fix(preset): align minimal agent with RL composition
This commit is contained in:
Yichen Jiang
@@ -1,39 +1,71 @@
|
||||
# The `minimal` agent preset: the two-tool benchmark surface.
|
||||
# The `minimal` agent preset: the Claude SWE-compatible RL surface.
|
||||
#
|
||||
# The native model surface is exactly persistent `bash` plus
|
||||
# `str_replace_editor`. Everything else a session could reach — skills, goals,
|
||||
# plan mode, delegation, workflows, todo, web — is simply absent rather than
|
||||
# disabled, because a preset composes what an agent has instead of subtracting
|
||||
# from a shared default.
|
||||
#
|
||||
# The host composition is unchanged: this agent still runs inside the same
|
||||
# sandbox, approval, persistence, and model routing as any other session.
|
||||
# The persona is the complete system prompt, so global identity, Web surface,
|
||||
# tool guidance, and later assembly listeners cannot add prompt text. The model
|
||||
# composes only the persistent `bash` and `str_replace_editor` tools.
|
||||
|
||||
- id: persona
|
||||
name: '@deepseek-ai/dsh-persona'
|
||||
config:
|
||||
text: >-
|
||||
You are a coding agent powered by the {{model}} model. Your working directory is {{cwd}}.
|
||||
text: You are a helpful software engineer assistant.
|
||||
complete: true
|
||||
|
||||
# `bash-env` stays in the HOST composition: `apps/cli/src/web.ts` injects it to
|
||||
# publish `DSH_WEB_URL`/`DSH_WEB_MODE`, and a host row that injects a service is
|
||||
# the criterion for host-plane ownership — injection resolves before any session
|
||||
# exists, so there is no agent to key by. Behind a preset realm those variables
|
||||
# never reached the model's shell at all. `tool-bash` consumes the host registry
|
||||
# from here; the executor behind it (`bash-sandbox`) is host-plane too, where the
|
||||
# sandbox policy owns it.
|
||||
#
|
||||
# `run_in_background` is off because this preset mounts no `tool-tasks`. The
|
||||
# host registry already refuses a start for an owner no attached control
|
||||
# surface serves, so this is not the safety boundary — it is the model-facing
|
||||
# one: an agent that could never collect a task should not be offered the
|
||||
# parameter at all, and disabling it drops the parameter from the schema.
|
||||
- id: tool-bash
|
||||
name: '@deepseek-ai/dsh-tool-bash'
|
||||
# The PTY registry is an agent-owned service, so it lives in an entry-local
|
||||
# realm. The backend still consumes the host sandbox policy and subprocess
|
||||
# implementation, while the tool registers into this agent's scoped catalog.
|
||||
- id: persistent-shell
|
||||
name: cordis:group
|
||||
group: true
|
||||
isolate:
|
||||
pty: true
|
||||
config:
|
||||
enableRunInBackground: false
|
||||
- id: pty
|
||||
name: '@deepseek-ai/dsh-pty'
|
||||
|
||||
- id: tool-str-replace-editor
|
||||
- id: pty-local
|
||||
name: '@deepseek-ai/dsh-pty-local'
|
||||
config:
|
||||
timeoutMs: 300000
|
||||
|
||||
- id: persistent-bash
|
||||
name: '@deepseek-ai/dsh-tool-bash-persistent'
|
||||
config:
|
||||
timeoutMs: 300000
|
||||
description: |-
|
||||
Run commands in a bash shell
|
||||
* When invoking this tool, the contents of the "command" parameter does NOT need to be XML-escaped.
|
||||
* You don't have access to the internet via this tool.
|
||||
* You do have access to a mirror of common linux and python packages via apt and pip.
|
||||
* State is persistent across command calls and discussions with the user.
|
||||
* To inspect a particular line range of a file, e.g. lines 10-25, try 'sed -n 10,25p /path/to/the/file'.
|
||||
* Please avoid commands that may produce a very large amount of output.
|
||||
* Please run long lived commands in the background, e.g. 'sleep 10 &' or start a server in the background.
|
||||
|
||||
# Absolute paths are unconditional in the current editor; the legacy
|
||||
# `requireAbsolutePath` switch is no longer a configuration field.
|
||||
- id: str-replace-editor
|
||||
name: '@deepseek-ai/dsh-tool-str-replace-editor'
|
||||
config:
|
||||
maxOutputChars: 16000
|
||||
|
||||
# RL core's fixed 128K window now comes from the routed model metadata rather
|
||||
# than compact-basic config. Its remaining policy is preserved explicitly.
|
||||
- id: compaction
|
||||
name: cordis:group
|
||||
group: true
|
||||
isolate:
|
||||
tokenMeter: true
|
||||
compact: true
|
||||
config:
|
||||
- id: token-meter
|
||||
name: '@deepseek-ai/dsh-token-meter'
|
||||
|
||||
- id: compact-basic
|
||||
name: '@deepseek-ai/dsh-compact-basic'
|
||||
config:
|
||||
thresholdRatio: 0.8
|
||||
retainTokens: 20480
|
||||
summarizationProvider: ''
|
||||
summarizationModel: ''
|
||||
maxTokens: 8192
|
||||
compactionRetries: 1
|
||||
|
||||
@@ -1,3 +1,3 @@
|
||||
name: 极简模式
|
||||
description: 只向模型呈现 bash 与 str_replace_editor，适合 benchmark 与最小复现。
|
||||
description: 固定 RL 系统提示词，只呈现持久 bash 与 str_replace_editor。
|
||||
order: 3
|
||||
|
||||
@@ -1,113 +0,0 @@
|
||||
# Opt-in Web shell for the RL core agent contract. The model receives exactly
|
||||
# the configured persona plus the native `bash` and `str_replace_editor`
|
||||
# schemas; the Web host, browser shell, persistence, and permission stack stay.
|
||||
|
||||
# Match the Claude SWE-compatible RL core prompt. Disabling the Web runtime's
|
||||
# surface context removes its GUI orientation, managed shell variables, and the
|
||||
# launcher's source-checkout section through one configuration contract.
|
||||
# Workspace instructions are model-visible user context rather than a system
|
||||
# section, but RL core disables them as part of the same prompt contract.
|
||||
- id: system-prompt
|
||||
config:
|
||||
includeHarnessIdentity: false
|
||||
persona: !!js process.env.DSH_SYSTEM_PROMPT ?? 'You are a helpful software engineer assistant.'
|
||||
|
||||
- id: web-runtime
|
||||
config:
|
||||
surfaceContext: false
|
||||
|
||||
- id: workspace-context
|
||||
disabled: true
|
||||
|
||||
- id: tools
|
||||
config:
|
||||
mode: native
|
||||
|
||||
# Disable every model-facing consumer in the base/Web tree. plan-mode owns the
|
||||
# always-registered exit_plan_mode tool even while the session is not planning.
|
||||
- id: tool-bash
|
||||
disabled: true
|
||||
|
||||
- id: tool-tasks
|
||||
disabled: true
|
||||
|
||||
- id: tool-fs
|
||||
disabled: true
|
||||
|
||||
- id: tool-fs-search
|
||||
disabled: true
|
||||
|
||||
- id: tool-web
|
||||
disabled: true
|
||||
|
||||
- id: tool-skill
|
||||
disabled: true
|
||||
|
||||
- id: plan-mode
|
||||
disabled: true
|
||||
|
||||
- id: tool-subagent-control
|
||||
disabled: true
|
||||
|
||||
- id: tool-subagent-list-agents
|
||||
disabled: true
|
||||
|
||||
- id: tool-subagent
|
||||
disabled: true
|
||||
|
||||
- id: tool-subagent-fork
|
||||
disabled: true
|
||||
|
||||
- id: tool-workflow
|
||||
disabled: true
|
||||
|
||||
- id: tool-todo
|
||||
disabled: true
|
||||
|
||||
# These consumers are shared defaults on the ordinary shipped surfaces, but
|
||||
# this opt-in profile keeps exactly its two named tools.
|
||||
- id: tool-goal
|
||||
disabled: true
|
||||
|
||||
- id: tool-ralph
|
||||
disabled: true
|
||||
|
||||
- id: tool-str-replace-editor
|
||||
disabled: true
|
||||
|
||||
# The matching browser controls must not offer surfaces whose tool this
|
||||
# overlay omits: the panels would render for a capability the model does not
|
||||
# have. Turning the row off no longer removes a tool — `ui-question`'s host
|
||||
# half is empty and `tool-ask-user` is composed per preset — so this is a UI
|
||||
# decision now, not a capability one.
|
||||
- id: ui-plan
|
||||
disabled: true
|
||||
|
||||
- id: ui-question
|
||||
disabled: true
|
||||
|
||||
- insert:
|
||||
- id: pty
|
||||
name: '@deepseek-ai/dsh-pty'
|
||||
|
||||
# This backend consumes the existing Web sandbox and permission policy.
|
||||
# It loads only on Linux/macOS; Windows and other platforms fail at boot.
|
||||
# Its 300s send wait matches the persistent Bash command timeout instead of
|
||||
# pty-local's 30s default. An open persistent shell fences permission-mode
|
||||
# changes until it closes.
|
||||
- id: pty-local
|
||||
name: '@deepseek-ai/dsh-pty-local'
|
||||
config:
|
||||
timeoutMs: 300000
|
||||
|
||||
- id: persistent-bash
|
||||
name: '@deepseek-ai/dsh-tool-bash-persistent'
|
||||
config:
|
||||
timeoutMs: 300000
|
||||
|
||||
# The editor consumes the Web fs-sandbox provider and therefore retains
|
||||
# the selected session permission mode.
|
||||
- id: str-replace-editor
|
||||
name: '@deepseek-ai/dsh-tool-str-replace-editor'
|
||||
config:
|
||||
maxOutputChars: 16000
|
||||
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write apps/cli/reference/README.md
|
||||
README.md: 0b5faf8993cd8065fffcfec5f240b0084508db91
|
||||
README.zh.md: b9c48c16dd4be186266d30a438329463c31aca70
|
||||
README.md: 12574a369acf2697842ae3aae95ce152d52c009d
|
||||
README.zh.md: f80dfba10292a03b1d855481bf4fa947a42a53c2
|
||||
|
||||
@@ -59,9 +59,7 @@ All modes treat the invoking directory as the default workspace root, load appli
|
||||
|
||||
New sessions default to the `workspace-write` permission preset. Bash and filesystem mutations are restricted to the session workspace and platform temporary roots; reads, network access, and process visibility are not confined. `DSH_PERMISSION_MODE` changes the process fallback. Stored General-settings permissions affect later Web sessions, not an already-open one.
|
||||
|
||||
`DSH_TOOLS_MODE` selects `native`, `code`, or `both` for the process; another value fails at boot. [`config/core-web.cordis.yml`](../config/core-web.cordis.yml) is an optional RL-compatible `--patch` overlay that pins native mode, renders only `DSH_SYSTEM_PROMPT` or `You are a helpful software engineer assistant.` as the system prompt, disables Workspace instructions and every Web runtime prompt contribution, and exposes only persistent `bash` and `str_replace_editor` while retaining the shipped host, browser, workspace, persistence, and permission composition.
|
||||
|
||||
`DSH_SYSTEM_PROMPT` is passed as the system-prompt [`persona`](../../../packages/core/system-prompt/README.md#config): complete `{{…}}` groups use that contract's strict variable interpolation rules and have no literal-brace escape; any set value, including an empty string, is authoritative and an empty value therefore removes the system prompt, while only an unset variable selects the fallback.
|
||||
`DSH_TOOLS_MODE` selects `native`, `code`, or `both` for the process; another value fails at boot. The shipped `minimal` agent preset keeps that deployment presentation, fixes the complete system prompt to `You are a helpful software engineer assistant.`, and composes only persistent `bash` plus `str_replace_editor`. Select 极简模式 when creating a Web session; every other prompt section and model-facing plugin remains absent from that agent while the shared browser, workspace, persistence, sandbox, and permission host stays in place.
|
||||
|
||||
## Shared deployment behavior
|
||||
|
||||
|
||||
@@ -59,9 +59,7 @@ dsh web --dump-config
|
||||
|
||||
新会话默认使用 `workspace-write` 权限预设。Bash 和文件系统修改仅限于会话 workspace 与平台临时根目录；读取、网络访问和进程可见性不受限制。`DSH_PERMISSION_MODE` 更改进程后备值。General settings 中存储的权限影响后续 Web 会话，不改变已打开的会话。
|
||||
|
||||
`DSH_TOOLS_MODE` 为进程选择 `native`、`code` 或 `both`；其他值会导致启动失败。[`config/core-web.cordis.yml`](../config/core-web.cordis.yml) 是可选的 RL 兼容 `--patch` overlay：它固定使用 `native` 模式，仅将 `DSH_SYSTEM_PROMPT` 或 `You are a helpful software engineer assistant.` 渲染为系统提示词，禁用 Workspace 指令与所有 Web 运行时提示词贡献，并且在保留随附宿主、浏览器、workspace、持久化和权限组合的同时，仅暴露持久 `bash` 和 `str_replace_editor`。
|
||||
|
||||
`DSH_SYSTEM_PROMPT` 会传给系统提示词的 [`persona`](../../../packages/core/system-prompt/README.md#config)：完整的 `{{…}}` 分组遵循该约定的严格变量插值规则，且无法转义为字面花括号；任何已设置的值（包括空字符串）都具有权威性，因此空值会移除系统提示词，只有未设置该变量时才会选择后备值。
|
||||
`DSH_TOOLS_MODE` 为进程选择 `native`、`code` 或 `both`；其他值会导致启动失败。随附的 `minimal` agent preset 会保留该部署的呈现方式，将完整系统提示词固定为 `You are a helpful software engineer assistant.`，并且仅组合持久 `bash` 和 `str_replace_editor`。创建 Web 会话时请选择极简模式；该 agent 不包含任何其他提示词段落或面向模型的插件，而共享的浏览器、workspace、持久化、沙箱与权限宿主保持不变。
|
||||
|
||||
## 共享部署行为
|
||||
|
||||
|
||||
@@ -9,7 +9,6 @@ import { afterEach, beforeEach, describe, expect, it } from 'vitest'
|
||||
/** Published-entry acceptance for argument errors, profile lifecycle, and boot-free config dumps. */
|
||||
const repoRoot = fileURLToPath(new URL('../../../', import.meta.url))
|
||||
const dshBin = join(repoRoot, 'apps/cli/lib/bin.js')
|
||||
const coreWebOverlay = fileURLToPath(new URL('../config/core-web.cordis.yml', import.meta.url))
|
||||
const invalidProvider = fileURLToPath(new URL('./fixtures/invalid-provider.cordis.yml', import.meta.url))
|
||||
|
||||
async function runBuiltBin(
|
||||
@@ -543,16 +542,5 @@ describe.skipIf(!existsSync(dshBin))('dsh BUILT bin (node lib/bin.js, no tsx)',
|
||||
expect(stdout).toContain(`patched by ${profilePatch}, ${overlay}`)
|
||||
expect(stderr).toContain('patch: entry "absent-row" not found')
|
||||
}, 30_000)
|
||||
|
||||
it('shows the RL Web patch disabling runtime surface context', async () => {
|
||||
const { stdout, code, stderr } = await runBuiltBin(
|
||||
['web', '--patch', coreWebOverlay, '--dump-config'],
|
||||
{ DSH_HOME: home },
|
||||
)
|
||||
expect(code).toBe(0)
|
||||
expect(stderr).toBe('')
|
||||
expect(stdout).toContain("name: '@deepseek-ai/dsh-web-app'")
|
||||
expect(stdout).toContain('surfaceContext: false')
|
||||
}, 30_000)
|
||||
})
|
||||
})
|
||||
|
||||
@@ -22,6 +22,15 @@ const BASE_PATCH = join(REPO_ROOT, 'packages/bundle/base/cordis.patch.yml')
|
||||
const WEB_PATCH = join(REPO_ROOT, 'packages/bundle/web-app/cordis.patch.yml')
|
||||
/** The installation anchor whose dependency surface the preset module fallback mirrors. */
|
||||
const INSTALL_ANCHOR = join(REPO_ROOT, 'apps/cli/package.json')
|
||||
const MINIMAL_PROMPT = 'You are a helpful software engineer assistant.'
|
||||
const MINIMAL_BASH_DESCRIPTION = `Run commands in a bash shell
|
||||
* When invoking this tool, the contents of the "command" parameter does NOT need to be XML-escaped.
|
||||
* You don't have access to the internet via this tool.
|
||||
* You do have access to a mirror of common linux and python packages via apt and pip.
|
||||
* State is persistent across command calls and discussions with the user.
|
||||
* To inspect a particular line range of a file, e.g. lines 10-25, try 'sed -n 10,25p /path/to/the/file'.
|
||||
* Please avoid commands that may produce a very large amount of output.
|
||||
* Please run long lived commands in the background, e.g. 'sleep 10 &' or start a server in the background.`
|
||||
|
||||
/**
|
||||
* Boot the shipped Web composition, minus the rows that would bind a port,
|
||||
@@ -143,14 +152,20 @@ describe('the shipped Web composition', () => {
|
||||
}
|
||||
})
|
||||
|
||||
it('composes exactly two tools from `minimal`', async () => {
|
||||
it('composes the exact RL prompt and two tools from `minimal`', async () => {
|
||||
const handle = await ctx.agents.create({
|
||||
sessionId: SessionId('preset-minimal'),
|
||||
setup: agentCtx => ctx.agentPresets.mount(agentCtx, 'minimal').then(() => undefined),
|
||||
})
|
||||
try {
|
||||
// Exactly what the preset lists — nothing arrives from the host.
|
||||
expect(toolNames(ctx, handle.agent)).toEqual(['bash', 'str_replace_editor'])
|
||||
const assembly = await ctx.systemPrompt.assemble({ scope: handle.agent })
|
||||
expect(assembly.sections).toEqual([
|
||||
{ name: 'deployment:persona', text: MINIMAL_PROMPT },
|
||||
])
|
||||
expect(assembly.tools.map(tool => tool.name)).toEqual(['bash', 'str_replace_editor'])
|
||||
expect(assembly.tools.find(tool => tool.name === 'bash')?.description).toBe(MINIMAL_BASH_DESCRIPTION)
|
||||
expect(JSON.stringify(assembly.tools.find(tool => tool.name === 'str_replace_editor')?.parameters))
|
||||
.toContain('Absolute path')
|
||||
} finally {
|
||||
await handle.dispose()
|
||||
}
|
||||
@@ -340,15 +355,14 @@ describe('the shipped Web composition', () => {
|
||||
expect(await readFile(path, 'utf8')).toBe(before)
|
||||
})
|
||||
|
||||
it('gives each session its own persona', async () => {
|
||||
it('gives each session its own complete persona', async () => {
|
||||
const handle = await ctx.agents.create({
|
||||
sessionId: SessionId('preset-persona'),
|
||||
setup: agentCtx => ctx.agentPresets.mount(agentCtx, 'minimal').then(() => undefined),
|
||||
})
|
||||
try {
|
||||
const assembly = await ctx.systemPrompt.assemble({ scope: handle.agent })
|
||||
expect(assembly.sections.find(section => section.name === 'deployment:persona')?.text)
|
||||
.toContain('You are a coding agent powered by')
|
||||
expect(assembly.sections).toEqual([{ name: 'deployment:persona', text: MINIMAL_PROMPT }])
|
||||
} finally {
|
||||
await handle.dispose()
|
||||
}
|
||||
|
||||
@@ -1,137 +0,0 @@
|
||||
import { writeFile } from 'node:fs/promises'
|
||||
import { join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { afterAll, beforeAll, describe, expect, it } from 'vitest'
|
||||
import type { AgentHandle } from '@deepseek-ai/dsh-agent'
|
||||
import { CallId, createUserMessage } from '@deepseek-ai/dsh-llm'
|
||||
import { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import { assertFixtureInventory, launchWebScaffold, type WebScaffold } from './scaffold.ts'
|
||||
|
||||
const CORE_WEB_OVERLAY = fileURLToPath(new URL('../../cli/config/core-web.cordis.yml', import.meta.url))
|
||||
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/core-web-profile', import.meta.url))
|
||||
const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
|
||||
const PROMPT = 'Reply exactly CORE_WEB_REQUEST_OK and stop.'
|
||||
|
||||
describe('core Web profile', () => {
|
||||
let scaffold: WebScaffold
|
||||
let agentHandle: AgentHandle
|
||||
|
||||
beforeAll(async () => {
|
||||
const systemPrompt = process.env.DSH_SYSTEM_PROMPT
|
||||
Reflect.deleteProperty(process.env, 'DSH_SYSTEM_PROMPT')
|
||||
try {
|
||||
scaffold = await launchWebScaffold({ extraOverlayPath: CORE_WEB_OVERLAY, replayFixture: FIXTURE })
|
||||
} finally {
|
||||
if (systemPrompt !== undefined) process.env.DSH_SYSTEM_PROMPT = systemPrompt
|
||||
}
|
||||
agentHandle = await scaffold.ctx.agents.create({
|
||||
sessionId: SessionId('core-web-profile-smoke'),
|
||||
meta: { cwd: scaffold.workspaceCwd },
|
||||
agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
})
|
||||
})
|
||||
|
||||
afterAll(async () => {
|
||||
const failures: unknown[] = []
|
||||
await agentHandle?.dispose().catch((error: unknown) => failures.push(error))
|
||||
await scaffold?.close().catch((error: unknown) => failures.push(error))
|
||||
if (failures.length === 1) throw failures[0]
|
||||
if (failures.length > 1) throw new AggregateError(failures, 'core Web profile smoke teardown failed')
|
||||
})
|
||||
|
||||
it('sends the RL prompt and tool schemas through a real request, then executes both tools', async () => {
|
||||
agentHandle.agent.followup(createUserMessage({
|
||||
content: [{ type: 'text', text: PROMPT }],
|
||||
source: { kind: 'user' },
|
||||
}))
|
||||
await agentHandle.agent.whenIdle()
|
||||
|
||||
const requestHeader = agentHandle.agent.session.requestHeader()
|
||||
if (requestHeader === undefined) throw new Error('the core Web agent issued no model request')
|
||||
|
||||
const seedPath = join(scaffold.workspaceCwd, 'profile-smoke.txt')
|
||||
await writeFile(seedPath, 'CORE_WEB_EDITOR_OK\n')
|
||||
const signal = new AbortController().signal
|
||||
const bash = await scaffold.ctx.tools.execute({
|
||||
signal,
|
||||
callId: CallId('core-web-bash-smoke'),
|
||||
name: 'bash',
|
||||
arguments: { command: "printf 'CORE_WEB_BASH_OK\\n'" },
|
||||
agent: agentHandle.agent,
|
||||
})
|
||||
const editor = await scaffold.ctx.tools.execute({
|
||||
signal,
|
||||
callId: CallId('core-web-editor-smoke'),
|
||||
name: 'str_replace_editor',
|
||||
arguments: { command: 'view', path: seedPath },
|
||||
agent: agentHandle.agent,
|
||||
})
|
||||
|
||||
const text = (result: typeof bash): string => result.content
|
||||
.filter(block => block.type === 'text')
|
||||
.map(block => block.text)
|
||||
.join('')
|
||||
.replaceAll(scaffold.workspaceCwd, '{{cwd}}')
|
||||
.trimEnd()
|
||||
|
||||
expect({
|
||||
prompt: requestHeader.system,
|
||||
tools: requestHeader.tools?.map(tool => tool.name),
|
||||
bash: text(bash),
|
||||
editor: text(editor),
|
||||
}).toMatchInlineSnapshot(`
|
||||
{
|
||||
"bash": "CORE_WEB_BASH_OK",
|
||||
"editor": "Here's the content of {{cwd}}/profile-smoke.txt with line numbers (which has a total of 2 lines):
|
||||
1 CORE_WEB_EDITOR_OK
|
||||
2",
|
||||
"prompt": "You are a helpful software engineer assistant.",
|
||||
"tools": [
|
||||
"bash",
|
||||
"str_replace_editor",
|
||||
],
|
||||
}
|
||||
`)
|
||||
expect(requestHeader.tools).toEqual(scaffold.ctx.tools.schemas(agentHandle.agent))
|
||||
|
||||
const entries = [...scaffold.ctx.loader.entries()]
|
||||
expect(entries.find(entry => entry.options.id === 'persistent-bash')?.fiber).toBeDefined()
|
||||
expect(entries.find(entry => entry.options.id === 'pty-local')?.fiber).toBeDefined()
|
||||
expect(entries.find(entry => entry.options.id === 'str-replace-editor')?.fiber).toBeDefined()
|
||||
expect(entries.find(entry => entry.options.id === 'web-runtime')?.fiber).toBeDefined()
|
||||
expect(entries.find(entry => entry.options.id === 'workspace-context')?.fiber).toBeUndefined()
|
||||
await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl'])
|
||||
})
|
||||
|
||||
it('uses DSH_SYSTEM_PROMPT as the complete prompt when configured', async () => {
|
||||
const previous = process.env.DSH_SYSTEM_PROMPT
|
||||
process.env.DSH_SYSTEM_PROMPT = 'RL prompt override'
|
||||
let overrideScaffold: WebScaffold | undefined
|
||||
let overrideAgent: AgentHandle | undefined
|
||||
try {
|
||||
overrideScaffold = await launchWebScaffold({ extraOverlayPath: CORE_WEB_OVERLAY, replayFixture: FIXTURE })
|
||||
overrideAgent = await overrideScaffold.ctx.agents.create({
|
||||
sessionId: SessionId('core-web-profile-override'),
|
||||
meta: { cwd: overrideScaffold.workspaceCwd },
|
||||
agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
})
|
||||
overrideAgent.agent.followup(createUserMessage({
|
||||
content: [{ type: 'text', text: PROMPT }],
|
||||
source: { kind: 'user' },
|
||||
}))
|
||||
await overrideAgent.agent.whenIdle()
|
||||
expect(overrideAgent.agent.session.requestHeader()?.system).toBe('RL prompt override')
|
||||
} finally {
|
||||
try {
|
||||
await overrideAgent?.dispose()
|
||||
} finally {
|
||||
try {
|
||||
await overrideScaffold?.close()
|
||||
} finally {
|
||||
if (previous === undefined) Reflect.deleteProperty(process.env, 'DSH_SYSTEM_PROMPT')
|
||||
else process.env.DSH_SYSTEM_PROMPT = previous
|
||||
}
|
||||
}
|
||||
}
|
||||
})
|
||||
})
|
||||
115
apps/web/tests/minimal-preset.snapshot.ts
Normal file
115
apps/web/tests/minimal-preset.snapshot.ts
Normal file
@@ -0,0 +1,115 @@
|
||||
import { mkdir, writeFile } from 'node:fs/promises'
|
||||
import { join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import { afterAll, beforeAll, describe, expect, it } from 'vitest'
|
||||
import type { AgentHandle } from '@deepseek-ai/dsh-agent'
|
||||
import { CallId, createUserMessage } from '@deepseek-ai/dsh-llm'
|
||||
import { SessionId } from '@deepseek-ai/dsh-session'
|
||||
import type {} from '@deepseek-ai/dsh-agent-presets'
|
||||
import type {} from '@deepseek-ai/dsh-system-prompt'
|
||||
import { assertFixtureInventory, launchWebScaffold, type WebScaffold } from './scaffold.ts'
|
||||
|
||||
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/minimal-preset', import.meta.url))
|
||||
const FIXTURE = join(SNAPSHOT_DIR, 'session.jsonl')
|
||||
const PROMPT = 'Reply exactly MINIMAL_PRESET_REQUEST_OK and stop.'
|
||||
|
||||
describe('minimal agent preset', () => {
|
||||
let scaffold: WebScaffold
|
||||
let agentHandle: AgentHandle
|
||||
let disposeInjectedPrompt: () => void
|
||||
|
||||
beforeAll(async () => {
|
||||
scaffold = await launchWebScaffold({ replayFixture: FIXTURE })
|
||||
disposeInjectedPrompt = scaffold.ctx.systemPrompt.section({
|
||||
name: 'test:injected-prompt',
|
||||
order: 999,
|
||||
text: 'THIS TEXT MUST NOT REACH THE MODEL.',
|
||||
})
|
||||
agentHandle = await scaffold.ctx.agents.create({
|
||||
sessionId: SessionId('minimal-preset-smoke'),
|
||||
meta: { cwd: scaffold.workspaceCwd, agentPreset: 'minimal' },
|
||||
agentOptions: { provider: 'deepseek-official', model: 'deepseek-v4-flash' },
|
||||
setup: agentCtx => scaffold.ctx.agentPresets.mount(agentCtx, 'minimal').then(() => undefined),
|
||||
})
|
||||
})
|
||||
|
||||
afterAll(async () => {
|
||||
const failures: unknown[] = []
|
||||
await agentHandle?.dispose().catch((error: unknown) => failures.push(error))
|
||||
try {
|
||||
disposeInjectedPrompt?.()
|
||||
} catch (error: unknown) {
|
||||
failures.push(error)
|
||||
}
|
||||
await scaffold?.close().catch((error: unknown) => failures.push(error))
|
||||
if (failures.length === 1) throw failures[0]
|
||||
if (failures.length > 1) throw new AggregateError(failures, 'minimal preset smoke teardown failed')
|
||||
})
|
||||
|
||||
it('sends the exact RL prompt and schemas, then executes the persistent shell and editor', async () => {
|
||||
agentHandle.agent.followup(createUserMessage({
|
||||
content: [{ type: 'text', text: PROMPT }],
|
||||
source: { kind: 'user' },
|
||||
}))
|
||||
await agentHandle.agent.whenIdle()
|
||||
|
||||
const requestHeader = agentHandle.agent.session.requestHeader()
|
||||
if (requestHeader === undefined) throw new Error('the minimal agent issued no model request')
|
||||
|
||||
const stateDir = join(scaffold.workspaceCwd, 'persistent-state')
|
||||
await mkdir(stateDir)
|
||||
const signal = new AbortController().signal
|
||||
await scaffold.ctx.tools.execute({
|
||||
signal,
|
||||
callId: CallId('minimal-bash-state-setup'),
|
||||
name: 'bash',
|
||||
arguments: { command: `cd ${JSON.stringify(stateDir)} && export DSH_MINIMAL_STATE=PERSISTED` },
|
||||
agent: agentHandle.agent,
|
||||
})
|
||||
const bash = await scaffold.ctx.tools.execute({
|
||||
signal,
|
||||
callId: CallId('minimal-bash-state-read'),
|
||||
name: 'bash',
|
||||
arguments: { command: 'printf \'%s:%s\n\' "$DSH_MINIMAL_STATE" "$PWD"' },
|
||||
agent: agentHandle.agent,
|
||||
})
|
||||
const seedPath = join(scaffold.workspaceCwd, 'preset-smoke.txt')
|
||||
await writeFile(seedPath, 'MINIMAL_EDITOR_OK\n')
|
||||
const editor = await scaffold.ctx.tools.execute({
|
||||
signal,
|
||||
callId: CallId('minimal-editor-smoke'),
|
||||
name: 'str_replace_editor',
|
||||
arguments: { command: 'view', path: seedPath },
|
||||
agent: agentHandle.agent,
|
||||
})
|
||||
|
||||
const text = (result: typeof bash): string => result.content
|
||||
.filter(block => block.type === 'text')
|
||||
.map(block => block.text)
|
||||
.join('')
|
||||
.replaceAll(scaffold.workspaceCwd, '{{cwd}}')
|
||||
.trimEnd()
|
||||
|
||||
expect({
|
||||
prompt: requestHeader.system,
|
||||
tools: requestHeader.tools?.map(tool => tool.name),
|
||||
bash: text(bash),
|
||||
editor: text(editor),
|
||||
}).toMatchInlineSnapshot(`
|
||||
{
|
||||
"bash": "PERSISTED:{{cwd}}/persistent-state",
|
||||
"editor": "Here's the content of {{cwd}}/preset-smoke.txt with line numbers (which has a total of 2 lines):
|
||||
1 MINIMAL_EDITOR_OK
|
||||
2",
|
||||
"prompt": "You are a helpful software engineer assistant.",
|
||||
"tools": [
|
||||
"bash",
|
||||
"str_replace_editor",
|
||||
],
|
||||
}
|
||||
`)
|
||||
expect(requestHeader.tools?.toSorted((left, right) => left.name.localeCompare(right.name)))
|
||||
.toEqual(scaffold.ctx.tools.schemas(agentHandle.agent).toSorted((left, right) => left.name.localeCompare(right.name)))
|
||||
await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl'])
|
||||
})
|
||||
})
|
||||
@@ -1,7 +1,7 @@
|
||||
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1785974400000,"cwd":"{{cwd}}"}
|
||||
{"type":"user/message","seq":0,"time":1785974400001,"data":{"content":[{"type":"text","text":"Reply exactly CORE_WEB_REQUEST_OK and stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"session","version":0,"id":"{{sessionId}}","createdAt":1785974400000,"cwd":"{{cwd}}","agentPreset":"minimal"}
|
||||
{"type":"user/message","seq":0,"time":1785974400001,"data":{"content":[{"type":"text","text":"Reply exactly MINIMAL_PRESET_REQUEST_OK and stop."}],"source":{"kind":"user","rpcId":"{{rpcId}}"}},"surfaceOp":"append"}
|
||||
{"type":"assistant/chunk","seq":1,"time":1785974400002,"data":{"turn":1,"step":1,"chunk":{"type":"block-start","index":0,"blockType":"text"}}}
|
||||
{"type":"assistant/chunk","seq":2,"time":1785974400003,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"CORE_WEB_REQUEST_OK"}}}
|
||||
{"type":"assistant/chunk","seq":3,"time":1785974400004,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"CORE_WEB_REQUEST_OK"}}}}
|
||||
{"type":"assistant/chunk","seq":2,"time":1785974400003,"data":{"turn":1,"step":1,"chunk":{"type":"text-delta","index":0,"text":"MINIMAL_PRESET_REQUEST_OK"}}}
|
||||
{"type":"assistant/chunk","seq":3,"time":1785974400004,"data":{"turn":1,"step":1,"chunk":{"type":"block-end","index":0,"block":{"type":"text","text":"MINIMAL_PRESET_REQUEST_OK"}}}}
|
||||
{"type":"assistant/chunk","seq":4,"time":1785974400005,"data":{"turn":1,"step":1,"chunk":{"type":"usage","usage":{"inputTokens":10,"outputTokens":4}}}}
|
||||
{"type":"assistant/chunk","seq":5,"time":1785974400006,"data":{"turn":1,"step":1,"chunk":{"type":"finish","reason":{"kind":"stop"}}}}
|
||||
@@ -24,7 +24,7 @@
|
||||
"exclude": [
|
||||
"tests/scaffold.ts",
|
||||
"tests/scaffold-hermetic.e2e.ts",
|
||||
"tests/core-web-profile.snapshot.ts",
|
||||
"tests/minimal-preset.snapshot.ts",
|
||||
"tests/live-interactions.e2e.ts",
|
||||
"tests/question-composer.e2e.ts",
|
||||
"tests/approval-composer.e2e.ts",
|
||||
|
||||
Reference in New Issue
Block a user