Official updates for developers building with @ClaudeAI
May 8 • 7 tweets • 2 min read
Last week we shipped 50+ Claude Code reliability fixes. This week it's 60+ more.
Smoother long-running sessions, a more efficient agent loop, auth that works in more environments, and terminal fixes: 🧵
1/ Stability
• claude -p now handles >10MB of piped stdin
• Requests resume cleanly after waking a Mac from sleep
• Memory stays bounded when a stdio MCP server writes non-protocol data to stdout (was growing past 10GB)
• Output now appears reliably after thinking completes
May 6 • 6 tweets • 2 min read
In Claude Managed Agents, we’ve added multiagent orchestration, an outcomes loop for rubric-driven self-improvement, dreaming for self-learning, & webhooks.
Multi-agent orchestration enables task delegation to specialized sub-agents.
Each sub-agent has its own context window, but they share a container + filesystem to coordinate work.
Claude Code ships with a built-in skill for working with the Claude Platform.
Useful for model migrations, using API features (e.g., prompt caching), or onboarding to newer APIs like Claude Managed Agents.
Running "/claude-api migrate" in Claude Code reviews your codebase and walks you through updating model names, prompts, and effort settings for a new Claude model (like Opus 4.7).