fix(web): orient agents to the running GUI
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each
|
||||
# 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
|
||||
README.md: 42d2a9641cf5d497c9aae45d9f60fce4498addb9
|
||||
README.zh.md: 0a62f8bb72e2cf2dbe045d28b81768bf4df800de
|
||||
# pnpm run verify-translation-pairing --write apps/cli/README.md
|
||||
README.md: 87cf1597fbb1ce91a7d61f912c42b0d6a68b2eea
|
||||
README.zh.md: b3743f57a4dafda71e437a04ee0148b32dba2dca
|
||||
|
||||
@@ -14,7 +14,7 @@ The TUI surface:
|
||||
- tells the agent where its own source lives: after boot it adds a prompt section naming this harness checkout, resolved from the launcher's real path so it holds under a PATH symlink and an arbitrary cwd, so the self-referential `cordis` toolset can read and modify it;
|
||||
- applies the personal overlay from `~/.dsh` (see [app-boot's Personal config](../../packages/ui/app-boot/README.md#personal-config)): `.env` fills environment gaps (ambient > project `.env` > personal `.env`), `config.yaml` patches the booted tree.
|
||||
|
||||
The Web and headless surfaces boot one shared composition (`cordis.yml`): both treat the invoking directory as the default project and Workspace root, create named Workspaces beneath that root unless `--workspace-root <path>` overrides it, load applicable `AGENTS.md`/`CLAUDE.md` instructions into each agent-loop request prefix with a 65,536-byte render budget, and opt into first-message model titles. Headless differs only in listening on an OS-assigned port (parallel `dsh -p` runs never collide; the stderr-printed URL opens the live session in a browser). Both need the frontend dist and client bundles built (`pnpm run build && pnpm run build:web`).
|
||||
The Web and headless surfaces boot one shared composition (`cordis.yml`): both tell the coding agent its model and session working directory, treat the invoking directory as the default project and Workspace root, create named Workspaces beneath that root unless `--workspace-root <path>` overrides it, load applicable `AGENTS.md`/`CLAUDE.md` instructions into each agent-loop request prefix with a 65,536-byte render budget, and opt into first-message model titles. Web additionally names the DeepSeek Harness Web GUI as the interaction surface and this checkout as its own source location; references such as “this page” therefore identify the GUI without claiming access to implicit DOM, route, or screenshot state. Headless differs only in listening on an OS-assigned port (parallel `dsh -p` runs never collide; the stderr-printed URL opens the live session in a browser). Both need the frontend dist and client bundles built (`pnpm run build && pnpm run build:web`).
|
||||
|
||||
`DSH_TOOLS_MODE` selects the tool presentation mode for the whole Web/headless process: `native` (the schema default when unset), `code` (the `run_code`-only Code Mode wire), or `both`; any other value fails loud at boot through the `dsh-tools` config schema. It is a TEMPORARY seam — process-wide because Loader composition is static — and is removed once the web UI owns per-session tool-mode selection; the TUI surface ignores it (its config tree pins its own mode).
|
||||
|
||||
|
||||
@@ -14,7 +14,7 @@ TUI 界面:
|
||||
- 告知 agent 自身源码所在位置:启动后添加一个命名此 harness checkout 的提示词段。该路径从启动器的真实路径解析,因此在 PATH 符号链接和任意 cwd 下仍然有效,使自指的 `cordis` 工具集可以读取并修改它;
|
||||
- 应用 `~/.dsh` 中的个人覆盖(参见 [app-boot 的个人配置](../../packages/ui/app-boot/README.md#personal-config)):`.env` 填补环境缺口(环境中已有的值 > 项目 `.env` > 个人 `.env`),`config.yaml` 则修补已启动的树。
|
||||
|
||||
Web 和无头界面启动同一个共享组合(`cordis.yml`):两者都将调用目录视为默认项目和 Workspace 根目录,除非通过 `--workspace-root <path>` 覆盖,否则会在该根目录下创建具名 Workspace;它们会把适用的 `AGENTS.md`/`CLAUDE.md` 指令加载到每个 agent-loop 请求前缀中,渲染预算为 65,536 字节,并选用首条消息模型标题。无头界面唯一的差异是监听操作系统分配的端口(并行 `dsh -p` 运行绝不冲突;stderr 打印的 URL 会在浏览器中打开实时会话)。两者都需要先构建前端 dist 和客户端 bundle(`pnpm run build && pnpm run build:web`)。
|
||||
Web 和无头界面启动同一个共享组合(`cordis.yml`):两者都会告知编码 agent 所用模型和会话工作目录,将调用目录视为默认项目和 Workspace 根目录,除非通过 `--workspace-root <path>` 覆盖,否则会在该根目录下创建具名 Workspace;它们会把适用的 `AGENTS.md`/`CLAUDE.md` 指令加载到每个 agent-loop 请求前缀中,渲染预算为 65,536 字节,并选用首条消息模型标题。Web 还会明确说明交互界面是 DeepSeek Harness Web GUI,并把当前 checkout 标记为自身源码位置;因此,「这个页面」等表述会指向该 GUI,但 agent 不会声称可以访问未显式提供的 DOM、路由或截图状态。无头界面唯一的差异是监听操作系统分配的端口(并行 `dsh -p` 运行绝不冲突;stderr 打印的 URL 会在浏览器中打开实时会话)。两者都需要先构建前端 dist 和客户端 bundle(`pnpm run build && pnpm run build:web`)。
|
||||
|
||||
`DSH_TOOLS_MODE` 为整个 Web/无头进程选择工具呈现模式:可选值为 `native`(未设置时的 schema 默认值)、`code`(仅含 `run_code` 的 Code Mode 协议接口)或 `both`;任何其他值都会经由 `dsh-tools` 配置 schema 在启动时明确报错。它是一个临时 seam:Loader 组合是静态的,因此该设置作用于整个进程;待 Web UI 负责逐会话工具模式选择后便会移除。TUI 界面会忽略该变量(其配置树固定了自身模式)。
|
||||
|
||||
|
||||
@@ -40,7 +40,8 @@
|
||||
- id: system-prompt
|
||||
name: '@deepseek-ai/dsh-system-prompt'
|
||||
config:
|
||||
persona: ''
|
||||
persona: >-
|
||||
You are a coding agent powered by the {{model}} model. Your working directory is {{cwd}}.
|
||||
|
||||
- id: tools
|
||||
name: '@deepseek-ai/dsh-tools'
|
||||
|
||||
@@ -8,9 +8,32 @@
|
||||
|
||||
import { networkInterfaces } from 'node:os'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import type { Context } from 'cordis'
|
||||
import { addHarnessSourceSection } from '@deepseek-ai/dsh-app-boot'
|
||||
import type {} from '@deepseek-ai/dsh-system-prompt'
|
||||
import { AppCLIEntry } from './app-cli-entry.ts'
|
||||
|
||||
const CONFIG_PATH = fileURLToPath(new URL('../cordis.yml', import.meta.url))
|
||||
const SOURCE_ROOT = fileURLToPath(new URL('../../..', import.meta.url))
|
||||
|
||||
/** Stable model-visible orientation for sessions created through `dsh web`. */
|
||||
export const WEB_SURFACE_PROMPT = 'You are interacting with the user through the DeepSeek Harness Web GUI. '
|
||||
+ 'When the user refers to "this page", "this GUI", or "this app" without naming another target, they mean this GUI. '
|
||||
+ 'The browser provides no implicit DOM, route, or screenshot context.'
|
||||
|
||||
/**
|
||||
* Add the launcher-owned source location and Web-surface orientation after the
|
||||
* shared config tree settles. The request header logs both sections with every
|
||||
* model-visible prompt.
|
||||
* @param ctx - settled Web application context.
|
||||
* @param sourceRoot - absolute checkout root resolved from the launcher module.
|
||||
*/
|
||||
export function installWebPromptContext(ctx: Context, sourceRoot: string): void {
|
||||
const systemPrompt = ctx.get('systemPrompt')
|
||||
if (systemPrompt === undefined) throw new Error('dsh web: systemPrompt service missing after settled boot')
|
||||
addHarnessSourceSection(ctx, sourceRoot)
|
||||
systemPrompt.section({ name: 'app:web-surface', order: -98, text: WEB_SURFACE_PROMPT })
|
||||
}
|
||||
|
||||
// Display-only mirrors of the webserver schema's allowed hosts: the loopback
|
||||
// address the local URL always prints, and the all-interfaces value that gates
|
||||
@@ -40,6 +63,7 @@ export async function runWeb(
|
||||
...workspaceRoot !== undefined && { workspaceRoot },
|
||||
})
|
||||
const { ctx, port: boundPort } = await entry.run()
|
||||
installWebPromptContext(ctx, SOURCE_ROOT)
|
||||
|
||||
let exiting = false
|
||||
const shutdown = (code: number): void => {
|
||||
|
||||
@@ -9,20 +9,22 @@
|
||||
// Record: DSH_SNAPSHOT=record rewrites session.jsonl, then a keyless
|
||||
// DSH_SNAPSHOT=refresh regenerates ui.expected.md.
|
||||
import { readFile } from 'node:fs/promises'
|
||||
import { join } from 'node:path'
|
||||
import { fileURLToPath } from 'node:url'
|
||||
import type { Browser, Page } from 'playwright'
|
||||
import { chromium } from 'playwright'
|
||||
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
|
||||
import type { SessionEvent } from '@deepseek-ai/dsh-session'
|
||||
import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session'
|
||||
import {
|
||||
assertFixtureInventory, captureStableAria, compareOrRefreshGolden, fixtureUserPrompts,
|
||||
launchWebScaffold, recordFixture, watchConsole, webSnapshotMode, type WebScaffold,
|
||||
} from './scaffold.ts'
|
||||
import { connectFreshWorkspace, saveFailureShot } from './support.ts'
|
||||
import { connectFreshWorkspace, REPO_ROOT, saveFailureShot } from './support.ts'
|
||||
|
||||
const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/fresh-round-trip', import.meta.url))
|
||||
const FIXTURE = fileURLToPath(new URL('./snapshots/fresh-round-trip/session.jsonl', import.meta.url))
|
||||
const UI_EXPECTED = fileURLToPath(new URL('./snapshots/fresh-round-trip/ui.expected.md', import.meta.url))
|
||||
const SYSTEM_PROMPT_EXPECTED = fileURLToPath(new URL('./snapshots/fresh-round-trip/system-prompt.expected.md', import.meta.url))
|
||||
const MODE = webSnapshotMode()
|
||||
|
||||
// The scenario's one drive prompt. Record sends it; replay asserts the
|
||||
@@ -35,6 +37,7 @@ describe('web e2e: fresh round trip through the real assembly', () => {
|
||||
let browser: Browser
|
||||
let page: Page
|
||||
let tripwire: ReturnType<typeof watchConsole>
|
||||
let settledSessionId: SessionId | undefined
|
||||
const sessionEvents: SessionEvent[] = []
|
||||
|
||||
beforeAll(async () => {
|
||||
@@ -69,11 +72,24 @@ describe('web e2e: fresh round trip through the real assembly', () => {
|
||||
await input.fill(PROMPT)
|
||||
await input.press('Enter')
|
||||
const sessionId = await settled
|
||||
settledSessionId = sessionId
|
||||
if (MODE === 'record') {
|
||||
await recordFixture(scaffold, sessionId, FIXTURE)
|
||||
}
|
||||
}, 200_000)
|
||||
|
||||
it('records the Web surface, source checkout, and session cwd in the request header', async () => {
|
||||
if (settledSessionId === undefined) throw new Error('the drive turn did not publish a session id')
|
||||
const agent = scaffold.ctx.agents.get(settledSessionId)
|
||||
if (agent === undefined) throw new Error(`the settled Web agent ${settledSessionId} is no longer live`)
|
||||
const system = agent.session.requestHeader()?.system
|
||||
if (system === undefined) throw new Error('the settled Web request has no system prompt')
|
||||
const prefix = system.split('\n\n').slice(0, 4).join('\n\n')
|
||||
.split(REPO_ROOT).join('{{sourceRoot}}')
|
||||
.split(join(scaffold.workspaceCwd, 'workspace')).join('{{cwd}}')
|
||||
await compareOrRefreshGolden(SYSTEM_PROMPT_EXPECTED, prefix, MODE)
|
||||
})
|
||||
|
||||
it.skipIf(MODE === 'record')('rendered the settled turn: markdown, tool row, composer restore', async () => {
|
||||
onTestFailed(() => saveFailureShot(page, 'web-e2e-round-trip-settled'))
|
||||
// Browser settled-poll after host completion (host strictly precedes render).
|
||||
@@ -129,6 +145,6 @@ describe('web e2e: fresh round trip through the real assembly', () => {
|
||||
it.skipIf(MODE === 'record')('stayed clean: no pageerrors, no reconnect self-healing, no server errors', async () => {
|
||||
expect(tripwire.pageErrors).toEqual([])
|
||||
expect(tripwire.warnings).toEqual([])
|
||||
await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'ui.expected.md'])
|
||||
await assertFixtureInventory(SNAPSHOT_DIR, ['session.jsonl', 'system-prompt.expected.md', 'ui.expected.md'])
|
||||
})
|
||||
})
|
||||
|
||||
@@ -44,6 +44,7 @@ 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 { installWebPromptContext } from '../../cli/src/web.ts'
|
||||
import { DIST_INDEX, REPO_ROOT, requireDist } from './support.ts'
|
||||
|
||||
/** Snapshot mode for the lane, from $DSH_SNAPSHOT (same vocabulary as the ACP/TUI suites). */
|
||||
@@ -202,6 +203,7 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
|
||||
})
|
||||
await ctx.loader.await()
|
||||
assertEntriesLoaded(ctx, 'web e2e scaffold')
|
||||
installWebPromptContext(ctx, REPO_ROOT)
|
||||
const boundPort = ctx.get('httpServer')?.port
|
||||
if (boundPort === undefined) {
|
||||
throw new Error('web e2e scaffold: httpServer service missing after settled boot')
|
||||
|
||||
@@ -0,0 +1,7 @@
|
||||
You are an AI agent powered by the DeepSeek Harness SDK.
|
||||
|
||||
Your own source code is the checkout at {{sourceRoot}}; you can read it there to learn how dsh works and how to extend it.
|
||||
|
||||
You are interacting with the user through the DeepSeek Harness Web GUI. When the user refers to "this page", "this GUI", or "this app" without naming another target, they mean this GUI. The browser provides no implicit DOM, route, or screenshot context.
|
||||
|
||||
You are a coding agent powered by the deepseek-v4-flash model. Your working directory is {{cwd}}.
|
||||
Reference in New Issue
Block a user