Refactor sample scripts and clean up code formatting across various files

Author: howieleung

sdk/ai/azure-ai-projects/azure/ai/projects/_utils/utils.py

@@ -10,7 +10,6 @@
 
 from .._utils.model_base import Model, SdkJSONEncoder
 
-
 # file-like tuple could be `(filename, IO (or bytes))` or `(filename, IO (or bytes), content_type)`
 FileContent = Union[str, bytes, IO[str], IO[bytes]]
 

sdk/ai/azure-ai-projects/azure/ai/projects/operations/_operations.py

@@ -12327,7 +12327,7 @@ def list_memories(
                 raise TypeError("missing required argument: scope")
             body = {"scope": scope}
             body = {k: v for k, v in body.items() if v is not None}
-        
+
         content_type = content_type or "application/json"
         _content = None
         if isinstance(body, (IOBase, bytes)):

sdk/ai/azure-ai-projects/samples/agents/sample_external_agents_crud.py

@@ -76,4 +76,4 @@
         print(f"  - {external_agent.name} ({external_agent.id})")
 
     deleted = project_client.agents.delete(agent_name, force=True)
-    print(f"Deleted external agent: {deleted.name} deleted={deleted.deleted}")
+    print(f"Deleted external agent: {deleted.name} deleted={deleted.deleted}")

sdk/ai/azure-ai-projects/samples/agents/sample_external_agents_crud_async.py

@@ -84,4 +84,4 @@ async def main() -> None:
 
 
 if __name__ == "__main__":
-    asyncio.run(main())
+    asyncio.run(main())

sdk/ai/azure-ai-projects/samples/datasets/sample_dataset_generation_job_traces_for_finetuning.py

@@ -97,7 +97,9 @@
     # ------------------------------------------------------------------
     # 1. Submit a fine-tuning data generation job that reads agent traces.
     # ------------------------------------------------------------------
-    print(f"Create a fine-tuning data generation job from traces for agent `{agent_name}` (window: {traces_window_days} day(s)).")
+    print(
+        f"Create a fine-tuning data generation job from traces for agent `{agent_name}` (window: {traces_window_days} day(s))."
+    )
     job = DataGenerationJob(
         inputs=DataGenerationJobInputs(
             name=f"traces-finetuning-{run_id}",

sdk/ai/azure-ai-projects/samples/evaluations/sample_rubric_evaluator_generation_basic.py

@@ -101,8 +101,7 @@
             "evaluator_name": evaluator_name,
             "evaluator_display_name": "Reservation Quality (Generated)",
             "evaluator_description": (
-                "Quality evaluator generated from a prompt describing a "
-                "restaurant reservation assistant."
+                "Quality evaluator generated from a prompt describing a " "restaurant reservation assistant."
             ),
             "sources": [
                 {
@@ -212,8 +211,7 @@
                         item={
                             "query": "Book a table for 4 tomorrow at 7 PM.",
                             "response": (
-                                "Booked - table for 4 tomorrow at 7:00 PM. A confirmation "
-                                "SMS is on its way."
+                                "Booked - table for 4 tomorrow at 7:00 PM. A confirmation " "SMS is on its way."
                             ),
                         }
                     ),

sdk/ai/azure-ai-projects/samples/evaluations/sample_rubric_evaluator_generation_lifecycle.py

@@ -79,8 +79,7 @@
             "type": "Prompt",
             "description": "Inline application overview.",
             "prompt": (
-                "You are evaluating a simple Q&A assistant that answers factual "
-                "questions clearly and concisely."
+                "You are evaluating a simple Q&A assistant that answers factual " "questions clearly and concisely."
             ),
         }
     ],

sdk/ai/azure-ai-projects/tests/samples/llm_instructions.py

@@ -18,8 +18,7 @@
 
 from typing import Final
 
-agent_tools_instructions: Final[str] = (
-    """
+agent_tools_instructions: Final[str] = """
 We just ran Python code and captured print/log output in an attached log file (TXT).
 Validate whether sample execution/output is correct for a tool-driven assistant workflow.
 
@@ -44,11 +43,9 @@
 
 Always include `reason` with a concise explanation tied to the observed print output.
 """.strip()
-)
 
 
-memories_instructions: Final[str] = (
-    """
+memories_instructions: Final[str] = """
 We just ran Python code and captured print/log output in an attached log file (TXT).
 Validate whether sample execution/output is correct for a memories workflow.
 
@@ -73,11 +70,9 @@
 
 Always include `reason` with a concise explanation tied to the observed print output.
 """.strip()
-)
 
 
-agents_instructions: Final[str] = (
-    """
+agents_instructions: Final[str] = """
 We just ran Python code and captured print/log output in an attached log file (TXT).
 Validate whether sample execution/output is correct.
 
@@ -108,11 +103,9 @@
 
 Always include `reason` with a concise explanation tied to the observed print output.
 """.strip()
-)
 
 
-chat_completions_instructions: Final[str] = (
-    """
+chat_completions_instructions: Final[str] = """
 We just ran Python code and captured print/log output in an attached log file (TXT).
 Validate whether sample execution/output is correct for Chat Completions scenarios.
 
@@ -131,11 +124,9 @@
 
 Always include `reason` with a concise explanation tied to the observed print output.
 """.strip()
-)
 
 
-resource_management_instructions: Final[str] = (
-    """
+resource_management_instructions: Final[str] = """
 We just ran Python code and captured print/log output in an attached log file (TXT).
 Validate whether sample execution/output is correct for resource-management samples (for example
 connections, files, and deployments).
@@ -161,11 +152,9 @@
 
 Always include `reason` with a concise explanation tied to the observed print output.
 """.strip()
-)
 
 
-fine_tuning_instructions: Final[str] = (
-    """
+fine_tuning_instructions: Final[str] = """
 We just ran Python code and captured print/log output in an attached log file (TXT).
 Validate whether sample execution/output is correct for a fine-tuning workflow.
 
@@ -189,11 +178,9 @@
 
 Always include `reason` with a concise explanation tied to the observed print output.
 """.strip()
-)
 
 
-evaluations_instructions: Final[str] = (
-    """
+evaluations_instructions: Final[str] = """
 We just ran Python code for an evaluation sample and captured print/log output in an attached log file (TXT).
 Your job: determine if the sample code executed to completion WITHOUT throwing an unhandled exception.
 
@@ -215,11 +202,9 @@
 
 Always respond with `reason` indicating the reason for the response.
 """.strip()
-)
 
 
-hosted_agents_instructions: Final[str] = (
-    """
+hosted_agents_instructions: Final[str] = """
 We just ran Python code for a hosted-agent sample and captured print/log output in an attached log file (TXT).
 Validate whether the sample executed correctly.
 
@@ -241,7 +226,6 @@
 
 Always include `reason` with a concise explanation tied to the observed print output.
 """.strip()
-)
 
 
 # Folder (under samples/) -> instructions.

sdk/ai/azure-ai-projects/tests/samples/test_samples.py

@@ -151,22 +151,29 @@ def test_deployments_samples(self, sample_path: str, **kwargs) -> None:
         executor.validate_print_calls_by_llm()
 
     @servicePreparer()
-    @additionalSampleTests(
-        [
-            AdditionalSampleTestDetail(
-                test_id="sample_dataset_generation_job_simpleqna_with_prompt_source",
-                sample_filename="sample_dataset_generation_job_simpleqna_with_prompt_source.py",
-                env_vars={
-                    "POLL_INTERVAL_SECONDS": "60",
-                },
-            ),
-        ]
-    )
+    # @additionalSampleTests(
+    #     [
+    #         AdditionalSampleTestDetail(
+    #             test_id="sample_dataset_generation_job_simpleqna_with_prompt_source",
+    #             sample_filename="sample_dataset_generation_job_simpleqna_with_prompt_source.py",
+    #             env_vars={
+    #                 "POLL_INTERVAL_SECONDS": "60",
+    #             },
+    #         ),
+    #     ]
+    # )
     @pytest.mark.parametrize(
         "sample_path",
         get_sample_paths(
             "datasets",
-            samples_to_skip=["sample_dataset_generation_job_simpleqna_with_prompt_source.py"],
+            samples_to_skip=[
+                "sample_dataset_generation_job_simpleqna_with_prompt_source.py",  # PR #47067: recording not yet available
+                "sample_dataset_generation_job_traces_for_finetuning.py",  # PR #47067: recording not yet available
+                "sample_dataset_generation_job_simpleqna_for_finetuning.py",  # PR #47067: recording not yet available
+                "sample_dataset_generation_job_traces_for_evaluation.py",  # PR #47067: recording not yet available
+                "sample_dataset_generation_job_simpleqna_with_agent_source.py",  # PR #47067: recording not yet available
+                "sample_dataset_generation_job_simpleqna_with_file_source.py",  # PR #47067: recording not yet available
+            ],
         ),
     )
     @SamplePathPasser()

sdk/ai/azure-ai-projects/tests/samples/test_samples_evaluations.py

@@ -152,6 +152,15 @@ class TestSamplesEvaluations(AzureRecordedTestCase):
                 "sample_synthetic_data_agent_evaluation.py",  # Synthetic data gen is long-running preview feature
                 "sample_synthetic_data_model_evaluation.py",  # Synthetic data gen is long-running preview feature
                 "sample_eval_catalog_prompt_based_evaluators.py",  # For some reason fails with 500 (Internal server error)
+                "sample_multiturn_conversation_evaluation.py",  # PR #47034: new multi-turn sample, recording not yet available
+                "sample_multiturn_conversation_simulation.py",  # PR #47034: new multi-turn sample, recording not yet available
+                "sample_multiturn_trace_evaluation_agent_filter.py",  # PR #47034: new multi-turn sample, recording not yet available
+                "sample_multiturn_trace_evaluation_by_id.py",  # PR #47034: new multi-turn sample, recording not yet available
+                "sample_rubric_evaluator_generation_all_sources.py",  # PR #47057: recording not yet available
+                "sample_rubric_evaluator_generation_lifecycle.py",  # PR #47057: recording not yet available
+                "sample_rubric_evaluator_generation_basic.py",  # PR #47057: recording not yet available
+                "sample_rubric_evaluator_manual.py",  # PR #47057: recording not yet available
+                "sample_rubric_evaluator_generation_iterate.py",  # PR #47057: recording not yet available
             ],
         ),
     )