imccyu
ec601ca13d
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.
59 lines
2.6 KiB
TypeScript
59 lines
2.6 KiB
TypeScript
import { createUserMessage } from '@deepseek-ai/dsh-llm'
|
|
import { mkdtemp, rm } from 'node:fs/promises'
|
|
import { tmpdir } from 'node:os'
|
|
import { join } from 'node:path'
|
|
import { afterEach, describe, expect, it } from 'vitest'
|
|
import type { Context } from '@deepseek-ai/cordis'
|
|
import { codingHarness, TODO_SYSTEM_PROMPT, waitForIdle } from './harness.ts'
|
|
import { SessionId } from '@deepseek-ai/dsh-session'
|
|
|
|
/**
|
|
* A REAL model drives the REAL todo_write tool: verify the WORLD (the session
|
|
* log gains a todo/write event whose snapshot the model actually produced), not
|
|
* the agent's self-report. Key-gated (see vitest.e2e.config.ts).
|
|
*/
|
|
|
|
let ctx: Context | undefined
|
|
let workdir: string | undefined
|
|
|
|
afterEach(async () => {
|
|
await ctx?.fiber.dispose()
|
|
ctx = undefined
|
|
if (workdir !== undefined) await rm(workdir, { recursive: true, force: true })
|
|
workdir = undefined
|
|
})
|
|
|
|
describe.skipIf(!process.env.DEEPSEEK_API_KEY)('todo_write: real model records a plan', () => {
|
|
it('appends a todo/write event with the model-produced task list', async () => {
|
|
workdir = await mkdtemp(join(tmpdir(), 'dsh-todo-write-e2e-'))
|
|
ctx = await codingHarness(workdir, { persona: TODO_SYSTEM_PROMPT })
|
|
const agent = ctx.agentLoop.create(SessionId('e2e-todo'), { provider: 'deepseek-official', model: 'deepseek-v4-flash' })
|
|
|
|
agent.followup(createUserMessage({
|
|
content: [{ type: 'text', text:
|
|
'Use the todo_write tool to record a plan of exactly three steps for work '
|
|
+ 'running in parallel: "inspect the failing test" (in_progress), '
|
|
+ '"watch the background build" (in_progress), then "apply the fix" (pending). '
|
|
+ 'Send all three in one todo_write call, then reply with the single word DONE.' }], source: { kind: 'user' } }))
|
|
await waitForIdle(ctx, agent)
|
|
|
|
const events = [...agent.session.events]
|
|
|
|
// The model actually called the tool.
|
|
const calls = events.filter(event => event.type === 'tool/call')
|
|
expect(calls.some(event => event.data.name === 'todo_write')).toBe(true)
|
|
|
|
// And the tool wrote a todo/write event to the log — verify the WORLD,
|
|
// including two simultaneously in_progress tasks (the parallel contract).
|
|
const todoEvents = events.filter(event => event.type === 'todo/write')
|
|
expect(todoEvents.length).toBeGreaterThan(0)
|
|
|
|
const todos = (todoEvents.at(-1)!).data.todos
|
|
expect(todos).toEqual([
|
|
{ content: 'inspect the failing test', status: 'in_progress' },
|
|
{ content: 'watch the background build', status: 'in_progress' },
|
|
{ content: 'apply the fix', status: 'pending' },
|
|
])
|
|
}, 120_000)
|
|
})
|