Skip to content
Agentsweak signalverified

Claude Code 2.1.235 to 2.1.237: Concise style, ANTHROPIC_DEFAULT_MODEL, and spell checking

Three releases in three days change several things about daily work. Version 2.1.237 introduces a built-in Concise output style, in which Claude leads with the result and skips the preamble and the recap, and fixes prompt caching for sessions that go through a proxy gateway or a custom base URL. Version 2.1.236 adds the ANTHROPIC_DEFAULT_MODEL environment variable, which sets the model new sessions start on, and a notify_when_idle option that asks another session to report when it frees up. Version 2.1.235 introduces optional spell checking through aspell, hunspell, or ispell, and reduces memory and processor use for sessions running in the cloud.

By Redakcija WebAiRadarPublished 1 min readwritten by a model

Three releases in three days. The biggest difference in daily work comes from the built-in Concise output style, but there is also a long-requested variable for the default model and one security fix worth not skipping.

Version 2.1.237 and the Concise style

In this style Claude leads with the result and skips the preamble and the recap of what it just did, while doing the work just as thoroughly. You pick it under Output style in /config.

Prompt caching was also fixed for sessions that go through a proxy gateway or a custom base URL. If you run Claude through your own proxy, that is a direct saving, because the cache used to fall away and the bill was higher than it should have been.

Version 2.1.236: default model, notification, and the sandbox

  • ANTHROPIC_DEFAULT_MODEL sets the model new sessions start on. A manual choice with /model still wins and survives a restart, which is how it differs from the older ANTHROPIC_MODEL variable.
  • The notify_when_idle option in cross-session messaging asks another session on the same machine to report the next time it is idle. It fires once, requires explicit consent, involves no polling, and works on macOS and Linux.
  • In the macOS sandbox, deny-read rules by pattern such as **/.env now take precedence inside allowed areas, cover the contents of matched folders, and cannot be bypassed by renaming a file.

Version 2.1.235 and spell checking

Misspelled words are now optionally underlined in the input box as you type, through an installed aspell, hunspell, or ispell. A bug that invalidated the entire prompt cache when the language server disconnected or reconnected mid-session was also fixed.

BrandsClaude

Related

OPENCLAW 2026.10.232,768characters, and past that a key could slip thr
Agentsmedium signal

OpenClaw 2026.10.2 stops long tool output from slipping credentials past redaction

A bug in OpenClaw's secret masking let a credential through whenever it straddled the boundary between two slices of a long text. The fix ships in 2026.10.2 along with repaired updates from 2026.10.1 and a new compaction default for OpenAI and Anthropic API keys.

OpenClawverified

The OpenClaw web interface with a conversation on the left and the Bits & Bolts reference MCP app open beside it, showing a 3D keycap model and an Attach view + note button.
Agentsmedium signal

OpenClaw 2026.10.1 lets agents search installed skills and changes how sessions message each other

OpenClaw released version 2026.10.1 on October 10, 2026, its first stable release since 2026.9.7. Agents can now search the skills installed on a machine and read only the one a task needs, instead of carrying the whole library in the prompt. Opt-in MCP Apps run beside chat, and full backups can go to an external drive or Cloudflare R2. Three changes can break existing setups: session-to-session messaging, the old required argument, and Workboard data stored before July 2026.

OpenClawverified

CLAUDE CODE2.1.294hooks written as instructions now block what t
Agentsmedium signal

Claude Code 2.1.294 fixes prompt hooks that let through the actions they were written to block

Anthropic released Claude Code 2.1.294 on October 8, 2026. It fixes prompt and agent hooks phrased as instructions, which could allow exactly the actions they were meant to stop. Version 2.1.295 followed the same day with an onFailure setting that makes a crashed or timed-out command or HTTP hook block the action. Releases 2.1.292 and 2.1.293 from earlier in the week closed several permission and sandbox gaps.

Claude Code Releases (GitHub)verified