AI agents, week of 2026-10-05

2026-10-07 · github.com/vercel/ai

Patch Changes - 6f6b9c0: fix(ai): reject pending result promises and cancel the pending stream when the abort signal fires - d3bcad9: feat(provider): report decision refusals as refusal answers - Updated dependencies [d3bcad9] - @ai-sdk/provider@4.0.24 - @ai-sdk/gateway@4.0.106…

2026-10-06 · github.com/anthropics/claude-agent-sdk-python

Internal/Other Changes - Updated bundled Claude CLI to version 2.1.292 - CI: security hardening for GitHub Actions workflows that call Claude — egress-firewall runner, network allow list, auto permission mode, and a check workflow to enforce them ( 1329) - CI: raised PyPI per-fi…

2026-10-06 · github.com/anthropics/claude-code

What's changed - Added --marketplace to claude plugin install : adds the marketplace if needed, under the same policy checks as claude plugin marketplace add , then installs the plugin from it - Added an effort parameter to the Agent tool, so Claude runs a sub-agent at the effor…

2026-10-06 · github.com/google-gemini/gemini-cli

What's Changed fix(cli): display retry progress indicator during connection recovery ( 28340) by @amelidev in https://github.com/google-gemini/gemini-cli/pull/29468 Changelog for v0.61.0-preview.1 by @gemini-cli-robot in https://github.com/google-gemini/gemini-cli/pull/29469 Cha…

2026-10-06 · github.com/github/github-mcp-server

Highlights :sparkles: More and more agents are supporting Code Mode or Programmatic Tool Calling so we have added support for structured outputs and output schemas to help do this effectively. These schemas are only advertised to clients advertising MCP 2026-07-28 spec support (…

2026-10-06 · github.com/langchain-ai/langgraph

Changes since 1.2.13 release(langgraph): 1.2.14 ( 9215)

2026-10-06 · github.com/mistralai/mistral-vibe

Added - The app-server can discover built-in plugins from roots an embedding application ships, alongside the ones inside the package. - Vibe Code warns when the selected model cannot view attached images. - Vibe Code sessions list their background processes in a side panel with…

2026-10-06 · github.com/sst/opencode

Core Improvements - Added canonical redirects and JSON and Markdown data formats for agent-readable stats. Bugfixes - xAI tool results now include supported images, while unsupported image formats are skipped. (@Jaaneek) Thank you to 3 community contributors: - @dc85: - docs(web…

2026-10-06 · github.com/OpenHands/OpenHands

1.25.0 (2026-10-06) What's Changed Features feat: outline the back navigation control on settings sub-pages by @errmakov in https://github.com/OpenHands/OpenHands/pull/17587 feat(settings): bulk-add provider models as LLM profiles by @georgeglarson in https://github.com/OpenHand…

2026-10-06 · github.com/strands-agents/harness-sdk

python/v1.58.1 Auto-drafted from commits in python/v1.58.0..python/v1.58.1 , grouped by conventional-commit type. Edit on the release page after publish if you want a polished writeup; the canonical release notes live on the website. 🚀 Features - feat(mcp/ts): restore legacy ta…

2026-10-05 · github.com/openai/codex

Bug Fixes - Preserve SYSTEMROOT , TEMP , and TMP when launching remote stdio MCP servers with explicitly configured remote environment variables, allowing Unix hosts to retain the Windows executor's startup environment. Changelog - 51121: Backport Windows remote MCP environment…

2026-10-05 · github.com/mastra-ai/mastra

Highlights Tool Context Can Read the Full Conversation ( agent.getMessages() ) Tools now have access to the current conversation state via context.agent.getMessages() in both standard and durable agent loops, including remembered messages and in-run responses—enabling richer, co…

2026-10-05 · github.com/modelcontextprotocol/typescript-sdk

Package Version --- --- @modelcontextprotocol/client 2.3.1 @modelcontextprotocol/server 2.3.1 @modelcontextprotocol/core 2.3.1 @modelcontextprotocol/server-legacy 2.3.1 @modelcontextprotocol/codemod 2.3.1 @modelcontextprotocol/node , express , hono , fastify unchanged Changes -…

2026-10-05 · github.com/earendil-works/pi

New Features - Tool patterns and --no-mcp : --tools and --exclude-tools accept patterns, for example --tools read,codemode,'mcp radius ' keeps only one MCP server's tools. --tools now keeps MCP tools unless an entry starts with mcp , and --no-mcp turns off MCP for one run. See T…

2026-10-05 · github.com/QwenLM/qwen-code

Bundled CLI Version This SDK release bundles CLI version: 0.25.0 Source: CLI built from source (same branch/ref as SDK) --- Bundled CLI Version This SDK release bundles CLI version: 0.24.7 Source: CLI built from source (same branch/ref as SDK) --- Bundled CLI Version This SDK re…

2026-10-07 · Simon Willison

<p><strong><a href="https://wikimediafoundation.org/news/2026/10/05/openai-rogue-agent-activities-found-on-wikimedia-projects/">OpenAI “rogue” agent activities found on Wikimedia projects</a></strong></p> Given how tempting a target wikis are for rogue agent…

2026-10-06 · OpenAI News

Learn how OpenAI and Ironclad are training and evaluating AI agents on complex contracting workflows to advance computer use for professional work.

2026-10-06 · GitHub Blog

We're rebuilding GitHub's Git infrastructure while GitHub keeps running, creating a foundation for agent-scale software development. The post Building Git infrastructure for agent-scale development appeared first on The GitHub Blog .

2026-10-06 · Cursor changelog

See and reply to the local agents running on your computer from the Cursor iOS app.

2026-10-06 · GitHub Changelog

If your Copilot usage metrics have shown agent activity or agent lines of code falling while Copilot usage kept growing, we& 8217;ve found the cause, and a fix is rolling out& 8230; The post Update your IDE to restore agent activity in Copilot usage metrics a…

2026-10-05 · AWS Machine Learning blog

Build a Retrieval Augmented Generation (RAG) application on Amazon Bedrock Managed Knowledge Base with LangChain, and see how agentic retrieval handles the multi-part questions that single-shot retrieval answers poorly. Run the same query through both paths,…

2026-10-05 · AWS Machine Learning blog

Multi-agent systems need deeper guarantees than fluent responses: they must select the right tools, respect constraints, and explain their decisions. Learn how to build a Strands-based multi-agent supply chain decisioning system and evaluate it with Amazon Be…

2026-10-05 · Cloudflare blog

We celebrated our 16th birthday with 46 announcements across open source, post-quantum security, AI agents, and developer platform upgrades. Here’s a day-by-day roundup of everything we shipped.

2026-10-05 · AWS Machine Learning blog

Amazon SageMaker optimized generative AI inference introduces the aws-ai-ml skill through the Agent Toolkit for AWS, giving coding agents like Kiro, Claude Code, and Codex deep expertise in inference optimization and benchmarking. Describe what you want, and…

2026-10-05 · AWS Machine Learning blog

Anthropic Claude Opus 5.5 and Claude Sonnet 5.5 are available on Amazon Bedrock in the AWS GovCloud (US) Regions. Learn how to use them with Claude Code, Anthropic's agentic coding tool, for compliance-aligned, AI-assisted development on regulated and ITAR wo…

2026-10-05 · Hacker News · 482 points · 325 comments

2026-10-05 · Hacker News · 299 points · 194 comments

2026-10-06 · Hacker News · 149 points · 77 comments

2026-10-05 · Hacker News · 61 points · 84 comments