Does Fork Chat Affect Cache? And How Long Does Cache Last?

[Abdelrahman_Mohamed]

I have a question about Cursor chat behavior:

1. Does using Fork Chat affect prompt/context cache in any way?
   For example, does a forked chat reuse the same cache, create a new one, or reduce cache efficiency?

2. Approximately how long does cache last before expiring?
   Is it session-based, time-based, or dependent on context changes?

Would appreciate clarification on how caching works in practice, especially for long coding sessions.

[Colin]

Hey @Abdelrahman_Mohamed!

You’ll get a cache hit on forked chats as long as the cache hasn’t expired!

@Abdelrahman_Mohamed

Approximately how long does cache last before expiring?
Is it session-based, time-based, or dependent on context changes?

Each provider is different. Anthropic models, for example, have a 5-minute TTL.

Some recent discussion about caching over here.

Understanding Write Cache

Hey @Brandyn_Brosemer! When you send a request, we build the prompt in a cache-friendly way and hand it to the underlying model provider (Anthropic, OpenAI, etc.), and the provider’s own cache is what decides whether you get a cache hit or a full re-seed. So the cache duration and refresh behavior are ultimately defined by the model provider, not by Cursor, and they don’t change based on whether you’re running locally, in a Cloud Agent, or self-hosted. Anthropic is the only provider that has a…