fix: support legacy gen_ai.prompt/completion attributes for Ollama traces#136
Open
mesutoezdil wants to merge 1 commit intoagentevals-dev:mainfrom
Open
fix: support legacy gen_ai.prompt/completion attributes for Ollama traces#136mesutoezdil wants to merge 1 commit intoagentevals-dev:mainfrom
mesutoezdil wants to merge 1 commit intoagentevals-dev:mainfrom
Conversation
…aces Instrumentors like opentelemetry-instrumentation-ollama emit flat indexed attributes instead of the current gen_ai.input.messages JSON arrays. Without a fallback, user text and agent responses are not extracted from Ollama traces. Closes agentevals-dev#88
mesutoezdil
force-pushed
the
fix/legacy-genai-attributes
branch
from
7368aaa to
369fe1d
Compare
1 task
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #88
Some instrumentors like opentelemetry-instrumentation-ollama emit flat indexed attributes instead of the gen_ai.input.messages and gen_ai.output.messages JSON arrays that the current code expects:
Without a fallback the extraction functions return None for these spans and the conversation is not reconstructed.
Added _parse_legacy_indexed_attrs in extraction.py. It reads the flat attributes by prefix, groups them by index, and returns a message list in the same shape the existing code already handles. The two extraction functions try the standard attributes first and fall through to this only when those are absent. No existing behavior changes.
Five tests cover the new path and verify that standard attributes still win when both are present.