firendly summary model error

[anquan789]

Describe the bug
When I use Z.ai as the global model, the strongly summarized still uses OpenAI.

code
provider_config = ProviderConfig(
default_provider="zai/glm-4.7",
research_provider="zai/glm-4.7", # For complex planning / 用于复杂规划
engineer_provider="zai/glm-4.7", # For code generation / 用于代码生成
orchestrator_provider="zai/glm-4.7",
ops_provider="zai/glm-4.7",
tool_provider="zai/glm-4.7", # For internal tools/helpers / 用于内部工具/助手
)

try:
df = pd.read_csv("housing_data.csv")
except FileNotFoundError:
# 没有文件就用一份演示数据
df = pd.DataFrame({
"square_footage": [1500, 2100, 1800, 2500, 1200],
"bedrooms": [3, 4, 3, 5, 2],
"bathrooms": [2, 2.5, 2, 3, 1.5],
"price": [300000, 450000, 380000, 550000, 250000],
})

datasets = [df]

3) 定义 Plexe 模型意图（自然语言描述任务）

model = plexe.Model(
intent="根据房屋的面积、卧室和卫生间数量预测房价。"
)

print("Starting model build with GLM-4.7...")
model.build(
datasets=datasets,
provider=provider_config, #⭐ 指定用智谱 GLM
max_iterations=5, # 尝试多种建模方案
timeout=600,
run_timeout=180,
chain_of_thought=True,
verbose=False,
)

print(f"Model build finished. State: {model.get_state()}")

Screenshots

Environment (please complete the following information):

• OS: mac os intel
• Python Version :3.12