Merge branch 'main' into main

Author: kkchandi

samples/agent-catalog/3p-agent-samples/README.md

@@ -1,3 +1,9 @@
 ## Agent Catalog - 3P Agent Samples
 
-WARNING: <disclaimer here>
+This folder contains Third-Party Agent code samples.
+
+**IMPORTANT NOTE:**  Starter templates, instructions, code samples and resources in this 3P-agent-samples file (“samples”) are designed to assist in accelerating development of agents for specific scenarios. It is important that you review all provided resources and carefully test Agent behavior in the context of your use case: ([Learn more](https://learn.microsoft.com/en-us/legal/cognitive-services/agents/transparency-note?context=%2Fazure%2Fai-services%2Fagents%2Fcontext%2Fcontext)). 
+
+Certain Agent offerings may be subject to legal and regulatory requirements, may require licenses, or may not be suitable for all industries, scenarios, or use cases. By using any sample, you are acknowledging that Agents or other output created using that sample are solely your responsibility, and that you will comply with all applicable laws, regulations, and relevant safety standards, terms of service, and codes of conduct.
+
+**WARNING:**  The samples in this 3P-agent-samples folder were created by third parties, not Microsoft, and have not been tested or verified by Microsoft. Your use is subject to the terms provided by the relevant third party.  By using any third-party sample in this file, you are acknowledging that Microsoft has no responsibility to you or others with respect to these samples.  

samples/agent-catalog/3p-agent-samples/foundry-agent-service-sdk/README.md

@@ -0,0 +1,9 @@
+## Agent Catalog - 3P Agent Samples for Azure AI Foundry Agent Service SDK
+
+This folder contains Third-Party Agent code samples for Azure Ai Foundry Service SDK.
+
+**IMPORTANT NOTE:**  Starter templates, instructions, code samples and resources in this 3P-agent-samples file (“samples”) are designed to assist in accelerating development of agents for specific scenarios. It is important that you review all provided resources and carefully test Agent behavior in the context of your use case: ([Learn more](https://learn.microsoft.com/en-us/legal/cognitive-services/agents/transparency-note?context=%2Fazure%2Fai-services%2Fagents%2Fcontext%2Fcontext)). 
+
+Certain Agent offerings may be subject to legal and regulatory requirements, may require licenses, or may not be suitable for all industries, scenarios, or use cases. By using any sample, you are acknowledging that Agents or other output created using that sample are solely your responsibility, and that you will comply with all applicable laws, regulations, and relevant safety standards, terms of service, and codes of conduct.
+
+**WARNING:**  The samples in this 3P-agent-samples folder were created by third parties, not Microsoft, and have not been tested or verified by Microsoft. Your use is subject to the terms provided by the relevant third party.  By using any third-party sample in this file, you are acknowledging that Microsoft has no responsibility to you or others with respect to these samples.  

samples/agent-catalog/3p-agent-samples/foundry-agent-service-sdk/auquan/README.md

@@ -1,3 +1,8 @@
+**IMPORTANT NOTE FROM MICROSOFT:** The sample below was created by a third party, not Microsoft, and has not been tested or verified by Microsoft. Your use is subject to the terms provided by the relevant third party.  By using the third-party sample in this file, you are acknowledging that Microsoft has no responsibility to you or others with respect to this sample.  
+
+
+------
+
 # Auquan Due Diligence Risk Analyst Agent
 
 This code sample for the Due Diligence Risk Analyst enables building an expert system designed to provide comprehensive risk analysis and timeline tracking for companies. It specializes in analyzing company risks across multiple dimensions including operational, financial, regulatory, and sustainability metrics. The agent processes structured risk data from Auquan's API, generates detailed timelines, and provides actionable insights through well-formatted reports with visual risk indicators.
@@ -99,17 +104,17 @@ template.py
 ---
 ## 💬 Example Agent Interactions
 
-- "Do a risk analysis for Microsoft"
+- "Do a risk analysis for Darktrace"
 
-- "What are the critical risks identified for Microsoft?"
+- "What are the critical risks identified for Openai"
 
-- "Generate a sustainability analysis for Microsoft"
+- "Generate a sustainability analysis for ClimatePartner"
 
-- "Create a table indicating risks for Microsoft showing all categories and severity"
+- "What is the overall risk range of Zoom?"
 
-- "What is the overall risk range of Microsoft?"
+- "What are the recent themes around Coursera and what are their impacts?"
 
-- "What are the recent themes around Microsoft and what are their impacts?"
+- "What are the recent risks for Autodesk ?"
 
 
 ## 🛠 Customization Tips
@@ -122,3 +127,7 @@ template.py
 
 - **Connect with local files**  
   Add your local files to include your data in risk-analysis
+
+
+## Note : 
+If you encounter a "rate limit exceeded" error, navigate to the "Models + Endpoints" tab in the Foundry Portal and increase the TPM (tokens per minute) limit for your model. We recommend setting it to around 100,000 to start with.

samples/agent-catalog/3p-agent-samples/foundry-agent-service-sdk/marqueeinsights-news-agent/README.md

@@ -1,10 +1,15 @@
+**IMPORTANT NOTE FROM MICROSOFT:** The sample below was created by a third party, not Microsoft, and has not been tested or verified by Microsoft. Your use is subject to the terms provided by the relevant third party.  By using the third-party sample in this file, you are acknowledging that Microsoft has no responsibility to you or others with respect to this sample.  
+
+
+------
+
 # AI News Agent
 
 This code sample enables creating an intelligent information summarization agent designed to help executives and decision-makers stay on top of the rapidly evolving world of artificial intelligence. By continuously scanning credible news sources, it identifies and summarizes the most impactful AI developments—especially those relevant to the Microsoft ecosystem, healthcare, and legal industries.
 
 The agent reduces information overload by prioritizing high-value updates and presenting them in a clear, digestible Markdown table format. Each summary includes a headline, date, key insight, strategic implications, and a verified source link.
 
-**AI News is not a replacement for human analysis or legal due diligence. Instead, it augments executive awareness by surfacing credible developments that may require further attention or discussion. All strategic decisions and compliance assessments remain the responsibility of the end user.**
+**WARNING:** AI News is not a replacement for human analysis or legal due diligence. Instead, it augments executive awareness by surfacing credible developments that may require further attention or discussion. All strategic decisions and compliance assessments remain the responsibility of the end user.
 
 
 ## 🎯 Use Cases

samples/agent-catalog/3p-agent-samples/foundry-agent-service-sdk/mihcm-hr-assist-agent/README.md

@@ -1,7 +1,14 @@
+**IMPORTANT NOTE FROM MICROSOFT:** The sample below was created by a third party, not Microsoft, and has not been tested or verified by Microsoft. Your use is subject to the terms provided by the relevant third party.  By using the third-party sample in this file, you are acknowledging that Microsoft has no responsibility to you or others with respect to this sample.  
+
+
+------
+
+
 # HR Assist Agent
 
 This repository provides a template for deploying and managing an Azure AI Agent for MiHCM. The project leverages Azure Bicep for infrastructure deployment and Python for interacting with Azure AI services and APIs.
 
+
 ## Features
 
 - **Azure AI Agent Deployment**: Automates the deployment of Azure AI resources, including AI Hubs, AI Projects, and dependent resources.
@@ -73,4 +80,4 @@ Ocp-Apim-Subscription-Key: <your key>
 ## Support
 Have a question or need assistance? Get in touch with our team:
 - Support: [email protected]
-- Info on how to setup an account with MiHCM: https://mihcm.com/contact-us/ 
+- Info on how to setup an account with MiHCM: https://mihcm.com/contact-us/ 

samples/agent-catalog/3p-agent-samples/foundry-agent-service-sdk/mihcm-hr-assist-agent/template.py

@@ -1,12 +1,16 @@
 import os
 import jsonref
-from azure.ai.projects import AIProjectClient
-from azure.identity import DefaultAzureCredential
-from azure.ai.projects.models import OpenApiTool,OpenApiConnectionAuthDetails, OpenApiConnectionSecurityScheme
-from dotenv import load_dotenv
-from datetime import datetime
-import requests
 import json
+from datetime import datetime
+from dotenv import load_dotenv
+from azure.identity import DefaultAzureCredential
+from azure.ai.agents import AgentsClient
+from azure.ai.agents.models import (
+    ListSortOrder,
+    OpenApiTool,
+    OpenApiConnectionAuthDetails,
+    OpenApiConnectionSecurityScheme,
+)
 
 
 """
@@ -40,6 +44,13 @@
 # Set the employee code for the user
 employeeCode = 1
 
+# Read config
+config = {
+    "project_endpoint": os.environ["PROJECT_ENDPOINT"],
+    "connection_id": os.environ["PROJECT_OPENAPI_CONNECTION_ID"],
+    "model_name": "gpt-4o"
+}
+
 #sample reuqests to test the agent
 
 # sample_requests = [
@@ -51,17 +62,14 @@
 #     "list all my work items for today and yesterday"
 # ]
 
-# Create an Azure AI Client from a connection string, copied from your Azure AI Foundry project.
-project_client = AIProjectClient.from_connection_string(
+# Create agent client
+agents_client = AgentsClient(
+    endpoint=config["project_endpoint"],
     credential=DefaultAzureCredential(),
-    conn_str=os.environ["PROJECT_CONNECTION_STRING"],
+    api_version="2025-05-15-preview"
 )
 
-# create a connection object for the openapi tool's API key
-connection_name = os.environ["PROJECT_OPENAPI_CONNECTION_NAME"]
-connection = project_client.connections.get(connection_name=connection_name)
-
-# use with local openapi.json file
+# Load OpenAPI spec
 with open('./mihcmExternalAPI.json', 'r') as f:
     openapi_spec = jsonref.loads(f.read())
 
@@ -70,11 +78,18 @@
 # response.raise_for_status()  # makes sure it raises an error if something goes wrong
 # openapi_spec = jsonref.loads(response.text)
 
-# Create Auth object for the OpenApiTool 
-auth = OpenApiConnectionAuthDetails(security_scheme=OpenApiConnectionSecurityScheme(connection_id=connection.id))
+# Set up the OpenAPI connection auth
+auth = OpenApiConnectionAuthDetails(
+    security_scheme=OpenApiConnectionSecurityScheme(connection_id=config["connection_id"])
+)
 
-# Initialize agent OpenAPI tool using the read in OpenAPI spec
-openapi = OpenApiTool(name="MiHCMAgent", spec=openapi_spec, description="Lets communicate with MiHCM agent to execute different tasks", auth=auth)
+# Define OpenAPI tool
+mihcm_tool = OpenApiTool(
+    name="MiHCMAgent",
+    spec=openapi_spec,
+    description="Lets communicate with MiHCM agent to execute different tasks",
+    auth=auth
+)
 
 #Agent instructions 
 instructions = f"""You are a helpful assistant.
@@ -92,40 +107,45 @@
 
 agent_request = "list all my work items for today and yesterday"
 
-# Create agent with OpenAPI tool and process assistant run
-with project_client:
-    agent = project_client.agents.create_agent(
-        model="gpt-4o-mini",
+# Run the interaction with the agent
+with agents_client:
+    # Create agent
+    agent = agents_client.create_agent(
+        model=config["model_name"],
         name="mi-agent",
         instructions=instructions,
-        tools=openapi.definitions
+        tools=mihcm_tool.definitions
     )
     print(f"Created agent, ID: {agent.id}")
 
-    # Create thread for communication
-    thread = project_client.agents.create_thread()
+    # Create thread
+    thread = agents_client.threads.create()
     print(f"Created thread, ID: {thread.id}")
-    # Create message to thread
-    message = project_client.agents.create_message(
+
+    # Create message
+    message = agents_client.messages.create(
         thread_id=thread.id,
         role="user",
-        content=agent_request,
+        content=agent_request
     )
-    print(f"Created message, ID: {message.id}")
+    print(f"Created message: {message['id']}")
 
-    # Create and process agent run in thread with tools
-    run = project_client.agents.create_and_process_run(thread_id=thread.id, agent_id=agent.id)
+    # Run agent
+    run = agents_client.runs.create_and_process(thread_id=thread.id, agent_id=agent.id)
     print(f"Run finished with status: {run.status}")
 
     if run.status == "failed":
         print(f"Run failed: {run.last_error}")
 
-    # Delete the assistant when done
-    project_client.agents.delete_agent(agent.id)
-    print("Deleted agent")
+    # Read response
+    messages = agents_client.messages.list(thread_id=thread.id, order=ListSortOrder.ASCENDING)
+    for msg in messages:
+        if msg.text_messages:
+            last_text = msg.text_messages[-1]
+            print(f"{msg.role}: {last_text.text.value}")
 
-    # Fetch and log all messages
-    messages = project_client.agents.list_messages(thread_id=thread.id,after=message.id,order="asc")
-    print(f"Messages: {messages.data[0].content[0].text.value}")
+    # Cleanup
+    agents_client.delete_agent(agent.id)
+    print("Deleted agent")
 
- 
+ 

samples/agent-catalog/3p-agent-samples/foundry-agent-service-sdk/saifr-comm-compliance-agent/README.md

@@ -1,15 +1,22 @@
+**IMPORTANT NOTE FROM MICROSOFT:** The sample below was created by a third party, not Microsoft, and has not been tested or verified by Microsoft. Your use is subject to the terms provided by the relevant third party.  By using the third-party sample in this file, you are acknowledging that Microsoft has no responsibility to you or others with respect to this sample.  
+
+
+------
+
+
 # Saifr Communication Compliance Agent
 
 ## Description 
 
 This code sample helps create the Saifr Communication Compliance Agent that converts potentially noncompliant text to a more compliant, fair, and balanced version, helping end users better adhere to relevant regulatory guidelines.
 
 
-_Saifr Agent is not intended to replace the end user’s legal, compliance, business, or other functions, 
+**WARNING:** Saifr Agent is not intended to replace the end user’s legal, compliance, business, or other functions, 
 or to satisfy any legal or regulatory obligations.  Note that all compliance responsibilities remain solely 
 those of the end user and that certain communications may require review and approval by properly licensed 
 individuals.  Saifr is not responsible for determining compliance with rules and will not be liable for 
-actions taken or not taken based on Agent use._
+actions taken or not taken based on Agent use.
+
 
 ### Architecture Overview
 The Saifr Communication Compliance Agent uses gpt-40-mini (version:2024-07-18) as the agent orchestrator LLM. We chose 

samples/agent-catalog/3p-agent-samples/foundry-agent-service-sdk/sightmachine-filler-optimization-agent/README.md

@@ -1,3 +1,8 @@
+**IMPORTANT NOTE FROM MICROSOFT:** The sample below was created by a third party, not Microsoft, and has not been tested or verified by Microsoft. Your use is subject to the terms provided by the relevant third party.  By using the third-party sample in this file, you are acknowledging that Microsoft has no responsibility to you or others with respect to this sample.  
+
+
+------
+
 <h1>
 <span style="display: flex; align-items: center;">
   <picture>
@@ -11,7 +16,8 @@
 
 This repository provides templates for deploying and running the Sight Machine Filler Agent.  Sight Machine is a data and analytics platform for manufacturing.  We model data, provide basic visualization and analytics tools, and provide advanced AI analytics for manufacturing plant floor users.  For more information, see www.sightmachine.com.
 
-**IMPORTANT**: Full functionality of this agent, including advanced features, requires a subscription to Sight Machine. However, basic example data allows users to test and explore the core functionality of the agent.
+**WARNING**: Full functionality of this agent, including advanced features, requires a subscription to Sight Machine. However, basic example data allows users to test and explore the core functionality of the agent.
+
 
 ## Use Cases
 
@@ -89,4 +95,4 @@ Finally, create the `local.settings.json` in the `python` folder.
 ## Support
 
 - Technical support: email `[email protected]`
-- Setting up an account: Fill out our [contact form](https://sightmachine.com/contact/)
+- Setting up an account: Fill out our [contact form](https://sightmachine.com/contact/)

samples/agent-catalog/CONTRIBUTING.md

@@ -38,14 +38,31 @@ Optional (as appropriate)
 
 ```text
 /<agent-name>/
+
 ├── README.md
-├── template.py
-├── deploy.bicep (optional)
-├── sample_data/ (optional)
-│   ├── example_input.json
-│   └── example_output.json
+├── python/                        # Python-specific implementation
+│   ├── template.py
+│   ├── deploy.bicep (optional)
+│   ├── src/
+│   │   └── custom_logic.py
+│   ├── tests/ (optional)
+│   │   └── test_agent.py
+│   └── sample_data/
+│       ├── example_input.json
+│       └── example_output.json
+├── csharp/                        # C# implementation
+│   ├── template.csproj
+│   ├── deploy.bicep (optional)
+│   ├── src/
+│   │   └── AgentLogic.cs
+│   │   └── Tools/
+│   │       └── CustomTool.cs
+│   ├── tests/ (optional)
+│   │   └── AgentTests.cs
 ├── assets/ (optional)
-│   └── architecture.png
+│   ├── architecture.png
+│   ├── knowledge_example.json
+│   └── logo.svg (required if not Microsoft-authored)
 └── LICENSE
 
 ```

samples/agent-catalog/msft-agent-samples/README.md

@@ -1,3 +1,7 @@
 ## Agent Catalog - Microsoft-authored Agent Samples
 
-WARNING: <disclaimer here>
+This folder contains Microsoft-authored Agent code samples for the Azure AI Agent Service SDK and the Semantic Kernel SDK.
+
+**IMPORTANT NOTE:** Starter templates, instructions, code samples and resources in this msft-agent-samples file (“samples”) are designed to assist in accelerating development of agents for specific scenarios. It is important that you review all provided resources and carefully test Agent behavior in the context of your use case: ([Learn More](https://learn.microsoft.com/en-us/legal/cognitive-services/agents/transparency-note?context=%2Fazure%2Fai-services%2Fagents%2Fcontext%2Fcontext)). 
+
+Certain Agent offerings may be subject to legal and regulatory requirements, may require licenses, or may not be suitable for all industries, scenarios, or use cases. By using any sample, you are acknowledging that Agents or other output created using that sample are solely your responsibility, and that you will comply with all applicable laws, regulations, and relevant safety standards, terms of service, and codes of conduct.