OpenRath：以会话为中心的智能体系统运行时状态

摘要

現代代理系統常面臨執行時期狀態碎片化的問題：對話記錄、工具效果、記憶事件、工作區配置、分支溯源及重播證據等資訊各自獨立紀錄，導致難以檢視或重現。OpenRath 透過類似 PyTorch 的編程模型解決此問題，適用於多代理、多工作階段的系統。此處的類比在於核心第一類執行時期抽象層的角色，而非張量運算。其核心抽象概念為 **Session**（工作階段），這是在代理與工作流程之間傳遞的執行時期數值。Session 具備可分支、可檢視、可重播、支援後端及可組合等特性。它記錄對話片段、沙箱配置、溯源元數據、代幣使用量、待辦事項與工具證據，同時定義記憶體互動在何處進入執行時期記錄。由於此狀態由程式執行過程所使用的同一個數值承載，因此分叉（fork）、合併（merge）與重播（replay）成為明確的執行時期操作，而非從外部軌跡重建的狀態。OpenRath 進一步定義了 Sandbox、Tool、Agent、Memory、Workflow 與 Selector 等元件，其中 Selector 將控制流程轉變為由執行時期路由的決策。本報告介紹其程式模型、架構、經審核的里程碑以及證據協議。其論述範圍僅限於受控的執行時期特性，而大範圍的量化比較、即時供應商品質、可選後端可用性以及記憶體品質等主題，則留待後續評估。核心論點為：Session 為代理系統提供了可稽核組合的第一類執行時期數值。

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.