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
A
Anthropic@AICoder·
👀89
🔥80

Claude Code 2.1.314 adds a block on writes outside working directories, IdP group routing for the apps gateway, and idle compaction in VS Code and Desktop

Anthropic published Claude Code v2.1.314 on GitHub at 01:06 UTC on Oct 30. The official CHANGELOG lists 119 entries, more than half of them fixes. The new features lean enterprise: permissions.blockWritesOutsideWorkingDirectories makes Write, Edit and NotebookEdit refuse paths outside the working directories in every permission mode; Claude apps gateway upstreams can be limited to IdP groups, and Bedrock upstreams can log which guardrail fired; idle compaction now also runs in VS Code and the Code tab of Claude Desktop. It also fixes sessions failing repeatedly when an admin caps effort, and claude -p exiting 0 with no output when startup failed.

Key Takeaways

  • Size: the official v2.1.314 CHANGELOG has 119 entries, more than half of them fixes; released at 01:06 UTC on Oct 30
  • Safety: the new permissions.blockWritesOutsideWorkingDirectories setting stops Write, Edit and NotebookEdit from writing outside the working directories in every permission mode
  • Enterprise gateway: upstreams take an optional groups list so only developers in those IdP groups are routed there, failover included; Bedrock upstreams gain guardrail_trace
  • Experience: idle compaction now runs in VS Code and the Claude Desktop Code tab, summarizing idle conversations above 200K tokens
  • Fixes: when an admin caps effort, Claude Code lowers it and retries; a failed claude -p startup now prints the error and exits 1
Read full story
Linked Models & Agents:

GitHub Copilot Automations go team-wide: repo-owned shared automations, 24 new triggers, 20 new tools and AI credit limits

At GitHub Universe on Oct 28, GitHub shipped a batch of Copilot Automations updates. Shared automations now belong to the repository, act as Copilot, bill AI credits to the repo owner and keep running after their creator leaves. Automations gain 24 new GitHub event triggers, REST API triggers from external systems and chaining, plus 20 new tools and custom MCP servers. Teams can cap AI credits per run, day, week or month, automations can propose improvements to their own prompts from real outcomes, and VS Code 1.144 can run them in the cloud.

GitHub Copilot Automations go team-wide: repo-owned shared automations, 24 new triggers, 20 new tools and AI credit limits

Key Takeaways

  • Shared automations belong to the repository: anyone with read access can view them, anyone with write access can edit, actions are attributed to Copilot and AI credits bill to the repo owner
  • 24 new triggers across issues, pull requests, discussions and security alerts, plus REST API triggers from systems like Jira, Sentry and PagerDuty
  • 20 new GitHub tools (merge PRs, retry workflow runs, upload screenshots and more) and support for custom MCP servers
  • AI credit limits can be set per run, day, week or month; org repos need an admin to enable the "Allow use of Copilot cloud agent billed to the organization" policy
  • Rolling out to Copilot Pro, Pro+, Max, Business and Enterprise; VS Code 1.144 runs them in the cloud with chat.automations.cloud.enabled
Read full story

Microsoft opens the GitHub-built Copilot harness in Foundry Agent Service: public preview, 20+ frontier models plus BYOK, billing from Dec 1

During GitHub Universe on Oct 28, Microsoft put the Microsoft Copilot harness, the shared agent execution layer behind Copilot Code, Copilot Studio, the GitHub Copilot app, the CLI and VS Code, into Foundry Agent Service as a public preview. Microsoft runs the agent loop and sandbox while developers supply instructions, skills, tools and model choice; Microsoft says it works across 20+ frontier models plus bring-your-own-key. Long-running resilience for hosted agents also reached GA. Harness runtime usage is free until Dec 1.

Microsoft opens the GitHub-built Copilot harness in Foundry Agent Service: public preview, 20+ frontier models plus BYOK, billing from Dec 1

Key Takeaways

  • Microsoft says the harness spans 20+ frontier models plus bring-your-own-key, so you can swap models without rewriting orchestration (official blog)
  • Preview building blocks: reusable skills, Foundry and MCP tools with explicit auth and approvals, file and code execution with built-in subagent delegation, and source-controlled agent definitions
  • Pricing: harness runtime is free until Dec 1; after that sandbox compute is USD 0.0994 per vCPU-hour and 0.0118 per GiB-hour, with model inference billed separately (Foundry blog)
  • Long-running resilience for hosted agents went GA the same week: interrupted work restarts with its original input, and your app saves checkpoints
  • Limits: you pick the harness only when creating a new agent; existing agents are unchanged and switching later is not supported yet
Read full story
ADSponsored

Anthropic donates the Agent Skills open standard to the Linux Foundation’s Agentic AI Foundation, after 70+ agent platforms adopted it with 1M skills published and nearly 280M installs

On 2026-10-22 Anthropic said it is donating Agent Skills, the open standard that teaches agents a task through a folder with a SKILL.md file, to the Agentic AI Foundation (AAIF) under the Linux Foundation, the same neutral home it gave MCP. The donation covers the Agent Skills name and logo, the GitHub organization and the agentskills.io domain. Anthropic says more than 70 agent platforms, including ChatGPT, Cursor, GitHub Copilot and VS Code, have integrated the standard since December 2025, with 1 million skills published and nearly 280 million installs. Engineers from Anthropic, Google, OpenAI and others will maintain it as individuals.

Anthropic donates the Agent Skills open standard to the Linux Foundation’s Agentic AI Foundation, after 70+ agent platforms adopted it with 1M skills published and nearly 280M installs

Key Takeaways

  • Official figure: 70+ agent platforms have integrated Agent Skills, including ChatGPT, Cursor, GitHub Copilot and VS Code
  • 1 million skills published and nearly 280 million installs so far (Anthropic figures)
  • Donated: the Agent Skills name and logo, the GitHub organization and the agentskills.io domain; you can keep using or contributing without joining AAIF
  • Lead Maintainers are David Soria Parra and Mahesh Murag, with engineers from Anthropic, Google, OpenAI and others maintaining it as individuals
  • Proposed first roadmap: versioned releases, a formal proposal process and security guidance for people who write and install skills
Read full story

VS Code 1.143 makes the Copilot SDK-based harness the default, adds multi-model comparison and on-device MAI Code 1.1 Flash

Microsoft shipped Visual Studio Code 1.143. The Copilot harness, built on the Copilot SDK, is now the default for new sessions and works across the editor and Agents window. A Compare Models preview runs several models on one task with an optional Judge model, an experimental mode runs MAI Code 1.1 Flash on a local NVIDIA GPU, and large chats open much faster.

VS Code 1.143 makes the Copilot SDK-based harness the default, adds multi-model comparison and on-device MAI Code 1.1 Flash

Key Takeaways

  • Default harness: new sessions use the Copilot harness built on the Copilot SDK, which can run in the background and move between the editor and the Agents window
  • Compare Models (Preview): one prompt runs 2 or more models in parallel, mixing Copilot, Claude and Codex harnesses, with an optional Judge model scoring time and token use and a Synthesize step
  • On-device models (Experimental): download MAI Code 1.1 Flash to run locally, labeled On-device with no AI credits used; needs an NVIDIA GPU with 96 GB+ memory
  • Performance (vendor figures): cold-opening a ~1,150-request chat dropped from 35.6 s to 9.0 s, and window freeze time from 28.3 s to 0.6 s
  • Also: the editor diagnostic highlight limit rises from 500 to 5,000 per file, and the Windows installer can install GitHub Copilot CLI
Read full story

VS Code Preview Introduces Canvases: Shared Workspaces for Developers and Coding Agents

The Microsoft VS Code team announced Canvases in VS Code Preview (v1.142), introducing dedicated shared visual workspaces connecting developers with autonomous coding agents. Addressing the severe UX limitations of cramped sidebar chat windows—where complex multi-file architectural modifications and agent diffs become hard to track—Canvases provides an expansive, interactive infinite-canvas whiteboard. Developers and agents (such as GitHub Copilot, Claude Code, and Cline) can collaboratively organize system flowcharts, live interactive code diffs, execution traces, and unit test rollouts side by side.

VS Code Preview Introduces Canvases: Shared Workspaces for Developers and Coding Agents

Key Takeaways

  • Microsoft VS Code Preview v1.142 introduced Canvases, pioneering a spatial human-agent collaborative interface
  • Transceives beyond claustrophobic sidebar chats to an expansive, pan-and-zoom whiteboard mapping concurrent multi-file agent diffs
  • Embeds code files, architecture diagrams, interactive git diffs, terminal outputs, and test runners as unified interactive cards
  • Natively bridges GitHub Copilot, Claude Code, and third-party coding agent harnesses, accelerating IDE spatial development
Read full story
A
Anthropicgithub.com·
👀132
🔥87

Claude Code 2.1.302 turns on fork subagents by default across claude -p, Agent SDK, desktop and VS Code; standalone Claude Design closes Dec 14

Claude Code v2.1.302 (Oct 16) makes fork subagents the default in claude -p, the Agent SDK, desktop and VS Code, starts permission-mode-less headless sessions on third-party providers in default mode, and adds CLAUDE_CODE_AUTO_MODE_MODEL. It also flags that standalone Claude Design (claude.ai/design) closes on Dec 14, 2026; design systems must be migrated to Claude Artifacts, while chats and comments are not carried over.

Key Takeaways

  • Fork subagents now default-on in claude -p, Agent SDK, desktop and VS Code; disable with CLAUDE_CODE_FORK_SUBAGENT=0
  • Headless sessions with no permission mode on third-party providers start in default mode (telemetry off or fresh install); --permission-mode auto keeps auto
  • New CLAUDE_CODE_AUTO_MODE_MODEL picks the client-side auto mode classifier model; prompt/agent hooks capped at 12 concurrent per event
  • Read tool refuses image sources over 128 MB; MCP servers on protocol 2026-07-28 that omit resultType/ttlMs/cacheScope no longer break
  • Standalone claude.ai/design closes Dec 14, 2026; chats, comments and public links are not migrated and originals are deleted afterward
Read full story

GitHub Copilot updates HydraFusion and adds HydraFusion Max, with Claude Opus 5.5 and the GPT-6 family in its model pool

On 2026-10-14 GitHub updated HydraFusion, Copilot's multi-model orchestration feature, and added HydraFusion Max for harder tasks. The pool now includes Claude Opus 5.5, GPT-6 Astra, GPT-6.1 Sol and GPT-6 Luna; effort is tuned per stage (medium for drafts, high for review), Cascade gains a judging step, and Critique now inspects the workspace with tools using parallel critics. Both remain in research preview across VS Code, the Copilot app and Copilot CLI.

Key Takeaways

  • Pool: Claude Opus 5.5, GPT-6 Astra, GPT-6.1 Sol, GPT-6 Luna, chosen per workflow (GitHub Changelog)
  • Per-stage effort: medium for drafts, high for review (previously each model's default)
  • Cascade adds a judge that requests repair only when needed; Critique uses tools on the workspace plus parallel critics
  • Two tiers: HydraFusion (balanced) and HydraFusion Max (deepest reasoning, orchestration still minds tokens)
  • Available in VS Code, Copilot app and Copilot CLI on Pro, Pro+, Business and Enterprise with preview features enabled
Read full story

Kilo Code 7.8.1: Agent Manager browser for public HTTPS/CDN previews; CycloneDX SBOM on every artifact

Kilo-Org shipped open-source coding agent platform Kilo Code v7.8.1 (includes 7.8.0) on 2026-09-25. 7.8.0 brings a high-resolution streamed Agent Manager browser for public HTTPS pages and CDN assets in localhost previews, with install/retry/settings guidance, native cross-origin checks, ordered clipboard, and stalled-session cleanup; plus close-task commands and a stoppable session-cleanup pass. 7.8.1 publishes CycloneDX SBOMs for every CLI archive, npm package, container image, VS Code extension, and JetBrains plugin—SHA-256 bound and GitHub-attestation signed. Azure Entra ID accepts resource name or full endpoint URL.

Kilo Code 7.8.1: Agent Manager browser for public HTTPS/CDN previews; CycloneDX SBOM on every artifact

Key Takeaways

  • Shipped: v7.8.1 / @kilocode/[email protected]
  • 7.8.0: Agent Manager browser for public HTTPS/CDN; close-task cmds; stoppable session cleanup
  • 7.8.1: CycloneDX SBOM + SHA-256 + GitHub attestation on every artifact
  • Azure Entra ID: resource name or full endpoint; block nested var refs in project MCP headers
  • Install: VS Code Marketplace / CLI / JetBrains; docs at kilo.ai/docs
Read full story
ADSponsored

Cline v4.1.21: ai& Japan OpenAI-compatible provider, 6,386 models / 209 providers, local long-reply compact retry

Cline VS Code extension shipped v4.1.21 on 2026-09-24 with a new Japan OpenAI-compatible provider (ai&), a refreshed catalog of 6,386 models across 209 providers (19 unpinned defaults change—11 to Claude Opus 5.5 including GitHub Copilot and Vertex), and compact-and-retry once when local servers (llama.cpp/Ollama/LM Studio) hit output-token limits. Minimum js-yaml raised to 4.3.2 for frontmatter parsing security.

Cline v4.1.21: ai& Japan OpenAI-compatible provider, 6,386 models / 209 providers, local long-reply compact retry

Key Takeaways

  • New provider ai& (Japan OpenAI-compatible open-weight endpoint)
  • Catalog: 6,386 models / 209 providers; 19 unpinned defaults shift (11 → Opus 5.5 incl. Copilot & Vertex)
  • Local models compact-and-retry once on output-token caps
  • js-yaml floor 4.3.2 for rule/skill frontmatter
  • Install via Marketplace or cline-4.1.21.vsix
Read full story

Toolport open-sources a local MCP gateway: configure once, share across Claude, Cursor, Codex

@DanKornas highlighted Toolport (MIT, github.com/btsouth/toolport): a local-first MCP gateway that lets you add and authenticate servers once, then share them across Claude, Cursor, Codex, VS Code, and peers via client profiles. Credentials stay in the OS keychain, with tool disablement, approval for destructive calls, and activity review. The project markets lazy discovery for large tool-token savings, plus a CLI and OpenAPI-generated full-API MCP server packs.

Key Takeaways

  • Local MCP gateway: one-time add/auth, then share across Claude/Cursor/Codex/VS Code.
  • Secrets in OS keychain; disable tools, approve destructive calls, review activity.
  • MIT open source; lazy discovery aims to cut tool tokens; CLI and OpenAPI server packs available.
Read full story

Claude Code 2.1.274: 108 CLI changes, tool_use_id loop fix, MCP and memory warnings

The unofficial-but-tolerated Claude Code Changelog bot (@ClaudeCodeLog) posted 2.1.274 with 108 CLI changes. Highlights: a visible critical-memory warning with safe free/restart steps; sessions no longer loop forever on unexpected tool_use_id 400s (transcripts self-heal when possible, else a clear /rewind error ends the loop); MCP 403 insufficient_scope now names missing permissions and points to /mcp re-auth; CLAUDE_CODE_MCP_STARTUP_WAIT_MS bounds how long the first non-interactive turn waits for MCP servers. Many more MCP/stream, /goal resume, self-hosted runner 401, VS Code, and cloud session/routine fixes. Source: anthropics/claude-code CHANGELOG #21274.

Key Takeaways

  • 2.1.274 ships 108 CLI changes: critical-memory warning with safe restart steps
  • Stops unexpected tool_use_id 400 retry loops; transcripts self-heal or show /rewind
  • MCP 403 names missing scopes and points to /mcp; CLAUDE_CODE_MCP_STARTUP_WAIT_MS added
Read full story

GitHub Copilot Auto adds efficiency, balance, and intelligence cost/quality tiers

GitHub staffer Pierce Boggan (@pierceboggan) announced Copilot Auto model selection now offers three tiers—efficiency (cost-first), balance (cost/quality/latency), and intelligence (quality-first). Auto still picks a model per prompt; usage is billed on the selected model, and paid subscribers keep a 10% Auto usage discount. Rolling out in VS Code, Copilot CLI, and the GitHub Copilot app (changelog 2026-09-14).

Key Takeaways

  • Copilot Auto adds efficiency, balance, and intelligence cost/quality tiers.
  • Still selects per prompt; billed on the chosen model with a 10% Auto discount for paid plans.
  • Rolling out in VS Code, Copilot CLI, and the GitHub Copilot app.
Read full story

GitHub Copilot adds Gemini 3.8 Flash to the model picker, including Pro seats

Gemini 3.8 Flash is now in the GitHub Copilot model picker across Pro, Pro+, Max, Business, and Enterprise—on VS Code, Visual Studio, Copilot CLI, cloud agent, Copilot app, JetBrains, Xcode, and Eclipse. Unlike GPT-6 Astra, Flash is available on plain Pro; introductory usage-based provider pricing runs through 2026-12-31.

Key Takeaways

  • Gemini 3.8 Flash is in Copilot's model picker, including plain Pro.
  • Surfaces: VS Code, Visual Studio, Copilot CLI, cloud agent, JetBrains, and more.
  • Introductory usage-based provider pricing through 2026-12-31; Biz/Enterprise still auto-enable new models unless policy is off.
Read full story