anthropic-sdk-python

Anthropic made the same change a few weeks after OpenAI did: https://github.com/anthropics/anthropic-sdk-python/releases/... The problem with httpx as a dependency is that it's currently working towards a 1.0 release which will be full of breaking changes. The httpx2 project is essentially a fork that promises not to break the existing API, which makes it a more stable dependency to build against. I wrote a pretty long comment about my concerns for the breaking 1.0 version last year - https://github.com/encode/httpx/discussions/3344#discussionc... - in that comment I recommended the HTTPX project release their 1.0 as a package called httpx2 instead, but a year later we now have an httpx2 (released by a different maintainer) that keeps the old API.

They just (minutes ago) updated the "What's new in Opus 4.8" documentation: https://platform.claude.com/docs/en/about-claude/models/what... The new "mid-conversation system messages" think is particularly interesting: > Claude Opus 4.8 accepts role: "system" messages immediately after a user turn in the messages array (subject to placement rules). This lets you append updated instructions later in a long-running conversation without restating the full system prompt, which preserves prompt cache hits on the earlier turns and reduces input cost on agentic loops. No beta header is required. See Mid-conversation system messages for usage details. Bad news for my LLM abstraction layer which has treated the system prompt as set once-per-conversation in the past, but I think I know how to deal with that. This commit to their client library has u