c2851d498f377c7a6fdc293be4cc3b517d05745d
Why: Baseline and candidate must exercise their actual default prompts with identical route and resource limits. Evidence: SELF live-tag compilation passes. Impact: Evaluation harness only; normal automatic notice quality remains outside the controlled comparison. Refs: fast-slow-u2-u3 Task 7
Agent-System-Backend
对话系统后端:Go 模块化单体,默认构建为单二进制(go:embed 内嵌前端与嵌入式 SQLite 存储)。组合 Agent-Native / Agent-Squad / Agent-Intent 生态,依赖 agent-system-core 契约。
契约与架构见 Agent-System-Documents 设计方案与架构文档;开发规范见 development-guidelines(Dev 仓 development/guidelines)。本仓为 Agent-System 多仓组合的组成部分。
Description
对话系统后端:会话与流式管道、智能体运行时与画像、工具/上下文/文档解析/检索/设置管理、插件宿主(组合 Agent-Native/Squad/Intent);依赖 Agent-System-Core 契约,默认单二进制非容器部署。
26 MiB
Languages
Go
98.5%
Python
1.4%