Source Intelligence

DisclaimerUnofficial, and not affiliated with Anthropic. Nearly all of this is read straight out of what ships: npm bundles, captured prompts, published docs. Anthropic's own notes go in verbatim, marked as theirs. The rest is my reading, and every entry carries the strings behind it. If one looks wrong, vote it down and say why.

All releases Home olderv1.0.40 v1.0.42newer

Claude Code v1.0.41

6 entries read diff v1.0.40 → v1.0.41 Markdown
Find
Pick an entry · j / k steps through
7 entries

Changesopen

#

# Claude Code v1.0.41 Changelog

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

Enhanced Hook System with Per-Command Timeouts#

The hook execution system now supports individual timeout configurations for each command within a hook. Previously, all commands shared a single global timeout, but now each command can specify its own timeout value.

Usage Example: When configuring hooks, you can now specify a timeout for individual commands:

{
  "hook_event_name": "pre-commit",
  "commands": [
    {
      "command": "npm test",
      "timeout": 30  // 30 seconds timeout
    },
    {
      "command": "npm run lint",
      "timeout": 10  // 10 seconds timeout
    }
  ]
}

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

New SubagentStop Hook Event#

A new hook event type SubagentStop has been added to the available hook events. This allows you to configure commands that run when a subagent completes its execution.

Available hook events now include:

  • PreToolUse - Before a tool is executed
  • PostToolUse - After a tool completes
  • Notification - For notification events
  • Stop - When the main process stops
  • SubagentStop - When a subagent completes (NEW)

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

Hook Input Structure Update#

The hook system now passes the complete hook configuration object to commands instead of just the userFacingInput field. This provides hooks with more context about the event that triggered them.

Before: Hooks received only userFacingInput as JSON After: Hooks receive the entire hook configuration object including hook_event_name and other metadata

Import Optimizations#

  • Consolidated stream imports to use named imports from node:stream and stream modules
  • Optimized process imports to use named import { cwd } from node:process
  • Added PassThrough stream imports for improved stream handling

Related

Other releases about the same thing. Found by shared names or similar wording; neither means one caused the other.

Better Error Handling#

  • Individual command timeouts are now properly cleared on both success and failure
  • Improved cleanup of abort controllers to prevent memory leaks
  • More consistent error reporting across hook executions

Code Structure#

  • Simplified the global timeout logic by moving timeout handling to individual command execution
  • Removed redundant timeout abort message since timeouts are now handled per-command
  • Cleaner separation of concerns between hook orchestration and command execution
Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v1.0.41. Text is unmodified from the upstream changelog. Everything else on this page came out of the bundle instead, which is why the two lists don't match.

  • Hooks: Split Stop hook triggering into Stop and SubagentStop
  • Hooks: Enabled optional timeout configuration for each command
  • Hooks: Added "hook_event_name" to hook input
  • Fixed a bug where MCP tools would display twice in tool list
  • New tool parameters JSON for Bash tool in tool_decision event
System prompt

The system prompt was not captured for this release, so this page cannot say whether it moved.