发布日期: 2026-07-25
版本号: v0.82.1

本次更新新增了Claude Opus 5模型支持,可通过Anthropic和亚马逊Bedrock使用,具备自适应思考、推理配置与提示缓存等功能;同时引入了面向Anthropic兼容网关的Bearer认证方式,并优化了模型目录的刷新与容错机制,使模型列表在重启后仍能保留。在功能增强方面,新增了消息渲染设置、改进了令牌认证继承、扩展了模型兼容性。技术实现上优化了目录刷新效率、统一了OAuth请求方式,并改善了错误信息报告。此外,修复了认证解析、模型列表显示、启动文件发现及llama.cpp模型持久化等多项问题。

更新内容 (中文)

新功能

  • Claude Opus 5 —— 现已通过自适应思考(包括 xhigh)、推理配置和提示缓存,在 Anthropic 与 Amazon Bedrock 上提供服务。详见 提供方
  • Anthropic 网关 Bearer 认证 —— ANTHROPIC_AUTH_TOKEN 可用于认证需要 Authorization: Bearer 的 Anthropic 兼容网关,包括压缩和分支摘要功能。详见 环境变量或认证文件
  • 更快、更可靠的模型目录 —— pi.dev 目录现在使用 If-None-Match 进行重新验证,未变更的提供方将返回空 304 响应,且 llama.cpp 模型在重启后仍会保留在列表中。详见 llama.cpp

新增

  • 向自定义消息渲染器公开了 outputPad 设置。详见 扩展 (#7045,由 @xl0 贡献)。
  • 为 Anthropic 兼容网关新增了继承的 ANTHROPIC_AUTH_TOKEN Bearer 认证。详见 提供方 (#5871)。
  • 新增了对 Anthropic 和 Amazon Bedrock 上 Claude Opus 5 的继承支持,包括自适应思考、推理配置、提示缓存,并保留了 AWS 验证消息 (#7081,由 @unexge 贡献;#7083,由 @davidbrai 贡献)。

变更

  • pi.dev 模型目录刷新改为使用 If-None-Match 重新验证,以便未变更的提供方目录返回空 304 而非完整下载。
  • 继承的 Radius OAuth 设备授权、令牌交换和刷新请求现直接使用配置的网关。
  • 继承的模型加载错误现会追加根本原因,因此像 OAuth refresh failed for openai-codex 这样的认证失败会报告提供方响应,而非仅显示包装器消息。

修复

  • 修复了认证完全解析为请求头的提供方的压缩和分支摘要问题 (#5871)。
  • 修复了不可用的作用域模型在 /models 中被隐藏的问题,允许其无需手动编辑设置即可移除 (#6949#7032,由 @christianklotz 贡献)。
  • 修复了启动时上下文文件发现过程,跳过与上下文文件名(如 AGENTS.md)匹配的目录,避免产生 EISDIR 警告 (#7106,由 @mrexodia 贡献)。
  • 修复了 llama.cpp 扩展以持久化其模型目录,使 llama.cpp 模型在首次成功刷新前仍保留在列表中。详见 llama.cpp (#7072,由 @davidbrai 贡献)。

更新内容 (原始)

New Features

  • Claude Opus 5 — Available on Anthropic and Amazon Bedrock with adaptive thinking (including xhigh), inference profiles, and prompt caching. See Providers.
  • Anthropic gateway bearer authANTHROPIC_AUTH_TOKEN authenticates against Anthropic-compatible gateways that require Authorization: Bearer, including compaction and branch summaries. See Environment Variables or Auth File.
  • Faster, more resilient model catalogs — pi.dev catalogs revalidate with If-None-Match so unchanged providers answer with an empty 304, and llama.cpp models stay listed across restarts. See llama.cpp.

Added

  • Exposed the outputPad setting to custom message renderers. See Extensions (#7045 by @xl0).
  • Added inherited ANTHROPIC_AUTH_TOKEN bearer authentication for Anthropic-compatible gateways. See Providers (#5871).
  • Added inherited Claude Opus 5 support for Anthropic and Amazon Bedrock with adaptive thinking, inference profiles, prompt caching, and preserved AWS validation messages (#7081 by @unexge, #7083 by @davidbrai).

Changed

  • Changed pi.dev model catalog refreshes to revalidate with If-None-Match, so unchanged provider catalogs answer with an empty 304 instead of a full download.
  • Changed inherited Radius OAuth device authorization, token exchange, and refresh requests to use the configured gateway directly.
  • Changed inherited model loading errors to append the underlying cause, so auth failures such as OAuth refresh failed for openai-codex report the provider response instead of a bare wrapper message.

Fixed

  • Fixed compaction and branch summaries for providers whose authentication resolves entirely to request headers (#5871)
  • Fixed unavailable scoped models being hidden from /models, allowing them to be removed without editing settings manually (#6949, #7032 by @christianklotz).
  • Fixed startup context file discovery to skip directories that match context file names such as AGENTS.md, which produced EISDIR warnings (#7106 by @mrexodia).
  • Fixed the llama.cpp extension to persist its model catalog, so llama.cpp models stay listed before the first successful refresh. See llama.cpp (#7072 by @davidbrai).

下载链接