feat(ai): Add support for AI token span data #3250
Merged
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
Dav1dde
reviewed
Mar 12, 2024
olksdr
reviewed
Mar 12, 2024
There was a problem hiding this comment.
As a side note, could you reword the PR description to align with Sentry's commit message guidelines? Thanks beforehand!
|
@colin-sentry are there any plans to follow up on this ? |
colin-sentry
changed the title
colin-sentry
force-pushed
the
tokens
branch
2 times, most recently
from
2bcb443 to
5be051d
Compare
|
@olksdr I'm having a bit of trouble writing a test for this - the test included in this PR still passes if you revert the regex change. |
|
Do we need all the new fields on span data? |
colin-sentry
changed the title
colin-sentry
changed the title
Discussed, by adding them to span data we can avoid them being removed as PII |
jjbayer
approved these changes
Mar 26, 2024
# for free
to join this conversation on GitHub.
Already have an account?
# 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Outdated suggestions cannot be applied.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.
Upstream in SDKs (getsentry/sentry-python#2791) we added strings like "ai.prompt_tokens.used"
This adds them as known data fields, otherwise they are removed as PII since most configurations consider any superstring of "token" to be a password.