azure-ai-evaluation 1.13.3__py3-none-any.whl → 1.13.5__py3-none-any.whl

azure/ai/evaluation/__init__.py

@@ -33,6 +33,7 @@ from ._evaluators._ungrounded_attributes import UngroundedAttributesEvaluator
 from ._evaluators._tool_call_accuracy import ToolCallAccuracyEvaluator
 from ._evaluators._document_retrieval import DocumentRetrievalEvaluator
 from ._evaluators._tool_output_utilization import _ToolOutputUtilizationEvaluator
+from ._evaluators._tool_call_success import _ToolCallSuccessEvaluator
 from ._model_configurations import (
     AzureAIProject,
     AzureOpenAIModelConfiguration,
@@ -133,6 +134,7 @@ __all__ = [
     "UngroundedAttributesEvaluator",
     "ToolCallAccuracyEvaluator",
     "_ToolOutputUtilizationEvaluator",
+    "_ToolCallSuccessEvaluator",
     "AzureOpenAIGrader",
     "AzureOpenAILabelGrader",
     "AzureOpenAIStringCheckGrader",

azure/ai/evaluation/_common/constants.py

@@ -20,7 +20,7 @@ PROMPT_BASED_REASON_EVALUATORS = [
     "tool_output_utilization",
     "task_completion",
     "tool_input_accuracy",
-    "tool_success",
+    "tool_call_success",
     "tool_call_accuracy",
 ]
 

azure/ai/evaluation/_constants.py

@@ -143,7 +143,6 @@ class _EvaluatorMetricMapping:
         "hate_unfairness": ["hate_unfairness"],
         "tool_input_accuracy": ["tool_input_accuracy"],
         "task_completion": ["task_completion"],
-        "tool_success": ["tool_success"],
         "tool_call_success": ["tool_call_success"],
         "tool_selection": ["tool_selection"],
         "tool_output_utilization": ["tool_output_utilization"],

azure/ai/evaluation/_eval_mapping.py

@@ -12,10 +12,14 @@
 # Import all evals
 from azure.ai.evaluation._evaluators._eci._eci import ECIEvaluator
 from azure.ai.evaluation._evaluators._task_completion import _TaskCompletionEvaluator
-from azure.ai.evaluation._evaluators._tool_input_accuracy import _ToolInputAccuracyEvaluator
+from azure.ai.evaluation._evaluators._tool_input_accuracy import (
+    _ToolInputAccuracyEvaluator,
+)
 from azure.ai.evaluation._evaluators._tool_selection import _ToolSelectionEvaluator
-from azure.ai.evaluation._evaluators._tool_success import _ToolSuccessEvaluator
-from azure.ai.evaluation._evaluators._task_navigation_efficiency import _TaskNavigationEfficiencyEvaluator
+from azure.ai.evaluation._evaluators._tool_call_success import _ToolCallSuccessEvaluator
+from azure.ai.evaluation._evaluators._task_navigation_efficiency import (
+    _TaskNavigationEfficiencyEvaluator,
+)
 from azure.ai.evaluation import (
     BleuScoreEvaluator,
     CodeVulnerabilityEvaluator,
@@ -77,7 +81,7 @@ EVAL_CLASS_MAP = {
     ToolCallAccuracyEvaluator: "tool_call_accuracy",
     _ToolInputAccuracyEvaluator: "tool_input_accuracy",
     _ToolSelectionEvaluator: "tool_selection",
-    _ToolSuccessEvaluator: "tool_success",
+    _ToolCallSuccessEvaluator: "tool_call_success",
     UngroundedAttributesEvaluator: "ungrounded_attributes",
     ViolenceEvaluator: "violence",
 }

azure/ai/evaluation/_evaluate/_evaluate.py

@@ -1865,8 +1865,8 @@ def _convert_results_to_aoai_evaluation_results(
                         criteria_groups[criteria_name] = {}
 
                     criteria_groups[criteria_name][metric_name] = value
-            elif key.startswith("inputs."):
-                input_key = key.replace("inputs.", "")
+            else:
+                input_key = key.replace("inputs.", "") if key.startswith("inputs.") else key
                 if input_key not in input_groups:
                     input_groups[input_key] = value
 

azure/ai/evaluation/_evaluators/_common/_base_eval.py

@@ -3,6 +3,7 @@
 # ---------------------------------------------------------
 
 import inspect
+import logging
 from abc import ABC, abstractmethod
 import json
 import copy
@@ -46,6 +47,8 @@ P = ParamSpec("P")
 T = TypeVar("T")
 T_EvalValue = TypeVar("T_EvalValue")
 
+logger = logging.getLogger(__name__)
+
 
 class DerivedEvalInput(TypedDict, total=False):
     """The eval input generated by EvaluatorBase._derive_conversation_starter."""
@@ -593,7 +596,7 @@ class EvaluatorBase(ABC, Generic[T_EvalValue]):
         try:
             eval_input_list = self._convert_kwargs_to_eval_input(**kwargs)
         except Exception as e:
-            print(f"Error converting kwargs to eval_input_list: {e}")
+            logger.error(f"Error converting kwargs to eval_input_list: {e}")
             raise e
         per_turn_results = []
         # Evaluate all inputs.
@@ -630,7 +633,7 @@ class EvaluatorBase(ABC, Generic[T_EvalValue]):
                             else:
                                 result[result_key] = EVALUATION_PASS_FAIL_MAPPING[False]
             except Exception as e:
-                print(f"Error calculating binary result: {e}")
+                logger.warning(f"Error calculating binary result: {e}")
             per_turn_results.append(result)
         # Return results as-is if only one result was produced.
 

azure/ai/evaluation/_evaluators/_task_adherence/_task_adherence.py

@@ -63,7 +63,7 @@ class TaskAdherenceEvaluator(PromptyEvaluatorBase[Union[str, float]]):
 
     _PROMPTY_FILE = "task_adherence.prompty"
     _RESULT_KEY = "task_adherence"
-    _OPTIONAL_PARAMS = []
+    _OPTIONAL_PARAMS = ["tool_definitions"]
 
     _DEFAULT_TASK_ADHERENCE_SCORE = 0
 
@@ -175,7 +175,7 @@ class TaskAdherenceEvaluator(PromptyEvaluatorBase[Union[str, float]]):
                         if isinstance(content, list):
                             for item in content:
                                 if isinstance(item, dict):
-                                    if item.get("type") == "text":
+                                    if item.get("type", None) in ("text", "input_text", "output_text"):
                                         assistant_parts.append(item.get("text", ""))
                                     elif item.get("type") == "tool_call":
                                         tool_parts.append(str(item.get("tool_call", "")))

azure/ai/evaluation/_evaluators/{_tool_success → _tool_call_success}/__init__.py

@@ -2,6 +2,6 @@
 # Copyright (c) Microsoft Corporation. All rights reserved.
 # ---------------------------------------------------------
 
-from ._tool_success import _ToolSuccessEvaluator
+from ._tool_call_success import _ToolCallSuccessEvaluator
 
-__all__ = ["_ToolSuccessEvaluator"]
+__all__ = ["_ToolCallSuccessEvaluator"]

azure/ai/evaluation/_evaluators/{_tool_success/_tool_success.py → _tool_call_success/_tool_call_success.py}

@@ -6,7 +6,12 @@ import os
 import logging
 from typing import Dict, Union, List, Optional
 from typing_extensions import overload, override
-from azure.ai.evaluation._exceptions import EvaluationException, ErrorBlame, ErrorCategory, ErrorTarget
+from azure.ai.evaluation._exceptions import (
+    EvaluationException,
+    ErrorBlame,
+    ErrorCategory,
+    ErrorTarget,
+)
 from azure.ai.evaluation._evaluators._common import PromptyEvaluatorBase
 from azure.ai.evaluation._common._experimental import experimental
 
@@ -15,8 +20,8 @@ logger = logging.getLogger(__name__)
 
 
 @experimental
-class _ToolSuccessEvaluator(PromptyEvaluatorBase[Union[str, float]]):
-    """The Tool Success evaluator determines whether tool calls done by an AI agent includes failures or not.
+class _ToolCallSuccessEvaluator(PromptyEvaluatorBase[Union[str, float]]):
+    """The Tool Call Success evaluator determines whether tool calls done by an AI agent includes failures or not.
 
     This evaluator focuses solely on tool call results and tool definitions, disregarding user's query to
     the agent, conversation history and agent's final response. Although tool definitions is optional,
@@ -36,34 +41,34 @@ class _ToolSuccessEvaluator(PromptyEvaluatorBase[Union[str, float]]):
 
     .. admonition:: Example:
         .. literalinclude:: ../samples/evaluation_samples_evaluate.py
-            :start-after: [START tool_success_evaluator]
-            :end-before: [END tool_success_evaluator]
+            :start-after: [START tool_call_success_evaluator]
+            :end-before: [END tool_call_success_evaluator]
             :language: python
             :dedent: 8
-            :caption: Initialize and call a _ToolSuccessEvaluator with a tool definitions and response.
+            :caption: Initialize and call a _ToolCallSuccessEvaluator with a tool definitions and response.
 
     .. admonition:: Example using Azure AI Project URL:
 
     .. literalinclude:: ../samples/evaluation_samples_evaluate_fdp.py
-        :start-after: [START tool_success_evaluator]
-        :end-before: [END tool_success_evaluator]
+        :start-after: [START tool_call_success_evaluator]
+        :end-before: [END tool_call_success_evaluator]
         :language: python
         :dedent: 8
-        :caption: Initialize and call a _ToolSuccessEvaluator using Azure AI Project URL in the following
+        :caption: Initialize and call a _ToolCallSuccessEvaluator using Azure AI Project URL in the following
             format https://{resource_name}.services.ai.azure.com/api/projects/{project_name}
 
     """
 
-    _PROMPTY_FILE = "tool_success.prompty"
-    _RESULT_KEY = "tool_success"
+    _PROMPTY_FILE = "tool_call_success.prompty"
+    _RESULT_KEY = "tool_call_success"
     _OPTIONAL_PARAMS = ["tool_definitions"]
 
-    id = "azureai://built-in/evaluators/tool_success"
+    id = "azureai://built-in/evaluators/tool_call_success"
     """Evaluator identifier, experimental and to be used only with evaluation in cloud."""
 
     @override
     def __init__(self, model_config, *, credential=None, **kwargs):
-        """Initialize the Tool Success evaluator."""
+        """Initialize the Tool Call Success evaluator."""
         current_dir = os.path.dirname(__file__)
         prompty_path = os.path.join(current_dir, self._PROMPTY_FILE)
         super().__init__(
@@ -86,7 +91,7 @@ class _ToolSuccessEvaluator(PromptyEvaluatorBase[Union[str, float]]):
         """Evaluate tool call success for a given response, and optionally tool definitions.
 
         Example with list of messages:
-            evaluator = _ToolSuccessEvaluator(model_config)
+            evaluator = _ToolCallSuccessEvaluator(model_config)
             response = [{'createdAt': 1700000070, 'run_id': '0', 'role': 'assistant',
             'content': [{'type': 'text', 'text': '**Day 1:** Morning: Visit Louvre Museum (9 AM - 12 PM)...'}]}]
 
@@ -97,7 +102,7 @@ class _ToolSuccessEvaluator(PromptyEvaluatorBase[Union[str, float]]):
         :paramtype response: Union[str, List[dict]]
         :keyword tool_definitions: Optional tool definitions to use for evaluation.
         :paramtype tool_definitions: Union[dict, List[dict]]
-        :return: A dictionary with the tool success evaluation results.
+        :return: A dictionary with the Tool Call Success evaluation results.
         :rtype: Dict[str, Union[str, float]]
         """
 
@@ -116,7 +121,7 @@ class _ToolSuccessEvaluator(PromptyEvaluatorBase[Union[str, float]]):
 
     @override
     async def _do_eval(self, eval_input: Dict) -> Dict[str, Union[str, float]]:  # type: ignore[override]
-        """Do Tool Success evaluation.
+        """Do Tool Call Success evaluation.
 
         :param eval_input: The input to the evaluator. Expected to contain whatever inputs are
         needed for the _flow method
@@ -126,19 +131,19 @@ class _ToolSuccessEvaluator(PromptyEvaluatorBase[Union[str, float]]):
         """
         if "response" not in eval_input:
             raise EvaluationException(
-                message="response is a required input to the Tool Success evaluator.",
-                internal_message="response is a required input to the Tool Success evaluator.",
+                message="response is a required input to the Tool Call Success evaluator.",
+                internal_message="response is a required input to the Tool Call Success evaluator.",
                 blame=ErrorBlame.USER_ERROR,
                 category=ErrorCategory.MISSING_FIELD,
-                target=ErrorTarget.TOOL_SUCCESS_EVALUATOR,
+                target=ErrorTarget.TOOL_CALL_SUCCESS_EVALUATOR,
             )
         if eval_input["response"] is None or eval_input["response"] == []:
             raise EvaluationException(
-                message="response cannot be None or empty for the Tool Success evaluator.",
-                internal_message="response cannot be None or empty for the Tool Success evaluator.",
+                message="response cannot be None or empty for the Tool Call Success evaluator.",
+                internal_message="response cannot be None or empty for the Tool Call Success evaluator.",
                 blame=ErrorBlame.USER_ERROR,
                 category=ErrorCategory.INVALID_VALUE,
-                target=ErrorTarget.TOOL_SUCCESS_EVALUATOR,
+                target=ErrorTarget.TOOL_CALL_SUCCESS_EVALUATOR,
             )
 
         eval_input["tool_calls"] = _reformat_tool_calls_results(eval_input["response"], logger)

azure/ai/evaluation/_evaluators/{_tool_success/tool_success.prompty → _tool_call_success/tool_call_success.prompty}

@@ -1,5 +1,5 @@
 ---
-name: Tool Success
+name: Tool Call Success
 description: Evaluates whether a Tool call was successful or resulted in a technical error
 model:
   api: chat

azure/ai/evaluation/_exceptions.py

@@ -85,7 +85,7 @@ class ErrorTarget(Enum):
     SIMILARITY_EVALUATOR = "SimilarityEvaluator"
     FLUENCY_EVALUATOR = "FluencyEvaluator"
     RETRIEVAL_EVALUATOR = "RetrievalEvaluator"
-    TOOL_SUCCESS_EVALUATOR = "_ToolSuccessEvaluator"
+    TOOL_CALL_SUCCESS_EVALUATOR = "_ToolCallSuccessEvaluator"
     TASK_ADHERENCE_EVALUATOR = "TaskAdherenceEvaluator"
     TASK_COMPLETION_EVALUATOR = "_TaskCompletionEvaluator"
     INDIRECT_ATTACK_EVALUATOR = "IndirectAttackEvaluator"

azure/ai/evaluation/_version.py

@@ -3,4 +3,4 @@
 # ---------------------------------------------------------
 # represents upcoming version
 
-VERSION = "1.13.3"
+VERSION = "1.13.5"

{azure_ai_evaluation-1.13.3.dist-info → azure_ai_evaluation-1.13.5.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: azure-ai-evaluation
-Version: 1.13.3
+Version: 1.13.5
 Summary: Microsoft Azure Evaluation Library for Python
 Home-page: https://github.com/Azure/azure-sdk-for-python
 Author: Microsoft Corporation
@@ -418,6 +418,18 @@ This project has adopted the [Microsoft Open Source Code of Conduct][code_of_con
 
 # Release History
 
+## 1.13.5 (2025-11-10)
+
+### Bugs Fixed
+
+- **TaskAdherenceEvaluator:** treat tool definitions as optional so evaluations with only query/response inputs no longer raise “Either 'conversation' or individual inputs must be provided.”
+
+## 1.13.4 (2025-11-10)
+
+### Bugs Fixed
+
+- Handle input data for evaluation result when evaluators.
+
 ## 1.13.3 (2025-11-08)
 
 ### Other Changes

{azure_ai_evaluation-1.13.3.dist-info → azure_ai_evaluation-1.13.5.dist-info}/RECORD

@@ -1,12 +1,12 @@
-azure/ai/evaluation/__init__.py,sha256=I0gt0HLyxnqtTIoj5pQgj1CtmzXvuEZb_sXuVNPGtzw,5419
-azure/ai/evaluation/_constants.py,sha256=g8yzM6YeIhJoC4ZIqHzyakjMMJ7cXHF5wUj1gvz9D6I,8081
-azure/ai/evaluation/_eval_mapping.py,sha256=szSJ4HSpct_JsoUX3svYIioW8cSqsKUVKLCshrcpSBE,3299
+azure/ai/evaluation/__init__.py,sha256=Qmb4OXIHXKtYH0ndXkH1onUYX9HUhqTXJiOAYwwnK9M,5522
+azure/ai/evaluation/_constants.py,sha256=6lWU_3Nse--HCBS8U7iZMYKlL7tLhtmL7wYYpnz564M,8039
+azure/ai/evaluation/_eval_mapping.py,sha256=awjtLDq0RtTrc5AvBBHWXj0mMyinMk_Ln2mkI1yvCPg,3335
 azure/ai/evaluation/_evaluator_definition.py,sha256=Z33dPXVAhMGEdn6kcE5d-p_v8VtE6Hpm6-PbNIqKh0Y,2901
-azure/ai/evaluation/_exceptions.py,sha256=AsbYxt8G8CpET2bbJzvtYJAw1bbNSI1T77k65ayuHNc,6274
+azure/ai/evaluation/_exceptions.py,sha256=90L9njT2aFznT4DGo5zuksuMcZRvOYUoxJ2nk90NfPo,6283
 azure/ai/evaluation/_http_utils.py,sha256=d1McnMRT5lnaoR8x4r3pkfH2ic4T3JArclOK4kAaUmg,17261
 azure/ai/evaluation/_model_configurations.py,sha256=OZ-QskAbBX7lwjeyum6EOoh1oWSi7lplghnfMoFPpUU,5167
 azure/ai/evaluation/_user_agent.py,sha256=SgUm6acnwyoENu8KroyaWRrJroJNqLZBccpQoeKyrHw,1144
-azure/ai/evaluation/_version.py,sha256=BliTNWOypBtp-bZgH9-o0e6Rtu7xf-1V46JsNOQJ06c,230
+azure/ai/evaluation/_version.py,sha256=UoLHgo6no_BDqgyiNVsfetHiZGXkGZGvSkj1U6I8FJ8,230
 azure/ai/evaluation/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 azure/ai/evaluation/_aoai/__init__.py,sha256=0Ji05ShlsJaytvexXUpCe69t0jSNd3PpNbhr0zCkr6A,265
 azure/ai/evaluation/_aoai/aoai_grader.py,sha256=ey8YWNstlFq9SCu-kH3oFFsHCJcBeEabQAEAGENDy2c,6228
@@ -22,7 +22,7 @@ azure/ai/evaluation/_azure/_models.py,sha256=Vxcg7WfpAyxLQ-EesZzLGqopguV9Oohfjf-
 azure/ai/evaluation/_azure/_token_manager.py,sha256=EoNbDLweJOukqReOKJVgnQ9AFLVuQeK3KJrJtZKTIAA,5489
 azure/ai/evaluation/_common/__init__.py,sha256=5PO6eGs0zdarngR5shIsEn5gp2XfpUnLyt4HR79Hf5o,933
 azure/ai/evaluation/_common/_experimental.py,sha256=GVtSn9r1CeR_yEa578dJVNDJ3P24eqe8WYdH7llbiQY,5694
-azure/ai/evaluation/_common/constants.py,sha256=BI3y7AjMs0gvl2J2FbreUpfFgwJ93zoYLzxmC5Uq-0s,6573
+azure/ai/evaluation/_common/constants.py,sha256=AE5nhGKXZTwbq51m69HgdlCf5-ybyPGMf6tzlRxkPfE,6578
 azure/ai/evaluation/_common/evaluation_onedp_client.py,sha256=9QSK5lvMHtrlT3mrQwORZC-xjaS6suheYKwbtWKUjUM,7512
 azure/ai/evaluation/_common/math.py,sha256=d4bwWe35_RWDIZNcbV1BTBbHNx2QHQ4-I3EofDyyNE0,2863
 azure/ai/evaluation/_common/rai_service.py,sha256=tr5gd6j-SH7VeFRCzCPyZef0XV9xq9RqO5rrOlJ5Ztw,47970
@@ -99,7 +99,7 @@ azure/ai/evaluation/_converters/_models.py,sha256=x6GxLItQtvccv8q6jWtOUmQL1ZdeIA
 azure/ai/evaluation/_converters/_sk_services.py,sha256=NfjflVgeJUF0MrvAiUd_uF2magn38Q_MKmHzaY41vOA,18239
 azure/ai/evaluation/_evaluate/__init__.py,sha256=Yx1Iq2GNKQ5lYxTotvPwkPL4u0cm6YVxUe-iVbu1clI,180
 azure/ai/evaluation/_evaluate/_eval_run.py,sha256=57rfW4MkE9LSlQNqdzxvq_nw8xYW-mqPQLw4WY_k-YU,22564
-azure/ai/evaluation/_evaluate/_evaluate.py,sha256=Wa7U3XCclwV2uEz6-8OprwewF51RXn2jc6SXmX_jrjI,119938
+azure/ai/evaluation/_evaluate/_evaluate.py,sha256=XjZ2rYRPjqCxPr3Asl2vtQ4nXMbuxm8evUve8roM0z4,119950
 azure/ai/evaluation/_evaluate/_evaluate_aoai.py,sha256=ViMDSEvmVCiJ96ZSiuHv66d0EL4o8Qa_r6jkxwxmB-g,44030
 azure/ai/evaluation/_evaluate/_utils.py,sha256=teIRlQlEctgFYA8S8FedelFicBrt8g05OPVsE6bq8FI,19751
 azure/ai/evaluation/_evaluate/_batch_run/__init__.py,sha256=cPLi_MJ_pCp8eKBxJbiSoxgTnN3nDLuaP57dMkKuyhg,552
@@ -119,7 +119,7 @@ azure/ai/evaluation/_evaluators/_coherence/__init__.py,sha256=GRqcSCQse02Spyki0U
 azure/ai/evaluation/_evaluators/_coherence/_coherence.py,sha256=r_21EFCX-2oAO6FxwUnBdUUwS-QgBiC0zGXSW3hXj2I,6335
 azure/ai/evaluation/_evaluators/_coherence/coherence.prompty,sha256=ANvh9mDFW7KMejrgdWqBLjj4SIqEO5WW9gg5pE0RLJk,6798
 azure/ai/evaluation/_evaluators/_common/__init__.py,sha256=xAymP_CZy4aPzWplMdXgQUQVDIUEMI-0nbgdm_umFYY,498
-azure/ai/evaluation/_evaluators/_common/_base_eval.py,sha256=qB0JmaxITudedxgIHTK6wGJsCHnaul41n6Jm-QGPaaU,34025
+azure/ai/evaluation/_evaluators/_common/_base_eval.py,sha256=1p9sLBfQDydc5okMK1VvU5agn52hkOlp_8-DkzHP59o,34094
 azure/ai/evaluation/_evaluators/_common/_base_multi_eval.py,sha256=yYFpoCDe2wMFQck0ykbX8IJBBidk6NT1wUTkVFlVSy8,2728
 azure/ai/evaluation/_evaluators/_common/_base_prompty_eval.py,sha256=M4gVGxd31QP6xA6U-rKDUC52MzexXOnP_9K2BcEAFPE,15903
 azure/ai/evaluation/_evaluators/_common/_base_rai_svc_eval.py,sha256=JSZhRxVKljM4XE4P2DGrJSnD6iWr7tlDIJ8g95rHaGg,9078
@@ -171,7 +171,7 @@ azure/ai/evaluation/_evaluators/_similarity/__init__.py,sha256=V2Mspog99_WBltxTk
 azure/ai/evaluation/_evaluators/_similarity/_similarity.py,sha256=fw250aoDCQ-oXalmyUoYXxK2p43nxnn4sjVqTVSPvD8,5951
 azure/ai/evaluation/_evaluators/_similarity/similarity.prompty,sha256=eoludASychZoGL625bFCaZai-OY7DIAg90ZLax_o4XE,4594
 azure/ai/evaluation/_evaluators/_task_adherence/__init__.py,sha256=9HtNrG7yYX0Ygq3cZoS_0obAvGgmy5HWcsBcPKoB15c,271
-azure/ai/evaluation/_evaluators/_task_adherence/_task_adherence.py,sha256=e5Tnkk-t_VpZWZvVdGkcE-iPBnljug3Y-Qou9EmgK8k,12672
+azure/ai/evaluation/_evaluators/_task_adherence/_task_adherence.py,sha256=31DzzKXtgQgoYPQ8OD1TAOZMlv3W7RXKtT0cdeXrCE0,12727
 azure/ai/evaluation/_evaluators/_task_adherence/task_adherence.prompty,sha256=cmrMjfqJXYtOPUcSCtGSiD8HUe4k53-n07kegjrH0Kg,7387
 azure/ai/evaluation/_evaluators/_task_completion/__init__.py,sha256=xW5ZKj8-ipSxORbLlSRAV01jHv8V9e0MpOhrBqnuMQY,276
 azure/ai/evaluation/_evaluators/_task_completion/_task_completion.py,sha256=ASQyPJQn0OWOFmYJ_uFofSptePt7t9tC8sO3LkAV-Gs,9083
@@ -181,6 +181,9 @@ azure/ai/evaluation/_evaluators/_task_navigation_efficiency/_task_navigation_eff
 azure/ai/evaluation/_evaluators/_tool_call_accuracy/__init__.py,sha256=vYB4Y_3n1LqTiEeZB1O1A0b14wpURBwtW0wPEN2FG9Q,288
 azure/ai/evaluation/_evaluators/_tool_call_accuracy/_tool_call_accuracy.py,sha256=YhuaMKqP8U6XfnW5QruF5-68cTUAWOAmBSSAB54DYPs,14807
 azure/ai/evaluation/_evaluators/_tool_call_accuracy/tool_call_accuracy.prompty,sha256=pQhNQC1w12WNBU4sdgyhO9gXhZY1dWrNIBK31ciW-V4,10138
+azure/ai/evaluation/_evaluators/_tool_call_success/__init__.py,sha256=pMYF75Q671a9OFQMBxiINqKHcW6GKf20_QGT594Cmd0,280
+azure/ai/evaluation/_evaluators/_tool_call_success/_tool_call_success.py,sha256=0s4UmTyQFg6PPDPKOa-RycNyP8x7xhRrYBnqIvIH_1I,13952
+azure/ai/evaluation/_evaluators/_tool_call_success/tool_call_success.prompty,sha256=Ti7UWCIC6B3x6Er5rizLwhIvTLEXFt6EiuMIYB_hbmA,10105
 azure/ai/evaluation/_evaluators/_tool_input_accuracy/__init__.py,sha256=Iu1GBkR76fpMafxOZhG9bTAbVIaR0HciVwbuTeczgrc,293
 azure/ai/evaluation/_evaluators/_tool_input_accuracy/_tool_input_accuracy.py,sha256=cPVw8bNERwQWwJtGYS9juomRvmOzCj6XO8Yx9syUDBk,11617
 azure/ai/evaluation/_evaluators/_tool_input_accuracy/tool_input_accuracy.prompty,sha256=JapLVUu_faMUO51Bo9uEy-VIn4sgh5n2uyASkeCnjSc,3028
@@ -190,9 +193,6 @@ azure/ai/evaluation/_evaluators/_tool_output_utilization/tool_output_utilization
 azure/ai/evaluation/_evaluators/_tool_selection/__init__.py,sha256=7nMGfFz8WgTg8s195-WHMNE-dhC3YN9P3xmmQQLWNEE,280
 azure/ai/evaluation/_evaluators/_tool_selection/_tool_selection.py,sha256=5GLqGpKBx2Tw9TMK2ugimMH7cCuH3zuScsViTxNPp8I,11873
 azure/ai/evaluation/_evaluators/_tool_selection/tool_selection.prompty,sha256=NorcOvfmlzXqEaaWs_VcmdFpStVmHeJ0cNA8yEyRJlQ,7441
-azure/ai/evaluation/_evaluators/_tool_success/__init__.py,sha256=XezZXpi62CHZiDZJ41tBY0kWpB36XYcMh9YVsI6xBz8,267
-azure/ai/evaluation/_evaluators/_tool_success/_tool_success.py,sha256=iWEcAF1dPALxCDrzV6lhN84jpDtHg00R7JO7ut0uTOw,13830
-azure/ai/evaluation/_evaluators/_tool_success/tool_success.prompty,sha256=innPK0WyTY7DWtA88Laj9JgRMmT-bQzfEq9Pq68gOSg,10100
 azure/ai/evaluation/_evaluators/_ungrounded_attributes/__init__.py,sha256=wGZBd_cRDgkuS-0HV9qm81dHK7ScYdKd98xLPtk6EwQ,118
 azure/ai/evaluation/_evaluators/_ungrounded_attributes/_ungrounded_attributes.py,sha256=zDoc7SSaOSVlT-uCurAbsIOMzJ6HAuXk0SfYDrBE3p8,3736
 azure/ai/evaluation/_evaluators/_xpia/__init__.py,sha256=VMEL8WrpJQeh4sQiOLzP7hRFPnjzsvwfvTzaGCVJPCM,88
@@ -298,8 +298,8 @@ azure/ai/evaluation/simulator/_model_tools/models.py,sha256=SJYI-IJfCo9bitMGfSSn
 azure/ai/evaluation/simulator/_prompty/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 azure/ai/evaluation/simulator/_prompty/task_query_response.prompty,sha256=2BzSqDDYilDushvR56vMRDmqFIaIYAewdUlUZg_elMg,2182
 azure/ai/evaluation/simulator/_prompty/task_simulate.prompty,sha256=NE6lH4bfmibgMn4NgJtm9_l3PMoHSFrfjjosDJEKM0g,939
-azure_ai_evaluation-1.13.3.dist-info/licenses/NOTICE.txt,sha256=4tzi_Yq4-eBGhBvveobWHCgUIVF-ZeouGN0m7hVq5Mk,3592
-azure_ai_evaluation-1.13.3.dist-info/METADATA,sha256=CqxRu1pcHp1Y910sXdN_9wnMcsKyOexJkhGj8zZAlw8,48602
-azure_ai_evaluation-1.13.3.dist-info/WHEEL,sha256=1tXe9gY0PYatrMPMDd6jXqjfpz_B-Wqm32CPfRC58XU,91
-azure_ai_evaluation-1.13.3.dist-info/top_level.txt,sha256=S7DhWV9m80TBzAhOFjxDUiNbKszzoThbnrSz5MpbHSQ,6
-azure_ai_evaluation-1.13.3.dist-info/RECORD,,
+azure_ai_evaluation-1.13.5.dist-info/licenses/NOTICE.txt,sha256=4tzi_Yq4-eBGhBvveobWHCgUIVF-ZeouGN0m7hVq5Mk,3592
+azure_ai_evaluation-1.13.5.dist-info/METADATA,sha256=k9CUcOdrbo27BI_G2LkIIJ2bbiOk6odKG327TcJEPEo,48938
+azure_ai_evaluation-1.13.5.dist-info/WHEEL,sha256=1tXe9gY0PYatrMPMDd6jXqjfpz_B-Wqm32CPfRC58XU,91
+azure_ai_evaluation-1.13.5.dist-info/top_level.txt,sha256=S7DhWV9m80TBzAhOFjxDUiNbKszzoThbnrSz5MpbHSQ,6
+azure_ai_evaluation-1.13.5.dist-info/RECORD,,