OpenRath：以会话为中心的智能体系统运行时状态

摘要

现代智能体系统常常面临运行时状态碎片化的问题：对话记录、工具效果、记忆事件、工作区放置、分支来源以及重放证据被分别记录，导致难以检查或复现。OpenRath通过一种类似PyTorch的编程模型来解决这一问题，该模型适用于多智能体、多会话系统。这里的类比涉及一个核心的一等运行时抽象的角色，而不是张量计算。其核心抽象是Session，即智能体与工作流之间传递的运行时值。Session是可分支、可检查、可重放、支持后端且可组合的。它记录对话片段、沙箱放置、谱系元数据、令牌使用、待办工作以及工具证据，同时定义记忆交互进入运行时记录的位置。由于这种状态由程序执行中使用的同一个值携带，因此分支、合并和重放成为显式的运行时操作，而非从外部追踪中重构的状态。OpenRath进一步定义了沙箱、工具、智能体、记忆、工作流和选择器，其中选择器将控制流转化为运行时路由的决策。本报告介绍了编程模型、架构、审计里程碑以及证据协议。其主张仅限于受控的运行时属性，而广泛的定量比较、实时提供商质量、可选后端可用性以及记忆质量则留待后续评估。核心论点是：Session为智能体系统提供了一个可审计组合的一等运行时值。

English

Modern agent systems often suffer from fragmented runtime state: transcripts, tool effects, memory events, workspace placement, branch provenance, and replay evidence are recorded separately and become difficult to inspect or reproduce. OpenRath addresses this issue with a PyTorch-like programming model for multi-agent, multi-session systems. The analogy concerns the role of a central first-class runtime abstraction, not tensor computation. Its core abstraction is Session, the runtime value passed between agents and workflows. A Session is branchable, inspectable, replayable, backend-aware, and composable. It records conversation chunks, sandbox placement, lineage metadata, token usage, pending work, and tool evidence, while defining where memory interactions enter the runtime record. Since this state is carried by the same value used in program execution, fork, merge, and replay become explicit runtime operations rather than states reconstructed from external traces. OpenRath further defines Sandbox, Tool, Agent, Memory, Workflow, and Selector, with Selector turning control flow into runtime-routed decisions. This report presents the programming model, architecture, audited milestones, and evidence protocol. Its claims are limited to controlled runtime properties, while broad quantitative comparisons, live-provider quality, optional-backend availability, and memory quality are left for follow-on evaluation. The central thesis is that Session provides agent systems with a first-class runtime value for auditable composition.