diff --git a/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.i18n.yaml b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.i18n.yaml new file mode 100644 index 0000000000..bdec24c41a --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.i18n.yaml @@ -0,0 +1,6 @@ +# Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each +# 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 .agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.md +2026-07-28-sdk-max-output-tokens.md: 5db48f21892d56addea7b72f73319f9dbfd1e71f +2026-07-28-sdk-max-output-tokens.zh.md: 38b172718716d100726188163ff22be9ea0a7325 diff --git a/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.md b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.md new file mode 100644 index 0000000000..5db48f2189 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.md @@ -0,0 +1,33 @@ +# Agent Note: SDK max output tokens + +Status: implemented + +English | [中文](2026-07-28-sdk-max-output-tokens.zh.md) + +## Problem + +The Python and TypeScript SDKs could select a provider and model but could not bound conversation-model output. The runtime therefore omitted `GenerateOptions.maxTokens`, leaving provider defaults in control even when an evaluation host required a fixed output budget. `compact-basic.maxTokens` could not fill this role because it limits only compaction-summary calls. + +## Decision + +The high-level SDKs expose one optional process-wide output cap: Python names it `max_tokens`, TypeScript names it `maxTokens`, and the shared `initialize` wire payload carries `maxTokens`. The JSON-RPC server rejects values that are not positive safe integers and stores the accepted cap with its provider/model route. + +Each SDK-created root Agent receives the cap through `AgentOptions.maxTokens`. Agent Loop places that value in the initial `LlmCallConfig`, logs it in the request header, and reconstructs every dispatched conversation request from that durable header. Omitting the option leaves `maxTokens` absent so the selected provider retains its default. + +In-process subagents inherit the parent's provider, model, and output cap. An explicit `SubagentStartRequest.agentOptions.maxTokens`, including one configured by `dsh-tool-subagent`, overrides the inherited value for that child and its descendants. Out-of-process providers own the configuration of their separate runtime; `subagent-dsh-sdk` therefore exposes its own optional `maxTokens` and forwards it through that child runtime's SDK handshake. + +Compaction, session-title generation, web search, and other auxiliary calls keep their independently owned output limits. `maxTokensAsSuccess` remains outcome mapping only: it does not set or alter the cap. + +## Alternatives considered + +**Set an adapter environment variable.** This would be DeepSeek-adapter-specific, invisible in the session request header, ineffective for intercepted or alternate adapters, and easy to confuse with a provider default. The cap belongs in provider-neutral request configuration. + +**Add `maxTokens` to every `session/prompt`.** Per-turn mutation would enlarge the wire and introduce request-config transitions that callers do not need for the current evaluation use case. A runtime initialization option gives every session in one SDK process the same reproducible budget. + +**Reuse `compact-basic.maxTokens`.** The compaction value controls summary generation, not ordinary conversation requests. Sharing it would couple two different token budgets and make tuning one silently change the other. + +## Consequences + +SDK callers can bound model output without editing Cordis composition, and direct Agent creation uses the same validated `AgentOptions` contract. The cap is visible in durable request headers and reaches provider adapters as `GenerateOptions.maxTokens`; DeepSeek serialization maps it to `max_tokens`. + +One SDK runtime has one default cap. A caller needing different caps runs separate runtime instances or explicitly overrides an in-process child through its agent options. Reaching the cap still produces the existing `max-tokens` stop reason, whose `ok` or `error` mapping remains deployment policy. diff --git a/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.zh.md b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.zh.md new file mode 100644 index 0000000000..38b1727187 --- /dev/null +++ b/.agents/notes/implemented/feature/2026-07-28-sdk-max-output-tokens.zh.md @@ -0,0 +1,33 @@ +# Agent Note: SDK 最大输出 token + +Status: implemented + +[English](2026-07-28-sdk-max-output-tokens.md) | 中文 + +## Problem + +Python 与 TypeScript SDK 可以选择提供方和模型，却无法限制对话模型输出。即使评测宿主要求固定输出预算，运行时仍会省略 `GenerateOptions.maxTokens`，由提供方默认值控制。`compact-basic.maxTokens` 只限制压缩摘要调用，不能承担这一职责。 + +## Decision + +高层 SDK 公开一个可选的进程级输出上限：Python 命名为 `max_tokens`，TypeScript 命名为 `maxTokens`，共享的 `initialize` 线载荷使用 `maxTokens`。JSON-RPC 服务端拒绝非正安全整数，并将通过校验的上限与提供方／模型路由一同保存。 + +每个由 SDK 创建的根 Agent 都通过 `AgentOptions.maxTokens` 获得该上限。Agent Loop 将它放入初始 `LlmCallConfig`、记录到请求 header，并从该持久化 header 重建每次分派的对话请求。省略该选项时，`maxTokens` 保持缺失，由所选提供方保留默认值。 + +进程内 subagent 继承父级的提供方、模型和输出上限。显式的 `SubagentStartRequest.agentOptions.maxTokens`（包括通过 `dsh-tool-subagent` 配置的值）会覆盖该子级及其后代的继承值。进程外提供方自行持有其独立运行时的配置；因此 `subagent-dsh-sdk` 公开独立的可选 `maxTokens`，并通过该子运行时自己的 SDK 握手传入。 + +压缩、会话标题生成、网页搜索和其他辅助调用继续使用各自持有的独立输出上限。`maxTokensAsSuccess` 仍然只负责结果映射，不会设置或改变上限。 + +## Alternatives considered + +**设置适配器环境变量。** 这种方式仅适用于 DeepSeek 适配器，不会出现在会话请求 header 中，对被拦截请求或其他适配器无效，也容易与提供方默认值混淆。该上限属于提供方无关的请求配置。 + +**在每个 `session/prompt` 上增加 `maxTokens`。** 按轮次修改会扩大线协议，并引入当前评测用例不需要的请求配置转换。运行时初始化选项可让一个 SDK 进程中的每个会话拥有相同、可重现的预算。 + +**复用 `compact-basic.maxTokens`。** 压缩值控制摘要生成，而非普通对话请求。共用会耦合两类不同 token 预算，调整一方时会静默改变另一方。 + +## Consequences + +SDK 调用方无需修改 Cordis 组合即可限制模型输出，直接创建 Agent 也使用同一套经过校验的 `AgentOptions` 契约。该上限在持久化请求 header 中可见，并以 `GenerateOptions.maxTokens` 到达提供方适配器；DeepSeek 序列化会将其映射为 `max_tokens`。 + +一个 SDK 运行时只有一个默认上限。需要不同上限的调用方应运行独立的 runtime 实例，或通过 agent options 显式覆盖某个进程内子级。达到上限时仍产生现有的 `max-tokens` 停止原因；将其映射为 `ok` 还是 `error` 仍由部署策略决定。 diff --git a/docs/config-catalog.md b/docs/config-catalog.md index 32a2a06d81..676054c215 100644 --- a/docs/config-catalog.md +++ b/docs/config-catalog.md @@ -108,7 +108,7 @@ export interface Config { Depends on: [`AgentOptions`](core-data-structures/core.md) · [`SessionId`](core-data-structures/core.md) -Source: [`packages/core/agent-loop/src/index.ts:147`](../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:155`](../packages/core/agent-loop/src/index.ts) ## `@deepseek-ai/dsh-agent-spine-demo` @@ -1397,6 +1397,8 @@ export interface Config { provider: string /** Model the child runtime initializes with (default `deepseek-v4-flash`). */ model: string + /** Optional per-request output-token cap for the child runtime. */ + maxTokens?: number /** * Extra environment variables for the child process — e.g. the child * runtime's own `DEEPSEEK_API_KEY`, or `DSH_CORDIS_CONFIG` naming its diff --git a/docs/cordis-catalog/events.md b/docs/cordis-catalog/events.md index a13a4f79cc..62f5ddfeb2 100644 --- a/docs/cordis-catalog/events.md +++ b/docs/cordis-catalog/events.md @@ -32,7 +32,7 @@ Effective broad cancellation was requested, before queued/outbox work is cleared Types: [Agent](../core-data-structures/core.md) · [AgentCancelCause](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:284`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:286`](../../packages/core/agent/src/types.ts) ### `agent/created` — emit @@ -54,7 +54,7 @@ A fully configured agent and live session were published. Setup is composition-o Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:216`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:218`](../../packages/core/agent/src/types.ts) ### `agent/disposed` — emit @@ -74,7 +74,7 @@ An agent left the registry; AgentLoop emits this after driver quiescence and sco Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:225`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:227`](../../packages/core/agent/src/types.ts) ### `agent/error` — emit @@ -96,7 +96,7 @@ A step or turn errored. The machine reports a failure here (plus the logger) eve Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:398`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:400`](../../packages/core/agent/src/types.ts) ### `agent/inbox/dequeue` — emit @@ -119,7 +119,7 @@ The driver claimed one item out of the inbox: a queued item at a turn boundary, Types: [Agent](../core-data-structures/core.md) · [InboxPlacement](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [UserMessage](../core-data-structures/session.md) -Source: [`packages/core/agent/src/types.ts:257`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:259`](../../packages/core/agent/src/types.ts) ### `agent/inbox/discard` — emit @@ -142,7 +142,7 @@ Pending inbox items were dropped without delivering them, so every enqueue occur Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [UserMessage](../core-data-structures/session.md) -Source: [`packages/core/agent/src/types.ts:274`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:276`](../../packages/core/agent/src/types.ts) ### `agent/inbox/enqueue` — emit @@ -164,7 +164,7 @@ An item entered the queued or steering inbox. `placement` is the acceptance-time Types: [Agent](../core-data-structures/core.md) · [InboxPlacement](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [UserMessage](../core-data-structures/session.md) -Source: [`packages/core/agent/src/types.ts:245`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:247`](../../packages/core/agent/src/types.ts) ### `agent/prompt-submit` — waterfall @@ -187,7 +187,7 @@ Allow, rewrite, or block one claimed prompt before it becomes a user message or Types: [Agent](../core-data-structures/core.md) · [PromptDecision](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [UserMessage](../core-data-structures/session.md) -Source: [`packages/core/agent/src/types.ts:311`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:313`](../../packages/core/agent/src/types.ts) ### `agent/request` — waterfall @@ -211,7 +211,7 @@ Replace the frozen call configuration. `await next()` yields the config the mach Types: [Agent](../core-data-structures/core.md) · [LlmCallConfig](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:337`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:339`](../../packages/core/agent/src/types.ts) ### `agent/request-error` — waterfall @@ -241,7 +241,7 @@ Handle a model-request failure after its failed step has closed but before the f Types: [Agent](../core-data-structures/core.md) · [LlmFailure](../core-data-structures/llm-streaming.md) · [RequestError](../core-data-structures/core.md) · [RequestErrorAction](../core-data-structures/core.md) · [ResolvedRetryPolicy](../core-data-structures/llm-streaming.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:356`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:358`](../../packages/core/agent/src/types.ts) ### `agent/session-start` — emit @@ -263,7 +263,7 @@ The session lifecycle began, once before the first turn. Use `agent.inject()` to Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [SessionStartSource](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:297`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:299`](../../packages/core/agent/src/types.ts) ### `agent/settled` — emit @@ -288,7 +288,7 @@ One drain chain reached its terminal turn: that turn's `turn/end` is already com Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) · [SettleReason](../core-data-structures/core.md) -Source: [`packages/core/agent/src/types.ts:385`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:387`](../../packages/core/agent/src/types.ts) ### `agent/status` — emit @@ -308,7 +308,7 @@ Agent status changed (`idle` ⇄ `running`). `send()` does not enter `running` s Types: [Agent](../core-data-structures/core.md) · [AgentStatus](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:234`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:236`](../../packages/core/agent/src/types.ts) ### `agent/step` — serial @@ -332,7 +332,7 @@ Awaited serial checkpoint before EVERY request of a turn is built (the first as Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:324`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:326`](../../packages/core/agent/src/types.ts) ### `agent/turn-stopping` — serial @@ -358,7 +358,7 @@ The turn is about to close: the model owes no response (no live tool calls, no f Types: [Agent](../core-data-structures/core.md) · [Scoped](../core-data-structures/scope.md) -Source: [`packages/core/agent/src/types.ts:371`](../../packages/core/agent/src/types.ts) +Source: [`packages/core/agent/src/types.ts:373`](../../packages/core/agent/src/types.ts) ## `agent-loop/*` @@ -381,7 +381,7 @@ A declarative agent entry failed before it could publish a live agent. Consumers Types: [SessionId](../core-data-structures/core.md) -Source: [`packages/core/agent-loop/src/index.ts:140`](../../packages/core/agent-loop/src/index.ts) +Source: [`packages/core/agent-loop/src/index.ts:148`](../../packages/core/agent-loop/src/index.ts) ## `approval/*` diff --git a/docs/cordis-catalog/services.md b/docs/cordis-catalog/services.md index d5420d7a9c..ac556aaf08 100644 --- a/docs/cordis-catalog/services.md +++ b/docs/cordis-catalog/services.md @@ -44,7 +44,7 @@ async resume(ownerCtx: Context, options: ResumeAgentOptions): Promise void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly acceptsNextStep: boolean;\n readonly ctx: Context;\n send(message: UserMessage, options: SendOptions): void;\n cancel(cause: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise;\n followup(message: UserMessage): void;\n steer(message: UserMessage): void;\n inject(message: UserMessage): void;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n };\n export interface AgentOptions {\n provider?: string;\n model?: string;\n }\n export type AgentStatus = 'idle' | 'running';\n export interface AssistantMessage extends Message {\n readonly role: 'assistant';\n readonly source: ModelMessageSource;\n }\n export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n }\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface CancelOptions {\n keepInbox?: boolean;\n }\n export interface ContentBlockMap {\n 'text': TextBlock;\n 'reasoning': ReasoningBlock;\n 'tool-call': ToolCallBlock;\n 'tool-result': ToolResultBlock;\n }\n export type ContentBlockType = keyof ContentBlockMap;\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface EpochHeader {\n config: LlmCallConfig;\n system?: string;\n tools?: ToolSchema[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export type FinishReason = FinishReasonMap[keyof FinishReasonMap];\n export interface FinishReasonMap {\n 'stop': {\n kind: 'stop';\n };\n 'tool-calls': {\n kind: 'tool-calls';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n 'aborted': {\n kind: 'aborted';\n failure: LlmFailure;\n };\n 'error': {\n kind: 'error';\n failure: LlmFailure;\n };\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export interface LlmCallConfig {\n provider: string;\n model: string;\n reasoningEffort?: ReasoningEffortId;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n }\n export interface LlmFailure {\n readonly message: string;\n readonly code: string;\n readonly status?: number;\n readonly providerRetryAfterMs?: number;\n readonly requestId?: ProviderRequestId;\n }\n export interface Message {\n readonly id: MessageId;\n readonly role: 'system' | 'user' | 'assistant';\n readonly content: ContentBlock[];\n readonly source: MessageSource;\n }\n export type MessageId = Branded<'MessageId'>;\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n model: ModelMessageSource;\n tool: ToolMessageSource;\n }\n export interface ModelMessageSource extends AssistantProvenance {\n kind: 'model';\n }\n export type ProviderRequestId = Branded<'ProviderRequestId'>;\n export interface ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type ReasoningEffortId = Branded<'ReasoningEffortId'>;\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ScopeKey = object;\n export interface SendOptions {\n target: SendTarget;\n wakeup: boolean;\n }\n export type SendTarget = 'next-turn' | 'next-step';\n export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n readonly firstLiveSeq: number;\n constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader);\n get events(): readonly SessionEvent[];\n get seq(): number;\n append(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent;\n requestHeader(): EpochHeader | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n }\n export type SessionEvent = {\n [K in SessionEventType]: {\n type: K;\n seq: number;\n time: number;\n data: SessionEventMap[K];\n } & (K extends SurfaceEventType ? {\n sourceEventSeqs?: number[];\n surfaceOp?: SurfaceOp;\n } : object);\n }[T];\n export interface SessionEventMap {\n 'turn/start': {\n turn: number;\n trigger: TurnTrigger;\n };\n 'turn/end': {\n turn: number;\n reason: TurnEndReason;\n };\n 'step/start': {\n turn: number;\n step: number;\n };\n 'step/end': {\n turn: number;\n step: number;\n };\n 'user/message': UserMessage;\n 'assistant/chunk': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n 'assistant/message': {\n turn: number;\n step: number;\n message: AssistantMessage;\n usage?: TokenUsage;\n };\n 'tool/call': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n 'tool/result': {\n turn: number;\n step: number;\n message: ToolResultMessage;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n 'steering/message': {\n turn: number;\n message: UserMessage;\n };\n 'todo/write': {\n todos: TodoItem[];\n };\n 'request/header': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n }\n export type SessionEventType = keyof SessionEventMap;\n export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n }\n export type StreamChunk = {\n type: 'block-start';\n index: number;\n blockType: ContentBlockType;\n } | {\n type: 'text-delta';\n index: number;\n text: string;\n } | {\n type: 'reasoning-delta';\n index: number;\n text: string;\n } | {\n type: 'tool-call-delta';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n } | {\n type: 'block-end';\n index: number;\n block: ContentBlock;\n } | {\n type: 'usage';\n usage: TokenUsage;\n } | {\n type: 'finish';\n reason: FinishReason;\n replayState?: unknown;\n };\n export type SurfaceEventType = 'user/message' | 'assistant/message' | 'tool/result' | 'steering/message';\n export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n }\n export type SurfaceOp = 'append' | {\n op: 'replace';\n start: number;\n end: number;\n };\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export interface TodoItem {\n content: string;\n status: 'pending' | 'in_progress' | 'completed';\n }\n export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n }\n export interface ToolCallBlock {\n type: 'tool-call';\n id: CallId;\n name: string;\n arguments: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise;\n finalizeContent?(exec: Readonly, result: Readonly): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: never;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: true;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolMessageSource {\n kind: 'tool';\n callId: CallId;\n }\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export interface ToolResultBlock {\n type: 'tool-result';\n toolCallId: CallId;\n content: ContentBlock[];\n isError?: boolean;\n }\n export interface ToolResultMessage extends Message {\n readonly role: 'user';\n readonly content: [\n ToolResultBlock\n ];\n readonly source: ToolMessageSource;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: UserMessage): void;\n concludeTurn(): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }\n export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];\n export interface TurnEndReasonMap {\n completed: {\n kind: 'completed';\n };\n aborted: {\n kind: 'aborted';\n };\n error: {\n kind: 'error';\n step: number;\n } & ({\n failure: LlmFailure;\n message?: never;\n code?: never;\n } | {\n message: string;\n code?: string;\n failure?: never;\n });\n disposed: {\n kind: 'disposed';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n interrupted: {\n kind: 'interrupted';\n };\n }\n export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap];\n export interface TurnTriggerMap {\n message: {\n kind: 'message';\n source: MessageSource;\n };\n retry: {\n kind: 'retry';\n };\n injection: {\n kind: 'injection';\n source: MessageSource;\n };\n }\n export interface UserMessage extends Message {\n readonly role: 'user';\n }"}],"isError":false}],"role":"user","id":"1c43b8df-aae8-42e7-8253-5b275edc09bc"}},"sourceEventSeqs":[11],"surfaceOp":"append"} +{"type":"tool/result","seq":12,"time":1784449176732,"data":{"turn":1,"step":1,"message":{"source":{"kind":"tool","callId":"inspect-tools-api"},"content":[{"type":"tool-result","toolCallId":"inspect-tools-api","content":[{"type":"text","text":"## api\n- tools — Tool registry and execution pipeline.\n /**\n * Register globally or in the calling agent scope. Scoped tools shadow\n * globals; duplicates within one layer and the reserved `run_code` name fail.\n * @param definition - tool schema, execution, and optional finalization/presentation callbacks.\n * @returns the exact disposer that unregisters the tool.\n */\n register(definition: ToolDefinition): () => void\n /**\n * Restrict global tools for the calling agent scope. Empty filters, unknown\n * names, scope-local names, and reserved transport names fail. Restrictions\n * intersect; scoped registrations remain visible.\n * @param filter - global-surface mask: `allow` (keep only) and/or `deny` (remove).\n * @returns the exact disposer that lifts this restriction.\n */\n restrict(filter: ToolRestriction): () => void\n /**\n * Register a monotonic guard after the extensible `tools/pre-execute`\n * waterfall. A plain-context guard applies globally; one registered through\n * `agent.ctx` applies only to that agent. Any matching guard may deny by\n * returning a reason, while no guard can force-allow a call another guard\n * denied. The exact effect disposer is returned for ordered ownership and\n * HMR cleanup.\n * @param guard - synchronous check; a returned string denies the execution.\n * @returns the exact disposer that unregisters the guard.\n */\n guard(guard: ToolGuard): () => void\n /**\n * Look up a tool as one scope sees it (scoped\n * shadows global; a restricted-away global reads as absent). Presenters pass\n * the calling agent so the rendered card matches the definition that\n * actually executed.\n * @param name - the tool name as registered.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns the definition the scope resolves, or undefined when none is visible.\n */\n get(name: string, scope?: ScopeKey): ToolDefinition | undefined\n /**\n * Project visible definitions onto the allowlisted model-facing schema fields,\n * excluding execution and presentation callbacks.\n * @param scope - the viewing scope (the agent); omitted = the global view.\n * @returns one deep-cloned schema per visible tool.\n */\n schemas(scope?: ScopeKey): ToolSchema[]\n /**\n * Classify a pending call through the caller's visible tool definition. Only\n * an exact `true` is parallel; unknown, hidden, undeclared, invalid, or\n * throwing classifiers are exclusive.\n * @param exec - call name, parsed arguments, and optional agent scope.\n * @returns the fail-closed scheduling mode.\n */\n executionMode(exec: ToolExecutionInput): ToolExecutionMode\n /**\n * Execute through pre-policy, guards, around-dispatch, post-policy,\n * definition-owned content finalization, and final notification. Tool and\n * listener failures resolve as materialized error results; an invisible tool\n * reports `UNKNOWN_TOOL`. The returned outcome is the same lossless, frozen\n * snapshot final observers receive. Cancellation\n * arriving after entry and before final result materialization skips a\n * not-yet-started body with `ABORTED_BEFORE_DISPATCH` or replaces a\n * successful started outcome with `ABORTED`; already-started work is still\n * drained and may retain a tool-owned structured error.\n * @param exec - the typed same-process call input. The registry assigns its\n * correlation token before policy begins.\n * @returns the materialized final result.\n */\n async execute(exec: ToolExecutionInput): Promise\ntype shapes (referenced by the signatures above — read these before assuming a field is a string):\n export interface Agent {\n readonly id: SessionId;\n readonly options: AgentOptions;\n readonly session: Session;\n readonly status: AgentStatus;\n readonly acceptsNextStep: boolean;\n readonly ctx: Context;\n send(message: UserMessage, options: SendOptions): void;\n cancel(cause: AgentCancelCause, options?: CancelOptions): void;\n whenIdle(): Promise;\n followup(message: UserMessage): void;\n steer(message: UserMessage): void;\n inject(message: UserMessage): void;\n }\n export type AgentCancelCause = {\n readonly kind: 'user';\n } | {\n readonly kind: 'parent';\n };\n export interface AgentOptions {\n provider?: string;\n model?: string;\n maxTokens?: number;\n }\n export type AgentStatus = 'idle' | 'running';\n export interface AssistantMessage extends Message {\n readonly role: 'assistant';\n readonly source: ModelMessageSource;\n }\n export interface AssistantProvenance {\n provider: string;\n model: string;\n replayState?: unknown;\n }\n export type Branded = string & {\n readonly [BRAND]: B;\n };\n export type CallId = Branded<'CallId'>;\n export interface CancelOptions {\n keepInbox?: boolean;\n }\n export interface ContentBlockMap {\n 'text': TextBlock;\n 'reasoning': ReasoningBlock;\n 'tool-call': ToolCallBlock;\n 'tool-result': ToolResultBlock;\n }\n export type ContentBlockType = keyof ContentBlockMap;\n export interface DiffCallView {\n card: 'diff';\n title: string;\n diffs: FileDiff[];\n locations?: FileLocation[];\n }\n export interface DiffResultView {\n card: 'diff';\n title?: string;\n diffs: FileDiff[];\n }\n export interface EpochHeader {\n config: LlmCallConfig;\n system?: string;\n tools?: ToolSchema[];\n }\n export interface FileDiff {\n path: string;\n oldText: string | null;\n newText: string;\n }\n export interface FileLocation {\n path: string;\n line?: number;\n }\n export type FinishReason = FinishReasonMap[keyof FinishReasonMap];\n export interface FinishReasonMap {\n 'stop': {\n kind: 'stop';\n };\n 'tool-calls': {\n kind: 'tool-calls';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n 'aborted': {\n kind: 'aborted';\n failure: LlmFailure;\n };\n 'error': {\n kind: 'error';\n failure: LlmFailure;\n };\n }\n export interface GenericCallView {\n card: 'generic';\n title: string;\n kind?: ToolCallKind;\n rawInput?: unknown;\n content?: ContentBlock[];\n locations?: FileLocation[];\n }\n export interface GenericResultView {\n card: 'generic';\n title?: string;\n content?: ContentBlock[];\n }\n export interface JsonSchemaNode {\n type?: JsonSchemaType;\n oneOf?: JsonSchemaNode[];\n properties?: Record;\n required?: string[];\n additionalProperties?: boolean;\n items?: JsonSchemaNode;\n enum?: JsonSchemaScalar[];\n const?: JsonSchemaScalar;\n description?: string;\n title?: string;\n default?: JsonValue;\n examples?: JsonValue;\n }\n export type JsonSchemaScalar = string | number | boolean | null;\n export type JsonSchemaType = 'object' | 'array' | 'string' | 'number' | 'integer' | 'boolean' | 'null';\n export type JsonValue = null | boolean | number | string | JsonValue[] | {\n [key: string]: JsonValue;\n };\n export interface LlmCallConfig {\n provider: string;\n model: string;\n reasoningEffort?: ReasoningEffortId;\n temperature?: number;\n maxTokens?: number;\n stop?: string[];\n }\n export interface LlmFailure {\n readonly message: string;\n readonly code: string;\n readonly status?: number;\n readonly providerRetryAfterMs?: number;\n readonly requestId?: ProviderRequestId;\n }\n export interface Message {\n readonly id: MessageId;\n readonly role: 'system' | 'user' | 'assistant';\n readonly content: ContentBlock[];\n readonly source: MessageSource;\n }\n export type MessageId = Branded<'MessageId'>;\n export type MessageSource = MessageSourceMap[keyof MessageSourceMap];\n export interface MessageSourceMap {\n user: {\n kind: 'user';\n };\n plugin: {\n kind: 'plugin';\n plugin: string;\n };\n model: ModelMessageSource;\n tool: ToolMessageSource;\n }\n export interface ModelMessageSource extends AssistantProvenance {\n kind: 'model';\n }\n export type ProviderRequestId = Branded<'ProviderRequestId'>;\n export interface ReasoningBlock {\n type: 'reasoning';\n text: string;\n }\n export type ReasoningEffortId = Branded<'ReasoningEffortId'>;\n export type RequestHeaderReason = 'initial' | 'resume' | 'change';\n export type ScopeKey = object;\n export interface SendOptions {\n target: SendTarget;\n wakeup: boolean;\n }\n export type SendTarget = 'next-turn' | 'next-step';\n export class Session {\n get surface(): SessionSurface;\n readonly header: SessionHeader;\n get id(): SessionId;\n readonly firstLiveSeq: number;\n constructor(id: SessionId, seed?: readonly SessionEvent[], header?: SessionHeader);\n get events(): readonly SessionEvent[];\n get seq(): number;\n append(type: T, data: SessionEventMap[T], ...opts: T extends SurfaceEventType ? [\n opts: SurfaceIntent\n ] : [\n ]): SessionEvent;\n requestHeader(): EpochHeader | undefined;\n deriveMessages(): Message[];\n deriveEventMessage(event: SessionEvent): Message | null;\n }\n export type SessionEvent = {\n [K in SessionEventType]: {\n type: K;\n seq: number;\n time: number;\n data: SessionEventMap[K];\n } & (K extends SurfaceEventType ? {\n sourceEventSeqs?: number[];\n surfaceOp?: SurfaceOp;\n } : object);\n }[T];\n export interface SessionEventMap {\n 'turn/start': {\n turn: number;\n trigger: TurnTrigger;\n };\n 'turn/end': {\n turn: number;\n reason: TurnEndReason;\n };\n 'step/start': {\n turn: number;\n step: number;\n };\n 'step/end': {\n turn: number;\n step: number;\n };\n 'user/message': UserMessage;\n 'assistant/chunk': {\n turn: number;\n step: number;\n chunk: StreamChunk;\n };\n 'assistant/message': {\n turn: number;\n step: number;\n message: AssistantMessage;\n usage?: TokenUsage;\n };\n 'tool/call': {\n turn: number;\n step: number;\n callId: CallId;\n name: string;\n arguments: string;\n };\n 'tool/result': {\n turn: number;\n step: number;\n message: ToolResultMessage;\n error?: {\n name: string;\n code: string;\n };\n meta?: JsonValue;\n };\n 'steering/message': {\n turn: number;\n message: UserMessage;\n };\n 'todo/write': {\n todos: TodoItem[];\n };\n 'request/header': {\n header: EpochHeader;\n reason: RequestHeaderReason;\n };\n }\n export type SessionEventType = keyof SessionEventMap;\n export interface SessionHeader {\n readonly version: number;\n readonly id: SessionId;\n readonly createdAt: number;\n readonly cwd?: string;\n readonly parentSession?: SessionId;\n readonly seedLength?: number;\n readonly delegationDepth?: number;\n }\n export type SessionId = Branded<'SessionId'>;\n export interface SessionSurface {\n readonly nodes: readonly number[];\n readonly replaceGeneration: number;\n }\n export type StreamChunk = {\n type: 'block-start';\n index: number;\n blockType: ContentBlockType;\n } | {\n type: 'text-delta';\n index: number;\n text: string;\n } | {\n type: 'reasoning-delta';\n index: number;\n text: string;\n } | {\n type: 'tool-call-delta';\n index: number;\n id: CallId;\n name?: string;\n argumentsDelta: string;\n } | {\n type: 'block-end';\n index: number;\n block: ContentBlock;\n } | {\n type: 'usage';\n usage: TokenUsage;\n } | {\n type: 'finish';\n reason: FinishReason;\n replayState?: unknown;\n };\n export type SurfaceEventType = 'user/message' | 'assistant/message' | 'tool/result' | 'steering/message';\n export interface SurfaceIntent {\n surfaceOp: SurfaceOp;\n sourceEventSeqs?: number[];\n }\n export type SurfaceOp = 'append' | {\n op: 'replace';\n start: number;\n end: number;\n };\n export interface TerminalCallView {\n card: 'terminal';\n title: string;\n description?: string;\n cwd?: string;\n }\n export interface TerminalResultView {\n card: 'terminal';\n title?: string;\n output?: string;\n exitCode?: number;\n signal?: string;\n }\n export interface TodoItem {\n content: string;\n status: 'pending' | 'in_progress' | 'completed';\n }\n export interface TokenUsage {\n inputTokens: number;\n outputTokens: number;\n cacheReadTokens?: number;\n cacheWriteTokens?: number;\n reasoningTokens?: number;\n }\n export interface ToolCallBlock {\n type: 'tool-call';\n id: CallId;\n name: string;\n arguments: string;\n }\n export type ToolCallKind = 'read' | 'edit' | 'delete' | 'move' | 'search' | 'execute' | 'fetch' | 'other';\n export type ToolCallView = GenericCallView | TerminalCallView | DiffCallView;\n export interface ToolDefinition extends ToolSchema {\n readonly output: ToolOutputDefinition;\n execute(args: unknown, exec: ToolRunContext): Promise;\n finalizeContent?(exec: Readonly, result: Readonly): ContentBlock[] | undefined;\n timeoutMs?: number;\n isConcurrencySafe?(args: unknown): boolean;\n presentCall?(args: unknown): ToolCallView | undefined;\n presentResult?(args: unknown, result: ToolResult): ToolResultView | undefined;\n }\n export interface ToolErrorInfo {\n name: string;\n code: string;\n }\n export interface ToolExecution extends ToolExecutionInput {\n readonly token: ToolExecutionToken;\n }\n export interface ToolExecutionFailure {\n readonly isError: true;\n readonly error: ToolFailure;\n readonly value?: never;\n readonly content: ContentBlock[];\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: never;\n }\n export interface ToolExecutionInput {\n readonly callId: CallId;\n readonly name: string;\n readonly arguments: unknown;\n readonly agent?: Agent;\n readonly parent?: ToolExecutionToken;\n readonly signal: AbortSignal;\n }\n export type ToolExecutionMode = {\n kind: 'parallel';\n } | {\n kind: 'exclusive';\n };\n export type ToolExecutionResult = ToolExecutionSuccess | ToolExecutionFailure;\n export interface ToolExecutionSuccess {\n readonly isError: false;\n readonly value: JsonValue;\n readonly content: ContentBlock[];\n readonly error?: never;\n readonly meta?: JsonValue;\n readonly additionalContexts?: UserMessage[];\n readonly concludesTurn?: true;\n }\n export type ToolExecutionToken = symbol & {\n readonly [toolExecutionTokenBrand]: true;\n };\n export interface ToolFailure {\n message: string;\n info?: ToolErrorInfo;\n }\n export type ToolGuard = (execution: Readonly) => string | undefined;\n export interface ToolMessageSource {\n kind: 'tool';\n callId: CallId;\n }\n export interface ToolOutputDefinition {\n readonly schema: JsonSchemaNode;\n render(args: unknown, value: JsonValue): ContentBlock[];\n presentationMeta?(args: unknown, value: JsonValue): JsonValue;\n }\n export interface ToolRestriction {\n readonly allow?: readonly string[];\n readonly deny?: readonly string[];\n }\n export interface ToolResult {\n content: ContentBlock[];\n isError: boolean;\n meta?: JsonValue;\n }\n export interface ToolResultBlock {\n type: 'tool-result';\n toolCallId: CallId;\n content: ContentBlock[];\n isError?: boolean;\n }\n export interface ToolResultMessage extends Message {\n readonly role: 'user';\n readonly content: [\n ToolResultBlock\n ];\n readonly source: ToolMessageSource;\n }\n export type ToolResultView = GenericResultView | TerminalResultView | DiffResultView;\n export interface ToolRunContext extends ToolExecution {\n deferContext(context: UserMessage): void;\n concludeTurn(): void;\n }\n export interface ToolSchema {\n name: string;\n description: string;\n parameters: Record;\n }\n export type TurnEndReason = TurnEndReasonMap[keyof TurnEndReasonMap];\n export interface TurnEndReasonMap {\n completed: {\n kind: 'completed';\n };\n aborted: {\n kind: 'aborted';\n };\n error: {\n kind: 'error';\n step: number;\n } & ({\n failure: LlmFailure;\n message?: never;\n code?: never;\n } | {\n message: string;\n code?: string;\n failure?: never;\n });\n disposed: {\n kind: 'disposed';\n };\n 'max-tokens': {\n kind: 'max-tokens';\n };\n interrupted: {\n kind: 'interrupted';\n };\n }\n export type TurnTrigger = TurnTriggerMap[keyof TurnTriggerMap];\n export interface TurnTriggerMap {\n message: {\n kind: 'message';\n source: MessageSource;\n };\n retry: {\n kind: 'retry';\n };\n injection: {\n kind: 'injection';\n source: MessageSource;\n };\n }\n export interface UserMessage extends Message {\n readonly role: 'user';\n }"}],"isError":false}],"role":"user","id":"1c43b8df-aae8-42e7-8253-5b275edc09bc"}},"sourceEventSeqs":[11],"surfaceOp":"append"} {"type":"step/end","seq":13,"time":1784449176732,"data":{"turn":1,"step":1}} {"type":"step/start","seq":14,"time":1784449176733,"data":{"turn":1,"step":2}} {"type":"assistant/chunk","seq":15,"time":1783951000015,"data":{"turn":1,"step":2,"chunk":{"type":"block-start","index":0,"blockType":"tool-call"}}} diff --git a/examples/jsonrpc-agent/tests/keyless-smoke.e2e.ts b/examples/jsonrpc-agent/tests/keyless-smoke.e2e.ts index 0d4e4d8f2e..f649bce215 100644 --- a/examples/jsonrpc-agent/tests/keyless-smoke.e2e.ts +++ b/examples/jsonrpc-agent/tests/keyless-smoke.e2e.ts @@ -105,7 +105,7 @@ describe('jsonrpc-agent keyless smoke', () => { jsonrpc: '2.0', id: 1, method: 'initialize', - params: { cwd: root, provider: 'deepseek', model: 'deepseek-v4-pro' }, + params: { cwd: root, provider: 'deepseek', model: 'deepseek-v4-pro', maxTokens: 1234 }, })}\n`) const initialized = await waitForLine(lines, value => value.id === 1, () => stderr) expect(initialized).toMatchObject({ @@ -133,6 +133,7 @@ describe('jsonrpc-agent keyless smoke', () => { const prompt = await waitForLine(lines, value => value.id === 2, () => stderr) expect(prompt).toMatchObject({ jsonrpc: '2.0', id: 2, result: { accepted: true } }) const tools = modelRequests[0]?.tools as { function?: { name?: string } }[] + expect(modelRequests[0]?.max_tokens).toBe(1234) expect(tools.map(tool => tool.function?.name).sort()).toEqual([ 'bash', 'edit', diff --git a/packages/cordis/tool-cordis/src/api-catalog.ts b/packages/cordis/tool-cordis/src/api-catalog.ts index 784497cc0e..311f7fc592 100644 --- a/packages/cordis/tool-cordis/src/api-catalog.ts +++ b/packages/cordis/tool-cordis/src/api-catalog.ts @@ -1389,7 +1389,7 @@ export const TYPE_API: readonly TypeApiEntry[] = [ }, { name: 'AgentOptions', - declaration: 'export interface AgentOptions {\n provider?: string;\n model?: string;\n}', + declaration: 'export interface AgentOptions {\n provider?: string;\n model?: string;\n maxTokens?: number;\n}', }, { name: 'AgentStatus', diff --git a/packages/core/agent-loop/README.i18n.yaml b/packages/core/agent-loop/README.i18n.yaml index f0e492c2aa..75edc1357f 100644 --- a/packages/core/agent-loop/README.i18n.yaml +++ b/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: 99fdc73e2dcb09ed7d47f021598dea8720cada5d -README.zh.md: fe9db9a625ea289e7e9364a182061dee1a0e773c +README.md: 6bb8b12af69f54c2a75cd672e4d3802887808c76 +README.zh.md: f9eb8aa3cdead427a88492e35c00eab80ba12f91 diff --git a/packages/core/agent-loop/README.md b/packages/core/agent-loop/README.md index 99fdc73e2d..6bb8b12af6 100644 --- a/packages/core/agent-loop/README.md +++ b/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 diff --git a/packages/core/agent-loop/README.zh.md b/packages/core/agent-loop/README.zh.md index fe9db9a625..f9eb8aa3cd 100644 --- a/packages/core/agent-loop/README.zh.md +++ b/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 diff --git a/packages/core/agent-loop/src/agent.ts b/packages/core/agent-loop/src/agent.ts index 3220c228cc..949e9801c4 100644 --- a/packages/core/agent-loop/src/agent.ts +++ b/packages/core/agent-loop/src/agent.ts @@ -581,11 +581,16 @@ 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, diff --git a/packages/core/agent-loop/src/index.ts b/packages/core/agent-loop/src/index.ts index 28a482b3bb..ca6b83dadb 100644 --- a/packages/core/agent-loop/src/index.ts +++ b/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 diff --git a/packages/core/agent-loop/tests/loop.spec.ts b/packages/core/agent-loop/tests/loop.spec.ts index 4a5ec2b4b3..e051642dfd 100644 --- a/packages/core/agent-loop/tests/loop.spec.ts +++ b/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) diff --git a/packages/core/agent/README.i18n.yaml b/packages/core/agent/README.i18n.yaml index f55931e999..59dcdac249 100644 --- a/packages/core/agent/README.i18n.yaml +++ b/packages/core/agent/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/README.md -README.md: 9fe207d940ddc80153131c3d76c992804bb83773 -README.zh.md: c7975fe5e0368aa46253c47c15f04e12a24a3b7b +README.md: 9ca79f28506b133a555bd7d1e984386c715fd9d6 +README.zh.md: 165f71f1b395bdf0c229e2c4b1a30e89347b6be1 diff --git a/packages/core/agent/README.md b/packages/core/agent/README.md index 9fe207d940..9ca79f2850 100644 --- a/packages/core/agent/README.md +++ b/packages/core/agent/README.md @@ -14,6 +14,8 @@ Tracks live agents and carries the initiating Agent through asynchronous driver The scoped-registration surface: `Agent.ctx` is the agent's scope context (`dsh-scope`, key = the agent) — register tools/sections/variables/listeners through it for that agent alone, all unwound on disposal. `agentEvents(ctx, agent)` is the fused dispatcher for ordinary agent-subject operations (carrier + injected subject in one move); its notification mode invokes every listener and contains both synchronous throws and returned-promise rejections. The registry lifecycle pair reuses one stable routing carrier. `assembleContextFor(agent)` builds the per-agent assembly context (`agent` + `scope` together). `installAgentLlmTarget(agentCtx, target)` snapshots a mutable provider/model/reasoning-effort selection during prompt assembly, applies the route to prompt variables, and applies the complete target to request routing for one step; an absent selected effort clears an inherited effort so the target uses adapter/provider defaults. `CreateAgentOptions.setup(agentCtx)` and `ResumeAgentOptions.setup(agentCtx)` compose a fresh or resumed agent's scoped world while both objects remain unpublished. Setup is trusted, composition-only same-process code: drive the agent only after creation resolves. +`AgentOptions` supplies the initial provider/model route and an optional positive `maxTokens` output cap. The concrete loop records the cap in the request header and applies it to each conversation-model request; callers that omit it leave provider defaults in control. + - `ctx.agents.register(agent: Agent): () => void` — record an **already-constructed** agent. Disposed with the calling fiber. - Advanced ordered lifecycle: `enter(agent, owner): () => void` enforces `agent.id === agent.session.id`, performs the authoritative ID collision check, and inserts without announcing; `owner` explicitly records the live creator-agent relation (or `undefined` for a root), independently of durable session lineage. `announce(agent)` emits `agent/created` exactly once. A detach requested synchronously by a creation listener is deferred until that dispatch unwinds, and every detach checks the captured entry object, so a stale capability cannot delete a later same-ID replacement. The async factory uses this split; ordinary plugins use `register()`. - `ctx.agents.get(id: SessionId): Agent | undefined` @@ -58,7 +60,7 @@ Turn and step boundaries and the model token stream are durable `session/event` The handle every plugin programs against: -- `agent.send(message, options)` — the one delivery primitive over the (`target` × `wakeup`) matrix. `message` is an already identified `UserMessage`; callers normally create it with `createUserMessage()` before routing begins. `SendOptions` owns only the `target` and `wakeup` policy. The agent detaches and freezes the complete value without minting or replacing its identity. The message's `agent/inbox/enqueue`/`dequeue`/`discard` events carry it so callers can correlate a queued item with its lifecycle; enqueue and dequeue also carry the resolved `queued | steering` placement so repeated message identities retire from the correct FIFO. `target: 'next-turn'` queues one independent FIFO item that, if admitted, becomes the sole ordinary prompt in its turn. `target: 'next-step'` with `wakeup: true` submits steering, while `target: 'next-step'` with `wakeup: false` injects durable context without running the model. The [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md) owns the turn rationale. +- `agent.send(message, options)` — the one delivery primitive over the (`target` × `wakeup`) matrix. `message` is an already identified, frozen `UserMessage`; callers normally create it with `createUserMessage()` before routing begins. `SendOptions` owns only the `target` and `wakeup` policy. The agent publishes or queues the complete value as-is without minting or replacing its identity. The message's `agent/inbox/enqueue`/`dequeue`/`discard` events carry it so callers can correlate a queued item with its lifecycle; enqueue and dequeue also carry the resolved `queued | steering` placement so repeated message identities retire from the correct FIFO. `target: 'next-turn'` queues one independent FIFO item that, if admitted, becomes the sole ordinary prompt in its turn. `target: 'next-step'` with `wakeup: true` submits steering, while `target: 'next-step'` with `wakeup: false` injects durable context without running the model. The [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md) owns the turn rationale. - `agent.followup(input)` — the `next-turn`/wakeup preset of `send()`: queue an ordinary follow-up turn and wake the driver. - `agent.steer(input)` — the `next-step`/wakeup preset: during prompt admission or an open turn, stage steering for the next safe boundary without dispatching `agent/prompt-submit`; outside that acceptance window, delegate to a woken follow-up. Admission failure leaves staged steering for retry or a later admitted prompt, while cancellation or disposal may discard it. - `agent.inject(input)` — the `next-step`/no-wakeup preset: append model-facing context without running the model; the next request sees a verbatim user-role message whose provenance is carried by the required `input.source`. During prompt admission or an open turn, injection waits in the outbox for the next safe boundary. Outside that acceptance window, it appends immediately without opening a turn; a context-only admission batch takes this fallback if admission closes without a turn, while context staged beside steering remains pending with it. Persistence reacts to `session/event` independently. Injection emits no `agent/inbox/*` event. diff --git a/packages/core/agent/README.zh.md b/packages/core/agent/README.zh.md index c7975fe5e0..165f71f1b3 100644 --- a/packages/core/agent/README.zh.md +++ b/packages/core/agent/README.zh.md @@ -14,6 +14,8 @@ Agent 接口、注册表、进程本地发起方作用域，以及 `agent/*` 事 带作用域的注册表层：`Agent.ctx` 是 agent 的作用域上下文（`dsh-scope`，键 = 该 agent）。通过它注册工具／段／变量／监听器，只对该 agent 生效，并在释放时全部撤销。`agentEvents(ctx, agent)` 是普通 agent 主体操作的融合分发器（一次完成载体 + 注入主体）；其通知 mode 会调用每个监听器，并同时收容同步抛出和返回 Promise 的拒绝。注册表生命周期对复用一个稳定路由载体。`assembleContextFor(agent)` 构建按 agent 的组装上下文（同时包含 `agent` + `scope`）。`installAgentLlmTarget(agentCtx, target)` 在提示词组装期间快照可变的提供方／模型／推理（reasoning）强度选择，将路由应用到提示词变量，并将完整目标应用到一个步骤的请求路由；如果没有选定推理强度，则会清除继承的推理强度，使该目标使用适配器／提供方默认值。`CreateAgentOptions.setup(agentCtx)` 和 `ResumeAgentOptions.setup(agentCtx)` 在新建或恢复的 agent 尚未发布时，组合其带作用域的世界。Setup 是受信任、仅用于组合的同进程代码：只有创建完成后才能驱动 agent。 +`AgentOptions` 提供初始的提供方／模型路由，以及可选的正整数 `maxTokens` 输出上限。实体循环会把该上限记录到请求 header，并应用到每次对话模型请求；调用方省略时由提供方默认值控制。 + - `ctx.agents.register(agent: Agent): () => void`：记录一个 **已经构造完成** 的 agent。随调用 fiber 释放。 - 高级有序生命周期：`enter(agent, owner): () => void` 强制 `agent.id === agent.session.id`，执行权威 ID 冲突检查，并在不通知的情况下插入；`owner` 显式记录实时创建方 agent 关系（根 agent 为 `undefined`），与持久会话谱系无关。`announce(agent)` 恰好发出一次 `agent/created`。创建监听器同步请求的 detach 会延后到该次分发结束；每次 detach 都会检查捕获的条目对象，因此陈旧能力无法删除后续使用同一 ID 的替代项。异步工厂使用这一拆分；普通插件使用 `register()`。 - `ctx.agents.get(id: SessionId): Agent | undefined` @@ -58,7 +60,7 @@ Agent *创建* 由实现 `AgentFactory` 的插件（`dsh-agent-loop`）提供， 每个插件面向的 handle： -- `agent.send(message, options)`：覆盖（`target` × `wakeup`）矩阵的唯一投递原语。`message` 是已有标识的 `UserMessage`；调用方通常会在开始路由前使用 `createUserMessage()` 创建它。`SendOptions` 只持有 `target` 与 `wakeup` 策略。agent 会将完整值与输入分离并冻结，但不会生成或替换其标识。该消息的 `agent/inbox/enqueue`/`dequeue`/`discard` 事件会携带其 id，调用方可据此把排队项与其生命周期关联；入队与出队事件还会携带解析出的 `queued | steering` 路由归类，使重复出现的消息标识能在正确的 FIFO 中完成结算。`target: 'next-turn'` 排队一条独立 FIFO 项，获准后成为其轮次中唯一的普通提示词。`target: 'next-step'` 且 `wakeup: true` 提交 steering（中途引导），而 `target: 'next-step'` 且 `wakeup: false` 注入持久上下文，不运行模型。轮次原理由 [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md)拥有。 +- `agent.send(message, options)`：覆盖（`target` × `wakeup`）矩阵的唯一投递原语。`message` 是已有标识且已冻结的 `UserMessage`；调用方通常会在开始路由前使用 `createUserMessage()` 创建它。`SendOptions` 只持有 `target` 与 `wakeup` 策略。agent 会原样发布或排队完整值，不会生成或替换其标识。该消息的 `agent/inbox/enqueue`/`dequeue`/`discard` 事件会携带完整消息，调用方可据此把排队项与其生命周期关联；入队与出队事件还会携带解析出的 `queued | steering` 路由归类，使重复出现的消息标识能在正确的 FIFO 中完成结算。`target: 'next-turn'` 排队一条独立 FIFO 项，获准后成为其轮次中唯一的普通提示词。`target: 'next-step'` 且 `wakeup: true` 提交 steering（中途引导），而 `target: 'next-step'` 且 `wakeup: false` 注入持久上下文，不运行模型。轮次原理由 [one-send-one-turn Agent Note](../../../.agents/notes/implemented/simplification/2026-07-17-one-send-one-turn.md)拥有。 - `agent.followup(input)`：`send()` 的 `next-turn`／wakeup 预设：排队一个普通后续轮次并唤醒驱动器。 - `agent.steer(input)`：`next-step`／wakeup 预设：提示词接纳期间或轮次打开时，为下一个安全边界暂存 steering，且不分发 `agent/prompt-submit`；该接收窗口之外则委托给会唤醒的后续轮次。接纳失败会保留暂存的 steering，以供重试或之后获准的提示词使用，而取消或 dispose 可能丢弃它。 - `agent.inject(input)`：`next-step`／不唤醒预设：追加面向模型的上下文而不运行模型；下一次请求会看到一条逐字的 user role 消息，其来源由必填的 `input.source` 携带。提示词接纳期间或轮次打开时，注入会在 outbox 中等待下一个安全边界。该接收窗口之外，它会立即追加而不开启轮次；如果接纳结束却未开启轮次，仅含上下文的接纳批次会采用这一回退，而与 steering 一同暂存的上下文则会随其继续待处理。持久化独立地响应 `session/event`。注入不发出 `agent/inbox/*` 事件。 diff --git a/packages/core/agent/src/types.ts b/packages/core/agent/src/types.ts index dcff0478c6..28b4ca4c71 100644 --- a/packages/core/agent/src/types.ts +++ b/packages/core/agent/src/types.ts @@ -23,6 +23,8 @@ export interface AgentOptions { provider?: string /** Model id interpreted by the selected provider adapter. */ model?: string + /** Maximum output tokens for each conversation-model request. */ + maxTokens?: number } /** diff --git a/packages/sdk/sdk-client/README.i18n.yaml b/packages/sdk/sdk-client/README.i18n.yaml index 5e66e24937..30fa3a1a99 100644 --- a/packages/sdk/sdk-client/README.i18n.yaml +++ b/packages/sdk/sdk-client/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/sdk/sdk-client/README.md -README.md: 33a933e10abfa865cf9ce34b87c377d07081cc68 -README.zh.md: 9f4453a00efef2685acec0194f83fcec2edf1409 +README.md: 3ac4de540401f6f40dab3e84f7005f91d024aee8 +README.zh.md: 1d9f8fbded8b477d519a5244735179fba581cdd0 diff --git a/packages/sdk/sdk-client/README.md b/packages/sdk/sdk-client/README.md index 33a933e10a..3ac4de5404 100644 --- a/packages/sdk/sdk-client/README.md +++ b/packages/sdk/sdk-client/README.md @@ -15,12 +15,13 @@ await using harness = new DeepSeekHarness({ launch: { command: 'node', args: ['lib/bin.js', 'cordis.yml'] }, provider: 'deepseek', model: 'deepseek-v4-flash', + maxTokens: 49_152, }) const result = await harness.run('say hi') console.log(result.status, result.finalResponse) ``` -The subprocess starts lazily on first use and stays owned by the instance across `run()` calls; `close()` (or `await using`) is required so the child is always reaped. `start()` memoizes the `initialize` handshake (the workspace cwd — resolved absolute before it crosses the wire — plus the provider/model route); a failed handshake reaps the runtime and swaps in a fresh client, so a later call retries with a new subprocess (until `close()`, which is terminal). `session(id?)` opens a named or fresh session handle; `run(input, { sessionId?, onNotification? })` sends one prompt turn and settles when the paired `session.finished` arrives, returning a `TurnResult`: `status` (`ok`/`error` as the deployment maps it), the structured `reason` (`TurnEndReason`), `finalResponse` (last assistant message text), root-session `events`, and raw `notifications` for that session plus descendants discovered from `subagent.started`, all in wire order. Model-level failure is a `status: 'error'` result, never a rejection; rejections mean transport loss, timeout, or protocol violation. +The subprocess starts lazily on first use and stays owned by the instance across `run()` calls; `close()` (or `await using`) is required so the child is always reaped. `start()` memoizes the `initialize` handshake (the workspace cwd — resolved absolute before it crosses the wire — plus the provider/model route and optional positive `maxTokens` output cap); a failed handshake reaps the runtime and swaps in a fresh client, so a later call retries with a new subprocess (until `close()`, which is terminal). The cap applies to each root-agent request and is inherited by in-process descendants; compaction plugins own their separate summary limits. `session(id?)` opens a named or fresh session handle; `run(input, { sessionId?, onNotification? })` sends one prompt turn and settles when the paired `session.finished` arrives, returning a `TurnResult`: `status` (`ok`/`error` as the deployment maps it), the structured `reason` (`TurnEndReason`), `finalResponse` (last assistant message text), root-session `events`, and raw `notifications` for that session plus descendants discovered from `subagent.started`, all in wire order. Model-level failure is a `status: 'error'` result, never a rejection; rejections mean transport loss, timeout, or protocol violation. ## HarnessClient diff --git a/packages/sdk/sdk-client/README.zh.md b/packages/sdk/sdk-client/README.zh.md index 9f4453a00e..1d9f8fbded 100644 --- a/packages/sdk/sdk-client/README.zh.md +++ b/packages/sdk/sdk-client/README.zh.md @@ -15,12 +15,13 @@ await using harness = new DeepSeekHarness({ launch: { command: 'node', args: ['lib/bin.js', 'cordis.yml'] }, provider: 'deepseek', model: 'deepseek-v4-flash', + maxTokens: 49_152, }) const result = await harness.run('say hi') console.log(result.status, result.finalResponse) ``` -子进程在首次使用时惰性启动，并在多次 `run()` 之间持续归实例所有；必须 `close()`（或 `await using`），子进程才总能被收割。`start()` 记忆化 `initialize` 握手（工作区 cwd——在跨越线之前解析为绝对路径——加 provider/model 路由）；握手失败会收割运行时并换入全新客户端，后续调用用新子进程重试（直到终结性的 `close()`）。`session(id?)` 打开具名或全新的会话句柄；`run(input, { sessionId?, onNotification? })` 发送一个 prompt 回合，在配对的 `session.finished` 到达时尘埃落定，返回 `TurnResult`：`status`（按部署映射的 `ok`/`error`）、结构化 `reason`（`TurnEndReason`）、`finalResponse`（最后一条助手消息文本）、根会话的 `events`，以及该会话和通过 `subagent.started` 发现的后代的原始 `notifications`，均按线序排列。模型层失败是 `status: 'error'` 的结果，绝不是拒绝；拒绝意味着传输丢失、超时或协议违例。 +子进程在首次使用时惰性启动，并在多次 `run()` 之间持续归实例所有；必须 `close()`（或 `await using`），子进程才总能被收割。`start()` 记忆化 `initialize` 握手（工作区 cwd——在跨越线之前解析为绝对路径——加 provider/model 路由和可选的正整数 `maxTokens` 输出上限）；握手失败会收割运行时并换入全新客户端，后续调用用新子进程重试（直到终结性的 `close()`）。该上限作用于根 agent 的每次请求，并由进程内后代继承；压缩插件单独持有摘要上限。`session(id?)` 打开具名或全新的会话句柄；`run(input, { sessionId?, onNotification? })` 发送一个 prompt 回合，在配对的 `session.finished` 到达时尘埃落定，返回 `TurnResult`：`status`（按部署映射的 `ok`/`error`）、结构化 `reason`（`TurnEndReason`）、`finalResponse`（最后一条助手消息文本）、根会话的 `events`，以及该会话和通过 `subagent.started` 发现的后代的原始 `notifications`，均按线序排列。模型层失败是 `status: 'error'` 的结果，绝不是拒绝；拒绝意味着传输丢失、超时或协议违例。 ## HarnessClient diff --git a/packages/sdk/sdk-client/src/api.ts b/packages/sdk/sdk-client/src/api.ts index 30479912d7..b5cfd12c6b 100644 --- a/packages/sdk/sdk-client/src/api.ts +++ b/packages/sdk/sdk-client/src/api.ts @@ -25,6 +25,7 @@ export class DeepSeekHarness implements AsyncDisposable { private readonly cwd: string private readonly provider: string private readonly model: string + private readonly maxTokens: number | undefined private initialized: Promise | undefined private closed = false @@ -38,6 +39,7 @@ export class DeepSeekHarness implements AsyncDisposable { this.cwd = resolve(options.cwd ?? options.launch.cwd ?? process.cwd()) this.provider = options.provider ?? 'deepseek' this.model = options.model ?? 'deepseek-v4-flash' + this.maxTokens = options.maxTokens } /** @@ -61,7 +63,12 @@ export class DeepSeekHarness implements AsyncDisposable { this.initialized ??= (async () => { try { this.clientInstance.start() - await this.clientInstance.initialize({ cwd: this.cwd, provider: this.provider, model: this.model }) + await this.clientInstance.initialize({ + cwd: this.cwd, + provider: this.provider, + model: this.model, + ...this.maxTokens === undefined ? {} : { maxTokens: this.maxTokens }, + }) } catch (error) { this.initialized = undefined await this.clientInstance.close() diff --git a/packages/sdk/sdk-client/src/types.ts b/packages/sdk/sdk-client/src/types.ts index ac4393126b..ad4998ca13 100644 --- a/packages/sdk/sdk-client/src/types.ts +++ b/packages/sdk/sdk-client/src/types.ts @@ -55,6 +55,8 @@ export interface DeepSeekHarnessOptions { provider?: string /** Model for SDK-created agents (default `deepseek-v4-flash`). */ model?: string + /** Maximum output tokens for each conversation-model request. */ + maxTokens?: number } /** The settled outcome of one {@link HarnessSession.run} turn. */ diff --git a/packages/sdk/sdk-client/tests/sdk-client.spec.ts b/packages/sdk/sdk-client/tests/sdk-client.spec.ts index 1ec334daa4..63093e602b 100644 --- a/packages/sdk/sdk-client/tests/sdk-client.spec.ts +++ b/packages/sdk/sdk-client/tests/sdk-client.spec.ts @@ -106,7 +106,7 @@ describe('DeepSeekHarness', () => { await harness.close() }) - it('sends the configured cwd/provider/model in the handshake exactly once', async () => { + it('sends the configured cwd/provider/model/maxTokens in the handshake exactly once', async () => { const dir = await tempDir('sdk-client-init-') const recordFile = join(dir, 'init.jsonl') const harness = new DeepSeekHarness({ @@ -114,13 +114,19 @@ describe('DeepSeekHarness', () => { cwd: dir, provider: 'custom-provider', model: 'custom-model', + maxTokens: 4096, }) cleanups.push(() => harness.close()) await harness.run('one') await harness.run('two') await harness.close() const records = (await readFile(recordFile, 'utf8')).trim().split('\n').map(line => JSON.parse(line) as object) - expect(records).toEqual([{ cwd: dir, provider: 'custom-provider', model: 'custom-model' }]) + expect(records).toEqual([{ + cwd: dir, + provider: 'custom-provider', + model: 'custom-model', + maxTokens: 4096, + }]) }) it('resolves a relative launch cwd to an absolute workspace before the handshake', async () => { diff --git a/packages/sdk/sdk-protocol/README.i18n.yaml b/packages/sdk/sdk-protocol/README.i18n.yaml index c7802c1795..072917a67f 100644 --- a/packages/sdk/sdk-protocol/README.i18n.yaml +++ b/packages/sdk/sdk-protocol/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/sdk/sdk-protocol/README.md -README.md: 79e6bc36a656ce0d68c8e01ab2f75e26b4ac8ca5 -README.zh.md: 8322da0f2bf7251f2b958c6a15f1738b9d8c41a4 +README.md: 62b26d4a82d358fa4efcb7ab84036e5f4848057f +README.zh.md: c08c32b2fbf0b63b28826bae8fd6c2a73bfe09d0 diff --git a/packages/sdk/sdk-protocol/README.md b/packages/sdk/sdk-protocol/README.md index 79e6bc36a6..62b26d4a82 100644 --- a/packages/sdk/sdk-protocol/README.md +++ b/packages/sdk/sdk-protocol/README.md @@ -22,7 +22,7 @@ The shared wire protocol for the DeepSeek Harness SDK runtime: one newline-delim | server→client | `subagent.started` | `SubagentStartedNotification` | | server→client | `subagent.finished` | `SubagentFinishedNotification` (in-process runs only) | -`HarnessSdkRequestMap` and `HarnessSdkNotificationMap` index these by method name. The notification payload types depend on `SessionEvent` (`dsh-session`), `ContentBlock` (`dsh-llm`), and `SubagentStopReason` (`dsh-subagent`) — the protocol streams full session-log envelopes, so the session vocabulary is part of the wire contract. `serverInfo.name` stays the wire-stable `deepseek-harness-sdk-runtime`. +`HarnessSdkRequestMap` and `HarnessSdkNotificationMap` index these by method name. `InitializeParams.maxTokens` is an optional positive safe integer that caps each conversation-model output for SDK-created agents and their in-process descendants; omission leaves the provider default in control. The notification payload types depend on `SessionEvent` (`dsh-session`), `ContentBlock` (`dsh-llm`), and `SubagentStopReason` (`dsh-subagent`) — the protocol streams full session-log envelopes, so the session vocabulary is part of the wire contract. `serverInfo.name` stays the wire-stable `deepseek-harness-sdk-runtime`. ## Model Experience diff --git a/packages/sdk/sdk-protocol/README.zh.md b/packages/sdk/sdk-protocol/README.zh.md index 8322da0f2b..c08c32b2fb 100644 --- a/packages/sdk/sdk-protocol/README.zh.md +++ b/packages/sdk/sdk-protocol/README.zh.md @@ -22,7 +22,7 @@ DeepSeek Harness SDK 运行时的共享线协议：一个按换行分帧的 JSON | server→client | `subagent.started` | `SubagentStartedNotification` | | server→client | `subagent.finished` | `SubagentFinishedNotification`（仅进程内 run） | -`HarnessSdkRequestMap` 与 `HarnessSdkNotificationMap` 按方法名索引这些类型。通知载荷类型依赖 `SessionEvent`（`dsh-session`）、`ContentBlock`（`dsh-llm`）与 `SubagentStopReason`（`dsh-subagent`）——协议以完整会话日志封套进行流式传输，因此会话词汇表是线契约的一部分。`serverInfo.name` 保持线上稳定值 `deepseek-harness-sdk-runtime`。 +`HarnessSdkRequestMap` 与 `HarnessSdkNotificationMap` 按方法名索引这些类型。`InitializeParams.maxTokens` 是可选的正安全整数，用于限制 SDK 创建的 agent 及其进程内后代每次对话模型输出；省略时由提供方默认值控制。通知载荷类型依赖 `SessionEvent`（`dsh-session`）、`ContentBlock`（`dsh-llm`）与 `SubagentStopReason`（`dsh-subagent`）——协议以完整会话日志封套进行流式传输，因此会话词汇表是线契约的一部分。`serverInfo.name` 保持线上稳定值 `deepseek-harness-sdk-runtime`。 ## Model Experience diff --git a/packages/sdk/sdk-protocol/src/types.ts b/packages/sdk/sdk-protocol/src/types.ts index 73459923ae..1b7a372f66 100644 --- a/packages/sdk/sdk-protocol/src/types.ts +++ b/packages/sdk/sdk-protocol/src/types.ts @@ -20,6 +20,8 @@ export interface InitializeParams { provider: string /** Model name every SDK-created agent runs on (the server may mount a fallback adapter; see `HarnessSdkServer.initialize`). */ model: string + /** Optional positive output-token cap inherited by SDK-created agents and their in-process descendants. */ + maxTokens?: number } /** Wire-stable server identity returned by initialization. */ diff --git a/packages/subagent/subagent-dsh-sdk/README.i18n.yaml b/packages/subagent/subagent-dsh-sdk/README.i18n.yaml index e5c410ea74..54cf6ef79d 100644 --- a/packages/subagent/subagent-dsh-sdk/README.i18n.yaml +++ b/packages/subagent/subagent-dsh-sdk/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/subagent/subagent-dsh-sdk/README.md -README.md: 95ddd154c8262e8854280e74618bdd9be9c938c0 -README.zh.md: c10145f34cd785d10f4b660a5f6414455ad42464 +README.md: e904ce3c09a1b44f8f5a0072b9ca85812898e74f +README.zh.md: b11cb9c8e0bf2577be71230292d73878b22896a0 diff --git a/packages/subagent/subagent-dsh-sdk/README.md b/packages/subagent/subagent-dsh-sdk/README.md index 95ddd154c8..e904ce3c09 100644 --- a/packages/subagent/subagent-dsh-sdk/README.md +++ b/packages/subagent/subagent-dsh-sdk/README.md @@ -6,7 +6,7 @@ The SDK provider runs each subagent as a complete DeepSeek Harness runtime in a ## Start and ownership -`start(request)` resolves the child's working directory, spawns the runtime through `DeepSeekHarness`, and completes the `initialize` handshake (with the configured `provider`/`model` route) before it fulfills. Fulfillment therefore means the child runtime is ready and ownership has transferred to the caller. A spawn, handshake, or pre-publication cancellation failure rejects only after the subprocess has been reaped; a working-directory resolution failure rejects before anything is spawned. +`start(request)` resolves the child's working directory, spawns the runtime through `DeepSeekHarness`, and completes the `initialize` handshake (with the configured `provider`/`model` route and optional `maxTokens` output cap) before it fulfills. Fulfillment therefore means the child runtime is ready and ownership has transferred to the caller. A spawn, handshake, or pre-publication cancellation failure rejects only after the subprocess has been reaped; a working-directory resolution failure rejects before anything is spawned. The working directory resolves exactly like the ACP backend, through the seam's shared out-of-process helpers ([`dsh-subagent`](../subagent/README.md)): the configured `cwd` override when set (validated once at load), else the delegating parent session's cwd — never the server process's own cwd. The resolved path becomes the child process cwd and the workspace cwd of its SDK session. @@ -32,6 +32,7 @@ The provider advertises no start-time capabilities (`outputSchema`/`depthLimit`/ | `cwd` | parent session cwd | Working-directory override; same validation as [`subagent-acp`](../subagent-acp/README.md). | | `provider` | `deepseek` | Provider route sent in the child's `initialize`. | | `model` | `deepseek-v4-flash` | Model sent in the child's `initialize`. | +| `maxTokens` | provider default | Per-request output-token cap sent in the child's `initialize`; it applies to the child root agent and its in-process descendants. | | `env` | `{}` | Explicit child environment layered over a credential-scrubbed parent environment (e.g. the child's own `DEEPSEEK_API_KEY`, or `DSH_CORDIS_CONFIG`). | | `shutdownTimeoutMs` | `1000` | Bound on the protocol `shutdown` exchange during dispose. | | `disposeEofGraceMs` | `6000` | Grace after stdin EOF before platform termination. | @@ -44,6 +45,7 @@ The provider advertises no start-time capabilities (`outputSchema`/`depthLimit`/ providerName: dsh-sdk command: node args: ['./packages/examples/jsonrpc-demo/lib/bin.js', './examples/jsonrpc-agent/cordis.yml'] + maxTokens: 49152 env: DEEPSEEK_API_KEY: !!js process.env.DEEPSEEK_API_KEY - id: tool-subagent diff --git a/packages/subagent/subagent-dsh-sdk/README.zh.md b/packages/subagent/subagent-dsh-sdk/README.zh.md index c10145f34c..b11cb9c8e0 100644 --- a/packages/subagent/subagent-dsh-sdk/README.zh.md +++ b/packages/subagent/subagent-dsh-sdk/README.zh.md @@ -6,7 +6,7 @@ SDK provider 把每个子代理作为一个完整的 DeepSeek Harness 运行时 ## 启动与所有权 -`start(request)` 先解析子进程工作目录，经 `DeepSeekHarness` 生成运行时，并在履行前完成 `initialize` 握手（携带配置的 `provider`/`model` 路由）。因此履行意味着子运行时已就绪、所有权已移交调用方。生成、握手或发布前取消的失败只在子进程被收割之后拒绝；工作目录解析失败在生成任何东西之前拒绝。 +`start(request)` 先解析子进程工作目录，经 `DeepSeekHarness` 生成运行时，并在履行前完成 `initialize` 握手（携带配置的 `provider`/`model` 路由及可选的 `maxTokens` 输出上限）。因此履行意味着子运行时已就绪、所有权已移交调用方。生成、握手或发布前取消的失败只在子进程被收割之后拒绝；工作目录解析失败在生成任何东西之前拒绝。 工作目录的解析与 ACP 后端完全一致，经由接缝共享的进程外助手（[`dsh-subagent`](../subagent/README.md)）：设置了 `cwd` 覆盖则用之（加载时校验一次），否则用发起委托的父会话 cwd——绝不用服务器进程自己的 cwd。解析出的路径同时成为子进程 cwd 与其 SDK 会话的工作区 cwd。 @@ -32,6 +32,7 @@ Provider 不宣告任何启动期能力（`outputSchema`/`depthLimit`/`toolFilte | `cwd` | 父会话 cwd | 工作目录覆盖；校验规则与 [`subagent-acp`](../subagent-acp/README.md) 相同。 | | `provider` | `deepseek` | 写入子进程 `initialize` 的 provider 路由。 | | `model` | `deepseek-v4-flash` | 写入子进程 `initialize` 的模型。 | +| `maxTokens` | provider 默认值 | 写入子进程 `initialize` 的单次请求输出 token 上限；对子根 Agent 及其进程内后代生效。 | | `env` | `{}` | 在凭据擦除后的父环境之上叠加的显式子环境（例如子进程自己的 `DEEPSEEK_API_KEY`，或 `DSH_CORDIS_CONFIG`）。 | | `shutdownTimeoutMs` | `1000` | 处置期间协议 `shutdown` 交换的时限。 | | `disposeEofGraceMs` | `6000` | stdin EOF 之后、平台终止之前的宽限。 | @@ -44,6 +45,7 @@ Provider 不宣告任何启动期能力（`outputSchema`/`depthLimit`/`toolFilte providerName: dsh-sdk command: node args: ['./packages/examples/jsonrpc-demo/lib/bin.js', './examples/jsonrpc-agent/cordis.yml'] + maxTokens: 49152 env: DEEPSEEK_API_KEY: !!js process.env.DEEPSEEK_API_KEY - id: tool-subagent diff --git a/packages/subagent/subagent-dsh-sdk/src/index.ts b/packages/subagent/subagent-dsh-sdk/src/index.ts index 829207e652..e25ed9fb27 100644 --- a/packages/subagent/subagent-dsh-sdk/src/index.ts +++ b/packages/subagent/subagent-dsh-sdk/src/index.ts @@ -46,6 +46,8 @@ export interface Config { provider: string /** Model the child runtime initializes with (default `deepseek-v4-flash`). */ model: string + /** Optional per-request output-token cap for the child runtime. */ + maxTokens?: number /** * Extra environment variables for the child process — e.g. the child * runtime's own `DEEPSEEK_API_KEY`, or `DSH_CORDIS_CONFIG` naming its @@ -73,14 +75,15 @@ export const Config: z = z.object({ cwd: z.string(), provider: z.string().default('deepseek'), model: z.string().default('deepseek-v4-flash'), + maxTokens: z.number().step(1).min(1).max(Number.MAX_SAFE_INTEGER), env: z.dict(z.string()).default({}), shutdownTimeoutMs: z.number().default(DEFAULT_SHUTDOWN_TIMEOUT_MS), disposeEofGraceMs: z.number().default(DEFAULT_DISPOSE_EOF_GRACE_MS), disposeGraceMs: z.number().default(DEFAULT_DISPOSE_GRACE_MS), }) -/** The shape after schemastery applied the defaults (cwd has none). */ -type ResolvedConfig = Required> & Pick +/** The shape after schemastery applied the defaults (`cwd` and `maxTokens` have none). */ +type ResolvedConfig = Required> & Pick /** * The SDK provider. Advertises NO start-time capabilities: an out-of-process @@ -101,6 +104,7 @@ class SdkProvider implements SubagentProvider { cwd: resolveChildCwd('subagent-dsh-sdk', this.config.cwd, request.parent.session.header.cwd), provider: this.config.provider, model: this.config.model, + ...this.config.maxTokens === undefined ? {} : { maxTokens: this.config.maxTokens }, env: this.config.env, shutdownTimeoutMs: this.config.shutdownTimeoutMs, disposeEofGraceMs: this.config.disposeEofGraceMs, @@ -121,6 +125,9 @@ export function apply(ctx: Context, config: Config): void { assertPositiveFinite('subagent-dsh-sdk', 'shutdownTimeoutMs', resolved.shutdownTimeoutMs) assertPositiveFinite('subagent-dsh-sdk', 'disposeEofGraceMs', resolved.disposeEofGraceMs) assertPositiveFinite('subagent-dsh-sdk', 'disposeGraceMs', resolved.disposeGraceMs) + if (resolved.maxTokens !== undefined && (!Number.isSafeInteger(resolved.maxTokens) || resolved.maxTokens <= 0)) { + throw new TypeError('subagent-dsh-sdk maxTokens must be a positive safe integer') + } // Interpret a relative configured cwd against the harness launch directory // ONCE, at load, and fail a misconfigured directory here — not per start. const configuredCwd = validateConfiguredCwd('subagent-dsh-sdk', resolved.cwd) diff --git a/packages/subagent/subagent-dsh-sdk/src/run.ts b/packages/subagent/subagent-dsh-sdk/src/run.ts index 829568ef74..ec88cc1fb1 100644 --- a/packages/subagent/subagent-dsh-sdk/src/run.ts +++ b/packages/subagent/subagent-dsh-sdk/src/run.ts @@ -35,6 +35,8 @@ export interface SdkRunSpec { provider: string /** Model the child runtime initializes with. */ model: string + /** Optional per-request output-token cap sent in the child runtime's initialize handshake. */ + maxTokens?: number /** * Extra environment variables to ADD for the child (e.g. the child * runtime's own `DEEPSEEK_API_KEY`, or `DSH_CORDIS_CONFIG`). Merged after @@ -126,6 +128,7 @@ export async function startSdkRun(request: SubagentStartRequest, spec: SdkRunSpe cwd: spec.cwd, provider: spec.provider, model: spec.model, + ...spec.maxTokens === undefined ? {} : { maxTokens: spec.maxTokens }, }) // Cancellation settles the result without waiting for a cooperative child. diff --git a/packages/subagent/subagent-dsh-sdk/tests/subagent-dsh-sdk.spec.ts b/packages/subagent/subagent-dsh-sdk/tests/subagent-dsh-sdk.spec.ts index a6b980bf45..16a9c57899 100644 --- a/packages/subagent/subagent-dsh-sdk/tests/subagent-dsh-sdk.spec.ts +++ b/packages/subagent/subagent-dsh-sdk/tests/subagent-dsh-sdk.spec.ts @@ -105,17 +105,22 @@ describe('dsh-subagent-dsh-sdk provider', () => { await ctx.fiber.dispose() }) - it('initializes the child with the configured provider/model and the parent cwd', async () => { + it('initializes the child with the configured provider/model/maxTokens and the parent cwd', async () => { const tmp = mkdtempSync(join(tmpdir(), 'subagent-dsh-sdk-init-')) const recordFile = join(tmp, 'init.jsonl') try { - const ctx = await setup({ FAKE_RECORD_INIT: recordFile }) + const ctx = await setup({ FAKE_RECORD_INIT: recordFile }, { maxTokens: 4096 }) const run = await ctx.subagents.start('dsh-sdk', request()) await run.result await run.dispose() const { readFileSync } = await import('node:fs') const records = readFileSync(recordFile, 'utf8').trim().split('\n').map(line => JSON.parse(line) as Record) - expect(records).toEqual([{ cwd: process.cwd(), provider: 'fake-provider', model: 'fake-model' }]) + expect(records).toEqual([{ + cwd: process.cwd(), + provider: 'fake-provider', + model: 'fake-model', + maxTokens: 4096, + }]) await ctx.fiber.dispose() } finally { rmSync(tmp, { recursive: true, force: true }) @@ -364,6 +369,45 @@ describe('dsh-subagent-dsh-sdk provider', () => { await ctx.fiber.dispose() }) + it.each([0, -1, 1.5, Number.NaN, Number.MAX_SAFE_INTEGER + 1])( + 'rejects invalid maxTokens %s at load', + async (maxTokens) => { + const ctx = new Context() + await ctx.plugin(SubagentService) + await expect(ctx.plugin(sdk, { + providerName: 'sdk', + command: 'true', + args: [], + provider: 'p', + model: 'm', + maxTokens, + env: {}, + })).rejects.toThrow('maxTokens') + await ctx.fiber.dispose() + }, + ) + + it.each([0, 1.5])( + 'defensively rejects invalid maxTokens %s when apply is called directly', + async (maxTokens) => { + const ctx = new Context() + await ctx.plugin(SubagentService) + expect(() => { sdk.apply(ctx, { + providerName: 'sdk', + command: 'true', + args: [], + provider: 'p', + model: 'm', + maxTokens, + env: {}, + shutdownTimeoutMs: DEFAULT_SHUTDOWN_TIMEOUT_MS, + disposeEofGraceMs: DEFAULT_DISPOSE_EOF_GRACE_MS, + disposeGraceMs: DEFAULT_DISPOSE_GRACE_MS, + }) }).toThrow('maxTokens must be a positive safe integer') + await ctx.fiber.dispose() + }, + ) + it('rejects an empty config cwd at load', async () => { const ctx = new Context() await ctx.plugin(SubagentService) diff --git a/packages/subagent/subagent-inprocess/README.i18n.yaml b/packages/subagent/subagent-inprocess/README.i18n.yaml index 82c3f1a57a..621b896045 100644 --- a/packages/subagent/subagent-inprocess/README.i18n.yaml +++ b/packages/subagent/subagent-inprocess/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/subagent/subagent-inprocess/README.md -README.md: 220a3f44d0eb14dfed3241c9561800f86a90aecf -README.zh.md: cd03f01cff19c42b8dc91a906ebb89779c494a24 +README.md: 3606799e6d16e80473006f82b834a10953270914 +README.zh.md: 7f52d3699d1240f960e437d12bc48a152658cd15 diff --git a/packages/subagent/subagent-inprocess/README.md b/packages/subagent/subagent-inprocess/README.md index 220a3f44d0..3606799e6d 100644 --- a/packages/subagent/subagent-inprocess/README.md +++ b/packages/subagent/subagent-inprocess/README.md @@ -16,7 +16,7 @@ The driver follows this sequence: 4. Publish the child, retain the returned `AgentHandle`, and drive one task with `child.followup(prompt)` followed by `child.whenIdle()`. 5. Read the child's own last assistant message and latest message-triggered turn reason, excluding any fork seed and later between-turn records. -The child gets the parent's working-directory/session lineage and inherits the parent model unless `request.agentOptions` overrides it. It gets a fresh flat registration scope: parent ownership does not import parent tool restrictions or establish an authority subset. +The child gets the parent's working-directory/session lineage and inherits the parent provider, model, and output-token cap unless `request.agentOptions` overrides them. It gets a fresh flat registration scope: parent ownership does not import parent tool restrictions or establish an authority subset. ## Cancellation and ownership diff --git a/packages/subagent/subagent-inprocess/README.zh.md b/packages/subagent/subagent-inprocess/README.zh.md index cd03f01cff..7f52d3699d 100644 --- a/packages/subagent/subagent-inprocess/README.zh.md +++ b/packages/subagent/subagent-inprocess/README.zh.md @@ -16,7 +16,7 @@ 4. 发布子 agent，保留返回的 `AgentHandle`，并通过先调用 `child.followup(prompt)`、再调用 `child.whenIdle()` 来驱动一项任务。 5. 读取子 agent 自身最后一条 assistant 消息，以及由消息触发的最新轮次原因；排除任何 fork 初始内容和后续轮次间记录。 -子 agent 会获得父 agent 的工作目录/会话谱系；除非 `request.agentOptions` 覆盖，否则还会继承父 agent 模型。它获得全新的扁平注册作用域：父级所有权不会导入父 agent 的工具限制，也不会建立权限子集。 +子 agent 会获得父 agent 的工作目录／会话谱系；除非 `request.agentOptions` 覆盖，否则还会继承父 agent 的提供方、模型和输出 token 上限。它获得全新的扁平注册作用域：父级所有权不会导入父 agent 的工具限制，也不会建立权限子集。 ## 取消与所有权 diff --git a/packages/subagent/subagent-inprocess/src/index.ts b/packages/subagent/subagent-inprocess/src/index.ts index 2cba77e09b..e57b1dff4a 100644 --- a/packages/subagent/subagent-inprocess/src/index.ts +++ b/packages/subagent/subagent-inprocess/src/index.ts @@ -88,9 +88,11 @@ export async function startInProcessRun( const parentHeader = parent.session.header const parentProvider = parent.options.provider const parentModel = parent.options.model + const parentMaxTokens = parent.options.maxTokens const agentOptions: AgentOptions = { ...parentProvider !== undefined ? { provider: parentProvider } : {}, ...parentModel !== undefined ? { model: parentModel } : {}, + ...parentMaxTokens !== undefined ? { maxTokens: parentMaxTokens } : {}, ...request.agentOptions, subagentDepth: childDepth, } diff --git a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts index ff2c2f35a8..7254ccb858 100644 --- a/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts +++ b/packages/subagent/subagent-inprocess/tests/subagent-inprocess.spec.ts @@ -1,7 +1,7 @@ import { createUserMessage } from '@deepseek-ai/dsh-llm' import { describe, expect, it } from 'vitest' import { Context } from 'cordis' -import { type Agent } from '@deepseek-ai/dsh-agent' +import { type Agent, type AgentOptions } from '@deepseek-ai/dsh-agent' import { SessionId } from '@deepseek-ai/dsh-session' import AgentLoop from '@deepseek-ai/dsh-agent-loop' import { mountAgentLoopTestDependencies } from '@deepseek-ai/dsh-agent-loop-testkit' @@ -22,7 +22,7 @@ async function mountInvariants(ctx: Context): Promise { await ctx.plugin(AgentLoopInvariant) } -async function setup(script: Script) { +async function setup(script: Script, parentOptions: Partial = {}) { const ctx = new Context() await mountAgentLoopTestDependencies(ctx) await mountInvariants(ctx) @@ -30,7 +30,7 @@ async function setup(script: Script) { await ctx.plugin(SubagentService) const adapter = new MockAdapter(script) ctx.llm.registerAdapter(['mock'], adapter) - const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock' }) + const parent = ctx.agentLoop.create(SessionId('parent'), { provider: 'mock', model: 'mock', ...parentOptions }) return { ctx, parent, adapter } } @@ -111,6 +111,27 @@ describe('startInProcessRun', () => { await run.dispose() }) + it('inherits the parent output-token cap and accepts an explicit child override', async () => { + const { ctx, parent, adapter } = await setup( + [textResponse('inherited'), textResponse('overridden')], + { maxTokens: 111 }, + ) + const inherited = await startInProcessRun(request(parent), {}) + await inherited.result + expect(adapter.requests[0]?.maxTokens).toBe(111) + expect(ctx.agents.get(inherited.id)?.options.maxTokens).toBe(111) + await inherited.dispose() + + const overridden = await startInProcessRun({ + ...request(parent), + agentOptions: { maxTokens: 222 }, + }, {}) + await overridden.result + expect(adapter.requests[1]?.maxTokens).toBe(222) + expect(ctx.agents.get(overridden.id)?.options.maxTokens).toBe(222) + await overridden.dispose() + }) + it('counts a RESUMED child by its persisted header depth, not the absent runtime depth', async () => { // Resume rebuilds runtime options, so the durable header must keep this // depth-1 child from delegating as though it were top-level. diff --git a/packages/subagent/tool-subagent/README.i18n.yaml b/packages/subagent/tool-subagent/README.i18n.yaml index bf88b03740..f021a7266e 100644 --- a/packages/subagent/tool-subagent/README.i18n.yaml +++ b/packages/subagent/tool-subagent/README.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -README.md: 0f1bc6eae00dce7b1832f76d0267edd2c6ef2a93 -README.zh.md: 49fca6af9fd039d4436f8c209a328d2fb0efcf07 +# pnpm run verify-translation-pairing --write packages/subagent/tool-subagent/README.md +README.md: 20bb6b9c59a13f23301368faefe18849ccc0b1e9 +README.zh.md: 9435ff638b0d021507af487a54fabac3018ca400 diff --git a/packages/subagent/tool-subagent/README.md b/packages/subagent/tool-subagent/README.md index 0f1bc6eae0..20bb6b9c59 100644 --- a/packages/subagent/tool-subagent/README.md +++ b/packages/subagent/tool-subagent/README.md @@ -21,7 +21,7 @@ With `run_in_background: true`, the tool registers the parent-owned task before | `provider` (required) | Provider name (`spawn`, `fork`, `acp`, ...). | | `toolName` | Model-facing name, default `subagent`; distinct for every loaded instance. | | `enableRunInBackground` | Exposes background mode, default `true`; disabling also rejects forced background calls. | -| `agentOptions` | Default child options, currently including `model`. | +| `agentOptions` | Provider-specific child `provider`, `model`, and positive `maxTokens`; the in-process provider treats explicit values as overrides of inherited parent options. | | `persona` | Per-child persona; requires provider `persona` capability. | | `toolFilter` | Per-child global-tool restriction; requires `toolFilter` capability. | | `maxDepth` | Absolute delegation-depth cap, default `3` (`0` forbids delegation); a numeric cap requires the `depthLimit` capability and fails the mount without it. `'provider-managed'` sends no cap for an out-of-process provider whose budget belongs to the child harness. The tool stays visible at the cap; each attempted start checks the calling agent's current depth and returns an errored tool result when rejected. | diff --git a/packages/subagent/tool-subagent/README.zh.md b/packages/subagent/tool-subagent/README.zh.md index 49fca6af9f..9435ff638b 100644 --- a/packages/subagent/tool-subagent/README.zh.md +++ b/packages/subagent/tool-subagent/README.zh.md @@ -21,7 +21,7 @@ | `provider`（必填） | 提供方名称（`spawn`、`fork`、`acp` 等）。 | | `toolName` | 面向模型的名称，默认 `subagent`；每个已加载实例必须不同。 | | `enableRunInBackground` | 公开后台模式，默认 `true`；禁用时也会拒绝强制后台调用。 | -| `agentOptions` | 默认子 agent 选项，目前包括 `model`。 | +| `agentOptions` | 传给具体 provider 的子 agent `provider`、`model` 和正整数 `maxTokens`；进程内 provider 会用显式值覆盖继承的父级选项。 | | `persona` | 每个子 agent 独立的 persona；要求提供方具备 `persona` 能力。 | | `toolFilter` | 每个子 agent 独立的全局工具限制；要求提供方具备 `toolFilter` 能力。 | | `maxDepth` | 绝对委派深度上限，默认 `3`（`0` 禁止委派）；数值上限要求 `depthLimit` 能力，缺失时挂载失败。对于预算由子 harness 拥有的进程外提供方，`'provider-managed'` 不发送上限。工具在达到上限时仍然可见；每次尝试启动都会检查调用 agent 的当前深度，被拒绝时返回出错的工具结果。 | diff --git a/packages/subagent/tool-subagent/src/index.ts b/packages/subagent/tool-subagent/src/index.ts index 4eb29d0c6e..a89abaa139 100644 --- a/packages/subagent/tool-subagent/src/index.ts +++ b/packages/subagent/tool-subagent/src/index.ts @@ -74,7 +74,8 @@ export const Config: z = z.object({ agentOptions: z.object({ provider: z.string(), model: z.string(), - }).default(undefined as unknown as { provider: string; model: string }), + maxTokens: z.number().step(1).min(1).max(Number.MAX_SAFE_INTEGER), + }).default(undefined as unknown as { provider: string; model: string; maxTokens: number }), persona: z.string(), // Preserve omission; Schemastery's `{ allow: [] }` default would deny every tool. toolFilter: z.object({ diff --git a/packages/ui/jsonrpc/README.i18n.yaml b/packages/ui/jsonrpc/README.i18n.yaml index 28bb4357db..3176b2ce40 100644 --- a/packages/ui/jsonrpc/README.i18n.yaml +++ b/packages/ui/jsonrpc/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/ui/jsonrpc/README.md -README.md: 48eb6106fe4b015f114b264a312249a92128266f -README.zh.md: 8ec2d57a206d770d0b77ee69036457e3b2864303 +README.md: b1219ba10269fc7d046da22c280ff1b91424a5ae +README.zh.md: 63615654769bf4ed7a69c09dc818af034c3a3c3c diff --git a/packages/ui/jsonrpc/README.md b/packages/ui/jsonrpc/README.md index 48eb6106fe..b1219ba102 100644 --- a/packages/ui/jsonrpc/README.md +++ b/packages/ui/jsonrpc/README.md @@ -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 diff --git a/packages/ui/jsonrpc/README.zh.md b/packages/ui/jsonrpc/README.zh.md index 8ec2d57a20..6361565476 100644 --- a/packages/ui/jsonrpc/README.zh.md +++ b/packages/ui/jsonrpc/README.zh.md @@ -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 diff --git a/packages/ui/jsonrpc/src/server.ts b/packages/ui/jsonrpc/src/server.ts index 7d9d5eddae..aa4769aebc 100644 --- a/packages/ui/jsonrpc/src/server.ts +++ b/packages/ui/jsonrpc/src/server.ts @@ -57,6 +57,7 @@ export class HarnessSdkServer { private cwd = process.cwd() private provider = 'deepseek' private model = 'deepseek' + private maxTokens: number | undefined private llmFiber: { dispose(): Promise } | undefined private readonly sessions = new Map() private readonly sessionCreations = new Map>() @@ -114,9 +115,14 @@ export class HarnessSdkServer { * @returns server identity for the handshake. */ async initialize(params: InitializeParams): Promise { + 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, {}) @@ -232,7 +238,11 @@ 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) diff --git a/packages/ui/jsonrpc/tests/server.spec.ts b/packages/ui/jsonrpc/tests/server.spec.ts index 12c841918d..19ad56881c 100644 --- a/packages/ui/jsonrpc/tests/server.spec.ts +++ b/packages/ui/jsonrpc/tests/server.spec.ts @@ -123,6 +123,7 @@ describe('HarnessSdkServer', () => { cwd: storageDir, provider: 'deepseek', model: 'dsagent-model', + maxTokens: 321, }) as { serverInfo: { name: string } } expect(init.serverInfo.name).toBe('deepseek-harness-sdk-runtime') @@ -132,8 +133,9 @@ 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') @@ -860,6 +862,27 @@ 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) @@ -974,15 +997,18 @@ 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 + initialize(params: { cwd: string; provider: string; model: string; maxTokens?: number }): Promise getOrCreateSession(sessionId: string): Promise shutdown(): Promise> } - 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() }) diff --git a/python/sdk/README.i18n.yaml b/python/sdk/README.i18n.yaml index ed74d60087..048fecb6f9 100644 --- a/python/sdk/README.i18n.yaml +++ b/python/sdk/README.i18n.yaml @@ -1,6 +1,6 @@ # Bilingual-pair consistency record (docs/i18n/README.md): the git blob hash of each # 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 -README.md: bfa31a712acd6fccf1458a0a80fc2ff80dfe114e -README.zh.md: 11ebcdd133b2fd839b73f50ef2be2e531e8bbc2a +# pnpm run verify-translation-pairing --write python/sdk/README.md +README.md: f1e16e724efd6f71f63e475e47d7e4d704b8ceac +README.zh.md: e56ae31020d1068e009056c20d8f11bab145dc8a diff --git a/python/sdk/README.md b/python/sdk/README.md index bfa31a712a..f1e16e724e 100644 --- a/python/sdk/README.md +++ b/python/sdk/README.md @@ -27,12 +27,13 @@ from deepseek_harness import DeepSeekHarness with DeepSeekHarness( provider="deepseek", model="deepseek-v4-flash", + max_tokens=49_152, cordis="examples/jsonrpc-agent/cordis.yml", ) as harness: result = harness.run("Make the requested code change.") ``` -`provider` selects a provider route registered by the chosen Cordis composition; `model` is the model id resolved by that adapter. The bundled default composition registers `deepseek`. A custom composition can mount `llm-pi-ai`, configure provider-specific credentials/endpoints there, and select any provider/model present in pi-ai's installed catalog. +`provider` selects a provider route registered by the chosen Cordis composition; `model` is the model id resolved by that adapter. `max_tokens` is an optional positive per-request output-token cap for the root agent and its in-process descendants; omission leaves the provider default in control. Compaction summaries keep the separate limit configured by their compaction plugin. The bundled default composition registers `deepseek`. A custom composition can mount `llm-pi-ai`, configure provider-specific credentials/endpoints there, and select any provider/model present in pi-ai's installed catalog. `HarnessClient` retains discovered subagent ancestry for the lifetime of the runtime process. During each `Session.run()`, `TurnResult.notifications` and `on_notification` receive the root session and all known descendant notifications in wire order, including nested subagent lifecycle and session events. `TurnResult.events` remains the root session's complete event stream, and `TurnResult.final_response` is the text content from its last `assistant/message`; descendant messages therefore cannot replace the root response. diff --git a/python/sdk/README.zh.md b/python/sdk/README.zh.md index 11ebcdd133..e56ae31020 100644 --- a/python/sdk/README.zh.md +++ b/python/sdk/README.zh.md @@ -23,12 +23,13 @@ from deepseek_harness import DeepSeekHarness with DeepSeekHarness( provider="deepseek", model="deepseek-v4-flash", + max_tokens=49_152, cordis="examples/jsonrpc-agent/cordis.yml", ) as harness: result = harness.run("Make the requested code change.") ``` -`provider` 用于选择当前 Cordis 组合已注册的提供方路由；`model` 是该适配器解析的模型 ID。内置默认组合注册 `deepseek`。自定义组合可以挂载 `llm-pi-ai`，在其中配置各提供方的凭据与端点，再选择 pi-ai 已安装目录中的任意提供方/模型组合。 +`provider` 用于选择当前 Cordis 组合已注册的提供方路由；`model` 是该适配器解析的模型 ID。`max_tokens` 是可选的正整数，用于限制根 agent 及其进程内后代每次请求的输出 token；省略时由提供方默认值控制。压缩摘要继续使用压缩插件单独配置的上限。内置默认组合注册 `deepseek`。自定义组合可以挂载 `llm-pi-ai`，在其中配置各提供方的凭据与端点，再选择 pi-ai 已安装目录中的任意提供方/模型组合。 `HarnessClient` 会在运行时进程的生命周期内保留已发现的 subagent（子 agent）祖先关系。每次执行 `Session.run()` 时，`TurnResult.notifications` 与 `on_notification` 会按线上的原始顺序收到根会话及所有已知后代的通知，其中包括嵌套 subagent 的生命周期与会话事件。`TurnResult.events` 仍只保存根会话的完整事件流，`TurnResult.final_response` 则取该会话最后一个 `assistant/message` 的文本内容，因此后代消息不会覆盖根会话回复。 diff --git a/python/sdk/src/deepseek_harness/api.py b/python/sdk/src/deepseek_harness/api.py index d96e974bc3..5986dc2cdc 100644 --- a/python/sdk/src/deepseek_harness/api.py +++ b/python/sdk/src/deepseek_harness/api.py @@ -20,6 +20,7 @@ class DeepSeekHarnessConfig: provider: str = "deepseek" model: str = "deepseek-v4-flash" + max_tokens: int | None = None cwd: str | None = None runtime_cwd: str | None = None session_root: str | None = None @@ -100,6 +101,7 @@ class DeepSeekHarness: cwd=self._cwd, provider=self.config.provider, model=self.config.model, + max_tokens=self.config.max_tokens, ) self._initialized = True diff --git a/python/sdk/src/deepseek_harness/client.py b/python/sdk/src/deepseek_harness/client.py index 8d4ec7f848..052969a694 100644 --- a/python/sdk/src/deepseek_harness/client.py +++ b/python/sdk/src/deepseek_harness/client.py @@ -120,12 +120,15 @@ class HarnessClient: cwd: str, provider: str, model: str, + max_tokens: int | None = None, ) -> InitializeResponse: payload: JsonObject = { "cwd": str(Path(cwd).resolve()), "provider": provider, "model": model, } + if max_tokens is not None: + payload["maxTokens"] = max_tokens try: return self.request("initialize", payload, response_model=InitializeResponse) except BaseException: diff --git a/python/sdk/tests/test_client.py b/python/sdk/tests/test_client.py index d5460b8683..de2927c598 100644 --- a/python/sdk/tests/test_client.py +++ b/python/sdk/tests/test_client.py @@ -15,6 +15,7 @@ from deepseek_harness import DeepSeekHarness, HarnessClient, HarnessConfig, Noti def test_high_level_sdk_runs_turn_and_collects_final_response(tmp_path: Path) -> None: script = tmp_path / "fake_runtime.py" env_dump = tmp_path / "env.json" + init_dump = tmp_path / "init.json" script.write_text( """ import json @@ -34,6 +35,7 @@ for line in sys.stdin: msg = json.loads(line) method = msg.get("method") if method == "initialize": + json.dump(msg.get("params"), open(os.environ["INIT_DUMP"], "w")) print(json.dumps({"jsonrpc": "2.0", "id": msg["id"], "result": {"serverInfo": {"name": "fake-runtime"}}}), flush=True) elif method == "session/prompt": params = msg.get("params") or {} @@ -62,12 +64,14 @@ for line in sys.stdin: with DeepSeekHarness( model="deepseek-v4-flash", + max_tokens=4096, cwd=str(tmp_path), cordis=str(tmp_path / "cordis.yml"), session_root=str(tmp_path / "sessions"), launch_args_override=(sys.executable, str(script)), env={ "ENV_DUMP": str(env_dump), + "INIT_DUMP": str(init_dump), "DEEPSEEK_API_KEY": "env-key", "DEEPSEEK_BASE_URL": "http://127.0.0.1:4321", }, @@ -83,6 +87,12 @@ for line in sys.stdin: assert dumped_env["DSH_CWD"] == str(tmp_path) assert dumped_env["DSH_SESSION_ROOT"] == str(tmp_path / "sessions") assert dumped_env["DSH_CORDIS_CONFIG"] == str(tmp_path / "cordis.yml") + assert json.loads(init_dump.read_text()) == { + "cwd": str(tmp_path), + "provider": "deepseek", + "model": "deepseek-v4-flash", + "maxTokens": 4096, + } def test_session_run_invokes_notification_callback_before_returning(tmp_path: Path) -> None: @@ -731,6 +741,8 @@ def test_public_signatures_omit_unsupported_wire_parameters() -> None: assert "profile" not in inspect.signature(DeepSeekHarness.run).parameters assert "profile" not in inspect.signature(Session.run).parameters assert "system_prompt" not in DeepSeekHarnessConfig.__dataclass_fields__ + assert "max_tokens" in DeepSeekHarnessConfig.__dataclass_fields__ + assert "max_tokens" in inspect.signature(HarnessClient.initialize).parameters assert "client_name" not in HarnessConfig.__dataclass_fields__ assert "client_version" not in HarnessConfig.__dataclass_fields__