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 changed files with 3177 additions and 151 deletions

View File

@@ -40,6 +40,7 @@
],
"license": "BSD-3-Clause",
"dependencies": {
"@deepseek-ai/dsh-attachment": "workspace:^",
"@deepseek-ai/dsh-brand": "workspace:^",
"@deepseek-ai/dsh-llm": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",

View File

@@ -5,6 +5,9 @@
import { z } from 'zod'
import type { RequestPayload, ResponseValue } from './rpc-map.ts'
import type { Wire } from './rpc.schema.ts'
import { imageMediaTypeSchema } from './sessions.schema.ts'
const modalitySchema = z.union([z.literal('text'), z.literal('image')])
/** host.describe request payload (empty object literal). */
export const hostDescribeRequestSchema = z.object({}) satisfies z.ZodType<Wire<RequestPayload<'host.describe'>>>
@@ -15,5 +18,20 @@ export const hostDescribeValueSchema = z.object({
cwd: z.string(),
provider: z.string().optional(),
model: z.string().optional(),
activeModel: z.object({
provider: z.string(),
id: z.string(),
name: z.string(),
description: z.string().optional(),
inputModalities: z.array(modalitySchema).optional(),
outputModalities: z.array(modalitySchema).optional(),
}).optional(),
imageLimits: z.object({
maxImageBytes: z.number().int().positive(),
maxImagesPerMessage: z.number().int().positive(),
maxMessageImageBytes: z.number().int().positive(),
maxImagePixels: z.number().int().positive(),
mediaTypes: z.array(imageMediaTypeSchema),
}).optional(),
attachedSessions: z.number().int().nonnegative(),
}) satisfies z.ZodType<Wire<ResponseValue<'host.describe'>>>

View File

@@ -4,6 +4,8 @@
*/
import type { RpcRequest, RpcResponse } from './rpc.ts'
import type { ImageAttachmentLimits } from '@deepseek-ai/dsh-attachment'
import type { LlmModelInfo } from '@deepseek-ai/dsh-llm/types'
/** Host-level unary methods. */
export interface HostApi {
@@ -20,6 +22,10 @@ export interface HostApi {
cwd: string
provider?: string
model?: string
/** Catalog entry for the active route; absent means its capabilities are unknown. */
activeModel?: LlmModelInfo
/** Resolved authoritative image-upload limits. */
imageLimits?: ImageAttachmentLimits
attachedSessions: number
}>>
}

View File

@@ -19,7 +19,7 @@ export interface ApiProxy {
}
// ---- Domain interfaces and payload entities ----
export type { HistoryEntry, SessionsApi, SessionSummary } from './sessions.ts'
export type { HistoryEntry, PromptContentPart, SessionsApi, SessionSummary } from './sessions.ts'
export type { HostApi } from './host.ts'
export type { EventsApi, MuxFrame, HostFrame, ToolCallView, ToolEventView, ToolResultView } from './events.ts'
export type { ApprovalResponsePayload } from './approvals.ts'

View File

@@ -14,6 +14,7 @@ export interface RpcMethodMap {
'session.create': SessionsApi['create']
'session.history': SessionsApi['history']
'session.prompt': SessionsApi['prompt']
'session.attachment': SessionsApi['attachment']
'session.cancel': SessionsApi['cancel']
'host.describe': HostApi['describe']
}

View File

@@ -35,6 +35,7 @@ export const rpcErrorSchema: z.ZodType<RpcError> = z.discriminatedUnion('code',
z.object({ code: z.literal('bad-request'), message: z.string(), details: z.object({ issues: z.array(z.custom<ZodIssue>()) }) }),
z.object({ code: z.literal('session-not-found'), message: z.string(), details: z.object({ sessionId: z.string() }) }),
z.object({ code: z.literal('agent-busy'), message: z.string(), details: z.object({ reason: z.string() }) }),
z.object({ code: z.literal('attachment-error'), message: z.string(), details: z.object({ reason: z.string() }) }),
z.object({ code: z.literal('internal'), message: z.string(), details: z.object({}) }),
]) as unknown as z.ZodType<RpcError>

View File

@@ -32,6 +32,7 @@ export interface RpcErrorDetailsMap {
'bad-request': { issues: ZodIssue[] }
'session-not-found': { sessionId: SessionId }
'agent-busy': { reason: string }
'attachment-error': { reason: string }
'internal': {}
}

View File

@@ -11,6 +11,7 @@ import type { RequestPayload, ResponseValue } from './rpc-map.ts'
import type { Wire } from './rpc.schema.ts'
import type { HistoryEntry, SessionSummary } from './sessions.ts'
import type { ToolEventView } from './events.ts'
import type { AttachmentIdType, ImageAttachmentRef } from '@deepseek-ai/dsh-attachment'
/** SessionId: one brand cast after shape validation (the only cast point in this domain). */
export const sessionIdSchema = z.string().min(1) as unknown as z.ZodType<SessionId>
@@ -84,14 +85,25 @@ export const sessionHistoryValueSchema = z.object({
hasMore: z.boolean(),
}) satisfies z.ZodType<Wire<ResponseValue<'session.history'>>>
/** ContentBlock passthrough: core is merge-extensible — the type discriminant envelope is strict, the rest stays wide. */
export const contentBlockSchema = z.looseObject({ type: z.string() })
/** Raster image media types accepted by the version-one browser wire. */
export const imageMediaTypeSchema = z.union([
z.literal('image/png'),
z.literal('image/jpeg'),
z.literal('image/webp'),
z.literal('image/gif'),
])
/** Prompt wire content is intentionally narrower than merge-extensible durable core content. */
export const promptContentPartSchema = z.discriminatedUnion('type', [
z.object({ type: z.literal('text'), text: z.string() }),
z.object({ type: z.literal('image'), mediaType: imageMediaTypeSchema, data: z.string(), name: z.string().optional() }),
])
/** session.prompt request payload. */
export const sessionPromptRequestSchema = z.object({
sessionId: sessionIdSchema,
mode: z.union([z.literal('queue'), z.literal('steer')]),
content: z.array(contentBlockSchema),
content: z.array(promptContentPartSchema),
}) as unknown as z.ZodType<RequestPayload<'session.prompt'>>
/** session.prompt response value. */
@@ -99,6 +111,31 @@ export const sessionPromptValueSchema = z.object({
accepted: z.literal(true),
}) satisfies z.ZodType<Wire<ResponseValue<'session.prompt'>>>
/** Opaque attachment id after string-shape validation. */
export const attachmentIdSchema = z.string().min(1) as unknown as z.ZodType<AttachmentIdType>
/** Durable image reference returned from the authenticated session lookup. */
export const imageAttachmentRefSchema = z.object({
attachmentId: attachmentIdSchema,
mediaType: imageMediaTypeSchema,
bytes: z.number().int().positive(),
width: z.number().int().positive(),
height: z.number().int().positive(),
name: z.string().optional(),
}) as unknown as z.ZodType<ImageAttachmentRef>
/** session.attachment request payload. */
export const sessionAttachmentRequestSchema = z.object({
sessionId: sessionIdSchema,
attachmentId: attachmentIdSchema,
}) satisfies z.ZodType<Wire<RequestPayload<'session.attachment'>>>
/** session.attachment response value. */
export const sessionAttachmentValueSchema = z.object({
attachment: imageAttachmentRefSchema,
data: z.string(),
}) satisfies z.ZodType<Wire<ResponseValue<'session.attachment'>>>
/** session.cancel request payload. */
export const sessionCancelRequestSchema = z.object({
sessionId: sessionIdSchema,

View File

@@ -4,7 +4,7 @@
* else references RequestPayload<'session.*'> / ResponseValue<'session.*'>.
*/
import type { ContentBlock } from '@deepseek-ai/dsh-llm/types'
import type { AttachmentIdType, ImageAttachmentRef, ImageMediaType } from '@deepseek-ai/dsh-attachment'
import type { SessionEvent, SessionId } from '@deepseek-ai/dsh-session/types'
import type { RpcId, RpcRequest, RpcResponse } from './rpc.ts'
import type { ToolEventView } from './events.ts'
@@ -44,6 +44,11 @@ export interface SessionSummary {
cwd?: string
}
/** Browser-submitted prompt content; image bytes are promoted to durable references by the host. */
export type PromptContentPart =
| { type: 'text'; text: string }
| { type: 'image'; mediaType: ImageMediaType; data: string; name?: string }
/** Session-domain unary methods (the map keys session.* of RpcMethodMap). */
export interface SessionsApi {
/** Lists persisted sessions (updatedAt descending). v1 returns everything; cursor is a reserved seat, unimplemented. */
@@ -64,10 +69,14 @@ export interface SessionsApi {
history(request: RpcRequest<{ sessionId: SessionId; beforeSeq?: number; maxMessages?: number }>):
Promise<RpcResponse<{ events: HistoryEntry[]; hasMore: boolean }>>
/** Sends a message. content is core's ContentBlock[] verbatim; mode maps 1:1 — queue→send, steer→steer. */
prompt(request: RpcRequest<{ sessionId: SessionId; mode: 'queue' | 'steer'; content: ContentBlock[] }>):
/** Sends text plus temporary base64 image uploads; the host persists images before calling the agent. */
prompt(request: RpcRequest<{ sessionId: SessionId; mode: 'queue' | 'steer'; content: PromptContentPart[] }>):
Promise<RpcResponse<{ accepted: true }>>
/** Reads one durable image after proving that this session's log references its id. */
attachment(request: RpcRequest<{ sessionId: SessionId; attachmentId: AttachmentIdType }> ):
Promise<RpcResponse<{ attachment: ImageAttachmentRef; data: string }>>
/** Stops: clears both FIFOs + aborts the current step (1:1 with agent.cancel). */
cancel(request: RpcRequest<{ sessionId: SessionId }>): Promise<RpcResponse<{ accepted: true }>>
}

View File

@@ -16,6 +16,7 @@ import { hostFrameSchema, muxFrameSchema } from '../api/events.schema.ts'
import { hostDescribeValueSchema } from '../api/host.schema.ts'
import {
sessionCancelValueSchema,
sessionAttachmentValueSchema,
sessionCreateValueSchema,
sessionHistoryValueSchema,
sessionListValueSchema,
@@ -43,6 +44,7 @@ export interface IApiClient {
create(payload: RequestPayload<'session.create'>, signal?: AbortSignal): Promise<RpcResponse<ResponseValue<'session.create'>>>
history(payload: RequestPayload<'session.history'>, signal?: AbortSignal): Promise<RpcResponse<ResponseValue<'session.history'>>>
prompt(payload: RequestPayload<'session.prompt'>, signal?: AbortSignal): Promise<RpcResponse<ResponseValue<'session.prompt'>>>
attachment(payload: RequestPayload<'session.attachment'>, signal?: AbortSignal): Promise<RpcResponse<ResponseValue<'session.attachment'>>>
cancel(payload: RequestPayload<'session.cancel'>, signal?: AbortSignal): Promise<RpcResponse<ResponseValue<'session.cancel'>>>
}
host: {
@@ -65,6 +67,7 @@ const UNARY_VALUE_SCHEMAS: { [K in keyof RpcMethodMap]: z.ZodType<Wire<ResponseV
'session.create': sessionCreateValueSchema,
'session.history': sessionHistoryValueSchema,
'session.prompt': sessionPromptValueSchema,
'session.attachment': sessionAttachmentValueSchema,
'session.cancel': sessionCancelValueSchema,
'host.describe': hostDescribeValueSchema,
}
@@ -246,6 +249,7 @@ export abstract class AbstractApiClient implements IApiClient {
create: (payload, signal) => this.callUnary('session.create', payload, signal),
history: (payload, signal) => this.callUnary('session.history', payload, signal),
prompt: (payload, signal) => this.callUnary('session.prompt', payload, signal),
attachment: (payload, signal) => this.callUnary('session.attachment', payload, signal),
cancel: (payload, signal) => this.callUnary('session.cancel', payload, signal),
}

View File

@@ -16,6 +16,7 @@ import type { Wire } from '../api/rpc.schema.ts'
import { clientRequestSchema, clientResponseSchema } from '../api/rpc.schema.ts'
import {
sessionCancelRequestSchema,
sessionAttachmentRequestSchema,
sessionCreateRequestSchema,
sessionHistoryRequestSchema,
sessionListRequestSchema,
@@ -42,6 +43,7 @@ const UNARY_ROUTES: UnaryRoutes = {
'session.create': { schema: sessionCreateRequestSchema, invoke: (api, r) => api.sessions.create(r) },
'session.history': { schema: sessionHistoryRequestSchema, invoke: (api, r) => api.sessions.history(r) },
'session.prompt': { schema: sessionPromptRequestSchema, invoke: (api, r) => api.sessions.prompt(r) },
'session.attachment': { schema: sessionAttachmentRequestSchema, invoke: (api, r) => api.sessions.attachment(r) },
'session.cancel': { schema: sessionCancelRequestSchema, invoke: (api, r) => api.sessions.cancel(r) },
'host.describe': { schema: hostDescribeRequestSchema, invoke: (api, r) => api.host.describe(r) },
}

View File

@@ -30,6 +30,10 @@ function scriptedApi(overrides: {
create: r => ok(r, { sessionId: sid('s-new') }),
history: r => ok(r, { events: [], hasMore: false }),
prompt: r => ok(r, { accepted: true as const }),
attachment: r => ok(r, {
attachment: { attachmentId: 'a' as never, mediaType: 'image/png', bytes: 1, width: 1, height: 1 },
data: 'AA==',
}),
cancel: r => ok(r, { accepted: true as const }),
...overrides.sessions,
},

View File

@@ -33,6 +33,12 @@ function fakeApi(overrides: Partial<{ muxFrames: MuxFrame[]; hostFrames: HostFra
async prompt(request) {
return { rpcId: request.rpcId, result: { ok: true, value: { accepted: true as const } } }
},
async attachment(request) {
return {
rpcId: request.rpcId,
result: { ok: true, value: { attachment: { attachmentId: 'a' as never, mediaType: 'image/png' as const, bytes: 1, width: 1, height: 1 }, data: 'AA==' } },
}
},
async cancel(request) {
return { rpcId: request.rpcId, result: { ok: true, value: { accepted: true as const } } }
},

View File

@@ -6,7 +6,8 @@ import {
} from '../src/api/rpc.schema.ts'
import { z } from 'zod'
import {
contentBlockSchema, sessionCancelRequestSchema, sessionCancelValueSchema, sessionCreateRequestSchema,
promptContentPartSchema, sessionAttachmentRequestSchema, sessionAttachmentValueSchema,
sessionCancelRequestSchema, sessionCancelValueSchema, sessionCreateRequestSchema,
sessionCreateValueSchema, sessionEventSchema, sessionHistoryRequestSchema, sessionHistoryValueSchema,
sessionIdSchema, sessionListRequestSchema, sessionListValueSchema, sessionPromptRequestSchema,
sessionPromptValueSchema, sessionSummarySchema,
@@ -31,6 +32,7 @@ describe('rpcErrorSchema', () => {
expect(rpcErrorSchema.parse({ code: 'bad-request', message: 'm', details: { issues: [] } }).code).toBe('bad-request')
expect(rpcErrorSchema.parse({ code: 'session-not-found', message: 'm', details: { sessionId: 's' } }).code).toBe('session-not-found')
expect(rpcErrorSchema.parse({ code: 'agent-busy', message: 'm', details: { reason: 'r' } }).code).toBe('agent-busy')
expect(rpcErrorSchema.parse({ code: 'attachment-error', message: 'm', details: { reason: 'r' } }).code).toBe('attachment-error')
expect(rpcErrorSchema.parse({ code: 'internal', message: 'm', details: {} }).code).toBe('internal')
})
@@ -105,7 +107,20 @@ describe('sessions domain schemas', () => {
expect(sessionPromptValueSchema.parse({ accepted: true }).accepted).toBe(true)
expect(sessionCancelRequestSchema.parse({ sessionId: 's1' }).sessionId).toBe('s1')
expect(sessionCancelValueSchema.parse({ accepted: true }).accepted).toBe(true)
expect(contentBlockSchema.parse({ type: 'text', text: 'x', extra: 1 })).toMatchObject({ extra: 1 })
expect(promptContentPartSchema.parse({ type: 'text', text: 'x', extra: 1 })).toEqual({ type: 'text', text: 'x' })
expect(promptContentPartSchema.parse({
type: 'image', mediaType: 'image/png', data: 'AA==', name: 'pixel.png',
})).toMatchObject({ type: 'image', mediaType: 'image/png', name: 'pixel.png' })
const attachment = {
attachmentId: `sha256:${'a'.repeat(64)}`,
mediaType: 'image/png' as const,
bytes: 1,
width: 1,
height: 1,
}
expect(sessionAttachmentRequestSchema.parse({ sessionId: 's1', attachmentId: attachment.attachmentId }))
.toMatchObject({ sessionId: 's1' })
expect(sessionAttachmentValueSchema.parse({ attachment, data: 'AA==' }).attachment).toEqual(attachment)
})
})

View File

@@ -11,6 +11,9 @@
{
"path": "../../util/brand"
},
{
"path": "../../attachment/attachment"
},
{
"path": "../../llm/llm"
},