Skip to content

feat(config): add MiniMax as a native model provider #216

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
octo-patch wants to merge 1 commit into
base: main
Choose a base branch
from
+13 −3
Open

feat(config): add MiniMax as a native model provider #216

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 12 additions & 3 deletions config/config.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -67,7 +67,7 @@ type modelT struct {
// ProviderOptions 是配置时可选的模型供应商,顺序即 UI 展示顺序(第一个为默认)。
// "custom" 为「其它」自定义:flash/pro 各自填 base_url/model/api_key/max_tokens/context_window,
// 全部兼容 OpenAI 接口。预设供应商(deepseek/mimo)只需填 api_key,套用 modelConfig 默认。
var ProviderOptions = []string{"deepseek", "mimo", "kimi", "qwen", "custom"}
var ProviderOptions = []string{"deepseek", "mimo", "kimi", "qwen", "minimax", "custom"}

// ProviderCustom 是「其它」自定义供应商的 id。
const ProviderCustom = "custom"
Expand Down Expand Up @@ -102,16 +102,25 @@ var modelConfig = map[string]modelT{
URL: "https://api.moonshot.cn/v1", // 必须带 /v1,端点为 /v1/chat/completions
FlashModel: "kimi-k2.5",
ProModel: "kimi-k2.6",
MaxTokens: 0, // 0 = 不发 max_tokens,走模型默认输出上限(见 agent.chatRequest omitempty)
MaxTokens: 0, // 0 = 不发 max_tokens,走模型默认输出上限(见 agent.chatRequest omitempty)
ContextWindow: 262144, // 256K
},
"qwen": {
URL: "https://dashscope.aliyuncs.com/compatible-mode/v1", // 阿里云北京;端点 /v1/chat/completions
FlashModel: "qwen3.7-plus",
ProModel: "qwen3.7-max",
MaxTokens: 0, // 0 = 不发 max_tokens,走模型默认输出上限
MaxTokens: 0, // 0 = 不发 max_tokens,走模型默认输出上限
ContextWindow: 1_048_576, // 1M
},
"minimax": {
// 全球站 OpenAI 兼容端点,端点为 /v1/chat/completions(agent 追加 /chat/completions)。
// 中国站为 https://api.minimaxi.com/v1,高级用户可用 custom 供应商或直接改 model.yaml 切换。
URL: "https://api.minimax.io/v1",
FlashModel: "MiniMax-M2.7", // 入门:上下文 204800
ProModel: "MiniMax-M3", // 旗舰:上下文 1M,与下方 ContextWindow 对齐
MaxTokens: 0, // 0 = 不发 max_tokens,走模型默认输出上限
ContextWindow: 1_000_000, // 1M(MiniMax-M3)
},
}

// Path 返回 ~/.deepx/model.yaml 绝对路径。
Expand Down
1 change: 1 addition & 0 deletions config/config_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,6 +15,7 @@ func TestDefaultForProviders(t *testing.T) {
}{
{"deepseek", "https://api.deepseek.com", "deepseek-v4-flash", "deepseek-v4-pro", 393216, 1_048_576},
{"mimo", "https://api.xiaomimimo.com/v1", "mimo-v2.5", "mimo-v2.5-pro", 131072, 1_048_576},
{"minimax", "https://api.minimax.io/v1", "MiniMax-M2.7", "MiniMax-M3", 0, 1_000_000},
{"unknown-provider", "https://api.deepseek.com", "deepseek-v4-flash", "deepseek-v4-pro", 393216, 1_048_576}, // 回退 deepseek
}
for _, c := range cases {
Expand Down