temporal-community · nadvolod · Oct 28, 2025 · Oct 28, 2025 · Oct 28, 2025 · Copilot
diff --git a/.github/copilot-instructions.md b/.github/copilot-instructions.md
@@ -34,7 +34,6 @@ async def call_agent_with_tools(query: str, trace_id: str) -> str:
 ### Essential Commands
 
 ```bash
-make setup          # Install deps - ALWAYS run first
 make env            # Validate OPENAI_API_KEY - run before exercises 1,3,4
 make temporal-up    # Start Temporal server - REQUIRED for exercises 2,3,4
 make exercise-{1-4} # Run specific exercise

diff --git a/CLAUDE.md b/CLAUDE.md
@@ -28,7 +28,8 @@ All tool calls have to be real, no mocking. Use the [weather API](https://docs.t
 ### Setup & Environment
 
 ```bash
-make setup          # Install dependencies and set up environment
+# Installation is done via temporal_installation.ipynb
+# Packages are installed per-exercise in each notebook
 make env            # Validate environment variables (OPENAI_API_KEY)
 ```
 
@@ -126,6 +127,7 @@ if __name__ == "__main__":
 Exercise 3 follows the production-ready structure from [temporal-weather-openai-agents](https://github.com/nadvolod/temporal-weather-openai-agents):
 
 #### **Component 1: activities.py**
+
 ```py
 import httpx
 from temporalio import activity
@@ -156,6 +158,7 @@ async def get_weather(state: str) -> dict:
 ```
 
 #### **Component 2: workflow.py**
+
 ```py
 from datetime import timedelta
 from temporalio import workflow
@@ -184,6 +187,7 @@ class WeatherAgentWorkflow:
 ```
 
 #### **Component 3: worker.py**
+
 ```py
 from temporalio.client import Client
 from temporalio.worker import Worker
@@ -215,6 +219,7 @@ async def main():
 ```
 
 #### **Component 4: starter.py**
+
 ```py
 from temporalio.client import Client
 from temporalio.contrib.openai_agents import OpenAIAgentsPlugin
@@ -236,6 +241,7 @@ async def main():
 ```
 
 **Key Benefits:**
+
 - ✅ Clean separation of concerns - each component has one responsibility
 - ✅ Agent tool calls are durable and automatically retried by Temporal
 - ✅ Full execution history visible in Temporal UI
@@ -244,6 +250,7 @@ async def main():
 - ✅ Proper sandbox configuration with `with_passthrough_modules()`
 
 **Important Notes:**
+
 - Activity returns `dict` not string - LLM interprets structured data
 - Single parameter: `user_query` (no trace_id)
 - `Runner()` is instantiated (not just `Runner`)
@@ -296,6 +303,7 @@ class RoutingWorkflow:
 ```
 
 **Key Differences from Other Exercises:**
+
 - ❌ **NOT a Jupyter notebook** - uses separate Python files like production apps
 - ✅ **3-file pattern:** workflow.py (logic) + worker.py (execution) + starter.py (invocation)
 - ✅ **Multiple specialized agents** with handoff coordination
@@ -338,6 +346,7 @@ All workflows in this repository follow a consistent naming pattern for workflow
 **Example:** `durable-agent-wed-oct-16-094832est`
 
 **Implementation:**
+
 ```python
 from datetime import datetime
 import pytz
@@ -349,17 +358,20 @@ workflow_id = f"durable-agent-{now.strftime('%a-%b-%d-%I%M%S').lower()}est"
 ```
 
 **Benefits:**
+
 - Human-readable workflow IDs
 - Chronologically sortable in Temporal UI
 - Timezone-aware (EST) for workshop coordination
 - Consistent pattern across all exercises
 
 **Examples by Exercise:**
+
 - Exercise 2: `hello-workflow-thu-oct-16-095919est`
 - Exercise 3: `durable-agent-wed-oct-16-094832est`
 - Exercise 4: `routing-fri-oct-17-103045est`
 
 **Required Dependencies:**
+
 - Add `pytz` to pip install commands: `%pip install --quiet temporalio openai-agents httpx rich nest-asyncio pytz`
 - Import: `from datetime import datetime` and `import pytz`
 

diff --git a/README.md b/README.md
@@ -77,6 +77,7 @@ This is a **90-minute workshop**: 30 minutes instruction + 4×15 minute exercise
 **Goal:** Create a simple AI agent with tool calling using real weather data
 
 **What you'll learn:**
+
 - 🤖 Build your first OpenAI agent with a weather tool
 - 🔧 Understand the agent → tool → response flow
 - 💡 See how LLMs decide when to use tools
@@ -91,6 +92,7 @@ This is a **90-minute workshop**: 30 minutes instruction + 4×15 minute exercise
 **Goal:** Understand Temporal workflows and activities
 
 **What you'll learn:**
+
 - 🏗️ Create your first Temporal workflow
 - ⚙️ Learn about activities as units of work
 - 🔍 Observe execution in the Temporal UI
@@ -105,6 +107,7 @@ This is a **90-minute workshop**: 30 minutes instruction + 4×15 minute exercise
 **Goal:** Combine agents + Temporal for production durability ⭐
 
 **What you'll learn:**
+
 - 🔄 Wrap LLM calls in Temporal activities
 - ✨ Get automatic retries on failures (magic! ✨)
 - 💾 Persist agent state across crashes
@@ -122,6 +125,7 @@ This is a **90-minute workshop**: 30 minutes instruction + 4×15 minute exercise
 **Goal:** Build a routing workflow with language-specific agents using production-ready file structure
 
 **What you'll learn:**
+
 - 🎯 Implement agent routing/triage patterns with OpenAI Agents SDK
 - 🌍 Create specialized language agents (French, Spanish, English)
 - 🔀 Use handoff patterns for agent-to-agent transitions
@@ -134,7 +138,6 @@ This is a **90-minute workshop**: 30 minutes instruction + 4×15 minute exercise
 
 ```bash
 # 🔧 Setup and validation
-make setup          # Install all dependencies
 make env            # Check environment variables (OPENAI_API_KEY)
 
 # 🧹 Code quality
@@ -228,6 +231,7 @@ pgrep -f temporal
 ```
 
 **Fix:** Use the `temporal_installation.ipynb` notebook to install and start Temporal:
+
 1. Open `temporal_installation.ipynb` in VS Code
 2. Run each cell to install Temporal CLI and start the dev server
 3. Verify at http://localhost:8233
@@ -241,9 +245,8 @@ The Temporal dev server must be running for exercises 2, 3, and 4! ⚡
 **Problem:** Import errors when running exercises ❌
 
 ```bash
-# Reinstall dependencies
-make setup
-# Or: pip install -e ".[dev]"
+# Packages are installed per-exercise/solution in each notebook
+# Run the first cell of the notebook to install required dependencies
 ```
 
 ---
@@ -304,20 +307,16 @@ pip install -e ".[dev]"
 1. **Students skip checking `.env`** 🔑
    - Do environment check before starting (`make env`)
    - Emphasize that exercises 1, 3, 4 need API key
-
 2. **Temporal not running** ⚡
    - Remind students to use `temporal_installation.ipynb` notebook to install and start Temporal
    - Walk through opening the notebook and running each cell
    - Show them how to verify at http://localhost:8233
-
 3. **Confusion between exercise and solution** 📓
    - Clearly explain: work in `exercises/`, compare with `solutions/`
    - Solution notebooks are complete standalone implementations
-
 4. **Activity timeouts** ⏳
    - Explain `start_to_close_timeout` defaults
    - Show how to adjust for longer-running operations
-
 5. **Notebook vs Python files** 📝
    - Exercises 1-3 are Jupyter notebooks (`.ipynb`)
    - Exercise 4 uses separate Python files (workflow.py, worker.py, starter.py)
@@ -328,16 +327,13 @@ pip install -e ".[dev]"
 - **Exercise 1:** Emphasize tool calling as the foundation of agentic behavior 🤖
   - Show how the agent decides to use tools
   - Highlight the real API integration (National Weather Service)
-
 - **Exercise 2:** Show the Temporal UI extensively - it's powerful for debugging! 🔍
   - Walk through execution history
   - Demonstrate the retry mechanism
-
 - **Exercise 3:** THIS IS THE KEY 🌟
   - Show how activities make LLM calls durable
   - The agent code doesn't change - Temporal wraps it!
   - Emphasize: production-ready with zero agent modifications
-
 - **Exercise 4:** Advanced routing workflow with production file structure 🔀
   - Language-based routing pattern (French/Spanish/English agents)
   - Handoff pattern enables agent-to-agent transitions

diff --git a/example-notebook/02-Adding-Durability-Solution.ipynb b/example-notebook/02-Adding-Durability-Solution.ipynb
@@ -1143,13 +1143,18 @@
    "provenance": []
   },
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3.11.14",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
    "name": "python",
-   "version": "3.11.13"
+   "version": "3.11.14"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "default"
+   }
   }
  },
  "nbformat": 4,

diff --git a/example-notebook/03-Human-in-the-Loop-Solution.ipynb b/example-notebook/03-Human-in-the-Loop-Solution.ipynb
@@ -1029,7 +1029,7 @@
    "version": ""
   },
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3.11.14",
    "language": "python",
    "name": "python3"
   },
@@ -1043,7 +1043,12 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.11.13"
+   "version": "3.11.14"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "default"
+   }
   }
  },
  "nbformat": 4,

diff --git a/exercises/01_agent_hello_world/exercise.ipynb b/exercises/01_agent_hello_world/exercise.ipynb
@@ -26,7 +26,7 @@
     "   OPENAI_API_KEY=sk-your-key-here\n",
     "   ```\n",
     "\n",
-    "2. **Dependencies:** Already installed if you ran `make setup`\n",
+    "2. **Dependencies:** Installed in the first cell of this notebook:\n",
     "   - `openai-agents` - OpenAI Agents SDK\n",
     "   - `httpx` - Async HTTP client\n",
     "   - `python-dotenv` - Environment variable management\n",
@@ -319,18 +319,37 @@
   {
    "cell_type": "markdown",
    "metadata": {},
-   "source": "## Next Steps\n\nOnce you've completed this exercise, you'll understand:\n\n- ✅ How to create agents with the OpenAI Agents SDK\n- ✅ How to define custom tools that call real APIs\n- ✅ How the agent decides when to use tools\n- ✅ How to run agents with async/await\n\n**Ready for more?** Proceed to:\n\n- **[Exercise 2: Temporal Hello World](../02_temporal_hello_world/exercise.ipynb)** - Learn Temporal workflows and activities\n- **[Exercise 3: Durable Agent](../03_durable_agent/exercise.ipynb)** - Combine agents + Temporal for production durability!"
+   "source": [
+    "## Next Steps\n",
+    "\n",
+    "Once you've completed this exercise, you'll understand:\n",
+    "\n",
+    "- ✅ How to create agents with the OpenAI Agents SDK\n",
+    "- ✅ How to define custom tools that call real APIs\n",
+    "- ✅ How the agent decides when to use tools\n",
+    "- ✅ How to run agents with async/await\n",
+    "\n",
+    "**Ready for more?** Proceed to:\n",
+    "\n",
+    "- **[Exercise 2: Temporal Hello World](../02_temporal_hello_world/exercise.ipynb)** - Learn Temporal workflows and activities\n",
+    "- **[Exercise 3: Durable Agent](../03_durable_agent/exercise.ipynb)** - Combine agents + Temporal for production durability!"
+   ]
   }
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3.11.14",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
    "name": "python",
-   "version": "3.11.0"
+   "version": "3.11.14"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "default"
+   }
   }
  },
  "nbformat": 4,

diff --git a/exercises/02_temporal_hello_world/exercise.ipynb b/exercises/02_temporal_hello_world/exercise.ipynb
@@ -197,13 +197,18 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3.11.14",
    "language": "python",
    "name": "python3"
   },
   "language_info": {
    "name": "python",
-   "version": "3.11.13"
+   "version": "3.11.14"
+  },
+  "vscode": {
+   "interpreter": {
+    "hash": "default"
+   }
   }
  },
  "nbformat": 4,