The Claude Code Changelog

Learn how to tame 529 overloaded errors in headless Claude Code runs using the newly released watchdog wait caps and retry delays. We break down the ideal CI environment configurations and highlight important quality-of-life fixes in versions 2.1.295 and 2.1.296.

We explore how the new allow_large parameter in Claude Code 2.1.296 handles oversized text files in a single pass while surprisingly cutting token costs. Plus, learn how to trigger it automatically and catch up on key fixes to encodings, PowerShell limits, and hook debugging.

Lachlan and James break down Claude Code 2.1.296, exploring how the new autoCompactWindow setting prevents worker subagents from bloating context windows and running up cache read costs. They also cover practical configuration tips, token limits, and new quality-of-life updates including cheaper Sonnet 5.5 cache reads.

Learn about Claude Code version 2.1.295 and the crucial new onFailure: "block" setting for command and HTTP hooks. We dive into how to prevent broken or missing guard scripts from failing open, plus key caveats to consider before updating your configuration.

Show Notes

• Releases · anthropics/claude-code - GitHub: https://github.com/anthropics/claude-code/releases

Anthropic launched Claude Haiku 5.5 featuring adjustable effort dials, a 1M token context window, and significantly slashed pricing. Learn how to configure custom subagents in Claude Code to take advantage of these massive cost savings while dodging key caveats like token price cliffs and verification quirks.

James and Lachlan explore Claude Code 2.1.292, which introduces a dedicated effort parameter for subagents to dramatically slash token costs in multi-agent workflows. They also cover practical orchestration tips, CI-friendly retry configurations, and critical security patches for UNC paths.

Lachlan and James break down Claude Code versions 2.1.290 and 2.1.291, highlighting new hourly refills for WebSearch budgets and pagination support for truncated WebFetch pages. They also cover critical regression fixes and expanded permission prompts for Bash commands with wildcards.

This episode breaks down the new --max findings flag for Claude Code code review, including how to cap, uncape, and reset findings, plus when to use effort levels and review comments or fixes. It also covers important caveats like sticky settings, background subagent behavior, and related quality-of-life updates in recent Claude Code releases.

This episode covers Claude Code 2.1.289, highlighting fixes to permission rules, sandbox behavior, symlinked file access, and managed machine safeguards. It also breaks down new agent spawn hooks, improved status tracking, and several stability and plugin updates.

This episode covers a fix in Claude Code 2.1.288 that makes path-scoped rules and nested CLAUDE.md files load on Write and Edit, even when a file is created before any read. It also breaks down the new InstructionsLoaded hook details, rule-loading caveats, and a handful of smaller workflow updates in the release.