Cover von The Claude Code Changelog

Technologie

The Claude Code Changelog

von Jellypod, Inc.

Website RSS

Folgenzu den neuesten

  1. Claude Code Wildcard Bug and the Safe Fix

    This episode breaks down a security bug in Claude Code 2.1.246 where sloppy Bash wildcard rules can accidentally approve dangerous commands, and shows how to rewrite them with explicit subcommands. It also covers the new startup warning, th

  2. Claude Code Cache TTL Tweaks and Cost Tracking

    This episode breaks down the latest Claude Code updates for prompt cache lifetime control, including longer cache retention for main sessions, shorter TTLs for subagents, and per-agent cache settings in YAML frontmatter. It also covers the

  3. Claude Code 2.1.251: Locking Down Model Switches

    This episode breaks down the latest Claude Code release, focusing on new governance controls that let teams intercept model switches, enforce policy, and add audit trails. It also covers session resume metrics, cache cost visibility, and ne

  4. Claude Code Restricted Mode for Safer Untrusted Repos

    We break down how Claude Code 2.1.248 helps protect agents inside untrusted repositories with a new restricted mode that disables risky tools, locks file access to the working directory, and ignores potentially malicious config files. The e

  5. Claude Code 2.1.247 Adds API Cost Optimization

    We break down Claude Code 2.1.247’s new /claude-api cost optimize command, which profiles API spend and helps cut costs through caching, token hygiene, batching, effort tuning, and model selection. The episode also covers the new SendFeedba

  6. Claude Code Fixes Cache Wipes and Adds Terminal Spellcheck

    We break down Claude Code’s latest update, including a critical fix for prompt cache wipes caused by LSP reconnects, plus new terminal spellcheck support using local tools like aspell and hunspell. The episode also covers safer grep behavio

  7. Claude Code 2.1.234: Mid-Turn Controls and Security Fixes

    This episode breaks down Claude Code 2.1.234’s biggest upgrades, including mid-turn directory changes, on-demand documentation loading, and auto-resume for daily limits. It also covers a critical Windows path security fix and the guardrails

  8. Claude Code Plugin Installs, Governance, and Security Fixes

    This episode covers fixes for stale plugin install caches, cleaner marketplace governance settings, and new validation tools for local SKILL.md files. It also dives into concurrency bug fixes and an important sandbox hardening change that p

  9. Restore Claude Code Todo Tools After the 2.1.233 Update

    Anthropic’s latest Claude Code update disables built-in todo and task tools on newer models by default, breaking workflows that depend on structured task tracking. The hosts explain how to restore them with an environment variable, plus cov

  10. Claude Code 2.1.233: Memory Caps for Runaway Builds

    This episode breaks down Claude Code 2.1.233’s new opt-in Linux memory cgroup support for Bash tool commands, showing how it can stop runaway builds and leaking processes from taking down your whole dev machine. It also covers GitLab Merge

  11. Claude Code 2.1.232: Forked Subagents and Session Messaging

    This episode covers the latest Claude Code 2.1.232 updates, including forked subagents inheriting full conversation context, background execution for interactive agents, and direct session messaging. It also touches on GitLab secret redacti

  12. Claude Code 2.1.229: Cache Staggering, Guardrails, and UI Upgrades

    We break down how Claude Code 2.1.229 reduces duplicate token spend by staggering parallel subagent fan-outs so prompt caches can warm up, plus how to disable the delay for local benchmarking. The episode also covers new guardrails for comm

  13. Claude Code v2.1.228 Fixes a Cross-Session Security Hole

    This episode breaks down a security fix in Claude Code v2.1.228 that holds cross-session messages for approval before they can reach elevated terminals. It also covers the new dialogExpiry setting for headless workflows, plus quality-of-lif

  14. Bypass Bedrock Bottlenecks with ANTHROPIC_BEDROCK_REGION_PREFIX

    This episode explains how ANTHROPIC_BEDROCK_REGION_PREFIX can reroute Claude Code requests through cross-region Bedrock inference profiles to avoid AWS us-east-1 bottlenecks and 429 rate limits. It also covers IAM permission requirements, G

  15. Claude Code Goes Self-Hosted

    We break down Anthropic’s new claude self hosted runner for Team and Enterprise users, showing how it lets Claude Code sessions run inside your own secure infrastructure instead of the cloud. The episode also covers the latest fail-fast per

  16. Claude Code Adds Secure ZIP Plugin Installs

    Claude Code 2.1.224 adds archive-based plugin installs, letting teams load plugins directly from HTTPS ZIP files without git or npm on locked-down systems. The episode also covers SHA-256 pinning, ZIP structure requirements, and other enter

  17. Claude Code 2.1.225: Proactive Agent Messaging

    This episode breaks down new proactive messaging for remote Claude Code agents, letting you start conversations across machines with SendMessage and ListAgents. It also covers clearer enterprise gateway warnings, auto mode safety fixes, and

  18. Claude Code Sessions Can Message Each Other

    This episode explores how Claude Code sessions can message each other across terminals using ListAgents and SendMessage, making multi-repo workflows and handoffs far smoother. It also covers the security controls, new archive plugin install

  19. Claude Code 2.1.223: Context Limits and Security Fixes

    We unpack the latest Claude Code update, from automatic compaction for 1M-context models and clearer startup warnings to new safeguards for background agents and custom model gateways. The episode also covers a critical security fix for hid

  20. Claude Code Patch Fixes Worktree Security Flaws

    This episode covers critical Claude Code security fixes, including tighter isolation for worktree subagents, stricter controls on repo-local settings, and global-only activation for Remote Control. It also touches on a token tracking bug an

  21. Claude Code Mode Mask Protects Secrets in Sandboxes

    This episode dives into Claude Code’s new mode mask security feature, which protects secrets in sandboxed builds by using dummy credential files and proxying real values only on network egress. It also covers practical release upgrades like

  22. Claude Code Shell Fixes for MCP Login and Automation

    This episode covers new Claude Code shell improvements for automating MCP server authentication from the command line, including claude mcp login and logout. It also explores bash command response control, sandbox credential protections, re

  23. Classifier-Driven Auto Mode Cuts Permission Fatigue

    This episode explores how classifier-driven auto mode reduces permission fatigue by handling ambiguous Bash actions contextually, while hard deny rules still enforce non-negotiable boundaries. It also covers the reset command, minor latency

  24. Claude Code’s New Auto-Backgrounding and Workflow Upgrades

    We break down Claude Code’s new automatic MCP backgrounding for long-running tool calls, including the default 120,000 ms threshold, how to customize it with CLAUDE_CODE_MCP_AUTO_BACKGROUND_MS, and how setting it to 0 keeps workflows synchr

  25. Securing Claude Code with a Process Wrapper

    This episode breaks down how Claude Code’s process wrapper can keep enterprise AI tooling inside corporate security and telemetry controls, from launcher scripts and audit logging to avoiding runaway background daemons. It also covers pract

  26. Claude Code’s Windows Backslash Bug

    This episode breaks down a Windows bug in Claude Code where unescaped backslashes in file paths triggered Unicode parsing errors, causing crashes and garbled folder names. It also covers recent Windows-focused fixes, including safer Git Bas

  27. Claude Code 2.1.219: Nested Subagent Streaming Unlocked

    We break down how Claude Code v2.1.219 finally exposes nested subagent activity in headless mode, making it easier to debug streaming text, thinking blocks, and tool events in real time. The episode also covers new JSON fields, MCP init err

  28. Claude Code’s DirectoryAdded Hook for Monorepos

    This episode explores how Claude Code’s DirectoryAdded hook helps monorepos dynamically load the right environment for newly registered subdirectories, avoiding toolchain mix-ups like using npm in a bun workspace. It also covers workspace t

  29. Lock Down Claude Code with Strict Network Allowlists

    Learn how Claude Code’s strict allowlist mode can help prevent prompt-fatigue mistakes by blocking unapproved network access by default. The episode also covers the config setup, common breakages like package installs, and why enterprise te

  30. Claude Opus 5 Brings a Million-Token Context to the CLI

    We break down the latest Claude Code update, where Opus 5 becomes the default model and a native one million token context window changes how developers can work with huge codebases. The episode also covers the new pricing model, prompt cac

Ältere Folgen

0:00 / 0:00