WorkBuddy 接入 Kimi K3 手动配置方法
想用 kimi K3 但 WorkBuddy 没法直接添加？跟着这个三步配置法，替换 API Key 就能用，亲测有效。
有用户分享在 WorkBuddy 中接入 kimi K3 模型的具体步骤。需在 ~/.
workbuddy 目录下新建 models.json，并填入包含 url、apiKey 等字段的配置。
配置中需要设置 supportsToolCall、supportsImages、supportsReasoning 为 true。替换 API Key 后重启 WorkBuddy 即可正常使用。
该方法可避免手动添加可能出现的兼容问题。
群里看到有人想要在workbuddy 接入kimi K3 但是自己手动添加可能会有问题，不能正常使用。
我看@Lonely__MH 的方法直接将下面的这个配置要求丢给任一Agent产品，Codex CC 等都可以。
方法步骤如下👇🏻
1. ~/.workbuddy 目录 下，新建 models.json
2. 将下面内容拷贝到json中，记得替换apikey
{ "id": "k3", "name": "k3", "vendor": "Custom", "url": " https:// https://t.co/MOmn4JjJqy", "apiKey": "你的API KEY", "supportsToolCall": true, "supportsImages": true, "supportsReasoning": true, "useCustomProtocol": false }
3. 重启 WorkBuddy
就可以使用了👇🏻
This report is categorized under AITOP's "How-to" desk, focusing on China's AI industry and domestic foundation model ecosystem. Within our cross-regional analytical framework, it directly maps to AI developer toolchains, coding agents, and engineering workflows. Key entities and technical topics under continuous tracking include kimi K3, WorkBuddy, API配置, 自定义模型.
Source attribution: curated from berryxia (@berryxia). Cross-source corroboration: 11 independent sources have covered this development (including pandaily, vLLM, @koltregaskes), confirming industry-wide signal strength.
