11 Commits
0.4.1 ... main

Author SHA1 Message Date
Steve Androulakis
3180084e7c find_events tool data for 2026 and 2027 2025-11-30 11:11:40 -08:00
Steve Androulakis
1bd69db1d0 stripe usd invoices 2025-09-29 14:30:42 -07:00
Steve Androulakis
98a1b75dff Fix mcp native tool goals (#58)
* frontend ui error configurable timeout

* fixed bug where goals with MCP stopped native tools from executing
2025-09-28 12:20:36 -07:00
Steve Androulakis
e248a6778d frontend ui error configurable timeout (#57) 2025-09-28 12:17:11 -07:00
Dan Davison
d0dca40b93 Add poe (#55) 2025-09-04 15:44:12 -07:00
Dan Davison
457fa1fce8 Add GitHub Actions CI (#54) 2025-09-04 09:54:31 -07:00
Dan Davison
3c71a062fd Improve implementation of is_mcp_tool (#53) 2025-09-04 09:54:12 -07:00
Ben Ellis
380009f292 Update README.md (#51)
Fix typo in the word "reliability"
2025-08-18 10:38:45 -07:00
Dan Davison
68ac9c40eb Migrate to uv (#52)
* uvx migrate-to-uv

* uv migration

* Fix hatch build

* Fixup

* uv run

* Add tab completion to devcontainer uv

Co-authored-by: Simon Emms <simon@simonemms.com>

* Revert "Add tab completion to devcontainer uv"

This reverts commit a3b7bdd84b.

---------

Co-authored-by: Simon Emms <simon@simonemms.com>
2025-07-30 11:37:42 -06:00
Simon Emms
4ed4efbe83 chore: add support for devcontainers (#50) 2025-07-22 09:47:07 -07:00
Steve Androulakis
40714071d6 Update todo.md
[ ] get this on the Model Context Protocol site's list of MCP clients https://modelcontextprotocol.io/clients
2025-06-20 13:04:54 -07:00
26 changed files with 3974 additions and 3415 deletions

View File

@@ -0,0 +1,20 @@
{
"image": "mcr.microsoft.com/devcontainers/base:ubuntu",
"name": "Temporal AI Agentic Demo",
"features": {
"ghcr.io/devcontainers/features/node:1": {},
"ghcr.io/va-h/devcontainers-features/uv:1": {},
"ghcr.io/devcontainers/features/python:1": {},
"ghcr.io/devcontainers-extra/features/temporal-cli:1": {},
"ghcr.io/mrsimonemms/devcontainers/tcld:1": {}
},
"forwardPorts": [
5173,
7233,
8000,
8233
],
"containerEnv": {
"VITE_HOST": "0.0.0.0"
}
}

37
.github/workflows/ci.yml vendored Normal file
View File

@@ -0,0 +1,37 @@
name: CI
on:
pull_request:
push:
branches: [ main ]
jobs:
lint-test:
runs-on: ${{ matrix.os }}
strategy:
matrix:
python-version: ['3.13']
os: [ubuntu-latest]
steps:
- name: Checkout repository
uses: actions/checkout@v4
- name: Install uv
uses: astral-sh/setup-uv@v6
with:
python-version: ${{ matrix.python-version }}
- name: Install dependencies
run: |
uv sync
- name: Format, lint, type check
run: |
uv run poe format
uv run poe lint
uv run poe lint-types
- name: Run tests
run: |
uv run pytest

View File

@@ -34,11 +34,10 @@ Default URLs:
1. **Prerequisites:**
```bash
# Install Poetry for Python dependency management
curl -sSL https://install.python-poetry.org | python3 -
# Start Temporal server (Mac)
# Install uv and Temporal server (MacOS)
brew install uv
brew install temporal
temporal server start-dev
```
@@ -50,9 +49,9 @@ Default URLs:
make run-api # Starts the API server
# Or manually:
poetry install
poetry run python scripts/run_worker.py # In one terminal
poetry run uvicorn api.main:app --reload # In another terminal
uv sync
uv run scripts/run_worker.py # In one terminal
uv run uvicorn api.main:app --reload # In another terminal
```
3. **Frontend (React):**
@@ -102,20 +101,20 @@ The project includes comprehensive tests using Temporal's testing framework:
```bash
# Install test dependencies
poetry install --with dev
uv sync
# Run all tests
poetry run pytest
uv run pytest
# Run with time-skipping for faster execution
poetry run pytest --workflow-environment=time-skipping
uv run pytest --workflow-environment=time-skipping
# Run specific test categories
poetry run pytest tests/test_tool_activities.py -v # Activity tests
poetry run pytest tests/test_agent_goal_workflow.py -v # Workflow tests
uv run pytest tests/test_tool_activities.py -v # Activity tests
uv run pytest tests/test_agent_goal_workflow.py -v # Workflow tests
# Run with coverage
poetry run pytest --cov=workflows --cov=activities
uv run pytest --cov=workflows --cov=activities
```
**Test Coverage:**
@@ -130,15 +129,15 @@ poetry run pytest --cov=workflows --cov=activities
## Linting and Code Quality
```bash
# Using Poetry tasks
poetry run poe format # Format code with black and isort
poetry run poe lint # Check code style and types
poetry run poe test # Run test suite
# Using poe tasks
uv run poe format # Format code with black and isort
uv run poe lint # Check code style and types
uv run poe test # Run test suite
# Manual commands
poetry run black .
poetry run isort .
poetry run mypy --check-untyped-defs --namespace-packages .
# Manual commands
uv run black .
uv run isort .
uv run mypy --check-untyped-defs --namespace-packages .
```
## Agent Customization
@@ -192,7 +191,7 @@ For detailed architecture information, see [architecture.md](docs/architecture.m
- Use clear commit messages describing the change purpose
- Reference specific files and line numbers when relevant (e.g., `workflows/agent_goal_workflow.py:125`)
- Open PRs describing **what changed** and **why**
- Ensure tests pass before submitting: `poetry run pytest --workflow-environment=time-skipping`
- Ensure tests pass before submitting: `uv run pytest --workflow-environment=time-skipping`
## Additional Resources
- **Setup Guide**: [setup.md](docs/setup.md) - Detailed configuration instructions

View File

@@ -4,17 +4,19 @@ WORKDIR /app
# Install system dependencies
RUN apt-get update && \
apt-get install -y --no-install-recommends gcc build-essential && \
apt-get install -y --no-install-recommends gcc build-essential curl && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
# Copy requirements first for better caching
RUN pip install --no-cache-dir poetry
# Install uv
RUN curl -LsSf https://astral.sh/uv/install.sh | sh
ENV PATH="$PATH:/root/.local/bin"
# Install Python dependencies without creating a virtualenv
COPY pyproject.toml poetry.lock ./
RUN poetry config virtualenvs.create false \
&& poetry install --without dev --no-interaction --no-ansi --no-root
# Copy dependency files and README (needed for package build)
COPY pyproject.toml uv.lock README.md ./
# Install dependencies and create virtual environment
RUN uv sync --frozen
# Copy application code
COPY . .
@@ -27,4 +29,4 @@ ENV PYTHONPATH=/app
EXPOSE 8000
# Default to running only the API server; worker and train-api are separate Compose services
CMD ["uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "8000"]
CMD ["uv", "run", "uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "8000"]

View File

@@ -1,35 +1,24 @@
.PHONY: setup install run-worker run-api run-frontend run-train-api run-legacy-worker run-enterprise setup-venv check-python run-dev
# Setup commands
setup: check-python setup-venv install
check-python:
@which python3 >/dev/null 2>&1 || (echo "Python 3 is required. Please install it first." && exit 1)
@which poetry >/dev/null 2>&1 || (echo "Poetry is required. Please install it first." && exit 1)
setup-venv:
python3 -m venv venv
@echo "Virtual environment created. Don't forget to activate it with 'source venv/bin/activate'"
install:
poetry install
setup:
uv sync
cd frontend && npm install
# Run commands
run-worker:
poetry run python scripts/run_worker.py
uv run scripts/run_worker.py
run-api:
poetry run uvicorn api.main:app --reload
uv run uvicorn api.main:app --reload
run-frontend:
cd frontend && npx vite
run-train-api:
poetry run python thirdparty/train_api.py
uv run thirdparty/train_api.py
run-legacy-worker:
poetry run python scripts/run_legacy_worker.py
uv run scripts/run_legacy_worker.py
run-enterprise:
cd enterprise && dotnet build && dotnet run
@@ -50,9 +39,7 @@ run-dev:
# Help command
help:
@echo "Available commands:"
@echo " make setup - Create virtual environment and install dependencies"
@echo " make setup-venv - Create virtual environment only"
@echo " make install - Install all dependencies"
@echo " make setup - Install all dependencies"
@echo " make run-worker - Start the Temporal worker"
@echo " make run-api - Start the API server"
@echo " make run-frontend - Start the frontend development server"

View File

@@ -22,7 +22,7 @@ It's really helpful to [watch the demo (5 minute YouTube video)](https://www.you
See multi-agent execution in action [here](https://www.youtube.com/watch?v=8Dc_0dC14yY).
## Why Temporal?
There are a lot of AI and Agentic AI tools out there, and more on the way. But why Temporal? Temporal gives this system reliablity, state management, a code-first approach that we really like, built-in observability and easy error handling.
There are a lot of AI and Agentic AI tools out there, and more on the way. But why Temporal? Temporal gives this system reliability, state management, a code-first approach that we really like, built-in observability and easy error handling.
For more, check out [architecture-decisions](docs/architecture-decisions.md).
## What is "Agentic AI"?
@@ -65,13 +65,13 @@ The project includes comprehensive tests for workflows and activities using Temp
```bash
# Install dependencies including test dependencies
poetry install --with dev
uv sync
# Run all tests
poetry run pytest
uv run pytest
# Run with time-skipping for faster execution
poetry run pytest --workflow-environment=time-skipping
uv run pytest --workflow-environment=time-skipping
```
**Test Coverage:**

View File

@@ -2,17 +2,17 @@ services:
api:
volumes:
- ./:/app:cached
command: uvicorn api.main:app --host 0.0.0.0 --port 8000 --reload
command: uv run uvicorn api.main:app --host 0.0.0.0 --port 8000 --reload
worker:
volumes:
- ./:/app:cached
command: python scripts/run_worker.py
command: uv run scripts/run_worker.py
train-api:
volumes:
- ./:/app:cached
command: python thirdparty/train_api.py
command: uv run thirdparty/train_api.py
frontend:
volumes:

View File

@@ -79,7 +79,7 @@ services:
- .env
environment:
- TEMPORAL_ADDRESS=temporal:7233
command: python scripts/run_worker.py
command: uv run scripts/run_worker.py
networks:
- temporal-network
@@ -94,7 +94,7 @@ services:
- .env
environment:
- TEMPORAL_ADDRESS=temporal:7233
command: python thirdparty/train_api.py
command: uv run thirdparty/train_api.py
networks:
- temporal-network

View File

@@ -8,40 +8,40 @@ This document provides guidelines for contributing to `temporal-ai-agent`. All s
We use `black` for code formatting and `isort` for import sorting to maintain a consistent codebase.
- **Format code:**
```bash
poetry run poe format
uv run poe format
```
Or manually:
```bash
poetry run black .
poetry run isort .
Or manually
```
uv run black .
uv run isort .
```
Please format your code before committing.
### Linting & Type Checking
We use `mypy` for static type checking and other linters configured via `poe the poet`.
We use `mypy` for static type checking and other linters configured via `poe`.
- **Run linters and type checks:**
```bash
poetry run poe lint
uv run poe lint
```
Or manually for type checking:
```bash
poetry run mypy --check-untyped-defs --namespace-packages .
uv run mypy --check-untyped-defs --namespace-packages .
```
Ensure all linting and type checks pass before submitting a pull request.
## Testing
Comprehensive testing is crucial for this project. We use `pytest` and Temporal's testing framework.
- **Install test dependencies** (if not already done with `poetry install --with dev`):
- **Install test dependencies:**
```bash
poetry install --with dev
uv sync
```
- **Run all tests:**
```bash
poetry run pytest
uv run pytest
```
- **Run tests with time-skipping (recommended for faster execution, especially in CI):**
```bash
poetry run pytest --workflow-environment=time-skipping
uv run pytest --workflow-environment=time-skipping
```
For detailed information on test categories, running specific tests, test environments, coverage, and troubleshooting, please refer to:
@@ -73,7 +73,7 @@ When you're ready to submit your changes:
1. Push your branch to the remote repository.
2. Open a Pull Request (PR) against the `main` branch.
3. **Describe your changes:** Clearly explain what you changed and why. Reference any related issues.
4. **Ensure tests pass:** All CI checks, including tests and linters, must pass. The command `poetry run pytest --workflow-environment=time-skipping` is a good one to run locally.
4. **Ensure tests pass:** All CI checks, including tests and linters, must pass. The command `uv run pytest --workflow-environment=time-skipping` is a good one to run locally.
5. **Request review:** Request a review from one or more maintainers.
## Reporting Bugs

View File

@@ -22,8 +22,6 @@ We've provided a Makefile to simplify the setup and running of the application.
```bash
# Initial setup
make setup # Creates virtual environment and installs dependencies
make setup-venv # Creates virtual environment only
make install # Installs all dependencies
# Running the application
make run-worker # Starts the Temporal worker
@@ -159,24 +157,22 @@ Default urls:
**Python Backend**
Requires [Poetry](https://python-poetry.org/) to manage dependencies.
Requires [`uv`](https://docs.astral.sh/uv/) to manage dependencies.
1. `python -m venv venv`
1. Install uv: `curl -LsSf https://astral.sh/uv/install.sh | sh`
2. `source venv/bin/activate`
3. `poetry install`
2. `uv sync`
Run the following commands in separate terminal windows:
1. Start the Temporal worker:
```bash
poetry run python scripts/run_worker.py
uv run scripts/run_worker.py
```
2. Start the API server:
```bash
poetry run uvicorn api.main:app --reload
uv run uvicorn api.main:app --reload
```
Access the API at `/docs` to see the available endpoints.
@@ -261,7 +257,7 @@ NOTE: This goal was developed for an on-stage demo and has failure (and its reso
Required to search and book trains!
```bash
poetry run python thirdparty/train_api.py
uv run thirdparty/train_api.py
# example url
# http://localhost:8080/api/search?from=london&to=liverpool&outbound_time=2025-04-18T09:00:00&inbound_time=2025-04-20T09:00:00
@@ -273,7 +269,7 @@ poetry run python thirdparty/train_api.py
These are Python activities that fail (raise NotImplemented) to show how Temporal handles a failure. You can run these activities with.
```bash
poetry run python scripts/run_legacy_worker.py
uv run scripts/run_legacy_worker.py
```
The activity will fail and be retried infinitely. To rescue the activity (and its corresponding workflows), kill the worker and run the .NET one in the section below.
@@ -328,8 +324,8 @@ For more details, check out [adding goals and tools guide](./adding-goals-and-to
[ ] Select an LLM and add your API key to `.env` <br />
[ ] (Optional) set your starting goal and goal category in `.env` <br />
[ ] (Optional) configure your Temporal Cloud settings in `.env` <br />
[ ] `poetry run python scripts/run_worker.py` <br />
[ ] `poetry run uvicorn api.main:app --reload` <br />
[ ] `uv run scripts/run_worker.py` <br />
[ ] `uv run uvicorn api.main:app --reload` <br />
[ ] `cd frontend`, `npm install`, `npx vite` <br />
[ ] Access the UI at `http://localhost:5173` <br />

View File

@@ -6,17 +6,17 @@ This guide provides instructions for running the comprehensive test suite for th
1. **Install dependencies**:
```bash
poetry install --with dev
uv sync
```
2. **Run all tests**:
```bash
poetry run pytest
uv run pytest
```
3. **Run with time-skipping for faster execution**:
```bash
poetry run pytest --workflow-environment=time-skipping
uv run pytest --workflow-environment=time-skipping
```
## Test Categories
@@ -39,33 +39,33 @@ This guide provides instructions for running the comprehensive test suite for th
```bash
# Run only activity tests
poetry run pytest tests/test_tool_activities.py -v
uv run pytest tests/test_tool_activities.py -v
# Run only workflow tests
poetry run pytest tests/test_agent_goal_workflow.py -v
uv run pytest tests/test_agent_goal_workflow.py -v
# Run a specific test
poetry run pytest tests/test_tool_activities.py::TestToolActivities::test_sanitize_json_response -v
uv run pytest tests/test_tool_activities.py::TestToolActivities::test_sanitize_json_response -v
# Run tests matching a pattern
poetry run pytest -k "validation" -v
uv run pytest -k "validation" -v
```
## Test Environment Options
### Local Environment (Default)
```bash
poetry run pytest --workflow-environment=local
uv run pytest --workflow-environment=local
```
### Time-Skipping Environment (Recommended for CI)
```bash
poetry run pytest --workflow-environment=time-skipping
uv run pytest --workflow-environment=time-skipping
```
### External Temporal Server
```bash
poetry run pytest --workflow-environment=localhost:7233
uv run pytest --workflow-environment=localhost:7233
```
## Environment Variables
@@ -122,7 +122,7 @@ tests/test_tool_activities.py::TestToolActivities::test_get_wf_env_vars_default_
### Common Issues
1. **Module not found errors**: Run `poetry install --with dev`
1. **Module not found errors**: Run `uv sync`
2. **Async warnings**: These are expected with pytest-asyncio and can be ignored
3. **Test timeouts**: Use `--workflow-environment=time-skipping` for faster execution
4. **Import errors**: Check that you're running tests from the project root directory
@@ -131,19 +131,19 @@ tests/test_tool_activities.py::TestToolActivities::test_get_wf_env_vars_default_
Enable verbose logging:
```bash
poetry run pytest --log-cli-level=DEBUG -s
uv run pytest --log-cli-level=DEBUG -s
```
Run with coverage:
```bash
poetry run pytest --cov=workflows --cov=activities
uv run pytest --cov=workflows --cov=activities
```
## Continuous Integration
For CI environments, use:
```bash
poetry run pytest --workflow-environment=time-skipping --tb=short
uv run pytest --workflow-environment=time-skipping --tb=short
```
## Additional Resources

View File

@@ -23,6 +23,8 @@
[ ] enable user to list agents at any time - like end conversation - probably with a next step<br />
[ ] get this on the Model Context Protocol site's list of MCP clients https://modelcontextprotocol.io/clients
## Ideas for more goals and tools
[ ] Add fintech goals <br />

View File

@@ -6,6 +6,10 @@ import { apiService } from "../services/api";
const POLL_INTERVAL = 600; // 0.6 seconds
const INITIAL_ERROR_STATE = { visible: false, message: '' };
const DEBOUNCE_DELAY = 300; // 300ms debounce for user input
const CONVERSATION_FETCH_ERROR_DELAY_MS = 10000; // wait 10s before showing fetch errors
const CONVERSATION_FETCH_ERROR_THRESHOLD = Math.ceil(
CONVERSATION_FETCH_ERROR_DELAY_MS / POLL_INTERVAL
);
function useDebounce(value, delay) {
const [debouncedValue, setDebouncedValue] = useState(value);
@@ -39,15 +43,36 @@ export default function App() {
const debouncedUserInput = useDebounce(userInput, DEBOUNCE_DELAY);
const errorTimerRef = useRef(null);
const conversationFetchErrorCountRef = useRef(0);
const handleError = useCallback((error, context) => {
console.error(`${context}:`, error);
const isConversationFetchError = error.status === 404;
const errorMessage = isConversationFetchError
? "Error fetching conversation. Retrying..." // Updated message
const isConversationFetchError =
context === "fetching conversation" && (error.status === 404 || error.status === 408);
if (isConversationFetchError) {
if (error.status === 404) {
conversationFetchErrorCountRef.current += 1;
const hasExceededThreshold =
conversationFetchErrorCountRef.current >= CONVERSATION_FETCH_ERROR_THRESHOLD;
if (!hasExceededThreshold) {
return;
}
} else {
// For timeouts or other connectivity errors surface immediately
conversationFetchErrorCountRef.current = CONVERSATION_FETCH_ERROR_THRESHOLD;
}
} else {
conversationFetchErrorCountRef.current = 0;
}
const errorMessage = isConversationFetchError
? "Error fetching conversation. Retrying..."
: `Error ${context.toLowerCase()}. Please try again.`;
setError(prevError => {
// If the same 404 error is already being displayed, don't reset state (prevents flickering)
if (prevError.visible && prevError.message === errorMessage) {
@@ -55,12 +80,12 @@ export default function App() {
}
return { visible: true, message: errorMessage };
});
// Clear any existing timeout
if (errorTimerRef.current) {
clearTimeout(errorTimerRef.current);
}
// Only auto-dismiss non-404 errors after 3 seconds
if (!isConversationFetchError) {
errorTimerRef.current = setTimeout(() => setError(INITIAL_ERROR_STATE), 3000);
@@ -72,6 +97,7 @@ export default function App() {
if (errorTimerRef.current) {
clearTimeout(errorTimerRef.current);
}
conversationFetchErrorCountRef.current = 0;
setError(INITIAL_ERROR_STATE);
}, []);

View File

@@ -1,5 +1,17 @@
const API_BASE_URL = 'http://127.0.0.1:8000';
const resolveRequestTimeout = () => {
const env = typeof import.meta !== 'undefined' ? import.meta.env : undefined;
const configured = env?.VITE_API_TIMEOUT_MS;
const parsed = Number.parseInt(configured, 10);
if (Number.isFinite(parsed) && parsed > 0) {
return parsed;
}
return 15000;
};
const REQUEST_TIMEOUT_MS = resolveRequestTimeout(); // default to 15s, overridable via Vite env
class ApiError extends Error {
constructor(message, status) {
super(message);
@@ -19,12 +31,31 @@ async function handleResponse(response) {
return response.json();
}
async function fetchWithTimeout(url, options = {}, timeout = REQUEST_TIMEOUT_MS) {
const controller = new AbortController();
const timeoutId = setTimeout(() => controller.abort(), timeout);
try {
return await fetch(url, { ...options, signal: controller.signal });
} catch (error) {
if (error.name === 'AbortError') {
throw new ApiError('Request timed out', 408);
}
throw error;
} finally {
clearTimeout(timeoutId);
}
}
export const apiService = {
async getConversationHistory() {
try {
const res = await fetch(`${API_BASE_URL}/get-conversation-history`);
const res = await fetchWithTimeout(`${API_BASE_URL}/get-conversation-history`);
return handleResponse(res);
} catch (error) {
if (error instanceof ApiError) {
throw error;
}
throw new ApiError(
'Failed to fetch conversation history',
error.status || 500
@@ -38,7 +69,7 @@ export const apiService = {
}
try {
const res = await fetch(
const res = await fetchWithTimeout(
`${API_BASE_URL}/send-prompt?prompt=${encodeURIComponent(message)}`,
{
method: 'POST',
@@ -49,6 +80,9 @@ export const apiService = {
);
return handleResponse(res);
} catch (error) {
if (error instanceof ApiError) {
throw error;
}
throw new ApiError(
'Failed to send message',
error.status || 500
@@ -58,7 +92,7 @@ export const apiService = {
async startWorkflow() {
try {
const res = await fetch(
const res = await fetchWithTimeout(
`${API_BASE_URL}/start-workflow`,
{
method: 'POST',
@@ -69,6 +103,9 @@ export const apiService = {
);
return handleResponse(res);
} catch (error) {
if (error instanceof ApiError) {
throw error;
}
throw new ApiError(
'Failed to start workflow',
error.status || 500
@@ -78,7 +115,7 @@ export const apiService = {
async confirm() {
try {
const res = await fetch(`${API_BASE_URL}/confirm`, {
const res = await fetchWithTimeout(`${API_BASE_URL}/confirm`, {
method: 'POST',
headers: {
'Content-Type': 'application/json'
@@ -86,10 +123,13 @@ export const apiService = {
});
return handleResponse(res);
} catch (error) {
if (error instanceof ApiError) {
throw error;
}
throw new ApiError(
'Failed to confirm action',
error.status || 500
);
}
}
};
};

View File

@@ -5,5 +5,6 @@ export default defineConfig({
plugins: [react()],
server: {
open: true,
host: process.env.VITE_HOST ?? 'localhost',
},
});

View File

@@ -27,7 +27,7 @@ goal_food_ordering = AgentGoal(
"When they express interest in items, get pricing using list_prices. "
"Add items to their cart using AddToCart as they decide - the order doesn't matter, multiple items can be added. "
"After they're done selecting items, get their customer details and create a Stripe customer. "
"For checkout: 1) create_invoice, 2) create_invoice_item for each individual item (IMPORTANT: create_invoice_item does NOT accept quantity parameter - call it once per item, so if user wants 2 pizzas, call create_invoice_item twice with the same price), "
"For checkout: 1) create_invoice (always include days_until_due so the invoice has a due date, e.g., days_until_due=7), 2) create_invoice_item for each individual item (IMPORTANT: create_invoice_item does NOT accept quantity parameter - call it once per item, so if user wants 2 pizzas, call create_invoice_item twice with the same price), "
"3) finalize_invoice. The finalized invoice will contain a hosted_invoice_url for payment.",
starter_prompt=starter_prompt_generic,
example_conversation_history="\n ".join(
@@ -59,8 +59,8 @@ goal_food_ordering = AgentGoal(
"agent: Thank you Jane! Creating your Stripe customer profile with name and email.",
"user_confirmed_tool_run: <user clicks confirm on create_customer tool with name='Jane Smith' and email='jane.smith@example.com'>",
'tool_result: {"customer": {"id": "cus_ExAmPlE12345", "name": "Jane Smith", "email": "jane.smith@example.com"}}',
"agent: Customer profile created! Now I'll create a draft invoice for your order.",
"user_confirmed_tool_run: <user clicks confirm on create_invoice tool with customer='cus_ExAmPlE12345'>",
"agent: Customer profile created! Now I'll create a draft invoice for your order with payment due in 7 days.",
"user_confirmed_tool_run: <user clicks confirm on create_invoice tool with customer='cus_ExAmPlE12345', days_until_due=7>",
'tool_result: {"invoice": {"id": "in_InvOicE54321", "status": "draft", "customer": "cus_ExAmPlE12345"}}',
"agent: Invoice created! Now adding your first Pepperoni Pizza to the invoice.",
"user_confirmed_tool_run: <user clicks confirm on create_invoice_item tool with customer='cus_ExAmPlE12345', invoice='in_InvOicE54321', price='price_pepperoni_large'>",

3147
poetry.lock generated

File diff suppressed because it is too large Load Diff

View File

@@ -1,57 +1,57 @@
[tool.poetry]
[project]
name = "temporal_AI_agent"
version = "0.2.0"
description = "Temporal AI Agent"
license = "MIT"
authors = [
"Steve Androulakis <steve.androulakis@temporal.io>",
"Laine Smith <lainecaseysmith@gmail.com>",
"Joshua Smith <josh.smith@temporal.io>"
{ name = "Steve Androulakis", email = "steve.androulakis@temporal.io" },
{ name = "Laine Smith", email = "lainecaseysmith@gmail.com" },
{ name = "Joshua Smith", email = "josh.smith@temporal.io" },
]
requires-python = ">=3.10,<4.0"
readme = "README.md"
# By default, Poetry will find packages automatically,
# but explicitly including them is fine:
packages = [
{ include = "**/*.py", from = "." }
license = "MIT"
dependencies = [
"temporalio>=1.8.0,<2",
"litellm>=1.70.0,<2",
"pyyaml>=6.0.2,<7",
"fastapi>=0.115.6,<0.116",
"uvicorn>=0.34.0,<0.35",
"python-dotenv>=1.0.1,<2",
"requests>=2.32.3,<3",
"pandas>=2.2.3,<3",
"stripe>=11.4.1,<12",
"gtfs-kit>=10.1.1,<11",
"fastmcp>=2.7.0,<3",
]
[tool.poetry.urls]
[project.urls]
"Bug Tracker" = "https://github.com/temporal-community/temporal-ai-agent/issues"
[dependency-groups]
dev = [
"pytest>=8.2",
"pytest-asyncio>=0.26.0,<0.27",
"black~=23.7",
"isort~=5.12",
"mypy>=1.16.0,<2",
"poethepoet>=0.37.0",
]
[tool.poe.tasks]
format = [{cmd = "black ."}, {cmd = "isort ."}]
lint = [{cmd = "black --check ."}, {cmd = "isort --check-only ."}, {ref = "lint-types" }]
lint-types = "mypy --check-untyped-defs --namespace-packages ."
test = "pytest"
[tool.poetry.dependencies]
python = ">=3.10,<4.0"
temporalio = "^1.8.0"
[tool.hatch.metadata]
allow-direct-references = true
# Standard library modules (e.g. asyncio, collections) don't need to be added
# since they're built-in for Python 3.8+.
litellm = "^1.70.0"
pyyaml = "^6.0.2"
fastapi = "^0.115.6"
uvicorn = "^0.34.0"
python-dotenv = "^1.0.1"
requests = "^2.32.3"
pandas = "^2.2.3"
stripe = "^11.4.1"
gtfs-kit = "^10.1.1"
fastmcp = "^2.7.0"
[tool.poetry.group.dev.dependencies]
pytest = ">=8.2"
pytest-asyncio = "^0.26.0"
black = "^23.7"
isort = "^5.12"
mypy = "^1.16.0"
[tool.hatch.build]
packages = ["activities", "api", "goals", "models", "prompts", "shared", "tools", "workflows"]
[build-system]
requires = ["poetry-core>=1.4.0"]
build-backend = "poetry.core.masonry.api"
requires = ["hatchling"]
build-backend = "hatchling.build"
[tool.pytest.ini_options]
asyncio_mode = "auto"

View File

@@ -53,31 +53,31 @@ Provides shared test fixtures and configuration:
Ensure you have the required dependencies installed:
```bash
poetry install --with dev
uv sync
```
### Basic Test Execution
Run all tests:
```bash
poetry run pytest
uv run pytest
```
Run specific test files:
```bash
# Workflow tests only
poetry run pytest tests/test_agent_goal_workflow.py
uv run pytest tests/test_agent_goal_workflow.py
# Activity tests only
poetry run pytest tests/test_tool_activities.py
uv run pytest tests/test_tool_activities.py
# Legacy tests
poetry run pytest tests/workflowtests/
uv run pytest tests/workflowtests/
```
Run with verbose output:
```bash
poetry run pytest -v
uv run pytest -v
```
### Test Environment Options
@@ -87,34 +87,34 @@ The tests support different Temporal environments via the `--workflow-environmen
#### Local Environment (Default)
Uses a local Temporal test server:
```bash
poetry run pytest --workflow-environment=local
uv run pytest --workflow-environment=local
```
#### Time-Skipping Environment
Uses Temporal's time-skipping test environment for faster execution:
```bash
poetry run pytest --workflow-environment=time-skipping
uv run pytest --workflow-environment=time-skipping
```
#### External Server
Connect to an existing Temporal server:
```bash
poetry run pytest --workflow-environment=localhost:7233
uv run pytest --workflow-environment=localhost:7233
```
#### Setup Script for AI Agent environments such as OpenAI Codex
```bash
export SHELL=/bin/bash
curl -sSL https://install.python-poetry.org | python3 -
curl -LsSf https://astral.sh/uv/install.sh | sh
export PATH="$HOME/.local/bin:$PATH"
ls
poetry install --with dev
uv sync
cd frontend
npm install
cd ..
# Pre-download the temporal test server binary
poetry run python3 -c "
uv run python -c "
import asyncio
import sys
from temporalio.testing import WorkflowEnvironment
@@ -139,22 +139,22 @@ asyncio.run(predownload())
Run tests by pattern:
```bash
# Run only validation tests
poetry run pytest -k "validation"
uv run pytest -k "validation"
# Run only workflow tests
poetry run pytest -k "workflow"
uv run pytest -k "workflow"
# Run only activity tests
poetry run pytest -k "activity"
uv run pytest -k "activity"
```
Run tests by marker (if you add custom markers):
```bash
# Run only integration tests
poetry run pytest -m integration
uv run pytest -m integration
# Skip slow tests
poetry run pytest -m "not slow"
uv run pytest -m "not slow"
```
## Test Configuration
@@ -276,7 +276,7 @@ The `sample_combined_input` fixture provides:
Enable detailed logging:
```bash
poetry run pytest --log-cli-level=DEBUG -s
uv run pytest --log-cli-level=DEBUG -s
```
### Temporal Web UI
@@ -301,21 +301,18 @@ jobs:
test:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v3
- uses: actions/setup-python@v4
with:
python-version: '3.10'
- run: pip install poetry
- run: poetry install --with dev
- run: poetry run pytest --workflow-environment=time-skipping
- uses: actions/checkout@v4
- uses: astral-sh/setup-uv@v5
- run: uv sync
- run: uv run pytest --workflow-environment=time-skipping
```
### Test Coverage
Generate coverage reports:
```bash
poetry add --group dev pytest-cov
poetry run pytest --cov=workflows --cov=activities --cov-report=html
uv add --group dev pytest-cov
uv run pytest --cov=workflows --cov=activities --cov-report=html
```
## Best Practices
@@ -342,7 +339,7 @@ poetry run pytest --cov=workflows --cov=activities --cov-report=html
- Check Temporal Python SDK documentation
- Review existing test patterns in the codebase
- Use `poetry run pytest --collect-only` to verify test discovery
- Use `uv run pytest --collect-only` to verify test discovery
- Run with `-v` flag for detailed output
## Legacy Tests

View File

@@ -312,6 +312,109 @@ async def test_mcp_tool_execution_flow(client: Client):
assert captured["dynamic_args"]["server_definition"]["name"] == server_def.name
@pytest.mark.asyncio
async def test_create_invoice_defaults_days_until_due(client: Client):
"""create_invoice should include a default days_until_due when missing."""
task_queue_name = str(uuid.uuid4())
server_def = MCPServerDefinition(name="test", command="python", args=["srv.py"])
goal = AgentGoal(
id="g_invoice_default",
category_tag="food",
agent_name="agent",
agent_friendly_description="",
description="",
tools=[],
starter_prompt="",
example_conversation_history="",
mcp_server_definition=server_def,
)
combined_input = CombinedInput(
agent_goal=goal,
tool_params=AgentGoalWorkflowParams(
conversation_summary=None, prompt_queue=deque()
),
)
captured: dict = {}
@activity.defn(name="get_wf_env_vars")
async def mock_get_wf_env_vars(input: EnvLookupInput) -> EnvLookupOutput:
return EnvLookupOutput(show_confirm=True, multi_goal_mode=True)
@activity.defn(name="agent_validatePrompt")
async def mock_validate(prompt: ValidationInput) -> ValidationResult:
return ValidationResult(validationResult=True, validationFailedReason={})
@activity.defn(name="agent_toolPlanner")
async def mock_planner(input: ToolPromptInput) -> dict:
if "planner_called" not in captured:
captured["planner_called"] = True
return {
"next": "confirm",
"tool": "create_invoice",
"args": {"customer": "cus_123"},
"response": "Creating invoice",
}
return {"next": "done", "response": "done"}
@activity.defn(name="mcp_list_tools")
async def mock_mcp_list_tools(
server_definition: MCPServerDefinition, include_tools=None
):
return {
"server_name": server_definition.name,
"success": True,
"tools": {
"create_invoice": {
"name": "create_invoice",
"description": "",
"inputSchema": {
"properties": {
"customer": {"type": "string"},
"days_until_due": {"type": "number"},
}
},
},
},
"total_available": 1,
"filtered_count": 1,
}
@activity.defn(name="dynamic_tool_activity", dynamic=True)
async def mock_dynamic_tool_activity(args: Sequence[RawValue]) -> dict:
payload = activity.payload_converter().from_payload(args[0].payload, dict)
captured["dynamic_args"] = payload
return {"tool": "create_invoice", "success": True, "content": {"ok": True}}
async with Worker(
client,
task_queue=task_queue_name,
workflows=[AgentGoalWorkflow],
activities=[
mock_get_wf_env_vars,
mock_validate,
mock_planner,
mock_mcp_list_tools,
mock_dynamic_tool_activity,
],
):
handle = await client.start_workflow(
AgentGoalWorkflow.run,
combined_input,
id=str(uuid.uuid4()),
task_queue=task_queue_name,
)
await handle.signal(AgentGoalWorkflow.user_prompt, "make invoice")
await asyncio.sleep(0.5)
await handle.signal(AgentGoalWorkflow.confirm)
await asyncio.sleep(0.5)
await handle.result()
assert "dynamic_args" in captured
assert captured["dynamic_args"]["days_until_due"] == 7
@pytest.mark.asyncio
async def test_mcp_tool_failure_recorded(client: Client):
"""Failure of an MCP tool should be recorded in conversation history."""

View File

@@ -47,7 +47,7 @@ def create_invoice(args: dict) -> dict:
stripe.InvoiceItem.create(
customer=customer_id,
amount=amount_cents,
currency="gbp",
currency="usd",
description=args.get("tripDetails", "Service Invoice"),
)

File diff suppressed because it is too large Load Diff

View File

@@ -1,9 +1,21 @@
import calendar
import json
from datetime import datetime
from pathlib import Path
from typing import Any
def find_events(args: dict) -> dict:
def find_events(args: dict[str, Any]) -> dict[str, Any]:
"""Find events that overlap with a given month in a specified city.
Args:
args: Dictionary containing:
- city: City name to search for events (e.g., 'Melbourne')
- month: Month name to search (e.g., 'April')
Returns:
Dictionary with 'events' list and 'note' with search context.
"""
search_city = args.get("city", "").lower()
search_month = args.get("month", "").capitalize()
@@ -16,36 +28,33 @@ def find_events(args: dict) -> dict:
except ValueError:
return {"error": "Invalid month provided."}
# Helper to wrap months into [1..12]
def get_adjacent_months(m):
prev_m = 12 if m == 1 else (m - 1)
next_m = 1 if m == 12 else (m + 1)
return [prev_m, m, next_m]
# Determine the target year: use next upcoming occurrence of the month
today = datetime.now()
if month_number >= today.month:
target_year = today.year
else:
target_year = today.year + 1
valid_months = get_adjacent_months(month_number)
# Build the search month date range
month_start = datetime(target_year, month_number, 1)
last_day = calendar.monthrange(target_year, month_number)[1]
month_end = datetime(target_year, month_number, last_day)
matching_events = []
for city_name, events in json.load(open(file_path)).items():
with open(file_path) as f:
data = json.load(f)
for city_name, events in data.items():
if search_city and search_city not in city_name.lower():
continue
for event in events:
date_from = datetime.strptime(event["dateFrom"], "%Y-%m-%d")
date_to = datetime.strptime(event["dateTo"], "%Y-%m-%d")
# If the event's start or end month is in our valid months
if date_from.month in valid_months or date_to.month in valid_months:
# Add metadata explaining how it matches
if date_from.month == month_number or date_to.month == month_number:
month_context = "requested month"
elif (
date_from.month == valid_months[0]
or date_to.month == valid_months[0]
):
month_context = "previous month"
else:
month_context = "next month"
event_start = datetime.strptime(event["dateFrom"], "%Y-%m-%d")
event_end = datetime.strptime(event["dateTo"], "%Y-%m-%d")
# Check if the event overlaps with the search month
# Two date ranges overlap if: start1 <= end2 AND start2 <= end1
if month_start <= event_end and event_start <= month_end:
matching_events.append(
{
"city": city_name,
@@ -53,12 +62,10 @@ def find_events(args: dict) -> dict:
"dateFrom": event["dateFrom"],
"dateTo": event["dateTo"],
"description": event["description"],
"month": month_context,
}
)
# Add top-level metadata if you wish
return {
"note": f"Returning events from {search_month} plus one month either side (i.e., {', '.join(datetime(2025, m, 1).strftime('%B') for m in valid_months)}).",
"note": f"Returning events that overlap with {search_month} {target_year}.",
"events": matching_events,
}

View File

@@ -180,10 +180,9 @@ search_fixtures_tool = ToolDefinition(
find_events_tool = ToolDefinition(
name="FindEvents",
description="Find upcoming events to travel to a given city (e.g., 'Melbourne') and a date or month. "
description="Find upcoming events to travel to a given city (e.g., 'Melbourne') and a month. "
"It knows about events in Oceania only (e.g. major Australian and New Zealand cities). "
"It will search 1 month either side of the month provided. "
"Returns a list of events. ",
"Returns events that overlap with the specified month. ",
arguments=[
ToolArgument(
name="city",
@@ -193,7 +192,7 @@ find_events_tool = ToolDefinition(
ToolArgument(
name="month",
type="string",
description="The month to search for events (will search 1 month either side of the month provided)",
description="The month to search for events (e.g., 'April')",
),
],
)

2401
uv.lock generated Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -6,7 +6,7 @@ from temporalio.common import RetryPolicy
from temporalio.exceptions import ActivityError
from models.data_types import ConversationHistory, ToolPromptInput
from models.tool_definitions import AgentGoal
from models.tool_definitions import AgentGoal, ToolDefinition
from prompts.agent_prompt_generators import (
generate_missing_args_prompt,
generate_tool_completion_prompt,
@@ -21,63 +21,19 @@ LLM_ACTIVITY_SCHEDULE_TO_CLOSE_TIMEOUT = timedelta(minutes=30)
def is_mcp_tool(tool_name: str, goal: AgentGoal) -> bool:
"""Check if a tool is an MCP tool based on the goal's MCP server definition"""
"""Check if a tool should be dispatched via MCP."""
if not goal.mcp_server_definition:
return False
# Check if the tool name matches any MCP tools that were loaded
# We can identify MCP tools by checking if they're not in the original static tools
from tools.tool_registry import (
book_pto_tool,
book_trains_tool,
change_goal_tool,
create_invoice_tool,
current_pto_tool,
ecomm_get_order,
ecomm_list_orders,
ecomm_track_package,
financial_check_account_is_valid,
financial_get_account_balances,
financial_move_money,
financial_submit_loan_approval,
find_events_tool,
food_add_to_cart_tool,
future_pto_calc_tool,
give_hint_tool,
guess_location_tool,
list_agents_tool,
paycheck_bank_integration_status_check,
search_fixtures_tool,
search_flights_tool,
search_trains_tool,
)
# Native tools are registered with tools.get_handler. If lookup succeeds,
# the tool should execute locally; otherwise treat it as MCP-provided.
from tools import get_handler
static_tool_names = {
list_agents_tool.name,
change_goal_tool.name,
give_hint_tool.name,
guess_location_tool.name,
search_flights_tool.name,
search_trains_tool.name,
book_trains_tool.name,
create_invoice_tool.name,
search_fixtures_tool.name,
find_events_tool.name,
current_pto_tool.name,
future_pto_calc_tool.name,
book_pto_tool.name,
paycheck_bank_integration_status_check.name,
financial_check_account_is_valid.name,
financial_get_account_balances.name,
financial_move_money.name,
financial_submit_loan_approval.name,
ecomm_list_orders.name,
ecomm_get_order.name,
ecomm_track_package.name,
food_add_to_cart_tool.name,
}
return tool_name not in static_tool_names
try:
get_handler(tool_name)
return False
except ValueError:
return True
async def handle_tool_execution(
@@ -98,6 +54,13 @@ async def handle_tool_execution(
# Add server definition to args for MCP tools
mcp_args = tool_data["args"].copy()
# Stripe's MCP server enforces days_until_due when the collection
# method defaults to send_invoice. Provide a reasonable default when
# the planner omits it so invoice creation doesn't fail upstream.
if current_tool == "create_invoice" and "days_until_due" not in mcp_args:
mcp_args["days_until_due"] = 7
mcp_args["server_definition"] = goal.mcp_server_definition
dynamic_result = await workflow.execute_activity(