mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
Merge branch 'codex/simp-ui-identity-residue' into codex/simp-hide-concrete-agent-loop
# Conflicts: # docs/event-producer-consumer.md # examples/coding-agent/tests/code-mode.e2e.ts # examples/coding-agent/tests/harness.ts # examples/coding-agent/tests/resume.e2e.ts # examples/cordis-agent/tests/harness.ts # packages/bash/tool-bash/tests/integration.spec.ts # packages/compact/compact-basic/tests/compact-loop-repro.spec.ts # packages/cordis/tool-cordis/tests/integration.spec.ts # packages/core/agent-loop/tests/contract-regressions.spec.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/todo/tool-todo/tests/integration.spec.ts
This commit is contained in:
@@ -1,4 +1,4 @@
|
||||
import { mkdtemp, readFile, rm } from 'node:fs/promises'
|
||||
import { mkdtemp, mkdir, readFile, rm, writeFile } from 'node:fs/promises'
|
||||
import { tmpdir } from 'node:os'
|
||||
import { join } from 'node:path'
|
||||
import { afterEach, describe, expect, it } from 'vitest'
|
||||
@@ -15,6 +15,9 @@ import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
|
||||
import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
|
||||
import * as LlmDeepSeek from '@deepseek-ai/dsh-llm-deepseek'
|
||||
import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
|
||||
import LocalFileSystem from '@deepseek-ai/dsh-fs-local'
|
||||
import * as ToolFs from '@deepseek-ai/dsh-tool-fs'
|
||||
import * as WorkspaceContext from '@deepseek-ai/dsh-workspace-context'
|
||||
|
||||
/**
|
||||
* With-key Code Mode proof: a real model receives only `run_code`, composes two
|
||||
@@ -24,6 +27,7 @@ import { WorkerCodeRuntime } from '@deepseek-ai/dsh-code-runtime-worker'
|
||||
|
||||
const PERSONA = 'You are coding-agent. You work by writing TypeScript programs for run_code: '
|
||||
+ 'batch related tool work into one program and print or return ONLY the findings that matter.'
|
||||
const WORKSPACE_PROBE = 'dragonfruit-8675309'
|
||||
|
||||
let ctx: Context | undefined
|
||||
let workdir: string | undefined
|
||||
@@ -46,13 +50,29 @@ async function codeModeHarness(cwd: string): Promise<Context> {
|
||||
await harness.plugin(ToolRegistry, { mode: 'code' })
|
||||
await harness.plugin(AgentRegistry)
|
||||
await harness.plugin(AgentLoop, { agents: [] })
|
||||
await harness.plugin(LlmDeepSeek, { models: ['deepseek-v4-flash'] })
|
||||
await harness.plugin(LlmDeepSeek)
|
||||
await harness.plugin(LocalBashExecutor, { cwd, timeoutMs: 30_000 })
|
||||
await harness.plugin(ToolBash)
|
||||
await harness.plugin(WorkerCodeRuntime, {})
|
||||
return harness
|
||||
}
|
||||
|
||||
async function workspaceCodeModeHarness(): Promise<Context> {
|
||||
const harness = new Context()
|
||||
await harness.plugin(LlmService)
|
||||
await harness.plugin(SessionStore)
|
||||
await harness.plugin(SystemPrompt, { persona: PERSONA })
|
||||
await harness.plugin(ToolRegistry, { mode: 'code' })
|
||||
await harness.plugin(AgentRegistry)
|
||||
await harness.plugin(LocalFileSystem, { cwd: '/' })
|
||||
await harness.plugin(ToolFs)
|
||||
await harness.plugin(WorkspaceContext, { maxBytes: 65536 })
|
||||
await harness.plugin(AgentLoop, { agents: [] })
|
||||
await harness.plugin(LlmDeepSeek, { models: [{ id: 'deepseek-v4-flash' }] })
|
||||
await harness.plugin(WorkerCodeRuntime, {})
|
||||
return harness
|
||||
}
|
||||
|
||||
function waitForIdle(harness: Context, agent: Agent): Promise<void> {
|
||||
return new Promise((resolve) => {
|
||||
const dispose = harness.on('agent/status', (subject, status) => {
|
||||
@@ -68,7 +88,7 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
|
||||
it('collapses the wire tool list to [run_code], bridges sub-calls, and returns curated output', async () => {
|
||||
workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-e2e-'))
|
||||
ctx = await codeModeHarness(workdir)
|
||||
const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { model: 'deepseek-v4-flash' })
|
||||
const agent = ctx.agentLoop.create(SessionId('e2e-code-mode'), { provider: 'deepseek', model: 'deepseek-v4-flash' })
|
||||
|
||||
agent.send([{
|
||||
type: 'text',
|
||||
@@ -108,4 +128,42 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY)('Code Mode: real model writes a p
|
||||
expect(finalText).toContain('alpha-7')
|
||||
expect(finalText).toContain('beta-9')
|
||||
}, 180_000)
|
||||
|
||||
it('delivers nested workspace instructions discovered by an fs sub-call after the outer result', async () => {
|
||||
workdir = await mkdtemp(join(tmpdir(), 'dsh-code-mode-workspace-e2e-'))
|
||||
await mkdir(join(workdir, '.git'), { recursive: true })
|
||||
await mkdir(join(workdir, 'pkg/deep'), { recursive: true })
|
||||
await writeFile(join(workdir, 'pkg/AGENTS.md'), `If asked for the Code Mode workspace handshake, reply with exactly ${WORKSPACE_PROBE} and nothing else.\n`)
|
||||
await writeFile(join(workdir, 'pkg/deep/task.txt'), 'Touch this file to discover the nested instructions.\n')
|
||||
ctx = await workspaceCodeModeHarness()
|
||||
const handle = await ctx.agents.create({
|
||||
sessionId: SessionId('e2e-code-mode-workspace-session'),
|
||||
meta: { cwd: workdir },
|
||||
agentOptions: { provider: 'deepseek', model: 'deepseek-v4-flash' },
|
||||
})
|
||||
|
||||
handle.agent.send([{
|
||||
type: 'text',
|
||||
text: 'Use one run_code program to call tools.read on pkg/deep/task.txt. After it finishes, answer: Code Mode workspace handshake?',
|
||||
}])
|
||||
await waitForIdle(ctx, handle.agent)
|
||||
|
||||
const events: SessionEvent[] = [...handle.agent.session.events]
|
||||
const dispatch = events.find(event => event.type === 'tool/code-dispatch' && event.data.name === 'read')
|
||||
const outerResult = events.find(event => event.type === 'tool/result')
|
||||
const workspaceContext = events.find(event => event.type === 'context/message'
|
||||
&& typeof event.data.meta === 'object'
|
||||
&& event.data.meta !== null
|
||||
&& !Array.isArray(event.data.meta)
|
||||
&& event.data.meta.kind === 'workspace-instructions')
|
||||
expect(dispatch).toBeDefined()
|
||||
expect(outerResult).toBeDefined()
|
||||
expect(workspaceContext).toBeDefined()
|
||||
expect(workspaceContext!.seq).toBeGreaterThan(outerResult!.seq)
|
||||
const finalMessage = events.findLast(event => event.type === 'assistant/message')
|
||||
const answer = finalMessage?.type === 'assistant/message'
|
||||
? finalMessage.data.content.filter(block => block.type === 'text').map(block => block.text).join('')
|
||||
: ''
|
||||
expect(answer).toContain(WORKSPACE_PROBE)
|
||||
}, 180_000)
|
||||
})
|
||||
|
||||
Reference in New Issue
Block a user