CATCH #2195
DETECTED OCT 20, 2026 21:20 UTC
THE CATCHscore 5/10
EXHIBIT 2195
Oct 20, 2026 21:20 UTC
github_releases+pages
anthropics/claude-code
Claude Code released v2.1.305, addressing numerous bug fixes, especially around tool search failures, sandbox permissions, and various operational improvements.
READY TO POST:
anthropic's claude code just dropped v2.1.305, fixing a bunch of issues from tool search on vertex/bedrock to sandbox permissions on linux. stability for the win!
a new claude code update (v2.1.305) is out with fixes for weird model naming, full disk bash errors, and better usage reporting. small but important dev experience bumps.
EVIDENCE — the receipts
[MERGED across 2 sources: github_releases, pages]
shared signal: claude-code
--- github_releases :: anthropics/claude-code ---
anthropics/claude-code release: v2.1.305
name: v2.1.305
published: 2026-10-20T20:46:50Z
url: https://github.com/anthropics/claude-code/releases/tag/v2.1.305
## What's changed
- Added `sandbox.allowNestedUserNamespaces` so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections
- Added `CLAUDE_CODE_RETRY_WATCHDOG_USAGE_LIMIT_RECHECK_MS` so unattended retry mode (`CLAUDE_CODE_RETRY_WATCHDOG`) notices a usage limit that was lifted before its reset
- Fixed every request failing on Vertex, Bedrock and other providers when the endpoint or a gateway rejects tool search, and behind gateways with ToolSearch disallowed or left out of `--tools` (a 2.1.304 regression): Claude Code now retries without it
- Fixed `/effort` and `/autocompact` settings not applying when the model name differed from a `modelOverrides` value by letter case or a `[1m]` tag
- Fixed new worktrees in a bare repository sometimes starting from local HEAD instead of the default branch, and unchanged subagent worktrees sometimes not being cleaned up
- Fixed Bash commands on a full disk failing with a raw `ENOSPC` file path: the error now says the disk is full and that nothing ran
- Fixed an MCP server passed by a cloud session or by the SDK's `setMcpServers` being replaced later in the session by a same-named server from your own settings
- Fixed Claude naming the wrong model for a subagent's work after the subagent switched to a fallback model
- Fixed cloud sessions and teammates not telling Claude when a compaction had to leave the oldest messages out of its summary to fit
- Fixed more cases of scheduled Cowork cloud sessions waiting five minutes for each subagent whose WebFetch needed a URL approval that nobody was there to give
- Fixed Workflow resume re-running already-completed `pipeline()`
caught by the 20-minute sweep ·
the live wire · all receipts