# AgentScope: Chinese AgentScope > ## Agent Instructions > For AgentScope Python, use https://docs.agentscope.io/stable/en/index for new projects. For existing projects, check the installed agentscope version and use matching versioned documentation. > The /latest/ alias points to development documentation. Use it only with the matching development source. Do not mix AgentScope 1.x and 2.x APIs. > State the AgentScope version when providing installation commands or code examples. ReMe uses its own continuously updated /reme/latest/ documentation. ## AgentScope - [Chinese / AgentScope / 2.0.9dev (134 pages)](https://docs.agentscope.io/_llms/zh/agent-scope/2-0-9dev.md): Documentation for Chinese / AgentScope / 2.0.9dev. ### 2.0.8 #### 快速开始 - [AgentScope 2.0 是什么？](https://docs.agentscope.io/versions/2.0.8/zh/index.md): 安全、高效、灵活、完备 - [快速开始](https://docs.agentscope.io/versions/2.0.8/zh/quickstart.md): 快速上手 AgentScope 2.0 - [更新日志](https://docs.agentscope.io/versions/2.0.8/zh/release-notes.md): AgentScope 版本改动和更新日志。 #### 核心模块 - [消息与事件](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/message-and-event.md): 智能体通信，与前端流式数据传输 - [计划模式](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/plan.md): 为智能体提供结构化任务清单，用于规划、追踪并协调复杂工作 - [中间件](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/middleware.md): 在智能体生命周期的关键位置拦截并扩展行为 - [RAG](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/rag.md): 为智能体构建检索增强生成（RAG）能力。 - [长期记忆](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/long-term-memory.md): 基于智能体中间件实现的，跨会话长期记忆 - [终端 UI](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/console.md): 在终端快速测试、验证智能体运行逻辑 - [A2A 协议](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/a2a.md): 连接并与 A2A 协议后的智能体进行对话 ##### 智能体 - [概述](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/agent/overview.md): AgentScope 的核心抽象：无状态的推理-行动循环引擎 - [配置智能体](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/agent/configure-agent.md): 用模型、工具与配置对象组装一个智能体 - [运行智能体](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/agent/run-agent.md): 运行智能体，处理它的回复、上下文与状态 - [中断智能体](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/agent/interrupt-agent.md): 干净地停止运行中或暂停中的智能体，并从一致状态恢复 - [人机交互](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/agent/human-in-the-loop.md): 暂停以等待用户确认或外部执行，再通过结果事件恢复 ##### 模型 - [概述](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/model/overview.md): 通过凭证接入模型 API，并用模型卡片发现可用模型 - [大语言模型](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/model/llm.md): 创建并调用对话模型，也可以接入你自己的模型 API - [语音合成](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/model/tts.md): 将文本转换为语音，支持标准与实时两种合成模式 - [嵌入模型](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/model/embedding.md): 将文本与多媒体内容转换为向量，服务检索、RAG 与记忆 ##### 上下文管理 - [概述](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/context/overview.md): 管理智能体的工作记忆，让长任务稳定推进 - [感知环境](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/context/environment-awareness.md): 让智能体持续感知时间、任务、上下文用量与工具报错的变化 - [压缩上下文](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/context/compress-context.md): 将上下文长度维护在预设的长度内 - [卸载上下文](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/context/offload-context.md): 持久化被移除的内容，供智能体按需回查 ##### 工具 - [概述](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/tool/overview.md): 通过 Toolkit 为智能体装配工具、MCP 服务与技能 - [Python 函数工具](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/tool/python-tool.md): 基于类或普通函数构建工具，并控制它们的执行方式 - [MCP](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/tool/mcp.md): 接入 MCP 服务并使用其工具 - [Skill](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/tool/skill.md): 用 Markdown 指令集拓展智能体能力 - [元工具](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/tool/manage-tools.md): 让智能体在运行时自主激活或停用工具组 ##### 流水线 - [概述](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/pipeline/overview.md): 按照固化逻辑运行多智能体，并向外提供统一接口 - [目标流水线](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/pipeline/goal.md): 让执行者反复工作，直到验证者认可结果 ##### 权限系统 - [概述](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/permission-system/overview.md): 规则、模式与工具内置检查如何共同决定每一次工具调用 - [权限模式](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/permission-system/permission-mode.md): 根据智能体的部署方式选择合适的全局策略 - [权限规则](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/permission-system/permission-rule.md): 为特定工具与调用编写允许、拒绝和询问规则 - [工具内置检查](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/permission-system/tool-check.md): 工具在运行时对自身输入执行的安全分析 ##### 工作区 - [概述](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/workspace/overview.md): 为智能体提供可执行、可持久化的运行环境 - [运行工作区](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/workspace/run-workspace.md): 在任意后端上创建工作区，并接入智能体 - [管理资源](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/workspace/manage-resources.md): 在运行时添加、移除 MCP 服务与技能 - [MCP 网关](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/workspace/mcp-gateway.md): 沙箱类工作区如何把内部的 MCP 服务暴露给主机 ##### 实时语音智能体 - [概述](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/realtime/overview.md): 让智能体用语音与用户对话，并在对话中调用工具完成任务 - [语音到语音](https://docs.agentscope.io/versions/2.0.8/zh/building-blocks/realtime/speech-to-speech.md): 通过端到端的语音模型实现实时语音对话 #### 智能体即服务 - [架构](https://docs.agentscope.io/versions/2.0.8/zh/deploy/agent-service.md): 把智能体部署为多租户、多会话的 HTTP 服务 - [智能体团队](https://docs.agentscope.io/versions/2.0.8/zh/deploy/agent-team.md): Leader 智能体通过内置 team 工具派生并协调 worker 智能体 - [资源共享](https://docs.agentscope.io/versions/2.0.8/zh/deploy/sharing.md): 以团队，组织为单位共享 API 凭证、智能体与知识库 - [RAG 服务](https://docs.agentscope.io/versions/2.0.8/zh/deploy/rag.md): 一键式启动的多租户、分布式 RAG 服务 - [工作区管理](https://docs.agentscope.io/versions/2.0.8/zh/deploy/workspace-manager.md): 在服务中分配、管理智能体的运行环境（Workspace） ##### MCP 与技能中心 - [概览](https://docs.agentscope.io/versions/2.0.8/zh/deploy/hub/overview.md): 快速接入不同来源的 MCP 与技能中心。 - [MCP 中心](https://docs.agentscope.io/versions/2.0.8/zh/deploy/hub/mcp-hub.md): 让用户从一个来源安装 MCP 服务，并配置自己的凭证。 - [技能中心](https://docs.agentscope.io/versions/2.0.8/zh/deploy/hub/skill-hub.md): 让用户安装他人发布的技能，并装配给自己的智能体。 ##### 消息渠道 - [概览](https://docs.agentscope.io/versions/2.0.8/zh/deploy/channel/overview.md): 让 AgentScope 服务中的智能体入驻 IM 平台。 - [会话路由](https://docs.agentscope.io/versions/2.0.8/zh/deploy/channel/routing.md): 决定 IM 平台来的消息交给哪个智能体、进入哪个会话。 - [飞书](https://docs.agentscope.io/versions/2.0.8/zh/deploy/channel/feishu.md): 在飞书中与智能体服务里的智能体对话。 - [钉钉](https://docs.agentscope.io/versions/2.0.8/zh/deploy/channel/dingtalk.md): 在钉钉中与智能体服务里的智能体对话。 - [Discord](https://docs.agentscope.io/versions/2.0.8/zh/deploy/channel/discord.md): 在 Discord 中与智能体服务里的智能体对话。 - [自定义渠道](https://docs.agentscope.io/versions/2.0.8/zh/deploy/channel/custom.md): 实现 ChannelBase，把智能体接入内置之外的平台。 ##### API ###### agent - [[Deprecated] Legacy sectioned schema — use /schema/v2](https://docs.agentscope.io/api-reference/agent/[deprecated]-legacy-sectioned-schema-—-use-schemav2.md): Return the legacy sectioned JSON Schema fragments. - [Full AgentData JSON Schema for the agent form](https://docs.agentscope.io/api-reference/agent/full-agentdata-json-schema-for-the-agent-form.md): Return the full :class:`AgentData` JSON Schema. - [List all agents](https://docs.agentscope.io/api-reference/agent/list-all-agents.md): Return all agent records belonging to the authenticated user. - [Create a new agent](https://docs.agentscope.io/api-reference/agent/create-a-new-agent.md): Create and persist a new agent configuration. - [Delete an agent](https://docs.agentscope.io/api-reference/agent/delete-an-agent.md): Permanently delete an agent configuration. - [Update an agent](https://docs.agentscope.io/api-reference/agent/update-an-agent.md): Partially update an existing agent configuration. ###### chat - [Trigger a chat run (fire-and-forget)](https://docs.agentscope.io/api-reference/chat/trigger-a-chat-run-fire-and-forget.md): Trigger a chat run for the specified session. ###### credential - [List JSON schemas for all credential types](https://docs.agentscope.io/api-reference/credential/list-json-schemas-for-all-credential-types.md): Return JSON schemas for all registered credential types. - [List all credentials](https://docs.agentscope.io/api-reference/credential/list-all-credentials.md): Return all credential records belonging to the authenticated user. - [Create a new credential](https://docs.agentscope.io/api-reference/credential/create-a-new-credential.md): Store a new credential. - [Delete a credential](https://docs.agentscope.io/api-reference/credential/delete-a-credential.md): Permanently delete a credential. - [Update a credential](https://docs.agentscope.io/api-reference/credential/update-a-credential.md): Replace the payload of an existing credential. ###### health - [Report service liveness and per-component readiness](https://docs.agentscope.io/api-reference/health/report-service-liveness-and-per-component-readiness.md): Report whether the service is ready to serve requests. ###### hub - [List Mcp Hubs](https://docs.agentscope.io/api-reference/hub/list-mcp-hubs.md): Return every registered MCP hub. - [List Mcp Cards](https://docs.agentscope.io/api-reference/hub/list-mcp-cards.md): Browse or search one MCP hub's catalog. - [Get Mcp Card](https://docs.agentscope.io/api-reference/hub/get-mcp-card.md): Return one MCP card, including the inputs the user must fill. - [Install Mcp](https://docs.agentscope.io/api-reference/hub/install-mcp.md): Fill a card's template and add the result to the user's library. - [List Skill Hubs](https://docs.agentscope.io/api-reference/hub/list-skill-hubs.md): Return every registered skill hub. - [List Skill Cards](https://docs.agentscope.io/api-reference/hub/list-skill-cards.md): Browse or search one skill hub's catalog. - [Get Skill Card](https://docs.agentscope.io/api-reference/hub/get-skill-card.md): Return one skill card, including its ``SKILL.md`` body. - [Install Skill](https://docs.agentscope.io/api-reference/hub/install-skill.md): Add a skill card to the user's library. ###### knowledge_bases - [List embedding models compatible with the KB dimension policy](https://docs.agentscope.io/api-reference/knowledge_bases/list-embedding-models-compatible-with-the-kb-dimension-policy.md): List embedding models the user can pick at KB-creation time. - [JSON Schema for the KB middleware's tunable parameters](https://docs.agentscope.io/api-reference/knowledge_bases/json-schema-for-the-kb-middlewares-tunable-parameters.md): Return the parameter schema for :class:`agentscope.middleware.RAGMiddleware`. - [List file types the configured parsers can ingest](https://docs.agentscope.io/api-reference/knowledge_bases/list-file-types-the-configured-parsers-can-ingest.md): Advertise the union of media types and filename extensions every registered parser accepts. - [List the caller's knowledge bases](https://docs.agentscope.io/api-reference/knowledge_bases/list-the-callers-knowledge-bases.md): Return all knowledge bases owned by the authenticated user. - [Create a new knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/create-a-new-knowledge-base.md): Create a new knowledge base for the authenticated user. - [Delete a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-knowledge-base.md): Permanently delete a knowledge base. - [Update mutable fields on a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/update-mutable-fields-on-a-knowledge-base.md): Update mutable fields on a knowledge base. - [List documents registered in a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/list-documents-registered-in-a-knowledge-base.md): List every document registered against a knowledge base. - [Upload a document into a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/upload-a-document-into-a-knowledge-base.md): Register an uploaded document and dispatch it for indexing. - [Batch-query indexing status of one or more documents](https://docs.agentscope.io/api-reference/knowledge_bases/batch-query-indexing-status-of-one-or-more-documents.md): Return the current lifecycle state of a batch of documents. - [Delete a document from a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-document-from-a-knowledge-base.md): Remove a document and all its chunks from a knowledge base. - [Search a knowledge base by natural-language query](https://docs.agentscope.io/api-reference/knowledge_bases/search-a-knowledge-base-by-natural-language-query.md): Run a similarity search over a knowledge base. ###### mcp - [List Mcps](https://docs.agentscope.io/api-reference/mcp/list-mcps.md): Return every MCP the user has installed, ordered by name. - [Delete Mcp](https://docs.agentscope.io/api-reference/mcp/delete-mcp.md): Remove an MCP from the user's library. - [Update Mcp](https://docs.agentscope.io/api-reference/mcp/update-mcp.md): Rename, enable/disable, or re-key an installed MCP. ###### schedule - [List all schedules](https://docs.agentscope.io/api-reference/schedule/list-all-schedules.md): List all schedules owned by the current user. - [Create a new schedule](https://docs.agentscope.io/api-reference/schedule/create-a-new-schedule.md): Create a new schedule and register it with the scheduler. - [Delete a schedule](https://docs.agentscope.io/api-reference/schedule/delete-a-schedule.md): Permanently delete a schedule. - [Update a schedule](https://docs.agentscope.io/api-reference/schedule/update-a-schedule.md): Partially update a schedule. - [List execution sessions for a schedule](https://docs.agentscope.io/api-reference/schedule/list-execution-sessions-for-a-schedule.md): Return all sessions triggered by a given schedule. ###### sessions - [List sessions for an agent](https://docs.agentscope.io/api-reference/sessions/list-sessions-for-an-agent.md): Return all sessions for an agent as enriched :class:`SessionView` entries. - [Create a new session](https://docs.agentscope.io/api-reference/sessions/create-a-new-session.md): Create (or resume) a session for a given agent and workspace. - [Delete a session](https://docs.agentscope.io/api-reference/sessions/delete-a-session.md): Permanently delete a session and all its associated state. - [Update a session](https://docs.agentscope.io/api-reference/sessions/update-a-session.md): Update the model configuration of an existing session. - [Interrupt a running or HITL-parked chat run for a session](https://docs.agentscope.io/api-reference/sessions/interrupt-a-running-or-hitl-parked-chat-run-for-a-session.md): Request interruption of an in-progress reply for a session. - [List messages for a session](https://docs.agentscope.io/api-reference/sessions/list-messages-for-a-session.md): Return persisted messages for a session. - [Probe the session's high-level status](https://docs.agentscope.io/api-reference/sessions/probe-the-sessions-high-level-status.md): Return the unified :class:`SessionStatus` for a session. - [Subscribe to a session's event stream (SSE)](https://docs.agentscope.io/api-reference/sessions/subscribe-to-a-sessions-event-stream-sse.md): Subscribe to a session's live event stream. ###### skill - [List Skills](https://docs.agentscope.io/api-reference/skill/list-skills.md): Return every skill the user has installed, ordered by name. - [Get Skill](https://docs.agentscope.io/api-reference/skill/get-skill.md): Return one installed skill, including its ``SKILL.md`` body. - [Delete Skill](https://docs.agentscope.io/api-reference/skill/delete-skill.md): Remove a skill from the user's library. ###### workspace - [List Mcps](https://docs.agentscope.io/api-reference/workspace/list-mcps.md): Return all MCP clients with live tool list and health status. - [Add Mcp](https://docs.agentscope.io/api-reference/workspace/add-mcp.md): Add an MCP client to the session's workspace. - [Add Mcps From Library](https://docs.agentscope.io/api-reference/workspace/add-mcps-from-library.md): Put MCPs the user has already installed into this workspace. - [Remove Mcp](https://docs.agentscope.io/api-reference/workspace/remove-mcp.md): Remove an MCP client from the session's workspace by name. - [List Skills](https://docs.agentscope.io/api-reference/workspace/list-skills.md): Return all skills available in the session's workspace. - [Add Skill](https://docs.agentscope.io/api-reference/workspace/add-skill.md): Add a skill to the session's workspace from the given path. - [Upload Skill](https://docs.agentscope.io/api-reference/workspace/upload-skill.md): Install a skill from an uploaded folder. - [Add Skills From Library](https://docs.agentscope.io/api-reference/workspace/add-skills-from-library.md): Put skills the user has already installed into this workspace. - [Remove Skill](https://docs.agentscope.io/api-reference/workspace/remove-skill.md): Remove a skill from the session's workspace by name. - [List Workspace Directory](https://docs.agentscope.io/api-reference/workspace/list-workspace-directory.md): List one directory level, reachable from a session's workspace. - [Create Download Token](https://docs.agentscope.io/api-reference/workspace/create-download-token.md): Mint a short-lived token for a browser-native download. - [Read Workspace File](https://docs.agentscope.io/api-reference/workspace/read-workspace-file.md): Stream one file out of a session's workspace. ###### model - [List all candidate models under the given credential type](https://docs.agentscope.io/api-reference/model/list-all-candidate-models-under-the-given-credential-type.md): Return all candidate models under the given credential type. ###### tts-model - [List all candidate TTS models under the given credential type](https://docs.agentscope.io/api-reference/tts-model/list-all-candidate-tts-models-under-the-given-credential-type.md): Return all candidate TTS models under the given credential type. ###### embedding-model - [List all candidate embedding models under the given credential type](https://docs.agentscope.io/api-reference/embedding-model/list-all-candidate-embedding-models-under-the-given-credential-type.md): Return all candidate embedding models under the credential type. ###### channels - [List Channel Types](https://docs.agentscope.io/api-reference/channels/list-channel-types.md): List supported channel types with their JSON schemas. - [List Channels](https://docs.agentscope.io/api-reference/channels/list-channels.md): List channels owned by the current user. - [Create Channel](https://docs.agentscope.io/api-reference/channels/create-channel.md): Create a channel. - [Get Channel](https://docs.agentscope.io/api-reference/channels/get-channel.md): Get channel details. - [Delete Channel](https://docs.agentscope.io/api-reference/channels/delete-channel.md): Delete a channel. - [Update Channel](https://docs.agentscope.io/api-reference/channels/update-channel.md): Update routing / session / config / enabled. - [Enable Channel](https://docs.agentscope.io/api-reference/channels/enable-channel.md): Enable a channel. - [Disable Channel](https://docs.agentscope.io/api-reference/channels/disable-channel.md): Disable a channel. - [Channel Status](https://docs.agentscope.io/api-reference/channels/channel-status.md): The channel's live connection status. - [List Channel Sessions](https://docs.agentscope.io/api-reference/channels/list-channel-sessions.md): Sessions this channel spawned, newest first. - [List Chat Ids](https://docs.agentscope.io/api-reference/channels/list-chat-ids.md): Known chats for routing config: platform list ∪ passively seen. #### 其他 - [常见问题](https://docs.agentscope.io/versions/2.0.8/zh/others/faq.md): 解答使用 AgentScope 2.0 时的常见问题。 - [版本迁移](https://docs.agentscope.io/versions/2.0.8/zh/others/change-log.md): AgentScope 2.0 与 1.0 的核心区别 ### 2.0.7 #### 快速开始 - [AgentScope 2.0 是什么？](https://docs.agentscope.io/versions/2.0.7/zh/index.md): 安全、高效、灵活、完备 - [快速开始](https://docs.agentscope.io/versions/2.0.7/zh/quickstart.md): 快速上手 AgentScope 2.0 - [更新日志](https://docs.agentscope.io/versions/2.0.7/zh/release-notes.md): AgentScope 版本改动和更新日志。 #### 核心模块 - [消息与事件](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/message-and-event.md): 智能体通信，与前端流式数据传输 - [计划模式](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/plan.md): 为智能体提供结构化任务清单，用于规划、追踪并协调复杂工作 - [中间件](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/middleware.md): 在智能体生命周期的关键位置拦截并扩展行为 - [RAG](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/rag.md): 为智能体构建检索增强生成（RAG）能力。 - [长期记忆](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/long-term-memory.md): 基于智能体中间件实现的，跨会话长期记忆 - [控制台](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/console.md): 在终端快速测试、验证智能体运行逻辑 ##### 智能体 - [概述](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/agent/overview.md): AgentScope 的核心抽象：无状态的推理-行动循环引擎 - [配置智能体](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/agent/configure-agent.md): 用模型、工具与配置对象组装一个智能体 - [运行智能体](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/agent/run-agent.md): 运行智能体，处理它的回复、上下文与状态 - [中断智能体](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/agent/interrupt-agent.md): 干净地停止运行中或暂停中的智能体，并从一致状态恢复 - [人机交互](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/agent/human-in-the-loop.md): 暂停以等待用户确认或外部执行，再通过结果事件恢复 ##### 模型 - [概述](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/model/overview.md): 通过凭证接入模型 API，并用模型卡片发现可用模型 - [大语言模型](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/model/llm.md): 创建并调用对话模型，也可以接入你自己的模型 API - [语音合成](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/model/tts.md): 将文本转换为语音，支持标准与实时两种合成模式 - [嵌入模型](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/model/embedding.md): 将文本与多媒体内容转换为向量，服务检索、RAG 与记忆 ##### 上下文管理 - [概述](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/context/overview.md): 管理智能体的工作记忆，让长任务稳定推进 - [感知环境](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/context/environment-awareness.md): 让智能体持续感知时间、任务与上下文用量的变化 - [压缩上下文](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/context/compress-context.md): 将上下文长度维护在预设的长度内 - [卸载上下文](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/context/offload-context.md): 持久化被移除的内容，供智能体按需回查 ##### 工具 - [概述](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/tool/overview.md): 通过 Toolkit 为智能体装配工具、MCP 服务与技能 - [Python 函数工具](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/tool/python-tool.md): 基于类或普通函数构建工具，并控制它们的执行方式 - [MCP](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/tool/mcp.md): 接入 MCP 服务并使用其工具 - [Skill](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/tool/skill.md): 用 Markdown 指令集拓展智能体能力 - [元工具](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/tool/manage-tools.md): 让智能体在运行时自主激活或停用工具组 ##### 权限系统 - [概述](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/permission-system/overview.md): 规则、模式与工具内置检查如何共同决定每一次工具调用 - [权限模式](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/permission-system/permission-mode.md): 根据智能体的部署方式选择合适的全局策略 - [权限规则](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/permission-system/permission-rule.md): 为特定工具与调用编写允许、拒绝和询问规则 - [工具内置检查](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/permission-system/tool-check.md): 工具在运行时对自身输入执行的安全分析 ##### 工作区 - [概述](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/workspace/overview.md): 为智能体提供可执行、可持久化的运行环境 - [运行工作区](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/workspace/run-workspace.md): 在任意后端上创建工作区，并接入智能体 - [管理资源](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/workspace/manage-resources.md): 在运行时添加、移除 MCP 服务与技能 - [MCP 网关](https://docs.agentscope.io/versions/2.0.7/zh/building-blocks/workspace/mcp-gateway.md): 沙箱类工作区如何把内部的 MCP 服务暴露给主机 #### 智能体即服务 - [架构](https://docs.agentscope.io/versions/2.0.7/zh/deploy/agent-service.md): 把智能体部署为多租户、多会话的 HTTP 服务 - [智能体团队](https://docs.agentscope.io/versions/2.0.7/zh/deploy/agent-team.md): Leader 智能体通过内置 team 工具派生并协调 worker 智能体 - [资源共享](https://docs.agentscope.io/versions/2.0.7/zh/deploy/sharing.md): 以团队，组织为单位共享 API 凭证、智能体与知识库 - [RAG 服务](https://docs.agentscope.io/versions/2.0.7/zh/deploy/rag.md): 一键式启动的多租户、分布式 RAG 服务 - [工作区管理](https://docs.agentscope.io/versions/2.0.7/zh/deploy/workspace-manager.md): 在服务中分配、管理智能体的运行环境（Workspace） ##### MCP 与技能中心 - [概览](https://docs.agentscope.io/versions/2.0.7/zh/deploy/hub/overview.md): 快速接入不同来源的 MCP 与技能中心。 - [MCP 中心](https://docs.agentscope.io/versions/2.0.7/zh/deploy/hub/mcp-hub.md): 让用户从一个来源安装 MCP 服务，并配置自己的凭证。 - [技能中心](https://docs.agentscope.io/versions/2.0.7/zh/deploy/hub/skill-hub.md): 让用户安装他人发布的技能，并装配给自己的智能体。 ##### 消息渠道 - [概览](https://docs.agentscope.io/versions/2.0.7/zh/deploy/channel/overview.md): 让 AgentScope 服务中的智能体入驻 IM 平台。 - [会话路由](https://docs.agentscope.io/versions/2.0.7/zh/deploy/channel/routing.md): 决定 IM 平台来的消息交给哪个智能体、进入哪个会话。 - [飞书](https://docs.agentscope.io/versions/2.0.7/zh/deploy/channel/feishu.md): 在飞书中与智能体服务里的智能体对话。 - [钉钉](https://docs.agentscope.io/versions/2.0.7/zh/deploy/channel/dingtalk.md): 在钉钉中与智能体服务里的智能体对话。 - [Discord](https://docs.agentscope.io/versions/2.0.7/zh/deploy/channel/discord.md): 在 Discord 中与智能体服务里的智能体对话。 - [自定义渠道](https://docs.agentscope.io/versions/2.0.7/zh/deploy/channel/custom.md): 实现 ChannelBase，把智能体接入内置之外的平台。 ##### API ###### agent - [[Deprecated] Legacy sectioned schema — use /schema/v2](https://docs.agentscope.io/api-reference/agent/[deprecated]-legacy-sectioned-schema-—-use-schemav2.md): Return the legacy sectioned JSON Schema fragments. - [Full AgentData JSON Schema for the agent form](https://docs.agentscope.io/api-reference/agent/full-agentdata-json-schema-for-the-agent-form.md): Return the full :class:`AgentData` JSON Schema. - [List all agents](https://docs.agentscope.io/api-reference/agent/list-all-agents.md): Return all agent records belonging to the authenticated user. - [Create a new agent](https://docs.agentscope.io/api-reference/agent/create-a-new-agent.md): Create and persist a new agent configuration. - [Delete an agent](https://docs.agentscope.io/api-reference/agent/delete-an-agent.md): Permanently delete an agent configuration. - [Update an agent](https://docs.agentscope.io/api-reference/agent/update-an-agent.md): Partially update an existing agent configuration. ###### chat - [Trigger a chat run (fire-and-forget)](https://docs.agentscope.io/api-reference/chat/trigger-a-chat-run-fire-and-forget.md): Trigger a chat run for the specified session. ###### credential - [List JSON schemas for all credential types](https://docs.agentscope.io/api-reference/credential/list-json-schemas-for-all-credential-types.md): Return JSON schemas for all registered credential types. - [List all credentials](https://docs.agentscope.io/api-reference/credential/list-all-credentials.md): Return all credential records belonging to the authenticated user. - [Create a new credential](https://docs.agentscope.io/api-reference/credential/create-a-new-credential.md): Store a new credential. - [Delete a credential](https://docs.agentscope.io/api-reference/credential/delete-a-credential.md): Permanently delete a credential. - [Update a credential](https://docs.agentscope.io/api-reference/credential/update-a-credential.md): Replace the payload of an existing credential. ###### health - [Report service liveness and per-component readiness](https://docs.agentscope.io/api-reference/health/report-service-liveness-and-per-component-readiness.md): Report whether the service is ready to serve requests. ###### hub - [List Mcp Hubs](https://docs.agentscope.io/api-reference/hub/list-mcp-hubs.md): Return every registered MCP hub. - [List Mcp Cards](https://docs.agentscope.io/api-reference/hub/list-mcp-cards.md): Browse or search one MCP hub's catalog. - [Get Mcp Card](https://docs.agentscope.io/api-reference/hub/get-mcp-card.md): Return one MCP card, including the inputs the user must fill. - [Install Mcp](https://docs.agentscope.io/api-reference/hub/install-mcp.md): Fill a card's template and add the result to the user's library. - [List Skill Hubs](https://docs.agentscope.io/api-reference/hub/list-skill-hubs.md): Return every registered skill hub. - [List Skill Cards](https://docs.agentscope.io/api-reference/hub/list-skill-cards.md): Browse or search one skill hub's catalog. - [Get Skill Card](https://docs.agentscope.io/api-reference/hub/get-skill-card.md): Return one skill card, including its ``SKILL.md`` body. - [Install Skill](https://docs.agentscope.io/api-reference/hub/install-skill.md): Add a skill card to the user's library. ###### knowledge_bases - [List embedding models compatible with the KB dimension policy](https://docs.agentscope.io/api-reference/knowledge_bases/list-embedding-models-compatible-with-the-kb-dimension-policy.md): List embedding models the user can pick at KB-creation time. - [JSON Schema for the KB middleware's tunable parameters](https://docs.agentscope.io/api-reference/knowledge_bases/json-schema-for-the-kb-middlewares-tunable-parameters.md): Return the parameter schema for :class:`agentscope.middleware.RAGMiddleware`. - [List file types the configured parsers can ingest](https://docs.agentscope.io/api-reference/knowledge_bases/list-file-types-the-configured-parsers-can-ingest.md): Advertise the union of media types and filename extensions every registered parser accepts. - [List the caller's knowledge bases](https://docs.agentscope.io/api-reference/knowledge_bases/list-the-callers-knowledge-bases.md): Return all knowledge bases owned by the authenticated user. - [Create a new knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/create-a-new-knowledge-base.md): Create a new knowledge base for the authenticated user. - [Delete a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-knowledge-base.md): Permanently delete a knowledge base. - [Update mutable fields on a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/update-mutable-fields-on-a-knowledge-base.md): Update mutable fields on a knowledge base. - [List documents registered in a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/list-documents-registered-in-a-knowledge-base.md): List every document registered against a knowledge base. - [Upload a document into a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/upload-a-document-into-a-knowledge-base.md): Register an uploaded document and dispatch it for indexing. - [Batch-query indexing status of one or more documents](https://docs.agentscope.io/api-reference/knowledge_bases/batch-query-indexing-status-of-one-or-more-documents.md): Return the current lifecycle state of a batch of documents. - [Delete a document from a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-document-from-a-knowledge-base.md): Remove a document and all its chunks from a knowledge base. - [Search a knowledge base by natural-language query](https://docs.agentscope.io/api-reference/knowledge_bases/search-a-knowledge-base-by-natural-language-query.md): Run a similarity search over a knowledge base. ###### mcp - [List Mcps](https://docs.agentscope.io/api-reference/mcp/list-mcps.md): Return every MCP the user has installed, ordered by name. - [Delete Mcp](https://docs.agentscope.io/api-reference/mcp/delete-mcp.md): Remove an MCP from the user's library. - [Update Mcp](https://docs.agentscope.io/api-reference/mcp/update-mcp.md): Rename, enable/disable, or re-key an installed MCP. ###### schedule - [List all schedules](https://docs.agentscope.io/api-reference/schedule/list-all-schedules.md): List all schedules owned by the current user. - [Create a new schedule](https://docs.agentscope.io/api-reference/schedule/create-a-new-schedule.md): Create a new schedule and register it with the scheduler. - [Delete a schedule](https://docs.agentscope.io/api-reference/schedule/delete-a-schedule.md): Permanently delete a schedule. - [Update a schedule](https://docs.agentscope.io/api-reference/schedule/update-a-schedule.md): Partially update a schedule. - [List execution sessions for a schedule](https://docs.agentscope.io/api-reference/schedule/list-execution-sessions-for-a-schedule.md): Return all sessions triggered by a given schedule. ###### sessions - [List sessions for an agent](https://docs.agentscope.io/api-reference/sessions/list-sessions-for-an-agent.md): Return all sessions for an agent as enriched :class:`SessionView` entries. - [Create a new session](https://docs.agentscope.io/api-reference/sessions/create-a-new-session.md): Create (or resume) a session for a given agent and workspace. - [Delete a session](https://docs.agentscope.io/api-reference/sessions/delete-a-session.md): Permanently delete a session and all its associated state. - [Update a session](https://docs.agentscope.io/api-reference/sessions/update-a-session.md): Update the model configuration of an existing session. - [Interrupt a running or HITL-parked chat run for a session](https://docs.agentscope.io/api-reference/sessions/interrupt-a-running-or-hitl-parked-chat-run-for-a-session.md): Request interruption of an in-progress reply for a session. - [List messages for a session](https://docs.agentscope.io/api-reference/sessions/list-messages-for-a-session.md): Return persisted messages for a session. - [Probe the session's high-level status](https://docs.agentscope.io/api-reference/sessions/probe-the-sessions-high-level-status.md): Return the unified :class:`SessionStatus` for a session. - [Subscribe to a session's event stream (SSE)](https://docs.agentscope.io/api-reference/sessions/subscribe-to-a-sessions-event-stream-sse.md): Subscribe to a session's live event stream. ###### skill - [List Skills](https://docs.agentscope.io/api-reference/skill/list-skills.md): Return every skill the user has installed, ordered by name. - [Get Skill](https://docs.agentscope.io/api-reference/skill/get-skill.md): Return one installed skill, including its ``SKILL.md`` body. - [Delete Skill](https://docs.agentscope.io/api-reference/skill/delete-skill.md): Remove a skill from the user's library. ###### workspace - [List Mcps](https://docs.agentscope.io/api-reference/workspace/list-mcps.md): Return all MCP clients with live tool list and health status. - [Add Mcp](https://docs.agentscope.io/api-reference/workspace/add-mcp.md): Add an MCP client to the session's workspace. - [Add Mcps From Library](https://docs.agentscope.io/api-reference/workspace/add-mcps-from-library.md): Put MCPs the user has already installed into this workspace. - [Remove Mcp](https://docs.agentscope.io/api-reference/workspace/remove-mcp.md): Remove an MCP client from the session's workspace by name. - [List Skills](https://docs.agentscope.io/api-reference/workspace/list-skills.md): Return all skills available in the session's workspace. - [Add Skill](https://docs.agentscope.io/api-reference/workspace/add-skill.md): Add a skill to the session's workspace from the given path. - [Upload Skill](https://docs.agentscope.io/api-reference/workspace/upload-skill.md): Install a skill from an uploaded folder. - [Add Skills From Library](https://docs.agentscope.io/api-reference/workspace/add-skills-from-library.md): Put skills the user has already installed into this workspace. - [Remove Skill](https://docs.agentscope.io/api-reference/workspace/remove-skill.md): Remove a skill from the session's workspace by name. - [List Workspace Directory](https://docs.agentscope.io/api-reference/workspace/list-workspace-directory.md): List one directory level, reachable from a session's workspace. - [Create Download Token](https://docs.agentscope.io/api-reference/workspace/create-download-token.md): Mint a short-lived token for a browser-native download. - [Read Workspace File](https://docs.agentscope.io/api-reference/workspace/read-workspace-file.md): Stream one file out of a session's workspace. ###### model - [List all candidate models under the given credential type](https://docs.agentscope.io/api-reference/model/list-all-candidate-models-under-the-given-credential-type.md): Return all candidate models under the given credential type. ###### tts-model - [List all candidate TTS models under the given credential type](https://docs.agentscope.io/api-reference/tts-model/list-all-candidate-tts-models-under-the-given-credential-type.md): Return all candidate TTS models under the given credential type. ###### embedding-model - [List all candidate embedding models under the given credential type](https://docs.agentscope.io/api-reference/embedding-model/list-all-candidate-embedding-models-under-the-given-credential-type.md): Return all candidate embedding models under the credential type. ###### channels - [List Channel Types](https://docs.agentscope.io/api-reference/channels/list-channel-types.md): List supported channel types with their JSON schemas. - [List Channels](https://docs.agentscope.io/api-reference/channels/list-channels.md): List channels owned by the current user. - [Create Channel](https://docs.agentscope.io/api-reference/channels/create-channel.md): Create a channel. - [Get Channel](https://docs.agentscope.io/api-reference/channels/get-channel.md): Get channel details. - [Delete Channel](https://docs.agentscope.io/api-reference/channels/delete-channel.md): Delete a channel. - [Update Channel](https://docs.agentscope.io/api-reference/channels/update-channel.md): Update routing / session / config / enabled. - [Enable Channel](https://docs.agentscope.io/api-reference/channels/enable-channel.md): Enable a channel. - [Disable Channel](https://docs.agentscope.io/api-reference/channels/disable-channel.md): Disable a channel. - [Channel Status](https://docs.agentscope.io/api-reference/channels/channel-status.md): The channel's live connection status. - [List Channel Sessions](https://docs.agentscope.io/api-reference/channels/list-channel-sessions.md): Sessions this channel spawned, newest first. - [List Chat Ids](https://docs.agentscope.io/api-reference/channels/list-chat-ids.md): Known chats for routing config: platform list ∪ passively seen. #### 其他 - [常见问题](https://docs.agentscope.io/versions/2.0.7/zh/others/faq.md): AgentScope 2.0 常见问题 - [版本迁移](https://docs.agentscope.io/versions/2.0.7/zh/others/change-log.md): AgentScope 2.0 与 1.0 的核心区别 ### 2.0.6 #### 快速开始 - [AgentScope 2.0 是什么？](https://docs.agentscope.io/versions/2.0.6/zh/index.md): 安全、高效、灵活、完备 - [快速开始](https://docs.agentscope.io/versions/2.0.6/zh/quickstart.md): 快速上手 AgentScope 2.0 - [更新日志](https://docs.agentscope.io/versions/2.0.6/zh/release-notes.md): AgentScope 版本改动和更新日志。 #### 核心模块 - [消息与事件](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/message-and-event.md): 智能体通信，与前端流式数据传输 - [计划模式](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/plan.md): 为智能体提供结构化任务清单，用于规划、追踪并协调复杂工作 - [中间件](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/middleware.md): 在智能体生命周期的关键位置拦截并扩展行为 - [RAG](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/rag.md): 为智能体构建检索增强生成（RAG）能力。 - [长期记忆](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/long-term-memory.md): 基于智能体中间件实现的，跨会话长期记忆 ##### 智能体 - [概述](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/agent/overview.md): AgentScope 的核心抽象：无状态的推理-行动循环引擎 - [配置智能体](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/agent/configure-agent.md): 用模型、工具与配置对象组装一个智能体 - [运行智能体](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/agent/run-agent.md): 运行智能体，处理它的回复、上下文与状态 - [中断智能体](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/agent/interrupt-agent.md): 干净地停止运行中或暂停中的智能体，并从一致状态恢复 - [人机交互](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/agent/human-in-the-loop.md): 暂停以等待用户确认或外部执行，再通过结果事件恢复 ##### 模型 - [概述](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/model/overview.md): 通过凭证接入模型 API，并用模型卡片发现可用模型 - [大语言模型](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/model/llm.md): 创建并调用对话模型，也可以接入你自己的模型 API - [语音合成](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/model/tts.md): 将文本转换为语音，支持标准与实时两种合成模式 - [嵌入模型](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/model/embedding.md): 将文本与多媒体内容转换为向量，服务检索、RAG 与记忆 ##### 上下文管理 - [概述](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/context/overview.md): 管理智能体的工作记忆，让长任务稳定推进 - [感知环境](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/context/environment-awareness.md): 让智能体持续感知时间、任务与上下文用量的变化 - [压缩上下文](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/context/compress-context.md): 将上下文长度维护在预设的长度内 - [卸载上下文](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/context/offload-context.md): 持久化被移除的内容，供智能体按需回查 ##### 工具 - [概述](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/tool/overview.md): 通过 Toolkit 为智能体装配工具、MCP 服务与技能 - [Python 函数工具](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/tool/python-tool.md): 基于类或普通函数构建工具，并控制它们的执行方式 - [MCP](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/tool/mcp.md): 接入 MCP 服务并使用其工具 - [Skill](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/tool/skill.md): 用 Markdown 指令集拓展智能体能力 - [元工具](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/tool/manage-tools.md): 让智能体在运行时自主激活或停用工具组 ##### 权限系统 - [概述](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/permission-system/overview.md): 规则、模式与工具内置检查如何共同决定每一次工具调用 - [权限模式](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/permission-system/permission-mode.md): 根据智能体的部署方式选择合适的全局策略 - [权限规则](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/permission-system/permission-rule.md): 为特定工具与调用编写允许、拒绝和询问规则 - [工具内置检查](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/permission-system/tool-check.md): 工具在运行时对自身输入执行的安全分析 ##### 工作区 - [概述](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/workspace/overview.md): 为智能体提供可执行、可持久化的运行环境 - [运行工作区](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/workspace/run-workspace.md): 在任意后端上创建工作区，并接入智能体 - [管理资源](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/workspace/manage-resources.md): 在运行时添加、移除 MCP 服务与技能 - [MCP 网关](https://docs.agentscope.io/versions/2.0.6/zh/building-blocks/workspace/mcp-gateway.md): 沙箱类工作区如何把内部的 MCP 服务暴露给主机 #### 智能体即服务 - [架构](https://docs.agentscope.io/versions/2.0.6/zh/deploy/agent-service.md): 把智能体部署为多租户、多会话的 HTTP 服务 - [智能体团队](https://docs.agentscope.io/versions/2.0.6/zh/deploy/agent-team.md): Leader 智能体通过内置 team 工具派生并协调 worker 智能体 - [资源共享](https://docs.agentscope.io/versions/2.0.6/zh/deploy/sharing.md): 以团队，组织为单位共享 API 凭证、智能体与知识库 - [RAG 服务](https://docs.agentscope.io/versions/2.0.6/zh/deploy/rag.md): 一键式启动的多租户、分布式 RAG 服务 - [工作区管理](https://docs.agentscope.io/versions/2.0.6/zh/deploy/workspace-manager.md): 在服务中分配、管理智能体的运行环境（Workspace） ##### MCP 与技能中心 - [概览](https://docs.agentscope.io/versions/2.0.6/zh/deploy/hub/overview.md): 快速接入不同来源的 MCP 与技能中心。 - [MCP 中心](https://docs.agentscope.io/versions/2.0.6/zh/deploy/hub/mcp-hub.md): 让用户从一个来源安装 MCP 服务，并配置自己的凭证。 - [技能中心](https://docs.agentscope.io/versions/2.0.6/zh/deploy/hub/skill-hub.md): 让用户安装他人发布的技能，并装配给自己的智能体。 ##### 消息渠道 - [概览](https://docs.agentscope.io/versions/2.0.6/zh/deploy/channel/overview.md): 让 AgentScope 服务中的智能体入驻 IM 平台。 - [会话路由](https://docs.agentscope.io/versions/2.0.6/zh/deploy/channel/routing.md): 决定 IM 平台来的消息交给哪个智能体、进入哪个会话。 - [飞书](https://docs.agentscope.io/versions/2.0.6/zh/deploy/channel/feishu.md): 在飞书中与智能体服务里的智能体对话。 - [Discord](https://docs.agentscope.io/versions/2.0.6/zh/deploy/channel/discord.md): 在 Discord 中与智能体服务里的智能体对话。 - [自定义渠道](https://docs.agentscope.io/versions/2.0.6/zh/deploy/channel/custom.md): 实现 ChannelBase，把智能体接入内置之外的平台。 ##### API ###### agent - [[Deprecated] Legacy sectioned schema — use /schema/v2](https://docs.agentscope.io/api-reference/agent/[deprecated]-legacy-sectioned-schema-—-use-schemav2.md): Return the legacy sectioned JSON Schema fragments. - [Full AgentData JSON Schema for the agent form](https://docs.agentscope.io/api-reference/agent/full-agentdata-json-schema-for-the-agent-form.md): Return the full :class:`AgentData` JSON Schema. - [List all agents](https://docs.agentscope.io/api-reference/agent/list-all-agents.md): Return all agent records belonging to the authenticated user. - [Create a new agent](https://docs.agentscope.io/api-reference/agent/create-a-new-agent.md): Create and persist a new agent configuration. - [Delete an agent](https://docs.agentscope.io/api-reference/agent/delete-an-agent.md): Permanently delete an agent configuration. - [Update an agent](https://docs.agentscope.io/api-reference/agent/update-an-agent.md): Partially update an existing agent configuration. ###### chat - [Trigger a chat run (fire-and-forget)](https://docs.agentscope.io/api-reference/chat/trigger-a-chat-run-fire-and-forget.md): Trigger a chat run for the specified session. ###### credential - [List JSON schemas for all credential types](https://docs.agentscope.io/api-reference/credential/list-json-schemas-for-all-credential-types.md): Return JSON schemas for all registered credential types. - [List all credentials](https://docs.agentscope.io/api-reference/credential/list-all-credentials.md): Return all credential records belonging to the authenticated user. - [Create a new credential](https://docs.agentscope.io/api-reference/credential/create-a-new-credential.md): Store a new credential. - [Delete a credential](https://docs.agentscope.io/api-reference/credential/delete-a-credential.md): Permanently delete a credential. - [Update a credential](https://docs.agentscope.io/api-reference/credential/update-a-credential.md): Replace the payload of an existing credential. ###### health - [Report service liveness and per-component readiness](https://docs.agentscope.io/api-reference/health/report-service-liveness-and-per-component-readiness.md): Report whether the service is ready to serve requests. ###### hub - [List Mcp Hubs](https://docs.agentscope.io/api-reference/hub/list-mcp-hubs.md): Return every registered MCP hub. - [List Mcp Cards](https://docs.agentscope.io/api-reference/hub/list-mcp-cards.md): Browse or search one MCP hub's catalog. - [Get Mcp Card](https://docs.agentscope.io/api-reference/hub/get-mcp-card.md): Return one MCP card, including the inputs the user must fill. - [Install Mcp](https://docs.agentscope.io/api-reference/hub/install-mcp.md): Fill a card's template and add the result to the user's library. - [List Skill Hubs](https://docs.agentscope.io/api-reference/hub/list-skill-hubs.md): Return every registered skill hub. - [List Skill Cards](https://docs.agentscope.io/api-reference/hub/list-skill-cards.md): Browse or search one skill hub's catalog. - [Get Skill Card](https://docs.agentscope.io/api-reference/hub/get-skill-card.md): Return one skill card, including its ``SKILL.md`` body. - [Install Skill](https://docs.agentscope.io/api-reference/hub/install-skill.md): Add a skill card to the user's library. ###### knowledge_bases - [List embedding models compatible with the KB dimension policy](https://docs.agentscope.io/api-reference/knowledge_bases/list-embedding-models-compatible-with-the-kb-dimension-policy.md): List embedding models the user can pick at KB-creation time. - [JSON Schema for the KB middleware's tunable parameters](https://docs.agentscope.io/api-reference/knowledge_bases/json-schema-for-the-kb-middlewares-tunable-parameters.md): Return the parameter schema for :class:`agentscope.middleware.RAGMiddleware`. - [List file types the configured parsers can ingest](https://docs.agentscope.io/api-reference/knowledge_bases/list-file-types-the-configured-parsers-can-ingest.md): Advertise the union of media types and filename extensions every registered parser accepts. - [List the caller's knowledge bases](https://docs.agentscope.io/api-reference/knowledge_bases/list-the-callers-knowledge-bases.md): Return all knowledge bases owned by the authenticated user. - [Create a new knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/create-a-new-knowledge-base.md): Create a new knowledge base for the authenticated user. - [Delete a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-knowledge-base.md): Permanently delete a knowledge base. - [Update mutable fields on a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/update-mutable-fields-on-a-knowledge-base.md): Update mutable fields on a knowledge base. - [List documents registered in a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/list-documents-registered-in-a-knowledge-base.md): List every document registered against a knowledge base. - [Upload a document into a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/upload-a-document-into-a-knowledge-base.md): Register an uploaded document and dispatch it for indexing. - [Batch-query indexing status of one or more documents](https://docs.agentscope.io/api-reference/knowledge_bases/batch-query-indexing-status-of-one-or-more-documents.md): Return the current lifecycle state of a batch of documents. - [Delete a document from a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-document-from-a-knowledge-base.md): Remove a document and all its chunks from a knowledge base. - [Search a knowledge base by natural-language query](https://docs.agentscope.io/api-reference/knowledge_bases/search-a-knowledge-base-by-natural-language-query.md): Run a similarity search over a knowledge base. ###### mcp - [List Mcps](https://docs.agentscope.io/api-reference/mcp/list-mcps.md): Return every MCP the user has installed, ordered by name. - [Delete Mcp](https://docs.agentscope.io/api-reference/mcp/delete-mcp.md): Remove an MCP from the user's library. - [Update Mcp](https://docs.agentscope.io/api-reference/mcp/update-mcp.md): Rename, enable/disable, or re-key an installed MCP. ###### schedule - [List all schedules](https://docs.agentscope.io/api-reference/schedule/list-all-schedules.md): List all schedules owned by the current user. - [Create a new schedule](https://docs.agentscope.io/api-reference/schedule/create-a-new-schedule.md): Create a new schedule and register it with the scheduler. - [Delete a schedule](https://docs.agentscope.io/api-reference/schedule/delete-a-schedule.md): Permanently delete a schedule. - [Update a schedule](https://docs.agentscope.io/api-reference/schedule/update-a-schedule.md): Partially update a schedule. - [List execution sessions for a schedule](https://docs.agentscope.io/api-reference/schedule/list-execution-sessions-for-a-schedule.md): Return all sessions triggered by a given schedule. ###### sessions - [List sessions for an agent](https://docs.agentscope.io/api-reference/sessions/list-sessions-for-an-agent.md): Return all sessions for an agent as enriched :class:`SessionView` entries. - [Create a new session](https://docs.agentscope.io/api-reference/sessions/create-a-new-session.md): Create (or resume) a session for a given agent and workspace. - [Delete a session](https://docs.agentscope.io/api-reference/sessions/delete-a-session.md): Permanently delete a session and all its associated state. - [Update a session](https://docs.agentscope.io/api-reference/sessions/update-a-session.md): Update the model configuration of an existing session. - [Interrupt a running or HITL-parked chat run for a session](https://docs.agentscope.io/api-reference/sessions/interrupt-a-running-or-hitl-parked-chat-run-for-a-session.md): Request interruption of an in-progress reply for a session. - [List messages for a session](https://docs.agentscope.io/api-reference/sessions/list-messages-for-a-session.md): Return persisted messages for a session. - [Probe the session's high-level status](https://docs.agentscope.io/api-reference/sessions/probe-the-sessions-high-level-status.md): Return the unified :class:`SessionStatus` for a session. - [Subscribe to a session's event stream (SSE)](https://docs.agentscope.io/api-reference/sessions/subscribe-to-a-sessions-event-stream-sse.md): Subscribe to a session's live event stream. ###### skill - [List Skills](https://docs.agentscope.io/api-reference/skill/list-skills.md): Return every skill the user has installed, ordered by name. - [Get Skill](https://docs.agentscope.io/api-reference/skill/get-skill.md): Return one installed skill, including its ``SKILL.md`` body. - [Delete Skill](https://docs.agentscope.io/api-reference/skill/delete-skill.md): Remove a skill from the user's library. ###### workspace - [List Mcps](https://docs.agentscope.io/api-reference/workspace/list-mcps.md): Return all MCP clients with live tool list and health status. - [Add Mcp](https://docs.agentscope.io/api-reference/workspace/add-mcp.md): Add an MCP client to the session's workspace. - [Add Mcps From Library](https://docs.agentscope.io/api-reference/workspace/add-mcps-from-library.md): Put MCPs the user has already installed into this workspace. - [Remove Mcp](https://docs.agentscope.io/api-reference/workspace/remove-mcp.md): Remove an MCP client from the session's workspace by name. - [List Skills](https://docs.agentscope.io/api-reference/workspace/list-skills.md): Return all skills available in the session's workspace. - [Add Skill](https://docs.agentscope.io/api-reference/workspace/add-skill.md): Add a skill to the session's workspace from the given path. - [Upload Skill](https://docs.agentscope.io/api-reference/workspace/upload-skill.md): Install a skill from an uploaded folder. - [Add Skills From Library](https://docs.agentscope.io/api-reference/workspace/add-skills-from-library.md): Put skills the user has already installed into this workspace. - [Remove Skill](https://docs.agentscope.io/api-reference/workspace/remove-skill.md): Remove a skill from the session's workspace by name. - [List Workspace Directory](https://docs.agentscope.io/api-reference/workspace/list-workspace-directory.md): List one directory level, reachable from a session's workspace. - [Create Download Token](https://docs.agentscope.io/api-reference/workspace/create-download-token.md): Mint a short-lived token for a browser-native download. - [Read Workspace File](https://docs.agentscope.io/api-reference/workspace/read-workspace-file.md): Stream one file out of a session's workspace. ###### model - [List all candidate models under the given credential type](https://docs.agentscope.io/api-reference/model/list-all-candidate-models-under-the-given-credential-type.md): Return all candidate models under the given credential type. ###### tts-model - [List all candidate TTS models under the given credential type](https://docs.agentscope.io/api-reference/tts-model/list-all-candidate-tts-models-under-the-given-credential-type.md): Return all candidate TTS models under the given credential type. ###### embedding-model - [List all candidate embedding models under the given credential type](https://docs.agentscope.io/api-reference/embedding-model/list-all-candidate-embedding-models-under-the-given-credential-type.md): Return all candidate embedding models under the credential type. ###### channels - [List Channel Types](https://docs.agentscope.io/api-reference/channels/list-channel-types.md): List supported channel types with their JSON schemas. - [List Channels](https://docs.agentscope.io/api-reference/channels/list-channels.md): List channels owned by the current user. - [Create Channel](https://docs.agentscope.io/api-reference/channels/create-channel.md): Create a channel. - [Get Channel](https://docs.agentscope.io/api-reference/channels/get-channel.md): Get channel details. - [Delete Channel](https://docs.agentscope.io/api-reference/channels/delete-channel.md): Delete a channel. - [Update Channel](https://docs.agentscope.io/api-reference/channels/update-channel.md): Update routing / session / config / enabled. - [Enable Channel](https://docs.agentscope.io/api-reference/channels/enable-channel.md): Enable a channel. - [Disable Channel](https://docs.agentscope.io/api-reference/channels/disable-channel.md): Disable a channel. - [Channel Status](https://docs.agentscope.io/api-reference/channels/channel-status.md): The channel's live connection status. - [List Channel Sessions](https://docs.agentscope.io/api-reference/channels/list-channel-sessions.md): Sessions this channel spawned, newest first. - [List Chat Ids](https://docs.agentscope.io/api-reference/channels/list-chat-ids.md): Known chats for routing config: platform list ∪ passively seen. #### 其他 - [常见问题](https://docs.agentscope.io/versions/2.0.6/zh/others/faq.md): AgentScope 2.0 常见问题 - [版本迁移](https://docs.agentscope.io/versions/2.0.6/zh/others/change-log.md): AgentScope 2.0 与 1.0 的核心区别 ### 2.0.5 #### 快速开始 - [AgentScope 2.0 是什么？](https://docs.agentscope.io/versions/2.0.5/zh/index.md): 安全、高效、灵活、完备 - [快速开始](https://docs.agentscope.io/versions/2.0.5/zh/quickstart.md): 快速上手 AgentScope 2.0 - [更新日志](https://docs.agentscope.io/versions/2.0.5/zh/release-notes.md): AgentScope 版本改动和更新日志。 #### 核心模块 - [消息与事件](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/message-and-event.md): 智能体通信，与前端流式数据传输 - [计划模式](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/plan.md): 为智能体提供结构化任务清单，用于规划、追踪并协调复杂工作 - [中间件](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/middleware.md): 在智能体生命周期的关键位置拦截并扩展行为 - [RAG](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/rag.md): 为智能体构建检索增强生成（RAG）能力。 - [长期记忆](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/long-term-memory.md): 基于智能体中间件实现的，跨会话长期记忆 ##### 智能体 - [概述](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/agent/overview.md): AgentScope 的核心抽象：无状态的推理-行动循环引擎 - [配置智能体](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/agent/configure-agent.md): 用模型、工具与配置对象组装一个智能体 - [运行智能体](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/agent/run-agent.md): 运行智能体，处理它的回复、上下文与状态 - [中断智能体](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/agent/interrupt-agent.md): 干净地停止运行中或暂停中的智能体，并从一致状态恢复 - [人机交互](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/agent/human-in-the-loop.md): 暂停以等待用户确认或外部执行，再通过结果事件恢复 ##### 模型 - [概述](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/model/overview.md): 通过凭证接入模型 API，并用模型卡片发现可用模型 - [大语言模型](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/model/llm.md): 创建并调用对话模型，也可以接入你自己的模型 API - [语音合成](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/model/tts.md): 将文本转换为语音，支持标准与实时两种合成模式 - [嵌入模型](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/model/embedding.md): 将文本与多媒体内容转换为向量，服务检索、RAG 与记忆 ##### 上下文管理 - [概述](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/context/overview.md): 管理智能体的工作记忆，让长任务稳定推进 - [感知环境](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/context/environment-awareness.md): 让智能体持续感知时间、任务与上下文用量的变化 - [压缩上下文](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/context/compress-context.md): 将上下文长度维护在预设的长度内 - [卸载上下文](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/context/offload-context.md): 持久化被移除的内容，供智能体按需回查 ##### 工具 - [概述](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/tool/overview.md): 通过 Toolkit 为智能体装配工具、MCP 服务与技能 - [Python 函数工具](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/tool/python-tool.md): 基于类或普通函数构建工具，并控制它们的执行方式 - [MCP](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/tool/mcp.md): 接入 MCP 服务并使用其工具 - [Skill](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/tool/skill.md): 用 Markdown 指令集拓展智能体能力 - [元工具](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/tool/manage-tools.md): 让智能体在运行时自主激活或停用工具组 ##### 权限系统 - [概述](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/permission-system/overview.md): 规则、模式与工具内置检查如何共同决定每一次工具调用 - [权限模式](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/permission-system/permission-mode.md): 根据智能体的部署方式选择合适的全局策略 - [权限规则](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/permission-system/permission-rule.md): 为特定工具与调用编写允许、拒绝和询问规则 - [工具内置检查](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/permission-system/tool-check.md): 工具在运行时对自身输入执行的安全分析 ##### 工作区 - [概述](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/workspace/overview.md): 为智能体提供可执行、可持久化的运行环境 - [运行工作区](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/workspace/run-workspace.md): 在任意后端上创建工作区，并接入智能体 - [管理资源](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/workspace/manage-resources.md): 在运行时添加、移除 MCP 服务与技能 - [MCP 网关](https://docs.agentscope.io/versions/2.0.5/zh/building-blocks/workspace/mcp-gateway.md): 沙箱类工作区如何把内部的 MCP 服务暴露给主机 #### 智能体即服务 - [架构](https://docs.agentscope.io/versions/2.0.5/zh/deploy/agent-service.md): 把智能体部署为多租户、多会话的 HTTP 服务 - [智能体团队](https://docs.agentscope.io/versions/2.0.5/zh/deploy/agent-team.md): Leader 智能体通过内置 team 工具派生并协调 worker 智能体 - [资源共享](https://docs.agentscope.io/versions/2.0.5/zh/deploy/sharing.md): 以团队，组织为单位共享 API 凭证、智能体与知识库 - [RAG 服务](https://docs.agentscope.io/versions/2.0.5/zh/deploy/rag.md): 一键式启动的多租户、分布式 RAG 服务 - [工作区管理](https://docs.agentscope.io/versions/2.0.5/zh/deploy/workspace-manager.md): 在服务中分配、管理智能体的运行环境（Workspace） ##### API ###### agent - [[Deprecated] Legacy sectioned schema — use /schema/v2](https://docs.agentscope.io/api-reference/agent/[deprecated]-legacy-sectioned-schema-—-use-schemav2.md): Return the legacy sectioned JSON Schema fragments. - [Full AgentData JSON Schema for the agent form](https://docs.agentscope.io/api-reference/agent/full-agentdata-json-schema-for-the-agent-form.md): Return the full :class:`AgentData` JSON Schema. - [List all agents](https://docs.agentscope.io/api-reference/agent/list-all-agents.md): Return all agent records belonging to the authenticated user. - [Create a new agent](https://docs.agentscope.io/api-reference/agent/create-a-new-agent.md): Create and persist a new agent configuration. - [Delete an agent](https://docs.agentscope.io/api-reference/agent/delete-an-agent.md): Permanently delete an agent configuration. - [Update an agent](https://docs.agentscope.io/api-reference/agent/update-an-agent.md): Partially update an existing agent configuration. ###### chat - [Trigger a chat run (fire-and-forget)](https://docs.agentscope.io/api-reference/chat/trigger-a-chat-run-fire-and-forget.md): Trigger a chat run for the specified session. ###### credential - [List JSON schemas for all credential types](https://docs.agentscope.io/api-reference/credential/list-json-schemas-for-all-credential-types.md): Return JSON schemas for all registered credential types. - [List all credentials](https://docs.agentscope.io/api-reference/credential/list-all-credentials.md): Return all credential records belonging to the authenticated user. - [Create a new credential](https://docs.agentscope.io/api-reference/credential/create-a-new-credential.md): Store a new credential. - [Delete a credential](https://docs.agentscope.io/api-reference/credential/delete-a-credential.md): Permanently delete a credential. - [Update a credential](https://docs.agentscope.io/api-reference/credential/update-a-credential.md): Replace the payload of an existing credential. ###### knowledge_bases - [List embedding models compatible with the KB dimension policy](https://docs.agentscope.io/api-reference/knowledge_bases/list-embedding-models-compatible-with-the-kb-dimension-policy.md): List embedding models the user can pick at KB-creation time. - [JSON Schema for the KB middleware's tunable parameters](https://docs.agentscope.io/api-reference/knowledge_bases/json-schema-for-the-kb-middlewares-tunable-parameters.md): Return the parameter schema for :class:`agentscope.middleware.RAGMiddleware`. - [List file types the configured parsers can ingest](https://docs.agentscope.io/api-reference/knowledge_bases/list-file-types-the-configured-parsers-can-ingest.md): Advertise the union of media types and filename extensions every registered parser accepts. - [List the caller's knowledge bases](https://docs.agentscope.io/api-reference/knowledge_bases/list-the-callers-knowledge-bases.md): Return all knowledge bases owned by the authenticated user. - [Create a new knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/create-a-new-knowledge-base.md): Create a new knowledge base for the authenticated user. - [Delete a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-knowledge-base.md): Permanently delete a knowledge base. - [Update mutable fields on a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/update-mutable-fields-on-a-knowledge-base.md): Update mutable fields on a knowledge base. - [List documents registered in a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/list-documents-registered-in-a-knowledge-base.md): List every document registered against a knowledge base. - [Upload a document into a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/upload-a-document-into-a-knowledge-base.md): Register an uploaded document and dispatch it for indexing. - [Batch-query indexing status of one or more documents](https://docs.agentscope.io/api-reference/knowledge_bases/batch-query-indexing-status-of-one-or-more-documents.md): Return the current lifecycle state of a batch of documents. - [Delete a document from a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-document-from-a-knowledge-base.md): Remove a document and all its chunks from a knowledge base. - [Search a knowledge base by natural-language query](https://docs.agentscope.io/api-reference/knowledge_bases/search-a-knowledge-base-by-natural-language-query.md): Run a similarity search over a knowledge base. ###### schedule - [List all schedules](https://docs.agentscope.io/api-reference/schedule/list-all-schedules.md): List all schedules owned by the current user. - [Create a new schedule](https://docs.agentscope.io/api-reference/schedule/create-a-new-schedule.md): Create a new schedule and register it with the scheduler. - [Delete a schedule](https://docs.agentscope.io/api-reference/schedule/delete-a-schedule.md): Permanently delete a schedule. - [Update a schedule](https://docs.agentscope.io/api-reference/schedule/update-a-schedule.md): Partially update a schedule. - [List execution sessions for a schedule](https://docs.agentscope.io/api-reference/schedule/list-execution-sessions-for-a-schedule.md): Return all sessions triggered by a given schedule. ###### sessions - [List sessions for an agent](https://docs.agentscope.io/api-reference/sessions/list-sessions-for-an-agent.md): Return all sessions for an agent as enriched :class:`SessionView` entries. - [Create a new session](https://docs.agentscope.io/api-reference/sessions/create-a-new-session.md): Create (or resume) a session for a given agent and workspace. - [Delete a session](https://docs.agentscope.io/api-reference/sessions/delete-a-session.md): Permanently delete a session and all its associated state. - [Update a session](https://docs.agentscope.io/api-reference/sessions/update-a-session.md): Update the model configuration of an existing session. - [Interrupt a running or HITL-parked chat run for a session](https://docs.agentscope.io/api-reference/sessions/interrupt-a-running-or-hitl-parked-chat-run-for-a-session.md): Request interruption of an in-progress reply for a session. - [List messages for a session](https://docs.agentscope.io/api-reference/sessions/list-messages-for-a-session.md): Return persisted messages for a session. - [Probe the session's high-level status](https://docs.agentscope.io/api-reference/sessions/probe-the-sessions-high-level-status.md): Return the unified :class:`SessionStatus` for a session. - [Subscribe to a session's event stream (SSE)](https://docs.agentscope.io/api-reference/sessions/subscribe-to-a-sessions-event-stream-sse.md): Subscribe to a session's live event stream. ###### workspace - [List Mcps](https://docs.agentscope.io/api-reference/workspace/list-mcps.md): Return all MCP clients with live tool list and health status. - [Add Mcp](https://docs.agentscope.io/api-reference/workspace/add-mcp.md): Add an MCP client to the session's workspace. - [Remove Mcp](https://docs.agentscope.io/api-reference/workspace/remove-mcp.md): Remove an MCP client from the session's workspace by name. - [List Skills](https://docs.agentscope.io/api-reference/workspace/list-skills.md): Return all skills available in the session's workspace. - [Add Skill](https://docs.agentscope.io/api-reference/workspace/add-skill.md): Add a skill to the session's workspace from the given path. - [Remove Skill](https://docs.agentscope.io/api-reference/workspace/remove-skill.md): Remove a skill from the session's workspace by name. ###### model - [List all candidate models under the given credential type](https://docs.agentscope.io/api-reference/model/list-all-candidate-models-under-the-given-credential-type.md): Return all candidate models under the given credential type. ###### tts-model - [List all candidate TTS models under the given credential type](https://docs.agentscope.io/api-reference/tts-model/list-all-candidate-tts-models-under-the-given-credential-type.md): Return all candidate TTS models under the given credential type. #### 其他 - [常见问题](https://docs.agentscope.io/versions/2.0.5/zh/others/faq.md): AgentScope 2.0 常见问题 - [版本迁移](https://docs.agentscope.io/versions/2.0.5/zh/others/change-log.md): AgentScope 2.0 与 1.0 的核心区别 ### 2.0.4 #### 快速开始 - [AgentScope 2.0 是什么？](https://docs.agentscope.io/versions/2.0.4/zh/index.md): 安全、高效、灵活、完备 - [快速开始](https://docs.agentscope.io/versions/2.0.4/zh/quickstart.md): 快速上手 AgentScope 2.0 - [更新日志](https://docs.agentscope.io/versions/2.0.4/zh/release-notes.md): AgentScope 版本改动和更新日志。 #### 核心模块 - [消息与事件](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/message-and-event.md): 智能体通信，与前端流式数据传输 - [智能体](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/agent.md): 了解如何在 AgentScope v2.0 中定义和配置智能体 - [模型](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/model.md): 驱动智能体的 LLM、TTS、Embedding 与 Realtime 模型 - [上下文管理](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/context.md): 管理智能体的上下文窗口，让长任务稳定运行 - [工具](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/tool.md): 定义、注册并管理智能体可调用的能力 - [计划模式](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/plan.md): 为智能体提供结构化任务清单，用于规划、追踪并协调复杂工作 - [权限系统](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/permission-system.md): 精细控制 agent 可以执行哪些 tool、何时执行 - [中间件](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/middleware.md): 在智能体生命周期的关键位置拦截并扩展行为 - [RAG](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/rag.md): 为智能体构建检索增强生成（RAG）能力。 - [长期记忆](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/long-term-memory.md): 基于智能体中间件实现的，跨会话长期记忆 - [工作区](https://docs.agentscope.io/versions/2.0.4/zh/building-blocks/workspace.md): 为 agent 提供工具、skill 与上下文 offload 的执行环境 #### 智能体即服务 - [架构](https://docs.agentscope.io/versions/2.0.4/zh/deploy/agent-service.md): 把智能体部署为多租户、多会话的 HTTP 服务 - [智能体团队](https://docs.agentscope.io/versions/2.0.4/zh/deploy/agent-team.md): Leader 智能体通过内置 team 工具派生并协调 worker 智能体 - [RAG 服务](https://docs.agentscope.io/versions/2.0.4/zh/deploy/rag.md): 一键式启动的多租户、分布式 RAG 服务 ##### API ###### agent - [[Deprecated] Legacy sectioned schema — use /schema/v2](https://docs.agentscope.io/api-reference/agent/[deprecated]-legacy-sectioned-schema-—-use-schemav2.md): Return the legacy sectioned JSON Schema fragments. - [Full AgentData JSON Schema for the agent form](https://docs.agentscope.io/api-reference/agent/full-agentdata-json-schema-for-the-agent-form.md): Return the full :class:`AgentData` JSON Schema. - [List all agents](https://docs.agentscope.io/api-reference/agent/list-all-agents.md): Return all agent records belonging to the authenticated user. - [Create a new agent](https://docs.agentscope.io/api-reference/agent/create-a-new-agent.md): Create and persist a new agent configuration. - [Delete an agent](https://docs.agentscope.io/api-reference/agent/delete-an-agent.md): Permanently delete an agent configuration. - [Update an agent](https://docs.agentscope.io/api-reference/agent/update-an-agent.md): Partially update an existing agent configuration. ###### chat - [Trigger a chat run (fire-and-forget)](https://docs.agentscope.io/api-reference/chat/trigger-a-chat-run-fire-and-forget.md): Trigger a chat run for the specified session. ###### credential - [List JSON schemas for all credential types](https://docs.agentscope.io/api-reference/credential/list-json-schemas-for-all-credential-types.md): Return JSON schemas for all registered credential types. - [List all credentials](https://docs.agentscope.io/api-reference/credential/list-all-credentials.md): Return all credential records belonging to the authenticated user. - [Create a new credential](https://docs.agentscope.io/api-reference/credential/create-a-new-credential.md): Store a new credential. - [Delete a credential](https://docs.agentscope.io/api-reference/credential/delete-a-credential.md): Permanently delete a credential. - [Update a credential](https://docs.agentscope.io/api-reference/credential/update-a-credential.md): Replace the payload of an existing credential. ###### knowledge_bases - [List embedding models compatible with the KB dimension policy](https://docs.agentscope.io/api-reference/knowledge_bases/list-embedding-models-compatible-with-the-kb-dimension-policy.md): List embedding models the user can pick at KB-creation time. - [JSON Schema for the KB middleware's tunable parameters](https://docs.agentscope.io/api-reference/knowledge_bases/json-schema-for-the-kb-middlewares-tunable-parameters.md): Return the parameter schema for :class:`agentscope.middleware.RAGMiddleware`. - [List file types the configured parsers can ingest](https://docs.agentscope.io/api-reference/knowledge_bases/list-file-types-the-configured-parsers-can-ingest.md): Advertise the union of media types and filename extensions every registered parser accepts. - [List the caller's knowledge bases](https://docs.agentscope.io/api-reference/knowledge_bases/list-the-callers-knowledge-bases.md): Return all knowledge bases owned by the authenticated user. - [Create a new knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/create-a-new-knowledge-base.md): Create a new knowledge base for the authenticated user. - [Delete a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-knowledge-base.md): Permanently delete a knowledge base. - [Update mutable fields on a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/update-mutable-fields-on-a-knowledge-base.md): Update mutable fields on a knowledge base. - [List documents registered in a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/list-documents-registered-in-a-knowledge-base.md): List every document registered against a knowledge base. - [Upload a document into a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/upload-a-document-into-a-knowledge-base.md): Register an uploaded document and dispatch it for indexing. - [Batch-query indexing status of one or more documents](https://docs.agentscope.io/api-reference/knowledge_bases/batch-query-indexing-status-of-one-or-more-documents.md): Return the current lifecycle state of a batch of documents. - [Delete a document from a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-document-from-a-knowledge-base.md): Remove a document and all its chunks from a knowledge base. - [Search a knowledge base by natural-language query](https://docs.agentscope.io/api-reference/knowledge_bases/search-a-knowledge-base-by-natural-language-query.md): Run a similarity search over a knowledge base. ###### schedule - [List all schedules](https://docs.agentscope.io/api-reference/schedule/list-all-schedules.md): List all schedules owned by the current user. - [Create a new schedule](https://docs.agentscope.io/api-reference/schedule/create-a-new-schedule.md): Create a new schedule and register it with the scheduler. - [Delete a schedule](https://docs.agentscope.io/api-reference/schedule/delete-a-schedule.md): Permanently delete a schedule. - [Update a schedule](https://docs.agentscope.io/api-reference/schedule/update-a-schedule.md): Partially update a schedule. - [List execution sessions for a schedule](https://docs.agentscope.io/api-reference/schedule/list-execution-sessions-for-a-schedule.md): Return all sessions triggered by a given schedule. ###### sessions - [List sessions for an agent](https://docs.agentscope.io/api-reference/sessions/list-sessions-for-an-agent.md): Return all sessions for an agent as enriched :class:`SessionView` entries. - [Create a new session](https://docs.agentscope.io/api-reference/sessions/create-a-new-session.md): Create (or resume) a session for a given agent and workspace. - [Delete a session](https://docs.agentscope.io/api-reference/sessions/delete-a-session.md): Permanently delete a session and all its associated state. - [Update a session](https://docs.agentscope.io/api-reference/sessions/update-a-session.md): Update the model configuration of an existing session. - [Interrupt a running or HITL-parked chat run for a session](https://docs.agentscope.io/api-reference/sessions/interrupt-a-running-or-hitl-parked-chat-run-for-a-session.md): Request interruption of an in-progress reply for a session. - [List messages for a session](https://docs.agentscope.io/api-reference/sessions/list-messages-for-a-session.md): Return persisted messages for a session. - [Probe the session's high-level status](https://docs.agentscope.io/api-reference/sessions/probe-the-sessions-high-level-status.md): Return the unified :class:`SessionStatus` for a session. - [Subscribe to a session's event stream (SSE)](https://docs.agentscope.io/api-reference/sessions/subscribe-to-a-sessions-event-stream-sse.md): Subscribe to a session's live event stream. ###### workspace - [List Mcps](https://docs.agentscope.io/api-reference/workspace/list-mcps.md): Return all MCP clients with live tool list and health status. - [Add Mcp](https://docs.agentscope.io/api-reference/workspace/add-mcp.md): Add an MCP client to the session's workspace. - [Remove Mcp](https://docs.agentscope.io/api-reference/workspace/remove-mcp.md): Remove an MCP client from the session's workspace by name. - [List Skills](https://docs.agentscope.io/api-reference/workspace/list-skills.md): Return all skills available in the session's workspace. - [Add Skill](https://docs.agentscope.io/api-reference/workspace/add-skill.md): Add a skill to the session's workspace from the given path. - [Remove Skill](https://docs.agentscope.io/api-reference/workspace/remove-skill.md): Remove a skill from the session's workspace by name. ###### model - [List all candidate models under the given credential type](https://docs.agentscope.io/api-reference/model/list-all-candidate-models-under-the-given-credential-type.md): Return all candidate models under the given credential type. ###### tts-model - [List all candidate TTS models under the given credential type](https://docs.agentscope.io/api-reference/tts-model/list-all-candidate-tts-models-under-the-given-credential-type.md): Return all candidate TTS models under the given credential type. #### 其他 - [常见问题](https://docs.agentscope.io/versions/2.0.4/zh/others/faq.md): AgentScope 2.0 常见问题 - [版本迁移](https://docs.agentscope.io/versions/2.0.4/zh/others/change-log.md): AgentScope 2.0 与 1.0 的核心区别 ### 2.0.3 #### 快速开始 - [AgentScope 2.0 是什么？](https://docs.agentscope.io/versions/2.0.3/zh/index.md): 安全、高效、灵活、完备 - [快速开始](https://docs.agentscope.io/versions/2.0.3/zh/quickstart.md): 快速上手 AgentScope 2.0 - [更新日志](https://docs.agentscope.io/versions/2.0.3/zh/release-notes.md): AgentScope 版本改动和更新日志。 #### 核心模块 - [消息与事件](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/message-and-event.md): 智能体通信，与前端流式数据传输 - [智能体](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/agent.md): 了解如何在 AgentScope v2.0 中定义和配置智能体 - [模型](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/model.md): 驱动智能体的 LLM、TTS、Embedding 与 Realtime 模型 - [上下文管理](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/context.md): 管理 agent 的上下文窗口，让长任务稳定运行 - [工具](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/tool.md): 定义、注册并管理 agent 可调用的能力 - [计划模式](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/plan.md): 为智能体提供结构化任务清单，用于规划、追踪并协调复杂工作 - [权限系统](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/permission-system.md): 精细控制 agent 可以执行哪些 tool、何时执行 - [中间件](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/middleware.md): 在 agent 生命周期的关键位置拦截并扩展行为 - [RAG](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/rag.md): 为智能体构建检索增强生成（RAG）能力。 - [长期记忆](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/long-term-memory.md): 通过基于中间件的长期记忆后端，让知识在多个会话间持久保留 - [工作区](https://docs.agentscope.io/versions/2.0.3/zh/building-blocks/workspace.md): 为 agent 提供工具、skill 与上下文 offload 的执行环境 #### 智能体即服务 - [架构](https://docs.agentscope.io/versions/2.0.3/zh/deploy/agent-service.md): 把智能体部署为多租户、多会话的 HTTP 服务 - [智能体团队](https://docs.agentscope.io/versions/2.0.3/zh/deploy/agent-team.md): Leader 智能体通过内置 team 工具派生并协调 worker 智能体 - [RAG 服务](https://docs.agentscope.io/versions/2.0.3/zh/deploy/rag.md): 一键式启动的多租户、分布式 RAG 服务 ##### API ###### agent - [Get JSON Schema fragments for the agent form](https://docs.agentscope.io/api-reference/agent/get-json-schema-fragments-for-the-agent-form.md): Return the JSON Schema fragments used by the frontend to render the agent create / edit forms. - [List all agents](https://docs.agentscope.io/api-reference/agent/list-all-agents.md): Return all agent records belonging to the authenticated user. - [Create a new agent](https://docs.agentscope.io/api-reference/agent/create-a-new-agent.md): Create and persist a new agent configuration. - [Delete an agent](https://docs.agentscope.io/api-reference/agent/delete-an-agent.md): Permanently delete an agent configuration. - [Update an agent](https://docs.agentscope.io/api-reference/agent/update-an-agent.md): Partially update an existing agent configuration. ###### chat - [Trigger a chat run (fire-and-forget)](https://docs.agentscope.io/api-reference/chat/trigger-a-chat-run-fire-and-forget.md): Trigger a chat run for the specified session. ###### credential - [List JSON schemas for all credential types](https://docs.agentscope.io/api-reference/credential/list-json-schemas-for-all-credential-types.md): Return JSON schemas for all registered credential types. - [List all credentials](https://docs.agentscope.io/api-reference/credential/list-all-credentials.md): Return all credential records belonging to the authenticated user. - [Create a new credential](https://docs.agentscope.io/api-reference/credential/create-a-new-credential.md): Store a new credential. - [Delete a credential](https://docs.agentscope.io/api-reference/credential/delete-a-credential.md): Permanently delete a credential. - [Update a credential](https://docs.agentscope.io/api-reference/credential/update-a-credential.md): Replace the payload of an existing credential. ###### knowledge_bases - [List embedding models compatible with the KB dimension policy](https://docs.agentscope.io/api-reference/knowledge_bases/list-embedding-models-compatible-with-the-kb-dimension-policy.md): List embedding models the user can pick at KB-creation time. - [JSON Schema for the KB middleware's tunable parameters](https://docs.agentscope.io/api-reference/knowledge_bases/json-schema-for-the-kb-middlewares-tunable-parameters.md): Return the parameter schema for :class:`agentscope.middleware.RAGMiddleware`. - [List file types the configured parsers can ingest](https://docs.agentscope.io/api-reference/knowledge_bases/list-file-types-the-configured-parsers-can-ingest.md): Advertise the union of media types and filename extensions every registered parser accepts. - [List the caller's knowledge bases](https://docs.agentscope.io/api-reference/knowledge_bases/list-the-callers-knowledge-bases.md): Return all knowledge bases owned by the authenticated user. - [Create a new knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/create-a-new-knowledge-base.md): Create a new knowledge base for the authenticated user. - [Delete a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-knowledge-base.md): Permanently delete a knowledge base. - [Update mutable fields on a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/update-mutable-fields-on-a-knowledge-base.md): Update mutable fields on a knowledge base. - [List documents registered in a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/list-documents-registered-in-a-knowledge-base.md): List every document registered against a knowledge base. - [Upload a document into a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/upload-a-document-into-a-knowledge-base.md): Register an uploaded document and dispatch it for indexing. - [Batch-query indexing status of one or more documents](https://docs.agentscope.io/api-reference/knowledge_bases/batch-query-indexing-status-of-one-or-more-documents.md): Return the current lifecycle state of a batch of documents. - [Delete a document from a knowledge base](https://docs.agentscope.io/api-reference/knowledge_bases/delete-a-document-from-a-knowledge-base.md): Remove a document and all its chunks from a knowledge base. - [Search a knowledge base by natural-language query](https://docs.agentscope.io/api-reference/knowledge_bases/search-a-knowledge-base-by-natural-language-query.md): Run a similarity search over a knowledge base. ###### schedule - [List all schedules](https://docs.agentscope.io/api-reference/schedule/list-all-schedules.md): List all schedules owned by the current user. - [Create a new schedule](https://docs.agentscope.io/api-reference/schedule/create-a-new-schedule.md): Create a new schedule and register it with the scheduler. - [Delete a schedule](https://docs.agentscope.io/api-reference/schedule/delete-a-schedule.md): Permanently delete a schedule. - [Update a schedule](https://docs.agentscope.io/api-reference/schedule/update-a-schedule.md): Partially update a schedule. - [List execution sessions for a schedule](https://docs.agentscope.io/api-reference/schedule/list-execution-sessions-for-a-schedule.md): Return all sessions triggered by a given schedule. ###### sessions - [List sessions for an agent](https://docs.agentscope.io/api-reference/sessions/list-sessions-for-an-agent.md): Return all sessions for an agent as enriched :class:`SessionView` entries. - [Create a new session](https://docs.agentscope.io/api-reference/sessions/create-a-new-session.md): Create (or resume) a session for a given agent and workspace. - [Delete a session](https://docs.agentscope.io/api-reference/sessions/delete-a-session.md): Permanently delete a session and all its associated state. - [Update a session](https://docs.agentscope.io/api-reference/sessions/update-a-session.md): Update the model configuration of an existing session. - [List messages for a session](https://docs.agentscope.io/api-reference/sessions/list-messages-for-a-session.md): Return persisted messages for a session. - [Subscribe to a session's event stream (SSE)](https://docs.agentscope.io/api-reference/sessions/subscribe-to-a-sessions-event-stream-sse.md): Subscribe to a session's live event stream. ###### workspace - [List Mcps](https://docs.agentscope.io/api-reference/workspace/list-mcps.md): Return all MCP clients with live tool list and health status. - [Add Mcp](https://docs.agentscope.io/api-reference/workspace/add-mcp.md): Add an MCP client to the session's workspace. - [Remove Mcp](https://docs.agentscope.io/api-reference/workspace/remove-mcp.md): Remove an MCP client from the session's workspace by name. - [List Skills](https://docs.agentscope.io/api-reference/workspace/list-skills.md): Return all skills available in the session's workspace. - [Add Skill](https://docs.agentscope.io/api-reference/workspace/add-skill.md): Add a skill to the session's workspace from the given path. - [Remove Skill](https://docs.agentscope.io/api-reference/workspace/remove-skill.md): Remove a skill from the session's workspace by name. ###### model - [List all candidate models under the given credential type](https://docs.agentscope.io/api-reference/model/list-all-candidate-models-under-the-given-credential-type.md): Return all candidate models under the given credential type. ###### tts-model - [List all candidate TTS models under the given credential type](https://docs.agentscope.io/api-reference/tts-model/list-all-candidate-tts-models-under-the-given-credential-type.md): Return all candidate TTS models under the given credential type. #### 其他 - [常见问题](https://docs.agentscope.io/versions/2.0.3/zh/others/faq.md): AgentScope 2.0 常见问题 - [版本迁移](https://docs.agentscope.io/versions/2.0.3/zh/others/change-log.md): AgentScope 2.0 与 1.0 的核心区别 ### 2.0.2 #### 快速开始 - [AgentScope 2.0 是什么？](https://docs.agentscope.io/versions/2.0.2/zh/index.md): 更安全、更高效、更灵活、更完备 - [快速开始](https://docs.agentscope.io/versions/2.0.2/zh/quickstart.md): 快速上手 AgentScope 2.0 - [Changelog](https://docs.agentscope.io/versions/2.0.2/zh/change-log.md): AgentScope 2.0 与 1.0 的核心区别 #### 核心模块 - [消息与事件](https://docs.agentscope.io/versions/2.0.2/zh/building-blocks/message-and-event.md): 智能体通信，与前端流式数据传输 - [智能体](https://docs.agentscope.io/versions/2.0.2/zh/building-blocks/agent.md): 了解如何在 AgentScope v2.0 中定义和配置智能体 - [模型](https://docs.agentscope.io/versions/2.0.2/zh/building-blocks/model.md): 在 AgentScope 中配置并连接 LLM 模型提供商 - [上下文管理](https://docs.agentscope.io/versions/2.0.2/zh/building-blocks/context.md): 管理 agent 的上下文窗口，让长任务稳定运行 - [工具](https://docs.agentscope.io/versions/2.0.2/zh/building-blocks/tool.md): 定义、注册并管理 agent 可调用的能力 - [权限系统](https://docs.agentscope.io/versions/2.0.2/zh/building-blocks/permission-system.md): 精细控制 agent 可以执行哪些 tool、何时执行 - [中间件](https://docs.agentscope.io/versions/2.0.2/zh/building-blocks/middleware.md): 在 agent 生命周期的关键位置拦截并扩展行为 - [工作区](https://docs.agentscope.io/versions/2.0.2/zh/building-blocks/workspace.md): 为 agent 提供工具、skill 与上下文 offload 的执行环境 #### 部署 - [智能体服务](https://docs.agentscope.io/versions/2.0.2/zh/deploy/agent-service.md): 把智能体部署为多租户、多会话的 HTTP 服务 - [智能体团队](https://docs.agentscope.io/versions/2.0.2/zh/deploy/agent-team.md): Leader 智能体通过内置 team 工具派生并协调 worker 智能体 ##### API ###### agent - [Get JSON Schema fragments for the agent form](https://docs.agentscope.io/api-reference/agent/get-json-schema-fragments-for-the-agent-form.md): Return the JSON Schema fragments used by the frontend to render the agent create / edit forms. - [List all agents](https://docs.agentscope.io/api-reference/agent/list-all-agents.md): Return all agent records belonging to the authenticated user. - [Create a new agent](https://docs.agentscope.io/api-reference/agent/create-a-new-agent.md): Create and persist a new agent configuration. - [Delete an agent](https://docs.agentscope.io/api-reference/agent/delete-an-agent.md): Permanently delete an agent configuration. - [Update an agent](https://docs.agentscope.io/api-reference/agent/update-an-agent.md): Partially update an existing agent configuration. ###### chat - [Trigger a chat run (fire-and-forget)](https://docs.agentscope.io/api-reference/chat/trigger-a-chat-run-fire-and-forget.md): Trigger a chat run for the specified session. ###### credential - [List JSON schemas for all credential types](https://docs.agentscope.io/api-reference/credential/list-json-schemas-for-all-credential-types.md): Return JSON schemas for all registered credential types. - [List all credentials](https://docs.agentscope.io/api-reference/credential/list-all-credentials.md): Return all credential records belonging to the authenticated user. - [Create a new credential](https://docs.agentscope.io/api-reference/credential/create-a-new-credential.md): Store a new credential. - [Delete a credential](https://docs.agentscope.io/api-reference/credential/delete-a-credential.md): Permanently delete a credential. - [Update a credential](https://docs.agentscope.io/api-reference/credential/update-a-credential.md): Replace the payload of an existing credential. ###### schedule - [List all schedules](https://docs.agentscope.io/api-reference/schedule/list-all-schedules.md): List all schedules owned by the current user. - [Create a new schedule](https://docs.agentscope.io/api-reference/schedule/create-a-new-schedule.md): Create a new schedule and register it with the scheduler. - [Delete a schedule](https://docs.agentscope.io/api-reference/schedule/delete-a-schedule.md): Permanently delete a schedule. - [Update a schedule](https://docs.agentscope.io/api-reference/schedule/update-a-schedule.md): Partially update a schedule. - [List execution sessions for a schedule](https://docs.agentscope.io/api-reference/schedule/list-execution-sessions-for-a-schedule.md): Return all sessions triggered by a given schedule. ###### sessions - [List sessions for an agent](https://docs.agentscope.io/api-reference/sessions/list-sessions-for-an-agent.md): Return all sessions for an agent as enriched :class:`SessionView` entries. - [Create a new session](https://docs.agentscope.io/api-reference/sessions/create-a-new-session.md): Create (or resume) a session for a given agent and workspace. - [Delete a session](https://docs.agentscope.io/api-reference/sessions/delete-a-session.md): Permanently delete a session and all its associated state. - [Update a session](https://docs.agentscope.io/api-reference/sessions/update-a-session.md): Update the model configuration of an existing session. - [List messages for a session](https://docs.agentscope.io/api-reference/sessions/list-messages-for-a-session.md): Return persisted messages for a session. - [Subscribe to a session's event stream (SSE)](https://docs.agentscope.io/api-reference/sessions/subscribe-to-a-sessions-event-stream-sse.md): Subscribe to a session's live event stream. ###### workspace - [List Mcps](https://docs.agentscope.io/api-reference/workspace/list-mcps.md): Return all MCP clients with live tool list and health status. - [Add Mcp](https://docs.agentscope.io/api-reference/workspace/add-mcp.md): Add an MCP client to the session's workspace. - [Remove Mcp](https://docs.agentscope.io/api-reference/workspace/remove-mcp.md): Remove an MCP client from the session's workspace by name. - [List Skills](https://docs.agentscope.io/api-reference/workspace/list-skills.md): Return all skills available in the session's workspace. - [Add Skill](https://docs.agentscope.io/api-reference/workspace/add-skill.md): Add a skill to the session's workspace from the given path. - [Remove Skill](https://docs.agentscope.io/api-reference/workspace/remove-skill.md): Remove a skill from the session's workspace by name. ###### model - [List all candidate models under the given credential type](https://docs.agentscope.io/api-reference/model/list-all-candidate-models-under-the-given-credential-type.md): Return all candidate models under the given credential type. #### 其他 - [FAQ](https://docs.agentscope.io/versions/2.0.2/zh/others/faq.md): AgentScope v2.0 常见问题 ## OpenAPI Specs - [openapi](/versions/2.0.4/en/deploy/openapi.json) - [openapi](/versions/2.0.2/en/deploy/openapi.json) - [openapi](/versions/2.0.6/en/deploy/openapi.json) - [openapi](/versions/2.0.3/en/deploy/openapi.json)