We present \textbf{Turn}, a compiled, actor-based programming language -- statically typed for schema inference, dynamically typed at the value level -- for agentic software: programs that reason and act autonomously by delegating inference to large language models (LLMs). Existing approaches augment general-purpose languages with frameworks, encoding critical invariants (bounded context, typed inference output, credential isolation, durable state) as application-level conventions rather than language guarantees. Turn introduces five language-level constructs that address this gap. \emph{Cognitive Type Safety} makes LLM inference a typed primitive: the compiler generates a JSON Schema from a struct definition and the VM validates model output before binding. The \emph{confidence operator} enables deterministic control flow gated on model certainty. Turn's \emph{actor-based process model}, derived from Erlang, gives each agent an isolated context window, persistent memory, and mailbox. A \emph{capability-based identity system} returns opaque, unforgeable handles from the VM host, ensuring raw credentials never enter agent memory. Finally, \emph{compile-time schema absorption} (\texttt{use schema::<protocol>}) synthesizes typed API bindings from external specifications at compile time; the \texttt{openapi} adapter is shipped with \texttt{graphql}, \texttt{fhir}, and \texttt{mcp} in active development. We describe the language design, type rules, schema semantics, and a Rust-based bytecode VM, and evaluate Turn against representative agentic workloads. Turn is open source at https://github.com/ekizito96/Turn.

翻译：本文提出 **Turn**，一种编译型、基于参与者的编程语言——在模式推断层面采用静态类型，在值层面采用动态类型——专为智能体软件设计：即通过将推理任务委托给大型语言模型（LLM）来实现自主推理与行动的程序。现有方法通常在通用编程语言基础上通过框架进行增强，将关键不变性约束（如上下文边界、类型化推理输出、凭证隔离、持久化状态）编码为应用层约定而非语言级保障。Turn 通过引入五种语言级构造来填补这一空白。**认知类型安全** 将 LLM 推理实现为类型化原语：编译器根据结构体定义生成 JSON Schema，虚拟机在绑定前验证模型输出。**置信度运算符** 支持基于模型确定性的确定性控制流门控。Turn 的 **基于参与者的进程模型**（源自 Erlang）为每个智能体提供独立的上下文窗口、持久化内存和消息邮箱。**基于能力的身份系统** 从虚拟机宿主返回不透明且不可伪造的句柄，确保原始凭证永不进入智能体内存。最后，**编译时模式吸收**（`use schema::<protocol>`）在编译时根据外部规范合成类型化 API 绑定；`openapi` 适配器已随发行版提供，`graphql`、`fhir` 与 `mcp` 适配器正在积极开发中。本文阐述了语言设计、类型规则、模式语义及基于 Rust 的字节码虚拟机，并通过典型智能体工作负载对 Turn 进行了评估。Turn 已在 https://github.com/ekizito96/Turn 开源。