Cfg/groq

Makefile

@@ -39,6 +39,9 @@ setup-temporal-mac:
 	brew install temporal
 	temporal server start-dev
 
+make start-temporal-server:
+	temporal server start-dev
+
 # Run all development services
 run-dev:
 	@echo "Starting all development services..."
@@ -60,4 +63,4 @@ help:
 	@echo "  make run-legacy-worker  - Start the legacy worker"
 	@echo "  make run-enterprise     - Build and run the enterprise .NET worker"
 	@echo "  make setup-temporal-mac - Install and start Temporal server on Mac"
-	@echo "  make run-dev            - Start all development services (worker, API, frontend) in parallel"
+	@echo "  make run-dev            - Start all development services (worker, API, frontend) in parallel"

activities/tool_activities.py

@@ -40,10 +40,13 @@ def __init__(self, mcp_client_manager: MCPClientManager = None):
         self.llm_model = os.environ.get("LLM_MODEL", "openai/gpt-4")
         self.llm_key = os.environ.get("LLM_KEY")
         self.llm_base_url = os.environ.get("LLM_BASE_URL")
+        self.llm_provider = os.environ.get("LLM_PROVIDER")
         self.mcp_client_manager = mcp_client_manager
         print(f"Initializing ToolActivities with LLM model: {self.llm_model}")
         if self.llm_base_url:
             print(f"Using custom base URL: {self.llm_base_url}")
+        if self.llm_provider:
+            print(f"Using LLM provider: {self.llm_provider}")
         if self.mcp_client_manager:
             print("MCP client manager enabled for connection pooling")
 
@@ -134,6 +137,8 @@ async def agent_toolPlanner(self, input: ToolPromptInput) -> dict:
             if self.llm_base_url:
                 completion_kwargs["base_url"] = self.llm_base_url
 
+            if self.llm_provider:
+                completion_kwargs["provider"] = self.llm_provider
             response = completion(**completion_kwargs)
 
             response_content = response.choices[0].message.content

notes/README.md

@@ -0,0 +1,57 @@
+# Learning Journey: Temporal AI Agent Experiments
+
+This directory contains my personal notes, experiments, and learnings while exploring the Temporal AI Agent system. The goal is to understand how to effectively use agentic systems within Temporal's durable workflow model.
+
+## Directory Structure
+
+- [`experiments/`](./experiments/): Detailed documentation of specific experiments and tests
+  - Each experiment is numbered for easy reference
+  - Contains setup, observations, and results
+
+- [`learnings/`](./learnings/): Key concepts and patterns discovered
+  - Temporal concepts
+  - Agent patterns
+  - Challenges and solutions
+
+- [`resources/`](./resources/): Useful references and links
+  - External documentation
+  - Relevant articles
+  - Community discussions
+
+## Quick Start
+
+The experiments are numbered sequentially (001, 002, etc.) and can be found in the `experiments/` directory. Each experiment includes:
+- Objective
+- Setup instructions
+- Code changes/additions
+- Results and observations
+- Learnings and takeaways
+
+## Key Topics
+
+1. Temporal Workflows with AI Agents
+2. Agent-based Decision Making
+3. Durable Execution Patterns
+4. Error Handling and Recovery
+5. Testing and Debugging Strategies
+
+## Progress Tracking
+
+- [ ] Basic workflow setup and execution
+- [ ] Agent integration and configuration
+- [ ] Complex decision-making scenarios
+- [ ] Error handling and recovery patterns
+- [ ] Performance optimization
+- [ ] Production-ready considerations
+
+## Notes
+
+- This is a learning repository forked from the original temporal-ai-agent demo
+- These notes are personal and reflect my learning journey
+- Feel free to adapt and modify the structure as needed
+
+## References
+
+- [Original Repository](https://github.com/temporalio/temporal-ai-agent)
+- [Temporal Documentation](https://docs.temporal.io/)
+- [AI Agent Documentation](./docs/README.md)

notes/experiments/000-run-tests.md

@@ -0,0 +1,24 @@
+# Experiment 000 - Run Tests
+## Objective
+- Run tests for the Temporal AI Agent project
+
+## Steps
+1. Install poetry if not already installed
+`brew install poetry`
+2. Install development dependencies
+`poetry install --with dev`
+2. Run the tests `poetry run pytest`
+
+## Issues and fixes
+
+### No module named pytest_asyncio
+**Error**
+```
+ImportError while loading conftest '/Users/joeszodfridt/src/temporal/temporal-ai-agent/tests/conftest.py'.
+tests/conftest.py:7: in <module>
+    import pytest_asyncio
+E   ModuleNotFoundError: No module named 'pytest_asyncio'
+```
+**Remediation**
+- Install development dependencies
+`poetry install --with dev`

notes/experiments/001-basic-workflow.md

@@ -0,0 +1,87 @@
+# Experiment 001: Setup and run locally out of the box demo
+
+**Date**:
+
+## Objective
+To understand what's involved in setting up and running the Temporal AI Agent locally out of the box demo.
+
+## Setup
+
+### Environment
+- Local development environment
+  - I'm using asdf (already installed)to manage python versions
+  - Temporal is already installed using brew, `brew install temporal`
+
+- Temporal server running
+  - Start server using make commands: `make start-temporal-server `
+
+### Configuration
+Copy `.env.example` to `.env` and configure
+- Set `LLM_KEY=YOUR_API_KEY`
+- Set `LLM_MODEL=YOUR_MODEL_NAME`, e.g `anthropic/claude-3-5-sonnet-20240620`
+- Set `STRIPE_API_KEY=` to generate mock data, use your Stripe API key if you have one
+
+
+## Implementation Steps
+
+Start local Temporal server
+`make start-temporal-server`
+
+Start api, workers, workflow and UI
+`make run-dev`
+
+Temporal workflow monitor
+- URL is displayed in the output when server is started
+
+Application UI
+
+
+## Observations
+
+### What Worked Well
+- Demo runs when using Antrhopic and my personal key. NF key is always out of capacity
+- Demo fails when running with Ollama locally. Will need some code changes to support Ollama
+
+### Challenges Encountered
+- Challenge 1
+  - Solution/Workaround:
+- Challenge 2
+  - Solution/Workaround:
+
+## Key Learnings
+
+1. Learning 1
+   - Details...
+2. Learning 2
+   - Details...
+
+## Questions to Explore
+- [ ] Question 1
+- [ ] Question 2
+
+## Next Steps
+- [ ] What to try next
+- [ ] Areas to improve
+
+## Resources Used
+- Link 1
+- Link 2
+
+## Code Snippets and Examples
+
+### Example 1: Description
+```python
+# Add example code here
+```
+
+### Example 2: Description
+```python
+# Add example code here
+```
+
+## Notes for Future Reference
+- Important note 1
+- Important note 2
+
+---
+Last Updated:

notes/experiments/002-basic-workflow-groq.md

@@ -0,0 +1,73 @@
+# Experiment 002: Run basic demo using Groq models
+
+**Date**: 6/26/25
+
+## Objective
+Get the out of the box demo using Groq for LLM models
+
+
+## Setup
+
+### Environment
+- Same as in basic workflow no changes
+
+### Configuration
+- Uncomment the Groq LLM configuration in .env
+
+## Implementation Steps
+- Start temporal server: `make start-temporal-server`
+- Start the apis, workers, etc.: `make run-dev`
+- Run the demo
+
+## Observations
+- Groq is fast!!!
+- Quickly burn through the free tokens as Groq is rate limiting my free plan requests
+- The demo handles the rate limit without crashing
+- Workflow will timeout gracefully after 30 minutes, and app will stay alive
+- Demo doesn't have any messaging about service provider hitting rate limiting
+
+### What Worked Well
+
+### Challenges Encountered
+- Challenge 1
+  - Solution/Workaround:
+- Challenge 2
+  - Solution/Workaround:
+
+## Key Learnings
+
+1. Learning 1
+   - Details...
+2. Learning 2
+   - Details...
+
+## Questions to Explore
+- [ ] Question 1
+- [ ] Question 2
+
+## Next Steps
+- [ ] What to try next
+- [ ] Areas to improve
+
+## Resources Used
+- Link 1
+- Link 2
+
+## Code Snippets and Examples
+
+### Example 1: Description
+```python
+# Add example code here
+```
+
+### Example 2: Description
+```python
+# Add example code here
+```
+
+## Notes for Future Reference
+- Important note 1
+- Important note 2
+
+---
+Last Updated:

notes/experiments/experiment-template.md

@@ -0,0 +1,65 @@
+# Experiment 000: Title
+
+**Date**:
+
+## Objective
+
+
+## Setup
+
+### Environment
+
+
+### Configuration
+
+
+## Implementation Steps
+
+
+## Observations
+
+### What Worked Well
+
+### Challenges Encountered
+- Challenge 1
+  - Solution/Workaround:
+- Challenge 2
+  - Solution/Workaround:
+
+## Key Learnings
+
+1. Learning 1
+   - Details...
+2. Learning 2
+   - Details...
+
+## Questions to Explore
+- [ ] Question 1
+- [ ] Question 2
+
+## Next Steps
+- [ ] What to try next
+- [ ] Areas to improve
+
+## Resources Used
+- Link 1
+- Link 2
+
+## Code Snippets and Examples
+
+### Example 1: Description
+```python
+# Add example code here
+```
+
+### Example 2: Description
+```python
+# Add example code here
+```
+
+## Notes for Future Reference
+- Important note 1
+- Important note 2
+
+---
+Last Updated: