feat(client): add optional override default cache ttl capability for prompt caching #1249
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
|
|
![greptile-apps[bot]](https://avatars.githubusercontent.com/in/867647?s=60&v=4){kind=small}
There was a problem hiding this comment.
4 files reviewed, 1 comment
Edit PR Review Bot Settings | Greptile
cemasma
force-pushed
the
add-override-default-cache-ttl-capability
branch
from
ab08393 to
1e84c57
Compare
cemasma
force-pushed
the
add-override-default-cache-ttl-capability
branch
4 times, most recently
from
26baec6 to
2aa1c48
Compare
cemasma
force-pushed
the
add-override-default-cache-ttl-capability
branch
from
2aa1c48 to
e7fe63a
Compare
cemasma
force-pushed
the
add-override-default-cache-ttl-capability
branch
from
29333d7 to
178645f
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Summary
This PR enhances the Langfuse Python SDK’s prompt caching mechanism by enabling runtime overrides of the default 60-second TTL (default_cache_ttl_seconds). It allows developers to optionally specify a custom TTL—or disable caching entirely—during the initialization of the Langfuse client.
Goal
Important
Add capability to override default cache TTL for prompt caching in Langfuse Python SDK, with tests for custom TTL and caching behavior.
default_cache_ttl_secondsparameter toLangfuseclass inclient.pyto allow overriding the default cache TTL for prompts.PromptCacheinprompt_cache.pyto usedefault_cache_ttl_secondsif provided.PromptCacheItemto respect the new TTL setting.test_prompt.pyto verify custom TTL functionality, including overriding default TTL and disabling caching.This description was created by
for ab08393. You can customize this summary. It will automatically update as commits are pushed.
Greptile Summary
Disclaimer: Experimental PR review
Adds capability to override default prompt cache TTL (60 seconds) during Langfuse client initialization, allowing global configuration of prompt caching behavior.
default_cache_ttl_secondsparameter tolangfuse/_client/client.pyfor configuring cache duration at client levellangfuse/_utils/prompt_cache.pyto support custom TTL configuration with backward compatibilitylangfuse/_client/resource_manager.pyto propagate TTL settings through the initialization chaintests/test_prompt.pyverifying custom TTL behavior and cache expiration