Related Issues/PRs

#20043

Resolve #20043

What changes are proposed in this pull request?

As titled - fixes the tool name extraction for our judges

How is this PR tested?

• Existing unit/integration tests
• New unit/integration tests
• Manual tests

import mlflow
from mlflow.entities import SpanType
from mlflow.genai.scorers.deepeval import ToolCorrectness

mlflow.set_tracking_uri("sqlite:///test_wrapper.db")
mlflow.set_experiment("wrapper_test")


@mlflow.trace
def agent_with_wrapper_tool(query: str):
    # Simulate a wrapper tool call like FastMCPToolset creates
    with mlflow.start_span(name="ToolManager.handle_call", span_type=SpanType.TOOL) as span:
        span.set_inputs({"call": {"tool_name": "list_client", "args": {"param": query}}})
        result = {"clients": ["client_a", "client_b"]}
        span.set_outputs(result)
    return f"Found clients for: {query}"


# Create a trace
response = agent_with_wrapper_tool("test query")
print(f"Agent response: {response}\n")

# Retrieve the trace
traces = mlflow.search_traces(experiment_ids=["1"])
trace_id = traces.iloc[0]["trace_id"]
trace = mlflow.get_trace(trace_id)

# Show what's in the trace
tool_spans = trace.search_spans(span_type=SpanType.TOOL)
print("Tool spans in trace:")
for span in tool_spans:
    print(f"  span.name: '{span.name}'")
    print(f"  inputs: {span.inputs}")

# Test with ToolCorrectness scorer
print("\n--- Testing ToolCorrectness scorer ---")
scorer = ToolCorrectness()

expectations = {
    "expected_tool_calls": [{"name": "list_client"}]
}

result = scorer(
    inputs={"query": "test query"},
    outputs={"response": response},
    expectations=expectations,
    trace=trace,
)

print(f"\nScorer result:")
print(f"  {result}")

results:

Tool spans in trace:
  span.name: 'ToolManager.handle_call'
  inputs: {'call': {'tool_name': 'list_client', 'args': {'param': 'test query'}}}

--- Testing ToolCorrectness scorer ---

Scorer result:
  Feedback(name='ToolCorrectness', source=AssessmentSource(source_type='LLM_JUDGE', source_id='openai:/gpt-4.1-mini'), trace_id=None, run_id=None, rationale="[\n\t Tool Calling Reason: All expected tools ['list_client'] were called (order not considered).\n\t Tool Selection Reason: No available tools were provided to assess tool selection criteria\n]\n", metadata={'score': 1.0, 'threshold': 0.5, 'mlflow.scorer.framework': 'deepeval'}, span_id=None, create_time_ms=1769038707044, last_update_time_ms=1769038707044, assessment_id=None, error=None, expectation=None, feedback=FeedbackValue(value=<CategoricalRating.YES: 'yes'>, error=None), overrides=None, valid=True)

Note that before the fix, this judge returned NO

Does this PR require documentation update?

• No. You can skip the rest of this section.
• Yes. I've updated:
  • Examples
  • API references
  • Instructions

Release Notes

Is this a user-facing change?

• No. You can skip the rest of this section.
• Yes. Give a description of this change to be included in the release notes for MLflow users.

Fix tool name extraction which impacted the ToolCallCorrectness scorer.

What component(s), interfaces, languages, and integrations does this PR affect?

Components

• area/tracking: Tracking Service, tracking client APIs, autologging
• area/models: MLmodel format, model serialization/deserialization, flavors
• area/model-registry: Model Registry service, APIs, and the fluent client calls for Model Registry
• area/scoring: MLflow Model server, model deployment tools, Spark UDFs
• area/evaluation: MLflow model evaluation features, evaluation metrics, and evaluation workflows
• area/gateway: MLflow AI Gateway client APIs, server, and third-party integrations
• area/prompts: MLflow prompt engineering features, prompt templates, and prompt management
• area/tracing: MLflow Tracing features, tracing APIs, and LLM tracing functionality
• area/projects: MLproject format, project running backends
• area/uiux: Front-end, user experience, plotting, JavaScript, JavaScript dev server
• area/build: Build and test infrastructure for MLflow
• area/docs: MLflow documentation pages

How should the PR be classified in the release notes? Choose one:

• rn/none - No description will be included. The PR will be mentioned only by the PR number in the "Small Bugfixes and Documentation Updates" section
• rn/breaking-change - The PR will be mentioned in the "Breaking Changes" section
• rn/feature - A new user-facing feature worth mentioning in the release notes
• rn/bug-fix - A user-facing bug fix worth mentioning in the release notes
• rn/documentation - A user-facing documentation change worth mentioning in the release notes

Should this PR be included in the next patch release?

Yes should be selected for bug fixes, documentation updates, and other small changes. No should be selected for new features and larger changes. If you're unsure about the release classification of this PR, leave this unchecked to let the maintainers decide.

• Yes (this PR will be cherry-picked and included in the next patch release)
• No (this PR will be included in the next minor release)