In brief

Claude Code shipped fifteen prompt-cache repairs and a setting that caps reasoning effort

Roughly fifteen fixes in 2.1.267 are prompt-cache-break repairs: resumed sessions rewriting tool definitions, mid-session MCP tools appended inline, `/model` switching resending every tool definition. If you resume long sessions or attach connectors mid-run you were paying uncached input on turns you believed were cached. Separately, `effort:` frontmatter on custom commands, skills and subagents was being ignored entirely on Opus 4.7, Opus 4.8 and Fable 5. A new `maxEffortLevel` caps effort across Bedrock, Vertex and Foundry.

What it changes Upgrade if you resume sessions over 5 MB or attach MCP tools mid-run, and re-check that any effort: frontmatter you wrote was ever taking effect.

The changelog carries no dates. The 9 September date is the npm registry publish timestamp for 2.1.267, which is the release event rather than a date printed on the page.

Who is telling you this

Anthropic · primary

Written by
No individual byline
For
Anthropic, publishing the changelog for its own product
What they gain if this is true
The paper’s best guess: cache-break admissions cost Anthropic little and lower its own serving cost when fixed, which is what makes them credible.

Published in the edition of Thursday, 10 September 2026 · Beat: Tooling