feat(sdk): support max output tokens
This commit is contained in:
@@ -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/ui/jsonrpc/README.md
|
||||
README.md: 48eb6106fe4b015f114b264a312249a92128266f
|
||||
README.zh.md: 8ec2d57a206d770d0b77ee69036457e3b2864303
|
||||
README.md: b1219ba10269fc7d046da22c280ff1b91424a5ae
|
||||
README.zh.md: 63615654769bf4ed7a69c09dc818af034c3a3c3c
|
||||
|
||||
@@ -22,7 +22,7 @@ The plugin answers `shutdown`, disposes SDK-owned agents and subscriptions to qu
|
||||
|
||||
## Wire notes
|
||||
|
||||
`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime`. A session accepts one in-flight prompt; overlap fails immediately, other sessions remain independent, and the session is reusable after settlement. `session.finished` reports that prompt's message-triggered turn outcome; later between-turn records still stream as `session.event` notifications but cannot replace the prompt status. Persistence roots and persona come from `cordis.yml`.
|
||||
`initialize.serverInfo.name` is the wire-stable `deepseek-harness-sdk-runtime`. An optional positive `initialize.maxTokens` becomes the request output cap of each SDK-created agent and its in-process descendants; invalid values reject initialization, while omission sends no cap and preserves provider defaults. A session accepts one in-flight prompt; overlap fails immediately, other sessions remain independent, and the session is reusable after settlement. `session.finished` reports that prompt's message-triggered turn outcome; later between-turn records still stream as `session.event` notifications but cannot replace the prompt status. Persistence roots and persona come from `cordis.yml`.
|
||||
|
||||
## Model Experience
|
||||
|
||||
|
||||
@@ -22,7 +22,7 @@ Stdout 只承载 JSON-RPC 帧。部署不得组合 stdout logger;诊断应写
|
||||
|
||||
## 协议说明
|
||||
|
||||
`initialize.serverInfo.name` 的协议稳定值为 `deepseek-harness-sdk-runtime`。一个会话只接受一个进行中的提示词;重叠请求会立即失败,其他会话保持独立,当前请求结算后该会话可再次使用。`session.finished` 报告由该提示词消息触发的轮次结果;后续轮次间记录仍会作为 `session.event` 通知流式发出,但不能替换该提示词的状态。持久化根目录和 persona 由 `cordis.yml` 提供。
|
||||
`initialize.serverInfo.name` 的协议稳定值为 `deepseek-harness-sdk-runtime`。可选的正整数 `initialize.maxTokens` 会成为每个 SDK 创建的 agent 及其进程内后代的请求输出上限;非法值会使初始化失败,省略时则不发送上限并保留提供方默认值。一个会话只接受一个进行中的提示词;重叠请求会立即失败,其他会话保持独立,当前请求结算后该会话可再次使用。`session.finished` 报告由该提示词消息触发的轮次结果;后续轮次间记录仍会作为 `session.event` 通知流式发出,但不能替换该提示词的状态。持久化根目录和 persona 由 `cordis.yml` 提供。
|
||||
|
||||
## 模型体验
|
||||
|
||||
|
||||
@@ -56,6 +56,7 @@ export class HarnessSdkServer {
|
||||
private cwd = process.cwd()
|
||||
private provider = 'deepseek'
|
||||
private model = 'deepseek'
|
||||
private maxTokens: number | undefined
|
||||
private llmFiber: { dispose(): Promise<void> } | undefined
|
||||
private readonly sessions = new Map<string, SessionRecord>()
|
||||
private readonly sessionCreations = new Map<string, Promise<SessionRecord>>()
|
||||
@@ -113,9 +114,14 @@ export class HarnessSdkServer {
|
||||
* @returns server identity for the handshake.
|
||||
*/
|
||||
async initialize(params: InitializeParams): Promise<InitializeResult> {
|
||||
if (params.maxTokens !== undefined
|
||||
&& (!Number.isSafeInteger(params.maxTokens) || params.maxTokens <= 0)) {
|
||||
throw new TypeError('initialize maxTokens must be a positive safe integer')
|
||||
}
|
||||
this.cwd = resolve(params.cwd)
|
||||
this.provider = params.provider
|
||||
this.model = params.model
|
||||
this.maxTokens = params.maxTokens
|
||||
if (!this.hasAdapterFor(this.provider)) {
|
||||
if (this.provider !== 'deepseek') throw new Error(`no adapter registered for provider "${this.provider}"`)
|
||||
this.llmFiber = await this.ctx.plugin(LlmDeepSeek, {})
|
||||
@@ -231,7 +237,11 @@ export class HarnessSdkServer {
|
||||
const handle = await this.ctx.agents.create({
|
||||
sessionId: SessionId(sessionId),
|
||||
meta: { cwd: this.cwd },
|
||||
agentOptions: { provider: this.provider, model: this.model },
|
||||
agentOptions: {
|
||||
provider: this.provider,
|
||||
model: this.model,
|
||||
...this.maxTokens === undefined ? {} : { maxTokens: this.maxTokens },
|
||||
},
|
||||
})
|
||||
const rec: SessionRecord = { handle, lastTurnEnd: undefined, activePrompt: false }
|
||||
this.sessions.set(sessionId, rec)
|
||||
|
||||
@@ -122,6 +122,7 @@ describe('HarnessSdkServer', () => {
|
||||
cwd: storageDir,
|
||||
provider: 'deepseek',
|
||||
model: 'dsagent-model',
|
||||
maxTokens: 321,
|
||||
}) as { serverInfo: { name: string } }
|
||||
expect(init.serverInfo.name).toBe('deepseek-harness-sdk-runtime')
|
||||
|
||||
@@ -131,8 +132,9 @@ describe('HarnessSdkServer', () => {
|
||||
})
|
||||
|
||||
expect(llmServer.requests).toHaveLength(1)
|
||||
const body = llmServer.requests[0] as { model: string; messages: { role: string }[] }
|
||||
const body = llmServer.requests[0] as { model: string; messages: { role: string }[]; max_tokens?: number }
|
||||
expect(body.model).toBe('dsagent-model')
|
||||
expect(body.max_tokens).toBe(321)
|
||||
expect(body.messages[0]?.role).toBe('system')
|
||||
expect(body.messages.at(-1)?.role).toBe('user')
|
||||
expect(llmServer.headers[0]?.authorization).toBe('Bearer test-key')
|
||||
@@ -859,6 +861,27 @@ describe('HarnessSdkServer', () => {
|
||||
}
|
||||
})
|
||||
|
||||
it.each([0, -1, 1.5, Number.NaN, Number.MAX_SAFE_INTEGER + 1])(
|
||||
'rejects invalid initialize maxTokens %s at the wire boundary',
|
||||
async (maxTokens) => {
|
||||
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-invalid-max-tokens-'))
|
||||
const ctx = await makeHarness(storageDir)
|
||||
try {
|
||||
const server = new HarnessSdkServer(ctx, new FakeTransport())
|
||||
await expect(server.initialize({
|
||||
cwd: storageDir,
|
||||
provider: 'deepseek',
|
||||
model: 'model',
|
||||
maxTokens,
|
||||
})).rejects.toThrow('initialize maxTokens must be a positive safe integer')
|
||||
await server.shutdown()
|
||||
} finally {
|
||||
await ctx.fiber.dispose()
|
||||
await rm(storageDir, { recursive: true, force: true })
|
||||
}
|
||||
},
|
||||
)
|
||||
|
||||
it('classifies defensive finish states', async () => {
|
||||
const storageDir = await mkdtemp(join(tmpdir(), 'dsh-jsonrpc-finish-states-'))
|
||||
const ctx = await makeHarness(storageDir)
|
||||
@@ -973,15 +996,18 @@ describe('HarnessSdkServer', () => {
|
||||
get: () => ({ listProviders: () => [{ id: 'mock', name: 'Mock' }] }),
|
||||
} as unknown as Context
|
||||
const server = new HarnessSdkServer(ctx, new FakeTransport()) as unknown as {
|
||||
initialize(params: { cwd: string; provider: string; model: string }): Promise<unknown>
|
||||
initialize(params: { cwd: string; provider: string; model: string; maxTokens?: number }): Promise<unknown>
|
||||
getOrCreateSession(sessionId: string): Promise<unknown>
|
||||
shutdown(): Promise<Record<string, never>>
|
||||
}
|
||||
|
||||
await server.initialize({ cwd: '.', provider: 'mock', model: 'model' })
|
||||
await server.initialize({ cwd: '.', provider: 'mock', model: 'model', maxTokens: 123 })
|
||||
await server.getOrCreateSession('relative')
|
||||
|
||||
expect(create).toHaveBeenCalledWith(expect.objectContaining({ meta: { cwd: process.cwd() } }))
|
||||
expect(create).toHaveBeenCalledWith(expect.objectContaining({
|
||||
meta: { cwd: process.cwd() },
|
||||
agentOptions: { provider: 'mock', model: 'model', maxTokens: 123 },
|
||||
}))
|
||||
await server.shutdown()
|
||||
})
|
||||
|
||||
|
||||
Reference in New Issue
Block a user