Merge branch 'stack/agent-profiles-4-settings' into stack/agent-profiles-5-web-ui

This commit is contained in:
Yichen Jiang
2026-08-07 01:01:50 +08:00
188 changed files with 8407 additions and 654 deletions

View File

@@ -1,6 +1,27 @@
# Opt-in two-tool profile over the shipped Web composition. The default native
# model surface is exactly persistent `bash` plus `str_replace_editor`; the
# Web host, browser shell, workspace, persistence, and permission stack remain.
# 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.

View File

@@ -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: 62275139809364d80296433e804ade3d447f37e6
README.zh.md: e508caaf05622c0c177eaacd070978368ff84af3
README.md: 8b8a0e7dbebafedd6a4f8d988adb3fd11c7bd026
README.zh.md: d1d6d5a594596a8be5db30021163f0fcea4a95bf

View File

@@ -53,7 +53,9 @@ 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 `--patch` overlay that reduces the native model surface to persistent `bash` and `str_replace_editor` while retaining the shipped host, browser, workspace, persistence, and permission composition.
`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 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.
## Shared deployment behavior

View File

@@ -53,7 +53,9 @@ 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``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 `--patch` overlay它在保留随附宿主、浏览器、workspace、持久化和权限组合的同时把原生模型 surface 缩减为持久 `bash``str_replace_editor`
`DSH_TOOLS_MODE` 为进程选择 `native``code``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固定使用 `native` 模式,仅将 `DSH_SYSTEM_PROMPT``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``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 `{{…}}` 分组遵循该契约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。
## 共享部署行为

View File

@@ -95,6 +95,9 @@ export function prepareProfile(name: string, userLayer = true): Profile {
return profile
}
/** Read-only row index of a profile composition before launcher flag patches. */
export type ProfileRows = ReadonlyMap<string, { name?: string; config?: unknown }>
/** One profile's patch layers (application order) and the row index of its pre-flag composition. */
interface ComposedProfile {
profile: Profile
@@ -109,7 +112,7 @@ interface ComposedProfile {
* for flag merges and row checks. Flag patches must not insert rows the
* launcher consults here (they only override values and insert dev glue).
*/
rows: Map<string, { name?: string; config?: unknown }>
rows: ProfileRows
}
/** The full patch stack of one composed profile, in application order. */
@@ -155,11 +158,11 @@ export interface RunProfileOptions {
/** `--patch` overlay paths, in argv order. */
patchFiles: readonly string[]
/** Launcher hook turning the pre-flag composed rows into flag patches (the web alias's flag family). */
deriveFlagPatches?: (rows: ComposedProfile['rows']) => PatchOptions[]
deriveFlagPatches?: (rows: ProfileRows) => PatchOptions[]
/** One-shot task text; requires the composition to mount the headless runner row. */
task?: string
/** Surface setup registered after Loader installation and before any config-tree entry mounts. */
prepare?: (ctx: Context) => Promise<void> | void
prepare?: (ctx: Context, rows: ProfileRows) => Promise<void> | void
}
/**
@@ -231,7 +234,7 @@ export async function runProfile(options: RunProfileOptions): Promise<{ ctx: Con
}
hostCtx.provide('headlessIo', io)
}
await options.prepare?.(hostCtx)
await options.prepare?.(hostCtx, composed.rows)
})
app.current = ctx
// A surface can dispose the whole tree while startup was still in flight

View File

@@ -14,7 +14,7 @@ import { dshHomePath } from '@deepseek-ai/dsh-paths'
import type { Context } from 'cordis'
import type { PatchOptions } from '@cordisjs/plugin-include'
import { addHarnessSourceSection } from '@deepseek-ai/dsh-app-boot'
import { runProfile } from './profile-boot.ts'
import { runProfile, type ProfileRows } from './profile-boot.ts'
const SOURCE_ROOT = fileURLToPath(new URL('../../..', import.meta.url))
@@ -78,7 +78,7 @@ export interface WebFlags {
* @returns the flag patch list, in application order.
*/
function deriveWebFlagPatches(
rows: Map<string, { name?: string; config?: unknown }>,
rows: ProfileRows,
flags: WebFlags,
): PatchOptions[] {
const overrides = new Map<string, Record<string, unknown>>()
@@ -122,6 +122,18 @@ function deriveWebFlagPatches(
return patches
}
/**
* Whether the composed Web runtime keeps its model- and shell-visible surface
* context. The bundle schema defaults the field to true, so only an explicit
* false suppresses both the bundle contributions and the launcher-owned
* source-checkout section.
* @param rows - the composed Web profile rows before launcher flag patches.
* @returns true unless the web-runtime row explicitly disables surface context.
*/
export function webSurfaceContextEnabled(rows: ProfileRows): boolean {
return (rows.get('web-runtime')?.config as { surfaceContext?: boolean } | undefined)?.surfaceContext !== false
}
/**
* Serve the browser UI from the web profile. Host/port/workspace-root flags
* are passed through only when given (absent, the composed profile values
@@ -135,7 +147,8 @@ export async function runWeb(flags: WebFlags): Promise<void> {
profile: 'web',
patchFiles: flags.patches,
deriveFlagPatches: rows => deriveWebFlagPatches(rows, flags),
prepare: (ctx: Context) => {
prepare: (ctx: Context, rows: ProfileRows) => {
if (!webSurfaceContextEnabled(rows)) return
ctx.inject(['systemPrompt'], (promptCtx) => {
addHarnessSourceSection(promptCtx, SOURCE_ROOT)
})

View File

@@ -8,6 +8,7 @@ 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(
@@ -367,5 +368,16 @@ 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)
})
})

View File

@@ -1,7 +1,7 @@
/** Single-sample LAN-trust resolution for the /api browser-trust fence (`resolveLanTrust`). */
import { describe, expect, it, vi } from 'vitest'
import { resolveLanTrust } from '../src/web.ts'
import { resolveLanTrust, webSurfaceContextEnabled } from '../src/web.ts'
vi.mock('node:os', () => ({
networkInterfaces: () => ({
@@ -31,3 +31,15 @@ describe('resolveLanTrust', () => {
expect(resolveLanTrust(undefined, ['lab.internal'])).toEqual({ lanAddresses: [], trustedHosts: ['lab.internal'] })
})
})
describe('webSurfaceContextEnabled', () => {
it('defaults to enabled and honors an explicit complete-prompt disable', () => {
expect(webSurfaceContextEnabled(new Map())).toBe(true)
expect(webSurfaceContextEnabled(new Map([
['web-runtime', { config: { mode: 'production' } }],
]))).toBe(true)
expect(webSurfaceContextEnabled(new Map([
['web-runtime', { config: { surfaceContext: false } }],
]))).toBe(false)
})
})

View File

@@ -3,21 +3,27 @@ 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 } from '@deepseek-ai/dsh-llm'
import { CallId, createUserMessage } from '@deepseek-ai/dsh-llm'
import { SessionId } from '@deepseek-ai/dsh-session'
import { launchWebScaffold, type WebScaffold } from './scaffold.ts'
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 () => {
scaffold = await launchWebScaffold({
extraOverlayPath: CORE_WEB_OVERLAY,
toolsMode: 'native',
})
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 },
@@ -33,7 +39,16 @@ describe('core Web profile', () => {
if (failures.length > 1) throw new AggregateError(failures, 'core Web profile smoke teardown failed')
})
it('boots and executes both tools through the shipped Web composition', async () => {
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
@@ -60,7 +75,8 @@ describe('core Web profile', () => {
.trimEnd()
expect({
tools: scaffold.ctx.tools.schemas().map(tool => tool.name),
prompt: requestHeader.system,
tools: requestHeader.tools?.map(tool => tool.name),
bash: text(bash),
editor: text(editor),
}).toMatchInlineSnapshot(`
@@ -69,16 +85,53 @@ describe('core Web profile', () => {
"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
}
}
}
})
})

View File

@@ -161,6 +161,58 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
expect(tripwire.pageErrors).toEqual([])
}, 60_000)
it('never paints the takeover chrome on a configured reload, even with the settings join held open', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-onboarding-configured-reload'))
// Regression pin for the reload white flash: both steps are satisfied
// (welcome acknowledged, credential configured), yet each must LOAD its
// private join before it can decide not to show. The chrome lives inside
// the step (OnboardingSurface), so the deciding window paints and blocks
// nothing. Holding settings.describe widens that window from loopback
// RTT scale to a deterministic hundreds of milliseconds, removing all
// timing dependence from the sampler assertions below.
//
// The sampler init script persists across this shared page's later
// navigations (init scripts re-run per navigation); that stays harmless
// because no later scenario in this file legitimately shows the
// takeover, and only this test reads __takeoverSightings.
await page.addInitScript(() => {
const sightings: string[] = []
;(window as unknown as { __takeoverSightings: string[] }).__takeoverSightings = sightings
setInterval(() => {
if (document.querySelector('[class*="onboardingStage"], [class*="onboardingMask"]') !== null) {
sightings.push('chrome')
}
if (document.getElementById('root')?.inert === true) sightings.push('inert')
}, 8)
})
// EVERY settings.describe issued before the release is held — not just
// the first — so the pin cannot silently collapse back to loopback
// timing if a second boot-time consumer of the join ever appears.
let released = false
const heldRoutes: Array<() => void> = []
const releaseDescribe = (): void => {
released = true
for (const resolve of heldRoutes.splice(0)) resolve()
}
await page.route('**/api/settings.describe', async (route) => {
if (!released) await new Promise<void>((resolve) => { heldRoutes.push(resolve) })
await route.continue()
})
const warningsBefore = tripwire.warnings.length
await page.reload({ waitUntil: 'commit' })
await page.waitForSelector('[class*="frame"]', { timeout: 15_000 })
// The app is painted and interactive while the steps are still deciding.
await page.waitForTimeout(600)
releaseDescribe()
await page.waitForTimeout(400)
await page.unroute('**/api/settings.describe')
acknowledgeReloadConnectionLoss(tripwire, warningsBefore)
expect(await page.evaluate(() =>
(window as unknown as { __takeoverSightings: string[] }).__takeoverSightings)).toEqual([])
expect(await page.locator('[class*="onboardingStage"]').count()).toBe(0)
expect(tripwire.pageErrors).toEqual([])
}, 60_000)
it('configures arbitrary DeepSeek models and prompts after the selected model is removed', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-onboarding-deepseek-models'))
// Opened here rather than inherited: the credential test reloads the page

View File

@@ -34,7 +34,13 @@ import Loader from '@cordisjs/plugin-loader'
import Include, { type PatchOptions } from '@cordisjs/plugin-include'
import Group from '@cordisjs/plugin-group'
import { scrubRequestHeaders } from '@deepseek-ai/dsh-acp-snapshot'
import { assertEntriesLoaded, loadOverlayPatches } from '@deepseek-ai/dsh-app-boot'
import {
addHarnessSourceSection,
assertEntriesLoaded,
composeEntries,
healProfilesModuleFallback,
loadOverlayPatches,
} from '@deepseek-ai/dsh-app-boot'
import { dshHomePath } from '@deepseek-ai/dsh-paths'
import {
WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_SETTINGS_NAMESPACE, WELCOME_NOTICE_VERSION,
@@ -55,7 +61,6 @@ import * as ToolCordis from '@deepseek-ai/dsh-tool-cordis'
// Empty type imports carry the httpServer/agents/sessionPersistence Context merges.
import type {} from '@deepseek-ai/dsh-host-webserver'
import type {} from '@deepseek-ai/dsh-agent'
import { addHarnessSourceSection, healProfilesModuleFallback } from '@deepseek-ai/dsh-app-boot'
import { REPO_ROOT, requireDist } from './support.ts'
/** Snapshot mode for the lane, from $DSH_SNAPSHOT (same vocabulary as the other snapshot suites). */
@@ -255,6 +260,11 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
const extraOverlayPatches = options.extraOverlayPath === undefined
? []
: loadOverlayPatches('web e2e scaffold', options.extraOverlayPath)
const composedRows = composeEntries([basePatches, surfacePatches, extraOverlayPatches])
const webRuntimeConfig = composedRows.find(row => row.id === 'web-runtime')?.config as {
surfaceContext?: boolean
} | undefined
const surfaceContext = webRuntimeConfig?.surfaceContext !== false
const patches: PatchOptions[] = [
...basePatches,
...surfacePatches,
@@ -305,7 +315,9 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
},
// The bundle's web-runtime row resolves the same built dist under test
// (apps/web IS @deepseek-ai/dsh-frontend); only the URL line is silenced.
{ id: 'web-runtime', config: { mode: 'production', printUrl: false } },
// Preserve the composed surface-context choice because a patch replaces
// the row's complete config.
{ id: 'web-runtime', config: { mode: 'production', printUrl: false, surfaceContext } },
...options.remoteAuthority === undefined
? []
: [{ id: 'connection', config: { trustedHosts: [options.remoteAuthority] } }],
@@ -366,7 +378,9 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
// The shipped CLI deliberately has no dependency on this opt-in package.
// Keep the Loader row real without broadening the product installation.
if (options.cordisTools === true) ctx.loader.builtins['tool-cordis'] = ToolCordis
ctx.inject(['systemPrompt'], (promptCtx) => { addHarnessSourceSection(promptCtx, REPO_ROOT) })
if (surfaceContext) {
ctx.inject(['systemPrompt'], (promptCtx) => { addHarnessSourceSection(promptCtx, REPO_ROOT) })
}
await ctx.loader.create({
name: 'cordis:include',
config: { path: pathToFileURL(rootConfig).href, patches },

View File

@@ -0,0 +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":"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":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"}}}}