The Claude Code Changelog
Jellypod
0
This unofficial podcast, hosted by Lachlan and James and powered by Jellypod AI, helps listeners stay up to date with everything Anthropic ships to Claude. Each episode highlights what changed, how to use it, and why it matters. It covers product updates, new workflows, and more from the Claude Code changelog.
Episodes
-
Claude Code 2.1.330: Terminal Charts with Easel 21.11.2026 3mClaude Code 2.1.330 introduces easel, a new built-in plugin that renders inline bar charts and MCP time-series graphs directly in your macOS or Linux terminal. We also cover 30-day scheduled tasks, stricter rm safety checks, and new VS Code commands. -
Claude Code 2.1.329: /code-review Overhaul & 91 Bug Fixes 20.11.2026 3mWe break down the /code-review changes in version 2.1.329, including its wider default branch scope and explicit gh pr diff handling for pull requests. We also cover quality-of-life updates to /tasks, /teleport, and fixes for .claude.json data loss. -
Failing Closed with MCP Tool Hooks in Claude Code 2.1.328 19.11.2026 4mDiscover how Claude Code 2.1.328 lets you configure mcp_tool hooks to fail closed with "onFailure": "block", preventing unvalidated commands from executing when your security server goes down. We also cover auto mode updates for cloud providers, new environment variables, and essential bug fixes. -
Passing MCP JSON via Stdin in Claude Code 2.1.327 18.11.2026 3mLearn how Claude Code version 2.1.327 lets you pass MCP configurations via standard input using claude mcp add-json -, keeping sensitive Bearer tokens out of shell history and process lists. We also explore the expanded diagnostic checks in /status, safer .mcp.json edits, and other workflow fixes. -
Code Mode Meets Agent Teams and Stricter Permissions in Claude Code 2.1.326 17.11.2026 4mDiscover how Claude Code 2.1.326 allows Code Mode to run alongside agent teams, reducing round trips by letting workers batch multi-file operations locally. We also cover significant permission updates, including stricter wildcard shell rules, tighter sandbox file controls, and new git guards for subagents in worktrees. -
Terminal Prompt Suggestions and How to Disable Them in Claude Code 16.11.2026 3mLearn how Claude Code's new terminal prompt suggestions work, how to accept or edit them with Tab, and how to disable them via promptSuggestionEnabled in your settings.json. We also cover background task throttling and quick quality-of-life updates in release 2.1.325. -
Fixing Context Sizing and Model Pinning for Subagents in Claude Code 2.1.325 15.11.2026 3mClaude Code version 2.1.325 fixes context sizing for subagents on distinct models, preventing workers with smaller context windows from receiving outputs sized for the main session. It also preserves subagent model pins across plan mode switches and includes fixes for third-party gateway context compaction, fallback plan saving, and zstd decoding. -
Fixing Sandboxed Bash Permission Prompts in Claude Code 2.1.325 14.11.2026 4mLearn how Claude Code version 2.1.325 changes sandboxed Bash permissions by requiring explicit approval unless configured with autoAllowBashIfSandboxed true. We also cover crucial fixes to permission gaps, new prompts for scheduled tasks and loops, and smaller quality-of-life updates. -
Claude Code 2.1.323: Code Mode and Context Window Traps 13.11.2026 4mA deep dive into Claude Code 2.1.323, examining experimental Code Mode and critical default shifts like the 1M context assumption for unrecognized models. We also cover crucial updates to agent-to-agent message caps, plugin validation, and sandbox symlink permissions. -
Claude Code 2.1.321: Why Deny Rules Are Your New Safety Fence 12.11.2026 3mIn Claude Code 2.1.321, mods written by Claude turn on automatically in auto and bypass modes, with mod tool calls bypassing ask rules entirely. Learn why explicit deny rules are now your primary safety barrier, how to freeze skills in CI, and what changed with path checks and model picking. -
Fast Mode on Vertex AI and Claude Fable 5.2 11.11.2026 4mExplore the updates in Claude Code versions 2.1.321 and 2.1.322, featuring the introduction of Claude Fable 5.2 and Fast mode support on Google Cloud Vertex AI. Learn how to configure your environment, manage separate prompt caches to avoid unexpected token costs, and leverage new skill auto-reloading. -
Custom Settings Profiles for Claude Remote Control 10.11.2026 3mLearn how to use the new --settings flag added to claude remote-control in version 2.1.321 to configure custom profiles and safeguards for remote sessions. We also cover essential caveats, model updates, and critical sandbox and MCP OAuth security patches. -
Optimizing Claude API Latency with Claude Code 2.1.319 09.11.2026 4mExplore the new /claude-api latency-optimize command in Claude Code 2.1.319, which tests faster API settings against your evals to reduce latency bottlenecks. -
Fixing CI Breakages from Auto Mode Changes in 2.1.319 08.11.2026 3mIn Claude Code 2.1.319, auto mode removes its automatic client-side fallback when server safety checks fail, meaning headless pipelines behind gateways can now fail closed with exit code one. Learn how to diagnose your setup using /status, configure the CLAUDE_CODE_AUTO_MODE_SERVER environment variable, and prepare your CI workflows. -
Fixing Unattended Agent Stalls with denyInsteadOfPrompting 07.11.2026 4mDiscover how Claude Code 2.1.319 prevents unattended agents from stalling with the new permissions.denyInsteadOfPrompting setting. Learn how to configure it properly alongside explicit allow rules, and catch up on smaller quality-of-life additions like background MCP tasks. -
Expanded MCP Denylist Policies in Claude Code 2.1.318 06.11.2026 4mLearn how Claude Code 2.1.318 expands deniedMcpServers URL matching to block Anthropic-provided servers and cloud connectors. We cover configuring organizational denylists, verifying policies with claude mcp list, and several smaller MCP quality-of-life fixes. -
Tuning Reasoning Effort in Claude Code 2.1.318 Forks 05.11.2026 3mDiscover how Claude Code 2.1.318 lets you pass a custom effort parameter to $.model.fork, cutting down latency and token burn on lightweight mod tasks like handoff briefs and summaries. We also break down other key updates in this release, including cross-account IAM role assumption on the apps gateway and a fix for false-success exits in non-interactive mode. -
Preventing Silent Auth Expirations in Claude Code 2.1.318 04.11.2026 4mLearn how Claude Code 2.1.318 prevents unattended CI and headless runs from failing silently due to expired logins. We cover new expiration fields in claude auth status, warnings in claude -p, and switching to setup-token for permanent machine credentials. -
Failing Closed with Agent SDK Hooks in Claude Code 2.1.317 03.11.2026 5mLearn how Claude Code version 2.1.317 introduces onFailure: "block" for programmatic Agent SDK hook callbacks, preventing unattended agents from failing open on unexpected errors. We also cover protections against account email leakage in tools, isolated transcripts for nested headless sessions, and full-file re-reading behavior. -
Locking Down Write Boundaries in Claude Code 02.11.2026 4mLearn how to use Claude Code's blockWritesOutsideWorkingDirectories setting to lock down file write boundaries during unattended or headless runs across every permission mode.
Popular in
The podcast also appears in the podcast charts of these countries.