feat: add MiniMax as first-class LLM provider

- Temperature auto-clamping for MiniMax models: (0, 1] range enforcement
- <think> tag handling for MiniMax M2.7 reasoning output (alongside existing <thinking> support)
- MiniMax configuration example in mykey_template.py
- Updated README.md and GETTING_STARTED.md with MiniMax provider docs
- 19 unit tests + 6 integration tests (3 live tests with MINIMAX_API_KEY)

MiniMax models (M2.7, M2.7-highspeed, M2.5, M2.5-highspeed) are accessed via
the standard OpenAI-compatible interface at https://api.minimax.io/v1, using
the existing LLMSession with an 'oai'-prefixed config key.
This commit is contained in:
PR Bot
2026-03-29 07:09:46 +08:00
parent 1d94384ee5
commit b6f697d40f
8 changed files with 570 additions and 9 deletions

View File

@@ -80,6 +80,16 @@ claude_config = {
}
```
```python
# MiniMax 使用 OpenAI 兼容格式,变量名含 'oai' 即可
# 温度自动修正为 (0, 1],支持 M2.7 / M2.5 全系列204K 上下文
oai_minimax_config = {
'apikey': 'eyJh...',
'apibase': 'https://api.minimax.io/v1',
'model': 'MiniMax-M2.7',
}
```
**使用标准工具调用格式(适合较弱模型):**
```python
@@ -105,6 +115,7 @@ native_claude_config = {
| `native` + `oai` | OpenAI 标准工具调用 | 较弱模型推荐,工具调用更规范 |
> 例:用 Claude 模型,但 API 服务提供的是 OpenAI 兼容接口 → 变量名用 `oai_xxx`。
> 例:用 MiniMax 模型 → 变量名用 `oai_minimax_config`MiniMax 走 OpenAI 兼容接口。
**`apibase` 填写规则**(会自动拼接端点路径):