||||
})
|
||||
|
||||
it('keeps the full toolset in plan mode and renders the configured mode section', async () => {
|
||||
const ctx = await setup()
|
||||
registerNamedTools(ctx, ['read', 'write', 'todo_write'])
|
||||
const agent = await agentWithSession(ctx, 'agent-1', { active: true })
|
||||
const assembly = await assembleFor(ctx, agent)
|
||||
expect(assembly.tools.map(tool => tool.name).sort()).toEqual([EXIT_PLAN_MODE, 'read', 'todo_write', 'write'])
|
||||
expect(assembly.sections.find(section => section.name === 'plan:policy')?.text).toBe(TEST_PLAN_SECTION)
|
||||
})
|
||||
|
||||
it('leaves foreign assemble additions alone (no assemble-layer filtering)', async () => {
|
||||
// Plan guidance does not filter the registry or later assembly additions.
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
ctx.on('system-prompt/assemble', async (_assembly, _context, next) => {
|
||||
const final = await next()
|
||||
final.tools = [...final.tools, { name: 'added-later', description: 'added after next()', parameters: {} }]
|
||||
return final
|
||||
})
|
||||
await ctx.plugin(PlanModeService, PLAN_CONFIG)
|
||||
registerNamedTools(ctx, ['read'])
|
||||
const planning = await agentWithSession(ctx, 'planning', { active: true })
|
||||
expect((await assembleFor(ctx, planning)).tools.map(tool => tool.name))
|
||||
.toEqual(['exit_plan_mode', 'read', 'added-later'])
|
||||
const defaulted = await agentWithSession(ctx, 'defaulted')
|
||||
expect((await assembleFor(ctx, defaulted)).tools.map(tool => tool.name))
|
||||
.toEqual(['exit_plan_mode', 'read', 'added-later'])
|
||||
})
|
||||
|
||||
it('keeps run_code the only wire tool in plan mode under the registry Code Mode; the SDK gains the exit binding', async () => {
|
||||
// Minimal scriptable runtime: the SDK section resolves ctx.codeRuntime at
|
||||
// assembly time (the code-mode.spec fake's shape).
|
||||
class FakeRuntime extends CodeRuntime {
|
||||
readonly language = 'typescript'
|
||||
readonly isolation = 'fake'
|
||||
run(_request: CodeRunRequest): Promise<CodeRunResult> { return Promise.resolve({ logs: [] }) }
|
||||
}
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry, { mode: 'code' })
|
||||
await ctx.plugin(FakeRuntime)
|
||||
await ctx.plugin(PlanModeService, PLAN_CONFIG)
|
||||
registerNamedTools(ctx, ['read', 'write'])
|
||||
const agent = await agentWithSession(ctx, 'agent-1', { active: true })
|
||||
const assembly = await assembleFor(ctx, agent)
|
||||
expect(assembly.tools.map(tool => tool.name)).toEqual(['run_code'])
|
||||
// The SDK documents the full binding set plus the exit; plan mode never
|
||||
// prunes capabilities and restrains through guidance alone.
|
||||
const sdk = assembly.sections.find(section => section.name === 'tools:sdk')?.text ?? ''
|
||||
expect(sdk).toContain('read(args:')
|
||||
expect(sdk).toContain('write(args:')
|
||||
expect(sdk).toContain('exit_plan_mode(args:')
|
||||
})
|
||||
|
||||
it('keeps native wire schemas and the SDK in step under mode both', async () => {
|
||||
class FakeRuntime extends CodeRuntime {
|
||||
readonly language = 'typescript'
|
||||
readonly isolation = 'fake'
|
||||
run(_request: CodeRunRequest): Promise<CodeRunResult> { return Promise.resolve({ logs: [] }) }
|
||||
}
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry, { mode: 'both' })
|
||||
await ctx.plugin(FakeRuntime)
|
||||
await ctx.plugin(PlanModeService, PLAN_CONFIG)
|
||||
registerNamedTools(ctx, ['read', 'write'])
|
||||
const agent = await agentWithSession(ctx, 'agent-1', { active: true })
|
||||
const assembly = await assembleFor(ctx, agent)
|
||||
// The stable registry contribution reaches both surfaces: the exit tool
|
||||
// is present on the wire AND in the SDK alongside the untouched toolset.
|
||||
expect(assembly.tools.map(tool => tool.name).sort()).toEqual(['exit_plan_mode', 'read', 'run_code', 'write'])
|
||||
const sdk = assembly.sections.find(section => section.name === 'tools:sdk')?.text ?? ''
|
||||
expect(sdk).toContain('read(args:')
|
||||
expect(sdk).toContain('write(args:')
|
||||
expect(sdk).toContain('exit_plan_mode(args:')
|
||||
})
|
||||
|
||||
it('keeps the Code Mode SDK byte-identical across mode switches', async () => {
|
||||
class FakeRuntime extends CodeRuntime {
|
||||
readonly language = 'typescript'
|
||||
readonly isolation = 'fake'
|
||||
run(_request: CodeRunRequest): Promise<CodeRunResult> { return Promise.resolve({ logs: [] }) }
|
||||
}
|
||||
const withPlanMode = new Context()
|
||||
await withPlanMode.plugin(SystemPrompt)
|
||||
await withPlanMode.plugin(ToolRegistry, { mode: 'code' })
|
||||
await withPlanMode.plugin(FakeRuntime)
|
||||
await withPlanMode.plugin(PlanModeService, PLAN_CONFIG)
|
||||
registerNamedTools(withPlanMode, ['read', 'write'])
|
||||
const agent = await agentWithSession(withPlanMode)
|
||||
const defaultSdk = (await assembleFor(withPlanMode, agent)).sections.find(section => section.name === 'tools:sdk')?.text ?? ''
|
||||
expect(defaultSdk).toContain('read(args:')
|
||||
expect(defaultSdk).toContain('write(args:')
|
||||
expect(defaultSdk).toContain('exit_plan_mode(args:')
|
||||
agent.session.append('plan/mode', { active: true })
|
||||
const planSdk = (await assembleFor(withPlanMode, agent)).sections.find(section => section.name === 'tools:sdk')?.text ?? ''
|
||||
expect(planSdk).toBe(defaultSdk)
|
||||
|
||||
// Loading the plan-mode plugin deliberately adds one stable binding compared
|
||||
// with a deployment that does not compose plan mode at all.
|
||||
const bare = new Context()
|
||||
await bare.plugin(SystemPrompt)
|
||||
await bare.plugin(ToolRegistry, { mode: 'code' })
|
||||
await bare.plugin(FakeRuntime)
|
||||
registerNamedTools(bare, ['read', 'write'])
|
||||
const bareSdk = (await bare.systemPrompt.assemble({ agent })).sections.find(section => section.name === 'tools:sdk')?.text ?? ''
|
||||
expect(bareSdk).not.toContain('exit_plan_mode(args:')
|
||||
expect(defaultSdk).not.toBe(bareSdk)
|
||||
})
|
||||
})
|
||||
|
||||
describe('no execution gating beyond the exit tool', () => {
|
||||
it('passes agent-less and default-mode executions through', async () => {
|
||||
const ctx = await setup()
|
||||
registerNamedTools(ctx, ['write'])
|
||||
const agentless = await execute(ctx, 'write')
|
||||
expect(agentless.isError).toBe(false)
|
||||
const agent = await agentWithSession(ctx)
|
||||
const defaulted = await execute(ctx, 'write', agent)
|
||||
expect(defaulted.isError).toBe(false)
|
||||
})
|
||||
|
||||
it('runs every call in plan mode untouched — guidance and enforcement are separate axes', async () => {
|
||||
const ctx = await setup()
|
||||
registerNamedTools(ctx, ['read', 'write', 'bash'])
|
||||
const agent = await agentWithSession(ctx, 'agent-1', { active: true })
|
||||
for (const name of ['read', 'write', 'bash']) {
|
||||
const result = await execute(ctx, name, agent)
|
||||
expect(result.isError).toBe(false)
|
||||
}
|
||||
})
|
||||
})
|
||||
|
||||
describe('/plan', () => {
|
||||
it('registers only when a commands service is composed and optionally submits the next-step message', async () => {
|
||||
const bare = await setup()
|
||||
expect(bare.get('commands')).toBeUndefined()
|
||||
|
||||
const ctx = await setup()
|
||||
await ctx.plugin(CommandService)
|
||||
// The `ctx.inject` child mounts asynchronously once `commands` resolves.
|
||||
await new Promise(resolve => setImmediate(resolve))
|
||||
const plainAgent = await agentWithSession(ctx, 'plain-plan-command')
|
||||
const plainSteer = vi.fn()
|
||||
;(plainAgent as unknown as { steer: typeof plainSteer }).steer = plainSteer
|
||||
expect(ctx.commands.list(plainAgent)).toEqual([
|
||||
{ name: 'plan', description: 'Enter plan mode', input: { hint: '[message]' } },
|
||||
])
|
||||
|
||||
const signal = new AbortController().signal
|
||||
expect(await ctx.commands.execute(plainAgent, '/mode', signal)).toBeUndefined()
|
||||
expect(await ctx.commands.execute(plainAgent, '/review', signal)).toBeUndefined()
|
||||
const plain = await ctx.commands.execute(plainAgent, '/plan', signal)
|
||||
expect(plain).toEqual({ kind: 'success', text: 'Entering plan mode (applies from the next step).' })
|
||||
expect(ctx.planMode.get(plainAgent)).toEqual({ active: false, pending: true })
|
||||
expect(plainSteer).not.toHaveBeenCalled()
|
||||
|
||||
const messageAgent = await agentWithSession(ctx, 'message-plan-command')
|
||||
const messageSteer = vi.fn()
|
||||
;(messageAgent as unknown as { steer: typeof messageSteer }).steer = messageSteer
|
||||
const plan = await ctx.commands.execute(messageAgent, '/plan draft the migration ', signal)
|
||||
expect(plan).toEqual({ kind: 'success', text: 'Entering plan mode (applies from the next step).' })
|
||||
expect(ctx.planMode.get(messageAgent)).toEqual({ active: false, pending: true })
|
||||
expect(messageSteer).toHaveBeenCalledExactlyOnceWith([{ type: 'text', text: 'draft the migration' }])
|
||||
})
|
||||
|
||||
it('removes the contributed command when the plan-mode plugin is disposed', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
await ctx.plugin(CommandService)
|
||||
const fiber = await ctx.plugin(PlanModeService, PLAN_CONFIG)
|
||||
await new Promise(resolve => setImmediate(resolve))
|
||||
const agent = await agentWithSession(ctx)
|
||||
expect(ctx.commands.list(agent).map(command => command.name)).toEqual(['plan'])
|
||||
|
||||
await fiber.dispose()
|
||||
|
||||
expect(ctx.commands.list(agent)).toEqual([])
|
||||
})
|
||||
})
|
||||
|
||||
describe('exit_plan_mode', () => {
|
||||
async function setupWithReview(answer?: { selected: string[]; custom?: string }) {
|
||||
const ctx = await setup()
|
||||
await ctx.plugin(UserInteractionService)
|
||||
const asked: AskUserQuestionRequest[] = []
|
||||
if (answer !== undefined) {
|
||||
ctx.userInteraction.registerProvider({
|
||||
ask: (request) => {
|
||||
asked.push(request)
|
||||
return Promise.resolve({ answers: [{ id: 'plan-review', ...answer }] })
|
||||
},
|
||||
})
|
||||
}
|
||||
const agent = await agentWithSession(ctx, 'agent-1', { active: true })
|
||||
return { ctx, agent, asked }
|
||||
}
|
||||
|
||||
function callExit(ctx: Context, agent: Agent | undefined, plan = '# The plan\n\ndo things') {
|
||||
return ctx.tools.execute({
|
||||
callId: CallId(`call-exit-${++callCounter}`),
|
||||
name: EXIT_PLAN_MODE,
|
||||
arguments: { plan },
|
||||
signal: new AbortController().signal,
|
||||
...agent ? { agent } : {},
|
||||
})
|
||||
}
|
||||
|
||||
it('registers the tool with one required plan argument', async () => {
|
||||
const ctx = await setup()
|
||||
const schema = ctx.tools.schemas().find(entry => entry.name === EXIT_PLAN_MODE)
|
||||
const parameters = schema?.parameters as { required?: string[]; properties?: Record<string, unknown> }
|
||||
expect(schema?.description).toMatch(/^Use only in plan mode\./)
|
||||
expect(Object.keys(parameters.properties ?? {})).toEqual(['plan'])
|
||||
expect(parameters.required).toEqual(['plan'])
|
||||
})
|
||||
|
||||
it('rejects an agent-less call', async () => {
|
||||
const ctx = await setup()
|
||||
const result = await callExit(ctx, undefined)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: exit_plan_mode requires a calling agent (no session to switch)' }])
|
||||
})
|
||||
|
||||
it('rejects a call outside plan mode while remaining advertised', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx)
|
||||
expect(ctx.tools.schemas().map(tool => tool.name)).toContain(EXIT_PLAN_MODE)
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: exit_plan_mode is only available in plan mode' }])
|
||||
})
|
||||
|
||||
it('rejects an empty or heading-less plan before asking the reviewer', async () => {
|
||||
const { ctx, agent, asked } = await setupWithReview({ selected: ['Approve'] })
|
||||
for (const plan of ['', 'do things']) {
|
||||
const result = await callExit(ctx, agent, plan)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: exit_plan_mode requires a non-empty markdown plan starting with a # heading' }])
|
||||
}
|
||||
expect(asked).toHaveLength(0)
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('degrades to the manual exit when no user-interaction seam is composed', async () => {
|
||||
const ctx = await setup()
|
||||
const agent = await agentWithSession(ctx, 'agent-1', { active: true })
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: no user-interaction channel is available to review the plan; ask the user to switch the session mode instead' }])
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('degrades the same way when the seam has no provider (NO_PROVIDER)', async () => {
|
||||
const { ctx, agent } = await setupWithReview()
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: no user-interaction provider is registered' }])
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('approve: records the boundary-applied switch and confirms (the fold flips at the flush)', async () => {
|
||||
const { ctx, agent, asked } = await setupWithReview({ selected: ['Approve'] })
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(false)
|
||||
if (result.isError) throw new Error('expected approved plan result')
|
||||
expect(result.value).toEqual({ approved: true })
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Plan approved — plan mode exited; carry out the plan starting with your next step.' }])
|
||||
// Boundary-applied, not a direct append: the fold stays plan until the
|
||||
// step's end, so the plan policy covers any remaining call of the SAME batch.
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: true, pending: false })
|
||||
await boundary(ctx, agent, 'step/end')
|
||||
expect(foldPlanMode(agent.session.events)).toBe(false)
|
||||
expect(asked).toHaveLength(1)
|
||||
expect(asked[0]?.agent).toBe(agent)
|
||||
expect(asked[0]?.questions[0]?.detail).toBe('# The plan\n\ndo things')
|
||||
expect(asked[0]?.questions[0]?.options?.map(option => option.label)).toEqual(['Approve', 'Keep planning'])
|
||||
})
|
||||
|
||||
it('carries the exact plan through a Code Mode review and logs the nested dispatch', async () => {
|
||||
const plan = '# Code Mode plan\n\nUse the existing seam.'
|
||||
class ExitRuntime extends CodeRuntime {
|
||||
readonly language = 'typescript'
|
||||
readonly isolation = 'fake'
|
||||
async run(request: CodeRunRequest): Promise<CodeRunResult> {
|
||||
const exit = request.bindings[0]?.functions[EXIT_PLAN_MODE]
|
||||
if (exit === undefined) throw new Error('missing exit_plan_mode binding')
|
||||
return { logs: [], value: await exit({ plan }) }
|
||||
}
|
||||
}
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry, { mode: 'code' })
|
||||
await ctx.plugin(ExitRuntime)
|
||||
await ctx.plugin(PlanModeService, PLAN_CONFIG)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
const asked: AskUserQuestionRequest[] = []
|
||||
ctx.userInteraction.registerProvider({
|
||||
ask: (request) => {
|
||||
asked.push(request)
|
||||
return Promise.resolve({ answers: [{ id: 'plan-review', selected: ['Approve'] }] })
|
||||
},
|
||||
})
|
||||
const agent = await agentWithSession(ctx, 'code-mode-exit', { active: true })
|
||||
|
||||
const result = await ctx.tools.execute({
|
||||
callId: CallId(`call-exit-${++callCounter}`),
|
||||
name: RUN_CODE_NAME,
|
||||
arguments: { code: `return await tools.${EXIT_PLAN_MODE}({ plan: ${JSON.stringify(plan)} })` },
|
||||
signal: new AbortController().signal,
|
||||
agent,
|
||||
})
|
||||
|
||||
expect(result.isError).toBe(false)
|
||||
expect(asked).toHaveLength(1)
|
||||
expect(asked[0]?.questions[0]).toMatchObject({
|
||||
header: 'Plan review',
|
||||
question: 'Approve this plan and leave plan mode?',
|
||||
detail: plan,
|
||||
})
|
||||
expect(agent.session.events.find(event => event.type === 'tool/code-dispatch')?.data).toMatchObject({
|
||||
name: EXIT_PLAN_MODE,
|
||||
arguments: { plan },
|
||||
isError: false,
|
||||
})
|
||||
expect(ctx.planMode.get(agent)).toEqual({ active: true, pending: false })
|
||||
})
|
||||
|
||||
it('an approved exit keeps plan guidance until the boundary and never removes the tool', async () => {
|
||||
const { ctx, agent } = await setupWithReview({ selected: ['Approve'] })
|
||||
const approved = await callExit(ctx, agent)
|
||||
expect(approved.isError).toBe(false)
|
||||
// Calls of the SAME assistant response (no boundary between) were
|
||||
// requested under the plan-shaped header — the fold stays plan for that
|
||||
// whole batch; the boundary flush is what flips the next step.
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
const assembly = await ctx.systemPrompt.assemble({ agent })
|
||||
expect(assembly.tools.some(tool => tool.name === EXIT_PLAN_MODE)).toBe(true)
|
||||
expect(assembly.sections.find(section => section.name === 'plan:policy')?.text).toBe(TEST_PLAN_SECTION)
|
||||
await boundary(ctx, agent, 'step/end')
|
||||
expect(foldPlanMode(agent.session.events)).toBe(false)
|
||||
const afterExit = await ctx.systemPrompt.assemble({ agent })
|
||||
expect(afterExit.tools).toEqual(assembly.tools)
|
||||
expect(afterExit.sections.find(section => section.name === 'plan:policy')?.text).toBe('')
|
||||
})
|
||||
|
||||
it('the exit flush narrates nothing — the tool result is the narration', async () => {
|
||||
const { ctx, agent } = await setupWithReview({ selected: ['Approve'] })
|
||||
header(agent.session)
|
||||
await callExit(ctx, agent)
|
||||
await boundary(ctx, agent, 'step/end')
|
||||
expect(foldPlanMode(agent.session.events)).toBe(false)
|
||||
expect(noticeTexts(agent.session)).toEqual([])
|
||||
})
|
||||
|
||||
it('keep planning returns the corrective error carrying the feedback verbatim', async () => {
|
||||
const { ctx, agent } = await setupWithReview({ selected: ['Keep planning'], custom: 'consider the resume path' })
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: The user chose to keep planning; their feedback: consider the resume path' }])
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('keep planning without feedback returns the generic corrective error', async () => {
|
||||
const { ctx, agent } = await setupWithReview({ selected: ['Keep planning'] })
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: The user chose to keep planning; revise the plan and present it again.' }])
|
||||
})
|
||||
|
||||
it('a custom-text-only answer is feedback, never consent', async () => {
|
||||
const { ctx, agent } = await setupWithReview({ selected: [], custom: 'add tests first' })
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: The user chose to keep planning; their feedback: add tests first' }])
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('requires exactly the single Approve selection', async () => {
|
||||
const { ctx, agent } = await setupWithReview({ selected: ['Approve', 'Keep planning'] })
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: The user chose to keep planning; revise the plan and present it again.' }])
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('treats custom text alongside Approve as feedback, not consent', async () => {
|
||||
const { ctx, agent } = await setupWithReview({ selected: ['Approve'], custom: 'change the tests' })
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: The user chose to keep planning; their feedback: change the tests' }])
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('treats duplicate review answer items as non-consent', async () => {
|
||||
const { ctx, agent } = await setupWithReview()
|
||||
ctx.userInteraction.registerProvider({
|
||||
ask: () => Promise.resolve({ answers: [
|
||||
{ id: 'plan-review', selected: ['Approve'] },
|
||||
{ id: 'plan-review', selected: ['Keep planning'] },
|
||||
] }),
|
||||
})
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: The user chose to keep planning; revise the plan and present it again.' }])
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('a missing answer item reads as keep-planning', async () => {
|
||||
const { ctx, agent } = await setupWithReview()
|
||||
ctx.userInteraction.registerProvider({ ask: () => Promise.resolve({ answers: [] }) })
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: The user chose to keep planning; revise the plan and present it again.' }])
|
||||
})
|
||||
|
||||
it('forwards the execution abort signal to the review question', async () => {
|
||||
const { ctx, agent, asked } = await setupWithReview({ selected: ['Approve'] })
|
||||
const controller = new AbortController()
|
||||
const result = await ctx.tools.execute({
|
||||
callId: CallId(`call-exit-${++callCounter}`),
|
||||
name: EXIT_PLAN_MODE,
|
||||
arguments: { plan: '# P' },
|
||||
agent,
|
||||
signal: controller.signal,
|
||||
})
|
||||
expect(result.isError).toBe(false)
|
||||
expect(asked[0]?.signal).toBe(controller.signal)
|
||||
})
|
||||
|
||||
it('fails the call when the plugin is disposed while the review awaits (no phantom exit)', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
const fiber = await ctx.plugin(PlanModeService, PLAN_CONFIG)
|
||||
await ctx.plugin(UserInteractionService)
|
||||
let answer!: (value: { answers: { id: string; selected: string[] }[] }) => void
|
||||
ctx.userInteraction.registerProvider({
|
||||
ask: () => new Promise((resolve) => { answer = resolve }),
|
||||
})
|
||||
const agent = await agentWithSession(ctx, 'agent-1', { active: true })
|
||||
const pending = callExit(ctx, agent)
|
||||
// Let execute reach the review await, then unload the plugin (HMR) and
|
||||
// only afterwards approve. The boundary listeners are gone, so a success
|
||||
// would claim an exit that can never flush — the call must fail instead.
|
||||
await new Promise(resolve => setImmediate(resolve))
|
||||
await fiber.dispose()
|
||||
answer({ answers: [{ id: 'plan-review', selected: ['Approve'] }] })
|
||||
const result = await pending
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: the plan-mode service was reloaded while the plan was under review; present the plan again' }])
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('a throwing provider surfaces as the corrective isError and the mode stays plan', async () => {
|
||||
const { ctx, agent } = await setupWithReview()
|
||||
ctx.userInteraction.registerProvider({ ask: () => { throw new Error('review aborted') } })
|
||||
const result = await callExit(ctx, agent)
|
||||
expect(result.isError).toBe(true)
|
||||
expect(result.content).toEqual([{ type: 'text', text: 'Error: review aborted' }])
|
||||
expect(foldPlanMode(agent.session.events)).toBe(true)
|
||||
})
|
||||
|
||||
it('presents the call as a generic card titled by the plan first heading', async () => {
|
||||
const ctx = await setup()
|
||||
const def = ctx.tools.get(EXIT_PLAN_MODE)!
|
||||
expect(def.presentCall?.({ plan: '## Fix the flake\n\nsteps' })).toEqual({
|
||||
card: 'generic',
|
||||
title: 'Fix the flake',
|
||||
kind: 'other',
|
||||
content: [{ type: 'text', text: '## Fix the flake\n\nsteps' }],
|
||||
})
|
||||
expect(def.presentCall?.({ plan: 'no heading here' })).toEqual({
|
||||
card: 'generic',
|
||||
title: 'Plan',
|
||||
kind: 'other',
|
||||
content: [{ type: 'text', text: 'no heading here' }],
|
||||
})
|
||||
})
|
||||
|
||||
it('presents the result as a generic review card', async () => {
|
||||
const ctx = await setup()
|
||||
const def = ctx.tools.get(EXIT_PLAN_MODE)!
|
||||
const content = [{ type: 'text' as const, text: 'ok' }]
|
||||
expect(def.presentResult?.({ plan: '# P' }, { content, isError: false })).toEqual({
|
||||
card: 'generic',
|
||||
title: 'Plan review',
|
||||
content,
|
||||
})
|
||||
})
|
||||
})
|
||||
|
||||
describe('HMR disposal', () => {
|
||||
it('does not flush a retry boundary that resumes after plugin disposal', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
const fiber = await ctx.plugin(PlanModeService, PLAN_CONFIG)
|
||||
const agent = await agentWithSession(ctx, 'disposed-in-flight-recovery')
|
||||
const recoveryEntered = Promise.withResolvers<true>()
|
||||
const releaseRecovery = Promise.withResolvers<true>()
|
||||
ctx.on('agent/request-error', async (_agent, _turn, _step, _error, _failure, _history, _signal, _next) => {
|
||||
recoveryEntered.resolve(true)
|
||||
await releaseRecovery.promise
|
||||
return { action: 'retry' }
|
||||
})
|
||||
ctx.planMode.set(agent, true)
|
||||
|
||||
const recovery = recoveryBoundary(ctx, agent, { action: 'fail' })
|
||||
await recoveryEntered.promise
|
||||
await fiber.dispose()
|
||||
releaseRecovery.resolve(true)
|
||||
|
||||
expect(await recovery).toEqual({ action: 'retry' })
|
||||
expect(agent.session.events.some(event => event.type === 'plan/mode')).toBe(false)
|
||||
})
|
||||
|
||||
it('unregisters the service, listeners, prompt section, and stable exit tool with the plugin fiber', async () => {
|
||||
const ctx = new Context()
|
||||
await ctx.plugin(SystemPrompt)
|
||||
await ctx.plugin(ToolRegistry)
|
||||
const fiber = await ctx.plugin(PlanModeService, PLAN_CONFIG)
|
||||
const agent = await agentWithSession(ctx, 'disposed-recovery')
|
||||
ctx.planMode.set(agent, true)
|
||||
expect(ctx.get('planMode')).toBeInstanceOf(PlanModeService)
|
||||
expect(ctx.tools.get(EXIT_PLAN_MODE)).toBeDefined()
|
||||
expect((await ctx.systemPrompt.assemble()).sections.map(section => section.name)).toContain('plan:policy')
|
||||
|
||||
await fiber.dispose()
|
||||
expect(ctx.get('planMode')).toBeUndefined()
|
||||
expect(ctx.tools.get(EXIT_PLAN_MODE)).toBeUndefined()
|
||||
expect((await ctx.systemPrompt.assemble()).sections.map(section => section.name)).not.toContain('plan:policy')
|
||||
expect(await recoveryBoundary(ctx, agent, { action: 'retry' })).toEqual({ action: 'retry' })
|
||||
expect(agent.session.events.some(event => event.type === 'plan/mode')).toBe(false)
|
||||
})
|
||||
})
|
||||
Reference in New Issue
Block a user