Blog · November 17, 2026 · 8 min read · by Vilva Athiban P B

Claude Code 2.1.326: What Changed for Unattended Runs — Background Sessions, Permission and Settings Fixes, Code Mode with Agent Teams

Claude Code 2.1.326 is the newest version as of 17 November 2026, and its changelog entry is one of the longest in months. This post reads the official CHANGELOG.md for 2.1.326 and 2.1.325 the way we read 2.1.323 and 2.1.319: for people who leave Claude Code running and want to be told when it stops. Changelog lines are quoted as written; the “what to do” under each group is our reading.

1. Code Mode now starts with agent teams

“Added support for turning on Code Mode while agent teams are enabled; if you already turned it on, sessions with teams on now start in Code Mode”. The second half is the one to notice: an opt-in you made weeks ago now applies to team sessions. Alongside it, skills no longer fail to load “in Code Mode under auto mode when an inline ! command needs approval; Claude is now asked to run it”, and mods can again call tools through $.tool.call. One change tightens it: “Improved permission checks in Code Mode; more sandboxed commands now ask or are refused”.

What to do: if you opted in and run teams, re-run one job interactively and watch for new asks. Our Code Mode explainer covers what the mode changes for permissions.

2. Start-up now tells you what is wrong

  • “Added a startup warning when an --allowedTools, --disallowedTools or --tools value has an entry that doesn’t look like a complete rule”. A mistyped rule used to pass in silence, then prompt a human who was not there.
  • “Fixed a prompt typed after --add-dir, --allowedTools or another list option being dropped without a message”.
  • “Added a row to /status that says when your provider or an environment variable such as DISABLE_TELEMETRY turns features off”, and commands that are off for that reason now “say why instead of ‘Unknown command’”.
  • “Added a message explaining why MCP servers stop loading when an administrator adds managed-mcp.json during a session”; such a file “may apply at the next check; restart open sessions for it to apply in full”.
  • “Added Ctrl+O to show hidden startup notices”.

What to do: put the prompt before the list options in your scripts, re-check every --allowedTools string once after updating, and run /status in the environment the job uses; our environment variables guide lists the switches that row can name.

3. “esc to stop”, and what Esc actually does

“Added an esc to stop footer hint in a subagent’s view where Esc would stop it”, and a fix for “esc to interrupt” “showing while Esc would go to a panel or footer item”. The hint now appears only where the key really interrupts. If you came here to disable “esc to interrupt”, the keybindings reference is the honest source: in the Chat context Escape is chat:cancel (“Cancel current input”), while Ctrl+C is app:interrupt, a reserved “Hardcoded interrupt/cancel” that cannot be rebound. /keybindings opens ~/.claude/keybindings.json, where a key can be unbound by setting it to null; the reference does not say what unbinding Escape does to a running turn, so test it interactively first.

4. Background sessions: three fixes worth an upgrade

“Fixed background sessions losing the LLM gateway your shell exported after a crash, after a reopen from another folder, or when the background service lacks it: they now stop before any model request”. “Fixed the background service ending your own processes, such as an SSH login, when a process number on its list had been reused by another user’s process”. “Fixed a background session being killed and its request lost when you opened, stopped or removed the older session whose conversation it had resumed”. From 2.1.325: background sessions no longer use “(and billing) an API key or token from the shell that started the background service”, and “more cases of a session moving to another sign-in in the background” are now refused.

What to do: update, then notify on every exit: the first fix turns a silent wrong-gateway run into one that stops early, which is correct and still needs a notification. Also note “Fixed desktop notifications not being sent inside tmux (with allow-passthrough on), or to iTerm2 over SSH, on the default setting”, the subject of our tmux and SSH post. Background sessions themselves are in our --bg and agent view guide.

5. Permissions and settings: rules that only looked saved

  • “Fixed rules added in /permissions or at a main-conversation tool prompt, and /add-dir folders, looking saved when the settings file couldn’t be written; the terminal now warns and names it”. An “always allow” you clicked yesterday may never have reached disk.
  • “Fixed managed settings with certain key names stopping Claude Code from starting or affecting other managed files”; values nested “past 64 levels are now dropped with a warning”; and a settings file saved with an error mid-session is no longer “skipped silently; a warning now names the file”.
  • “Fixed PreToolUse hooks in managed settings leaving no OpenTelemetry tool_decision event or permission_denials entry when they refused a direct tool call”. New beside it: OTEL_RESOURCE_INCLUDE_HOST adds host.name and host.id, “off by default”; see our audit post.
  • “Changed a hook’s "decision": "block" to hold in more cases, so a hook that always prints one may start blocking calls”.
  • From 2.1.325: sandboxed Bash commands now “follow the normal permission flow by default; set sandbox.autoAllowBashIfSandboxed: true to keep running them without prompts”, and scheduled tasks and /loop now “ask before running a skill that declares allowed-tools or hooks; add Skill(name) to permissions.allow to run it unattended”.

What to do: open /permissions once after updating and confirm the rules you believe exist are listed; add the two settings above if sandboxed or scheduled runs started prompting.

// settings for a run nobody is watching (2.1.325+)
{
  "sandbox": { "autoAllowBashIfSandboxed": true },
  "permissions": { "allow": ["Skill(my-nightly-skill)"] }
}

6. /rewind, recap and auto mode

/rewind no longer restores “only some files after running /branch twice while a slow backup copy was still running”, and a turn whose changes were not tracked “now reads ‘Code changes unknown’” instead of “No code changes”. “Fixed the automatic session recap being sent after a reply billed to usage credits; /recap still works”; our recap post has the background. And “Fixed auto mode staying on its local classifier, which counts toward usage, because of a stale saved value”; if your auto mode usage looked high, this may be why.

7. MCP: results that belonged to another call

“Fixed parallel MCP tool calls reading another call’s saved result when two long results arrived in the same millisecond (anthropics/claude-code#105138)”. For a run that fans out MCP calls, that is a correctness bug. Also: “Fixed tool search sometimes loading another MCP server’s tool when asked for a tool by its exact name; you may be asked again for that tool”, and “Fixed MCP prompts disappearing when two servers have nearly identical names”. Rename near-duplicate servers; see our tool search post.

8. Mods

“Added overflowX="scroll" on a mod’s Box, and maxLines and wrap="clip" on its Text”: a status panel built as a mod can now clip.

How to update, and the checklist

claude update
# or, for npm installs:
npm install -g @anthropic-ai/claude-code@latest
claude --version   # expect 2.1.326
  • Run /status and read the new “turned off” row.
  • Re-check every --allowedTools string for the new warning.
  • Confirm /permissions lists the rules you thought were saved.
  • Add Skill(name) allow rules for scheduled skills.
  • Notify on every exit; stopped-early is now a normal outcome.

That last line is where AI Done Now sits: it alerts you on your Mac when Claude Code finishes or needs permission; our notifications guide and background tasks post cover the setup.

FAQ

Does 2.1.326 turn Code Mode on for me?

Only “if you already turned it on”; then sessions with agent teams enabled now start in it too.

Can I disable the “esc to interrupt” hint?

The changelog adds and corrects the hint but offers no switch. The keybindings reference binds Escape to chat:cancel and supports unbinding keys; it does not document the effect on a running turn.

Why did my sandboxed or scheduled run start prompting?

2.1.325 moved sandboxed Bash to the normal permission flow and made scheduled tasks ask before skills with allowed-tools or hooks; the two settings in section 5 restore the old behaviour.

Is the MCP result mix-up fixed for all servers?

The entry names a condition, “two long results arrived in the same millisecond”, not a server type.

Keep reading

Desk Exercises for Programmers: 15 Moves to Do While Your AI Agent Codes

7 min read

Exercise While Coding: Turn Claude Code Wait Time Into Micro-Workouts

7 min read

Claude Code Notch Notifications on Mac: See When Claude Is Done Without Watching the Terminal

7 min read

Claude Code Tips and Tricks: 12 Ways to Use Claude Code Effectively

8 min read

Claude Code Multiple Sessions: How to Run Agents in Parallel Without Losing Track

6 min read

A Claude Code Workflow That Doesn't Involve Watching the Terminal

5 min read

Claude Code Hooks: A Practical Guide to Automating Your Agent Workflow

7 min read

Claude Code Auto Mode: Fewer Permission Prompts Without Living Dangerously

7 min read

Claude Code Subagents: How to Delegate Work to Specialized Agents

7 min read

Claude Code Context Management: Treat the Context Window Like a Budget

6 min read

Per-Subagent Model Selection: Route the Grunt Work Down, Keep the Judgment Up Top

7 min read

Skills and Plugins: How to Teach Claude Code Your Way of Working

7 min read

Claude Code Background Tasks: Run Long Commands Without Blocking Your Session

6 min read

Codex CLI Notifications: How to Get a Ding When Codex Is Done or Needs Input

7 min read

Cursor Notification When Done: Every Way to Get Notified When Cursor Finishes

6 min read

Claude Code Notifications: How to Get Notified When Claude Code Finishes or Needs Your Input

6 min read

Want to Be Notified When Claude Responds? How Claude Notifications Work on Web, Desktop, and Mobile

5 min read

Claude Code Notification Scripts: Copy-Paste Recipes for Every Platform

6 min read

Get a Ding the Moment Codex Needs Your Response

6 min read

Get Notified the Moment Claude Code Is Waiting for Your Input

6 min read

“Notifications Are Turned Off for Claude” — Here Is the Fix

6 min read

Codex Sound When Done: Make Codex CLI Play a Sound When It Finishes

6 min read

terminal-notifier + Claude Code: Native macOS Alerts When Your Agent Finishes

6 min read

Gemini CLI Notifications: How to Get a Sound or Alert When Gemini Finishes

6 min read

Get Claude Code Notifications on Your Phone

6 min read

Claude Code Remote Control, Explained

7 min read

preferredNotifChannel: Claude Code's Built-In Notification Setting

6 min read

Claude Code Notifications in tmux and Over SSH

7 min read

Claude Code Effort Levels: Why Your Setting Keeps Getting Ignored

8 min read

Codex vs Claude Code Notifications: How Each One Tells You It Is Done

8 min read

Claude Code Notifications Not Working: A Diagnostic Checklist

10 min read

Claude Code Notifications Inside Your Editor's Terminal

7 min read

CLAUDE_CODE_DISABLE_BACKGROUND_TASKS Explained

7 min read

CLAUDE_CODE_DISABLE_BG_SHELL_PRESSURE_REAP Explained

8 min read

Cursor Alerts Explained: Every Alert Cursor Raises, and How to Control Them

7 min read

Claude Code Environment Variables: The Groups That Actually Matter

10 min read

Claude Code Notifications on WSL and Windows

9 min read

Claude Code Checkpoints and /rewind

8 min read

Claude Remote Control: How It Works, Turning It Off, and Auto Mode

7 min read

Claude Code /loop: Poll a Deploy, Babysit a PR, and Get Told When It's Done

8 min read

Setting Up NotchFit With OpenAI Codex CLI: Hooks, $notchfit-plan, and the Daily Flow

7 min read

Claude Mods Explained: What the New Plugin Layer Can Do, and How to Turn On 'You Should Know'

9 min read

NotchFit vs Mac Break Reminder Apps: A Clock or a Signal From Your Coding Agent?

8 min read

Claude Code Headless Mode: Running claude -p in Scripts and CI, and the Three Signals That It Finished

10 min read

Building a Movement Habit at a Desk: Use the Agent Run as the Cue, One Set as the Unit, and Streaks Carefully

8 min read

Claude Code MCP Servers Explained: Adding Servers, Choosing a Scope, Handling Secrets, and Why Long Tool Calls Go to the Background

10 min read

/notchfit:plan Explained: How Claude Code or Codex Writes a Weekly Workout Plan the Notch Can Actually Run

8 min read

Claude Code Spinner Verbs Explained: What “Pondering” and “Brewing” Mean, How to Change Them, and Why You Should Stop Watching the Spinner

7 min read

Why NotchFit's Done and Permission Alerts Wait Until Your Set Ends, When That Costs You, and How to Turn the Workout Off

7 min read

How to Resume a Claude Code Session: --continue vs --resume, Naming Sessions, the Session Picker, Branching, and What Comes Back

9 min read

NotchFit on a Mac Without a Notch: How Pill Mode Works on Mac mini, iMac, Mac Studio and a MacBook With the Lid Closed

6 min read

How to Run a Claude Code Session in the Background: /background, claude --bg, Agent View, and Getting Back to It

9 min read

What a Notch App Can See: NotchFit's Local-First Design, What the Claude Code and Codex Hooks Send, and What Stays on Your Mac

7 min read

Why Codex CLI Asks for Permission Every Time, and How to Tune the Sandbox and Approval Policy Without Going Full Access

8 min read

What to Do While Claude Code or Codex Works: A Simple Protocol for the Two-to-Twenty-Minute Gap in Every Agent Run

7 min read

Is It Possible to Get a Notification When Claude Code or Codex Hits a Reset? Yes for Claude Code: the quota_auto_resume Hooks, Explained

8 min read

What a MacBook Notch App Can Actually Do: The Five Kinds of Notch Utility, Their Trade-offs, and Where NotchFit Fits

7 min read

How to Make MCP Servers Not Take Up as Much Context in Claude Code: Tool Search, alwaysLoad, Scopes and Output Caps

8 min read

The notchfit Command Line: Drive Your Workout, Read Status as JSON, Validate Plans and Test the Notch Without Leaving the Terminal

7 min read

How to Audit MCP Tool Calls Made by Claude Code: A Five-Minute Hook Audit Log, OpenTelemetry Tool Events, and the Transcript for Investigations

9 min read

Exercise Snacks: What the Research Actually Says About One-Minute Vigorous Breaks, What It Does Not, and How NotchFit's Agent-Run Sets Compare

8 min read

How Long Until a Claude Code MCP Tool Call Times Out? The Four Timers (Startup, Two-Minute Backgrounding, Idle, Wall-Clock), Their Defaults, and Which One to Change

8 min read

Sitting Too Long as a Developer: The Posture Problems Coding Agents Made Worse, What the Research Says About Breaking Up Sitting, and How NotchFit Turns an Agent Run Into the Break

8 min read

Claude Code .mcp.json Explained: Where Project-Scoped MCP Servers Are Read From, What Happens in Subfolders and Monorepos, and Why a Committed Server Shows Pending Approval

8 min read

Standing Desk Exercises for Developers: Why Standing Still Is Not the Goal, Eight Movements That Fit a Thirty-Second Agent Run, and How NotchFit Cues Them From the Notch

8 min read

The claude mcp Command Reference: add Syntax by Transport, What --scope local, project and user Actually Mean, add-json and add-from-claude-desktop, list, get, remove, login and serve

9 min read

Your First Week With NotchFit: Install and Simulate, Run Real Tasks, Write a Smaller Plan Than You Want, Tune the Alerts, Survive the First Skipped Day, and Decide What Stays

8 min read

How to Stop a Running Claude Code Task: Esc vs Ctrl+C, Background Tasks, Subagents, and Disconnecting Remote Control

8 min read

Pomodoro vs Agent-Driven Breaks: Timing Movement to Claude Code and Codex Runs Instead of a Timer

7 min read

Claude Desktop MCP Configuration: claude_desktop_config.json, Logs, Extensions, and the Difference From Claude Code

9 min read

The 20-20-20 Rule for Developers: Eye Strain, the Evidence, and Agent Runs as the Cue

8 min read

Claude Agent SDK + MCP Servers: mcpServers, allowedTools, Status Checks and Auth

9 min read

Discreet Desk Exercises for an Open-Plan Office While Claude Code Runs

7 min read

claude remote-control Server Mode: Run Claude Code as a Session Server

9 min read

Wrist and Forearm Stretches for Developers: A 60-Second Routine for Every Claude Code Run

7 min read

Claude Remote Control vs Claude Code on the Web: Which to Use and How They Differ

9 min read

Neck and Shoulder Stretches for Developers: A 90-Second Routine Between Agent Runs

7 min read

What Happens When You Step Away From a Claude Code Session: Prompt Cache Expiry, Idle Compaction, and When to Come Back

8 min read

Hip Flexor and Lower Back Stretches for Developers: A Two-Minute Standing Routine Between Agent Runs

7 min read

Claude Code's Monitor Tool: Watch Logs, CI Runs and PRs (Even a WebSocket) and Let Claude React While You Keep Working

7 min read

Hunched Over the Keyboard? Upper-Back (Thoracic) Stretches for Developers: A Two-Minute Seated Routine Between Agent Runs

6 min read

Claude Code Ultrareview: The 15–25 Minute Cloud Review, What to Do While It Runs, and How the Findings Come Back

8 min read

Why Your Legs Go Dead After a Long Claude Code Session: A Two-Minute Standing Calf, Glute and Hamstring Routine Between Agent Runs

7 min read

claude --teleport: Pull a Cloud Session Into Your Terminal, Start One With --cloud, Send Follow-Ups From the CLI, and the Requirements That Trip People Up

8 min read

Rounded Shoulders From Typing? A Two-Minute Chest Opener, Chair Twist and Wall Press Desk Routine for Developers Between Agent Runs

7 min read

Claude Code ultrathink Explained: It Now Runs the Turn at xhigh Effort, How It Differs From /effort, What It Costs in Time, and What to Do While It Runs

7 min read

Best Break Reminder Apps for Mac in 2026: Time Out, Stretchly, BreakTimer, LookAway and NotchFit Compared

7 min read

Claude Code 2.1.319: denyInsteadOfPrompting, MCP Background Tasks and What Changes for Unattended Runs and Notifications

8 min read

Drink Water and Stand Up Cues for Developers: Use Claude Code Agent Runs as Hydration and Standing Reminders

7 min read

Claude Code 2.1.323: Code Mode, Progress Heartbeat, Auto-Mode Fallback and 1M Context — What Changed for Unattended Runs

9 min read

Notch Media Controls on a Mac: What the MacBook Notch Can and Cannot Do, Dynamic Island-Style Apps vs NotchFit

7 min read

Claude Code Code Mode Explained: Claude Writes JavaScript to Call Tools — Requirements, Limits, Permissions, Hooks and What It Means for Unattended Runs

9 min read

NotchFit's Hide Workout Toggle: Using the Notch as a Pure Claude Code / Codex Status Panel (and When to Turn the Exercises Back On)

7 min read

Claude Code Session Recap Explained: The One-Line Summary You See When You Come Back to the Terminal, /recap, and How to Turn It Off

8 min read

A Five-Day Desk-Stretch Schedule for Developers: Rotating the NotchFit Routines Through the Week (Wrists Monday, Neck Tuesday, Hips Wednesday, Upper Back Thursday, Legs Friday)

7 min read

NotchFit Spoken Alerts: Let Your Mac Say 'Claude Is Done' Out Loud (On-Device macOS Voices, the Mute Button, the Mid-Set Wait and When to Turn Them Off)

7 min read