Feat: Guardrail support

examples/tutorials/10_agentic/10_temporal/050_agent_chat_guardrails/.dockerignore

@@ -0,0 +1,43 @@
+# Python
+__pycache__/
+*.py[cod]
+*$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Environments
+.env**
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+
+# Git
+.git
+.gitignore
+
+# Misc
+.DS_Store 

examples/tutorials/10_agentic/10_temporal/050_agent_chat_guardrails/Dockerfile

@@ -0,0 +1,46 @@
+# syntax=docker/dockerfile:1.3
+FROM python:3.12-slim
+COPY --from=ghcr.io/astral-sh/uv:0.6.4 /uv /uvx /bin/
+
+# Install system dependencies
+RUN apt-get update && apt-get install -y \
+    htop \
+    vim \
+    curl \
+    tar \
+    python3-dev \
+    postgresql-client \
+    build-essential \
+    libpq-dev \
+    gcc \
+    cmake \
+    netcat-openbsd \
+    && apt-get clean \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install tctl (Temporal CLI)
+RUN curl -L https://github.com/temporalio/tctl/releases/download/v1.18.1/tctl_1.18.1_linux_arm64.tar.gz -o /tmp/tctl.tar.gz && \
+    tar -xzf /tmp/tctl.tar.gz -C /usr/local/bin && \
+    chmod +x /usr/local/bin/tctl && \
+    rm /tmp/tctl.tar.gz
+
+RUN uv pip install --system --upgrade pip setuptools wheel
+
+ENV UV_HTTP_TIMEOUT=1000
+
+# Copy just the requirements file to optimize caching
+COPY 010_agent_chat/requirements.txt /app/requirements.txt
+
+WORKDIR /app/
+
+# Install the required Python packages
+RUN uv pip install --system -r requirements.txt
+
+# Copy the project code
+COPY 010_agent_chat/project /app/project
+
+# Run the ACP server using uvicorn
+CMD ["uvicorn", "project.acp:acp", "--host", "0.0.0.0", "--port", "8000"]
+
+# When we deploy the worker, we will replace the CMD with the following
+# CMD ["python", "-m", "run_worker"] 

examples/tutorials/10_agentic/10_temporal/050_agent_chat_guardrails/README.md

@@ -0,0 +1,42 @@
+# [Agentic] Agent Chat with Guardrails
+
+This tutorial demonstrates how to implement streaming multiturn tool-enabled chat with input and output guardrails using Temporal workflows in AgentEx agents.
+
+## Overview
+
+This example extends the basic agent chat functionality by adding guardrails that can filter both user inputs and AI outputs. This is useful for content moderation, compliance, or preventing certain topics from being discussed.
+
+## Guardrails
+
+### Input Guardrails
+- **Spaghetti Guardrail**: Blocks any mention of "spaghetti" in user messages
+- **Soup Guardrail**: Blocks any mention of "soup" in user messages
+
+### Output Guardrails  
+- **Pizza Guardrail**: Prevents the AI from mentioning "pizza" in responses
+- **Sushi Guardrail**: Prevents the AI from mentioning "sushi" in responses
+
+## Testing the Guardrails
+
+To see the guardrails in action:
+
+1. **Test Input Guardrails:**
+   - Try: "Tell me about spaghetti" 
+   - Try: "What's your favorite soup?"
+   - The guardrails will block these messages before they reach the AI
+
+2. **Test Output Guardrails:**
+   - Ask: "What are popular Italian foods?" (may trigger pizza guardrail)
+   - Ask: "What are popular Japanese foods?" (may trigger sushi guardrail)
+   - The AI may generate responses containing these words, but the guardrails will block them
+
+## Implementation Details
+
+The guardrails are implemented as functions that:
+- Check the input/output for specific content
+- Return a `GuardrailFunctionOutput` with:
+  - `tripwire_triggered`: Whether to block the content
+  - `output_info`: Metadata about the check
+  - `rejection_message`: Custom message shown when content is blocked
+
+See `workflow.py` for the complete implementation.