llm 0.33 发布

本次发布中，我最关注的更新：

• 已升级至 OpenAI Python 库 3.x，并将 HTTP 客户端依赖从 httpx 切换为 httpx2。#1608、#1631

昨天我已经为此发布了快速的 0.32.1 修复，但这次是更全面的修复。

• llm embed 和 llm embed-multi 现在接受 --key 参数。Python 中的 EmbeddingModel.embed()、EmbeddingModel.embed_multi()、Collection.embed() 和 Collection.embed_multi() 方法也接受 key=，可将每次调用解析出的密钥传递给嵌入插件，同时不改变共享的模型状态。现有读取 self.key 的插件仍可通过兼容性回退机制继续工作。感谢 ChrisJr404。#757、#1620

嵌入模型现在采用了与常规 LLM 模型相同的密钥处理模式。

• llm prompt -t/--template 现在可以重复使用，以按顺序组合模板。这使得一个模板中的模型配置和选项可以与另一个模板中的提示词结合使用。

这解锁了一种很实用的模式：你可以创建模板，将模型及一组默认选项打包在一起：

llm -m gpt-5.6-luna -o reasoning_effort high --save lhigh
llm "Generate an SVG of a pelican riding a bicycle" --save pelican
# 组合并运行这些模板
llm -t lhigh -t pelican

这对于试用不同模型尤其有用，因为这些模型提供了各自对 OpenAI Responses API 的仿真实现。

My highlights from this release:

• Upgraded to the OpenAI Python library 3.x and switched the HTTP client dependency from httpx to httpx2. #1608, #1631

I shipped a quick 0.32.1 fix for this yesterday, but this is the more comprehensive fix.

• llm embed and llm embed-multi now accept --key. The Python EmbeddingModel.embed(), EmbeddingModel.embed_multi(), Collection.embed() and Collection.embed_multi() methods accept key= too, passing the resolved per-call key to embedding plugins without changing shared model state. Existing plugins that read self.key continue to work through a compatibility fallback. Thanks, ChrisJr404. #757, #1620

The embedding models now use the same pattern for keys that regular LLM models do.

• llm prompt -t/--template can now be repeated to combine templates in order. This allows model configuration and options from one template to be used with a prompt from another.

This unlocks a neat pattern where you can create templates that package a model with a set of default options:

llm -m gpt-5.6-luna -o reasoning_effort high --save lhigh
llm "Generate an SVG of a pelican riding a bicycle" --save pelican
# Combine and run the templates
llm -t lhigh -t pelican

This is particularly useful for exercising different models that provide their own imitation of the OpenAI Responses API.