gitops/optimclaw
1
0
Fork 0
mirror of https://github.com/outbackdingo/optimclaw.git synced 2026-08-25 14:53:34 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: upgrade MiniMax default model to M2.7 (#1357)

Browse Source 
* feat: upgrade MiniMax default model to M2.7

- Add MiniMax-M2.7 and MiniMax-M2.7-highspeed to model list
- Set MiniMax-M2.7 as default model
- Keep all previous models as alternatives
- Update related tests

* fix: use canonical model name in test per review

Use MiniMax-M2.7-highspeed (canonical casing) in the reasoning
models test for consistency with the documentation and provider
configuration.

[skip-regression-check]
This commit is contained in:
Octopus
2026-03-18 11:34:05 -07:00
committed by GitHub
parent 9286978547
commit 2d0b195321
4 changed files with 7 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.env.example
+1 -1
View File
@@ -78,7 +78,7 @@ NEARAI_AUTH_URL=https://private.near.ai
# === MiniMax ===
# LLM_BACKEND=minimax
# MINIMAX_API_KEY=...
# MINIMAX_MODEL=MiniMax-M2.5
# MINIMAX_MODEL=MiniMax-M2.7
# MINIMAX_BASE_URL=https://api.minimax.io/v1 # default (global); use https://api.minimaxi.com/v1 for China
# === Anthropic Direct ===
docs/LLM_PROVIDERS.md
+2 -2
View File
@@ -15,7 +15,7 @@ configurations.
| io.net | `ionet` | `IONET_API_KEY` | Intelligence API |
| Mistral | `mistral` | `MISTRAL_API_KEY` | Mistral models |
| Yandex AI Studio | `yandex` | `YANDEX_API_KEY` | YandexGPT models |
| MiniMax | `minimax` | `MINIMAX_API_KEY` | MiniMax-M2.5 models |
| MiniMax | `minimax` | `MINIMAX_API_KEY` | MiniMax-M2.7 models |
| Cloudflare Workers AI | `cloudflare` | `CLOUDFLARE_API_KEY` | Access to Workers AI |
| Ollama | `ollama` | No | Local inference |
| AWS Bedrock | `bedrock` | AWS credentials | Native Converse API |
@@ -84,7 +84,7 @@ LLM_BACKEND=minimax
MINIMAX_API_KEY=...
```
Available models: `MiniMax-M2.5` (default), `MiniMax-M2.5-highspeed`
Available models: `MiniMax-M2.7` (default), `MiniMax-M2.7-highspeed`, `MiniMax-M2.5`, `MiniMax-M2.5-highspeed`
To use the China mainland endpoint, set:
providers.json
+2 -2
View File
@@ -393,8 +393,8 @@
"api_key_required": true,
"base_url_env": "MINIMAX_BASE_URL",
"model_env": "MINIMAX_MODEL",
"default_model": "MiniMax-M2.5",
"description": "MiniMax API (MiniMax-M2.5 and MiniMax-M2.5-highspeed models)",
"default_model": "MiniMax-M2.7",
"description": "MiniMax API (MiniMax-M2.7, MiniMax-M2.7-highspeed, MiniMax-M2.5 and MiniMax-M2.5-highspeed models)",
"setup": {
"kind": "api_key",
"secret_name": "llm_minimax_api_key",
src/llm/reasoning_models.rs
+2
View File
@@ -108,6 +108,8 @@ mod tests {
assert!(has_native_thinking("nanbeige-4.1-3b"));
assert!(has_native_thinking("step-3.5-flash-197b"));
assert!(has_native_thinking("minimax-m2.5-139b"));
assert!(has_native_thinking("MiniMax-M2.7"));
assert!(has_native_thinking("MiniMax-M2.7-highspeed"));
}
#[test]