# Claude Code v2.1.260

- Product: Claude Code (https://whatsnew.fyi/product/claude-code)
- Vendor: Anthropic
- Date: 2026-09-03
- Version: v2.1.260
- Original notes: https://github.com/anthropics/claude-code/releases/tag/v2.1.260
- Permalink: https://whatsnew.fyi/product/claude-code/releases/v2.1.260

What's New is an index, not a publisher: every entry below links to the vendor's own release notes, which are the authoritative source. Entries are labelled where they are hand-curated sample data, pre-releases, or drawn from a secondary source such as a developer blog.

Reuse: the summaries, labels and curation here are © What's New. Quote freely with attribution and a link back; wholesale republication of the corpus is not permitted — terms: https://whatsnew.fyi/terms. The vendors' own release notes remain their publishers'.

---

- **added** — Add a diff panel that opens beside the conversation in fullscreen mode and shows uncommitted changes as Claude edits, toggled with `/diff`
- **added** — Add likely cause for prompt-cache misses to `/cost` and the status line's `prompt_cache` field
- **added** — Add `/reload-plugins` to headless sessions
- **added** — Add text form of `/advisor` for the desktop app, Remote Control, and headless sessions
- **added** — Add `oidc.scope_on_refresh` to the Claude apps gateway for IdPs that return an id_token on refresh only when asked for `openid` again
- **added** — Add Claude apps gateway support for newer Claude Desktop keys in `desktop` policy blocks, including `userPluginMarketplacesEnabled` and `userPluginUploadsEnabled`
- **fixed** — Fix `Edit`/`Write`/`Read` permission rules whose path contains parentheses being dropped as invalid or ignored by the Bash sandbox
- **fixed** — Fix one file permission rule with an uncompilable pattern making every file edit fail with `Invalid regular expression`; such a deny rule now guards the literal path it spells
- **fixed** — Fix Bash permission checks auto-approving zsh commands that hide a command substitution in a REPORTTIME, REPORTMEMORY or DIRSTACKSIZE assignment
- **fixed** — Fix Bedrock model discovery, token counting and AWS SSO/STS credential calls failing with "unable to get local issuer certificate" when the corporate root CA is only in the OS certificate store
- **fixed** — Fix `permissions.blockReadsOutsideWorkingDirectories` on macOS hiding the user's git config from sandboxed git and hiding a worktree-isolated sub-agent's own checkout
- **fixed** — Fix managed settings not loading for claude.ai Enterprise/Team users who also had a leftover API key from an earlier `/login`
- **fixed** — Fix `/status` listing a signed-in claude.ai account and a configured API key as if both were in effect; the credential not in use is now marked
- **fixed** — Fix managed `skillOverrides` entries keyed on a bundled skill's alias not applying, and `Skill(name)` deny rules not covering a nested skill listed as `<dir>:name`
- **fixed** — Fix `model: fable` agents ignoring the `[1m]` tag on an `ANTHROPIC_DEFAULT_FABLE_MODEL` pin and silently running with a 200K context window
- **fixed** — Fix the `/model` picker not showing Fable 5.1 for organizations that can use it
- **fixed** — Fix prompt caching on Claude Fable 5.1 not covering the context attached after tool results
- **fixed** — Fix model switching staying blocked for the rest of the session after a plugin hook load failure
- **fixed** — Fix model switching being blocked for the session when an organization-managed plugin's marketplace could not be loaded
- **fixed** — Fix SDK-provided MCP servers sometimes missing from the first turn and only appearing on the next one

##### What's changed

- Added a diff panel that opens beside the conversation in fullscreen mode and shows your uncommitted changes as Claude edits; toggle it with `/diff`
- Added a likely cause for prompt-cache misses (e.g. tool definitions or system prompt changed, idle past the TTL) to `/cost` and the status line's `prompt_cache` field
- Added `/reload-plugins` to headless sessions, so it appears in the Claude Code Desktop and SDK command lists
- Added a text form of `/advisor` (`/advisor`, `/advisor <model>`, `/advisor off`) for the desktop app, Remote Control, and other headless (`-p`/Agent SDK) sessions
- Added `oidc.scope_on_refresh` to the Claude apps gateway for IdPs that return an id_token on refresh only when asked for `openid` again
- Added Claude apps gateway support for newer Claude Desktop keys in `desktop` policy blocks, including `userPluginMarketplacesEnabled` and `userPluginUploadsEnabled`
- Fixed `Edit`/`Write`/`Read` permission rules whose path contains parentheses being dropped as invalid or ignored by the Bash sandbox, which left "read-only" folders writable
- Fixed one file permission rule with an uncompilable pattern (e.g. an unclosed `[`) making every file edit fail with `Invalid regular expression`; such a deny rule now guards the literal path it spells
- Fixed Bash permission checks auto-approving zsh commands that hide a command substitution in a REPORTTIME, REPORTMEMORY or DIRSTACKSIZE assignment; these now prompt for approval
- Fixed Bedrock model discovery, token counting and AWS SSO/STS credential calls failing with "unable to get local issuer certificate" when the corporate root CA is only in the OS certificate store
- Fixed `permissions.blockReadsOutsideWorkingDirectories` on macOS hiding the user's git config from sandboxed git and hiding a worktree-isolated sub-agent's own checkout
- Fixed managed settings not loading for claude.ai Enterprise/Team users who also had a leftover API key from an earlier `/login`
- Fixed `/status` listing a signed-in claude.ai account and a configured API key as if both were in effect; the credential not in use is now marked
- Fixed managed `skillOverrides` entries keyed on a bundled skill's alias (e.g. `checkup` for `/doctor`) not applying, and `Skill(name)` deny rules not covering a nested skill listed as `<dir>:name`
- Fixed `model: fable` agents ignoring the `[1m]` tag on an `ANTHROPIC_DEFAULT_FABLE_MODEL` pin and silently running with a 200K context window
- Fixed the `/model` picker not showing Fable 5.1 for organizations that can use it, which was only accepted when typed as `/model claude-fable-5-1`
- Fixed prompt caching on Claude Fable 5.1 not covering the context attached after tool results, so it was re-sent as uncached input on every tool-call turn
- Fixed model switching staying blocked for the rest of the session after a plugin hook load failure; each switch now re-checks and the refusal names the cause
- Fixed model switching being blocked for the session when an organization-managed plugin's marketplace could not be loaded
- Fixed SDK-provided MCP servers (e.g. Desktop connectors) sometimes missing from the first turn and only appearing on the next one
- Fixed Claude in Chrome tools failing with "Not connected" mid-task in cloud-hosted claude.ai sessions when a connector was added or removed
- Fixed flags, joined emoji and accented letters splitting across wrapped lines, and stale text staying on screen when a flag or joined emoji falls in the terminal's last two columns (now shown as `…`)
- Fixed Remote Control accepting a model pick that is not a valid model name; it is now refused with an error instead of failing on the next message
- Fixed `/rewind` and `--rewind-files` reporting success when checkpoint backup files were missing and nothing was actually restored
- Fixed `/rewind` leaving stale file-read tracking from the rewound-away turns, which caused "File unchanged since last read" stubs and full-file re-injection after external edits
-

_[Truncated at 4000 characters — full notes: https://github.com/anthropics/claude-code/releases/tag/v2.1.260]_