Claude Code 2.1.218 Runs /code-review as a Background Subagent
Version 2.1.218 moves /code-review off your main conversation into a background subagent, and fork-context skills now background by default. Here is what changed and how to opt out.
Tag: ai-agents
213 posts · Page 10 of 22
Cursor Cloud Agents vs GitHub Copilot Coding Agent for Background PRs
Pick Copilot coding agent when the work starts and ends on GitHub and you want issue-to-PR with native branch protection. Pick Cursor cloud agents when you want a live, editor-attached VM, multi-repo tasks, and to take over the run by hand. Full feature matrix, the 59-minute cap, the Actions-approval gotcha, and June 2026 billing for both.
Claude Code 2.1.213 Puts Hard Caps on Runaway Subagent Fleets
Version 2.1.213 caps concurrent subagents and stops nested spawns by default, building on the per-session limits from 2.1.212. Here are the new defaults and env vars.
Fix: Claude Code Autocompact Thrashing on a Large File or Tool Output
Claude Code compacts, then a single oversized file read or tool result immediately refills the window and it compacts again. Drop the item with /clear, read files in slices, and force big output to disk.
Microsoft Agent Framework orchestration: sequential vs concurrent vs group chat vs handoff vs magentic
Sequential for pipelines, concurrent for fan-out, group chat for moderated rounds, handoff for routing, magentic for open-ended planning. The C# builders and how to choose.
Fix: MCP Server Throws "fetch is not defined" and EBADENGINE on Node.js Below 18
An MCP server on Node 16 warns EBADENGINE at install, then dies with 'fetch is not defined' on the first tool call. Upgrade to Node 18+ (20+ for the 2.x SDK) or polyfill the web globals.
Fix: Claude Code misreads an MCP server's stderr startup message as an error
Claude Code logs every MCP server stderr line at [ERROR] and marks working servers as failed. If your tools still run, it is cosmetic. Here is how to confirm it and quiet the noise.
How to Package Reusable Domain Expertise as an Agent Skill in .NET with the Microsoft Agent Framework
There is no single Skill type in the Microsoft Agent Framework, but you can package domain expertise as a reusable agent, reuse it in-process with AsAIFunction, and advertise it across frameworks as an A2A AgentSkill. Full walkthrough on Agent Framework 1.0 and .NET 11.
Fix: all MCP servers fail to load after one malformed-JSON syntax error in the config
One trailing comma or unescaped Windows path in your MCP config makes every server vanish, not just the broken one. Validate the JSON, fix the five usual suspects, restart.
How to Set Per-Session AI Credit Spend Limits in the Copilot CLI and SDK
Copilot CLI 1.0.66 and SDK 1.0.5 (public preview, July 1 2026) add per-session AI credit limits. Cap what a single agent run can spend with --max-ai-credits, /limits set, or SessionLimitsConfig, and understand why it is a soft cap that can overshoot.