Add web multimodal image attachments

packages/client/runtime/package.json

@@ -35,6 +35,7 @@
   },
   "license": "BSD-3-Clause",
   "dependencies": {
+    "@deepseek-ai/dsh-attachment": "workspace:^",
     "@deepseek-ai/dsh-client-connection": "workspace:^",
     "@deepseek-ai/dsh-client-ui-slots": "workspace:^",
     "@deepseek-ai/dsh-llm": "workspace:^",

packages/client/runtime/src/client/sessions/conversation.ts

@@ -4,6 +4,7 @@
 // string here (narrow to real brands when convenient).
 
 import type { ContentBlock } from '@deepseek-ai/dsh-llm/types'
+import type { ImageAttachmentRef } from '@deepseek-ai/dsh-attachment'
 import type { RpcError, RpcId, SessionId, ToolCallView, ToolResultView } from '@deepseek-ai/dsh-client-connection/client'
 
 /** Assistant content blocks sorted by what the UI cares about
@@ -11,6 +12,7 @@ import type { RpcError, RpcId, SessionId, ToolCallView, ToolResultView } from '@
 export type AssistantBlock =
   | { kind: 'text'; text: string }
   | { kind: 'reasoning'; text: string }
+  | { kind: 'image'; attachment: ImageAttachmentRef; alt?: string }
   | { kind: 'tool-call'; callId: string; name: string; argsRaw: string }
   | { kind: 'other'; block: unknown }
 
@@ -32,6 +34,10 @@ export function toAssistantBlock(block: ContentBlock): AssistantBlock {
   switch (block.type) {
     case 'text': return { kind: 'text', text: block.text }
     case 'reasoning': return { kind: 'reasoning', text: block.text }
+    case 'image': return {
+      kind: 'image', attachment: block.attachment,
+      ...block.alt === undefined ? {} : { alt: block.alt },
+    }
     case 'tool-call': return { kind: 'tool-call', callId: String(block.id), name: block.name, argsRaw: block.arguments }
     default: return { kind: 'other', block }
   }

packages/client/runtime/src/client/sessions/session.ts

@@ -3,9 +3,9 @@
 // created, they keep consuming mux frames in the background; React connects directly via
 // subscribe/getSnapshot.
 
-import type { ContentBlock } from '@deepseek-ai/dsh-llm/types'
+import type { AttachmentIdType, ImageAttachmentRef } from '@deepseek-ai/dsh-attachment'
 import type { SessionEvent } from '@deepseek-ai/dsh-session/types'
-import type { HistoryEntry, IApiClient, MuxFrame, RpcError, RpcId, RpcResult, SessionId, ToolEventView } from '@deepseek-ai/dsh-client-connection/client'
+import type { HistoryEntry, IApiClient, MuxFrame, PromptContentPart, RpcError, RpcId, RpcResult, SessionId, ToolEventView } from '@deepseek-ai/dsh-client-connection/client'
 import { transportError } from '@deepseek-ai/dsh-client-connection/client'
 import type { ObservableSnapshot } from '../contract/store.ts'
 import type {
@@ -82,11 +82,11 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
 
   /**
    * Send (queue/steer passed through 1:1); failures land in the snapshot's promptError.
-   * @param content - core content blocks verbatim.
+   * @param content - text plus browser-owned temporary image uploads.
    * @param mode - queue appends after the current turn; steer interrupts it.
    * @returns the prompt result (also mirrored into promptError on failure).
    */
-  async prompt(content: ContentBlock[], mode: 'queue' | 'steer'): Promise<RpcResult<{ accepted: true }>> {
+  async prompt(content: PromptContentPart[], mode: 'queue' | 'steer'): Promise<RpcResult<{ accepted: true }>> {
     this.promptError = null
     this.lastAgentError = null
     this.notifier.markDirty()
@@ -103,6 +103,23 @@ export class Session implements ObservableSnapshot<ConversationSnapshot> {
     return result
   }
 
+  /**
+   * Resolve one image referenced by this session into browser-consumable bytes.
+   * @param attachmentId - opaque id found in the folded session log.
+   * @returns the authenticated reference and decoded bytes.
+   */
+  async readAttachment(attachmentId: AttachmentIdType): Promise<RpcResult<{ attachment: ImageAttachmentRef; data: Uint8Array }>> {
+    try {
+      const result = (await this.api.sessions.attachment({ sessionId: this.sessionId, attachmentId })).result
+      if (!result.ok) return result
+      const binary = atob(result.value.data)
+      const data = Uint8Array.from(binary, char => char.charCodeAt(0))
+      return { ok: true, value: { attachment: result.value.attachment, data } }
+    } catch (error) {
+      return transportError(error)
+    }
+  }
+
   /**
    * Stop: contract session.cancel 1:1; failures land in promptError (same error-strip display slot).
    * @returns the cancel result.

packages/client/runtime/tests/conversation.spec.ts

@@ -1,22 +1,30 @@
 /** Assistant block classifier (moved here with sessions/conversation.ts). */
 
 import { describe, expect, it } from 'vitest'
+import { AttachmentId } from '@deepseek-ai/dsh-attachment'
 import type { ContentBlock } from '@deepseek-ai/dsh-client-connection/client'
 import { toAssistantBlock, toAssistantBlocks } from '../src/client/sessions/conversation.ts'
 
 describe('toAssistantBlock', () => {
   it('classifies the four block shapes', () => {
+    const attachment = {
+      attachmentId: AttachmentId(`sha256:${'a'.repeat(64)}`),
+      mediaType: 'image/png' as const,
+      bytes: 68,
+      width: 1,
+      height: 1,
+    }
     const blocks: ContentBlock[] = [
       { type: 'text', text: '正文' },
       { type: 'reasoning', text: '思考' },
       { type: 'tool-call', id: 'c1', name: 'echo', arguments: '{}' } as ContentBlock,
-      { type: 'image', data: 'x' } as unknown as ContentBlock,
+      { type: 'image', attachment },
     ]
     expect(toAssistantBlocks(blocks)).toEqual([
       { kind: 'text', text: '正文' },
       { kind: 'reasoning', text: '思考' },
       { kind: 'tool-call', callId: 'c1', name: 'echo', argsRaw: '{}' },
-      { kind: 'other', block: blocks[3] },
+      { kind: 'image', attachment },
     ])
     expect(toAssistantBlock(blocks[0] as ContentBlock)).toEqual({ kind: 'text', text: '正文' })
   })

packages/client/runtime/tests/fake-api.ts

@@ -51,6 +51,8 @@ export class FakeApiClient implements IApiClient {
     () => Promise.resolve(ok({ events: [], hasMore: false }))
 
   onPrompt: (payload: unknown) => Promise<RpcResponse<{ accepted: true }>> = () => Promise.resolve(ok({ accepted: true as const }))
+  onAttachment: (payload: unknown) => Promise<RpcResponse<{ attachment: { attachmentId: never; mediaType: 'image/png'; bytes: number; width: number; height: number }; data: string }>> =
+    () => Promise.resolve(ok({ attachment: { attachmentId: 'a' as never, mediaType: 'image/png', bytes: 1, width: 1, height: 1 }, data: 'AA==' }))
   onCancel: (payload: unknown) => Promise<RpcResponse<{ accepted: true }>> = () => Promise.resolve(ok({ accepted: true as const }))
   onDescribe: (payload: unknown) => Promise<RpcResponse<{ version: string; cwd: string; attachedSessions: number }>> =
     () => Promise.resolve(ok({ version: '0-fake', cwd: '/f', attachedSessions: 0 }))
@@ -67,6 +69,7 @@ export class FakeApiClient implements IApiClient {
     history: (payload: { sessionId: SessionId; beforeSeq?: number; maxMessages?: number }) =>
       this.record('session.history', payload, this.onHistory(payload)),
     prompt: (payload: unknown) => this.record('session.prompt', payload, this.onPrompt(payload)),
+    attachment: (payload: unknown) => this.record('session.attachment', payload, this.onAttachment(payload)),
     cancel: (payload: unknown) => this.record('session.cancel', payload, this.onCancel(payload)),
   }
 

packages/client/runtime/tests/session.spec.ts

@@ -239,6 +239,21 @@ describe('prompt and cancel errors', () => {
     expect(result.ok).toBe(false)
     expect(session.getSnapshot().promptError).toMatchObject({ op: 'stop', error: { code: 'internal' } })
   })
+
+  it('reads session-authorized attachment bytes and keeps the opaque id on the wire', async () => {
+    const { api, session } = makeSession()
+    const result = await session.readAttachment('attachment-1' as never)
+    expect(result).toEqual({
+      ok: true,
+      value: {
+        attachment: { attachmentId: 'a', mediaType: 'image/png', bytes: 1, width: 1, height: 1 },
+        data: Uint8Array.of(0),
+      },
+    })
+    expect(api.callsOf('session.attachment')).toEqual([{
+      sessionId: SID, attachmentId: 'attachment-1',
+    }])
+  })
 })
 
 describe('pending interactions', () => {

packages/client/runtime/tsconfig.json

@@ -8,6 +8,9 @@
     "src"
   ],
   "references": [
+    {
+      "path": "../../attachment/attachment"
+    },
     {
       "path": "../../../vendor/cordis"
     },