AI Coding Live News

Cursor marketplace served a tampered Claude Code 2.1.313 extension with an SSH backdoor, affecting at most 5,000 users

Cursor posted a security notice on X at 07:46 UTC on Oct 30: version 2.1.313 of Anthropic.claude-code in its VS Code extension marketplace was a maliciously modified build, not developed by Anthropic, available from about 2:27am to 1:35pm PT on Oct 29 and affecting at most 5,000 users. The payload collects host details, adds an attacker SSH key, tries to open a reverse SSH tunnel and installs persistence. Cursor pulled the version, shut down and rebuilt the marketplace, rotated keys and had the attacker server taken offline; it asks users to update Claude Code for VS Code to 2.1.314 and follow the check and cleanup steps in its blog post.

Key Takeaways

  • Scope: Anthropic.claude-code 2.1.313 (darwin-arm64 and win32-x64 packages) in the Cursor extension marketplace, downloadable from about 2:27am to 1:35pm PT on Oct 29 (about 11 hours), at most 5,000 users
  • Payload: collects hostname, username, OS, environment variable names, Git email and public IP; adds an attacker SSH key labeled svc-telemetry; tries a reverse SSH tunnel, retrying about every 60 seconds; reports to /beacon on port 8099
  • Cursor says enabling the local SSH service needs admin rights, so that step fails on most macOS and Windows hosts, but the key, persistence and beacon still run; the attacker server is now offline
  • Cursor pulled the version, shut down and rebuilt the marketplace, rotated keys and confirmed no other extensions were tampered with; it has no evidence other versions or Anthropic's official distribution were affected
  • Self-check: on macOS run grep svc-telemetry ~/.ssh/authorized_keys; if found, isolate the host, run Cursor's remediation script, rotate credentials from a trusted machine, and update to 2.1.314
Read full story

LiteLLM 1.107.0 hit by a supply-chain compromise: PyPI wheels and Docker images shipped a credential stealer and backdoor; LiteLLM says it is contained and advises pinning 1.106.2

On October 21 the release pipeline of the popular LLM gateway LiteLLM was compromised. A malicious 1.107.0 was live on PyPI for about two hours (11:39 to 13:23 UTC), and the Docker tags v1.107.0, latest, main-latest and main-stable pointed to a poisoned image from 11:46 to 14:20 UTC. LiteLLM's incident report says the payload steals cloud, SSH, AI-tool and proxy keys on every Python start; the artifacts are pulled, OSS users should pin 1.106.2 and rotate secrets, and the private enterprise registry was not affected.

LiteLLM 1.107.0 hit by a supply-chain compromise: PyPI wheels and Docker images shipped a credential stealer and backdoor; LiteLLM says it is contained and advises pinning 1.106.2

Key Takeaways

  • Scope (vendor figures): all 7 PyPI wheels of litellm==1.107.0, live 11:39:51 to 13:23 UTC; 4 Docker Hub and GHCR tags poisoned from 11:46:56 UTC
  • Attack chain: the attacker held 3 sets of developer GitHub CLI credentials, one belonging to an org owner, used it to disable branch protection and force-push, then had the release workflow build and sign from the lookalike repo Berri-AI/litellm
  • Payload: cook.pth, cook.py and sitecustomize.py run on any Python start and survive uninstalling litellm; a second loader fetches remote code hourly
  • Fix: delete the 3 files and matching .pyc first, then pin litellm==1.106.2 or rebuild from scratch, and rotate every provider key in the proxy DB, the master key and the database password
  • This is LiteLLM's second supply-chain incident of 2026 (versions 1.82.7/1.82.8 in March); the GitHub source tag v1.107.0 itself is clean
Read full story

Claude Code desktop reworks multi-session flow: saved environments, nested parallel sessions, /btw side tabs and a needs-you sidebar

On 2026-10-14 (UTC) ClaudeDevs announced a Claude Code desktop update built for running many sessions side by side: a new-session screen with recent folders, saved environments (several folders, an SSH host or the cloud) with an optional worktree per folder, nested sessions for parallel tasks that report only results back to the main thread, one-click follow-up sessions, /btw side questions in their own tab, and a sidebar that separates working sessions from ones that need you, plus a live to-do list, recap cards and a side rail showing where a session runs, its context and its changes. Update the desktop app to get it; Anthropic published no performance numbers.

Claude Code desktop reworks multi-session flow: saved environments, nested parallel sessions, /btw side tabs and a needs-you sidebar

Key Takeaways

  • 6-post official thread; the lead post had about 15.8K likes and 1.31M impressions at fetch time
  • Parallel work: each task Claude runs in parallel becomes a nested session that reports only its result back, keeping the main thread readable
  • Saved environments: folders, an SSH host or the cloud, with an optional Git worktree per folder (default <project-root>/.claude/worktrees/)
  • Attention: sidebar splits working vs needs-you sessions; live to-do, recap card on hand-off; /btw (or Cmd+;) side questions stay out of the main history
  • No benchmarks published; users already ask to un-nest forked sessions in the sidebar (GitHub issue #100216)
Read full story

Codex composer predictions enter beta: Codex suggests your next message, Tab to accept, free of usage for Pro

On Oct 9 OpenAI opened composer predictions in beta in the Codex desktop app for personal ChatGPT Pro users. After each response Codex may prefill your next message from the current thread; press Tab to accept and edit before sending. Local and SSH threads only, with GPT-6 Astra and GPT-6.1 Sol; generating predictions does not count toward usage limits during the beta.

Codex composer predictions enter beta: Codex suggests your next message, Tab to accept, free of usage for Pro

Key Takeaways

  • Personal ChatGPT Pro (18+), Codex desktop app, local and SSH threads only
  • Supported models: GPT-6 Astra and GPT-6.1 Sol
  • Predictions are free during beta; sent messages bill normally
  • Tab accepts without sending; disable via Settings → General → Composer → Show predictions
  • Announcement post: ~3,250 likes and ~230K views within hours
Read full story
ADSponsored

Pydantic AI 2.52.0: unified Workspaces for Coder/Shell; web_fetch HTML DoS fix; CLAI2 ships

Pydantic AI shipped v2.52.0 on 2026-09-30 (pydantic-ai==2.52.0): ctx.workspace unifies local/sandbox file+command APIs with E2B, Fly.io Sprites, Modal, SSH, and Bubblewrap backends; harness moves in-repo to 0.52.0; first pydantic-clai2 release (uvx pydantic-clai2). Also patches local web_fetch nested-HTML resource exhaustion (GHSA-v36g-jcw9-x7cw, CVSS 6.5) and adds Claude Sonnet 5.5 plus GPT-6.1 Sol support.

Pydantic AI 2.52.0: unified Workspaces for Coder/Shell; web_fetch HTML DoS fix; CLAI2 ships

Key Takeaways

  • Release v2.52.0; 533 commits ahead of v2.51.0
  • Security: local web_fetch nested-HTML DoS patched (GHSA-v36g-jcw9-x7cw, CVSS 6.5); v1 patch 1.107.7; provider-native fetch unaffected
  • Workspaces via ctx.workspace (#6492) with E2B/Sprites/Modal/SSH/Bubblewrap backends; harness in-repo at 0.52.0; CLAI2 first release
  • Models: Claude Sonnet 5.5 (#8974), GPT-6.1 Sol (#9305); Anthropic default max_tokens 16384 on Sonnet 4.5+ (#9025)
  • Upgrade: pip install -U 'pydantic-ai==2.52.0'; uvx pydantic-clai2; docs: Workspace + Harness
Read full story

Claude Code 2.1.285: `claude --desktop`; plugin configure & MCP install-time config; allowedProviders lock-down

Anthropic Claude Code shipped v2.1.285 on 2026-09-29 (npm @anthropic-ai/[email protected]): claude --desktop opens the desktop app on the current directory or a resumed session; claude plugin configure plus --config server.key=value set MCP options at install time; managed allowedProviders limits which API providers a machine may use; CLAUDE_CODE_DISABLE_WEB_FETCH disables WebFetch. ~4 commits / 67 files vs v2.1.284, plus many SSH/sandbox/subagent permission fixes.

Claude Code 2.1.285: `claude --desktop`; plugin configure & MCP install-time config; allowedProviders lock-down

Key Takeaways

  • Release v2.1.285; ~4 commits / 67 files vs v2.1.284
  • claude --desktop opens Claude Desktop on cwd or --continue/--resume
  • plugin configure + install-time --config server.key=value for bundled MCP settings
  • Managed allowedProviders + CLAUDE_CODE_DISABLE_WEB_FETCH
  • Upgrade: npm i -g @anthropic-ai/[email protected]; docs at code.claude.com/docs
Read full story

Cline Desktop v0.0.37 Released: Adds Built-in Updater & Highlights Dialog, Patches Bedrock Reasoning Config

Cline Desktop (@cline_dev) has shipped release v0.0.37. The update introduces a comprehensive lifecycle management experience, embedding a dedicated 'About' view within Settings that enables in-app update checks, one-click restarts, and inline changelog inspection. Users are greeted with an updated 'What's New' dialog highlighting recent architectural milestones including SSH remotes, Git worktrees, pull request telemetry, and parallel sub-agents. Crucially, the release patches an AWS Bedrock inference bug that triggered 'Unknown parameter: reasoningConfig' on OpenAI models, while adding a macOS diagnostic export shortcut.

Cline Desktop v0.0.37 Released: Adds Built-in Updater & Highlights Dialog, Patches Bedrock Reasoning Config

Key Takeaways

  • Introduces an in-app About settings pane featuring direct update checking, automated restart patching, and release notes.
  • Launches a unified What's New dialog summarizing SSH remotes, Git worktrees, PR composer status, and parallel sub-agents.
  • Fixes an AWS Bedrock regression causing OpenAI models to crash with 'Unknown parameter: reasoningConfig'.
  • Adds a direct macOS Help menu shortcut for one-click diagnostic log exporting.
  • Signed binaries for macOS, Windows, and Linux available directly on GitHub Releases.
Read full story

Cline Desktop v0.0.37: About & What's new surfaces; Bedrock OpenAI inference profiles fix reasoningConfig errors

Cline Desktop v0.0.37 (2026-09-26) adds Settings → About (version/channel, check/restart updates, recent release notes, report issue), a one-time What's new dialog after updates, macOS Help→Export Diagnostics, and fixes Bedrock OpenAI inference-profile calls that failed with Unknown parameter reasoningConfig when reasoning effort was set.

Cline Desktop v0.0.37: About & What's new surfaces; Bedrock OpenAI inference profiles fix reasoningConfig errors

Key Takeaways

  • Shipped: desktop-v0.0.37 vs desktop-v0.0.36 on GitHub Releases
  • UX: Settings About page with version/channel, update buttons, release notes links, Report an issue
  • Onboarding: one-time What's new after update; Highlights on About reopens it
  • Ops: macOS Help→Export Diagnostics opens the export directly
  • Bedrock: OpenAI models via us.openai./global.openai. inference profiles no longer fail on reasoningConfig when reasoning effort is set
Read full story

Cognition ships Devin Cloud in Terminal and devin ssh: CLI cloud sessions plus SSH into Devin VMs

@cognition introduced Devin Cloud in Terminal and devin ssh: create, steer, and resume Devin Cloud sessions from the CLI with /cloud, and for the first time SSH into Devin’s dedicated VM then /handoff the work back to your own device.

Cognition ships Devin Cloud in Terminal and devin ssh: CLI cloud sessions plus SSH into Devin VMs

Key Takeaways

  • New CLI: /cloud to create, steer, and resume Devin Cloud sessions in the terminal.
  • devin ssh: first-time SSH into Devin’s dedicated VM.
  • /handoff: return cloud work to your own device for local workflows.
Read full story
Linked Models & Agents:

Navop open-sources a native all-in-one workspace with ACP for Codex, Claude Code, and OpenCode

@DanKornas introduced feigeCode/navop, a native desktop workspace that keeps database workbenches, SSH/local terminals, SFTP, and remote desktop in one app. AI features cover SQL help, terminal assistance, and an Agent Hub; builders can attach Codex, Claude Code, and OpenCode over ACP and optionally expose host tools via MCP. The repository had about 1.4k GitHub stars at verification.

Key Takeaways

  • Native all-in-one workspace for databases, SSH/terminals, SFTP, and remote desktop.
  • ACP hooks for Codex, Claude Code, and OpenCode plus an Agent Hub for terminals, project files, and Git diffs.
  • Optional local MCP tool exposure; feigeCode/navop had about 1.4k stars at verification.
Read full story
ADSponsored

Claude Code 2.1.275 ships with 96 CLI changes, send-now, and signed-shell sync

Claude Code Changelog announced 2.1.275 with 96 CLI changes. Highlights include send-now to interrupt a turn and immediately send queued messages, signed shells that sync Claude skills and plugins, and secret stripping from Git/SSH URLs in plugin and marketplace output to reduce credential leakage risk.

Key Takeaways

  • Added send-now shortcuts to interrupt a turn and immediately send all queued messages.
  • Signed shells can sync Claude skills and plugins while plugin and marketplace output strips secrets from Git/SSH URLs.
  • The release improves reliability and security for CLI-based agentic development workflows.
Read full story

Cursor 3.20.21: Computer Use on Mac, Max Mode in model picker, local agents can run tools, SSH remote windows

Community changelog: SpaceXAI Cursor updated to 3.20.21 with Computer Use on Mac, Max Mode visible in the model picker, local agents able to run tools, and windows connected over SSH to another computer. Also covers the open-agent chat box, deferred list refresh until window focus, and PR tabs that can sit in front of app tabs.

Key Takeaways

  • Computer Use on Mac; local agents can run tools.
  • Max Mode shows in the model picker; SSH remote work windows supported.
  • Also: open-agent chat box, focus-before-refresh lists, and PR tabs over app tabs.
Read full story

kooky: macOS terminal for AI coding agents with workspaces, sessions, git worktrees, CLI

Open-source (MIT) macOS terminal kooky is built for AI coding: sidebar workspaces and split panes, one-click built-in or custom agent sessions, live running/waiting/failed states, plus git worktrees, SSH workspaces, session history, and kooky-cli for scripted tab control.

Key Takeaways

  • Role: open-source macOS AI coding terminal centered on workspaces and agent sessions.
  • Features: split panes, one-click sessions, activity states, git worktrees/SSH, kooky-cli.
  • License: MIT.
Read full story
Linked Models & Agents: