Files
deepseek-harness/packages/todo/tool-todo/tests/integration.spec.ts
imccyu ec601ca13d build(vendor): rescope the vendored Cordis packages into @deepseek-ai
Machine-produced by `pnpm run rescope-vendor --apply` plus the regeneration it
prints: `pnpm install` for the lockfile, `pnpm run gen-third-party-notices`,
`verify-translation-pairing --write` for the touched bilingual pairs,
`gen-doc-graphs`, and one typert snapshot whose ids embed character offsets.
`pnpm run rescope-vendor --check` verifies the result.

Renames nine vendored packages (cordis, cosmokit, schemastery and the six
@cordisjs plugins) and every reference that resolves them: manifest names and
dependency keys, module specifiers including declare-module merges, cordis.yml
plugin names, tsconfig paths, every Markdown fence, and `docs/` prose.
Directory names, upstream versions, and dependency ranges are unchanged, so
vendor/README.md still reads as an upstream snapshot; its manifest table gains
an upstream-name column so THIRD_PARTY_NOTICES keeps MIT attribution pointed
at each fork's origin.

The tutorial tier follows the rename end to end: its yaml fences named plugins
the Loader can no longer resolve, its `ts ignore-check` fences disagreed with
the compiled fences beside them, and its prose quoted both. The contracts that
told readers to keep upstream names — the root convention and the vendoring
cookbook's tree comment and manifest invariant — now say to rescope instead.

Two rules read `@deepseek-ai/` as "another workspace plugin": the client bundle
purity gate now names the vendored libraries a browser bundle inlines, and the
files where a bare `cordis` is an agent-preset id keep that product data.
2026-08-10 22:04:13 +08:00

102 lines
4.1 KiB
TypeScript

import { createUserMessage } from '@deepseek-ai/dsh-llm'
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import { SessionId, type SessionEvent } from '@deepseek-ai/dsh-session'
import type { Agent } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit'
import * as ToolTodo from '@deepseek-ai/dsh-tool-todo'
import { MockAdapter, textResponse, toolCallResponse } from '../../../core/agent-loop/tests/mock-adapter.ts'
/**
* Full-loop integration: a scripted mock model drives the REAL todo_write tool
* through the agent loop, exercising the same execution paths a live model would — the
* tool/call + tool/result session events AND the todo/write event the tool
* appends. Only the model is mocked; the tool and the session log are real.
*/
async function harness(adapter: MockAdapter): Promise<Context> {
const ctx = new Context()
await mountAgentLoopTestDependencies(ctx)
await ctx.plugin(AgentLoop, { agents: [] })
await ctx.plugin(ToolTodo, { allowParallelInProgress: true })
ctx.llm.registerAdapter(['mock'], adapter)
return ctx
}
function waitForIdle(ctx: Context, agent: Agent): Promise<void> {
return new Promise((resolve) => {
const dispose = ctx.on('agent/status', ({ agent: 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('todo_write tool through the agent loop', () => {
it('model calls todo_write: a tool/call, a non-error tool/result, and a todo/write snapshot land', async () => {
const adapter = new MockAdapter([
toolCallResponse('call-1', 'todo_write', {
todos: [
{ content: 'read the code', status: 'in_progress' },
{ content: 'write the fix', status: 'pending' },
],
}, 'Planning the work.'),
textResponse('Plan recorded.'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('it-todo'), { provider: 'mock', model: 'mock' })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'plan a two-step task' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
const log = agent.session.events
expect(findEvent(log, 'tool/call').data.name).toBe('todo_write')
expect(findEvent(log, 'tool/result').data.message.content[0].isError).toBe(false)
const todoEvent = findEvent(log, 'todo/write')
expect(todoEvent.data.todos).toEqual([
{ content: 'read the code', status: 'in_progress' },
{ content: 'write the fix', status: 'pending' },
])
})
it('a second todo_write replaces the list (last-write-wins on the log)', async () => {
const adapter = new MockAdapter([
toolCallResponse('call-1', 'todo_write', { todos: [{ content: 'step one', status: 'in_progress' }] }),
toolCallResponse('call-2', 'todo_write', {
todos: [
{ content: 'step one', status: 'completed' },
{ content: 'step two', status: 'in_progress' },
],
}),
textResponse('Done planning.'),
])
const ctx = await harness(adapter)
const agent = ctx.agentLoop.create(SessionId('it-todo-2'), { provider: 'mock', model: 'mock' })
agent.followup(createUserMessage({ content: [{ type: 'text', text: 'plan then update' }], source: { kind: 'user' } }))
await waitForIdle(ctx, agent)
const todoEvents = agent.session.events.filter(e => e.type === 'todo/write')
expect(todoEvents).toHaveLength(2)
expect(findEvent(agent.session.events, 'todo/write', 'last').data.todos).toEqual([
{ content: 'step one', status: 'completed' },
{ content: 'step two', status: 'in_progress' },
])
})
})