# autogentstudio - Doramagic AI Context Pack > 定位：安装前体验与判断资产。它帮助宿主 AI 有一个好的开始，但不代表已经安装、执行或验证目标项目。 ## 充分原则 - **充分原则，不是压缩原则**：AI Context Pack 应该充分到让宿主 AI 在开工前理解项目价值、能力边界、使用入口、风险和证据来源；它可以分层组织，但不以最短摘要为目标。 - **压缩策略**：只压缩噪声和重复内容，不压缩会影响判断和开工质量的上下文。 ## 给宿主 AI 的使用方式 你正在读取 Doramagic 为 autogentstudio 编译的 AI Context Pack。请把它当作开工前上下文：帮助用户理解适合谁、能做什么、如何开始、哪些必须安装后验证、风险在哪里。不要声称你已经安装、运行或执行了目标项目。 ## Claim 消费规则 - **事实来源**：Repo Evidence + Claim/Evidence Graph；Human Wiki 只提供显著性、术语和叙事结构。 - **事实最低状态**：`supported` - `supported`：可以作为项目事实使用，但回答中必须引用 claim_id 和证据路径。 - `weak`：只能作为低置信度线索，必须要求用户继续核实。 - `inferred`：只能用于风险提示或待确认问题，不能包装成项目事实。 - `unverified`：不得作为事实使用，应明确说证据不足。 - `contradicted`：必须展示冲突来源，不得替用户强行选择一个版本。 ## 它最适合谁 - **想在安装前理解开源项目价值和边界的用户**：当前证据主要来自项目文档。 证据：`README.md` Claim：`clm_0002` supported 0.86 ## 它能做什么 - **命令行启动或安装流程**（需要安装后验证）：项目文档中存在可执行命令，真实使用需要在本地或宿主环境中运行这些命令。 证据：`README.md` Claim：`clm_0001` supported 0.86 ## 怎么开始 - `pip install -U "autogen-agentchat" "autogen-ext[openai]"` 证据：`README.md` Claim：`clm_0003` supported 0.86 - `pip install -U "autogenstudio"` 证据：`README.md` Claim：`clm_0004` supported 0.86 ## 继续前判断卡 - **当前建议**：需要管理员/安全审批 - **为什么**：继续前可能涉及密钥、账号、外部服务或敏感上下文，建议先经过管理员或安全审批。 ### 30 秒判断 - **现在怎么做**：需要管理员/安全审批 - **最小安全下一步**：先跑 Prompt Preview；若涉及凭证或企业环境，先审批再试装 - **先别相信**：角色质量和任务匹配不能直接相信。 - **继续会触碰**：角色选择偏差、命令执行、本地环境或项目文件 ### 现在可以相信 - **适合人群线索：想在安装前理解开源项目价值和边界的用户**（supported）：有 supported claim 或项目证据支撑，但仍不等于真实安装效果。 证据：`README.md` Claim：`clm_0002` supported 0.86 - **能力存在：命令行启动或安装流程**（supported）：可以相信项目包含这类能力线索；是否适合你的具体任务仍要试用或安装后验证。 证据：`README.md` Claim：`clm_0001` supported 0.86 - **存在 Quick Start / 安装命令线索**（supported）：可以相信项目文档出现过启动或安装入口；不要因此直接在主力环境运行。 证据：`README.md` Claim：`clm_0003` supported 0.86 ### 现在还不能相信 - **角色质量和任务匹配不能直接相信。**（unverified）：角色库证明有很多角色，不证明每个角色都适合你的具体任务，也不证明角色能产生高质量结果。 - **不能把角色文案当成真实执行能力。**（unverified）：安装前只能判断角色描述和任务画像是否匹配，不能证明它能在宿主 AI 里完成任务。 - **真实输出质量不能在安装前相信。**（unverified）：Prompt Preview 只能展示引导方式，不能证明真实项目中的结果质量。 - **宿主 AI 版本兼容性不能在安装前相信。**（unverified）：Claude、Cursor、Codex、Gemini 等宿主加载规则和版本差异必须在真实环境验证。 - **不会污染现有宿主 AI 行为，不能直接相信。**（inferred）：Skill、plugin、AGENTS/CLAUDE/GEMINI 指令可能改变宿主 AI 的默认行为。 - **可安全回滚不能默认相信。**（unverified）：除非项目明确提供卸载和恢复说明，否则必须先在隔离环境验证。 - **真实安装后是否与用户当前宿主 AI 版本兼容？**（unverified）：兼容性只能通过实际宿主环境验证。 - **项目输出质量是否满足用户具体任务？**（unverified）：安装前预览只能展示流程和边界，不能替代真实评测。 ### 继续会触碰什么 - **角色选择偏差**：用户对任务应该由哪个专家角色处理的判断。 原因：选错角色会让 AI 从错误专业视角回答，浪费时间或误导决策。 - **命令执行**：包管理器、网络下载、本地插件目录、项目配置或用户主目录。 原因：运行第一条命令就可能产生环境改动；必须先判断是否值得跑。 证据：`README.md` - **本地环境或项目文件**：安装结果、插件缓存、项目配置或本地依赖目录。 原因：安装前无法证明写入范围和回滚方式，需要隔离验证。 证据：`README.md` - **环境变量 / API Key**：项目入口文档明确出现 API key、token、secret 或账号凭证配置。 原因：如果真实安装需要凭证，应先使用测试凭证并经过权限/合规判断。 证据：`README.md`, `dotnet/README.md`, `python/docs/src/user-guide/autogenstudio-user-guide/usage.md`, `python/packages/agbench/README.md` 等 - **宿主 AI 上下文**：AI Context Pack、Prompt Preview、Skill 路由、风险规则和项目事实。 原因：导入上下文会影响宿主 AI 后续判断，必须避免把未验证项包装成事实。 ### 最小安全下一步 - **先跑 Prompt Preview**：先用交互式试用验证任务画像和角色匹配，不要先导入整套角色库。（适用：任何项目都适用，尤其是输出质量未知时。） - **只在隔离目录或测试账号试装**：避免安装命令污染主力宿主 AI、真实项目或用户主目录。（适用：存在命令执行、插件配置或本地写入线索时。） - **不要使用真实生产凭证**：环境变量/API key 一旦进入宿主或工具链，可能产生账号和合规风险。（适用：出现 API、TOKEN、KEY、SECRET 等环境线索时。） - **安装后只验证一个最小任务**：先验证加载、兼容、输出质量和回滚，再决定是否深用。（适用：准备从试用进入真实工作流时。） ### 退出方式 - **保留安装前状态**：记录原始宿主配置和项目状态，后续才能判断是否可恢复。 - **保留原始角色选择记录**：如果输出偏题，可以回到任务画像阶段重新选择角色，而不是继续沿着错误角色推进。 - **记录安装命令和写入路径**：没有明确卸载说明时，至少要知道哪些目录或配置需要手动清理。 - **准备撤销测试 API key 或 token**：测试凭证泄露或误用时，可以快速止损。 - **如果没有回滚路径，不进入主力环境**：不可回滚是继续前阻断项，不应靠信任或运气继续。 ## 哪些只能预览 - 解释项目适合谁和能做什么 - 基于项目文档演示典型对话流程 - 帮助用户判断是否值得安装或继续研究 ## 哪些必须安装后验证 - 真实安装 Skill、插件或 CLI - 执行脚本、修改本地文件或访问外部服务 - 验证真实输出质量、性能和兼容性 ## 边界与风险判断卡 - **把安装前预览误认为真实运行**：用户可能高估项目已经完成的配置、权限和兼容性验证。 处理方式：明确区分 prompt_preview_can_do 与 runtime_required。 Claim：`clm_0005` inferred 0.45 - **命令执行会修改本地环境**：安装命令可能写入用户主目录、宿主插件目录或项目配置。 处理方式：先在隔离环境或测试账号中运行。 证据：`README.md` Claim：`clm_0006` supported 0.86 - **待确认**：真实安装后是否与用户当前宿主 AI 版本兼容？。原因：兼容性只能通过实际宿主环境验证。 - **待确认**：项目输出质量是否满足用户具体任务？。原因：安装前预览只能展示流程和边界，不能替代真实评测。 - **待确认**：安装命令是否需要网络、权限或全局写入？。原因：这影响企业环境和个人环境的安装风险。 ## 开工前工作上下文 ### 加载顺序 - 先读取 how_to_use.host_ai_instruction，建立安装前判断资产的边界。 - 读取 claim_graph_summary，确认事实来自 Claim/Evidence Graph，而不是 Human Wiki 叙事。 - 再读取 intended_users、capabilities 和 quick_start_candidates，判断用户是否匹配。 - 需要执行具体任务时，优先查 role_skill_index，再查 evidence_index。 - 遇到真实安装、文件修改、网络访问、性能或兼容性问题时，转入 risk_card 和 boundaries.runtime_required。 ### 任务路由 - **命令行启动或安装流程**：先说明这是安装后验证能力，再给出安装前检查清单。 边界：必须真实安装或运行后验证。 证据：`README.md` Claim：`clm_0001` supported 0.86 ### 上下文规模 - 文件总数：1753 - 重要文件覆盖：40/1753 - 证据索引条目：80 - 角色 / Skill 条目：77 ### 证据不足时的处理 - **missing_evidence**：说明证据不足，要求用户提供目标文件、README 段落或安装后验证记录；不要补全事实。 - **out_of_scope_request**：说明该任务超出当前 AI Context Pack 证据范围，并建议用户先查看 Human Manual 或真实安装后验证。 - **runtime_request**：给出安装前检查清单和命令来源，但不要替用户执行命令或声称已执行。 - **source_conflict**：同时展示冲突来源，标记为待核实，不要强行选择一个版本。 ## Prompt Recipes ### 适配判断 - 目标：判断这个项目是否适合用户当前任务。 - 预期输出：适配结论、关键理由、证据引用、安装前可预览内容、必须安装后验证内容、下一步建议。 ```text 请基于 autogentstudio 的 AI Context Pack，先问我 3 个必要问题，然后判断它是否适合我的任务。回答必须包含：适合谁、能做什么、不能做什么、是否值得安装、证据来自哪里。所有项目事实必须引用 evidence_refs、source_paths 或 claim_id。 ``` ### 安装前体验 - 目标：让用户在安装前感受核心工作流，同时避免把预览包装成真实能力或营销承诺。 - 预期输出：一段带边界标签的体验剧本、安装后验证清单和谨慎建议；不含真实运行承诺或强营销表述。 ```text 请把 autogentstudio 当作安装前体验资产，而不是已安装工具或真实运行环境。 请严格输出四段： 1. 先问我 3 个必要问题。 2. 给出一段“体验剧本”：用 [安装前可预览]、[必须安装后验证]、[证据不足] 三种标签展示它可能如何引导工作流。 3. 给出安装后验证清单：列出哪些能力只有真实安装、真实宿主加载、真实项目运行后才能确认。 4. 给出谨慎建议：只能说“值得继续研究/试装”“先补充信息后再判断”或“不建议继续”，不得替项目背书。 硬性边界： - 不要声称已经安装、运行、执行测试、修改文件或产生真实结果。 - 不要写“自动适配”“确保通过”“完美适配”“强烈建议安装”等承诺性表达。 - 如果描述安装后的工作方式，必须使用“如果安装成功且宿主正确加载 Skill，它可能会……”这种条件句。 - 体验剧本只能写成“示例台词/假设流程”：使用“可能会询问/可能会建议/可能会展示”，不要写“已写入、已生成、已通过、正在运行、正在生成”。 - Prompt Preview 不负责给安装命令；如用户准备试装，只能提示先阅读 Quick Start 和 Risk Card，并在隔离环境验证。 - 所有项目事实必须来自 supported claim、evidence_refs 或 source_paths；inferred/unverified 只能作风险或待确认项。 ``` ### 角色 / Skill 选择 - 目标：从项目里的角色或 Skill 中挑选最匹配的资产。 - 预期输出：候选角色或 Skill 列表，每项包含适用场景、证据路径、风险边界和是否需要安装后验证。 ```text 请读取 role_skill_index，根据我的目标任务推荐 3-5 个最相关的角色或 Skill。每个推荐都要说明适用场景、可能输出、风险边界和 evidence_refs。 ``` ### 风险预检 - 目标：安装或引入前识别环境、权限、规则冲突和质量风险。 - 预期输出：环境、权限、依赖、许可、宿主冲突、质量风险和未知项的检查清单。 ```text 请基于 risk_card、boundaries 和 quick_start_candidates，给我一份安装前风险预检清单。不要替我执行命令，只说明我应该检查什么、为什么检查、失败会有什么影响。 ``` ### 宿主 AI 开工指令 - 目标：把项目上下文转成一次对话开始前的宿主 AI 指令。 - 预期输出：一段边界明确、证据引用明确、适合复制给宿主 AI 的开工前指令。 ```text 请基于 autogentstudio 的 AI Context Pack，生成一段我可以粘贴给宿主 AI 的开工前指令。这段指令必须遵守 not_runtime=true，不能声称项目已经安装、运行或产生真实结果。 ``` ## 角色 / Skill 索引 - 共索引 77 个角色 / Skill / 项目文档条目。 - **Docs**（project_doc）：You can find the project documentation here https://microsoft.github.io/autogen/dev/ . 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/design/readme.md` - **How to build and run the website**（project_doc）：Firstly, go to autogen/dotnet folder and run the following command to build the website: 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/dotnet/README.md` - **Building the AutoGen Documentation**（project_doc）：AutoGen documentation is based on the sphinx documentation system and uses the myst-parser to render markdown files. It uses the pydata-sphinx-theme https://pydata-sphinx-theme.readthedocs.io/en/latest/ to style the documentation. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/README.md` - **AutoGen ! Maintenance Mode https://img.shields.io/badge/status-maintenance%20mode-orange https://github.com/microsoft/a…**（project_doc）：! Twitter https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40pyautogen https://twitter.com/pyautogen ! LinkedIn https://img.shields.io/badge/LinkedIn-Company?style=flat&logo=linkedin&logoColor=white https://www.linkedin.com/company/105812540 ! Discord https://img.shields.io/badge/discord-chat-green?logo=discord https://aka.ms/autogen-discord ! Documentation https://img… 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`README.md` - **AutoGen for .NET**（project_doc）：Thre are two sets of packages here: AutoGen.\ the older packages derived from AutoGen 0.2 for .NET - these will gradually be deprecated and ported into the new packages Microsoft.AutoGen. the new packages for .NET that use the event-driven model - These APIs are not yet stable and are subject to change. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/README.md` - **AutoGen Python Development Guide**（project_doc）：! Docs dev https://img.shields.io/badge/Docs-dev-blue https://microsoft.github.io/autogen/dev/ ! Docs latest release https://img.shields.io/badge/Docs-latest%20release-blue https://microsoft.github.io/autogen/dev/ ! PyPi autogen-core https://img.shields.io/badge/PyPi-autogen--core-blue?logo=pypi https://pypi.org/project/autogen-core/ ! PyPi autogen-agentchat https://img.shields.io/badge/PyPi-autogen--agentchat-blue?… 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/README.md` - **NuGet Directory**（project_doc）：This directory contains resources and metadata for packaging the AutoGen.NET SDK as a NuGet package. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/nuget/README.md` - **AutoGen 0.4 .NET Hello World Sample**（project_doc）：AutoGen 0.4 .NET Hello World Sample 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/samples/Hello/HelloAgent/README.md` - **AutoGen 0.4 .NET Hello World Sample**（project_doc）：AutoGen 0.4 .NET Hello World Sample 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/samples/Hello/HelloAgentState/README.md` - **Multiproject App Host for HelloAgent**（project_doc）：Multiproject App Host for HelloAgent 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/samples/Hello/README.md` - **GitHub Dev Team with AI Agents**（project_doc）：Build a Dev Team using event driven agents. This project is an experiment and is not intended to be used in production. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/samples/dev-team/README.md` - **TODO**（project_doc）： 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/samples/dev-team/seed-memory/README.md` - **AutoGen.LMStudio**（project_doc）：This package provides support for consuming openai-like API from LMStudio local server. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/src/AutoGen.LMStudio/README.md` - **AutoGen.SourceGenerator**（project_doc）：This package carries a source generator that adds support for type-safe function definition generation. Simply mark a method with Function attribute, and the source generator will generate a function definition and a function call wrapper for you. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/src/AutoGen.SourceGenerator/README.md` - **Microsoft.AutoGen**（project_doc）：- Getting started sample ../../samples/getting-started/ 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/src/Microsoft.AutoGen/readme.md` - **How to build and run the website**（project_doc）：Prerequisites - dotnet 7.0 or later 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/website/README.md` - **AutoGenBench**（project_doc）：AutoGenBench agbench is a tool for repeatedly running a set of pre-defined AutoGen tasks in a setting with tightly-controlled initial conditions. With each run, AutoGenBench will start from a blank slate. The agents being evaluated will need to work out what code needs to be written, and what libraries or dependencies to install, to solve tasks. The results of each run are logged, and can be ingested by analysis or… 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/agbench/README.md` - **GAIA Benchmark**（project_doc）：This scenario implements the GAIA https://arxiv.org/abs/2311.12983 agent benchmark. Before you begin, make sure you have followed instruction in ../README.md to prepare your environment. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/agbench/benchmarks/GAIA/README.md` - **HumanEval Benchmark**（project_doc）：This scenario implements a modified version of the HumanEval https://arxiv.org/abs/2107.03374 benchmark. Compared to the original benchmark, there are two key differences here: 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/agbench/benchmarks/HumanEval/README.md` - **Benchmarking Agents**（project_doc）：This directory provides ability to benchmarks agents e.g., built using Autogen using AgBench. Use the instructions below to prepare your environment for benchmarking. Once done, proceed to relevant benchmarks directory e.g., benchmarks/GAIA for further scenario-specific instructions. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/agbench/benchmarks/README.md` - **AutoGen AgentChat**（project_doc）：- Documentation https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/autogen-agentchat/README.md` - **AutoGen Core**（project_doc）：- Documentation https://microsoft.github.io/autogen/stable/user-guide/core-user-guide/index.html 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/autogen-core/README.md` - **AutoGen Extensions**（project_doc）：- Documentation https://microsoft.github.io/autogen/stable/user-guide/extensions-user-guide/index.html 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/autogen-ext/README.md` - **Task-Centric Memory**（project_doc）：Task-Centric Memory EXPERIMENTAL, RESEARCH IN PROGRESS 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/autogen-ext/src/autogen_ext/experimental/task_centric_memory/README.md` - **MCP Session Host**（project_doc）：The McpSessionHost supports MCP Server - MCP Host requests within the AutoGen ecosystem. By design it should require minimal or no changes to your AutoGen agents, simply provide a host to the McpWorkbench . 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/autogen-ext/src/autogen_ext/tools/mcp/_host/README.md` - **Magentic-One**（project_doc）：Magentic-One is now available as part of the autogen-agentchat library. Please see the user guide https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/magentic-one.html for information. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/autogen-magentic-one/README.md` - **AutoGen Studio**（project_doc）：! PyPI version https://badge.fury.io/py/autogenstudio.svg https://badge.fury.io/py/autogenstudio ! PyPI - Downloads https://img.shields.io/pypi/dm/autogenstudio 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/autogen-studio/README.md` - **AutoGen Studio frontend**（project_doc）：Run the UI in dev mode make changes and see them reflected in the browser with hot reloading : 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/autogen-studio/frontend/README.md` - **AddComponentDropdown Usage Examples**（project_doc）：AddComponentDropdown Usage Examples 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/autogen-studio/frontend/src/components/shared/README.md` - **test-utils**（project_doc）： 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/autogen-test-utils/README.md` - **component-schema-gen**（project_doc）：This is a tool to generate schema for built in components. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/component-schema-gen/README.md` - **magentic-one-cli**（project_doc）： 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/magentic-one-cli/README.md` - **pyautogen**（project_doc）：NOTE: This is a proxy package for the latest version of autogen-agentchat https://pypi.org/project/autogen-agentchat/ . If you are looking for the 0.2.x version, please pin to pyautogen~=0.2.0 . To migrate from 0.2.x to the latest version, please refer to the migration guide https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/migration-guide.html . Read our previous clarification regarding to… 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/pyautogen/README.md` - **Multi-Agent PostgreSQL Data Management System with AutoGen and Azure PostgreSQL**（project_doc）：Multi-Agent PostgreSQL Data Management System with AutoGen and Azure PostgreSQL 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/agentchat_azure_postgresql/README.md` - **Building a Multi-Agent Application with AutoGen and Chainlit**（project_doc）：Building a Multi-Agent Application with AutoGen and Chainlit 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/agentchat_chainlit/README.md` - **AgentChat Chess Game**（project_doc）：This is a simple chess game that you can play with an AI agent. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/agentchat_chess_game/README.md` - **AgentChat App with FastAPI**（project_doc）：This sample demonstrates how to create a simple chat application using AgentChat https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html and FastAPI https://fastapi.tiangolo.com/ . 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/agentchat_fastapi/README.md` - **Building an AI Assistant Application with AutoGen and GraphRAG**（project_doc）：Building an AI Assistant Application with AutoGen and GraphRAG 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/agentchat_graphrag/README.md` - **Streamlit AgentChat Sample Application**（project_doc）：Streamlit AgentChat Sample Application 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/agentchat_streamlit/README.md` - **Async Human-in-the-Loop Example**（project_doc）：An example showing human-in-the-loop which waits for human input before making the tool call. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/core_async_human_in_the_loop/README.md` - **Core ChainLit Integration Sample**（project_doc）：In this sample, we will demonstrate how to build simple chat interface that interacts with a Core https://microsoft.github.io/autogen/stable/user-guide/core-user-guide/index.html agent or a team, using Chainlit https://github.com/Chainlit/chainlit , and support streaming messages. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/core_chainlit/README.md` - **Chess Game Example**（project_doc）：An example with two chess player agents that executes its own tools to demonstrate tool use and reflection on tool use. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/core_chess_game/README.md` - **Distributed Group Chat**（project_doc）：This example runs a gRPC server using GrpcWorkerAgentRuntimeHost ../../src/autogen core/application/ worker runtime host.py and instantiates three distributed runtimes using GrpcWorkerAgentRuntime ../../src/autogen core/application/ worker runtime.py . These runtimes connect to the gRPC server as hosts and facilitate a round-robin distributed group chat. This example leverages the Azure OpenAI Service https://azure.… 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/core_distributed-group-chat/README.md` - **Multi Agent Orchestration, Distributed Agent Runtime Example**（project_doc）：Multi Agent Orchestration, Distributed Agent Runtime Example 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/core_semantic_router/README.md` - **AutoGen-Core Streaming Chat with Multi-Agent Handoffs via FastAPI**（project_doc）：AutoGen-Core Streaming Chat with Multi-Agent Handoffs via FastAPI 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/core_streaming_handoffs_fastapi/README.md` - **AutoGen-Core Streaming Chat API with FastAPI**（project_doc）：AutoGen-Core Streaming Chat API with FastAPI 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/core_streaming_response_fastapi/README.md` - **Python and dotnet agents interoperability sample**（project_doc）：Python and dotnet agents interoperability sample 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/core_xlang_hello_python_agent/README.md` - **gitty Warning: WIP**（project_doc）：This is an AutoGen powered CLI that generates draft replies for issues and pull requests to reduce maintenance overhead for open source projects. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/gitty/README.md` - **Task-Centric Memory Code Samples**（project_doc）：Task-Centric Memory Code Samples EXPERIMENTAL, RESEARCH IN PROGRESS 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/samples/task_centric_memory/README.md` - **{{cookiecutter.package name}}**（project_doc）： 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/templates/new-package/{{cookiecutter.package_name}}/README.md` - **Contributing**（project_doc）：The project welcomes contributions from developers and organizations worldwide. Our goal is to foster a collaborative and inclusive community where diverse perspectives and expertise can drive innovation and enhance the project's capabilities. Whether you are an individual contributor or represent an organization, we invite you to join us in shaping the future of this project. Possible contributions include but not… 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`CONTRIBUTING.md` - **Contributing to AutoGenBench**（project_doc）：As part of the broader AutoGen project, AutoGenBench welcomes community contributions. Contributions are subject to AutoGen's contribution guidelines https://microsoft.github.io/autogen/docs/Contribute , as well as a few additional AutoGenBench-specific requirements outlined here. You may also wish to develop your own private benchmark scenarios and the guidance in this document will help with such efforts as well.… 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/packages/agbench/CONTRIBUTING.md` - **AutoGen 0.4 .NET Hello World Sample**（project_doc）：AutoGen 0.4 .NET Hello World Sample 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/test/Microsoft.AutoGen.Integration.Tests.AppHosts/HelloAgentTests/README.md` - **Python and dotnet agents interoperability sample**（project_doc）：Python and dotnet agents interoperability sample 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`dotnet/test/Microsoft.AutoGen.Integration.Tests.AppHosts/core_xlang_hello_python_agent/README.md` - **AutoGen Core**（project_doc）：AutoGen Core for .NET follows the same concepts and conventions of its Python counterpart. In fact, in order to understand the concepts in the .NET version, we recommend reading the Python documentation https://microsoft.github.io/autogen/stable/ first. Unless otherwise stated, the concepts in the Python version map to .NET. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/dotnet/core/index.md` - **Installation**（project_doc）：The Core and Contracts packages will give you what you need for writing and running agents using the Core API within a single process. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/dotnet/core/installation.md` - **optionally - for distributed agent systems:**（project_doc）：AutoGen .NET A .NET framework for building AI agents and applications 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/dotnet/index.md` - **AutoGen**（project_doc）：.hero-title { font-size: 60px; font-weight: bold; margin: 2rem auto 0; } 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/index.md` - **Examples**（project_doc）：A list of examples to help you get started with AgentChat. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/agentchat-user-guide/examples/index.md` - **AgentChat**（project_doc）：AgentChat is a high-level API for building multi-agent applications. It is built on top of the autogen-core ../core-user-guide/index.md package. For beginner users, AgentChat is the recommended starting point. For advanced users, autogen-core ../core-user-guide/index.md 's event-driven programming model provides more flexibility and control over the underlying components. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/agentchat-user-guide/index.md` - **Installation**（project_doc）：Create a Virtual Environment optional 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/agentchat-user-guide/installation.md` - **Introduction**（project_doc）：This tutorial provides a step-by-step guide to using AgentChat. Make sure you have first followed the installation instructions ../installation.md to prepare your environment. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/agentchat-user-guide/tutorial/index.md` - **AutoGen Studio**（project_doc）：! PyPI version https://badge.fury.io/py/autogenstudio.svg https://badge.fury.io/py/autogenstudio ! Downloads https://static.pepy.tech/badge/autogenstudio/week https://pepy.tech/project/autogenstudio 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/autogenstudio-user-guide/index.md` - **Installation**（project_doc）：There are two ways to install AutoGen Studio - from PyPi or from source. We recommend installing from PyPi unless you plan to modify the source code. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/autogenstudio-user-guide/installation.md` - **Cookbook**（project_doc）：This section contains a collection of recipes that demonstrate how to use the Core API features. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/core-user-guide/cookbook/index.md` - **Core**（project_doc）：{toctree} :maxdepth: 1 :hidden: :caption: Core Concepts 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/core-user-guide/index.md` - **Installation**（project_doc）：Create a Virtual Environment optional 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/core-user-guide/installation.md` - **Extensions**（project_doc）：installation discover create-your-own 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/extensions-user-guide/index.md` - **Installation**（project_doc）：First-part maintained extensions are available in the autogen-ext package. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`python/docs/src/user-guide/extensions-user-guide/installation.md` - **Programming Model**（project_doc）：Understanding your workflow and mapping it to agents is the key to building an agent system in AutoGen. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/design/01 - Programming Model.md` - **Topics**（project_doc）：This document describes the semantics and components of publishing messages and subscribing to topics. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/design/02 - Topics.md` - **Agent Worker Protocol**（project_doc）：The system consists of multiple processes, each being either a service process or a worker process. Worker processes host application code agents and connect to a service process. Workers advertise the agents which they support to the service, so the service can decide which worker to place agents on. Service processes coordinate placement of agents on worker processes and facilitate communication between agents. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/design/03 - Agent Worker Protocol.md` - **Agent and Topic ID Specs**（project_doc）：This document describes the structure, constraints, and behavior of Agent IDs and Topic IDs. 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/design/04 - Agent and Topic ID Specs.md` - **AutoGen Services**（project_doc）：Each AutoGen agent system has one or more Agent Workers and a set of services for managing/supporting the agents. The services and workers can all be hosted in the same process or in a distributed system. When in the same process communication and event delivery is in-memory. When distributed, workers communicate with the service over gRPC. In all cases, events are packaged as CloudEvents. There are multiple options… 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/design/05 - Services.md` - **Differences from Python**（project_doc）：Publishing to a topic that an agent is also subscribed to 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/dotnet/core/differences-from-python.md` - **Using Protocol Buffers to Define Message Types**（project_doc）：Using Protocol Buffers to Define Message Types 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/dotnet/core/protobuf-message-types.md` - **Tutorial**（project_doc）：!TIP If you'd prefer to just see the code the entire sample is available as a project here https://github.com/microsoft/autogen/tree/main/dotnet/samples/GettingStarted . 激活提示：当用户需要理解项目结构、安装方式或边界时参考。 证据：`docs/dotnet/core/tutorial.md` ## 证据索引 - 共索引 80 条证据。 - **Docs**（documentation）：You can find the project documentation here https://microsoft.github.io/autogen/dev/ . 证据：`docs/design/readme.md` - **How to build and run the website**（documentation）：Firstly, go to autogen/dotnet folder and run the following command to build the website: 证据：`docs/dotnet/README.md` - **Building the AutoGen Documentation**（documentation）：AutoGen documentation is based on the sphinx documentation system and uses the myst-parser to render markdown files. It uses the pydata-sphinx-theme https://pydata-sphinx-theme.readthedocs.io/en/latest/ to style the documentation. 证据：`python/docs/README.md` - **AutoGen ! Maintenance Mode https://img.shields.io/badge/status-maintenance%20mode-orange https://github.com/microsoft/a…**（documentation）：! Twitter https://img.shields.io/twitter/url/https/twitter.com/cloudposse.svg?style=social&label=Follow%20%40pyautogen https://twitter.com/pyautogen ! LinkedIn https://img.shields.io/badge/LinkedIn-Company?style=flat&logo=linkedin&logoColor=white https://www.linkedin.com/company/105812540 ! Discord https://img.shields.io/badge/discord-chat-green?logo=discord https://aka.ms/autogen-discord ! Documentation https://img.shields.io/badge/Documentation-AutoGen-blue?logo=read-the-docs https://microsoft.github.io/autogen/ ! Blog https://img.shields.io/badge/Blog-AutoGen-blue?logo=blogger https://devblogs.microsoft.com/autogen/ 证据：`README.md` - **AutoGen for .NET**（documentation）：Thre are two sets of packages here: AutoGen.\ the older packages derived from AutoGen 0.2 for .NET - these will gradually be deprecated and ported into the new packages Microsoft.AutoGen. the new packages for .NET that use the event-driven model - These APIs are not yet stable and are subject to change. 证据：`dotnet/README.md` - **AutoGen Python Development Guide**（documentation）：! Docs dev https://img.shields.io/badge/Docs-dev-blue https://microsoft.github.io/autogen/dev/ ! Docs latest release https://img.shields.io/badge/Docs-latest%20release-blue https://microsoft.github.io/autogen/dev/ ! PyPi autogen-core https://img.shields.io/badge/PyPi-autogen--core-blue?logo=pypi https://pypi.org/project/autogen-core/ ! PyPi autogen-agentchat https://img.shields.io/badge/PyPi-autogen--agentchat-blue?logo=pypi https://pypi.org/project/autogen-agentchat/ ! PyPi autogen-ext https://img.shields.io/badge/PyPi-autogen--ext-blue?logo=pypi https://pypi.org/project/autogen-ext/ 证据：`python/README.md` - **NuGet Directory**（documentation）：This directory contains resources and metadata for packaging the AutoGen.NET SDK as a NuGet package. 证据：`dotnet/nuget/README.md` - **AutoGen 0.4 .NET Hello World Sample**（documentation）：AutoGen 0.4 .NET Hello World Sample 证据：`dotnet/samples/Hello/HelloAgent/README.md` - **AutoGen 0.4 .NET Hello World Sample**（documentation）：AutoGen 0.4 .NET Hello World Sample 证据：`dotnet/samples/Hello/HelloAgentState/README.md` - **Multiproject App Host for HelloAgent**（documentation）：Multiproject App Host for HelloAgent 证据：`dotnet/samples/Hello/README.md` - **GitHub Dev Team with AI Agents**（documentation）：Build a Dev Team using event driven agents. This project is an experiment and is not intended to be used in production. 证据：`dotnet/samples/dev-team/README.md` - **TODO**（documentation）：TODO 证据：`dotnet/samples/dev-team/seed-memory/README.md` - **AutoGen.LMStudio**（documentation）：This package provides support for consuming openai-like API from LMStudio local server. 证据：`dotnet/src/AutoGen.LMStudio/README.md` - **AutoGen.SourceGenerator**（documentation）：This package carries a source generator that adds support for type-safe function definition generation. Simply mark a method with Function attribute, and the source generator will generate a function definition and a function call wrapper for you. 证据：`dotnet/src/AutoGen.SourceGenerator/README.md` - **Microsoft.AutoGen**（documentation）：- Getting started sample ../../samples/getting-started/ 证据：`dotnet/src/Microsoft.AutoGen/readme.md` - **How to build and run the website**（documentation）：Prerequisites - dotnet 7.0 or later 证据：`dotnet/website/README.md` - **AutoGenBench**（documentation）：AutoGenBench agbench is a tool for repeatedly running a set of pre-defined AutoGen tasks in a setting with tightly-controlled initial conditions. With each run, AutoGenBench will start from a blank slate. The agents being evaluated will need to work out what code needs to be written, and what libraries or dependencies to install, to solve tasks. The results of each run are logged, and can be ingested by analysis or metrics scripts such as agbench tabulate . By default, all runs are conducted in freshly-initialized docker containers, providing the recommended level of consistency and safety. 证据：`python/packages/agbench/README.md` - **GAIA Benchmark**（documentation）：This scenario implements the GAIA https://arxiv.org/abs/2311.12983 agent benchmark. Before you begin, make sure you have followed instruction in ../README.md to prepare your environment. 证据：`python/packages/agbench/benchmarks/GAIA/README.md` - **HumanEval Benchmark**（documentation）：This scenario implements a modified version of the HumanEval https://arxiv.org/abs/2107.03374 benchmark. Compared to the original benchmark, there are two key differences here: 证据：`python/packages/agbench/benchmarks/HumanEval/README.md` - **Benchmarking Agents**（documentation）：This directory provides ability to benchmarks agents e.g., built using Autogen using AgBench. Use the instructions below to prepare your environment for benchmarking. Once done, proceed to relevant benchmarks directory e.g., benchmarks/GAIA for further scenario-specific instructions. 证据：`python/packages/agbench/benchmarks/README.md` - **AutoGen AgentChat**（documentation）：- Documentation https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html 证据：`python/packages/autogen-agentchat/README.md` - **AutoGen Core**（documentation）：- Documentation https://microsoft.github.io/autogen/stable/user-guide/core-user-guide/index.html 证据：`python/packages/autogen-core/README.md` - **AutoGen Extensions**（documentation）：- Documentation https://microsoft.github.io/autogen/stable/user-guide/extensions-user-guide/index.html 证据：`python/packages/autogen-ext/README.md` - **Task-Centric Memory**（documentation）：Task-Centric Memory EXPERIMENTAL, RESEARCH IN PROGRESS 证据：`python/packages/autogen-ext/src/autogen_ext/experimental/task_centric_memory/README.md` - **MCP Session Host**（documentation）：The McpSessionHost supports MCP Server - MCP Host requests within the AutoGen ecosystem. By design it should require minimal or no changes to your AutoGen agents, simply provide a host to the McpWorkbench . 证据：`python/packages/autogen-ext/src/autogen_ext/tools/mcp/_host/README.md` - **Magentic-One**（documentation）：Magentic-One is now available as part of the autogen-agentchat library. Please see the user guide https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/magentic-one.html for information. 证据：`python/packages/autogen-magentic-one/README.md` - **AutoGen Studio**（documentation）：! PyPI version https://badge.fury.io/py/autogenstudio.svg https://badge.fury.io/py/autogenstudio ! PyPI - Downloads https://img.shields.io/pypi/dm/autogenstudio 证据：`python/packages/autogen-studio/README.md` - **AutoGen Studio frontend**（documentation）：Run the UI in dev mode make changes and see them reflected in the browser with hot reloading : 证据：`python/packages/autogen-studio/frontend/README.md` - **AddComponentDropdown Usage Examples**（documentation）：AddComponentDropdown Usage Examples 证据：`python/packages/autogen-studio/frontend/src/components/shared/README.md` - **test-utils**（documentation）：test-utils 证据：`python/packages/autogen-test-utils/README.md` - **component-schema-gen**（documentation）：This is a tool to generate schema for built in components. 证据：`python/packages/component-schema-gen/README.md` - **magentic-one-cli**（documentation）：magentic-one-cli 证据：`python/packages/magentic-one-cli/README.md` - **pyautogen**（documentation）：NOTE: This is a proxy package for the latest version of autogen-agentchat https://pypi.org/project/autogen-agentchat/ . If you are looking for the 0.2.x version, please pin to pyautogen~=0.2.0 . To migrate from 0.2.x to the latest version, please refer to the migration guide https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/migration-guide.html . Read our previous clarification regarding to forks https://github.com/microsoft/autogen/discussions/4217 . We have regained admin access to this package. 证据：`python/packages/pyautogen/README.md` - **Multi-Agent PostgreSQL Data Management System with AutoGen and Azure PostgreSQL**（documentation）：Multi-Agent PostgreSQL Data Management System with AutoGen and Azure PostgreSQL 证据：`python/samples/agentchat_azure_postgresql/README.md` - **Building a Multi-Agent Application with AutoGen and Chainlit**（documentation）：Building a Multi-Agent Application with AutoGen and Chainlit 证据：`python/samples/agentchat_chainlit/README.md` - **AgentChat Chess Game**（documentation）：This is a simple chess game that you can play with an AI agent. 证据：`python/samples/agentchat_chess_game/README.md` - **AgentChat App with FastAPI**（documentation）：This sample demonstrates how to create a simple chat application using AgentChat https://microsoft.github.io/autogen/stable/user-guide/agentchat-user-guide/index.html and FastAPI https://fastapi.tiangolo.com/ . 证据：`python/samples/agentchat_fastapi/README.md` - **Building an AI Assistant Application with AutoGen and GraphRAG**（documentation）：Building an AI Assistant Application with AutoGen and GraphRAG 证据：`python/samples/agentchat_graphrag/README.md` - **Streamlit AgentChat Sample Application**（documentation）：Streamlit AgentChat Sample Application 证据：`python/samples/agentchat_streamlit/README.md` - **Async Human-in-the-Loop Example**（documentation）：An example showing human-in-the-loop which waits for human input before making the tool call. 证据：`python/samples/core_async_human_in_the_loop/README.md` - **Core ChainLit Integration Sample**（documentation）：In this sample, we will demonstrate how to build simple chat interface that interacts with a Core https://microsoft.github.io/autogen/stable/user-guide/core-user-guide/index.html agent or a team, using Chainlit https://github.com/Chainlit/chainlit , and support streaming messages. 证据：`python/samples/core_chainlit/README.md` - **Chess Game Example**（documentation）：An example with two chess player agents that executes its own tools to demonstrate tool use and reflection on tool use. 证据：`python/samples/core_chess_game/README.md` - **Distributed Group Chat**（documentation）：This example runs a gRPC server using GrpcWorkerAgentRuntimeHost ../../src/autogen core/application/ worker runtime host.py and instantiates three distributed runtimes using GrpcWorkerAgentRuntime ../../src/autogen core/application/ worker runtime.py . These runtimes connect to the gRPC server as hosts and facilitate a round-robin distributed group chat. This example leverages the Azure OpenAI Service https://azure.microsoft.com/en-us/products/ai-services/openai-service to implement writer and editor LLM agents. Agents are instructed to provide concise answers, as the primary goal of this example is to showcase the distributed runtime rather than the quality of agent responses. 证据：`python/samples/core_distributed-group-chat/README.md` - **Multi Agent Orchestration, Distributed Agent Runtime Example**（documentation）：Multi Agent Orchestration, Distributed Agent Runtime Example 证据：`python/samples/core_semantic_router/README.md` - **AutoGen-Core Streaming Chat with Multi-Agent Handoffs via FastAPI**（documentation）：AutoGen-Core Streaming Chat with Multi-Agent Handoffs via FastAPI 证据：`python/samples/core_streaming_handoffs_fastapi/README.md` - **AutoGen-Core Streaming Chat API with FastAPI**（documentation）：AutoGen-Core Streaming Chat API with FastAPI 证据：`python/samples/core_streaming_response_fastapi/README.md` - **Python and dotnet agents interoperability sample**（documentation）：Python and dotnet agents interoperability sample 证据：`python/samples/core_xlang_hello_python_agent/README.md` - **gitty Warning: WIP**（documentation）：This is an AutoGen powered CLI that generates draft replies for issues and pull requests to reduce maintenance overhead for open source projects. 证据：`python/samples/gitty/README.md` - **Task-Centric Memory Code Samples**（documentation）：Task-Centric Memory Code Samples EXPERIMENTAL, RESEARCH IN PROGRESS 证据：`python/samples/task_centric_memory/README.md` - **{{cookiecutter.package name}}**（documentation）：{{cookiecutter.package name}} 证据：`python/templates/new-package/{{cookiecutter.package_name}}/README.md` - **Contributing**（documentation）：The project welcomes contributions from developers and organizations worldwide. Our goal is to foster a collaborative and inclusive community where diverse perspectives and expertise can drive innovation and enhance the project's capabilities. Whether you are an individual contributor or represent an organization, we invite you to join us in shaping the future of this project. Possible contributions include but not limited to: 证据：`CONTRIBUTING.md` - **Contributing to AutoGenBench**（documentation）：As part of the broader AutoGen project, AutoGenBench welcomes community contributions. Contributions are subject to AutoGen's contribution guidelines https://microsoft.github.io/autogen/docs/Contribute , as well as a few additional AutoGenBench-specific requirements outlined here. You may also wish to develop your own private benchmark scenarios and the guidance in this document will help with such efforts as well. Below you will find the general requirements, followed by a detailed technical description. 证据：`python/packages/agbench/CONTRIBUTING.md` - **AutoGen 0.4 .NET Hello World Sample**（documentation）：AutoGen 0.4 .NET Hello World Sample 证据：`dotnet/test/Microsoft.AutoGen.Integration.Tests.AppHosts/HelloAgentTests/README.md` - **Python and dotnet agents interoperability sample**（documentation）：Python and dotnet agents interoperability sample 证据：`dotnet/test/Microsoft.AutoGen.Integration.Tests.AppHosts/core_xlang_hello_python_agent/README.md` - **AutoGen Core**（documentation）：AutoGen Core for .NET follows the same concepts and conventions of its Python counterpart. In fact, in order to understand the concepts in the .NET version, we recommend reading the Python documentation https://microsoft.github.io/autogen/stable/ first. Unless otherwise stated, the concepts in the Python version map to .NET. 证据：`docs/dotnet/core/index.md` - **Installation**（documentation）：The Core and Contracts packages will give you what you need for writing and running agents using the Core API within a single process. 证据：`docs/dotnet/core/installation.md` - **optionally - for distributed agent systems:**（documentation）：AutoGen .NET A .NET framework for building AI agents and applications 证据：`docs/dotnet/index.md` - **AutoGen**（documentation）：.hero-title { font-size: 60px; font-weight: bold; margin: 2rem auto 0; } 证据：`python/docs/src/index.md` - **Examples**（documentation）：A list of examples to help you get started with AgentChat. 证据：`python/docs/src/user-guide/agentchat-user-guide/examples/index.md` - **AgentChat**（documentation）：AgentChat is a high-level API for building multi-agent applications. It is built on top of the autogen-core ../core-user-guide/index.md package. For beginner users, AgentChat is the recommended starting point. For advanced users, autogen-core ../core-user-guide/index.md 's event-driven programming model provides more flexibility and control over the underlying components. 证据：`python/docs/src/user-guide/agentchat-user-guide/index.md` - 其余 20 条证据见 `AI_CONTEXT_PACK.json` 或 `EVIDENCE_INDEX.json`。 ## 宿主 AI 必须遵守的规则 - **把本资产当作开工前上下文，而不是运行环境。**：AI Context Pack 只包含证据化项目理解，不包含目标项目的可执行状态。 证据：`docs/design/readme.md`, `docs/dotnet/README.md`, `python/docs/README.md` - **回答用户时区分可预览内容与必须安装后才能验证的内容。**：安装前体验的消费者价值来自降低误装和误判，而不是伪装成真实运行。 证据：`docs/design/readme.md`, `docs/dotnet/README.md`, `python/docs/README.md` ## 用户开工前应该回答的问题 - 你准备在哪个宿主 AI 或本地环境中使用它？ - 你只是想先体验工作流，还是准备真实安装？ - 你最在意的是安装成本、输出质量、还是和现有规则的冲突？ ## 验收标准 - 所有能力声明都能回指到 evidence_refs 中的文件路径。 - AI_CONTEXT_PACK.md 没有把预览包装成真实运行。 - 用户能在 3 分钟内看懂适合谁、能做什么、如何开始和风险边界。 --- ## Doramagic Context Augmentation 下面内容用于强化 Repomix/AI Context Pack 主体。Human Manual 只提供阅读骨架；踩坑日志会被转成宿主 AI 必须遵守的工作约束。 ## Human Manual 骨架 使用规则：这里只是项目阅读路线和显著性信号，不是事实权威。具体事实仍必须回到 repo evidence / Claim Graph。 宿主 AI 硬性规则： - 不得把页标题、章节顺序、摘要或 importance 当作项目事实证据。 - 解释 Human Manual 骨架时，必须明确说它只是阅读路线/显著性信号。 - 能力、安装、兼容性、运行状态和风险判断必须引用 repo evidence、source path 或 Claim Graph。 - **AutoGen项目简介**：importance `high` - source_paths: README.md, python/README.md, dotnet/README.md, python/packages/autogen-core/README.md, python/packages/autogen-agentchat/README.md - **快速入门指南**：importance `high` - source_paths: python/docs/src/user-guide/agentchat-user-guide/quickstart.ipynb, python/docs/src/user-guide/agentchat-user-guide/tutorial/index.md, python/docs/src/user-guide/agentchat-user-guide/installation.md, python/packages/autogen-agentchat/src/autogen_agentchat/__init__.py, python/packages/autogen-ext/examples/mcp_example_server.py - **分层架构设计**：importance `high` - source_paths: python/packages/autogen-core/src/autogen_core/__init__.py, python/packages/autogen-core/src/autogen_core/_agent_runtime.py, python/packages/autogen-core/src/autogen_core/_single_threaded_agent_runtime.py, python/packages/autogen-agentchat/src/autogen_agentchat/__init__.py, python/packages/autogen-agentchat/src/autogen_agentchat/agents/__init__.py - **运行时模型与消息机制**：importance `high` - source_paths: python/packages/autogen-core/src/autogen_core/_runtime_impl_helpers.py, python/packages/autogen-core/src/autogen_core/_subscription.py, python/packages/autogen-core/src/autogen_core/_type_subscription.py, python/packages/autogen-core/src/autogen_core/_message_context.py, python/packages/autogen-core/src/autogen_core/_default_subscription.py - **分布式运行时**：importance `medium` - source_paths: python/packages/autogen-ext/src/autogen_ext/runtimes/grpc/_worker_runtime.py, python/packages/autogen-ext/src/autogen_ext/runtimes/grpc/_worker_runtime_host.py, python/packages/autogen-ext/src/autogen_ext/runtimes/grpc/protos/agent_worker_pb2_grpc.py, dotnet/src/Microsoft.AutoGen/Core.Grpc/GrpcAgentRuntime.cs, python/samples/core_distributed-group-chat/README.md - **多智能体编排**：importance `high` - source_paths: python/packages/autogen-agentchat/src/autogen_agentchat/base/_team.py, python/packages/autogen-agentchat/src/autogen_agentchat/base/_handoff.py, python/packages/autogen-agentchat/src/autogen_agentchat/tools/_agent.py, python/packages/autogen-agentchat/src/autogen_agentchat/tools/_team.py, python/packages/autogen-core/src/autogen_core/_agent_proxy.py - **群聊模式与选择器**：importance `high` - source_paths: python/packages/autogen-agentchat/src/autogen_agentchat/teams/_group_chat/_round_robin_group_chat.py, python/packages/autogen-agentchat/src/autogen_agentchat/teams/_group_chat/_selector_group_chat.py, python/packages/autogen-agentchat/src/autogen_agentchat/teams/_group_chat/_graph/_digraph_group_chat.py, python/packages/autogen-agentchat/src/autogen_agentchat/teams/_group_chat/_swarm_group_chat.py, python/packages/autogen-agentchat/src/autogen_agentchat/teams/_group_chat/_magentic_one/_magentic_one_group_chat.py - **代码执行器**：importance `high` - source_paths: python/packages/autogen-core/src/autogen_core/code_executor/__init__.py, python/packages/autogen-core/src/autogen_core/code_executor/_base.py, python/packages/autogen-ext/src/autogen_ext/code_executors/azure/_azure_container_code_executor.py, python/packages/autogen-ext/src/autogen_ext/code_executors/docker/_docker_code_executor.py, python/packages/autogen-ext/src/autogen_ext/code_executors/jupyter/_jupyter_code_executor.py ## Repo Inspection Evidence / 源码检查证据 - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `027ecf0a379bcc1d09956d46d12d44a3ad9cee14` - inspected_files: `README.md`, `docs/switcher.json`, `docs/design/03 - Agent Worker Protocol.md`, `docs/design/04 - Agent and Topic ID Specs.md`, `docs/design/02 - Topics.md`, `docs/design/05 - Services.md`, `docs/design/01 - Programming Model.md`, `docs/design/readme.md`, `docs/dotnet/index.md`, `docs/dotnet/docfx.json`, `docs/dotnet/toc.yml`, `docs/dotnet/README.md`, `docs/dotnet/core/differences-from-python.md`, `docs/dotnet/core/index.md`, `docs/dotnet/core/protobuf-message-types.md`, `docs/dotnet/core/installation.md`, `docs/dotnet/core/toc.yml`, `docs/dotnet/core/tutorial.md`, `docs/dotnet/template/public/main.js` 宿主 AI 硬性规则： - 没有 repo_clone_verified=true 时，不得声称已经读过源码。 - 没有 repo_inspection_verified=true 时，不得把 README/docs/package 文件判断写成事实。 - 没有 quick_start_verified=true 时，不得声称 Quick Start 已跑通。 ## Doramagic Pitfall Constraints / 踩坑约束 这些规则来自 Doramagic 发现、验证或编译过程中的项目专属坑点。宿主 AI 必须把它们当作工作约束，而不是普通说明文字。 ### Constraint 1: 来源证据：Multi-agent systems need a 'mission keeper' role — not a Boss Agent, but a dedicated goal integrity node - Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：Multi-agent systems need a 'mission keeper' role — not a Boss Agent, but a dedicated goal integrity node - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | cevd_850c646256974bf887dcfebeae9a7286 | https://github.com/microsoft/autogen/issues/7487 | 来源讨论提到 node 相关条件，需在安装/试用前复核。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 2: 来源证据：[Feature] FunASR as self-hosted speech-to-text tool for voice agents - Trigger: GitHub 社区证据显示该项目存在一个安装相关的待验证问题：[Feature] FunASR as self-hosted speech-to-text tool for voice agents - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | cevd_0583aa188952475b905a04658c2a82e8 | https://github.com/microsoft/autogen/issues/7742 | 来源讨论提到 python 相关条件，需在安装/试用前复核。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 3: 来源证据：RFC: Cross-agent shared memory store with on-demand capsule recall (agent/group/global scopes) - Trigger: GitHub 社区证据显示该项目存在一个配置相关的待验证问题：RFC: Cross-agent shared memory store with on-demand capsule recall (agent/group/global scopes) - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | cevd_cf0842636cfd495e8993e39e969d192b | https://github.com/microsoft/autogen/issues/7748 | 来源类型 github_issue 暴露的待验证使用条件。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 4: 失败模式：security_permissions: Discussion: standardising the agent-task marketplace surface — draft AIP-1 spec - Trigger: Developers should check this security_permissions risk before relying on the project: Discussion: standardising the agent-task marketplace surface — draft AIP-1 spec - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: Discussion: standardising the agent-task marketplace surface — draft AIP-1 spec. Context: Observed when using node - Why it matters: Developers may expose sensitive permissions or credentials: Discussion: standardising the agent-task marketplace surface — draft AIP-1 spec - Evidence: failure_mode_cluster:github_issue | fmev_9e6caea1ca7b69ebf5b4767ec0ee2b9b | https://github.com/microsoft/autogen/issues/7724 | Discussion: standardising the agent-task marketplace surface — draft AIP-1 spec - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 5: 失败模式：security_permissions: [Feature Request] Memory Poisoning Protection for AutoGen Agents via OWASP Agent Memory Guard - Trigger: Developers should check this security_permissions risk before relying on the project: [Feature Request] Memory Poisoning Protection for AutoGen Agents via OWASP Agent Memory Guard - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: [Feature Request] Memory Poisoning Protection for AutoGen Agents via OWASP Agent Memory Guard. Context: Observed when using python - Why it matters: Developers may expose sensitive permissions or credentials: [Feature Request] Memory Poisoning Protection for AutoGen Agents via OWASP Agent Memory Guard - Evidence: failure_mode_cluster:github_issue | fmev_2f20b0c2046b47a5b5c05f1437c92ff3 | https://github.com/microsoft/autogen/issues/7783 | [Feature Request] Memory Poisoning Protection for AutoGen Agents via OWASP Agent Memory Guard - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 6: 来源证据：Discussion: standardising the agent-task marketplace surface — draft AIP-1 spec - Trigger: GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：Discussion: standardising the agent-task marketplace surface — draft AIP-1 spec - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能影响授权、密钥配置或安全边界。 - Evidence: community_evidence:github | cevd_9ac9d80f24ec4c59bc8f142b0e8882a5 | https://github.com/microsoft/autogen/issues/7724 | 来源讨论提到 node 相关条件，需在安装/试用前复核。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 7: 来源证据：Feature proposal: Backpressure contract declarations for multi-agent coordination - Trigger: GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：Feature proposal: Backpressure contract declarations for multi-agent coordination - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能影响授权、密钥配置或安全边界。 - Evidence: community_evidence:github | cevd_e6095aa394984c59b3dbc72bb1022927 | https://github.com/microsoft/autogen/issues/7321 | 来源讨论提到 python 相关条件，需在安装/试用前复核。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 8: 来源证据：Payment primitive for multi-agent systems - how are teams handling this? - Trigger: GitHub 社区证据显示该项目存在一个安全/权限相关的待验证问题：Payment primitive for multi-agent systems - how are teams handling this? - Host AI rule: 来源问题仍为 open，Pack Agent 需要复核是否仍影响当前版本。 - Why it matters: 可能影响授权、密钥配置或安全边界。 - Evidence: community_evidence:github | cevd_35f60f0f1011435394f5e2583cd804a6 | https://github.com/microsoft/autogen/issues/7492 | 来源类型 github_issue 暴露的待验证使用条件。 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 9: 失败模式：installation: [Feature] FunASR as self-hosted speech-to-text tool for voice agents - Trigger: Developers should check this installation risk before relying on the project: [Feature] FunASR as self-hosted speech-to-text tool for voice agents - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: [Feature] FunASR as self-hosted speech-to-text tool for voice agents. Context: Observed when using python, cuda - Why it matters: Developers may fail before the first successful local run: [Feature] FunASR as self-hosted speech-to-text tool for voice agents - Evidence: failure_mode_cluster:github_issue | fmev_eb4ef4bf1d7dc63fc84e0d3693c929f8 | https://github.com/microsoft/autogen/issues/7742 | [Feature] FunASR as self-hosted speech-to-text tool for voice agents - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。 ### Constraint 10: 失败模式：installation: python-v0.6.2 - Trigger: Developers should check this installation risk before relying on the project: python-v0.6.2 - Host AI rule: Before packaging this project, run the relevant install/config/quickstart check for: python-v0.6.2. Context: Observed when using python, docker - Why it matters: Upgrade or migration may change expected behavior: python-v0.6.2 - Evidence: failure_mode_cluster:github_release | fmev_0a7e034c78e6a265885801941e670b18 | https://github.com/microsoft/autogen/releases/tag/python-v0.6.2 | python-v0.6.2 - Hard boundary: 不要把这个坑点包装成已解决、已验证或可忽略，除非后续验证证据明确证明它已经关闭。