Summary

• Add Zhipu AI (智谱) GLM series model configuration examples to config.example.yaml
• Support for general-purpose, vision, long-context, and coding-specific models

What

Added commented configuration examples for 4 Zhipu GLM models:

• glm-5.1: General flagship model with deep thinking support
• glm-4.6v: Multimodal vision model for image understanding
• glm-4-long: Long context model (128K tokens)
• glm-5.1-coding: Coding-specific endpoint

Why

Zhipu AI is a leading Chinese LLM provider with OpenAI-compatible API. Users can now easily configure GLM models in DeerFlow without manually writing configuration.

How

• Uses langchain_openai:ChatOpenAI (OpenAI-compatible)
• Base URL: https://open.bigmodel.cn/api/paas/v4 (general) or /api/coding/paas/v4 (coding)
• Environment variable: $ZHIPU_API_KEY
• Follows existing configuration patterns (similar to Novita AI, MiniMax)

Test plan

• Configuration follows existing patterns in config.example.yaml
• All required fields documented (name, display_name, use, model, api_key, base_url)
• Thinking mode configuration included for applicable models
• Vision support flag correctly set for multimodal model

Checklist

• Code follows project style guidelines
• Documentation updated (config.example.yaml)