feat: report eval details to SW

Author: radu-mocanu

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "uipath"
-version = "2.1.60"
+version = "2.1.61"
 description = "Python SDK and CLI for UiPath Platform, enabling programmatic interaction with automation services, process management, and deployment tools."
 readme = { file = "README.md", content-type = "text/markdown" }
 requires-python = ">=3.10"

src/uipath/_cli/_evals/_models/_output.py

@@ -62,9 +62,19 @@ class EvaluationRunResultDto(BaseModel):
 class EvaluationRunResult(BaseModel):
     model_config = ConfigDict(alias_generator=to_camel, populate_by_name=True)
 
+    score: float = 0.0
     evaluation_name: str
     evaluation_run_results: List[EvaluationRunResultDto]
 
+    def compute_average_score(self) -> None:
+        """Compute average score for this single eval_item."""
+        if not self.evaluation_run_results:
+            self.score = 0.0
+            return
+
+        total_score = sum(dto.result.score for dto in self.evaluation_run_results)
+        self.score = total_score / len(self.evaluation_run_results)
+
 
 class UiPathEvalOutput(BaseModel):
     model_config = ConfigDict(alias_generator=to_camel, populate_by_name=True)
@@ -74,12 +84,15 @@ class UiPathEvalOutput(BaseModel):
     evaluation_set_results: List[EvaluationRunResult]
 
     def compute_average_score(self) -> None:
-        total_score = 0.0
-        total_count = 0
-
-        for evaluation_set_result in self.evaluation_set_results:
-            for evaluation_run_result in evaluation_set_result.evaluation_run_results:
-                total_score += evaluation_run_result.result.score
-                total_count += 1
-
-        self.score = total_score / total_count if total_count > 0 else 0.0
+        """Compute overall average by calling eval_item.compute_average_score()."""
+        if not self.evaluation_set_results:
+            self.score = 0.0
+            return
+
+        for eval_result in self.evaluation_set_results:
+            eval_result.compute_average_score()
+
+        eval_item_scores = [
+            eval_result.score for eval_result in self.evaluation_set_results
+        ]
+        self.score = sum(eval_item_scores) / len(eval_item_scores)

src/uipath/_cli/_evals/_models/_sw_reporting.py

@@ -0,0 +1,21 @@
+from typing import Any
+
+from pydantic import BaseModel, ConfigDict
+from pydantic.alias_generators import to_camel
+
+from uipath.eval.models import EvalItemResult
+
+
+class StudioWebProgressItem(BaseModel):
+    eval_run_id: str
+    eval_results: list[EvalItemResult]
+    success: bool
+    agent_output: dict[str, Any]
+    agent_execution_time: float
+
+
+class StudioWebAgentSnapshot(BaseModel):
+    model_config = ConfigDict(alias_generator=to_camel, populate_by_name=True)
+
+    input_schema: dict[str, Any]
+    output_schema: dict[str, Any]