Claude-Code v2.1.31 Release: Key Updates and Bug Fixes
This update covers the release v2.1.31 of Claude-Code, which introduces several notable improvements and fixes. Key changes include the addition of session resume hints that guide users on how to continue conversations after exiting. The update also expands support for full-width (zenkaku) spaces input using the Japanese IME in checkbox selections.
Several bugs have been addressed in this release. Notably, issues causing sessions to lock up due to too-large PDF file errors have been fixed, allowing smoother resumption of tasks without needing to start anew. Additionally, bash commands will no longer incorrectly report failures with "Read-only file system" errors when sandbox mode is enabled.
A critical fix was made to the streaming API path where the temperatureOverride parameter was previously ignored. All streaming requests erroneously defaulted to a temperature value of 1, regardless of configuration. This version now respects the specified temperature override, providing more expected behavior.
The update enhances system prompts to better utilize dedicated tools (e.g., Read, Edit, Glob, Grep) instead of relying on bash equivalents. This reduces unnecessary bash command usage. Error messages related to PDF and request sizes have been clarified to show the actual limits of 100 pages and 20MB.
For developers using strict language servers, LSP shutdown/exit compatibility is improved to handle null parameters. Additionally, misleading Anthropic API pricing has been removed from the model selector for users relying on third-party providers like Bedrock, Vertex, and Foundry.
📖 Read the full source: GitHub Claude-Code
👀 See Also
Meta Releases BOxCrete AI Model for Concrete Mix Design
Meta has released Bayesian Optimization for Concrete (BOxCrete), an open-source AI model for designing sustainable concrete mixes using U.S.-produced materials. The model improves on previous versions with better noise robustness and slump prediction capabilities.
Anthropic's Claude Mythos AI model revealed in data leak, described as 'step change' in capabilities
Anthropic is testing a new AI model called Claude Mythos (also referred to as Capybara) that represents a 'step change' in performance, with dramatically higher scores on software coding, academic reasoning, and cybersecurity tests compared to Claude Opus 4.6. The model's existence was revealed through a data leak from an unsecured, publicly-accessible data cache containing approximately 3,000 unpublished assets.
Longitudinal study finds AI productivity gains at 10%, not 10x
A longitudinal study tracking 40 companies from November 2024 through February 2026 found AI usage increased by 65% on average, but pull request throughput only increased by 9.97%. The data suggests coding was never the primary bottleneck in software development.
Claude-Code v2.1.84 adds PowerShell tool, environment variables, and multiple fixes
Claude-Code v2.1.84 introduces a PowerShell tool for Windows as an opt-in preview, adds environment variables for model configuration and streaming timeouts, and includes numerous bug fixes and performance improvements.