●QUOTA — The 50 percent weekly usage boost for Claude Code subscribers ends August 19. One day left to front-load any heavy parallel work●PRICING — Claude Sonnet 5's introductory rate of $2 per million input tokens and $10 output ends August 31; standard pricing of $3 and $15 takes over on September 1●MIGRATION — The legacy Workbench and the experimental prompt tool APIs retired on August 17. Anything that depended on them now needs a hand-rolled equivalent on the Messages API●GOVERNMENT — Claude for Government is in beta. Anthropic remains the contracting and billing party, so agencies can start without a separate cloud provider relationship●PROVENANCE — Claude models released from August 2 onward embed a machine-readable watermark in generated text. It applies worldwide rather than only in the EU, with no stated effect on quality, speed, or price●CLI — v2.1.233 adds memory cgroup support for Bash tool commands on Linux, so CLAUDE_CODE_TOOL_MEMORY_LIMIT keeps a runaway build from stalling the session●QUOTA — The 50 percent weekly usage boost for Claude Code subscribers ends August 19. One day left to front-load any heavy parallel work●PRICING — Claude Sonnet 5's introductory rate of $2 per million input tokens and $10 output ends August 31; standard pricing of $3 and $15 takes over on September 1●MIGRATION — The legacy Workbench and the experimental prompt tool APIs retired on August 17. Anything that depended on them now needs a hand-rolled equivalent on the Messages API●GOVERNMENT — Claude for Government is in beta. Anthropic remains the contracting and billing party, so agencies can start without a separate cloud provider relationship●PROVENANCE — Claude models released from August 2 onward embed a machine-readable watermark in generated text. It applies worldwide rather than only in the EU, with no stated effect on quality, speed, or price●CLI — v2.1.233 adds memory cgroup support for Bash tool commands on Linux, so CLAUDE_CODE_TOOL_MEMORY_LIMIT keeps a runaway build from stalling the session

TAG

Caching

2 articles

← Back to all tags

Claude Code¹ WebFetch¹ Environment Variables¹ Solo Development¹ claude-api¹ redis¹ semantic-cache¹ cache-invalidation¹ production¹ observability¹

⟐ Claude Code/2026-08-18Intermediate

Choosing a WebFetch Cache TTL That Fits the Way You Research

Claude Code lets you tune the WebFetch URL cache TTL. Here is how to see the shape of your own research sessions with a tiny observation server, then trade fetch count against freshness with numbers instead of guesswork.

⬡ API & SDK/2026-06-18Advanced

When Your Claude API Response Cache Returns Stale Answers and Near-Miss Wrong Ones — Field Notes on Freshness and False-Hit Suppression

A Claude API response cache improves latency and cost immediately, but the problems that hurt in production are not average hit rate — they are stale hits and semantic false hits. Here is the key design, freshness management, false-hit suppression, and observability that keep a cache honest.