Merge remote-tracking branch 'refs/remotes/origin/worktree/web-multimodal-image-input' into worktree/pr555-simplify

# Conflicts: # .agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.i18n.yaml # .agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.md # .agents/notes/implemented/feature/2026-07-22-web-multimodal-image-input-and-durable-attachments.zh.md # apps/cli/README.i18n.yaml # apps/cli/README.md # apps/cli/README.zh.md # apps/cli/src/app-cli-entry.ts # packages/client/connection/src/client/fixture.ts # packages/client/ui-conversation/src/client/service.ts # packages/host/apiproxy/src/api-proxy.ts # packages/host/apiproxy/src/api/host.schema.ts # packages/host/apiproxy/src/api/host.ts # packages/host/apiproxy/tests/fetch-carrier.spec.ts
2026-07-30 01:16:58 +08:00
parent 6312e43a11 b99d261501
commit d6c82001b3
97 changed files with 1375 additions and 447 deletions
--- a/packages/client/ui-conversation/src/client/apply.ts
+++ b/packages/client/ui-conversation/src/client/apply.ts
@@ -196,9 +196,9 @@ export function apply(ctx: Context): void {
      const shell = inputHub.shell(sessionId)
      return {
        keyboard: shell,
-        addImages: (files, current) => {
+        addImages: (files) => {
          try {
-            const images = conversation.createDraftImages(files, current)
+            const images = conversation.createDraftImages(files)
            shell.addImages(images.map(image => image.id))
            return null
          } catch (error: unknown) {
--- a/packages/client/ui-conversation/src/client/contract/slots.ts
+++ b/packages/client/ui-conversation/src/client/contract/slots.ts
@@ -273,7 +273,7 @@ export interface ComposerBarInjected {
  /** The InputBar-exclusive keyboard/DOM command face (decision 20 private plane). */
  keyboard: ComposerKeyboard
  /** Create browser previews and append their ids to the session input state. */
-  addImages: (files: readonly File[], current: readonly ComposerAttachment[]) => string | null
+  addImages: (files: readonly File[]) => string | null
  /** Release one browser preview and remove its id from the session input state. */
  removeImage: (id: string) => void
  /** Resolve ordered input-state ids to browser-owned draft attachments. */
--- a/packages/client/ui-conversation/src/client/service.ts
+++ b/packages/client/ui-conversation/src/client/service.ts
@@ -123,7 +123,6 @@ export class ConversationService extends Service implements IConversation {
    mode: 'queue' | 'steer',
    images: readonly File[],
  ): Promise<void> {
-    this.validateImages(images, [])
    const uploaded = await this.serializeImages(images)
    const content = [...uploaded, ...(text === '' ? [] : [{ type: 'text' as const, text }])]
    const result = await session.prompt(content, mode)
@@ -133,14 +132,10 @@ export class ConversationService extends Service implements IConversation {
  /**
   * Create runtime-only draft attachments and their object URLs.
   * @param files - browser-owned image files.
-   * @param current - images already present in the same composer.
   * @returns ordered attachment descriptors whose ids may enter the input state.
   */
-  createDraftImages(
-    files: readonly File[],
-    current: readonly ComposerAttachment[] = [],
-  ): readonly ComposerAttachment[] {
-    this.validateImages(files, current)
+  createDraftImages(files: readonly File[]): readonly ComposerAttachment[] {
+    for (const file of files) imageMediaType(file.type)
    return files.map((file) => {
      const attachment = browserDraftAttachment(file)
      this.draftAttachments.set(attachment.id, attachment)
@@ -276,36 +271,6 @@ export class ConversationService extends Service implements IConversation {
    return sessions
  }

-  /** Apply host-advertised fast-path checks before any object URL or base64 allocation. */
-  private validateImages(
-    files: readonly File[],
-    current: readonly ComposerAttachment[],
-  ): void {
-    if (files.length === 0 && current.length === 0) return
-    // Model capability is checked only by the host against the session's
-    // current target; the client owns deployment upload limits.
-    const description = this.requireSessions().hostDescription()
-    const limits = description?.imageLimits
-    const all = [...current.map(attachment => attachment.file), ...files]
-    if (limits !== undefined && all.length > limits.maxImagesPerMessage) {
-      throw new Error(`每条消息最多添加 ${limits.maxImagesPerMessage} 张图片`)
-    }
-    let totalBytes = 0
-    for (const file of all) {
-      const mediaType = imageMediaType(file.type)
-      if (limits !== undefined && !limits.mediaTypes.includes(mediaType)) {
-        throw new Error(`当前部署不支持 ${mediaType} 图片`)
-      }
-      if (limits !== undefined && file.size > limits.maxImageBytes) {
-        throw new Error(`图片 ${file.name || '未命名图片'} 超过单张大小限制`)
-      }
-      totalBytes += file.size
-    }
-    if (limits !== undefined && totalBytes > limits.maxMessageImageBytes) {
-      throw new Error('图片总大小超过单条消息限制')
-    }
-  }
-
  /** Convert browser files to the prompt wire's canonical base64 image parts. */
  private serializeImages(images: readonly File[]): Promise<Parameters<SessionFace['prompt']>[0]> {
    return Promise.all(images.map(async file => ({
--- a/packages/client/ui-conversation/src/client/skeleton/InputBar.tsx
+++ b/packages/client/ui-conversation/src/client/skeleton/InputBar.tsx
@@ -234,7 +234,7 @@ export function InputBar({
      .map(item => item.getAsFile())
      .filter((file): file is File => file !== null)
    if (files.length > 0) {
-      setDropError(addImages(files, attachments))
+      setDropError(addImages(files))
    }
    const text = e.clipboardData.getData('text/plain')
    if (text === '') {
@@ -290,7 +290,7 @@ export function InputBar({
    if (locked || machineBusy) return
    const dropped = [...event.dataTransfer.files]
    if (dropped.length === 0) return
-    setDropError(addImages(dropped, attachments))
+    setDropError(addImages(dropped))
  }

  const closePreview = useCallback(() => { setPreview(null) }, [])
--- a/packages/client/ui-conversation/tests/input-bar.spec.tsx
+++ b/packages/client/ui-conversation/tests/input-bar.spec.tsx
@@ -49,7 +49,7 @@ interface BenchOptions {
  leftItems?: React.ReactNode
  rightItems?: React.ReactNode
  attachments?: readonly ComposerAttachment[]
-  addImages?: (files: readonly File[], current: readonly ComposerAttachment[]) => string | null
+  addImages?: (files: readonly File[]) => string | null
 }

 /** Real machine behind the bar entry: sink spy, no slash pipeline (plain text goes straight to the sink). */
@@ -464,7 +464,7 @@ describe('image draft rail', () => {
        getData: () => '同时粘贴的文字',
      },
    })
-    expect(addImages).toHaveBeenCalledWith([image], [])
+    expect(addImages).toHaveBeenCalledWith([image])
    expect(shell.snapshot.draft).toBe('同时粘贴的文字')

    const video = new File([Uint8Array.of(1)], 'clip.mp4', { type: 'video/mp4' })
@@ -494,7 +494,7 @@ describe('image draft rail', () => {
    expect(dataTransfer.dropEffect).toBe('copy')
    expect(fireEvent.drop(card, { dataTransfer })).toBe(false)
    expect(view.queryByRole('status')).toBeNull()
-    expect(addImages).toHaveBeenCalledWith([image], [])
+    expect(addImages).toHaveBeenCalledWith([image])
  })

  it('ignores unsupported dropped files and refuses drops while locked', () => {
@@ -507,7 +507,7 @@ describe('image draft rail', () => {
      dataTransfer: { types: ['Files'], files: [documentFile], dropEffect: 'none' },
    })
    expect(view.getByText(/不支持的图片格式/)).toBeTruthy()
-    expect(addImages).toHaveBeenCalledWith([documentFile], [])
+    expect(addImages).toHaveBeenCalledWith([documentFile])

    const image = new File([Uint8Array.of(1)], 'locked.png', { type: 'image/png' })
    const locked = bench({ disabled: true, addImages })
--- a/packages/client/ui-conversation/tests/service-orchestration.spec.ts
+++ b/packages/client/ui-conversation/tests/service-orchestration.spec.ts
@@ -49,47 +49,6 @@ describe('ConversationService', () => {
    await b.runtime.dispose()
  })

-  it('accepts ordered batches and preflights their advertised count and aggregate limits', async () => {
-    const b = await bench()
-    const described = vi.spyOn(b.runtime.sessions, 'hostDescription').mockReturnValue({
-      version: 'test',
-      cwd: '/tmp',
-      imageLimits: {
-        maxImageBytes: 3,
-        maxImagesPerMessage: 2,
-        maxMessageImageBytes: 3,
-        maxImagePixels: 4,
-        mediaTypes: ['image/png'],
-      },
-      attachedSessions: 1,
-    })
-    const created = vi.spyOn(URL, 'createObjectURL')
-      .mockReturnValueOnce('blob:first')
-      .mockReturnValueOnce('blob:second')
-    const revoked = vi.spyOn(URL, 'revokeObjectURL').mockReturnValue(undefined)
-    try {
-      const attachments = b.root.createDraftImages([
-        new File([Uint8Array.of(1)], 'first.png', { type: 'image/png' }),
-        new File([Uint8Array.of(2)], 'second.png', { type: 'image/png' }),
-      ])
-      expect(attachments.map(attachment => attachment.file.name)).toEqual(['first.png', 'second.png'])
-      expect(() => b.root.createDraftImages([
-        new File([Uint8Array.of(3)], 'third.png', { type: 'image/png' }),
-      ], attachments)).toThrow('每条消息最多添加 2 张图片')
-      const first = attachments[0]
-      if (first === undefined) throw new Error('first draft attachment missing')
-      expect(() => b.root.createDraftImages([
-        new File([Uint8Array.of(3, 4, 5)], 'large.png', { type: 'image/png' }),
-      ], [first])).toThrow('图片总大小超过单条消息限制')
-      expect(created).toHaveBeenCalledTimes(2)
-    } finally {
-      await b.runtime.dispose()
-      described.mockRestore()
-      created.mockRestore()
-      revoked.mockRestore()
-    }
-  })
-
  it('releases draft images when the session scope is disposed', async () => {
    const b = await bench()
    const created = vi.spyOn(URL, 'createObjectURL').mockReturnValue('blob:draft-1')
@@ -110,6 +69,31 @@ describe('ConversationService', () => {
    await b.runtime.dispose()
  })

+  it('checks media type before preview allocation and leaves deployment limits to the host', async () => {
+    const b = await bench()
+    const created = vi.spyOn(URL, 'createObjectURL').mockImplementation(file => `blob:${(file as File).name}`)
+    try {
+      const files = Array.from(
+        { length: 11 },
+        (_, index) => new File([Uint8Array.of(index)], `${index}.png`, { type: 'image/png' }),
+      )
+      expect(b.root.createDraftImages(files)).toHaveLength(11)
+      expect(created).toHaveBeenCalledTimes(11)
+
+      const beforeRejectedBatch = created.mock.calls.length
+      expect(() => {
+        b.root.createDraftImages([
+          new File([Uint8Array.of(1)], 'valid.png', { type: 'image/png' }),
+          new File([Uint8Array.of(2)], 'invalid.svg', { type: 'image/svg+xml' }),
+        ])
+      }).toThrow('不支持的图片格式：image/svg+xml')
+      expect(created).toHaveBeenCalledTimes(beforeRejectedBatch)
+    } finally {
+      created.mockRestore()
+    }
+    await b.runtime.dispose()
+  })
+
  it('releases in-flight send images when the scope dies before the failure lands', async () => {
    const b = await bench()
    const created = vi.spyOn(URL, 'createObjectURL').mockReturnValue('blob:inflight-1')