fix: add file_name and file_mime_type to token usage telemetry events

- Pass file metadata in TokenUsageScope for MapHandler, Summarize,
  GapAnalysis, and RAI executors so the workbook file-type query works
- Fix dedup in model cost KQL query (workbook + queries file)

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: Prachig-Microsoft

src/ContentProcessor/src/libs/pipeline/handlers/map_handler.py

@@ -266,11 +266,14 @@ async def execute(self, context: MessageContext) -> StepResult:
         )
 
         # Track token usage for this LLM call
+        source_file = context.data_pipeline.get_source_files()[0]
         with TokenUsageScope(
             token_emitter,
             agent_name="MapHandler",
             model_deployment_name=self.application_context.configuration.app_azure_openai_model,
             process_id=context.data_pipeline.pipeline_status.process_id,
+            file_name=source_file.name,
+            file_mime_type=source_file.mime_type or "",
         ) as scope:
             scope.add(gpt_response)
 

src/ContentProcessorWorkflow/src/steps/gap_analysis/executor/gap_executor.py

@@ -197,11 +197,15 @@ async def handle_execute(
 
         # Track token usage for gap analysis
         model_name = agent_framework_helper.settings.get_service_config("default").chat_deployment_name
+        file_names = ", ".join(f.file_name for f in processed_files) if processed_files else ""
+        file_types = ", ".join(set(f.mime_type for f in processed_files if f.mime_type)) if processed_files else ""
         with TokenUsageScope(
             token_emitter,
             agent_name="GapAnalysis",
             model_deployment_name=model_name,
             process_id=result.claim_process_id,
+            file_name=file_names,
+            file_mime_type=file_types,
         ) as scope:
             scope.add(model_response)
 

src/ContentProcessorWorkflow/src/steps/rai/executor/rai_executor.py

@@ -191,11 +191,15 @@ async def handle_exectue(
 
         # Track token usage for RAI check
         model_name = agent_framework_helper.settings.get_service_config("default").chat_deployment_name
+        file_names = ", ".join(f.file_name for f in processed_files) if processed_files else ""
+        file_types = ", ".join(set(f.mime_type for f in processed_files if f.mime_type)) if processed_files else ""
         with TokenUsageScope(
             token_emitter,
             agent_name="RAI",
             model_deployment_name=model_name,
             process_id=result.claim_process_id,
+            file_name=file_names,
+            file_mime_type=file_types,
         ) as scope:
             scope.add(model_response)
 

src/ContentProcessorWorkflow/src/steps/summarize/executor/summarize_executor.py

@@ -197,11 +197,15 @@ async def handle_execute(
 
         # Track token usage for summarization
         model_name = agent_framework_helper.settings.get_service_config("default").chat_deployment_name
+        file_names = ", ".join(f.file_name for f in processed_files) if processed_files else ""
+        file_types = ", ".join(set(f.mime_type for f in processed_files if f.mime_type)) if processed_files else ""
         with TokenUsageScope(
             token_emitter,
             agent_name="Summarize",
             model_deployment_name=model_name,
             process_id=result.claim_process_id,
+            file_name=file_names,
+            file_mime_type=file_types,
         ) as scope:
             scope.add(model_response)