Codex tracing support#226
Open
db-nethra wants to merge 2 commits into
Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What
With the MLflow 3.14 release, the MLflow TypeScript tracing packages now support sending Codex traces to Unity Catalog-backed storage. This PR wires that support into Ucode.
Change
The Codex agent setup now installs and validates
@mlflow/codex, configures Codex to invoke MLflow after a completed turn, and supplies the required tracing environment when Codex launches. It also removes Ucode-managed tracing configuration when tracing is disabled.The shared tracing flow now recognizes Codex as tracing-capable and supplies the selected MLflow experiment ID and UC trace location. This routes Codex sessions into the configured UC-backed
ucode-tracesexperiment.Tests
tests/test_agent_codex.pyverifies MLflow hook configuration, runtime installation, launch environment, and cleanup.tests/test_tracing.pyandtests/test_e2e_tracing.pyverify Codex traces reach the configured UC-backed experiment with the expected spans and model attribution.Related
Built on the Codex UC trace-location support added in [mlflow/mlflow#23771]
The upstream instrumentation currently includes Codex harness context, such as system instructions and discovered
AGENTS.mdcontent, in the initial trace. Filtering this context belongs upstream in MLflow’s Codex tracing package.