↓ Skip to main content
  1. Articles/

Claude Code v2.1.327: The Data-Loss Release, Plus Tighter Path and Auto Mode Rules

·1180 words·6 mins·
Florent Clairambault
Author
Florent Clairambault
CTO & software engineer — writing daily about spec-driven development and agentic coding

Version 2.1.327 is the newest entry at the top of the official Claude Code changelog. I read the raw file, which is over a million characters, and only its first 100,000. This post is a summary of release notes, not a field test. I have not run this version, and the entry lists 172 bullets, so I cover the ones that matter for autonomous workflows and skip the terminal-rendering fixes.

The headline: things that used to disappear
#

Most releases are dominated by features. This one reads like a cleanup of ways the tool could quietly destroy your files. Per the changelog:

  • Project-scope claude mcp add and claude mcp remove could delete other top-level keys in .mcp.json. That is fixed, and claude mcp add --scope project now stops instead of overwriting when the file lists servers at the top level without an mcpServers key.
  • /export could overwrite an existing file without asking. It now asks, and /export <name> keeps the file.
  • In Remote Control, stopping a worktree-mode server could delete a running session’s git-ignored files, such as .env.
  • Self-hosted runners started with --use-anthropic-git-proxy could delete a non-empty GIT_CONFIG_GLOBAL directory at startup. It is now kept, with a warning.
  • Compaction after a reply cut off at the output token limit could lose that reply’s tool call and result.
  • ExitWorktree now asks before removing a worktree that may hold unsaved work.

If you run agents unattended, this is the category that hurts. A permission prompt is a visible failure. A deleted .env or a half-written .mcp.json is the kind you find on Thursday. These are the changelog’s claims; I haven’t reproduced any of the original bugs.

Path checks get stricter
#

The changelog lists several changes to how Claude Code decides what is inside your project:

  • Path checks now refuse some symbolic links.
  • What counts as “inside a working directory” changed, so some paths now ask for permission where they didn’t before.
  • permissions.blockReadsOutsideWorkingDirectories now asks about more Bash commands in bypass and auto modes, denies some in auto mode, and refuses more Bash commands naming paths under Read or Edit deny rules.
  • Bash commands whose variables expand to very long text are denied.
  • Claude in Chrome now refuses to upload some credential files.

The changelog doesn’t say which commands or paths are affected, so I can’t tell you what will newly prompt. The practical takeaway: if you have unattended jobs that read through symlinks or outside the repo, run them once interactively after upgrading and watch for new prompts.

Auto mode: fewer allow rules honored, fallback going away
#

Two entries concern auto mode:

  • Auto mode now ignores more package-running allow rules, with Bash(pnpm dlx *) as the example, along with path or version forms of the ignored rules. The reasoning is plausible: an allow rule for a package runner is effectively an allow rule for arbitrary code from a registry. But note the consequence. A rule you wrote may silently stop doing anything in auto mode.
  • The notice for the billed-classifier fallback changed, and the changelog says an upcoming release removes the fallback. It doesn’t explain what replaces it. I’d read this as a warning to check how your auto mode setup behaves when the classifier isn’t available, rather than assuming the fallback will keep covering you.

Also fixed: auto mode ignoring some wildcard PowerShell allow rules naming a .\ script, and Code Mode scripts getting prompts and denials in auto mode when a second script started. Code Mode itself now starts even when an installed mod hooks tool calls, though administrators can still disable it in managed settings.

Subagents and background work
#

For people running agent teams, several fixes target model and permission leakage:

  • A finished subagent could resume on a sibling subagent’s model and effort. Subagents launched without a model now stay on their starting model when resumed, including after /model.
  • In-process teammates on a different model used to compact at the lead’s limit. They now use their own limit and model.
  • A subagent resumed by a sibling’s message now follows session permission settings.
  • Background agents: fixes for the main conversation not learning that one had finished, and for Claude reporting one as running while it sat on a permission prompt.

This is the kind of plumbing that decides whether multi-agent runs are trustworthy. Nothing here is flashy, and all of it is claimed rather than tested by me.

Operational details worth knowing
#

  • MCP via stdin: claude mcp add-json <name> - reads the server JSON from stdin, so tokens stay off the command line and out of shell history. It is not available inside a Claude Code session.
  • Remote MCP retries: most remote servers that stayed disconnected after long outages are now retried in the background for about a day.
  • /status as a linter: it now flags broken agent, skill, command and output style files, keybinding errors, an unavailable sandbox, ignored permission settings and hook matchers that never match. Hook matchers that never match are a real silent failure for anyone enforcing policy through hooks.
  • Gateways: a managed-settings checksum header (x-claude-code-managed-settings-checksum) is added to gateway hint headers when CLAUDE_CODE_GATEWAY_HINT_HEADERS=1, and attributionProject names a session’s billing group on Claude apps gateways.
  • Shell head start: the first Bash command is faster, and shell start-up files may now run before approval. CLAUDE_CODE_DISABLE_SHELL_HEAD_START=1 turns this off. If your shell profile has side effects, that is worth a look.
  • Secrets in commits: on newer models and in PowerShell, Claude is told not to commit likely secret files. That is an instruction to the model, not an enforcement mechanism, so a pre-commit hook is still the right backstop.
  • WebFetch: URLs over 2,000 characters are refused before any prompt, and only the first 100 @ mentions in a message are looked up.
  • Telemetry: in Anthropic-hosted cloud sessions, CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC now acts at most as DISABLE_TELEMETRY.
  • /tui classic: the new name for the non-fullscreen renderer. /tui default still works.

What I’d do with this release
#

  1. Upgrade, then re-run one unattended job interactively. The symlink and working-directory changes can introduce new prompts that would stall a headless run.
  2. Audit your auto mode allow rules. Anything shaped like Bash(<package-runner> *) may no longer be honored.
  3. Commit your .mcp.json and .env backups. The old data-loss bugs are reportedly fixed, but a version-controlled .mcp.json costs nothing.
  4. Run /status. If it finds a hook matcher that never matches, you’ve learned that a policy you thought was enforced wasn’t.

The pattern
#

This is the third changelog post in a row on the 2.1.32x line, and the theme is consistent: the product’s trust boundary is the permission system, and most of the work is closing gaps in it. That is the right work. A terminal-native agent with real shell access is only as good as the boundary around it, and a changelog full of boundary fixes is evidence the team treats it as the product. It is also a reminder that the boundary is still being found. Treat each release as something to verify against your own workflows rather than trust.

Sources
#

AI Tools

Claude Code v2.1.326: Auto Mode Becomes the Fallback, and Credentials Files Get a Guard

Claude Code v2.1.326 (Nov 16) lets Code Mode run alongside agent teams, starts sessions in auto mode when no mode is set and organization policy hasn’t loaded, and blocks file tools from writing to sign-in files like .credentials.json. Based on the official changelog only; I have not run this version.

Nov 17, 2026 · 3 min read

AI Tools

Claude Code v2.1.309 Is a Sandbox and Permissions Hardening Release. Read It Like One.

Claude Code v2.1.309 ships roughly 60 changelog bullets, and the heart of it is closing gaps in the sandbox, Bash permission checks and worktree isolation guard. It also makes claude ultrareview require workspace trust and denies dangerous rm calls outright in bypass mode on Desktop and VS Code. Changelog-only analysis; not run.

Oct 23, 2026 · 6 min read

AI Tools

Claude Code v2.1.323–325: Code Mode, a Sandbox That Asks Again, and 1M Context by Default

Three Claude Code releases in four days (Nov 10–13) add an experimental Code Mode where Claude writes JavaScript to call tools, put sandboxed Bash back into the normal permission flow, and assume a 1M context window for unrecognized model IDs. Based on the official changelog only; I have not run these versions.

Nov 14, 2026 · 4 min read

AI Tools

Claude Code v2.1.321's Quiet Security Fixes: Six Holes in the Permission Boundary

The Fable 5.2 launch release, Claude Code v2.1.321, also closed at least six permission-boundary bugs: an MCP OAuth redirect that could leak refresh tokens, a read-only Bash command running outside the sandbox, and cp/mv bypassing deny rules. Based on the official changelog; I have not reproduced any of them.

Nov 11, 2026 · 5 min read

Guides

Claude Code v2.1.305 and v2.1.306: A Sandbox Escape Hatch, a Smarter Retry Watchdog, and a Managed-MCP Behavior Change

Claude Code v2.1.305 adds an opt-in sandbox.allowNestedUserNamespaces setting, a usage-limit recheck for unattended retry mode, and a change to how allowedMcpServers treats managed stdio servers. v2.1.306 is two fixes. Changelog-only analysis: I did not run either release.

Oct 21, 2026 · 6 min read