Merge pull request #1050 from deepseek-harness/worktree/custom-deepseek-models

feat(web): configure custom DeepSeek models, with a restyled Models card

apps/web/tests/access-confirmation.e2e.ts

@@ -2,7 +2,6 @@
 // the same locale-aware, in-page risk confirmation. Zero model calls: the
 // scenario boots the shipped Web composition and exercises the real
 // permission projection, client command path, HTTP RPC, and pushed update.
-import { mkdirSync } from 'node:fs'
 import { fileURLToPath } from 'node:url'
 import { join } from 'node:path'
 import type { Browser, Page } from 'playwright'
@@ -12,27 +11,7 @@ import {
   assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
   launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
-import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
-
-/**
- * connectFreshWorkspace twin over the product default Chinese locale (the
- * shared helper's anchors assume the English page every other scenario
- * boots; this scenario deliberately keeps zh, so the localized picker
- * copy is the anchor set).
- */
-async function connectFreshWorkspaceZh(page: Page, root: string, name = 'workspace'): Promise<void> {
-  mkdirSync(join(root, name), { recursive: true })
-  await page.getByRole('button', { name: '选择工作区' }).click()
-  const dialog = page.getByRole('dialog', { name: '选择工作区目录' })
-  await dialog.waitFor({ timeout: 10_000 })
-  await dialog.getByRole('button', { name: '编辑路径' }).click()
-  const pathInput = dialog.getByRole('textbox', { name: '编辑路径' })
-  await pathInput.fill(join(root, name))
-  await pathInput.press('Enter')
-  await dialog.getByRole('button', { name: '打开', exact: true }).click()
-  await page.locator('textarea:enabled[placeholder="描述你想要构建的内容"]')
-    .waitFor({ timeout: 15_000 })
-}
+import { ZH_BROWSER_LOCALE, connectFreshWorkspaceZh, saveFailureShot } from './support.ts'
 
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/access-confirmation', import.meta.url))
 const UI_EXPECTED = join(SNAPSHOT_DIR, 'ui.expected.md')

apps/web/tests/lifecycle-chrome.e2e.ts

@@ -104,6 +104,10 @@ describe('web e2e: lifecycle & chrome (workspace flow / reload / dark mode)', ()
       await input.press('Enter')
       const planButton = activePage.getByRole('button', { name: 'Plan mode on, press to turn off' })
       await planButton.waitFor({ timeout: 10_000 })
+      // The golden encodes an empty composer, and the button arriving does not
+      // mean the submitted text is gone yet: under load the capture caught a
+      // textbox still holding `/plan`.
+      await expect.poll(() => input.inputValue(), { timeout: 10_000 }).toBe('')
       const planSnapshot = await captureStableAria(activePage, '[class*="frame"]', activeScaffold.workspaceCwd)
       await compareOrRefreshGolden(PLAN_ACTIVE_EXPECTED, planSnapshot, MODE)
       const planStyle = await planButton.evaluate((element) => {

apps/web/tests/message-actions.e2e.ts

@@ -126,9 +126,8 @@ describe('web e2e: message IconActions and clocks on settled history', () => {
 
   it.skipIf(MODE === 'record')('matches the conversation aria golden with IconActions and clocks', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-message-actions-aria'))
-    await page.getByRole('button', {
-      name: 'Select model, current deepseek-v4-flash',
-    }).waitFor({ timeout: 10_000 })
+    await page.getByRole('button', { name: 'Select model', exact: true })
+      .waitFor({ timeout: 10_000 })
     // Keep a footer focused so opacity-hidden actions stay in the a11y tree
     // as an active/focused control during the capture.
     await page.getByRole('button', { name: 'Copy' }).first().focus()

apps/web/tests/onboarding-deepseek-config.e2e.ts

@@ -12,7 +12,7 @@ import {
   acknowledgeReloadConnectionLoss, assertFixtureInventory, captureStableAria, compareOrRefreshGolden,
   launchWebScaffold, watchConsole, webSnapshotMode, type WebScaffold,
 } from './scaffold.ts'
-import { ZH_BROWSER_LOCALE, saveFailureShot } from './support.ts'
+import { ZH_BROWSER_LOCALE, connectFreshWorkspaceZh, saveFailureShot } from './support.ts'
 import { settingsNamespace } from '@deepseek-ai/dsh-settings'
 import {
   WELCOME_NOTICE_ACK_FIELD, WELCOME_NOTICE_COPY, WELCOME_NOTICE_SETTINGS_NAMESPACE,
@@ -22,6 +22,7 @@ import {
 const SNAPSHOT_DIR = fileURLToPath(new URL('./snapshots/onboarding-deepseek-config', import.meta.url))
 const WELCOME_EXPECTED = join(SNAPSHOT_DIR, 'welcome.expected.md')
 const MISSING_EXPECTED = join(SNAPSHOT_DIR, 'missing.expected.md')
+const MODELS_EXPECTED = join(SNAPSHOT_DIR, 'models.expected.md')
 const MODE = webSnapshotMode()
 
 describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup', () => {
@@ -160,7 +161,60 @@ describe.skipIf(MODE === 'record')('web e2e: first-run DeepSeek credential setup
     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
+    // to exercise the welcome step, so nothing carries an open dialog across.
+    await page.getByRole('button', { name: '设置', exact: true }).click()
+    const settings = page.getByRole('dialog', { name: '设置' })
+    await settings.waitFor({ timeout: 10_000 })
+    await settings.getByRole('button', { name: '模型' }).click()
+    const deepSeek = settings.getByText('DeepSeek', { exact: true }).first()
+    await deepSeek.waitFor({ timeout: 10_000 })
+    await deepSeek.locator('xpath=ancestor::li').getByRole('button', { name: '编辑' }).click()
+    await settings.getByText('自定义设置').click()
+    await settings.getByRole('button', { name: /删除模型/ }).first().click()
+    await settings.getByRole('button', { name: '添加模型' }).click()
+    const customModelId = settings.getByLabel('模型 ID 2')
+    await customModelId.fill('private-preview')
+    await settings.getByLabel('显示名称 2').fill('Private Preview')
+    // Capacities live behind the row's own disclosure, as in the pi-ai form.
+    await settings.getByRole('button', { name: '容量 2' }).click()
+    await settings.getByLabel('上下文窗口 2').fill('131072')
+    await settings.getByLabel('最大输出 token 数 2').fill('64K')
+
+    const modelEditor = await captureStableAria(page, '[role="dialog"]', scaffold.workspaceCwd)
+    await compareOrRefreshGolden(MODELS_EXPECTED, modelEditor, MODE)
+    await settings.getByRole('button', { name: '保存', exact: true }).click()
+    await customModelId.waitFor({ state: 'detached', timeout: 15_000 })
+
+    const document = await readFile(join(scaffold.harnessHome, 'settings.yaml'), 'utf8')
+    expect(document).toContain('id: deepseek-v4-pro')
+    expect(document).toContain('id: private-preview')
+    expect(document).toContain('name: Private Preview')
+    expect(document).toContain('contextWindow: 131072')
+    expect(document).toContain('maxTokens: 64000')
+    expect(document).not.toContain('id: deepseek-v4-flash')
+
+    await page.keyboard.press('Escape')
+    // A connected Workspace is what puts a live composer — and its model
+    // trigger — on the page; the scaffold boots without one.
+    await connectFreshWorkspaceZh(page, scaffold.workspaceCwd, 'model-fallback-e2e')
+
+    const modelTrigger = page.getByRole('button', { name: '选择模型', exact: true })
+    await modelTrigger.waitFor({ timeout: 10_000 })
+    await modelTrigger.click()
+    await page.getByRole('menuitem', { name: /模型/ }).click()
+    expect(await page.getByText('deepseek-v4-flash', { exact: true }).count()).toBe(0)
+    await page.getByRole('menuitemradio', { name: 'Private Preview' }).waitFor({ timeout: 10_000 })
+    expect(tripwire.warnings).toEqual([])
+    expect(tripwire.pageErrors).toEqual([])
+  }, 60_000)
+
   it('keeps the fixture inventory closed', async () => {
-    await assertFixtureInventory(SNAPSHOT_DIR, ['missing.expected.md', 'welcome.expected.md'])
+    await assertFixtureInventory(
+      SNAPSHOT_DIR,
+      ['missing.expected.md', 'models.expected.md', 'welcome.expected.md'],
+    )
   })
 })

apps/web/tests/seeded-history.e2e.ts

@@ -241,12 +241,11 @@ describe('web e2e: seeded history renders through cold resume', () => {
 
   it.skipIf(MODE === 'record')('matches the historical conversation aria golden', async () => {
     onTestFailed(() => saveFailureShot(page, 'web-e2e-seeded-aria'))
-    await page.getByRole('button', {
-      // This scenario deliberately leaves the LLM seam open to prove zero
-      // model calls. History still restores the selected id, but no catalog
-      // adapter exists to provide its presentation name.
-      name: 'Select model, current deepseek-v4-flash',
-    }).waitFor({ timeout: 10_000 })
+    // This scenario deliberately leaves the LLM seam open to prove zero
+    // model calls. History still restores the routed id, but without an
+    // advertised catalog row the selector prompts for a listed replacement.
+    await page.getByRole('button', { name: 'Select model', exact: true })
+      .waitFor({ timeout: 10_000 })
     const snapshot = (await captureStableAria(page, '[class*="centerCol"]', scaffold.workspaceCwd))
       .split(SEED_ID).join('{{seededId}}')
     await compareOrRefreshGolden(UI_EXPECTED, snapshot, MODE)

apps/web/tests/snapshots/bash-abort-row/ui.expected.md

@@ -26,8 +26,8 @@
 - button "Commands":
   - img
 - 'button "Access mode, current: Workspace Write"': Workspace Write
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: 1 turns · 1 steps Tool call {{duration}} Cache hit 0% Input 10 tok · Output 10 tok

apps/web/tests/snapshots/lifecycle-chrome/plan-active.expected.md

@@ -30,8 +30,8 @@
   - img
 - 'button "Access mode, current: Workspace Write"': Workspace Write
 - button "Plan mode on, press to turn off": Plan
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: Details

apps/web/tests/snapshots/markdown-images/ui.expected.md

@@ -24,8 +24,8 @@
 - button "Commands":
   - img
 - 'button "Access mode, current: Workspace Write"': Workspace Write
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: 1 turns · 1 steps Input 0 tok · Output 0 tok

apps/web/tests/snapshots/message-actions/ui.expected.md

@@ -51,8 +51,8 @@
 - button "Commands":
   - img
 - 'button "Access mode, current: Workspace Write"': Workspace Write
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: 2 turns · 3 steps Tool call {{duration}} Cache hit 98% Input 7.8K tok · Output 103 tok

apps/web/tests/snapshots/onboarding-deepseek-config/models.expected.md

@@ -0,0 +1,70 @@
+- dialog "设置":
+  - navigation:
+    - text: 设置
+    - button "通用设置":
+      - img
+      - text: 通用设置
+    - button "模型":
+      - img
+      - text: 模型
+  - button "关闭":
+    - img
+    - text: 关闭
+  - heading "模型" [level=2]
+  - paragraph: 填入各提供方的 API 密钥即可使用其模型。
+  - list:
+    - listitem:
+      - text: DeepSeek
+      - button "编辑"
+      - text: DeepSeek deepseek-official API 密钥
+      - textbox "API 密钥":
+        - /placeholder: 已配置——输入新值可替换
+      - group:
+        - text: 自定义设置 API 地址
+        - textbox "API 地址":
+          - /placeholder: https://api.deepseek.com
+        - text: 推理强度
+        - combobox "推理强度":
+          - option "默认" [selected]
+          - option "off"
+          - option "high"
+          - option "max"
+        - region "模型目录":
+          - text: 模型目录 已自定义模型目录
+          - button "恢复默认模型"
+          - textbox "模型 ID 1":
+            - /placeholder: 模型 ID
+            - text: deepseek-v4-pro
+          - textbox "显示名称 1":
+            - /placeholder: 显示名称
+            - text: DeepSeek-V4-Pro
+          - button "容量 1":
+            - img
+          - button "删除模型 1":
+            - img
+          - textbox "模型 ID 2":
+            - /placeholder: 模型 ID
+            - text: private-preview
+          - textbox "显示名称 2":
+            - /placeholder: 显示名称
+            - text: Private Preview
+          - button "容量 2" [expanded]:
+            - img
+          - button "删除模型 2":
+            - img
+          - text: 上下文窗口
+          - textbox "上下文窗口 2":
+            - /placeholder: 1M
+            - text: "131072"
+          - text: 最大输出 token 数
+          - textbox "最大输出 token 数 2":
+            - /placeholder: 256K
+            - text: 64K
+          - button "添加模型":
+            - img
+            - text: 添加模型
+      - button "取消"
+      - button "保存"
+  - button "添加提供方":
+    - img
+    - text: 添加提供方

apps/web/tests/snapshots/seeded-history/command-row.expected.md

@@ -47,8 +47,8 @@
 - button "Commands":
   - img
 - 'button "Access mode, current: Read Only"': Read Only
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok

apps/web/tests/snapshots/seeded-history/ui.expected.md

@@ -45,8 +45,8 @@
 - button "Commands":
   - img
 - 'button "Access mode, current: Workspace Write"': Workspace Write
-- button "Select model, current deepseek-v4-flash":
-  - text: deepseek-v4-flash
+- button "Select model":
+  - text: Select model
   - img
 - button "Send message" [disabled]
 - text: 1 turns · 2 steps Tool call {{duration}} Cache hit 98% Input 15.8K tok · Output 135 tok

apps/web/tests/support.ts

@@ -88,6 +88,28 @@ export async function connectFreshWorkspace(page: Page, root: string, name = 'wo
     .waitFor({ timeout: 15_000 })
 }
 
+/**
+ * {@link connectFreshWorkspace} over the product default Chinese locale: the
+ * English helper's anchors assume the locale every other scenario boots, so a
+ * scenario that deliberately keeps zh needs the localized picker copy.
+ * @param page - the browser page under test.
+ * @param root - workspace parent directory.
+ * @param name - directory created under `root` and connected.
+ */
+export async function connectFreshWorkspaceZh(page: Page, root: string, name = 'workspace'): Promise<void> {
+  mkdirSync(join(root, name), { recursive: true })
+  await page.getByRole('button', { name: '选择工作区' }).click()
+  const dialog = page.getByRole('dialog', { name: '选择工作区目录' })
+  await dialog.waitFor({ timeout: 10_000 })
+  await dialog.getByRole('button', { name: '编辑路径' }).click()
+  const pathInput = dialog.getByRole('textbox', { name: '编辑路径' })
+  await pathInput.fill(join(root, name))
+  await pathInput.press('Enter')
+  await dialog.getByRole('button', { name: '打开', exact: true }).click()
+  await page.locator('textarea:enabled[placeholder="描述你想要构建的内容"]')
+    .waitFor({ timeout: 15_000 })
+}
+
 /** Failure evidence goes to the gitignored .artifacts/ (repo convention). */
 export async function saveFailureShot(page: Page, name: string): Promise<void> {
   const dir = fileURLToPath(new URL('../../../.artifacts', import.meta.url))