GitHub / anthropics/claude-code releases · Oct 8, 2026 · 3:22 AM

Claude Code 2.1.293 stops Claude redoing finished work after compaction and plugs an HTTP MCP memory leak

Released Oct 7, the update fixes Claude treating its last pre-compaction actions as unfinished and retracting or redoing them, fixes HTTP MCP connections holding every sent request until they closed, and now loads path-scoped rules and nested CLAUDE.md files when Claude reads a file via cat, head, or grep in Bash. It also makes Haiku 5.5 the default Haiku on the Anthropic API and adds agentType to the subagent status-line payload.

Read at github.com

Claude Code

An AI coding agent for terminal, IDE, web, and Slack

More news

View all

Claude Max and Team plans now include $100 to $500 a month in API credits, but not for Claude Code

Announced Oct 7, Max 5x gets $100 and Max 20x gets $200 a month, while Team gets $20 per Standard seat and $100 per Premium seat, pooled and capped at $500, once you link a Claude Console organization in billing. The credits cover the Claude API, Managed Agents, the Agent SDK, and the playground (not Claude Code or Bedrock/Vertex), and they expire each billing cycle with no rollover…

Claude Platform Docs 12 minutes ago

Codex Day 3: GPT-6 lands in ChatGPT's Chat tab and every paid account gets a banked usage reset

Codex lead Tibo's Day 3 post (Oct 7) headlines GPT 6 in ChatGPT Chat, with GPT 6 Sol for paid tiers now and GPT 6 Luna for Free and Go users from Oct 8, while the models in Work and Codex stay unchanged. He also said Codex and ChatGPT Work hit a new high of 40M active users and that a banked reset is loading into every paid account, so you can save it for when you actually hit your limit…

X / @thsottiaux (Codex lead) 2 hours ago

Codync turns Claude Code, Codex, and 40 more coding agents into bots you message from your phone

Shown on HN Oct 7, the MIT licensed project runs one Rust binary, codync host , on your Mac, Windows, or Linux machine that drives any agent in the ACP registry with the plans you're already signed into, and you chat with each bot (its own folder, memory, and approval rules) from an iPhone app, desktop app, or terminal. Remote access goes through a free end to end encrypted Cloudflare relay, and bots can ask each other for help, like a Claude bot requesting a Codex review…

Show HN / GitHub 3 hours ago

Copilot CLI's /model picker now finds your local Ollama models and switches to them mid-session

Starting in Copilot CLI 1.0.94 0 (announced Oct 7), /model lists tool calling, streaming capable models from a running Ollama instance next to the cloud ones, and you can add one for the current session without restarting. Picking a local model doesn't turn on offline mode or disable telemetry, so set COPILOT OFFLINE=true if you want that…

GitHub Changelog 4 hours ago

Liquid AI open-sources d1-3B, a decision model that answers in 8 ms on an RTX 4090 with zero output tokens

Released Oct 7 on Hugging Face alongside the experimental d1 omni 600M (text plus image or audio), d1 3B returns a typed answer in one forward pass instead of generating text, scoring 48.57 on the Decision Index v0.2.1 public split, which Liquid says matches Decider 35B A3B at 12x smaller. It has day one llama.cpp support and runs a question in 16 to 50 ms on Jetson boards, so it's a cheap local option for gating, routing, or moderation steps in an agent loop…

Liquid AI Blog 5 hours ago

Spotted something we missed? Start a thread.