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
This commit is contained in:
Tianyi Cui
@@ -2,5 +2,5 @@
|
||||
# side as of the last confirmed-consistent state. Both languages carry equal authority;
|
||||
# after editing either side, bring the other along and re-record with:
|
||||
# pnpm run verify-translation-pairing --write packages/host/apiproxy/README.md
|
||||
README.md: b5f80dcb3a077a411db3b721737a9c16b56fcecf
|
||||
README.zh.md: 1c3c7486f7d500f8c2d36028d47f29b112d9b5ae
|
||||
README.md: 1f0daedc54888a1951bc83c474f83287aaf42307
|
||||
README.zh.md: abf5417cdbe93f1199c621ac101249986969da93
|
||||
|
||||
@@ -22,7 +22,7 @@ Directory picking delegates to the composed `ctx.directoryPicker` backend ([the
|
||||
|
||||
`host.openPath` opens a filesystem path with the operating system's default application (`open` on macOS, `Invoke-Item` on Windows, `xdg-open` on Linux). The opener is injectable for tests. The browser carrier applies the same loopback, same-origin restriction as `host.pickDirectory`.
|
||||
|
||||
The `command.*` and `skill.*` domains expose the host command registry and skill catalog to clients. Every method addresses one session's agent by `sessionId` (a served session always has an Agent; `command.*` resumes cold sessions through the same path as `session.*`, while `skill.list` resolves the project root from the session header without touching the Agent registry). `command.execute` runs a slash-command line host-side with pure admission semantics: the response reports whether the line resolved to a handler plus the minted lifecycle `commandId` when it did (correlating the acknowledgment with the flow node), while the outcome rides the durably logged `command/run`/`command/done` lifecycle pair broadcast on the mux stream; the carrier's request signal cancels the running handler. `host/commands-changed` is the catalog invalidation frame: clients refetch `command.list` instead of diffing.
|
||||
The `command.*` and `skill.*` domains expose the host command registry and skill catalog to clients. Every method addresses one session's agent by `sessionId` (a served session always has an Agent; `command.*` resumes cold sessions through the same path as `session.*`, while `skill.list` resolves the project root from the session header without touching the Agent registry). `skill.list` serves the browser's user-selected model-reference path, so it returns only skills that are both model-invocable and user-invocable; this domain has no direct skill-loading RPC. `command.execute` runs a slash-command line host-side with pure admission semantics: the response reports whether the line resolved to a handler plus the minted lifecycle `commandId` when it did (correlating the acknowledgment with the flow node), while the outcome rides the durably logged `command/run`/`command/done` lifecycle pair broadcast on the mux stream; the carrier's request signal cancels the running handler. `host/commands-changed` is the catalog invalidation frame: clients refetch `command.list` instead of diffing.
|
||||
|
||||
## Carrier layer (`/client` + root)
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@ Workspace 列表与 Session 列表是相互独立的重连基线。`workspace.cr
|
||||
|
||||
`host.openPath` 会用操作系统的默认应用打开一个文件系统路径（macOS 为 `open`，Windows 为 `Invoke-Item`，Linux 为 `xdg-open`）。打开器可在测试中注入。浏览器载体对其施加与 `host.pickDirectory` 相同的回环、同源限制。
|
||||
|
||||
`command.*` 与 `skill.*` 领域向客户端暴露宿主命令注册表和技能目录。每个方法都通过 `sessionId` 寻址一个会话的 Agent（被服务的会话必有 Agent；`command.*` 经由与 `session.*` 相同的路径恢复冷会话，而 `skill.list` 从会话头解析项目根目录，不触碰 Agent 注册表）。`command.execute` 在宿主侧运行一条斜杠命令行，语义为纯准入：响应报告该行是否解析到处理器，并在解析到时回带铸造的生命周期 `commandId`（将本次确认与流节点关联）；结局经由持久落账并在 mux 流广播的 `command/run`/`command/done` 生命周期事件对承载；载体的请求信号可取消正在运行的处理器。`host/commands-changed` 是目录失效帧：客户端重新拉取 `command.list` 而不是做差分。
|
||||
`command.*` 与 `skill.*` 领域向客户端暴露宿主命令注册表和技能目录。每个方法都通过 `sessionId` 寻址一个会话的 Agent（被服务的会话必有 Agent；`command.*` 经由与 `session.*` 相同的路径恢复冷会话，而 `skill.list` 从会话头解析项目根目录，不触碰 Agent 注册表）。`skill.list` 服务于浏览器中由用户选择的模型引用路径，因此仅返回模型和用户均可调用的 skill；该领域没有直接加载 skill 的 RPC。`command.execute` 在宿主侧运行一条斜杠命令行，语义为纯准入：响应报告该行是否解析到处理器，并在解析到时回带铸造的生命周期 `commandId`（将本次确认与流节点关联）；结局经由持久落账并在 mux 流广播的 `command/run`/`command/done` 生命周期事件对承载；载体的请求信号可取消正在运行的处理器。`host/commands-changed` 是目录失效帧：客户端重新拉取 `command.list` 而不是做差分。
|
||||
|
||||
## 载体层（`/client` + 根路径）
|
||||
|
||||
|
||||
@@ -1425,10 +1425,6 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
cwd: defaults.cwd,
|
||||
provider: defaults.provider,
|
||||
model: defaults.model,
|
||||
imageLimits: {
|
||||
...ctx.attachments.imageLimits,
|
||||
mediaTypes: [...ctx.attachments.imageLimits.mediaTypes],
|
||||
},
|
||||
attachedSessions: ctx.agents.list().length,
|
||||
}))
|
||||
},
|
||||
@@ -1642,7 +1638,8 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
|
||||
return err(request, { code: 'internal', message: 'skill registry is absent: this deployment does not mount @deepseek-ai/dsh-skill in its composition (cordis.yml or explicit assembly)', details: {} })
|
||||
}
|
||||
try {
|
||||
const skills = await skillRegistry.list({ cwd })
|
||||
const skills = (await skillRegistry.list({ cwd }))
|
||||
.filter(skill => skill.invocation.modelInvocable && skill.invocation.userInvocable)
|
||||
return ok(request, {
|
||||
skills: skills.map(skill => ({
|
||||
name: skill.name,
|
||||
|
||||
@@ -6,7 +6,6 @@ import { z } from 'zod'
|
||||
import type { DirectoryEntry } from './host.ts'
|
||||
import type { RequestPayload, ResponseValue } from './rpc-map.ts'
|
||||
import type { Wire } from './rpc.schema.ts'
|
||||
import { imageMediaTypeSchema } from './sessions.schema.ts'
|
||||
|
||||
/** host.describe request payload (empty object literal). */
|
||||
export const hostDescribeRequestSchema = z.object({}) satisfies z.ZodType<Wire<RequestPayload<'host.describe'>>>
|
||||
@@ -17,13 +16,6 @@ export const hostDescribeValueSchema = z.object({
|
||||
cwd: z.string(),
|
||||
provider: z.string().optional(),
|
||||
model: z.string().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'>>>
|
||||
|
||||
|
||||
@@ -4,7 +4,6 @@
|
||||
*/
|
||||
|
||||
import type { RpcRequest, RpcResponse } from './rpc.ts'
|
||||
import type { ImageAttachmentLimits } from '@deepseek-ai/dsh-attachment'
|
||||
|
||||
/** One directory row of a listing: a child entry or a breadcrumb ancestor. */
|
||||
export interface DirectoryEntry {
|
||||
@@ -48,8 +47,6 @@ export interface HostApi {
|
||||
cwd: string
|
||||
provider?: string
|
||||
model?: string
|
||||
/** Resolved authoritative image-upload limits. */
|
||||
imageLimits?: ImageAttachmentLimits
|
||||
attachedSessions: number
|
||||
}>>
|
||||
|
||||
|
||||
@@ -20,6 +20,6 @@ export interface SkillEntry {
|
||||
|
||||
/** Skill-domain unary methods (the map key skill.* of RpcMethodMap). */
|
||||
export interface SkillsApi {
|
||||
/** Lists model-invocable skills for the addressed session's project root. */
|
||||
/** Lists skills usable by the browser's user-selected model-reference path. */
|
||||
list(request: RpcRequest<{ sessionId: SessionId }>): Promise<RpcResponse<{ skills: readonly SkillEntry[] }>>
|
||||
}
|
||||
|
||||
@@ -184,10 +184,28 @@ describe('skill.list', () => {
|
||||
name: 'probe',
|
||||
list: (options) => {
|
||||
seenCwds.push(options.cwd)
|
||||
return Promise.resolve([{
|
||||
name: 'commit-helper', description: 'Git commits', whenToUse: 'when committing',
|
||||
source: 'custom', provider: 'probe', rank: 0, locator: null,
|
||||
}])
|
||||
return Promise.resolve([
|
||||
{
|
||||
name: 'commit-helper', description: 'Git commits', whenToUse: 'when committing',
|
||||
invocation: { modelInvocable: true, userInvocable: true },
|
||||
source: 'custom', provider: 'probe', rank: 0, locator: null,
|
||||
},
|
||||
{
|
||||
name: 'user-only', description: 'User-only',
|
||||
invocation: { modelInvocable: false, userInvocable: true },
|
||||
source: 'custom', provider: 'probe', rank: 0, locator: null,
|
||||
},
|
||||
{
|
||||
name: 'model-only', description: 'Model-only',
|
||||
invocation: { modelInvocable: true, userInvocable: false },
|
||||
source: 'custom', provider: 'probe', rank: 0, locator: null,
|
||||
},
|
||||
{
|
||||
name: 'trusted-only', description: 'Trusted-only',
|
||||
invocation: { modelInvocable: false, userInvocable: false },
|
||||
source: 'custom', provider: 'probe', rank: 0, locator: null,
|
||||
},
|
||||
])
|
||||
},
|
||||
get: () => Promise.resolve(undefined),
|
||||
}))
|
||||
|
||||
@@ -7,12 +7,6 @@ import { RpcId } from '../src/api/rpc.ts'
|
||||
import { toFetchHandler } from '../src/fetch/handler.ts'
|
||||
import { AbstractApiClient, InProcessApiClient } from '../src/fetch/client.ts'
|
||||
|
||||
declare module '@deepseek-ai/dsh-llm' {
|
||||
interface ModelModalityMap {
|
||||
audio: 'audio'
|
||||
}
|
||||
}
|
||||
|
||||
/** Minimal in-memory ApiProxy: echoes rpcIds, scripts one frame per stream. */
|
||||
function fakeApi(overrides: Partial<{
|
||||
muxFrames: MuxFrame[]
|
||||
@@ -259,26 +253,6 @@ describe('unary round trip (handler ⇄ client, no network)', () => {
|
||||
expect((await c.host.describe({})).result.ok).toBe(true)
|
||||
})
|
||||
|
||||
it('round-trips a declaration-merged model modality through host.describe', async () => {
|
||||
const c = client(fakeApi({
|
||||
hostDescription: {
|
||||
version: 'v',
|
||||
cwd: '/w',
|
||||
attachedSessions: 0,
|
||||
},
|
||||
}))
|
||||
|
||||
const response = await c.host.describe({})
|
||||
expect(response.result).toEqual({
|
||||
ok: true,
|
||||
value: {
|
||||
version: 'v',
|
||||
cwd: '/w',
|
||||
attachedSessions: 0,
|
||||
},
|
||||
})
|
||||
})
|
||||
|
||||
it('round-trips the native picker without the default unary timeout', async () => {
|
||||
const api = fakeApi()
|
||||
api.host.pickDirectory = async (request) => {
|
||||
|
||||
@@ -242,7 +242,7 @@ describe('sessions domain schemas', () => {
|
||||
})
|
||||
|
||||
describe('host domain schemas', () => {
|
||||
it('validates describe request/value and preserves merge-extensible modalities', () => {
|
||||
it('validates describe request/value', () => {
|
||||
expect(hostDescribeRequestSchema.parse({})).toEqual({})
|
||||
const value = hostDescribeValueSchema.parse({
|
||||
version: '1',
|
||||
|
||||
Reference in New Issue
Block a user