ai-model-wechat

AI text generation and streaming for WeChat Mini Programs via wx.cloud.extend.AI. If this environment only installed the current skill, start from the CloudBase main entry and use the published cloudbase/references/... paths for sibling skills. Keep local references/... paths for files that ship with the current skill directory. When this file points to a sibling skill such as auth-tool or web-development , use the standalone fallback URL shown next to that reference. Use this skill for calling AI models in WeChat Mini Program using wx.cloud.extend.AI . Use it when you need to: Do NOT use for: CloudBase provides these built-in providers and models: ⚠️ Different from JS/Node SDK: Return value is raw model response. ⚠️ Different from JS/Node SDK: Must wrap parameters in data object, supports callbacks. - Supports two methods: generateText() for non-streaming responses and streamText() for real-time streaming with callback support ( onText , onEvent , onFinish ) - Built-in models include Hunyuan (recommended: hunyuan-2.0-instruct-20251111 ) and DeepSeek (recommended: deepseek-v3.2 ) - API differs from JS/Node SDK: generateText() returns raw model response; streamText() requires parameters wrapped in a data object - Requires WeChat base library 3.7.1+ with no additional SDK installation needed - Not suitable for browser/Web apps, Node.js backends, or image generation - CloudBase...