Remove GitHub Models support, doesnt support Responses API

Author: pamelafox

.env.sample

@@ -1,14 +1,11 @@
-# API_HOST can be either azure, openai, or github:
+# API_HOST can be either azure or openai:
 API_HOST=azure
 # Configure for Azure:
 AZURE_OPENAI_ENDPOINT=https://YOUR-AZURE-OPENAI-SERVICE-NAME.openai.azure.com
 AZURE_OPENAI_CHAT_DEPLOYMENT=YOUR-AZURE-DEPLOYMENT-NAME
 # Configure for OpenAI.com:
 OPENAI_API_KEY=YOUR-OPENAI-KEY
 OPENAI_MODEL=gpt-3.5-turbo
-# Configure for GitHub models: (GITHUB_TOKEN already exists inside Codespaces)
-GITHUB_MODEL=gpt-4.1-mini
-GITHUB_TOKEN=YOUR-GITHUB-PERSONAL-ACCESS-TOKEN
 # Configure for Redis (used by agent_history_redis.py, defaults to dev container Redis):
 REDIS_URL=redis://localhost:6379
 # Configure OTLP exporter (not needed in devcontainer, which sets these via docker-compose):

README.md

@@ -1,7 +1,7 @@
 <!--
 ---
 name: Python Agent Framework Demos
-description: Collection of Python examples for Microsoft Agent Framework using GitHub Models or Azure AI Foundry.
+description: Collection of Python examples for Microsoft Agent Framework using Microsoft Foundry.
 languages:
 - python
 products:
@@ -17,14 +17,13 @@ urlFragment: python-agentframework-demos
 [![Open in GitHub Codespaces](https://img.shields.io/static/v1?style=for-the-badge&label=GitHub+Codespaces&message=Open&color=brightgreen&logo=github)](https://codespaces.new/Azure-Samples/python-agentframework-demos)
 [![Open in Dev Containers](https://img.shields.io/static/v1?style=for-the-badge&label=Dev%20Containers&message=Open&color=blue&logo=visualstudiocode)](https://vscode.dev/redirect?url=vscode://ms-vscode-remote.remote-containers/cloneInVolume?url=https://github.com/Azure-Samples/python-agentframework-demos)
 
-This repository provides examples of [Microsoft Agent Framework](https://learn.microsoft.com/agent-framework/) using LLMs from [GitHub Models](https://github.com/marketplace/models), [Azure AI Foundry](https://learn.microsoft.com/azure/ai-foundry/), or other model providers. GitHub Models are free to use for anyone with a GitHub account, up to a [daily rate limit](https://docs.github.com/github-models/prototyping-with-ai-models#rate-limits).
+This repository provides examples of [Microsoft Agent Framework](https://learn.microsoft.com/agent-framework/) using LLMs from [Azure AI Foundry](https://learn.microsoft.com/azure/ai-foundry/) or other model providers.
 
 * [Getting started](#getting-started)
   * [GitHub Codespaces](#github-codespaces)
   * [VS Code Dev Containers](#vs-code-dev-containers)
   * [Local environment](#local-environment)
 * [Configuring model providers](#configuring-model-providers)
-  * [Using GitHub Models](#using-github-models)
   * [Using Azure AI Foundry models](#using-azure-ai-foundry-models)
   * [Using OpenAI.com models](#using-openaicom-models)
 * [Running the Python examples](#running-the-python-examples)
@@ -95,35 +94,11 @@ The dev container includes a Redis server, which is used by the `agent_history_r
 
 ## Configuring model providers
 
-These examples can be run with Azure AI Foundry, OpenAI.com, or GitHub Models, depending on the environment variables you set. All the scripts reference the environment variables from a `.env` file, and an example `.env.sample` file is provided. Host-specific instructions are below.
-
-## Using GitHub Models
-
-If you open this repository in GitHub Codespaces, you can run the scripts for free using GitHub Models without any additional steps, as your `GITHUB_TOKEN` is already configured in the Codespaces environment.
-
-If you want to run the scripts locally, you need to set up the `GITHUB_TOKEN` environment variable with a GitHub personal access token (PAT). You can create a PAT by following these steps:
-
-1. Go to your GitHub account settings.
-2. Click on "Developer settings" in the left sidebar.
-3. Click on "Personal access tokens" in the left sidebar.
-4. Click on "Tokens (classic)" or "Fine-grained tokens" depending on your preference.
-5. Click on "Generate new token".
-6. Give your token a name and select the scopes you want to grant. For this project, you don't need any specific scopes.
-7. Click on "Generate token".
-8. Copy the generated token.
-9. Set the `GITHUB_TOKEN` environment variable in your terminal or IDE:
-
-    ```shell
-    export GITHUB_TOKEN=your_personal_access_token
-    ```
-
-10. Optionally, you can use a model other than "gpt-4.1-mini" by setting the `GITHUB_MODEL` environment variable. Use a model that supports function calling, such as: `gpt-5`, `gpt-4.1-mini`, `gpt-4o`, `gpt-4o-mini`, `o3-mini`, `AI21-Jamba-1.5-Large`, `AI21-Jamba-1.5-Mini`, `Codestral-2501`, `Cohere-command-r`, `Ministral-3B`, `Mistral-Large-2411`, `Mistral-Nemo`, `Mistral-small`
+These examples can be run with Azure AI Foundry or OpenAI.com, depending on the environment variables you set. All the scripts reference the environment variables from a `.env` file, and an example `.env.sample` file is provided. Host-specific instructions are below.
 
 ## Using Azure AI Foundry models
 
-You can run all examples in this repository using GitHub Models. If you want to run the examples using models from Azure AI Foundry instead, you need to provision the Azure AI resources, which will incur costs.
-
-This project includes infrastructure as code (IaC) to provision Azure OpenAI deployments of "gpt-4.1-mini" and "text-embedding-3-large" via Azure AI Foundry. The IaC is defined in the `infra` directory and uses the Azure Developer CLI to provision the resources.
+This project includes infrastructure as code (IaC) to provision Azure OpenAI deployments of "gpt-5-mini" and "text-embedding-3-large" via Azure AI Foundry. The IaC is defined in the `infra` directory and uses the Azure Developer CLI to provision the resources.
 
 1. Make sure the [Azure Developer CLI (azd)](https://aka.ms/install-azd) is installed.
 

examples/agent_basic.py

@@ -9,7 +9,7 @@
 
 # Configure OpenAI client based on environment
 load_dotenv(override=True)
-API_HOST = os.getenv("API_HOST", "github")
+API_HOST = os.getenv("API_HOST", "azure")
 
 async_credential = None
 if API_HOST == "azure":
@@ -20,12 +20,6 @@
         api_key=token_provider,
         model=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"],
     )
-elif API_HOST == "github":
-    client = OpenAIChatClient(
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-        model=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
-    )
 else:
     client = OpenAIChatClient(
         api_key=os.environ["OPENAI_API_KEY"], model=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")

examples/agent_evaluation.py

@@ -28,7 +28,7 @@
 logger.setLevel(logging.INFO)
 
 load_dotenv(override=True)
-API_HOST = os.getenv("API_HOST", "github")
+API_HOST = os.getenv("API_HOST", "azure")
 
 async_credential = None
 if API_HOST == "azure":
@@ -44,18 +44,6 @@
         azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
         azure_deployment=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"],
     )
-elif API_HOST == "github":
-    client = OpenAIChatClient(
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-        model=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
-    )
-    eval_model_config = OpenAIModelConfiguration(
-        type="openai",
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-        model="openai/gpt-4.1-mini",
-    )
 else:
     client = OpenAIChatClient(
         api_key=os.environ["OPENAI_API_KEY"], model=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")

examples/agent_evaluation_batch.py

@@ -33,21 +33,14 @@
 logger.setLevel(logging.INFO)
 
 load_dotenv(override=True)
-API_HOST = os.getenv("API_HOST", "github")
+API_HOST = os.getenv("API_HOST", "azure")
 
 if API_HOST == "azure":
     model_config = AzureOpenAIModelConfiguration(
         type="azure_openai",
         azure_endpoint=os.environ["AZURE_OPENAI_ENDPOINT"],
         azure_deployment=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"],
     )
-elif API_HOST == "github":
-    model_config = OpenAIModelConfiguration(
-        type="openai",
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-        model="openai/gpt-4.1-mini",
-    )
 else:
     model_config = OpenAIModelConfiguration(
         type="openai",

examples/agent_evaluation_generate.py

@@ -29,7 +29,7 @@
 logger.setLevel(logging.INFO)
 
 load_dotenv(override=True)
-API_HOST = os.getenv("API_HOST", "github")
+API_HOST = os.getenv("API_HOST", "azure")
 
 async_credential = None
 if API_HOST == "azure":
@@ -40,12 +40,6 @@
         api_key=token_provider,
         model=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"],
     )
-elif API_HOST == "github":
-    client = OpenAIChatClient(
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-        model=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
-    )
 else:
     client = OpenAIChatClient(
         api_key=os.environ["OPENAI_API_KEY"], model=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")

examples/agent_history_redis.py

@@ -21,7 +21,7 @@
 
 # Configure OpenAI client based on environment
 load_dotenv(override=True)
-API_HOST = os.getenv("API_HOST", "github")
+API_HOST = os.getenv("API_HOST", "azure")
 REDIS_URL = os.getenv("REDIS_URL", "redis://localhost:6379")
 
 async_credential = None
@@ -33,12 +33,6 @@
         api_key=token_provider,
         model=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"],
     )
-elif API_HOST == "github":
-    client = OpenAIChatClient(
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-        model=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
-    )
 else:
     client = OpenAIChatClient(
         api_key=os.environ["OPENAI_API_KEY"], model=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")

examples/agent_history_sqlite.py

@@ -23,7 +23,7 @@
 
 # Configure OpenAI client based on environment
 load_dotenv(override=True)
-API_HOST = os.getenv("API_HOST", "github")
+API_HOST = os.getenv("API_HOST", "azure")
 
 async_credential = None
 if API_HOST == "azure":
@@ -34,12 +34,6 @@
         api_key=token_provider,
         model=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"],
     )
-elif API_HOST == "github":
-    client = OpenAIChatClient(
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-        model=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
-    )
 else:
     client = OpenAIChatClient(
         api_key=os.environ["OPENAI_API_KEY"], model=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")

examples/agent_knowledge_aisearch.py

@@ -22,7 +22,7 @@
 
 Requires:
   - An Azure AI Search service with a Knowledge Base
-  - An OpenAI-compatible model endpoint (Azure OpenAI, GitHub Models, or OpenAI)
+  - An OpenAI-compatible model endpoint (Azure OpenAI or OpenAI)
 
 Environment variables:
   - AZURE_SEARCH_ENDPOINT: Your Azure AI Search endpoint
@@ -55,7 +55,7 @@
 
 # ── Configuration ────────────────────────────────────────────────────
 load_dotenv(override=True)
-API_HOST = os.getenv("API_HOST", "github")
+API_HOST = os.getenv("API_HOST", "azure")
 
 SEARCH_ENDPOINT = os.environ["AZURE_SEARCH_ENDPOINT"]
 KNOWLEDGE_BASE_NAME = os.environ["AZURE_SEARCH_KNOWLEDGE_BASE_NAME"]
@@ -71,12 +71,6 @@
         api_key=token_provider,
         model=os.environ["AZURE_OPENAI_CHAT_DEPLOYMENT"],
     )
-elif API_HOST == "github":
-    client = OpenAIChatClient(
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-        model=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
-    )
 else:
     client = OpenAIChatClient(
         api_key=os.environ["OPENAI_API_KEY"], model=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")

examples/agent_knowledge_pg.py

@@ -20,7 +20,7 @@
 
 Requires:
   - PostgreSQL with pgvector extension (see docker-compose.yml)
-  - An embedding model (GitHub Models, Azure OpenAI, or OpenAI)
+  - An embedding model (Azure OpenAI or OpenAI)
 
 See also: agent_knowledge_sqlite.py for a simpler SQLite-only (keyword search) version.
 """
@@ -51,7 +51,7 @@
 
 # ── OpenAI clients (chat + embeddings) ───────────────────────────────
 load_dotenv(override=True)
-API_HOST = os.getenv("API_HOST", "github")
+API_HOST = os.getenv("API_HOST", "azure")
 POSTGRES_URL = os.getenv("POSTGRES_URL", "postgresql://admin:LocalPasswordOnly@db:5432/postgres")
 EMBEDDING_DIMENSIONS = 256  # Smaller dimension for efficiency
 
@@ -75,17 +75,6 @@
         api_key=sync_token_provider(),
     )
     embed_model = os.environ.get("AZURE_OPENAI_EMBEDDING_DEPLOYMENT", "text-embedding-3-small")
-elif API_HOST == "github":
-    chat_client = OpenAIChatClient(
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-        model=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
-    )
-    embed_client = OpenAI(
-        base_url="https://models.github.ai/inference",
-        api_key=os.environ["GITHUB_TOKEN"],
-    )
-    embed_model = "text-embedding-3-small"
 else:
     chat_client = OpenAIChatClient(
         api_key=os.environ["OPENAI_API_KEY"], model=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")