# Conflicts: # docs/architecture.md # docs/config-catalog.md # docs/cordis-catalog/events.md # docs/cordis-catalog/services.md # docs/core-data-structures/core.md # docs/event-producer-consumer.md # docs/module-graph.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/coding-task.e2e.ts # examples/coding-agent/tests/compaction.e2e.ts # examples/coding-agent/tests/full-loop.e2e.ts # examples/coding-agent/tests/todo-write.e2e.ts # examples/cordis-agent/tests/cordis-tools.e2e.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/bash/tool-bash/tests/tools.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/context/time-context/tests/time-context.spec.ts # packages/cordis/tool-cordis/src/api-catalog.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/README.md # packages/core/agent-loop/src/agent.ts # packages/core/agent-loop/src/index.ts # packages/core/agent-loop/tests/agent.spec.ts # packages/core/agent-loop/tests/cancel.spec.ts # packages/core/agent-loop/tests/config-session-id.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.ts # packages/core/agent-loop/tests/coverage-edges.spec.ts # packages/core/agent-loop/tests/interception.spec.ts # packages/core/agent-loop/tests/loop.spec.ts # packages/core/agent-loop/tests/properties.spec.ts # packages/core/agent-loop/tests/request-cache.e2e.ts # packages/core/agent-loop/tests/request-reconstruction.spec.ts # packages/core/agent-loop/tests/resume.spec.ts # packages/core/agent-loop/tests/scope-lifecycle.spec.ts # packages/core/agent-loop/tests/tool-order.spec.ts # packages/core/agent-loop/tests/turn-stop.spec.ts # packages/core/agent/src/types.ts # packages/examples/agent-spine-demo/README.md # packages/examples/agent-spine-demo/tests/agent-core.spec.ts # packages/examples/stdio-demo/README.md # packages/examples/stdio-demo/src/index.ts # packages/examples/stdio-demo/tests/stdio-agent.spec.ts # packages/fs/tool-fs/tests/fs-tools.e2e.ts # packages/guard/repeat-tool-guard/tests/repeat-tool-guard.spec.ts # packages/hooks/hooks-claude/tests/bridge.spec.ts # packages/hooks/hooks-claude/tests/coverage.spec.ts # packages/hooks/hooks-codex/tests/bridge.spec.ts # packages/hooks/hooks-codex/tests/coverage.spec.ts # packages/subagent/subagent-fork/tests/multi-subagent.spec.ts # packages/subagent/subagent-fork/tests/subagent-fork.spec.ts # packages/subagent/subagent-inprocess/tests/structured.spec.ts # packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts # packages/subagent/subagent-spawn/tests/spawn.e2e.ts # packages/subagent/subagent-spawn/tests/subagent-spawn.spec.ts # packages/todo/tool-todo/tests/integration.spec.ts # packages/ui/acp/tests/dispose.spec.ts # packages/ui/acp/tests/edges.spec.ts # packages/workflow/workflow-workerthread/tests/integration.spec.ts
54 lines
2.2 KiB
TypeScript
54 lines
2.2 KiB
TypeScript
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 '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', model: 'deepseek-v4-flash' })
|
|
|
|
agent.send([{ type: 'text', text:
|
|
'Use the todo_write tool to record a plan of exactly two steps: first '
|
|
+ '"inspect the failing test" (in_progress), then "apply the fix" (pending). '
|
|
+ 'Send both in one todo_write call, then reply with the single word DONE.' }])
|
|
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.
|
|
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: 'apply the fix', status: 'pending' },
|
|
])
|
|
}, 120_000)
|
|
})
|