Custom anthropic cache_idxs
#36
Open
Conversation
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
KeremTurgutlu
commented
Oct 22, 2025
| res = [] | ||
| for idx in cache_idxs: | ||
| try: | ||
| while msgs[idx].get('tool_calls', []) or msgs[idx]['role'] == 'tool': idx -= 1 |
There was a problem hiding this comment.
Some cache_idxs can end up being shifted back to the same idx. For example if last 4 messages are tool blocks / results and user sets cahce_idxs=[-4,-3,-2,-1] then it will be cache_idxs=[-5,-5,-5,-5].
We can keep shifting them until all idxs are unique (if possible otherwise collision is unavoidable) but this might complicate the logic a bit?
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
This PR introduces
cache_idxsargument which will let users to provide custom cache idx locations to insert Anthropic cache control breakpoints.If a cache idx corresponds to a tool call block or a tool result then it will be skipped and shifted to the closest previous valid message.
By default the last message will be cached if
cache=Trueand nocache_idxsis provided.For example, to cache both the sysp and the last message a user can set
cache_idxs=[0,-1]assumingspis also given.