# solace-agent-mesh - 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 solace-agent-mesh 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`, `docs/docs/documentation/enterprise/quickstart-kubernetes.md` Claim：`clm_0001` supported 0.86 ## 怎么开始 - `pip install -e .[test]` 证据：`README.md` Claim：`clm_0003` supported 0.86 - `curl -s http://localhost:8000/health` 证据：`docs/docs/documentation/enterprise/quickstart-kubernetes.md` Claim：`clm_0004` unverified 0.25 - `curl -s http://localhost:8080/api/v1/platform/health` 证据：`docs/docs/documentation/enterprise/quickstart-kubernetes.md` Claim：`clm_0005` unverified 0.25 ## 继续前判断卡 - **当前建议**：先做角色匹配试用 - **为什么**：这个项目更像角色库，核心风险是选错角色或把角色文案当执行能力；先用 Prompt Preview 试角色匹配，再决定是否沙盒导入。 ### 30 秒判断 - **现在怎么做**：先做角色匹配试用 - **最小安全下一步**：先用 Prompt Preview 试角色匹配；满意后再隔离导入 - **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`, `docs/docs/documentation/enterprise/quickstart-kubernetes.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`, `docs/docs/documentation/enterprise/quickstart-kubernetes.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`, `docs/docs/documentation/enterprise/quickstart-kubernetes.md` - **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。） - **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。 - **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_0006` 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`, `docs/docs/documentation/enterprise/quickstart-kubernetes.md` Claim：`clm_0007` 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`, `docs/docs/documentation/enterprise/quickstart-kubernetes.md` Claim：`clm_0001` supported 0.86 ### 上下文规模 - 文件总数：1602 - 重要文件覆盖：40/1602 - 证据索引条目：80 - 角色 / Skill 条目：76 ### 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 solace-agent-mesh 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 solace-agent-mesh 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 solace-agent-mesh 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 76 个角色 / Skill / 项目文档条目。 - **Solace Agent Mesh Documentation**（project_doc）：To run Solace Agent Mesh locally, follow these steps: 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/README.md` - **Key Functions**（project_doc）：Agents are specialized processing units within the Agent Mesh framework that are built around the Google Agent Development Kit ADK and provide the core intelligence layer. They: 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/docs/documentation/components/agents.md` - **🔑 Key Features**（project_doc）：Solace Agent Mesh Open-source framework for building event driven multi-agent AI systems Star ⭐️ this repo to stay updated as we ship new features and improvements. 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` - **Solace Agent Mesh - Evaluation Framework**（project_doc）：Solace Agent Mesh - Evaluation Framework 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：`evaluation/README.md` - **SAM REST API Client**（project_doc）：A Python client library for interacting with Solace Agent Mesh SAM REST API Gateway. 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：`client/sam-rest-client/README.md` - **Frontend Development Guidelines**（project_doc）：React 19, TanStack Query v5, Tailwind v4, Radix UI, Vitest, Playwright 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：`client/webui/frontend/.claude/CLAUDE.md` - **Frontend Web UI**（project_doc）：Frontend interface for Solace Agent Mesh SAM platform. This React application provides a modern chat interface for interacting with AI agents and visualizing agent communication flows. 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：`client/webui/frontend/README.md` - **Cypress Testing for Solace Agent Mesh Community**（project_doc）：Cypress Testing for Solace Agent Mesh Community 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：`client/webui/frontend/cypress/README.md` - **How to contribute**（project_doc）：We'd love for you to contribute and welcome your help. Here are some guidelines to follow: 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` - **API Endpoint Pattern**（project_doc）：Every API resource lives in its own folder under src/lib/api/ / with four files: 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：`client/webui/frontend/.claude/docs/api-endpoints.md` - **Feature Flags**（project_doc）：Feature flags are defined in YAML and served to the frontend via /api/v1/config/features . The frontend uses OpenFeature SDK with a custom SamFeatureProvider . 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：`client/webui/frontend/.claude/docs/feature-flags.md` - **Artifact Management Tools**（project_doc）：This guide details how agents utilize built-in tools to manage file artifacts and their associated metadata. The system employs an explicit, metadata-aware methodology wherein the agent maintains full control over the lifecycle of artifacts, including their creation, listing, loading, and return. 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/docs/documentation/components/builtin-tools/artifact-management.md` - **Using Text-to-Speech TTS Tools**（project_doc）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 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/docs/documentation/components/builtin-tools/audio-tools.md` - **Configuring Built-in Tools**（project_doc）：import NetworkAccessRequiredSomeFeatures from '@site/docs/partials/network-access-required-some-features.mdx'; 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/docs/documentation/components/builtin-tools/builtin-tools.md` - **Data Analysis Tools**（project_doc）：Agent Mesh includes a suite of optional built-in tools that enable agents to perform data analysis tasks directly on artifacts. These tools provide functionality for SQL querying, JQ transformations, and Plotly chart generation. 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/docs/documentation/components/builtin-tools/data-analysis-tools.md` - **Dynamic Embeds**（project_doc）：Dynamic embeds provide a mechanism for agents to insert context-dependent information into their text responses or tool parameters using a specialized «...» syntax. This feature allows for the dynamic retrieval and formatting of data without requiring explicit tool calls for simple data retrieval or calculations. 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/docs/documentation/components/builtin-tools/embeds.md` - **Image Tools**（project_doc）：import NetworkAccessRequiredSomeFeatures from '@site/docs/partials/network-access-required-some-features.mdx'; 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/docs/documentation/components/builtin-tools/image-tools.md` - **Research Tools**（project_doc）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 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/docs/documentation/components/builtin-tools/research-tools.md` - **Agent Mesh CLI**（project_doc）：Agent Mesh comes with a comprehensive CLI tool that you can use to create, and run an instance of Agent Mesh, which is referred to as an Agent Mesh application. Agent Mesh CLI also allows you to add agents and gateways, manage plugins, help you debug, and much more. 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/docs/documentation/components/cli.md` - **Agents**（project_doc）：Agent Mesh provides a comprehensive set of components that work together to create a distributed AI agent ecosystem. Each component serves a specific purpose, from managing the command-line interface to orchestrating complex multi-agent workflows. 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/docs/documentation/components/components.md` - **Gateways**（project_doc）：import NetworkAccessRequiredSomeFeatures from '@site/docs/partials/network-access-required-some-features.mdx'; 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/docs/documentation/components/gateways.md` - **Orchestrator**（project_doc）：The A2A Agent-to-Agent protocol is the communication backbone of Agent Mesh that enables distributed agent coordination and workflow management. Unlike traditional centralized orchestration, the A2A protocol enables agents to discover each other, delegate tasks, and collaborate directly through standardized message patterns. 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/docs/documentation/components/orchestrator.md` - **Platform Service**（project_doc）：The Platform Service is a backend microservice responsible for management operations in Solace Agent Mesh. It operates independently from other components, allowing it to scale separately. 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/docs/documentation/components/platform-service.md` - **Official Core Plugins**（project_doc）：import NetworkAccessRequiredSomeFeatures from '@site/docs/partials/network-access-required-some-features.mdx'; 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/docs/documentation/components/plugins.md` - **Projects**（project_doc）：Projects are a powerful organizational feature in Agent Mesh that enable users to group related chat sessions, manage artifacts and maintain context across multiple conversations. They provide a workspace-like environment for managing AI interactions around specific topics, tasks, or domains. 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/docs/documentation/components/projects.md` - **Prompt Library**（project_doc）：:::warning Experimental Feature The Prompt Library is currently an experimental feature. While functional, the configuration options and API may change in future releases. ::: 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/docs/documentation/components/prompts.md` - **Proxies**（project_doc）：Proxies act as protocol bridges that connect Agent Mesh to external A2A agents. By translating between A2A over Solace event mesh and A2A over HTTPS protocols, proxies enable agents within the mesh to delegate tasks to external agents and include them in collaborative workflows. 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/docs/documentation/components/proxies.md` - **Speech Integration**（project_doc）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 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/docs/documentation/components/speech.md` - **Workflows**（project_doc）：Workflows :::warning Experimental Feature Workflows is currently an experimental feature. Expect this feature to change and improve in future releases. ::: 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/docs/documentation/components/workflows.md` - **Diagnosing and Resolving Problems**（project_doc）：Effective debugging in Agent Mesh requires a systematic approach that leverages the platform's distributed architecture. Because your system consists of multiple agents communicating through a Solace event broker, issues can arise at various levels—from individual agent logic to inter-component communication patterns. 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/docs/documentation/deploying/debugging.md` - **Deploying Agent Mesh**（project_doc）：Moving your Agent Mesh from development to production requires careful consideration of deployment strategies, monitoring capabilities, and troubleshooting approaches. Understanding your options and having robust observability tools ensures your agent mesh operates reliably at scale. 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/docs/documentation/deploying/deploying.md` - **Choosing Deployment Options**（project_doc）：Agent Mesh offers flexible deployment options designed to meet different operational requirements. Understanding these options helps you choose the right approach for your specific environment and scale needs. 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/docs/documentation/deploying/deployment-options.md` - **Health Checks**（project_doc）：Health checks enable orchestration platforms like Kubernetes to monitor the operational status of your Agent Mesh components. By exposing standardized health endpoints, your agents, gateways, and platform services can signal when they're ready to receive traffic, allowing for graceful deployments, automatic recovery from failures, and intelligent load balancing. 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/docs/documentation/deploying/health-checks.md` - **Logging**（project_doc）：This guide covers the essential information you need to effectively configure and manage logging in your Agent Mesh applications. Proper logging configuration is critical for troubleshooting issues, monitoring system behavior, and maintaining reliable production deployments. 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/docs/documentation/deploying/logging.md` - **Monitoring Your Agent Mesh**（project_doc）：Understanding how your Agent Mesh system operates in real-time is crucial for maintaining optimal performance and quickly identifying issues. The platform provides a comprehensive observability suite that gives you deep insights into system behavior, message flows, and agent interactions. 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/docs/documentation/deploying/observability.md` - **Proxy Configuration**（project_doc）：When deploying Agent Mesh in environments with restricted network access, you may need to configure proxy settings to enable communication with external services. This guide explains how to configure HTTPS proxy settings for Agent Mesh. 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/docs/documentation/deploying/proxy_configuration.md` - **Understanding the Architecture**（project_doc）：:::tip For a more comprehensive tutorial example, see the Build Your Own Agent tutorials/custom-agent.md guide. This page walks through the fundamental concepts for creating agents in Agent Mesh. ::: 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/docs/documentation/developing/create-agents.md` - **Creating Custom Gateways**（project_doc）：import NetworkAccessMayBeRequired from '@site/docs/partials/network-access-may-be-required.mdx'; 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/docs/documentation/developing/create-gateways.md` - **Creating Python Tools**（project_doc）：Agent Mesh provides a powerful and unified system for creating custom agent tools using Python. This is the primary way to extend an agent's capabilities with your own business logic, integrate with proprietary APIs, or perform specialized data processing. 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/docs/documentation/developing/creating-python-tools.md` - **Creating Service Providers**（project_doc）：This guide details the process for developers to create service provider plugins for integrating backend systems for example, HR platforms, CRMs with Agent Mesh. 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/docs/documentation/developing/creating-service-providers.md` - **Creating Workflows**（project_doc）：:::warning Experimental Feature Workflows is currently an experimental feature. Expect this feature to change and improve in future releases. ::: 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/docs/documentation/developing/creating-workflows.md` - **Developing with Agent Mesh**（project_doc）：Agent Mesh provides a framework for creating distributed AI applications using an event-driven architecture. You can build agents that communicate through the A2A Agent-to-Agent protocol, extend them with custom tools, integrate external systems through gateways, and create reusable components as plugins. 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/docs/documentation/developing/developing.md` - **Evaluating Agents**（project_doc）：The framework includes an evaluation system that helps you test your agents' behavior in a structured way. You can define test suites, run them against your agents, and generate detailed reports to analyze the results. When running evaluations locally, you can also benchmark different language models to see how they affect your agents' responses. 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/docs/documentation/developing/evaluations.md` - **Project Structure**（project_doc）：Agent Mesh is built on the A2A Agent-to-Agent protocol architecture, powered by Solace AI Connector https://github.com/SolaceLabs/solace-ai-connector , and uses the Solace event broker as the communication backbone. The framework is controlled by YAML configuration files that define agents, gateways, and plugins, enabling distributed AI agent communication through event-driven messaging. 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/docs/documentation/developing/structure.md` - **Amazon Bedrock Agents Integration**（project_doc）：This tutorial walks you through the process of integrating Amazon Bedrock Agents and Flows into Agent Mesh. This integration allows you to create agents that can interact with one or multiple Bedrock Agents or Flows, extending your Agent Mesh project with powerful AI capabilities from AWS. 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/docs/documentation/developing/tutorials/bedrock-agents.md` - **Building Custom Agent Images**（project_doc）：This tutorial walks you through packaging a custom agent plugin into a Docker/OCI image suitable for Kubernetes deployment. By the end you will have a container image that extends the SAM Enterprise base image with your own Python tool, ready to deploy with Helm. For the deployment step, see Agent and Workflow Deployment https://solaceproducts.github.io/solace-agent-mesh-helm-quickstart/docs/standalone-agent-deploym… 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/docs/documentation/developing/tutorials/building-custom-agent-images.md` - **Build Your Own Agent**（project_doc）：This tutorial shows you how to build a sophisticated weather agent using the Agent Mesh framework. Learn how to integrate with external APIs, manage resources properly, and create production-ready 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/docs/documentation/developing/tutorials/custom-agent.md` - **Event Mesh Gateway**（project_doc）：If you already have an event mesh https://solace.com/what-is-an-event-mesh/ in place, you can integrate Agent Mesh into it. This allows you to leverage existing infrastructure while introducing intelligence and automation through Agent Mesh. 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/docs/documentation/developing/tutorials/event-mesh-gateway.md` - **MCP Gateway**（project_doc）：This tutorial walks you through setting up the MCP Gateway, which exposes Solace Agent Mesh agents as a Model Context Protocol MCP server. This allows MCP-compatible client such as Claude Desktop, MCP Inspector, or custom applications to interact with Solace Agent Mesh agents through a standardized interface. 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/docs/documentation/developing/tutorials/mcp-gateway.md` - **MCP Integration**（project_doc）：This tutorial walks you through the process of integrating a Model Context Protocol MCP Server into Agent Mesh. 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/docs/documentation/developing/tutorials/mcp-integration.md` - **MongoDB Integration**（project_doc）：This tutorial sets up a MongoDB agent in Agent Mesh, which allows the Agent Mesh agent to answer natural language queries about a Mongo database. The agent translates user questions into MongoDB aggregation pipelines and executes them against your database. 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/docs/documentation/developing/tutorials/mongodb-integration.md` - **RAG Integration**（project_doc）：This tutorial guides you through setting up and configuring Agent Mesh Retrieval Augmented Generation RAG plugin. The RAG plugin enables your agents to answer questions by retrieving information from a knowledge base of your documents. 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/docs/documentation/developing/tutorials/rag-integration.md` - **Key Features**（project_doc）：Agent Mesh REST API Gateway provides a standard, robust, and secure HTTP-based entry point for programmatic and system-to-system integrations. It allows external clients to submit tasks to Agent Mesh agents, manage files, and discover agent capabilities using a familiar RESTful interface. 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/docs/documentation/developing/tutorials/rest-gateway.md` - **Slack Integration**（project_doc）：This tutorial integrates a Slack interface into Agent Mesh, enabling interaction with the system directly from your Slack workspace and channels. 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/docs/documentation/developing/tutorials/slack-integration.md` - **SQL Database Integration**（project_doc）：This tutorial sets up a SQL database agent in Agent Mesh, which allows the Agent Mesh agent to answer natural language queries about a sample coffee company database. This tutorial provides some sample data to set up an SQLite database, but you can use the same approach to connect to other database types, such as MySQL or 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：`docs/docs/documentation/developing/tutorials/sql-database.md` - **Microsoft Teams Gateway Setup — Manual Configuration Docker & Wheel**（project_doc）：Microsoft Teams Gateway Setup — Manual Configuration Docker & Wheel 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/docs/documentation/developing/tutorials/teams-integration.md` - **Agent Builder**（project_doc）：Agent Builder provides a visual, form-based interface for creating and managing agents without writing configuration files. This tool offers optional AI assistance that suggests initial configuration values based on a description of the agent you want to build. 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/docs/documentation/enterprise/agent-builder.md` - **Air-Gapped Kubernetes Installation**（project_doc）：This guide covers deploying Solace Agent Mesh Enterprise to Kubernetes clusters in air-gapped environments using Helm charts. Some features require network access to external services. Ensure the necessary routes and firewall rules are in place for any external endpoints your deployment uses LLM, OIDC, Slack, and so on . 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/docs/documentation/enterprise/airgap-kubernetes.md` - **Authentication Proxy**（project_doc）：Gateway OAuth enables apps and gateways like MCP to authenticate via the OAuth2 service without registering separate redirect URIs with OAuth providers. Apps redirect directly to the auth server, which handles the OAuth flow and returns a gateway code that can be exchanged for tokens. 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/docs/documentation/enterprise/auth-proxy.md` - **Connect External Agents**（project_doc）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 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/docs/documentation/enterprise/connect-external-agents.md` - **Connectors**（project_doc）：import NetworkAccessRequiredSomeFeatures from '@site/docs/partials/network-access-required-some-features.mdx'; 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/docs/documentation/enterprise/connectors/connectors.md` - **Overview**（project_doc）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 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/docs/documentation/enterprise/connectors/knowledgebase-connectors.md` - **Overview**（project_doc）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 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/docs/documentation/enterprise/connectors/mcp-connectors.md` - **Overview**（project_doc）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 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/docs/documentation/enterprise/connectors/openapi-connectors.md` - **Overview**（project_doc）：SQL connectors allow agents to query and analyze database information using natural language. 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/docs/documentation/enterprise/connectors/sql-connectors.md` - **Prerequisites**（project_doc）：This guide walks you through installing and running Agent Mesh Enterprise using Docker. You will download the enterprise image, load it into Docker, and launch a container configured for either development or production 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：`docs/docs/documentation/enterprise/docker-installation.md` - **Agent Mesh Enterprise**（project_doc）：Agent Mesh Enterprise extends the open-source framework with features that enterprise environments require. It is available as a self-managed container image that you can deploy in your own infrastructure. You can obtain access by joining the pilot program at solace.com/solace-agent-mesh-pilot-registration https://solace.com/solace-agent-mesh-pilot-registration/ . 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/docs/documentation/enterprise/enterprise.md` - **Event Mesh Gateway**（project_doc）：Event Mesh gateways enable Agent Mesh to consume events from Solace Event Mesh brokers and route them to agents. This gateway type triggers agent workflows in response to business events in real time. 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/docs/documentation/enterprise/gateways/event-mesh-gateway.md` - **Gateways**（project_doc）：import NetworkAccessRequiredSomeFeatures from '@site/docs/partials/network-access-required-some-features.mdx'; 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/docs/documentation/enterprise/gateways/gateways.md` - **Microsoft Teams Gateway Setup — Web Interface SAM Cloud & SAM Kubernetes**（project_doc）：Microsoft Teams Gateway Setup — Web Interface SAM Cloud & SAM Kubernetes 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/docs/documentation/enterprise/gateways/teams-gateway.md` - **Migration to Chart 1.500.0**（project_doc）：This guide covers breaking changes when upgrading from a prior Helm chart version to 1.500.0. 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：`docs/docs/documentation/enterprise/migration-v2.md` - **Offline Evaluations**（project_doc）：:::warning Experimental Feature This feature is under active development. Configuration schemas and behavior may change in future releases. Do not use in production without validating against the current release notes. ::: 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/docs/documentation/enterprise/offline-evaluations.md` - **Overview**（project_doc）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 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/docs/documentation/enterprise/openapi-tools.md` - **Metric Families Reference**（project_doc）：:::info Enterprise Only This feature is available in the Enterprise Edition only. ::: 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/docs/documentation/enterprise/otel-metrics/configuration.md` - **Key Concepts**（project_doc）：:::info Enterprise Only This feature is available in the Enterprise Edition only. ::: 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/docs/documentation/enterprise/otel-metrics/getting-started.md` - **Integration Patterns**（project_doc）：:::info Enterprise Only This feature is available in the Enterprise Edition only. ::: 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/docs/documentation/enterprise/otel-metrics/integration.md` ## 证据索引 - 共索引 80 条证据。 - **Solace Agent Mesh Documentation**（documentation）：To run Solace Agent Mesh locally, follow these steps: 证据：`docs/README.md` - **Key Functions**（documentation）：Agents are specialized processing units within the Agent Mesh framework that are built around the Google Agent Development Kit ADK and provide the core intelligence layer. They: 证据：`docs/docs/documentation/components/agents.md` - **🔑 Key Features**（documentation）：Solace Agent Mesh Open-source framework for building event driven multi-agent AI systems Star ⭐️ this repo to stay updated as we ship new features and improvements. 证据：`README.md` - **Solace Agent Mesh - Evaluation Framework**（documentation）：Solace Agent Mesh - Evaluation Framework 证据：`evaluation/README.md` - **SAM REST API Client**（documentation）：A Python client library for interacting with Solace Agent Mesh SAM REST API Gateway. 证据：`client/sam-rest-client/README.md` - **Frontend Development Guidelines**（documentation）：React 19, TanStack Query v5, Tailwind v4, Radix UI, Vitest, Playwright 证据：`client/webui/frontend/.claude/CLAUDE.md` - **Frontend Web UI**（documentation）：Frontend interface for Solace Agent Mesh SAM platform. This React application provides a modern chat interface for interacting with AI agents and visualizing agent communication flows. 证据：`client/webui/frontend/README.md` - **Cypress Testing for Solace Agent Mesh Community**（documentation）：Cypress Testing for Solace Agent Mesh Community 证据：`client/webui/frontend/cypress/README.md` - **Package**（package_manifest）：{ "name": "solace-agenitc-mesh-docs", "version": "0.0.0", "private": true, "scripts": { "docusaurus": "docusaurus", "start": "docusaurus start", "build": "docusaurus build", "swizzle": "docusaurus swizzle", "deploy": "docusaurus deploy", "clear": "docusaurus clear", "serve": "docusaurus serve", "write-translations": "docusaurus write-translations", "write-heading-ids": "docusaurus write-heading-ids", "typecheck": "tsc" }, "dependencies": { "@docusaurus/core": "^3.9.2", "@docusaurus/preset-classic": "^3.9.2", "@docusaurus/theme-mermaid": "^3.9.2", "@mdx-js/react": "^3.0.0", "clsx": "^2.0.0", "docusaurus-lunr-search": "^3.6.0", "prism-react-renderer": "^2.3.0", "react": "^19.2.3", "react-dom"… 证据：`docs/package.json` - **How to contribute**（documentation）：We'd love for you to contribute and welcome your help. Here are some guidelines to follow: 证据：`CONTRIBUTING.md` - **Package**（package_manifest）：{ "name": "@SolaceLabs/solace-agent-mesh-ui", "version": "2.13.2", "description": "Solace Agent Mesh UI components - React library for building agent communication interfaces", "author": "SolaceLabs ", "license": "Apache-2.0", "repository": { "type": "git", "url": "https://github.com/SolaceLabs/solace-agent-mesh", "directory": "client/webui/frontend" }, "homepage": "https://github.com/SolaceLabs/solace-agent-mesh/tree/main/client/webui/frontend", "bugs": { "url": "https://github.com/SolaceLabs/solace-agent-mesh/issues" }, "keywords": "solace", "agent-mesh", "ai", "react", "ui-components", "chat", "agents" , "type": "module", "main": "./dist/index.js", "module": "./dist/index.js", "types": "… 证据：`client/webui/frontend/package.json` - **Package**（package_manifest）：{ "name": "solace-agent-mesh-config-portal-frontend", "private": true, "sideEffects": false, "type": "module", "scripts": { "build": "remix vite:build", "dev": "remix vite:dev", "lint": "eslint --ignore-path .gitignore --cache --cache-location ./node modules/.cache/eslint .", "preview": "vite preview", "typecheck": "tsc" }, "dependencies": { "@remix-run/node": "2.17.5", "@remix-run/react": "2.17.5", "isbot": "^4", "lucide-react": "^0.542.0", "react": "^18.2.0", "react-dom": "^18.2.0", "react-markdown": "^10.1.0" }, "devDependencies": { "@remix-run/dev": "2.17.5", "@types/react": "^18.2.20", "@types/react-dom": "^18.2.7", "@typescript-eslint/eslint-plugin": "^6.7.4", "@typescript-eslint/pars… 证据：`config_portal/frontend/package.json` - **License**（source_file）：Apache License Version 2.0, January 2004 http://www.apache.org/licenses/ 证据：`LICENSE` - **API Endpoint Pattern**（documentation）：Every API resource lives in its own folder under src/lib/api/ / with four files: 证据：`client/webui/frontend/.claude/docs/api-endpoints.md` - **Feature Flags**（documentation）：Feature flags are defined in YAML and served to the frontend via /api/v1/config/features . The frontend uses OpenFeature SDK with a custom SamFeatureProvider . 证据：`client/webui/frontend/.claude/docs/feature-flags.md` - **Artifact Management Tools**（documentation）：This guide details how agents utilize built-in tools to manage file artifacts and their associated metadata. The system employs an explicit, metadata-aware methodology wherein the agent maintains full control over the lifecycle of artifacts, including their creation, listing, loading, and return. 证据：`docs/docs/documentation/components/builtin-tools/artifact-management.md` - **Using Text-to-Speech TTS Tools**（documentation）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 证据：`docs/docs/documentation/components/builtin-tools/audio-tools.md` - **Configuring Built-in Tools**（documentation）：import NetworkAccessRequiredSomeFeatures from '@site/docs/partials/network-access-required-some-features.mdx'; 证据：`docs/docs/documentation/components/builtin-tools/builtin-tools.md` - **Data Analysis Tools**（documentation）：Agent Mesh includes a suite of optional built-in tools that enable agents to perform data analysis tasks directly on artifacts. These tools provide functionality for SQL querying, JQ transformations, and Plotly chart generation. 证据：`docs/docs/documentation/components/builtin-tools/data-analysis-tools.md` - **Dynamic Embeds**（documentation）：Dynamic embeds provide a mechanism for agents to insert context-dependent information into their text responses or tool parameters using a specialized «...» syntax. This feature allows for the dynamic retrieval and formatting of data without requiring explicit tool calls for simple data retrieval or calculations. 证据：`docs/docs/documentation/components/builtin-tools/embeds.md` - **Image Tools**（documentation）：import NetworkAccessRequiredSomeFeatures from '@site/docs/partials/network-access-required-some-features.mdx'; 证据：`docs/docs/documentation/components/builtin-tools/image-tools.md` - **Research Tools**（documentation）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 证据：`docs/docs/documentation/components/builtin-tools/research-tools.md` - **Agent Mesh CLI**（documentation）：Agent Mesh comes with a comprehensive CLI tool that you can use to create, and run an instance of Agent Mesh, which is referred to as an Agent Mesh application. Agent Mesh CLI also allows you to add agents and gateways, manage plugins, help you debug, and much more. 证据：`docs/docs/documentation/components/cli.md` - **Agents**（documentation）：Agent Mesh provides a comprehensive set of components that work together to create a distributed AI agent ecosystem. Each component serves a specific purpose, from managing the command-line interface to orchestrating complex multi-agent workflows. 证据：`docs/docs/documentation/components/components.md` - **Gateways**（documentation）：import NetworkAccessRequiredSomeFeatures from '@site/docs/partials/network-access-required-some-features.mdx'; 证据：`docs/docs/documentation/components/gateways.md` - **Orchestrator**（documentation）：The A2A Agent-to-Agent protocol is the communication backbone of Agent Mesh that enables distributed agent coordination and workflow management. Unlike traditional centralized orchestration, the A2A protocol enables agents to discover each other, delegate tasks, and collaborate directly through standardized message patterns. 证据：`docs/docs/documentation/components/orchestrator.md` - **Platform Service**（documentation）：The Platform Service is a backend microservice responsible for management operations in Solace Agent Mesh. It operates independently from other components, allowing it to scale separately. 证据：`docs/docs/documentation/components/platform-service.md` - **Official Core Plugins**（documentation）：import NetworkAccessRequiredSomeFeatures from '@site/docs/partials/network-access-required-some-features.mdx'; 证据：`docs/docs/documentation/components/plugins.md` - **Projects**（documentation）：Projects are a powerful organizational feature in Agent Mesh that enable users to group related chat sessions, manage artifacts and maintain context across multiple conversations. They provide a workspace-like environment for managing AI interactions around specific topics, tasks, or domains. 证据：`docs/docs/documentation/components/projects.md` - **Prompt Library**（documentation）：:::warning Experimental Feature The Prompt Library is currently an experimental feature. While functional, the configuration options and API may change in future releases. ::: 证据：`docs/docs/documentation/components/prompts.md` - **Proxies**（documentation）：Proxies act as protocol bridges that connect Agent Mesh to external A2A agents. By translating between A2A over Solace event mesh and A2A over HTTPS protocols, proxies enable agents within the mesh to delegate tasks to external agents and include them in collaborative workflows. 证据：`docs/docs/documentation/components/proxies.md` - **Speech Integration**（documentation）：import NetworkAccessRequiredSingleFeature from '@site/docs/partials/network-access-required.mdx'; 证据：`docs/docs/documentation/components/speech.md` - **Workflows**（documentation）：Workflows :::warning Experimental Feature Workflows is currently an experimental feature. Expect this feature to change and improve in future releases. ::: 证据：`docs/docs/documentation/components/workflows.md` - **Diagnosing and Resolving Problems**（documentation）：Effective debugging in Agent Mesh requires a systematic approach that leverages the platform's distributed architecture. Because your system consists of multiple agents communicating through a Solace event broker, issues can arise at various levels—from individual agent logic to inter-component communication patterns. 证据：`docs/docs/documentation/deploying/debugging.md` - **Deploying Agent Mesh**（documentation）：Moving your Agent Mesh from development to production requires careful consideration of deployment strategies, monitoring capabilities, and troubleshooting approaches. Understanding your options and having robust observability tools ensures your agent mesh operates reliably at scale. 证据：`docs/docs/documentation/deploying/deploying.md` - **Choosing Deployment Options**（documentation）：Agent Mesh offers flexible deployment options designed to meet different operational requirements. Understanding these options helps you choose the right approach for your specific environment and scale needs. 证据：`docs/docs/documentation/deploying/deployment-options.md` - **Health Checks**（documentation）：Health checks enable orchestration platforms like Kubernetes to monitor the operational status of your Agent Mesh components. By exposing standardized health endpoints, your agents, gateways, and platform services can signal when they're ready to receive traffic, allowing for graceful deployments, automatic recovery from failures, and intelligent load balancing. 证据：`docs/docs/documentation/deploying/health-checks.md` - **Logging**（documentation）：This guide covers the essential information you need to effectively configure and manage logging in your Agent Mesh applications. Proper logging configuration is critical for troubleshooting issues, monitoring system behavior, and maintaining reliable production deployments. 证据：`docs/docs/documentation/deploying/logging.md` - **Monitoring Your Agent Mesh**（documentation）：Understanding how your Agent Mesh system operates in real-time is crucial for maintaining optimal performance and quickly identifying issues. The platform provides a comprehensive observability suite that gives you deep insights into system behavior, message flows, and agent interactions. 证据：`docs/docs/documentation/deploying/observability.md` - **Proxy Configuration**（documentation）：When deploying Agent Mesh in environments with restricted network access, you may need to configure proxy settings to enable communication with external services. This guide explains how to configure HTTPS proxy settings for Agent Mesh. 证据：`docs/docs/documentation/deploying/proxy_configuration.md` - **Understanding the Architecture**（documentation）：:::tip For a more comprehensive tutorial example, see the Build Your Own Agent tutorials/custom-agent.md guide. This page walks through the fundamental concepts for creating agents in Agent Mesh. ::: 证据：`docs/docs/documentation/developing/create-agents.md` - **Creating Custom Gateways**（documentation）：import NetworkAccessMayBeRequired from '@site/docs/partials/network-access-may-be-required.mdx'; 证据：`docs/docs/documentation/developing/create-gateways.md` - **Creating Python Tools**（documentation）：Agent Mesh provides a powerful and unified system for creating custom agent tools using Python. This is the primary way to extend an agent's capabilities with your own business logic, integrate with proprietary APIs, or perform specialized data processing. 证据：`docs/docs/documentation/developing/creating-python-tools.md` - **Creating Service Providers**（documentation）：This guide details the process for developers to create service provider plugins for integrating backend systems for example, HR platforms, CRMs with Agent Mesh. 证据：`docs/docs/documentation/developing/creating-service-providers.md` - **Creating Workflows**（documentation）：:::warning Experimental Feature Workflows is currently an experimental feature. Expect this feature to change and improve in future releases. ::: 证据：`docs/docs/documentation/developing/creating-workflows.md` - **Developing with Agent Mesh**（documentation）：Agent Mesh provides a framework for creating distributed AI applications using an event-driven architecture. You can build agents that communicate through the A2A Agent-to-Agent protocol, extend them with custom tools, integrate external systems through gateways, and create reusable components as plugins. 证据：`docs/docs/documentation/developing/developing.md` - **Evaluating Agents**（documentation）：The framework includes an evaluation system that helps you test your agents' behavior in a structured way. You can define test suites, run them against your agents, and generate detailed reports to analyze the results. When running evaluations locally, you can also benchmark different language models to see how they affect your agents' responses. 证据：`docs/docs/documentation/developing/evaluations.md` - **Project Structure**（documentation）：Agent Mesh is built on the A2A Agent-to-Agent protocol architecture, powered by Solace AI Connector https://github.com/SolaceLabs/solace-ai-connector , and uses the Solace event broker as the communication backbone. The framework is controlled by YAML configuration files that define agents, gateways, and plugins, enabling distributed AI agent communication through event-driven messaging. 证据：`docs/docs/documentation/developing/structure.md` - **Amazon Bedrock Agents Integration**（documentation）：This tutorial walks you through the process of integrating Amazon Bedrock Agents and Flows into Agent Mesh. This integration allows you to create agents that can interact with one or multiple Bedrock Agents or Flows, extending your Agent Mesh project with powerful AI capabilities from AWS. 证据：`docs/docs/documentation/developing/tutorials/bedrock-agents.md` - **Building Custom Agent Images**（documentation）：This tutorial walks you through packaging a custom agent plugin into a Docker/OCI image suitable for Kubernetes deployment. By the end you will have a container image that extends the SAM Enterprise base image with your own Python tool, ready to deploy with Helm. For the deployment step, see Agent and Workflow Deployment https://solaceproducts.github.io/solace-agent-mesh-helm-quickstart/docs/standalone-agent-deployment . 证据：`docs/docs/documentation/developing/tutorials/building-custom-agent-images.md` - **Build Your Own Agent**（documentation）：This tutorial shows you how to build a sophisticated weather agent using the Agent Mesh framework. Learn how to integrate with external APIs, manage resources properly, and create production-ready agents. 证据：`docs/docs/documentation/developing/tutorials/custom-agent.md` - **Event Mesh Gateway**（documentation）：If you already have an event mesh https://solace.com/what-is-an-event-mesh/ in place, you can integrate Agent Mesh into it. This allows you to leverage existing infrastructure while introducing intelligence and automation through Agent Mesh. 证据：`docs/docs/documentation/developing/tutorials/event-mesh-gateway.md` - **MCP Gateway**（documentation）：This tutorial walks you through setting up the MCP Gateway, which exposes Solace Agent Mesh agents as a Model Context Protocol MCP server. This allows MCP-compatible client such as Claude Desktop, MCP Inspector, or custom applications to interact with Solace Agent Mesh agents through a standardized interface. 证据：`docs/docs/documentation/developing/tutorials/mcp-gateway.md` - **MCP Integration**（documentation）：This tutorial walks you through the process of integrating a Model Context Protocol MCP Server into Agent Mesh. 证据：`docs/docs/documentation/developing/tutorials/mcp-integration.md` - **MongoDB Integration**（documentation）：This tutorial sets up a MongoDB agent in Agent Mesh, which allows the Agent Mesh agent to answer natural language queries about a Mongo database. The agent translates user questions into MongoDB aggregation pipelines and executes them against your database. 证据：`docs/docs/documentation/developing/tutorials/mongodb-integration.md` - **RAG Integration**（documentation）：This tutorial guides you through setting up and configuring Agent Mesh Retrieval Augmented Generation RAG plugin. The RAG plugin enables your agents to answer questions by retrieving information from a knowledge base of your documents. 证据：`docs/docs/documentation/developing/tutorials/rag-integration.md` - **Key Features**（documentation）：Agent Mesh REST API Gateway provides a standard, robust, and secure HTTP-based entry point for programmatic and system-to-system integrations. It allows external clients to submit tasks to Agent Mesh agents, manage files, and discover agent capabilities using a familiar RESTful interface. 证据：`docs/docs/documentation/developing/tutorials/rest-gateway.md` - **Slack Integration**（documentation）：This tutorial integrates a Slack interface into Agent Mesh, enabling interaction with the system directly from your Slack workspace and channels. 证据：`docs/docs/documentation/developing/tutorials/slack-integration.md` - **SQL Database Integration**（documentation）：This tutorial sets up a SQL database agent in Agent Mesh, which allows the Agent Mesh agent to answer natural language queries about a sample coffee company database. This tutorial provides some sample data to set up an SQLite database, but you can use the same approach to connect to other database types, such as MySQL or PostgreSQL. 证据：`docs/docs/documentation/developing/tutorials/sql-database.md` - **Microsoft Teams Gateway Setup — Manual Configuration Docker & Wheel**（documentation）：Microsoft Teams Gateway Setup — Manual Configuration Docker & Wheel 证据：`docs/docs/documentation/developing/tutorials/teams-integration.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/README.md`, `docs/docs/documentation/components/agents.md`, `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/README.md`, `docs/docs/documentation/components/agents.md`, `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。 - **Framework Overview & Architecture**：importance `high` - source_paths: README.md, src/solace_agent_mesh/__init__.py, src/solace_agent_mesh/common/app_base.py, src/solace_agent_mesh/common/sac/sam_component_base.py, src/solace_agent_mesh/agent/adk/app_llm_agent.py - **Agents, Orchestration, Workflows & A2A Protocol**：importance `high` - source_paths: src/solace_agent_mesh/agent/sac/app.py, src/solace_agent_mesh/agent/sac/component.py, src/solace_agent_mesh/agent/proxies/a2a/app.py, src/solace_agent_mesh/agent/proxies/a2a/component.py, src/solace_agent_mesh/agent/adk/embed_resolving_mcp_toolset.py - **Gateways, HTTP/SSE Platform & Artifact Management**：importance `high` - source_paths: src/solace_agent_mesh/gateway/http_sse/main.py, src/solace_agent_mesh/gateway/http_sse/component.py, src/solace_agent_mesh/gateway/http_sse/routers/sse.py, src/solace_agent_mesh/gateway/http_sse/routers/sessions.py, src/solace_agent_mesh/gateway/http_sse/routers/projects.py - **CLI, Plugins, Platform Services, Evaluation & Deployment**：importance `high` - source_paths: cli/main.py, cli/commands/init_cmd/__init__.py, cli/commands/add_cmd/agent_cmd.py, cli/commands/add_cmd/gateway_cmd.py, cli/commands/plugin_cmd/install_cmd.py ## Repo Inspection Evidence / 源码检查证据 - repo_clone_verified: true - repo_inspection_verified: true - repo_commit: `93aa41d5d5fd8aaaaf14166fd07b110ac0cd8921` - inspected_files: `Dockerfile`, `README.md`, `pyproject.toml`, `uv.lock`, `docs/README.md`, `docs/docs/documentation/components/_category_.json`, `docs/docs/documentation/components/agents.md`, `docs/docs/documentation/components/builtin-tools/_category_.json`, `docs/docs/documentation/components/builtin-tools/artifact-management.md`, `docs/docs/documentation/components/builtin-tools/audio-tools.md`, `docs/docs/documentation/components/builtin-tools/builtin-tools.md`, `docs/docs/documentation/components/builtin-tools/data-analysis-tools.md`, `docs/docs/documentation/components/builtin-tools/embeds.md`, `docs/docs/documentation/components/builtin-tools/image-tools.md`, `docs/docs/documentation/components/builtin-tools/research-tools.md`, `docs/docs/documentation/components/cli.md`, `docs/docs/documentation/components/components.md`, `docs/docs/documentation/components/gateways.md`, `docs/docs/documentation/components/orchestrator.md`, `docs/docs/documentation/components/platform-service.md` 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：Proposal: IACP as a bridge protocol for A2A + MCP agent meshes - 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：Proposal: IACP as a bridge protocol for A2A + MCP agent meshes - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | https://github.com/SolaceLabs/solace-agent-mesh/issues/1507 | 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 2: 来源证据：Blocking socket.getaddrinfo in async webhook path causes event loop starvation - 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：Blocking socket.getaddrinfo in async webhook path causes event loop starvation - Why it matters: 可能阻塞安装或首次运行。 - Evidence: community_evidence:github | https://github.com/SolaceLabs/solace-agent-mesh/issues/1593 | 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: 能力判断依赖假设 - Trigger: README/documentation is current enough for a first validation pass. - Host AI rule: 将假设转成下游验证清单。 - Why it matters: 假设不成立时，用户拿不到承诺的能力。 - Evidence: capability.assumptions | https://github.com/SolaceLabs/solace-agent-mesh | README/documentation is current enough for a first validation pass. - 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: 来源证据：Shared module-level _METADATA_LOAD_SEMAPHORE may be used across multiple event loops - Trigger: GitHub 社区证据显示该项目存在一个运行相关的待验证问题：Shared module-level _METADATA_LOAD_SEMAPHORE may be used across multiple event loops - Why it matters: 可能增加新用户试用和生产接入成本。 - Evidence: community_evidence:github | https://github.com/SolaceLabs/solace-agent-mesh/issues/1591 | 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 5: 维护活跃度未知 - Trigger: 未记录 last_activity_observed。 - Host AI rule: 补 GitHub 最近 commit、release、issue/PR 响应信号。 - Why it matters: 新项目、停更项目和活跃项目会被混在一起，推荐信任度下降。 - Evidence: evidence.maintainer_signals | https://github.com/SolaceLabs/solace-agent-mesh | last_activity_observed missing - 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。 - Trigger: no_demo - Evidence: downstream_validation.risk_items | https://github.com/SolaceLabs/solace-agent-mesh | no_demo; severity=medium - 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: 存在评分风险 - Trigger: no_demo - Why it matters: 风险会影响是否适合普通用户安装。 - Evidence: risks.scoring_risks | https://github.com/SolaceLabs/solace-agent-mesh | no_demo; severity=medium - 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：Bridging Solace Agent Mesh ↔ Nautilus A2A — interoperability probe + 10 NAU bounty - 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：Bridging Solace Agent Mesh ↔ Nautilus A2A — interoperability probe + 10 NAU bounty - Why it matters: 可能影响授权、密钥配置或安全边界。 - Evidence: community_evidence:github | https://github.com/SolaceLabs/solace-agent-mesh/issues/1582 | 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: issue/PR 响应质量未知 - Trigger: issue_or_pr_quality=unknown。 - Host AI rule: 抽样最近 issue/PR，判断是否长期无人处理。 - Why it matters: 用户无法判断遇到问题后是否有人维护。 - Evidence: evidence.maintainer_signals | https://github.com/SolaceLabs/solace-agent-mesh | issue_or_pr_quality=unknown - 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: 发布节奏不明确 - Trigger: release_recency=unknown。 - Host AI rule: 确认最近 release/tag 和 README 安装命令是否一致。 - Why it matters: 安装命令和文档可能落后于代码，用户踩坑概率升高。 - Evidence: evidence.maintainer_signals | https://github.com/SolaceLabs/solace-agent-mesh | release_recency=unknown - 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。