Back to Details

whats-new

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

What's New in Claude Code

Claude Code 新功能一览

Provide a curated summary of new Claude Code features. Supports two modes:
  • Automatic mode (default): Show changes since the last time the user checked, tracked via a cache file.
  • Explicit version mode: The user specifies a starting version (e.g., "what's changed since 1.0.30?"). Use the version they provide as the starting point.
Determine the version range, fetch the changelog, identify notable features, then spawn parallel agents — one per feature — for research and article writing.
提供Claude Code新功能的精选摘要，支持两种模式：
  • 自动模式（默认）：显示自用户上次检查以来的变更，通过缓存文件进行跟踪。
  • 指定版本模式：用户指定起始版本（例如“自1.0.30版本以来有哪些变化？”），以用户提供的版本作为起点。
确定版本范围、获取更新日志、识别重要功能，然后为每个功能启动并行Agent，进行研究和文章撰写。

Workflow

工作流程

Execute these steps in order:
按以下顺序执行步骤：

Step 1: Determine Versions

步骤1：确定版本

First, check if the user specified a starting version in their request (e.g., "since version 1.0.30", "since 1.0.30", "changes after 1.0.30"). If so, use that as the starting version and skip reading the cache file.
Otherwise, run these two Bash commands in parallel:
  1. claude --version
    — to get the currently installed Claude Code version
  2. cat ~/.claude/whats-new-in-claude-last-version 2>/dev/null
    — to get the last-checked version
Always run 
claude --version
to get the current version.
Parse the version numbers from the output.
Determining the starting version (in priority order):
  1. User specified a version: Use exactly what they said.
  2. Cache file exists and has content: Use its contents as the starting version.
  3. No cache file / first run: The starting version will be determined from the changelog in Step 3 (last 10 versions).
首先，检查用户的请求中是否指定了起始版本（例如“自1.0.30版本以来”、“自1.0.30起”、“1.0.30之后的变更”）。如果是，则使用该版本作为起始版本，并跳过读取缓存文件的操作。
否则，并行运行以下两条Bash命令：
  1. claude --version
    — 获取当前安装的Claude Code版本
  2. cat ~/.claude/whats-new-in-claude-last-version 2>/dev/null
    — 获取上次检查的版本
务必运行
claude --version
以获取当前版本。
从输出中解析版本号。
确定起始版本的优先级顺序：
  1. 用户指定版本：完全使用用户提供的版本。
  2. 缓存文件存在且有内容：使用缓存文件中的内容作为起始版本。
  3. 无缓存文件/首次运行：起始版本将在步骤3中从更新日志确定（最近10个版本）。

Step 2: Check If Already Current

步骤2：检查是否为最新版本

If the starting version equals the current version, inform the user there are no new changes since that version. Do not update the cache file. Stop here.
Skip this check if the user explicitly provided a version — they may want to re-read a range they've already seen.
如果起始版本与当前版本相同，告知用户自该版本以来没有新变更，不更新缓存文件，在此步骤停止。
如果用户明确提供了版本，则跳过此检查——用户可能希望重新查看已看过的版本范围。

Step 3: Fetch and Filter the Changelog

步骤3：获取并筛选更新日志

Fetch the Claude Code changelog using WebFetch:
URL: https://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md
Prompt: Extract all version headings and their content between version [current] and version [last-checked]. If this is a first run (no last-checked version), extract the last 10 version sections. Return the raw changelog entries for these versions.
Use the raw GitHub URL for clean markdown without HTML wrapper noise.
If the last-checked version does not appear in the changelog, fall back to the last 10 versions.
使用WebFetch获取Claude Code的更新日志：
URL: https://raw.githubusercontent.com/anthropics/claude-code/main/CHANGELOG.md
Prompt: 提取[当前版本]和[上次检查版本]之间的所有版本标题及其内容。如果是首次运行（无上次检查版本），提取最近10个版本的内容。返回这些版本的原始更新日志条目。
使用GitHub原始URL以获取无HTML包装干扰的纯净Markdown内容。
如果上次检查的版本未出现在更新日志中，则 fallback 到最近10个版本。

Step 4: Identify Notable Features

步骤4：识别重要功能

Review the extracted changelog entries and build a list of notable features. Each feature should be a distinct capability or improvement worth writing about.
Include: New features, significant improvements, new commands, new integrations, breaking changes, deprecations.
Exclude: Bug fixes, patch-level fixes, minor tweaks, dependency updates, internal refactors.
For each feature, note:
  • A short title
  • The version it appeared in
  • The relevant changelog text for that feature
Aim to identify all features worth covering individually. Do not group unrelated features together — each gets its own agent.
查看提取的更新日志条目，构建重要功能列表。每个功能应是值得撰写的独特能力或改进。
包含：新功能、重大改进、新命令、新集成、破坏性变更、弃用项。
排除：bug修复、补丁级修复、微小调整、依赖更新、内部重构。
为每个功能记录：
  • 简短标题
  • 推出该功能的版本
  • 该功能对应的更新日志文本
目标是识别所有值得单独介绍的功能，不要将不相关的功能分组——每个功能都有独立的Agent。

Step 5: Spawn Parallel Research Agents

步骤5：启动并行研究Agent

This is the critical parallelization step. Use the Task tool to spawn one 
whats-new-in-claude:changelog-researcher
agent per feature, all in a single message so they run in parallel. Use 
model: haiku
for each agent to keep things fast and cheap.
For each agent, provide a prompt like:
Research this Claude Code feature and write a detailed article about it.

Feature: [title]
Version: [version]
Changelog entry: [the raw changelog text for this feature]

Search the web for additional context on anthropic.com and code.claude.com, then write a 2-3 paragraph article.
Launch ALL agents in a single message — do not wait for one to finish before starting the next.
这是关键的并行化步骤。使用Task工具为每个功能启动一个
whats-new-in-claude:changelog-researcher
Agent，所有Agent在同一条消息中启动以实现并行运行。为每个Agent使用
model: haiku
以保证速度和成本效益。
为每个Agent提供如下提示：
研究此Claude Code功能并撰写一篇详细的文章。

功能：[标题]
版本：[版本号]
更新日志条目：[该功能的原始更新日志文本]

在anthropic.com和code.claude.com上搜索额外背景信息，然后撰写一篇2-3段的文章。
一次性启动所有Agent——不要等待一个Agent完成后再启动下一个。

Step 6: Collect and Present Results

步骤6：收集并呈现结果

As agents return, collect their articles. Once all agents have completed:
  1. If every agent returned 
    NO_NEW_FEATURES
    , tell the user: "No notable new features since version [starting-version] — just bug fixes and stability improvements."
  2. Otherwise, present the collected articles to the user as a single cohesive document:
    • Add an intro line like "Here's what's new in Claude Code since version [starting-version]:"
    • Order articles from most recent version to oldest
    • Add 
      ---
      separators between articles
    • If there are many features, add grouping headers (e.g., "Developer Experience", "Performance", "New Integrations") but keep every article intact — do not summarize or compress them
当Agent返回结果后，收集它们撰写的文章。所有Agent完成后：
  1. 如果所有Agent都返回
    NO_NEW_FEATURES
    ，告知用户：“自[起始版本]以来没有值得关注的新功能——仅包含bug修复和稳定性改进。”
  2. 否则，将收集到的文章整合成一份连贯的文档呈现给用户：
    • 添加引言，例如“以下是自[起始版本]以来Claude Code的新功能：”
    • 按版本从新到旧排序文章
    • 在文章之间添加
      ---
      分隔符
    • 如果功能较多，可添加分组标题（例如“开发者体验”、“性能优化”、“新集成”），但需保留每篇文章的完整内容——不要总结或压缩。

Step 7: Update the Cache

步骤7：更新缓存

After presenting the summary, use Bash to write the current version to the cache file:
bash
echo "[current-version]" > ~/.claude/whats-new-in-claude-last-version
呈现摘要后，使用Bash将当前版本写入缓存文件：
bash
echo "[当前版本]" > ~/.claude/whats-new-in-claude-last-version

Edge Cases

边缘情况处理

  • Changelog fetch fails: Inform the user that the changelog could not be retrieved. Suggest checking their network connection. Do not update the cache file.
  • Version not found in changelog: Fall back to showing the last 10 versions.
  • Very large gap (>20 versions): Identify the most significant features (cap at ~15 agents to avoid excessive parallelism). Mention to the user that many versions were covered and some minor items were omitted.
  • 更新日志获取失败：告知用户无法获取更新日志，建议检查网络连接，不更新缓存文件。
  • 版本未在更新日志中找到： fallback 到显示最近10个版本。
  • 版本差距过大（超过20个版本）：识别最重要的功能（限制约15个Agent以避免过度并行），并告知用户涵盖了多个版本，部分次要内容已省略。