# OpenCode > 全部文档的索引见 [llms.txt](https://ark.volcengine.com/llms.txt)；在任一文档页面地址后追加 `.md` 可获取该页的 Markdown 版本。 本文介绍如何配置方舟 Agent Plan 企业版到 OpenCode 中使用。 # 一、前提条件 * 需由管理员账号完成以下操作后，子账号方可配置并使用 AI 工具： 1. 购买方舟 Agent Plan 企业版套餐：[一、购买 Agent Plan 企业版](/docs/agent-plan-enterprise-get-started#d061dee7)。 2. 为子账号分配席位：[二、分配席位](/docs/agent-plan-enterprise-get-started#163f6c67)。 # 二、安装 OpenCode 前提条件：安装 [Node.js 18 或更新版本](https://nodejs.org/en/download/)。 在命令行界面，执行以下命令安装 OpenCode。 ```Bash npm install -g opencode-ai ``` 安装结束后，执行以下命令查看安装结果，若显示版本号则安装成功。 ```Bash opencode --version ``` # 三、配置 OpenCode 1. 创建并打开 OpenCode 的配置文件。文件路径因系统而异，具体操作如下： **选项：macOS/Linux** macOS/Linux 系统 OpenCode 配置文件路径：`~/.config/opencode/opencode.json`。 1. 如果在主目录下没有`.config/opencode`目录，执行以下命令创建目录。 ```Bash mkdir -p ~/.config/opencode ``` 2. 创建并打开配置文件。 ```Bash nano ~/.config/opencode/opencode.json ``` **选项：Windows** Windows 系统 OpenCode 配置文件路径：`%USERPROFILE%\.config\opencode\opencode.json`。以 CMD 命令行方式为例，操作如下。 1. 如果当前用户目录下没有`.config\opencode`目录，执行以下命令创建目录。 ```Bash if not exist "%USERPROFILE%\.config\opencode" mkdir "%USERPROFILE%\.config\opencode" ``` 2. 创建并打开配置文件。 ```Bash notepad "%USERPROFILE%\.config\opencode\opencode.json" ``` 2. 编辑 `opencode.json`，需关注的配置信息如下： * ``：替换为您自己的 [专属 API Key](https://ark.volcengine.com/region:cn-beijing/subscription/agent-plan-enterprise?agentMode=close)。 ![image-20260909-103103-932.png](https://arkdocs.tos-cn-beijing.volces.com/images/agent-plan/agent-plan-enterprise-api-key.png) * `model`：见 [支持模型及 Harness](/docs/agent-plan-enterprise-plan-overview#3a2d43d5)，需配置文本生成模型。 Agent Plan 兼容 OpenAI 接口协议，支持 Responses API、Chat API。推荐使用 Responses API 的配置，推理效果更好。 支持的两类 API 仅在 npm 配置上不同： * Responses API 配置：`"npm": "@ai-sdk/openai"` * Chat API 配置：`"npm": "@ai-sdk/openai-compatible"` 以配置 `ark-code-latest` 为例，具体信息如下。 > **注意** > > * `glm-5.3`、`glm-5.3-flash`、`deepseek-v4.1-flash`、`deepseek-v4-flash`、`deepseek-v4-pro` 支持 1M 上下文窗口用于包含大型代码库的长会话，可以通过 `limit.context` 字段显式指定窗口大小。 > * `provider.agent-plan.models` 节点下有**两处**（对象键、`name` 字段）需**替换为同一 Model Name**，切勿遗漏。 > * 若需开启模型图片理解能力，需在模型配置节点下新增如下配置项：`"modalities": {"input": ["text", "image"], "output": ["text"]}` **选项：Responses API** > **说明** > > npm 必须使用 `@ai-sdk/openai`，模型才会使用 Responses API，在 `baseURL` 的基础上自动拼接 `/responses`。 ```JSON { "$schema": "https://opencode.ai/config.json", "model": "agent-plan/ark-code-latest", "provider": { "agent-plan": { "npm": "@ai-sdk/openai", "name": "Volcano Engine（Responses API）", "options": { "baseURL": "https://ark.cn-beijing.volces.com/api/plan/v3", "apiKey": "" }, "models": { "ark-code-latest": { "name": "ark-code-latest", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "doubao-seed-2.1-pro": { "name": "doubao-seed-2.1-pro", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "doubao-seed-evolving": { "name": "doubao-seed-evolving", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "glm-5.3": { "name": "glm-5.3", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] } }, "glm-5.3-flash": { "name": "glm-5.3-flash", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "glm-latest": { "name": "glm-latest", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] } }, "deepseek-v4.1-flash": { "name": "deepseek-v4.1-flash", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "deepseek-v4-flash": { "name": "deepseek-v4-flash", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] } }, "deepseek-v4-pro": { "name": "deepseek-v4-pro", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] } }, "doubao-seed-2.1-lite": { "name": "doubao-seed-2.1-lite", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "doubao-seed-2.0-mini": { "name": "doubao-seed-2.0-mini", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "minimax-m3": { "name": "minimax-m3", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "kimi-k2.8-preview": { "name": "kimi-k2.8-preview", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } } } } } } ``` **选项：Chat API** > **说明** > > npm 必须使用 `@ai-sdk/openai-compatible`，模型才会使用 Chat API，在 `baseURL` 的基础上自动拼接 `/chat/completions`。 ```JSON { "$schema": "https://opencode.ai/config.json", "model": "agent-plan/ark-code-latest", "provider": { "agent-plan": { "npm": "@ai-sdk/openai-compatible", "name": "Volcano Engine（Chat API）", "options": { "baseURL": "https://ark.cn-beijing.volces.com/api/plan/v3", "apiKey": "" }, "models": { "ark-code-latest": { "name": "ark-code-latest", "limit": { "context": 256000, "output": 32000 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "doubao-seed-2.1-pro": { "name": "doubao-seed-2.1-pro", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "doubao-seed-evolving": { "name": "doubao-seed-evolving", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "glm-5.3": { "name": "glm-5.3", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] } }, "glm-5.3-flash": { "name": "glm-5.3-flash", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "glm-latest": { "name": "glm-latest", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] } }, "deepseek-v4.1-flash": { "name": "deepseek-v4.1-flash", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "deepseek-v4-flash": { "name": "deepseek-v4-flash", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] } }, "deepseek-v4-pro": { "name": "deepseek-v4-pro", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text" ], "output": [ "text" ] } }, "doubao-seed-2.1-lite": { "name": "doubao-seed-2.1-lite", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "doubao-seed-2.0-mini": { "name": "doubao-seed-2.0-mini", "limit": { "context": 256000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "minimax-m3": { "name": "minimax-m3", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } }, "kimi-k2.8-preview": { "name": "kimi-k2.8-preview", "limit": { "context": 1024000, "output": 65536 }, "modalities": { "input": [ "text", "image" ], "output": [ "text" ] } } } } } } ``` # 四、启动并使用 OpenCode 1. 启动 OpenCode： ```Bash opencode ``` 2. 输入`/models`，选择配置的模型并在 OpenCode 中使用。 # 其他操作 ## 配置视觉模型 方舟 Agent Plan Team Medium 及以上套餐提供图片生成模型配额，Team Large 及以上套餐提供视频生成模型配额。方舟提供 Skill 帮助 AI 工具快速接入并使用。具体配置方法请参见 [配置视觉模型](/docs/agent-plan-enterprise-visual-models)。 > **注意** > > * 不同的套餐支持的视觉模型有所不同，具体参见 [支持模型及 Harness](/docs/agent-plan-enterprise-plan-overview#3a2d43d5)。 > * 视觉模型不支持通过 Auto 及控制台切换使用。 ## 切换模型 你可以随时根据需求切换**文本生成模型**。方舟支持多种方式切换模型。 |配置方式 |通过控制台 |通过命令参数 |修改配置文件 | |---|---|---|---| |切换模型操作 |1. 参考[三、配置 OpenCode](/docs/agent-plan-enterprise-opencode#c807cb71)配置模型名称为 `ark-code-latest`。 |启动 OpenCode 后，执行`/models` 切换模型。 |参考[三、配置 OpenCode](/docs/agent-plan-enterprise-opencode#c807cb71)配置模型名称为您需要的模型。 | \ | |2. 在 [订阅页面](https://ark.volcengine.com/region:cn-beijing/subscription/agent-plan-enterprise?agentMode=close)，选择**我的** - **使用配置**，选择要使用的模型，切换后 3-5 分钟即可生效。 | | |