openclaw阿里云机器飞书部署版

星期三, 2026-03-11 | Author: Lee | AI | 9 views

阿里云也推出了一站式部署openclaw，和腾讯云稍微不同的是用admin用户进行启动的，和腾讯云直接root的用起来就是有点麻烦了，稍微麻烦了点

记录下踩点部分.

1.获取阿里云的机器 68一年，比腾讯云99的还便宜

直达地址：https://www.aliyun.com/activity/ecs/clawdbot?spm=5176.45303171.J_prbLYvsEQKDdDmwSsbh3D.1.5f504203Ic3h6n#J_006

直接选带openclaw的系统即可，当前选中的是openclaw 2026.3.3版本

2.在控制台可以重启对应网关和直接填写飞书的appid和密钥部分，如下图

3.创建飞书的机器人应用获取对应的appid和密钥部分
https://open.feishu.cn/app?lang=zh-CN

4.配置相关权限和通道信息（添加完成，要发布应用才可）
左侧边栏「权限管理」→ 「开通权限」，把“通讯录”、“消息与群组”、“云文档”和“多维表格”下面所有权限全开了，然后点击「确认」
左侧菜单点击「事件与回调」
注意：如果这一步报错提示“应用未建立长连接”，请检查前面步骤中的机器人App ID和App Secret是否已正确配置
然后点击「添加事件」
把“通讯录”、“消息与群组”、“云文档”里所有的权限全勾选上

5.在飞书应用里搜索 刚才添加的机器人
在机器上执行 图上的安全授权的命令
openclaw pairing approve feishu 你的授权码

6.也看到了真正烧钱的tokens的还没有配置，这里使用是阿里的code plan的配置
可以根据你的机器情况选，北京还是新加坡和北美的地址，这里是北京的地址
https://bailian.console.aliyun.com/cn-beijing?tab=model#/efm/coding\_plan

7.登录机器更新对应的模型的配置 models部分
进入/home/admin/.openclaw/下修改 openclaw.json部分，调整模型，
飞书的在控制台已经添加了，这里也可以直接改

 "models": {
    "mode": "merge",
    "providers": {
      "bailian": {
        "baseUrl": "https://coding.dashscope.aliyuncs.com/v1",
        "apiKey": "sk-sp-xxxxxx", //这里是你的api-key的配置
        "api": "openai-completions",
        "models": [
          {
            "id": "qwen3.5-plus",
            "name": "qwen3.5-plus",
            "reasoning": false,
            "input": [
              "text",
              "image"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 1000000,
            "maxTokens": 65536
          },
          {
            "id": "qwen3-max-2026-01-23",
            "name": "qwen3-max-2026-01-23",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 262144,
            "maxTokens": 65536
          },
          {
            "id": "qwen3-coder-next",
            "name": "qwen3-coder-next",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 262144,
            "maxTokens": 65536
          },
          {
            "id": "qwen3-coder-plus",
            "name": "qwen3-coder-plus",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 1000000,
            "maxTokens": 65536
          },
          {
            "id": "MiniMax-M2.5",
            "name": "MiniMax-M2.5",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 1000000,
            "maxTokens": 65536
          },
          {
            "id": "glm-5",
            "name": "glm-5",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 202752,
            "maxTokens": 16384
          },
          {
            "id": "glm-4.7",
            "name": "glm-4.7",
            "reasoning": false,
            "input": [
              "text"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 202752,
            "maxTokens": 16384
          },
          {
            "id": "kimi-k2.5",
            "name": "kimi-k2.5",
            "reasoning": false,
            "input": [
              "text",
              "image"
            ],
            "cost": {
              "input": 0,
              "output": 0,
              "cacheRead": 0,
              "cacheWrite": 0
            },
            "contextWindow": 262144,
            "maxTokens": 32768
          }
        ]
      }
    }
  }

还要调整部分agents使用的primary模型部分，这里的更改

"agents": {
    "defaults": {
       "model": {
        "primary": "bailian/qwen3.5-plus"
      },
      "models": {
        "bailian/qwen3.5-plus": {},
        "bailian/qwen3-max-2026-01-23": {},
        "bailian/qwen3-coder-next": {},
        "bailian/qwen3-coder-plus": {},
        "bailian/MiniMax-M2.5": {},
        "bailian/glm-5": {},
        "bailian/glm-4.7": {},
        "bailian/kimi-k2.5": {}
      },
      "workspace": "/home/admin/.openclaw/workspace",
      "compaction": {
        "mode": "safeguard"
      },
      "maxConcurrent": 4,
      "subagents": {
        "maxConcurrent": 8
      }
    }
  }

飞书的修改这部分

"channels": {
    "feishu": {
      "accounts": {
        "default": {
          "appId": "cli_xxxx",
          "appSecret": "xxxxx",
          "domain": "feishu",
          "enabled": true
        }
      }
    }
  }

8.在控制台重启OpenClaw网关即可
这里在飞书里就可以正常吩咐机器人干活了

9.踩坑 ssh登录后如何重启和操纵openclaw
我是root登录机器的，要用admin命令操作openclaw才行，使用下面命令切换下

sudo -iu admin
export XDG_RUNTIME_DIR=/run/user/$(id -u)
openclaw gateway restart

否则会报这个错误，可让人烦躁
openclaw gateway restart

🦞 OpenClaw 2026.3.3 (unknown) — You had me at ‘openclaw gateway start.’

Gateway service check failed: Error: systemctl is-enabled unavailable: Cannot access user instance remotely.

10.收工收工，后续愉快的玩耍吧。

赏

Tags: ,

文章作者: Lee

本文地址： https://b.xuekewen.com/2444.html

除非注明，Pomelo Lee文章均为原创，转载请以链接形式标明本文地址

No comments yet.

Leave a comment

Search

相关文章

热门文章

最新文章

文章分类

标签云

Links

Meta