Merge branch 'main' into workflowbuilders

Author: pamelafox

.devcontainer/Dockerfile

@@ -3,6 +3,13 @@ FROM mcr.microsoft.com/devcontainers/python:3.12-bookworm
 # Required for cloning agent-framework from GitHub (it uses Git LFS)
 RUN apt-get update && apt-get install -y git-lfs && git lfs install && rm -rf /var/lib/apt/lists/*
 
+# Required for building Rust-based Python packages (e.g. base2048 via pyrit/azure-ai-evaluation[redteam])
+ENV RUSTUP_HOME="/home/vscode/.rustup" CARGO_HOME="/home/vscode/.cargo"
+ENV PATH="/home/vscode/.cargo/bin:${PATH}"
+RUN mkdir -p /home/vscode/.rustup /home/vscode/.cargo \
+    && curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y \
+    && chown -R vscode:vscode /home/vscode/.rustup /home/vscode/.cargo
+
 COPY --from=ghcr.io/astral-sh/uv:latest /uv /uvx /usr/local/bin/
 
 COPY pyproject.toml uv.lock /tmp/uv-tmp/

.env.sample

@@ -7,7 +7,7 @@ AZURE_OPENAI_CHAT_DEPLOYMENT=YOUR-AZURE-DEPLOYMENT-NAME
 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-5-mini
+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

README.md

@@ -117,13 +117,13 @@ If you want to run the scripts locally, you need to set up the `GITHUB_TOKEN` en
     export GITHUB_TOKEN=your_personal_access_token
     ```
 
-10. Optionally, you can use a model other than "gpt-5-mini" by setting the `GITHUB_MODEL` environment variable. Use a model that supports function calling, such as: `gpt-5`, `gpt-5-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`
+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`
 
 ## 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-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.
+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.
 
 1. Make sure the [Azure Developer CLI (azd)](https://aka.ms/install-azd) is installed.
 
@@ -191,11 +191,14 @@ You can run the examples in this repository by executing the scripts in the `exa
 | [agent_memory_redis.py](examples/agent_memory_redis.py) | Long-term memory with RedisContextProvider, storing and retrieving conversational context from Redis. |
 | [agent_memory_mem0.py](examples/agent_memory_mem0.py) | Long-term memory with Mem0 OSS, extracting and recalling distilled user facts across sessions. |
 | [agent_supervisor.py](examples/agent_supervisor.py) | A supervisor orchestrating activity and recipe sub-agents. |
+<<<<<<< HEAD
 | [agent_with_subagent.py](examples/agent_with_subagent.py) | Context isolation with sub-agents to keep prompts focused on relevant tools. |
 | [agent_without_subagent.py](examples/agent_without_subagent.py) | Context bloat example where one agent carries all tool schemas in a single prompt. |
 | [agent_summarization.py](examples/agent_summarization.py) | Context compaction via summarization middleware to reduce token usage in long conversations. |
 | [workflow_magenticone.py](examples/workflow_magenticone.py) | A MagenticOne multi-agent workflow. |
 | [workflow_hitl.py](examples/workflow_hitl.py) | Human-in-the-loop (HITL) for tool-enabled agents with human feedback. |
+=======
+>>>>>>> main
 | [agent_middleware.py](examples/agent_middleware.py) | Agent, chat, and function middleware for logging, timing, and blocking. |
 | [agent_knowledge_aisearch.py](examples/agent_knowledge_aisearch.py) | Knowledge retrieval (RAG) using Azure AI Search with AgentFrameworkAzureAISearchRAG. |
 | [agent_knowledge_sqlite.py](examples/agent_knowledge_sqlite.py) | Knowledge retrieval (RAG) using a custom context provider with SQLite FTS5. |
@@ -205,6 +208,7 @@ You can run the examples in this repository by executing the scripts in the `exa
 | [agent_mcp_remote.py](examples/agent_mcp_remote.py) | An agent using a remote MCP server (Microsoft Learn) for documentation search. |
 | [agent_mcp_local.py](examples/agent_mcp_local.py) | An agent connected to a local MCP server (e.g. for expense logging). |
 | [openai_tool_calling.py](examples/openai_tool_calling.py) | Tool calling with the low-level OpenAI SDK, showing manual tool dispatch. |
+<<<<<<< HEAD
 | [workflow_rag_ingest.py](examples/workflow_rag_ingest.py) | A RAG ingestion pipeline using plain Python executors: fetch a document with markitdown, split into chunks, and embed with an OpenAI model. |
 | [workflow_agents.py](examples/workflow_agents.py) | A workflow with AI agents as executors: a Writer drafts content and a Reviewer provides feedback. |
 | [workflow_agents_sequential.py](examples/workflow_agents_sequential.py) | A sequential orchestration using `SequentialBuilder`: Writer and Reviewer run in order while sharing full conversation history. |
@@ -215,6 +219,8 @@ You can run the examples in this repository by executing the scripts in the `exa
 | [workflow_conditional_state_isolated.py](examples/workflow_conditional_state_isolated.py) | The stateful conditional workflow using a `create_workflow(...)` factory to build fresh agents/workflow per task for state isolation and thread safety. |
 | [workflow_switch_case.py](examples/workflow_switch_case.py) | A workflow with switch-case routing: a Classifier agent uses structured outputs to categorize a message and route to a specialized handler. |
 | [workflow_converge.py](examples/workflow_converge.py) | A branch-and-converge workflow: Reviewer routes to Publisher or Editor, then converges before final summary output. |
+=======
+>>>>>>> main
 | [agent_otel_aspire.py](examples/agent_otel_aspire.py) | An agent with OpenTelemetry tracing, metrics, and structured logs exported to the [Aspire Dashboard](https://aspire.dev/dashboard/standalone/). |
 | [agent_otel_appinsights.py](examples/agent_otel_appinsights.py) | An agent with OpenTelemetry tracing, metrics, and structured logs exported to [Azure Application Insights](https://learn.microsoft.com/azure/azure-monitor/app/app-insights-overview). Requires Azure provisioning via `azd provision`. |
 | [agent_evaluation_generate.py](examples/agent_evaluation_generate.py) | Generate synthetic evaluation data for the travel planner agent. |

chat_history.db

@@ -24,11 +24,11 @@
     client = OpenAIChatClient(
         base_url="https://models.github.ai/inference",
         api_key=os.environ["GITHUB_TOKEN"],
-        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-5-mini"),
+        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
     )
 else:
     client = OpenAIChatClient(
-        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-5-mini")
+        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")
     )
 
 agent = Agent(client=client, instructions="You're an informational agent. Answer questions cheerfully.")

examples/agent_basic.py

@@ -48,22 +48,22 @@
     client = OpenAIChatClient(
         base_url="https://models.github.ai/inference",
         api_key=os.environ["GITHUB_TOKEN"],
-        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-5-mini"),
+        model_id=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-5-mini",
+        model="openai/gpt-4.1-mini",
     )
 else:
     client = OpenAIChatClient(
-        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-5-mini")
+        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")
     )
     eval_model_config = OpenAIModelConfiguration(
         type="openai",
         api_key=os.environ["OPENAI_API_KEY"],
-        model=os.environ.get("OPENAI_MODEL", "gpt-5-mini"),
+        model=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini"),
     )
 
 

examples/agent_evaluation.py

@@ -46,13 +46,13 @@
         type="openai",
         base_url="https://models.github.ai/inference",
         api_key=os.environ["GITHUB_TOKEN"],
-        model="openai/gpt-5-mini",
+        model="openai/gpt-4.1-mini",
     )
 else:
     model_config = OpenAIModelConfiguration(
         type="openai",
         api_key=os.environ["OPENAI_API_KEY"],
-        model=os.environ.get("OPENAI_MODEL", "gpt-5-mini"),
+        model=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini"),
     )
 
 # Optional: Set AZURE_AI_PROJECT in .env to log results to Azure AI Foundry.

examples/agent_evaluation_batch.py

@@ -45,11 +45,11 @@
     client = OpenAIChatClient(
         base_url="https://models.github.ai/inference",
         api_key=os.environ["GITHUB_TOKEN"],
-        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-5-mini"),
+        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
     )
 else:
     client = OpenAIChatClient(
-        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-5-mini")
+        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")
     )
 
 

examples/agent_evaluation_generate.py

@@ -38,11 +38,11 @@
     client = OpenAIChatClient(
         base_url="https://models.github.ai/inference",
         api_key=os.environ["GITHUB_TOKEN"],
-        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-5-mini"),
+        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
     )
 else:
     client = OpenAIChatClient(
-        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-5-mini")
+        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")
     )
 
 
@@ -63,7 +63,7 @@ async def example_persistent_session() -> None:
     session_id = str(uuid.uuid4())
 
     # Phase 1: Start a conversation with a Redis-backed history provider
-    print("[dim]--- Phase 1: Starting conversation ---[/dim]")
+    print("[bold]--- Phase 1: Starting conversation ---[/bold]")
     redis_provider = RedisHistoryProvider(source_id="redis_chat", redis_url=REDIS_URL)
 
     agent = Agent(
@@ -84,7 +84,7 @@ async def example_persistent_session() -> None:
     print(f"[green]Agent:[/green] {response.text}")
 
     # Phase 2: Simulate an application restart — reconnect using the same session ID in Redis
-    print("\n[dim]--- Phase 2: Resuming after 'restart' ---[/dim]")
+    print("\n[bold]--- Phase 2: Resuming after 'restart' ---[/bold]")
     redis_provider2 = RedisHistoryProvider(source_id="redis_chat", redis_url=REDIS_URL)
 
     agent2 = Agent(
@@ -99,7 +99,6 @@ async def example_persistent_session() -> None:
     print("[blue]User:[/blue] Which of the cities I asked about had better weather?")
     response = await agent2.run("Which of the cities I asked about had better weather?", session=session2)
     print(f"[green]Agent:[/green] {response.text}")
-    print("[dim]Note: The agent remembered the conversation from Phase 1 via Redis persistence.[/dim]")
 
 
 async def main() -> None:
@@ -111,17 +110,15 @@ async def main() -> None:
     try:
         r.ping()
     except Exception as e:
-        print(f"[red]Cannot connect to Redis at {REDIS_URL}: {e}[/red]")
-        print(
-            "[red]Ensure Redis is running (e.g. via the dev container"
-            " or 'docker run -p 6379:6379 redis:7-alpine').[/red]"
+        logger.error(f"Cannot connect to Redis at {REDIS_URL}: {e}")
+        logger.error(
+            "Ensure Redis is running (e.g. via the dev container"
+            " or 'docker run -p 6379:6379 redis:7-alpine')."
         )
         return
     finally:
         r.close()
 
-    print("[dim]Redis connection verified.[/dim]")
-
     await example_persistent_session()
 
     if async_credential:

examples/agent_history_redis.py

@@ -38,11 +38,11 @@
     client = OpenAIChatClient(
         base_url="https://models.github.ai/inference",
         api_key=os.environ["GITHUB_TOKEN"],
-        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-5-mini"),
+        model_id=os.getenv("GITHUB_MODEL", "openai/gpt-4.1-mini"),
     )
 else:
     client = OpenAIChatClient(
-        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-5-mini")
+        api_key=os.environ["OPENAI_API_KEY"], model_id=os.environ.get("OPENAI_MODEL", "gpt-4.1-mini")
     )
 
 
@@ -111,7 +111,7 @@ async def main() -> None:
 
     # Phase 1: Start a conversation with a SQLite-backed history provider
     print("\n[bold]=== Persistent SQLite Session ===[/bold]")
-    print("[dim]--- Phase 1: Starting conversation ---[/dim]")
+    print("[bold]--- Phase 1: Starting conversation ---[/bold]")
 
     sqlite_provider = SQLiteHistoryProvider(db_path=db_path)
 
@@ -132,12 +132,8 @@ async def main() -> None:
     response = await agent.run("How about Paris?", session=session)
     print(f"[green]Agent:[/green] {response.text}")
 
-    messages = await sqlite_provider.get_messages(session_id)
-    print(f"[dim]Messages stored in SQLite: {len(messages)}[/dim]")
-    sqlite_provider.close()
-
     # Phase 2: Simulate an application restart — reconnect to the same session ID in SQLite
-    print("\n[dim]--- Phase 2: Resuming after 'restart' ---[/dim]")
+    print("\n[bold]--- Phase 2: Resuming after 'restart' ---[/bold]")
     sqlite_provider2 = SQLiteHistoryProvider(db_path=db_path)
 
     agent2 = Agent(
@@ -152,7 +148,6 @@ async def main() -> None:
     print("[blue]User:[/blue] Which of the cities I asked about had better weather?")
     response = await agent2.run("Which of the cities I asked about had better weather?", session=session2)
     print(f"[green]Agent:[/green] {response.text}")
-    print("[dim]Note: The agent remembered the conversation from Phase 1 via SQLite persistence.[/dim]")
 
     sqlite_provider2.close()