Claude Code v2.1.283 Release - Model Management and MCP Stability Improvements

Claude Code released v2.1.283. New availableModelsMatch and deniedModels settings enable precise control over specific model versions. Multiple stability issues

Claude Code · Release v2.1.283 · 2026-09-25

Claude Code released v2.1.283. New availableModelsMatch and deniedModels settings enable precise control over specific model versions. Multiple stability issues were fixed, including MCP (Model Context Protocol) server progress notification loss, stdio server termination problems, and transient 404 errors on stateless remote servers. The /doctor prompt-audit command allows auditing prompt patterns for legacy models, and MCP tool outputs were added to OpenTelemetry span events.

weltiq perspective: Enhanced model version management and improved MCP stability increase tool integration reliability during automated trading strategy execution, while the ability to lock specific AI model versions improves backtest reproducibility.

Release Notes Excerpt

What's changed Added x-claude-code-prompt-id to the gateway hint headers so LLM gateways can group the requests that serve one user prompt; opt in with CLAUDE_CODE_GATEWAY_HINT_HEADERS=1 Added availableModelsMatch managed setting: with "exact" , an availableModels entry allows only the model version it names, so new releases stay blocked until listed Added deniedModels managed setting to block specific models, even when availableModels allows them Added MCP tool, WebFetch and WebSearch outputs to the tool.output OpenTelemetry span event when OTEL_LOG_TOOL_CONTENT=1 Added /doctor prompt-audit (also /checkup prompt-audit ) to audit your CLAUDE.md files, skills, agents and commands for promptin…

Source: https://github.com/anthropics/claude-code/releases/tag/v2.1.283