◉CLAUDE LABJP
●MODEL — Claude Opus 4.8 and Haiku 4.5 arrive in the Messages API for coding and agentic work●CODE — Claude Code adds /rewind to resume before /clear, with steadier MCP reliability and OAuth retries●CODE — CPU use during streaming drops about 37%, improving stability on long-running sessions●CLOUD — Claude is generally available in Microsoft Foundry on Azure with Azure-native access●SECURITY — Static API keys can now be replaced with WIF short-lived, scoped credentials●POLICY — The US government clears Anthropic to release Mythos 5 to about 100 firms and agencies●MODEL — Claude Opus 4.8 and Haiku 4.5 arrive in the Messages API for coding and agentic work●CODE — Claude Code adds /rewind to resume before /clear, with steadier MCP reliability and OAuth retries●CODE — CPU use during streaming drops about 37%, improving stability on long-running sessions●CLOUD — Claude is generally available in Microsoft Foundry on Azure with Azure-native access●SECURITY — Static API keys can now be replaced with WIF short-lived, scoped credentials●POLICY — The US government clears Anthropic to release Mythos 5 to about 100 firms and agencies
TAG

Context Management

3 articles
← Back to all tags
Related:
Claude API2Agent SDK1MCP1Token Optimization1chat implementation1indie development1production issues1streaming1session management1cost optimization1Claude Code1long sessions1
⬡ API & SDK/2026-06-30Advanced

When a Tool Result Is Too Big and Melts Your Context Window: Designing Cursor-Based Pagination

When a list tool returns hundreds of rows at once, an agent's context can collapse in a single call. Here is a cursor-based pagination design that keeps tool output small and protects your token budget, with working code.

⬡ API & SDK/2026-05-14Advanced

6 Traps I Hit Building In-App AI Chat with Claude API — A Record of Getting to Production

Six real design mistakes I encountered shipping Claude API in-app chat to production — covering context management, streaming error detection, guardrails, session persistence, model versioning, and cost monitoring. Includes working TypeScript code.

⟐ Claude Code/2026-04-21Advanced

Keeping Claude Code Accurate Through Long Sessions: Signals of Context Decay and What to Do About Them

After a few hours in the same Claude Code session, output quality can quietly slip. This is a practical field guide to spotting the early signals, choosing where to end a session, and keeping a long workflow reliable.