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

AI Detection Tools Push Students to Use AI Defensively, Study Finds
AI detection tools in education are causing students to intentionally write worse to avoid false positives, with some students turning to AI tools defensively to check if their own writing will be flagged.

Hershey's Multi-Agent AI Runs Marketing Mix Modeling Monthly Instead of Quarterly
Hershey uses Mutinex (Claude/Gemini based multi-agent system) and Tracer to automate MMM, reducing analysis cycles from yearly to monthly for $2B in marketing spend.

Anthropic DNS Activity Reveals New STT Service, API RC2, and Tunnel Infrastructure
DNS monitoring of Anthropic's subdomains shows new records for a speech-to-text service on a 'Titanium' platform, an API release candidate 2, tunnel infrastructure, and an MCP proxy in staging.

Gen Z's AI Backlash: Usage Drives Skepticism, Not Acceptance
Polling shows Gen Z adopts AI tools but resents the AI-centric future. Many avoid AI entirely or disable features, citing job fears, environmental concerns, and social impact.