Add web multimodal image attachments

This commit is contained in:
Yichen Jiang
2026-07-23 15:20:47 +08:00
parent 3e3ea47296
commit cb4c11b869
116 files changed
+3177 -151

No files matched your search

@@ -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 }
}
@@ -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.