Repository navigation
feat(ai): Build LLM cache shadow reports - #127024
Merged
Merged
Conversation
vgrozdanic
force-pushed
the
feat/llm-cache-reporting
branch
from
October 12, 2026 12:45
0bf0409 to
2d752ed
Compare
Contributor
Sentry Snapshot Testing
|
vgrozdanic
force-pushed
the
feat/llm-cache-reporting
branch
3 times, most recently
from
October 13, 2026 05:17
6b2b1f5 to
0b2c696
Compare
vgrozdanic
marked this pull request as ready for review
October 13, 2026 05:28
ArthurKnaus
approved these changes
Oct 13, 2026
vgrozdanic
force-pushed
the
feat/llm-cache-reporting
branch
from
October 13, 2026 07:16
0b2c696 to
a0b447b
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Defines the reviewer-facing shadow report for each LLM prompt-cache candidate.
Each report preserves both provisional and validated classifications, severity rank, simulated issue disposition, cache evidence, pricing result, and any reason an enrichment step could not produce data. It also includes derived token signals and the fixed prompt-size threshold used during classification, making detector decisions explainable from one structured record.
For candidates that would become issues, the detector can sample up to three large calls from distinct traces. Samples contain only trace ID, span ID, timestamp, and token counts. They never fetch or record prompt content.
This layer builds report data but does not emit logs, schedule scans, or create issues.