feat(sdk): support max output tokens

packages/core/agent-loop/README.i18n.yaml

@@ -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/core/agent-loop/README.md
-README.md: c12140f27aed400b0f7b4246700473e877d37632
-README.zh.md: 6394cd86f5f3241be07ef711c76079624bce1bfe
+README.md: cd8b76a0d4f181bdf4620a4a17c9725ff1132c3b
+README.zh.md: d145dc785da8d78d24bc6bc014fb04ba005149fb

packages/core/agent-loop/README.md

@@ -42,13 +42,14 @@ interface Config {
     id: string                 // required
     provider?: string
     model?: string
+    maxTokens?: number         // positive per-request output-token cap
     resumeSessionId?: string   // load this persisted session instead of creating one
     cwd?: string               // optional workspace cwd for the fresh session
   }>
 }
 ```
 
-Configured agents start automatically. A model call requires both `provider` and `model`; `agent/request` may supply a missing pair before dispatch. `maxParallelToolCalls` bounds every agent's rolling pool for parallel-safe calls and defaults to `10`. `cwd` applies only to fresh sessions, while `resumeSessionId` retains persisted metadata. Configured agents use the deployment persona, and programmatic setup can shadow it per agent. This plugin supplies the per-agent `provider`, `model`, and `cwd` prompt variables; harness identity and deployment persona belong to `dsh-system-prompt`.
+Configured agents start automatically. A model call requires both `provider` and `model`; `agent/request` may supply a missing pair before dispatch. An optional positive `maxTokens` seeds each conversation request's output cap and is logged in its request header. `maxParallelToolCalls` bounds every agent's rolling pool for parallel-safe calls and defaults to `10`. `cwd` applies only to fresh sessions, while `resumeSessionId` retains persisted metadata. Configured agents use the deployment persona, and programmatic setup can shadow it per agent. This plugin supplies the per-agent `provider`, `model`, and `cwd` prompt variables; harness identity and deployment persona belong to `dsh-system-prompt`.
 
 ### Internal concrete driver
 

packages/core/agent-loop/README.zh.md

@@ -42,13 +42,14 @@ interface Config {
     id: string                 // required
     provider?: string
     model?: string
+    maxTokens?: number         // positive per-request output-token cap
     resumeSessionId?: string   // load this persisted session instead of creating one
     cwd?: string               // optional workspace cwd for the fresh session
   }>
 }
 ```
 
-通过配置创建的 agent 会自动启动。模型调用同时需要 `provider` 和 `model`；`agent/request` 可以在分发前补齐缺失的这一对值。`maxParallelToolCalls` 限制每个 agent 针对并行安全调用使用的滚动池，默认值为 `10`。`cwd` 仅应用于全新会话，而 `resumeSessionId` 保留持久化元数据。通过配置创建的 agent 使用部署 persona；编程式 setup 可以按 agent 遮蔽它。该插件提供逐 agent 的 `provider`、`model` 和 `cwd` 提示词变量；harness 身份与部署 persona 属于 `dsh-system-prompt`。
+通过配置创建的 agent 会自动启动。模型调用同时需要 `provider` 和 `model`；`agent/request` 可以在分发前补齐缺失的这一对值。可选的正整数 `maxTokens` 会为每次对话请求提供初始输出上限，并记录在请求 header 中。`maxParallelToolCalls` 限制每个 agent 针对并行安全调用使用的滚动池，默认值为 `10`。`cwd` 仅应用于全新会话，而 `resumeSessionId` 保留持久化元数据。通过配置创建的 agent 使用部署 persona；编程式 setup 可以按 agent 遮蔽它。该插件提供逐 agent 的 `provider`、`model` 和 `cwd` 提示词变量；harness 身份与部署 persona 属于 `dsh-system-prompt`。
 
 ### 包内部实体驱动器
 

packages/core/agent-loop/src/agent.ts

@@ -577,11 +577,16 @@ export class ReactLoopAgent implements Agent {
       && persistedConfig.model === route.model
       ? persistedConfig.reasoningEffort
       : undefined
+    const maxTokens = this.options.maxTokens
     const seedConfig = deepFreeze(structuredClone(
       this.requestHeaderLogged
         // eslint-disable-next-line @typescript-eslint/no-non-null-assertion -- the instance logged the header it now folds
         ? persistedConfig!
-        : { ...route, ...reasoningEffort === undefined ? {} : { reasoningEffort } },
+        : {
+          ...route,
+          ...reasoningEffort === undefined ? {} : { reasoningEffort },
+          ...maxTokens === undefined ? {} : { maxTokens },
+        },
     ))
     const proposedConfig = await this.loopCtx.waterfall(
       agentCarrier(this), 'agent/request', this, turn, step, signal,

packages/core/agent-loop/src/index.ts

@@ -112,6 +112,14 @@ function resolveMaxParallelToolCalls(value: number | undefined): number {
   return maxParallelToolCalls
 }
 
+/** Reject an output-token cap that cannot be represented exactly on the request wire. */
+function assertAgentOptions(options: AgentOptions): void {
+  if (options.maxTokens !== undefined
+    && (!Number.isSafeInteger(options.maxTokens) || options.maxTokens <= 0)) {
+    throw new TypeError('agent maxTokens must be a positive safe integer')
+  }
+}
+
 /** Prepared-but-unpublished agent resources sharing one memoized teardown. */
 interface PreparedAgent {
   agent: ReactLoopAgent
@@ -196,6 +204,7 @@ export class AgentLoop extends Service implements AgentFactory {
       sessionId: z.string().min(1),
       provider: z.string(),
       model: z.string(),
+      maxTokens: z.number().step(1).min(1).max(Number.MAX_SAFE_INTEGER),
       cwd: z.string(),
       resumeSessionId: z.string(),
     })).default([]),
@@ -327,6 +336,7 @@ export class AgentLoop extends Service implements AgentFactory {
    * fuses caller cancellation with lifecycle teardown for setup awaits.
    */
   private prepare(ownerCtx: Context, id: SessionId, options: AgentOptions, session: Session, callerSignal?: AbortSignal): PreparedAgent {
+    assertAgentOptions(options)
     ownerCtx.fiber.assertActive()
     // Every caller reaches prepare() synchronously from a service method
     // whose Cordis dispatch already requires the live factory fiber, or

packages/core/agent-loop/tests/loop.spec.ts

@@ -46,6 +46,19 @@ function send(agent: Agent, text: string) {
 }
 
 describe('agent loop', () => {
+  it.each([0, -1, 1.5, Number.NaN, Number.MAX_SAFE_INTEGER + 1])(
+    'rejects invalid AgentOptions.maxTokens %s before publication',
+    async (maxTokens) => {
+      const ctx = await harness(new MockAdapter([]))
+      expect(() => ctx.agentLoop.create(
+        SessionId('invalid-max-tokens'),
+        { provider: 'mock', model: 'mock', maxTokens },
+      )).toThrow('agent maxTokens must be a positive safe integer')
+      expect(ctx.agents.list()).toEqual([])
+      expect(ctx.sessions.list()).toEqual([])
+    },
+  )
+
   it('runs a simple turn: queued message → model → idle, with ordered events', async () => {
     const adapter = new MockAdapter([textResponse('hello there')])
     const ctx = await harness(adapter)