Add cache keep-alive to prevent expensive prompt cache re-creation on idle sessions#75
Open
Add cache keep-alive to prevent expensive prompt cache re-creation on idle sessions#75
Conversation
… idle sessions Anthropic's prompt cache has a 5-minute TTL that expires when a session is idle, forcing a full cache write (1.25x input cost) on the next request. This adds a configurable keep-alive mechanism that sends minimal API requests to refresh the cache TTL before it expires, keeping cached tokens at the 0.1x read rate. Key design decisions: - Keep-alive bypasses the Agent streaming state machine entirely (own method) - Sends max_tokens=1, no tools, no thinking to minimize cost - Disposable user message is NOT added to conversation history - Only fires when agent is idle and enough time has elapsed - Disabled by default (cache_keepalive_secs = 0) - 30-second tick in event loop checks if keepalive is needed https://claude.ai/code/session_01EvJrw9tyFxmUJrDmWteZcV
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Anthropic's prompt cache has a 5-minute TTL that expires when a session is idle,
forcing a full cache write (1.25x input cost) on the next request. This adds a
configurable keep-alive mechanism that sends minimal API requests to refresh the
cache TTL before it expires, keeping cached tokens at the 0.1x read rate.
Key design decisions:
https://claude.ai/code/session_01EvJrw9tyFxmUJrDmWteZcV