Complete samples from buffer history#27
Closed
rasmusfaber wants to merge 3 commits into
Closed
Conversation
Author
|
Closing to reopen against upstream origin. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR contains:
What is the current behavior? (You can also link to an open issue here)
Buffer-backed evals write events incrementally during execution, but final sample completion still depends on the in-memory sample event list. That keeps the recorder path coupled to resident transcript memory and makes streamed events harder to use as the source of truth.
What is the new behavior?
Buffer-backed sample history can now be opened as a consistent snapshot and materialized into final samples. When a buffer database is available, final sample logging completes from that history, including pooled model inputs/calls, attachments, and timelines, while non-buffer recorders continue to use the existing path.
Does this PR introduce a breaking change? (What changes might users need to make in their application due to this PR?)
No. The final logged sample should be equivalent, but buffer-backed evals now route completion through the streaming history path.
Other information:
This is PR 2 of 3 in the event-store transcript split and is stacked on the transcript subscriber PR. The first commit is a mechanical extraction of event pool/validation helpers used by the new buffer-history path.