Claude Code v2.1.145: JSON, 1M context

// 1h agoPRODUCT UPDATE

Claude Code v2.1.145: JSON, 1M context

ANNOUNCEMENT PRODUCT GITHUB PRODUCT HUNT

Claude Code adds JSON output for scriptable workflows and native 1M token support for Bedrock and Vertex AI. The update introduces "plugin X-ray" for inspecting MCP tools before installation.

// ANALYSIS

Anthropic is turning Claude Code into a first-class enterprise citizen by bridging the gap between standalone CLI and cloud-integrated developer infrastructure. Native 1M token support on Bedrock and Vertex makes the tool viable for massive codebase migrations that previously hit context limits, while new JSON output commands transform the tool into a scriptable building block for custom IDEs and background automation. Additionally, "Plugin X-ray" visibility addresses security concerns by allowing full inspection of MCP hooks and commands before installation, and enhanced OpenTelemetry tracing optimizes the tool for complex, multi-agent background tasks.

// TAGS

claude-codecliai-codingcoding-agentagentlong-contextmcpdevtool

DISCOVERED

1h ago

2026-05-20

PUBLISHED

1h ago

2026-05-20

RELEVANCE

9/ 10

AUTHOR

DIY Smart Code

// KEEP READING

More AI developer news from the feed

EXPLORE FULL FEED

RESEARCH2h ago

OpenAI model disproves Erdős geometry conjecture

OpenAI's internal reasoning model has autonomously disproved Paul Erdős's 1946 Unit Distance Conjecture by identifying a novel family of geometric constructions. The result, verified via the Lean proof assistant and validated by Fields Medalist Terence Tao, represents a landmark achievement where AI moved beyond pattern matching to solve a prominent open problem in combinatorial geometry.

RESEARCH3h ago

OpenAI o1 disproves 80-year-old Erdős geometry conjecture

OpenAI's general-purpose reasoning model has autonomously disproven the 1946 Erdős planar unit distance conjecture, a central problem in discrete geometry that had resisted human efforts for eight decades. By utilizing advanced algebraic number theory and Golod–Shafarevich theory to construct new point-set families, the model demonstrated that long-held square-grid assumptions were suboptimal, marking a watershed moment for AI in pure mathematics.

LAUNCH3h ago

Google Antigravity 2.0 shifts to parallel agents

Google’s Antigravity 2.0 pivots from an IDE-first assistant into an orchestrator for multiple autonomous agents, background tasks, and custom subagent workflows. The launch also adds an Antigravity CLI, an SDK, deeper Google AI Studio/Android/Firebase integration, and new AI Ultra pricing.