Repository navigation
feat(ai): Estimate LLM cache savings - #127023
Merged
Merged
Conversation
vgrozdanic
force-pushed
the
feat/llm-cache-pricing
branch
4 times, most recently
from
October 13, 2026 05:17
6c4cc1a to
0ce56d9
Compare
vgrozdanic
marked this pull request as ready for review
October 13, 2026 05:17
ArthurKnaus
approved these changes
Oct 13, 2026
vgrozdanic
force-pushed
the
feat/llm-cache-pricing
branch
from
October 13, 2026 07:16
0ce56d9 to
022ecfe
Compare
Contributor
Sentry Snapshot Testing
|
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 savings estimates so LLM prompt-cache findings can be ranked by possible cost impact, not only token volume.
For call sites that are not caching, the estimate applies the difference between normal input price and cached input price to uncached tokens. This is an upper bound because aggregate telemetry cannot reveal exact shared prefix length. For cache thrash, the estimate applies the difference between cache write price and cache read price to cache creation tokens.
Pricing comes from Sentry's existing AI model metadata. Each estimate keeps the exact prices used so later reports remain understandable when provider prices change. Missing metadata, unknown models, absent prices, and findings with no recoverable cost produce explicit pricing gaps instead of invented savings.
This layer only calculates estimates. It does not fetch prompt content, schedule scans, emit shadow logs, or create issues.