Merge remote-tracking branch 'origin/master' into feat/read-image-context

# Conflicts:
#	apps/cli/tests/web-agent-presets.e2e.ts
#	packages/fs/tool-fs/package.json
This commit is contained in:
creatixchu
2026-08-11 10:12:14 +08:00
1962 changed files with 25048 additions and 14905 deletions

View File

@@ -1,8 +1,15 @@
{
"name": "@deepseek-ai/dsh-frontend",
"description": "Web application entry: vite build over the @deepseek-ai/dsh-client-web shell library; dist/ served by apps/cli's dsh web",
"version": "0.0.1",
"private": true,
"version": "0.0.1-rc.1",
"publishConfig": {
"access": "restricted"
},
"repository": {
"type": "git",
"url": "git+https://github.com/deepseek-ai/deepseek-harness.git",
"directory": "apps/web"
},
"type": "module",
"exports": {
"./dist/*": "./dist/*",
@@ -23,11 +30,12 @@
"react-dom": "^18.2.0"
},
"devDependencies": {
"@cordisjs/plugin-group": "workspace:^",
"@deepseek-ai/cordis-plugin-group": "workspace:^",
"@deepseek-ai/dsh-client-modules": "workspace:^",
"@deepseek-ai/dsh-client-ui-primitives": "workspace:^",
"@deepseek-ai/dsh-client-ui-slots": "workspace:^",
"@deepseek-ai/dsh-client-web-react": "workspace:^",
"@deepseek-ai/dsh-cmdline": "workspace:^",
"@deepseek-ai/dsh-pwsh-local": "workspace:^",
"@types/node": "^22.0.0",
"@types/react": "~18.3.1",

View File

@@ -161,7 +161,7 @@ describe('web e2e: agent-preset authoring is a host-side copy', () => {
expect(composition).toBe(await readFile(join(SHIPPED_PRESETS, 'minimal', 'agent.cordis.yml'), 'utf8'))
const metadata = await readFile(join(userRoot, 'my-agent', 'preset.yml'), 'utf8')
expect(metadata).toContain('name: 我的模式')
expect(metadata).toContain('description: 仅提供 bash 与 str_replace_editor 的双工具编码 Agent,用于基准测试和最小复现。')
expect(metadata).toContain('description: 仅提供持久 bash 与 str_replace_editor 的双工具编码 Agent。')
expect(metadata).not.toContain('order:')
}, 60_000)

View File

@@ -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
}
}
}
})
})

View File

@@ -6,8 +6,8 @@ import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { chromium } from 'playwright'
import { expect, it } from 'vitest'
import { Context } from 'cordis'
import type { Fiber } from 'cordis'
import { Context } from '@deepseek-ai/cordis'
import type { Fiber } from '@deepseek-ai/cordis'
import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local'
import type { SubprocessHandle, SubprocessSpawnSpec } from '@deepseek-ai/dsh-subprocess'
import { REPO_ROOT } from './support.ts'

View 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'])
})
})

View File

@@ -29,13 +29,12 @@ import { join } from 'node:path'
import { pathToFileURL } from 'node:url'
import type { Page } from 'playwright'
import { expect } from 'vitest'
import { Context } from 'cordis'
import Loader from '@cordisjs/plugin-loader'
import Include, { type PatchOptions } from '@cordisjs/plugin-include'
import Group from '@cordisjs/plugin-group'
import { Context } from '@deepseek-ai/cordis'
import Loader from '@deepseek-ai/cordis-plugin-loader'
import Include, { type PatchOptions } from '@deepseek-ai/cordis-plugin-include'
import Group from '@deepseek-ai/cordis-plugin-group'
import { scrubRequestHeaders, stabilizeFixtureMessageIds } from '@deepseek-ai/dsh-acp-snapshot'
import {
addHarnessSourceSection,
assertEntriesLoaded,
composeEntries,
healProfilesModuleFallback,
@@ -65,6 +64,7 @@ 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 { provideCmdline } from '@deepseek-ai/dsh-cmdline'
import { REPO_ROOT, requireDist } from './support.ts'
/** Snapshot mode for the lane, from $DSH_SNAPSHOT (same vocabulary as the other snapshot suites). */
@@ -459,19 +459,26 @@ export async function launchWebScaffold(options: LaunchOptions = {}): Promise<We
ctx.baseUrl = pathToFileURL(profileDir).href + '/'
// This direct Loader harness supplies the same root-path capability as app-boot.
ctx.provide('dshHomePath', dshHomePath)
// A host with no command line still provides one: the web bundle's startup
// row releases the rows waiting on it, and with no arguments each starts on
// the values this scaffold composed above. An exit request can only come
// from a rejected argument, which a fixed empty list has none of.
provideCmdline(ctx, {
args: [],
exit: (code) => {
throw new Error(`web e2e scaffold: the web app requested exit ${String(code)} with no arguments to reject`)
},
})
await ctx.plugin(Loader)
ctx.loader.builtins.include = Include
// `cordis:group` beside it, exactly as `boot()` registers it: a group row is
// how a preset gives one `isolate` realm to a provider and its consumers,
// and a preset resolving package names from its own directory cannot reach
// `@cordisjs/plugin-group` by name.
// `@deepseek-ai/cordis-plugin-group` by name.
ctx.loader.builtins.group = Group
// 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
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

@@ -39,7 +39,6 @@ const EXPECTED_TOOLS = [
'read_image',
'send_message',
'skill',
'str_replace_editor',
'subagent',
'subagent_fork',
'task_kill',

View File

@@ -485,10 +485,13 @@ describe.skipIf(!process.env.DEEPSEEK_API_KEY || notReady.length > 0)('web smoke
child = spawn(
process.execPath,
[
'--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web', '--port', String(port),
'--import', tsxLoader, join(REPO_ROOT, 'apps/cli/src/bin.ts'), 'web',
// Launcher flags come first: the first token the launcher does not own
// starts the web app's own arguments.
// Pin the in-browser picker: the shipped `-auto` row would resolve to
// the native OS chooser on this bind, and no page can drive that.
'--patch', fileURLToPath(new URL('./pin-browse-picker.overlay.yml', import.meta.url)),
'--port', String(port),
],
{
cwd: sessionsDir,

View File

@@ -40,7 +40,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 极简模式"':
- text: 极简模式 内置 仅提供 bash 与 str_replace_editor 的双工具编码 Agent,用于基准测试和最小复现
- text: 极简模式 内置 仅提供持久 bash 与 str_replace_editor 的双工具编码 Agent。
- code: minimal
- 'button "查看: 极简模式"':
- img
@@ -62,7 +62,7 @@
- list:
- listitem:
- 'button "设为默认: 我的模式"':
- text: 我的模式 自定义 仅提供 bash 与 str_replace_editor 的双工具编码 Agent,用于基准测试和最小复现
- text: 我的模式 自定义 仅提供持久 bash 与 str_replace_editor 的双工具编码 Agent。
- code: my-agent
- 'button "查看路径: 我的模式"':
- img

View File

@@ -40,7 +40,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 极简模式"':
- text: 极简模式 内置 仅提供 bash 与 str_replace_editor 的双工具编码 Agent,用于基准测试和最小复现
- text: 极简模式 内置 仅提供持久 bash 与 str_replace_editor 的双工具编码 Agent。
- code: minimal
- 'button "查看: 极简模式"':
- img

View File

@@ -40,7 +40,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 极简模式"':
- text: 极简模式 内置 仅提供 bash 与 str_replace_editor 的双工具编码 Agent,用于基准测试和最小复现
- text: 极简模式 内置 仅提供持久 bash 与 str_replace_editor 的双工具编码 Agent。
- code: minimal
- 'button "查看: 极简模式"':
- img

View File

@@ -3,5 +3,5 @@
- text: Standard mode Full coding agent with file editing, shell, file and web search, skills, planning, goals, subagents, and workflows.
- img
- menuitem "Code mode All Standard mode capabilities, with tools exposed through the Code Mode SDK so the model can combine multi-step operations in one TypeScript program."
- menuitem "Minimal mode Two-tool coding agent with only bash and str_replace_editor, for benchmarks and minimal reproductions."
- menuitem "Minimal mode Two-tool coding agent with persistent bash and str_replace_editor."
- menuitem "Creator mode Built for creating custom agent presets, with all Standard mode capabilities plus runtime inspection, plugin experiments, and preset-authoring guidance."

View File

@@ -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"}}}}

View File

@@ -3,6 +3,8 @@
- button "Ask a research subagent to"
- text: /
- button "event-sourcing researcher" [disabled]
- img
- text: Standard mode
- button "1 subagent":
- text: 1 subagent
- img
@@ -41,7 +43,7 @@
- textbox "Message the agent"
- button "Commands":
- img
- 'button "Access mode, current: Workspace Write"': Workspace Write
- 'button "Access mode, current: Custom"': Custom
- button "6% of context used"
- button "Send message" [disabled]
- text: 2 turns · 2 steps LLM {{duration}} TTFT avg {{duration}} · {{throughput}} tok/s Cache hit 99% Input 15.6K tok · Output 158 tok

View File

@@ -3,6 +3,8 @@
- button "Ask a research subagent to"
- text: /
- button "event-sourcing researcher" [disabled]
- img
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"
@@ -18,6 +20,6 @@
- textbox "Parent session offline; sending is unavailable but you can still stop the run" [disabled]
- button "Commands" [disabled]:
- img
- 'button "Access mode, current: Workspace Write" [disabled]': Workspace Write
- 'button "Access mode, current: Custom" [disabled]': Custom
- button "Stop generating"
- button "Send message" [disabled]

View File

@@ -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",