# Claude Code v2.1.321

> Claude Code v2.1.321, released 9 Nov 2026 (2026-11-09). 418 entries read out of the shipped bundle. Unofficial, and not affiliated with Anthropic.

[Web version](https://changelogs.core-directive.com/v/2.1.321)

You can now use the Fable 5.2 and Mythos 5.2 models in Claude Code with the short names `fable-5-2` and `mythos-5-2`. Fable 5.2 is now listed as the latest model, and `fable52` works as an alias too. Plugins can use a new `tool.check` hook to make tool permissions stricter, but never looser for built-in tools. Plugins can also answer or rewrite outgoing web requests, and they are never lent your sign-in. Setting `CLAUDE_CODE_ULTRAREVIEW_PR_AS_MERGED` asks /ultrareview to review a pull request as it was merged. This release has 418 entries, and 270 of them are usable today.

Some features are in the build but are not switched on yet. A remote switch can make /privacy-settings open your privacy settings on claude.ai in your browser. Video attachments can carry a preview image, but only in hosted remote environments with a switch on. A skill's `compatibility` note can tell Claude when the skill needs your own computer or network, behind a switch that is off by default. Code editors may show a recommended extension, also behind a remote switch.

Stalled secure connections now stop with a clear error instead of hanging. The usual limit is 120 seconds, and the error says to check your network or proxy. The bridge command now loads the settings file you pass with `--settings`. Plugin sync now keeps plugins you already installed when your account's plugin list fails to load. A skills folder created after startup is now picked up and watched. The email address privacy prompt for shell and web actions no longer appears in the list of features.

## Sections

Each section is its own markdown document of whole entries, in pages of about 40 KB. The whole release in one document is [full.md](https://changelogs.core-directive.com/v/2.1.321/full.md).

- [What probably matters to you](https://changelogs.core-directive.com/v/2.1.321/what-probably-matters-to-you.md): 54 entries, 2 pages
- [Improvements](https://changelogs.core-directive.com/v/2.1.321/improvements.md): 211 entries, 6 pages
- [Bug Fixes](https://changelogs.core-directive.com/v/2.1.321/bug-fixes.md): 15 entries
- [In Development](https://changelogs.core-directive.com/v/2.1.321/in-development.md): 8 entries
- [Internal Changes](https://changelogs.core-directive.com/v/2.1.321/internal-changes.md): 129 entries, 3 pages
- [Removed](https://changelogs.core-directive.com/v/2.1.321/removed.md): 1 entry

## What probably matters to you

The first 10 of 54, one line each. The section's own pages have every one in full.

- [Fable 5.2 and Mythos 5.2 arrive, and fast mode changes around them](https://changelogs.core-directive.com/v/2.1.321/e/fable-52-and-mythos-52-model-recognition-added.json): Claude Code recognises the Fable 5.2 and Mythos 5.2 models, needs an explicit opt-in for fast mode on them, and keeps your model when fast mode supports it
- [Remote Control gets a --settings option and pins what its sessions start with](https://changelogs.core-directive.com/v/2.1.321/e/remote-control-child-sessions-refuse-a-settings-file-that-ch.json): `claude remote-control --settings ` passes a settings file to spawned sessions, which refuse to start if that file or their start folder changed
- [Fable 5.2 added as a model alias and highlighted in a reworked model picker](https://changelogs.core-directive.com/v/2.1.321/e/new-fable52-model-alias.json): A `fable52` model alias is added, and the model picker gains a collapsible 'More models' row with Fable 5.2 highlighted
- [Mod http.fetch hooks can block API requests with a hook_denied error, and attached notes are marked untrusted](https://changelogs.core-directive.com/v/2.1.321/e/mod-httpfetch-hook-can-deny-api-requests.json): A mod blocking a request now gives a specific hook_denied error, notes you did not write are flagged as untrusted, and a few messages change
- [EndConversation tool reworded, asks for a confirming second call, and records its cause](https://changelogs.core-directive.com/v/2.1.321/e/endconversation-confirmation-re-prompt.json): Claude's EndConversation tool gets new guidance wording, a two-step confirmation before ending, and a recorded cause when it ends the session
- [Privacy settings can open on claude.ai, and hosts can record a privacy checkup](https://changelogs.core-directive.com/v/2.1.321/e/privacy-settings-command-can-redirect-to-claudeai-behind-an.json): Behind a switch, `/privacy-settings` can send you to claude.ai, and apps embedding Claude Code can record a privacy checkup as shown or dismissed
- [Hook handling prepared for hook modules](https://changelogs.core-directive.com/v/2.1.321/e/hook-modules-gate-tengu-immutable-falcon.json): Claude Code's hook handling gains groundwork for hook modules: module-based plugins can count as holding hooks, and module hooks depend on a module capability
- [Claude Code can read a list of MCP tools to deny](https://changelogs.core-directive.com/v/2.1.321/e/mcp-denied-tools-setting-parsing-added.json): Claude Code can now check and merge a list of blocked MCP tools, called mcpDeniedTools, into its settings
- [Plugins can intercept and rewrite Claude Code's web requests](https://changelogs.core-directive.com/v/2.1.321/e/plugin-http-fetch-hook-httpfetch-with-credential-redactio.json): Plugins can now hook outgoing web requests to answer or rewrite them, but are never lent your sign-in
- [Plugins can now make tool permissions stricter, but never looser](https://changelogs.core-directive.com/v/2.1.321/e/plugin-toolcheck-hook-can-tighten-tool-permissions.json): A new `tool.check` hook lets plugins answer allow, deny or ask on a tool check, and only stricter answers take effect for built-in tools