Repository navigation
feat(ai): Validate LLM cache findings - #127017
Merged
Merged
Conversation
vgrozdanic
marked this pull request as ready for review
October 9, 2026 11:56
vgrozdanic
force-pushed
the
feat/llm-cache-validation
branch
from
October 12, 2026 12:44
cefadbd to
06b0065
Compare
ArthurKnaus
approved these changes
Oct 12, 2026
vgrozdanic
force-pushed
the
feat/llm-cache-validation
branch
from
October 12, 2026 15:28
06b0065 to
532e69b
Compare
Contributor
Sentry Snapshot Testing
|
vgrozdanic
force-pushed
the
feat/llm-cache-validation
branch
from
October 12, 2026 15:49
532e69b to
65f19bf
Compare
This was referenced Oct 15, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds validation rules that prevent provisional LLM cache classifications from becoming misleading shadow findings.
Traffic validation estimates how many calls could reuse cache within the default five-minute lifetime. It rejects call sites with too few reusable calls or a low reusable share. It also detects traffic that would only benefit from a longer one-hour lifetime, so we can distinguish cache configuration opportunities from ineffective caching.
Instrumentation validation distinguishes explicit zero cache-token values from spans that never reported cache attributes. Missing evidence and incomplete probes produce unknown or ineligible outcomes instead of findings.
This layer only defines validation behavior. It does not run telemetry queries, schedule detection, emit logs, or create issues. The next stack layers supply probe data and connect these rules to detector execution.