Claude Code v2.1.302
Claude Code v2.1.302 is a fix-heavy release (about 60 changelog entries). It adds an auto-mode classifier model setting and an idle-compaction toggle, and turns fork subagents on by default outside the terminal.
Why it matters
A maintenance release of Anthropic's terminal coding agent. It is mostly reliability fixes (compaction, MCP, plugins, Windows), plus a few behavior changes to subagents and permission modes that are worth knowing if you script Claude Code.
What's new
- New CLAUDE_CODE_AUTO_MODE_MODEL setting chooses the model for the client-side auto mode classifier, and a new "Idle compaction" toggle in /config.
- Fork subagents are now on by default in claude -p, the Agent SDK, the desktop app and VS Code (CLAUDE_CODE_FORK_SUBAGENT=0 turns them off).
- On third-party providers, claude -p and Agent SDK sessions with no permission mode now start in default mode; --permission-mode auto keeps auto.
- Fixes for MCP servers that negotiate protocol 2026-07-28 but omit some fields, plus a 128 MB cap on image reads in the Read tool.
- Notice that standalone Claude Design (claude.ai/design) closes by December 14, 2026; faster startup with many plugins enabled.
Taken from the project's own release notes. Claims about speed or accuracy are the maker's unless stated otherwise.
Quick facts
| Pricing | Requires a Claude account or Anthropic API access (plan details not checked)not verified |
|---|---|
| Free or paid | Paid |
| License | Proprietary (© Anthropic PBC; use subject to Anthropic's Commercial Terms) |
| Language | TypeScript (repo) |
| Platform | macOS, Linux, Windows; terminal, IDE, desktop |
| GitHub stars | ★ 151,410 (as of 2026-10-17) |
| Maker | Anthropic |
Links
- Official site: https://code.claude.com/docs/en/overview
- Repository: https://github.com/anthropics/claude-code
- Release notes: https://github.com/anthropics/claude-code/releases/tag/v2.1.302
- Docs: https://code.claude.com/docs/en/setup
Related ranking
See how established tools compare in Best AI Coding Agents & IDEs. New releases aren't scored until we review them against the rubric.
What we couldn't verify
- quick_facts.pricing
Checked 2026-10-17 from the release notes's own pages. Prices and star counts change, so confirm on the official site. Listing here is not a ranking or an endorsement.
The week's best new AI tools, ranked
One email a week: new releases worth your time, ranking changes, and one deep-dive. No spam.