Skip to content

Conversation

@ialisaleh
Copy link
Collaborator

@ialisaleh ialisaleh commented Dec 24, 2025

Closes #2563


Note

Improves reliability of LiteLLM instrumentation and tests.

  • Embedding results handling: In _finalize_span, read embedding and index from each item (dict or object), skip entries missing either, and record vectors as numeric tuples or base64 strings under EMBEDDING_EMBEDDINGS.{index}.EMBEDDING_VECTOR.
  • Tests updated: test_embeddings now accepts vectors as tuple or str.
  • CI stability: Added patch_tiktoken_encoding fixture to mock tiktoken.get_encoding in token count tests (avoids network calls) and adjusted imports/usages accordingly.

Written by Cursor Bugbot for commit a53fea3. This will update automatically on new commits. Configure here.

@ialisaleh ialisaleh self-assigned this Dec 24, 2025
@dosubot dosubot bot added the size:M This PR changes 30-99 lines, ignoring generated files. label Dec 24, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:M This PR changes 30-99 lines, ignoring generated files.

Projects

Status: No status

Development

Successfully merging this pull request may close these issues.

[bug] CI Failures For LiteLLM

1 participant