Unofficial AI-summarized news site (not affiliated with any AI company)
AI News JP / www.ai-news.jp
🔵 Standard AI Summary · Source: SDK (anthropic-sdk-python)

Organization API support enables multi-tenant workflows; thinking display mode now in beta testing

anthropic-sdk-python v1.1.0 Released: Updates Thinking Display Mode & Organization API Support

Original: anthropics/anthropic-sdk-python: v1.1.0

Importance: SDK小機能追加とバグ修正のマイナーアップデート。Organization API対応は企業ユーザーに限定的な影響。

Summary

Anthropic's official Python SDK has been updated to v1.1.0. Key additions include a new 'updates' thinking display mode (beta), support for Organization API endpoints, and missing anthropic-beta header values. Bug fixes address tool runner pausing issues and documentation corrections. This is a minor release with no reported breaking changes affecting existing users.

Key Points

  • 'updates' thinking display mode added (beta)
  • Organization API endpoints now supported
  • Tool runner pause_turn bug fixed
  • Legacy response API removed
  • Missing anthropic-beta header values restored
View developer notes (APIs, breaking changes, migration)

v1.1.0 adds multiple developer-facing capabilities: (1) New 'updates' thinking display mode available in beta for improved ext_api_call_id and tool usage tracking. (2) Organization API endpoint support enables multi-tenant API token management directly in SDK. (3) Missing anthropic-beta header values now populated, ensuring reliable beta feature access. (4) Tool execution pause_turn handling fix resolves agent loop stopping bug. Migration to direct httpx2 import completed; legacy response API removed.

API/SDKAudience: 開発者

Source: https://github.com/anthropics/anthropic-sdk-python/releases/tag/v1.1.0

Outlet: SDK (anthropic-sdk-python)

This article is an AI-generated summary (OpenAI GPT-4o-mini) of publicly available information from Anthropic, OpenAI, Google, Meta, Mistral, DeepSeek, Sakana, and other vendors. The original source URL is always provided in accordance with fair-use citation requirements. Summaries are AI-generated and may contain mistranslations or misinterpretations. Always verify details with the original source.