# Claude Code v2.1.310

> Claude Code v2.1.310, released 23 Oct 2026 (2026-10-23). 242 entries read out of the shipped bundle. Unofficial, and not affiliated with Anthropic.

[Web version](https://changelogs.core-directive.com/v/2.1.310)

Short model names such as opus and sonnet now work beyond Anthropic's own API. Fable is now recognised as a short model name too. A new Claude Test panel in the terminal shows each test's pass, fail or blocked mark, with a progress bar and time left. It builds on the groundwork for that panel in v2.1.309. On Vertex and Bedrock, default models can now come from a published model document. Setting CLAUDE_CODE_RETRY_WATCHDOG_SCOPE=capacity limits the automatic retry waiting to capacity errors only.

Several features are in this build but not switched on yet. A /claude-api check that scans your project for retiring Claude model names is built and stays off. Sending a project's documents to Claude as plain text is also off unless switched on remotely. The tool that writes project documents gains a safety check that is off by default. When switched on, it refuses to replace a document whose text differs from what Claude last saw. Groundwork for picking up background agents left behind after a resume is present but hidden.

Starting a cloud session now recovers when this computer is not yet a trusted device. Claude Code re-enrolls the computer and retries, or tells you to run /login. Saving incoming attachments no longer overwrites files that have the same name. Inline images inside tmux now stay in place when the pane moves, resizes or regains focus. A NODE_EXTRA_CA_CERTS file with one blocked certificate no longer causes the whole file to be ignored. The bundled claude-code.d.ts type definitions file is removed.

## 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/2.1.310/full.md).

- [What probably matters to you](https://changelogs.core-directive.com/v/2.1.310/what-probably-matters-to-you.md): 22 entries
- [Improvements](https://changelogs.core-directive.com/v/2.1.310/improvements.md): 112 entries, 4 pages
- [Bug Fixes](https://changelogs.core-directive.com/v/2.1.310/bug-fixes.md): 9 entries
- [In Development](https://changelogs.core-directive.com/v/2.1.310/in-development.md): 4 entries
- [Internal Changes](https://changelogs.core-directive.com/v/2.1.310/internal-changes.md): 94 entries, 3 pages
- [Removed](https://changelogs.core-directive.com/v/2.1.310/removed.md): 1 entry

## What probably matters to you

The first 10 of 22, one line each. The section's own pages have every one in full.

- [Resuming subagents: incremental transcript fetch and restoring orphaned background agents](https://changelogs.core-directive.com/v/2.1.310/e/orphan-background-agent-restore-logic-gated-by-tengu-wondrou.json): Subagent transcripts can be fetched incrementally against the local copy, and new switch-gated code finds launched background agents to restore on resume
- [Project documents can be sent as text, and project_write checks a document was seen before replacing it](https://changelogs.core-directive.com/v/2.1.310/e/project-docs-sent-as-text-in-context-new-gated.json): Project documents can be sent to Claude as plain text, and project_write refuses to replace a document whose current text Claude has not seen
- [Claude Test gains a progress panel in the terminal](https://changelogs.core-directive.com/v/2.1.310/e/claude-test-progress-panel-added-tied-to-a-built-in-claude.json): The built-in Claude Test plugin gets a terminal panel showing test progress, a pane note tool, and new settings for its browser tooling
- [/claude-api can scan your project for retiring Claude models, behind flags](https://changelogs.core-directive.com/v/2.1.310/e/claude-api-now-scans-the-project-for-retiring-claude-models.json): /claude-api can search the project for deprecated or retired Claude model IDs, behind the tengu_cosmic_sketch flag, with a prompt section only for one test group
- [Short model names work beyond Anthropic's own API, and fable is recognised](https://changelogs.core-directive.com/v/2.1.310/e/model-alias-resolver-accepts-fable-and-drops-the-firstpart.json): Short model names such as opus and sonnet are no longer limited to Anthropic's own API, and fable is now recognised as one
- [MCP server settings gain connectorId and keep the configured command](https://changelogs.core-directive.com/v/2.1.310/e/tool-server-settings-accept-connectorid.json): MCP server settings accept a new connectorId field, stdio servers keep their original configuredCommand, and mcp_call refuses some servers' tools
- [Artifact comments can wake a session, and reading them can need your approval](https://changelogs.core-directive.com/v/2.1.310/e/artifact-mcp-laptop-publish-row-comment-watch-note-and-lapt.json): A session can now be messaged when someone comments on its artifact, and reading those comments can first need your approval
- [Claude can ask you a few questions before building slides or a design](https://changelogs.core-directive.com/v/2.1.310/e/artifact-ask-first-elicitation-form-before-creating-slidesd.json): With CLAUDE_CODE_ARTIFACT_ASK_FIRST set, Claude asks a few questions in a form before creating a slides or design artifact
- [claude.ai artifacts can now be reached through an MCP server](https://changelogs.core-directive.com/v/2.1.310/e/artifact-route-can-now-resolve-to-artifacts-mcp.json): Claude Code now has a second route for claude.ai artifacts, through an MCP server, beside the built-in Artifact tools
- [Governed git tools: gh guard and a standalone proxy mode](https://changelogs.core-directive.com/v/2.1.310/e/gh-stand-in-accepts-a-standalone-proxy-port-token-and-any.json): In proxied sessions, the built-in gh now refuses to run outside the session's proxy, and a new standalone-proxy mode sets up git and gh