fix: use correct MiniMax endpoint, model name, and add .venv to gitignore

.env.example

@@ -29,6 +29,6 @@ export AZURE_OPENAI_API_KEY=
 # export QWEN_CHAT_MODEL=Qwen/Qwen3.5-4B
 
 # ── MiniMax (for minimax_chat backend) ──────────────────────────────
-# export MINIMAX_BASE_URL=https://api.minimax.chat/v1
+# export MINIMAX_BASE_URL=https://api.minimax.io/v1
 # export MINIMAX_API_KEY=...
-# export MINIMAX_MODEL=MiniMax/MiniMax-Text-01
+# export MINIMAX_MODEL=MiniMax-M2.7

.gitignore

@@ -40,3 +40,4 @@ docs/reflact_overview.html
 docs/render_ablation_paper_tables.py
 docs/让*
 .gradio/
+.venv

configs/_base_/default.yaml

@@ -45,9 +45,9 @@ model:
   target_azure_openai_managed_identity_client_id: ""
 
   # MiniMax backend settings (minimax_chat target)
-  minimax_base_url: ""          # https://api.minimax.chat/v1 if blank
+  minimax_base_url: ""          # https://api.minimax.io/v1 if blank
   minimax_api_key: ""
-  minimax_model: "MiniMax/MiniMax-Text-01"
+  minimax_model: "MiniMax-M2.7"
   minimax_temperature: "0.7"
   minimax_max_tokens: "8000"
   minimax_enable_thinking: "false"

skillopt/model/common.py

@@ -25,7 +25,7 @@ _BACKEND_DEFAULT_MODELS = {
     "claude_chat": "claude-sonnet-4-6",
     "claude_code_exec": "claude-sonnet-4-6",
     "qwen_chat": "Qwen/Qwen3.5-4B",
-    "minimax_chat": "MiniMax/MiniMax-Text-01",
+    "minimax_chat": "MiniMax-M2.7",
 }
 
 _BACKEND_ALIASES = {

skillopt/model/minimax_backend.py

@@ -17,7 +17,7 @@ from skillopt.model.common import (
     default_model_for_backend,
 )
 
-BASE_URL = os.environ.get("MINIMAX_BASE_URL", "https://api.minimax.chat/v1")
+BASE_URL = os.environ.get("MINIMAX_BASE_URL", "https://api.minimax.io/v1")
 API_KEY = os.environ.get("MINIMAX_API_KEY", "")
 TIMEOUT_SECONDS = float(os.environ.get("MINIMAX_TIMEOUT_SECONDS", "300") or 300)
 MAX_TOKENS = int(os.environ.get("MINIMAX_MAX_TOKENS", "8000") or 8000)