Design a Cache Index API with Explicit Freshness and Invalidation
A useful cache API needs more than get and set. Define identity, freshness, generations, and failure behavior so clients know when a response is safe to reuse.
Read the articleSubject collection / 3 articles
Invalidation
Explore the invalidation questions that connect these guides.
Invalidation connects a change in the world with a decision to stop reusing old work. It can follow a source update, a policy revision, or an access change. This collection focuses on making that relationship explicit rather than treating expiration as a universal solution.
Trace one changed dependency through your system. Which entries become unsuitable, what does a caller see, and where does the replacement come from? A useful invalidation design explains all three. Read the API and agent examples together to see why different reuse layers may need different boundaries.
Articles about invalidation
Agent Memory vs. a Response Cache: Give Each Store a Clear Job
A remembered preference, an active task, and a reusable answer need different rules for identity, updates, retention, and evaluation.
Read the article
What Is a Cache Index? Keys, Freshness, and Safe Reuse
A cache index helps a system decide which stored result belongs to a request—and whether reusing it is still appropriate.
Read the articleTake the next step.
Start with the Cache Index API guide to place the terminology in context. Then explore Agents Cache Index for a connected design question.
Read across the index.
A topic can cross several systems. Browse the complete Lab for the surrounding articles, or use the 22-topic directory to find a different entry point.