Claude Code 2.1.283 ships 94 changes: model pinning, gateway headers, prompt audit
ClaudeCodeLog · x · 2026-09-26
Claude Code CLI 2.1.283 is out with 94 changes. Highlights:
- Model controls: new availableModelsMatch managed setting — with "exact", an availableModels entry allows only the named version, blocking new releases; new deniedModels blocks specific models outright
- Gateway support: opt-in x-claude-code-prompt-id header (CLAUDECODEGATEWAYHINTHEADERS=1) lets LLM gateways group requests serving one user prompt
- Observability: with OTELLOGTOOLCONTENT=1, MCP tool, WebFetch and WebSearch outputs land in the tool.output OpenTelemetry span event
- Prompt audit: new /doctor prompt-audit (also /checkup prompt-audit) reviews CLAUDE.md, skills, agents and commands for prompting patterns written for older models
- Load testing: opt-in loadtestmode builds/signs requests, blocks upstream and serves canned replies
Plus click-to-expand for truncated cross-session messages and --plugin-dir improvements.
Related event: Claude Code 2.1.283 Ships 94 Changes Including Model Lockdown(2 posts)→
More from coding & agent
- Sydney Codex Community Buildathon set for Nov 14 with Cerebras-backed ultrafast compute track — paw_lean · 2026-11-11
- shadcn's improve hits 10k stars: let top models plan, cheap models execute code fixes — shadcn · 2026-11-11
- OpenAI open-sources Codex Security CLI and SDK for AI-driven vulnerability scanning and fixing — openai · 2026-11-11
- Claude Opus 5.5 runs an architecture search and finds AttnRes-Canon, a new top Transformer design — SonglinYang4 · 2026-11-11
- 5 research habits worth knowing: read papers backwards, reproduce first, wire coding agents via MCP — cneuralnetwork · 2026-11-11
- 'Adam can now do CAE': AI agent showcase in engineering simulation draws buzz — burhop · 2026-11-11