maxEffortLevel: One Setting to Throttle Every Model's Thinking Budget
Claude Code 2.1.267 adds a maxEffortLevel setting that caps the model effort level across every provider, including Bedrock, Vertex, and Foundry, while still letting users pick a lower level.
What it is
A Claude Code release adding organization-wide effort-level ceilings plus a debugging flag for iterating on system prompt text.
What it does
`maxEffortLevel`, settable top-level or per model under `modelSettings`, caps the maximum effort level regardless of provider; `--system-prompt-snapshot off` renders the system prompt fresh on every request instead of reusing a cached copy from earlier in the conversation, useful when actively editing prompt text. Full list in the release notes.
Why it matters
Teams paying per-token on high-effort reasoning models now have a hard cost ceiling they can enforce centrally, instead of relying on every developer to remember to dial effort down manually.
gateway.yaml Pricing Now Flows Straight Into Claude Code's /cost
Claude Code 2.1.268 lets administrators set custom rates in gateway.yaml so /cost and telemetry match the organization's actual spend meter, plus a startup warning when a gateway's allowed CIDR list is empty.
claude plugin eval: Reproducible Scoring for Claude Code Plugins
Claude Code 2.1.269 adds a claude plugin eval command that runs a plugin's own eval suite against Claude Code and produces a scored, reproducible JSON and HTML report.
Claude Code 2.1.265 Caps Saved Tool Output at 1GB
Claude Code 2.1.265 adds a 1GB cap on tool results saved to disk, live-reloading for a whole folder passed to --plugin-dir, and a fix for prompt-cache reuse in resumed subagents.