feat(litellm): improve GenAI util instrumentation#196
Open
sipercai wants to merge 3 commits into
Open
Conversation
12 tasks
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| def fake_completion(model, messages, **kwargs): | ||
| assert model == "custom-compatible-model" | ||
| assert kwargs["custom_llm_provider"] == "openai" | ||
| assert "dashscope.aliyuncs.com" in kwargs["api_base"] |
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
5 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Migrated from #191 to use an upstream repository branch for Copilot review and organization-side review flow.
Description
This PR improves the LoongSuite LiteLLM instrumentation to populate GenAI util invocation data consistently for chat completions, streaming completions, and embeddings.
It adds positional argument normalization, richer LiteLLM response mapping, streaming output aggregation for multi-choice and tool-call deltas, streaming time-to-first-token reporting, provider inference for OpenAI-compatible endpoints, and a real smoke example for non-streaming, streaming, and concurrent calls.
Fixes # (N/A)
Type of change
How Has This Been Tested?
tox -e precommittox -c tox-loongsuite.ini -e py310-test-loongsuite-instrumentation-litellm -- instrumentation-loongsuite/loongsuite-instrumentation-litellm/tests/test_genai_util_wrapper.py instrumentation-loongsuite/loongsuite-instrumentation-litellm/tests/test_utils.py instrumentation-loongsuite/loongsuite-instrumentation-litellm/tests/test_stream_completion.py instrumentation-loongsuite/loongsuite-instrumentation-litellm/tests/test_embedding.py -qDoes This PR Require a Core Repo Change?
Checklist:
See contributing.md for styleguide, changelog guidelines, and more.
Additional validation after review blocker fixes:
tox -e precommittox -c tox-loongsuite.ini -e py310-test-loongsuite-instrumentation-litellm -- instrumentation-loongsuite/loongsuite-instrumentation-litellm/tests/test_genai_util_wrapper.py instrumentation-loongsuite/loongsuite-instrumentation-litellm/tests/test_sync_completion.py instrumentation-loongsuite/loongsuite-instrumentation-litellm/tests/test_utils.py instrumentation-loongsuite/loongsuite-instrumentation-litellm/tests/test_stream_completion.py instrumentation-loongsuite/loongsuite-instrumentation-litellm/tests/test_embedding.py -q