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 olderv1.0.56 v1.0.58newer

Claude Code v1.0.57

8 entries read diff v1.0.56 → v1.0.57 Markdown
Find
Pick an entry · j / k steps through
1 entry

Changesopen

pr-comments Prompt Optimization#

The pr-comments prompt feature now uses Claude 3.5 Haiku model for improved performance when fetching and analyzing GitHub pull request comments. This optimization provides faster responses while maintaining quality for this specific use case.

Example usage remains the same:

# Fetch comments from the current PR
claude pr-comments

# With additional context
claude pr-comments "focus on security-related feedback"
1 entry

Internal Improvementsopen

#

  • Code cleanup: Removed numerous unused internal functions and variables, reducing bundle size and improving performance
  • Dependency updates: Updated AWS SDK components for better compatibility
  • Infrastructure improvements: Enhanced support for model-specific prompt configurations

Related

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

1 entry

Technical Detailsopen

#

The primary change allows individual prompt features to specify which Claude model they use. The pr-comments feature now explicitly uses claude-3-5-haiku-20241022 instead of the default model, optimizing for speed and cost-efficiency when processing pull request comments.

This update indicates a move toward task-specific model optimization, where different features can leverage the most appropriate Claude model based on their complexity and performance requirements.

1 entry

Notesopen

#

  • No breaking changes
  • No new CLI commands or flags
  • Existing pr-comments functionality remains unchanged from a user perspective
  • The model change is automatic and requires no configuration

Related

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

Verbatim
Official · Anthropic

Anthropic’s official release notes

Published verbatim by Anthropic for v1.0.57. 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.

  • Added support for specifying a model in slash commands
  • Improved permission messages to help Claude understand allowed tools
  • Fix: Remove trailing newlines from bash output in terminal wrapping
System prompt

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