Merge remote-tracking branch 'origin/master' into worktree/fix-minimal-preset-prompt

# Conflicts:
#	apps/cli/config/agent-presets/minimal/preset.yml
This commit is contained in:
Yichen Jiang
2026-08-10 21:05:29 +08:00
101 changed files with 1385 additions and 269 deletions

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: 只向模型呈现 bash 与 str_replace_editor,适合 benchmark 与最小复现。')
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

@@ -16,6 +16,10 @@ import { join } from 'node:path'
import type { Browser, Page } from 'playwright'
import { chromium } from 'playwright'
import { afterAll, beforeAll, describe, expect, it, onTestFailed } from 'vitest'
import {
SESSION_FORMAT_VERSION, SessionId as sessionId, type SessionEvent, type SessionId,
} from '@deepseek-ai/dsh-session'
import { snapshotSubagentDescriptor } from '@deepseek-ai/dsh-subagent'
import {
captureStableAria, compareOrRefreshGolden, launchWebScaffold, seedSession, watchConsole,
webSnapshotMode, type WebScaffold,
@@ -78,6 +82,60 @@ function seedLog(): string {
].join('\n')
}
/**
* Persist one child so the assembled header snapshot exercises both action
* contributors whose relative order is the product contract under test.
* @param scaffold - the booted Web scaffold.
* @param parentId - the seeded session whose header the browser opens.
*/
async function seedSubagent(scaffold: WebScaffold, parentId: SessionId): Promise<void> {
const childId = sessionId('agent-preset-selection-child')
const createdAt = 1784974100100
await scaffold.ctx.sessionPersistence.create({
version: SESSION_FORMAT_VERSION,
id: childId,
createdAt,
cwd: scaffold.workspaceCwd,
parentSession: parentId,
origin: 'subagent',
delegationDepth: 1,
agentPreset: 'minimal',
})
await scaffold.ctx.sessionPersistence.append(childId, [
{
type: 'turn/start',
seq: 0,
time: createdAt,
data: { turn: 1, trigger: { kind: 'message', source: { kind: 'user' } } },
},
{
type: 'user/message',
seq: 1,
time: createdAt + 1,
data: {
content: [{ type: 'text', text: 'Check the session-header action order.' }],
source: { kind: 'user' },
},
surfaceOp: 'append',
},
{
type: 'subagent/descriptor',
seq: 2,
time: createdAt + 2,
data: snapshotSubagentDescriptor({
mode: 'one-shot', provider: 'spawn', label: 'header order probe',
}),
},
{
type: 'turn/end',
seq: 3,
time: createdAt + 3,
data: { turn: 1, reason: { kind: 'completed' } },
},
] as SessionEvent[])
await scaffold.ctx.sessionProjectionCache.coldSnapshot(childId)
}
/**
* The preset the host reports for the blank session the workspace connect
* produced. Addressed by id rather than by scanning the serialized list: the
@@ -120,7 +178,8 @@ describe('web e2e: agent-preset selection', () => {
// A resumed session runs what it was created with; seeding one that
// records `minimal` is what makes the header label a claim about the
// session rather than an echo of the current default.
await seedSession(scaffold, seedLog(), SEED_ID, 'minimal')
const seededId = await seedSession(scaffold, seedLog(), SEED_ID, 'minimal')
await seedSubagent(scaffold, seededId)
await seedWorkspaceSkill(scaffold.workspaceCwd)
browser = await chromium.launch()
page = await newEnglishPage(browser)
@@ -143,12 +202,12 @@ describe('web e2e: agent-preset selection', () => {
await compareOrRefreshGolden(HERO_EXPECTED, snapshot, MODE)
// The chip opens on the deployment default, by the name that preset
// publishes rather than its directory name.
expect(snapshot).toContain('标准模式')
expect(snapshot).toContain('Standard mode')
})
it('names every preset and what it is for', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-agent-preset-menu'))
await page.getByRole('button', { name: '标准模式' }).click()
await page.getByRole('button', { name: 'Standard mode' }).click()
const menu = page.getByRole('menu')
await menu.waitFor({ timeout: 10_000 })
@@ -157,15 +216,15 @@ describe('web e2e: agent-preset selection', () => {
await compareOrRefreshGolden(MENU_EXPECTED, snapshot, MODE)
// Every shipped preset, each with the sentence saying what it composes —
// the id alone never said what a preset does.
expect(snapshot).toContain('极简模式')
expect(snapshot).toContain('创造模式')
expect(snapshot).toContain('Minimal mode')
expect(snapshot).toContain('Creator mode')
await page.keyboard.press('Escape')
})
it('applies the staged pick to the blank session, and the host honors it', async () => {
onTestFailed(() => saveFailureShot(page, 'web-e2e-agent-preset-stage'))
await page.getByRole('button', { name: '标准模式' }).click()
await page.getByRole('menuitem', { name: /极简模式/ }).click()
await page.getByRole('button', { name: 'Standard mode' }).click()
await page.getByRole('menuitem', { name: /Minimal mode/ }).click()
// The chip stages; the blank session the workspace connect produced is
// what the stage lands on. The host's own answer is what comes back.
@@ -197,8 +256,8 @@ describe('web e2e: agent-preset selection', () => {
// against its list row, so a row that never reprojected the first switch
// answers "already standard" and sends nothing — and restores the catalog
// instead of leaving the session reading the narrower composition.
await page.getByRole('button', { name: '极简模式' }).click()
await page.getByRole('menuitem', { name: /^标准模式/ }).first().click()
await page.getByRole('button', { name: 'Minimal mode' }).click()
await page.getByRole('menuitem', { name: /^Standard mode/ }).first().click()
await expect.poll(() => livePreset(scaffold.baseUrl), { timeout: 15_000 }).toBe('standard')
await composer.fill('/')
@@ -221,10 +280,12 @@ describe('web e2e: agent-preset selection', () => {
const snapshot = await captureStableAria(page, '[class*="titleRow"]', scaffold.workspaceCwd)
await compareOrRefreshGolden(HEADER_EXPECTED, snapshot, MODE)
expect(snapshot).toContain('极简模式')
expect(snapshot).toContain('Minimal mode')
expect(snapshot).toContain('button "1 subagent"')
expect(snapshot.indexOf('Minimal mode')).toBeLessThan(snapshot.indexOf('button "1 subagent"'))
// Static chrome, not a control: the header can only report a composition
// the host would refuse to change.
expect(snapshot).not.toContain('button "极简模式"')
expect(snapshot).not.toContain('button "Minimal mode"')
})
it('drove every surface without a page error or a stream warning', () => {

View File

@@ -20,7 +20,7 @@
- list:
- listitem:
- 'button "当前使用: 标准模式" [disabled] [pressed]':
- text: 标准模式 内置 当前使用 完整的编码 agent文件读写、shell、检索、计划、委派与工作流。
- text: 标准模式 内置 当前使用 功能完整的编码 Agent支持文件编辑、Shell、文件与网页检索、Skills、计划、目标、子代理和工作流。
- code: standard
- 'button "查看: 标准模式"':
- img
@@ -30,7 +30,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 代码模式"':
- text: 代码模式 内置 标准模式的工具改为 Code Mode 呈现:模型写一段 TypeScript 调用 SDK一次执行代替多轮工具调用
- text: 代码模式 内置 具备标准模式的全部能力,并通过 Code Mode SDK 呈现工具,让模型用一个 TypeScript 程序组合多步操作
- code: code
- 'button "查看: 代码模式"':
- img
@@ -40,7 +40,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 极简模式"':
- text: 极简模式 内置 只向模型呈现 bash 与 str_replace_editor,适合 benchmark 与最小复现
- 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
@@ -50,7 +50,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 创造模式"':
- text: 创造模式 内置 标准模式加上自指工具集,可以读改自己运行的这套组装,并据此创作新的预设
- text: 创造模式 内置 用于创建自定义 Agent preset具备标准模式的全部能力并提供运行时检查、插件实验和 preset 创作指导
- code: cordis
- 'button "查看: 创造模式"':
- img
@@ -62,7 +62,7 @@
- list:
- listitem:
- 'button "设为默认: 我的模式"':
- text: 我的模式 自定义 只向模型呈现 bash 与 str_replace_editor,适合 benchmark 与最小复现
- 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

@@ -20,7 +20,7 @@
- list:
- listitem:
- 'button "当前使用: 标准模式" [disabled] [pressed]':
- text: 标准模式 内置 当前使用 完整的编码 agent文件读写、shell、检索、计划、委派与工作流。
- text: 标准模式 内置 当前使用 功能完整的编码 Agent支持文件编辑、Shell、文件与网页检索、Skills、计划、目标、子代理和工作流。
- code: standard
- 'button "查看: 标准模式"':
- img
@@ -30,7 +30,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 代码模式"':
- text: 代码模式 内置 标准模式的工具改为 Code Mode 呈现:模型写一段 TypeScript 调用 SDK一次执行代替多轮工具调用
- text: 代码模式 内置 具备标准模式的全部能力,并通过 Code Mode SDK 呈现工具,让模型用一个 TypeScript 程序组合多步操作
- code: code
- 'button "查看: 代码模式"':
- img
@@ -40,7 +40,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 极简模式"':
- text: 极简模式 内置 只向模型呈现 bash 与 str_replace_editor,适合 benchmark 与最小复现
- 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
@@ -50,7 +50,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 创造模式"':
- text: 创造模式 内置 标准模式加上自指工具集,可以读改自己运行的这套组装,并据此创作新的预设
- text: 创造模式 内置 用于创建自定义 Agent preset具备标准模式的全部能力并提供运行时检查、插件实验和 preset 创作指导
- code: cordis
- 'button "查看: 创造模式"':
- img

View File

@@ -20,7 +20,7 @@
- list:
- listitem:
- 'button "当前使用: 标准模式" [disabled] [pressed]':
- text: 标准模式 内置 当前使用 完整的编码 agent文件读写、shell、检索、计划、委派与工作流。
- text: 标准模式 内置 当前使用 功能完整的编码 Agent支持文件编辑、Shell、文件与网页检索、Skills、计划、目标、子代理和工作流。
- code: standard
- 'button "查看: 标准模式"':
- img
@@ -30,7 +30,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 代码模式"':
- text: 代码模式 内置 标准模式的工具改为 Code Mode 呈现:模型写一段 TypeScript 调用 SDK一次执行代替多轮工具调用
- text: 代码模式 内置 具备标准模式的全部能力,并通过 Code Mode SDK 呈现工具,让模型用一个 TypeScript 程序组合多步操作
- code: code
- 'button "查看: 代码模式"':
- img
@@ -40,7 +40,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 极简模式"':
- text: 极简模式 内置 只向模型呈现 bash 与 str_replace_editor,适合 benchmark 与最小复现
- 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
@@ -50,7 +50,7 @@
- text: 复制
- listitem:
- 'button "设为默认: 创造模式"':
- text: 创造模式 内置 标准模式加上自指工具集,可以读改自己运行的这套组装,并据此创作新的预设
- text: 创造模式 内置 用于创建自定义 Agent preset具备标准模式的全部能力并提供运行时检查、插件实验和 preset 创作指导
- code: cordis
- 'button "查看: 创造模式"':
- img

View File

@@ -1,4 +1,7 @@
- navigation "Session hierarchy":
- button "Seeded turn" [disabled]
- img
- text: 极简模式
- text: Minimal mode
- button "1 subagent":
- text: 1 subagent
- img

View File

@@ -2,7 +2,7 @@
- img
- text: workspace
- img
- button "标准模式":
- button "Standard mode":
- img
- text: 标准模式
- text: Standard mode
- img

View File

@@ -1,7 +1,7 @@
- menu:
- menuitem "标准模式 完整的编码 agent文件读写、shell、检索、计划、委派与工作流。":
- text: 标准模式 完整的编码 agent文件读写、shell、检索、计划、委派与工作流。
- menuitem "Standard mode Full coding agent with file editing, shell, file and web search, skills, planning, goals, subagents, and workflows.":
- text: Standard mode Full coding agent with file editing, shell, file and web search, skills, planning, goals, subagents, and workflows.
- img
- menuitem "代码模式 标准模式的工具改为 Code Mode 呈现:模型写一段 TypeScript 调用 SDK一次执行代替多轮工具调用。"
- menuitem "极简模式 只向模型呈现 bash str_replace_editor,适合 benchmark 与最小复现。"
- menuitem "创造模式 标准模式加上自指工具集,可以读改自己运行的这套组装,并据此创作新的预设。"
- 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 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

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- 'button "Using ONE run_code program: run" [disabled]'
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Use only Cordis tools. First" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Use the bash tool to" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "workspace" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -25,9 +25,9 @@
- img
- text: workspace
- img
- button "标准模式":
- button "Standard mode":
- img
- text: 标准模式
- text: Standard mode
- img
- textbox "Describe what you want to build"
- button "Commands":

View File

@@ -25,9 +25,9 @@
- img
- text: workspace
- img
- button "标准模式":
- button "Standard mode":
- img
- text: 标准模式
- text: Standard mode
- img
- textbox "Describe what you want to build"
- button "Commands":

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Reply with the single word" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Reply with a one-sentence description" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Reply with a one-sentence description" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Reply with a one-sentence description" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Reply with a one-sentence description" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- 'button "Plan a small change: add" [disabled]'
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Use the ask_user_question tool to" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Reply with a one-sentence description" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Reply with a one-sentence description" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "workspace" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Reply with a one-sentence description" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Reply with a one-sentence description" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "/user-invoke-demo and confirm the fixtur" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Use the ask_user_question tool to" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Use the ask_user_question tool to" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Use the ask_user_question tool to" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Use the ask_user_question tool to" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Begin your reply with the" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Begin your reply with the" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -2,7 +2,7 @@
- navigation "Session hierarchy":
- button "Use web_search to search exactly" [disabled]
- img
- text: 标准模式
- text: Standard mode
- tablist:
- tab "Chat" [selected]
- tab "Trajectory"

View File

@@ -314,7 +314,7 @@ describe('web e2e: empty-draft Cmd+Enter steers the whole queue', () => {
await page.goto(scaffold.baseUrl, { waitUntil: 'load' })
await page.waitForSelector('[class*="frame"]', { timeout: 30_000 })
await connectFreshWorkspace(page, scaffold.workspaceCwd)
await page.getByText('标准模式', { exact: true }).waitFor({ timeout: 10_000 })
await page.getByText('Standard mode', { exact: true }).waitFor({ timeout: 10_000 })
}, 120_000)
afterAll(async () => {