1 Commits

Author SHA1 Message Date
Mason Egger
b0408d9ed6 Update API to use proper query
Looks like you changed the query handler in the Workflow but didn't update the API. Minor patch.
2025-06-16 10:53:40 -05:00
26 changed files with 3417 additions and 3976 deletions

View File

@@ -1,20 +0,0 @@
{
"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"
}
}

View File

@@ -1,37 +0,0 @@
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

@@ -34,10 +34,11 @@ Default URLs:
1. **Prerequisites:**
```bash
# Install uv and Temporal server (MacOS)
brew install uv
# Install Poetry for Python dependency management
curl -sSL https://install.python-poetry.org | python3 -
# Start Temporal server (Mac)
brew install temporal
temporal server start-dev
```
@@ -49,9 +50,9 @@ Default URLs:
make run-api # Starts the API server
# Or manually:
uv sync
uv run scripts/run_worker.py # In one terminal
uv run uvicorn api.main:app --reload # In another terminal
poetry install
poetry run python scripts/run_worker.py # In one terminal
poetry run uvicorn api.main:app --reload # In another terminal
```
3. **Frontend (React):**
@@ -101,20 +102,20 @@ The project includes comprehensive tests using Temporal's testing framework:
```bash
# Install test dependencies
uv sync
poetry install --with dev
# Run all tests
uv run pytest
poetry run pytest
# Run with time-skipping for faster execution
uv run pytest --workflow-environment=time-skipping
poetry run pytest --workflow-environment=time-skipping
# Run specific test categories
uv run pytest tests/test_tool_activities.py -v # Activity tests
uv run pytest tests/test_agent_goal_workflow.py -v # Workflow tests
poetry run pytest tests/test_tool_activities.py -v # Activity tests
poetry run pytest tests/test_agent_goal_workflow.py -v # Workflow tests
# Run with coverage
uv run pytest --cov=workflows --cov=activities
poetry run pytest --cov=workflows --cov=activities
```
**Test Coverage:**
@@ -129,15 +130,15 @@ uv run pytest --cov=workflows --cov=activities
## Linting and Code Quality
```bash
# 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
# 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
# Manual commands
uv run black .
uv run isort .
uv run mypy --check-untyped-defs --namespace-packages .
# Manual commands
poetry run black .
poetry run isort .
poetry run mypy --check-untyped-defs --namespace-packages .
```
## Agent Customization
@@ -191,7 +192,7 @@ 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: `uv run pytest --workflow-environment=time-skipping`
- Ensure tests pass before submitting: `poetry run pytest --workflow-environment=time-skipping`
## Additional Resources
- **Setup Guide**: [setup.md](docs/setup.md) - Detailed configuration instructions

View File

@@ -4,19 +4,17 @@ WORKDIR /app
# Install system dependencies
RUN apt-get update && \
apt-get install -y --no-install-recommends gcc build-essential curl && \
apt-get install -y --no-install-recommends gcc build-essential && \
apt-get clean && \
rm -rf /var/lib/apt/lists/*
# Install uv
RUN curl -LsSf https://astral.sh/uv/install.sh | sh
ENV PATH="$PATH:/root/.local/bin"
# Copy requirements first for better caching
RUN pip install --no-cache-dir poetry
# 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
# 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 application code
COPY . .
@@ -29,4 +27,4 @@ ENV PYTHONPATH=/app
EXPOSE 8000
# Default to running only the API server; worker and train-api are separate Compose services
CMD ["uv", "run", "uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "8000"]
CMD ["uvicorn", "api.main:app", "--host", "0.0.0.0", "--port", "8000"]

View File

@@ -1,24 +1,35 @@
.PHONY: setup install run-worker run-api run-frontend run-train-api run-legacy-worker run-enterprise setup-venv check-python run-dev
setup:
uv sync
# 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
cd frontend && npm install
# Run commands
run-worker:
uv run scripts/run_worker.py
poetry run python scripts/run_worker.py
run-api:
uv run uvicorn api.main:app --reload
poetry run uvicorn api.main:app --reload
run-frontend:
cd frontend && npx vite
run-train-api:
uv run thirdparty/train_api.py
poetry run python thirdparty/train_api.py
run-legacy-worker:
uv run scripts/run_legacy_worker.py
poetry run python scripts/run_legacy_worker.py
run-enterprise:
cd enterprise && dotnet build && dotnet run
@@ -39,7 +50,9 @@ run-dev:
# Help command
help:
@echo "Available commands:"
@echo " make setup - Install all dependencies"
@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 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 reliability, 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 reliablity, 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
uv sync
poetry install --with dev
# Run all tests
uv run pytest
poetry run pytest
# Run with time-skipping for faster execution
uv run pytest --workflow-environment=time-skipping
poetry run pytest --workflow-environment=time-skipping
```
**Test Coverage:**

View File

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

View File

@@ -79,7 +79,7 @@ services:
- .env
environment:
- TEMPORAL_ADDRESS=temporal:7233
command: uv run scripts/run_worker.py
command: python scripts/run_worker.py
networks:
- temporal-network
@@ -94,7 +94,7 @@ services:
- .env
environment:
- TEMPORAL_ADDRESS=temporal:7233
command: uv run thirdparty/train_api.py
command: python 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
uv run poe format
poetry run poe format
```
Or manually
```
uv run black .
uv run isort .
Or manually:
```bash
poetry run black .
poetry run isort .
```
Please format your code before committing.
### Linting & Type Checking
We use `mypy` for static type checking and other linters configured via `poe`.
We use `mypy` for static type checking and other linters configured via `poe the poet`.
- **Run linters and type checks:**
```bash
uv run poe lint
poetry run poe lint
```
Or manually for type checking:
```bash
uv run mypy --check-untyped-defs --namespace-packages .
poetry 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:**
- **Install test dependencies** (if not already done with `poetry install --with dev`):
```bash
uv sync
poetry install --with dev
```
- **Run all tests:**
```bash
uv run pytest
poetry run pytest
```
- **Run tests with time-skipping (recommended for faster execution, especially in CI):**
```bash
uv run pytest --workflow-environment=time-skipping
poetry 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 `uv 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 `poetry 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

@@ -22,6 +22,8 @@ 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
@@ -157,22 +159,24 @@ Default urls:
**Python Backend**
Requires [`uv`](https://docs.astral.sh/uv/) to manage dependencies.
Requires [Poetry](https://python-poetry.org/) to manage dependencies.
1. Install uv: `curl -LsSf https://astral.sh/uv/install.sh | sh`
1. `python -m venv venv`
2. `uv sync`
2. `source venv/bin/activate`
3. `poetry install`
Run the following commands in separate terminal windows:
1. Start the Temporal worker:
```bash
uv run scripts/run_worker.py
poetry run python scripts/run_worker.py
```
2. Start the API server:
```bash
uv run uvicorn api.main:app --reload
poetry run uvicorn api.main:app --reload
```
Access the API at `/docs` to see the available endpoints.
@@ -257,7 +261,7 @@ NOTE: This goal was developed for an on-stage demo and has failure (and its reso
Required to search and book trains!
```bash
uv run thirdparty/train_api.py
poetry run python 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
@@ -269,7 +273,7 @@ uv run 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
uv run scripts/run_legacy_worker.py
poetry run python 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.
@@ -324,8 +328,8 @@ 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 />
[ ] `uv run scripts/run_worker.py` <br />
[ ] `uv run uvicorn api.main:app --reload` <br />
[ ] `poetry run python scripts/run_worker.py` <br />
[ ] `poetry 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
uv sync
poetry install --with dev
```
2. **Run all tests**:
```bash
uv run pytest
poetry run pytest
```
3. **Run with time-skipping for faster execution**:
```bash
uv run pytest --workflow-environment=time-skipping
poetry 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
uv run pytest tests/test_tool_activities.py -v
poetry run pytest tests/test_tool_activities.py -v
# Run only workflow tests
uv run pytest tests/test_agent_goal_workflow.py -v
poetry run pytest tests/test_agent_goal_workflow.py -v
# Run a specific test
uv run pytest tests/test_tool_activities.py::TestToolActivities::test_sanitize_json_response -v
poetry run pytest tests/test_tool_activities.py::TestToolActivities::test_sanitize_json_response -v
# Run tests matching a pattern
uv run pytest -k "validation" -v
poetry run pytest -k "validation" -v
```
## Test Environment Options
### Local Environment (Default)
```bash
uv run pytest --workflow-environment=local
poetry run pytest --workflow-environment=local
```
### Time-Skipping Environment (Recommended for CI)
```bash
uv run pytest --workflow-environment=time-skipping
poetry run pytest --workflow-environment=time-skipping
```
### External Temporal Server
```bash
uv run pytest --workflow-environment=localhost:7233
poetry 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 `uv sync`
1. **Module not found errors**: Run `poetry install --with dev`
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
uv run pytest --log-cli-level=DEBUG -s
poetry run pytest --log-cli-level=DEBUG -s
```
Run with coverage:
```bash
uv run pytest --cov=workflows --cov=activities
poetry run pytest --cov=workflows --cov=activities
```
## Continuous Integration
For CI environments, use:
```bash
uv run pytest --workflow-environment=time-skipping --tb=short
poetry run pytest --workflow-environment=time-skipping --tb=short
```
## Additional Resources

View File

@@ -23,8 +23,6 @@
[ ] 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

@@ -6,10 +6,6 @@ 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);
@@ -43,36 +39,15 @@ 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 =
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..."
const isConversationFetchError = error.status === 404;
const errorMessage = isConversationFetchError
? "Error fetching conversation. Retrying..." // Updated message
: `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) {
@@ -80,12 +55,12 @@ 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);
@@ -97,7 +72,6 @@ export default function App() {
if (errorTimerRef.current) {
clearTimeout(errorTimerRef.current);
}
conversationFetchErrorCountRef.current = 0;
setError(INITIAL_ERROR_STATE);
}, []);

View File

@@ -1,17 +1,5 @@
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);
@@ -31,31 +19,12 @@ 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 fetchWithTimeout(`${API_BASE_URL}/get-conversation-history`);
const res = await fetch(`${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
@@ -69,7 +38,7 @@ export const apiService = {
}
try {
const res = await fetchWithTimeout(
const res = await fetch(
`${API_BASE_URL}/send-prompt?prompt=${encodeURIComponent(message)}`,
{
method: 'POST',
@@ -80,9 +49,6 @@ export const apiService = {
);
return handleResponse(res);
} catch (error) {
if (error instanceof ApiError) {
throw error;
}
throw new ApiError(
'Failed to send message',
error.status || 500
@@ -92,7 +58,7 @@ export const apiService = {
async startWorkflow() {
try {
const res = await fetchWithTimeout(
const res = await fetch(
`${API_BASE_URL}/start-workflow`,
{
method: 'POST',
@@ -103,9 +69,6 @@ export const apiService = {
);
return handleResponse(res);
} catch (error) {
if (error instanceof ApiError) {
throw error;
}
throw new ApiError(
'Failed to start workflow',
error.status || 500
@@ -115,7 +78,7 @@ export const apiService = {
async confirm() {
try {
const res = await fetchWithTimeout(`${API_BASE_URL}/confirm`, {
const res = await fetch(`${API_BASE_URL}/confirm`, {
method: 'POST',
headers: {
'Content-Type': 'application/json'
@@ -123,13 +86,10 @@ 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

@@ -5,6 +5,5 @@ 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 (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), "
"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), "
"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 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>",
"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'>",
'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 Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -1,57 +1,57 @@
[project]
[tool.poetry]
name = "temporal_AI_agent"
version = "0.2.0"
description = "Temporal AI Agent"
authors = [
{ 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"
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",
authors = [
"Steve Androulakis <steve.androulakis@temporal.io>",
"Laine Smith <lainecaseysmith@gmail.com>",
"Joshua Smith <josh.smith@temporal.io>"
]
readme = "README.md"
# By default, Poetry will find packages automatically,
# but explicitly including them is fine:
packages = [
{ include = "**/*.py", from = "." }
]
[project.urls]
[tool.poetry.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.hatch.metadata]
allow-direct-references = true
[tool.poetry.dependencies]
python = ">=3.10,<4.0"
temporalio = "^1.8.0"
[tool.hatch.build]
packages = ["activities", "api", "goals", "models", "prompts", "shared", "tools", "workflows"]
# 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"
[build-system]
requires = ["hatchling"]
build-backend = "hatchling.build"
requires = ["poetry-core>=1.4.0"]
build-backend = "poetry.core.masonry.api"
[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
uv sync
poetry install --with dev
```
### Basic Test Execution
Run all tests:
```bash
uv run pytest
poetry run pytest
```
Run specific test files:
```bash
# Workflow tests only
uv run pytest tests/test_agent_goal_workflow.py
poetry run pytest tests/test_agent_goal_workflow.py
# Activity tests only
uv run pytest tests/test_tool_activities.py
poetry run pytest tests/test_tool_activities.py
# Legacy tests
uv run pytest tests/workflowtests/
poetry run pytest tests/workflowtests/
```
Run with verbose output:
```bash
uv run pytest -v
poetry 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
uv run pytest --workflow-environment=local
poetry run pytest --workflow-environment=local
```
#### Time-Skipping Environment
Uses Temporal's time-skipping test environment for faster execution:
```bash
uv run pytest --workflow-environment=time-skipping
poetry run pytest --workflow-environment=time-skipping
```
#### External Server
Connect to an existing Temporal server:
```bash
uv run pytest --workflow-environment=localhost:7233
poetry run pytest --workflow-environment=localhost:7233
```
#### Setup Script for AI Agent environments such as OpenAI Codex
```bash
export SHELL=/bin/bash
curl -LsSf https://astral.sh/uv/install.sh | sh
curl -sSL https://install.python-poetry.org | python3 -
export PATH="$HOME/.local/bin:$PATH"
ls
uv sync
poetry install --with dev
cd frontend
npm install
cd ..
# Pre-download the temporal test server binary
uv run python -c "
poetry run python3 -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
uv run pytest -k "validation"
poetry run pytest -k "validation"
# Run only workflow tests
uv run pytest -k "workflow"
poetry run pytest -k "workflow"
# Run only activity tests
uv run pytest -k "activity"
poetry run pytest -k "activity"
```
Run tests by marker (if you add custom markers):
```bash
# Run only integration tests
uv run pytest -m integration
poetry run pytest -m integration
# Skip slow tests
uv run pytest -m "not slow"
poetry run pytest -m "not slow"
```
## Test Configuration
@@ -276,7 +276,7 @@ The `sample_combined_input` fixture provides:
Enable detailed logging:
```bash
uv run pytest --log-cli-level=DEBUG -s
poetry run pytest --log-cli-level=DEBUG -s
```
### Temporal Web UI
@@ -301,18 +301,21 @@ jobs:
test:
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- uses: astral-sh/setup-uv@v5
- run: uv sync
- run: uv run pytest --workflow-environment=time-skipping
- 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
```
### Test Coverage
Generate coverage reports:
```bash
uv add --group dev pytest-cov
uv run pytest --cov=workflows --cov=activities --cov-report=html
poetry add --group dev pytest-cov
poetry run pytest --cov=workflows --cov=activities --cov-report=html
```
## Best Practices
@@ -339,7 +342,7 @@ uv run pytest --cov=workflows --cov=activities --cov-report=html
- Check Temporal Python SDK documentation
- Review existing test patterns in the codebase
- Use `uv run pytest --collect-only` to verify test discovery
- Use `poetry run pytest --collect-only` to verify test discovery
- Run with `-v` flag for detailed output
## Legacy Tests

View File

@@ -312,109 +312,6 @@ 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="usd",
currency="gbp",
description=args.get("tripDetails", "Service Invoice"),
)

File diff suppressed because it is too large Load Diff

View File

@@ -1,21 +1,9 @@
import calendar
import json
from datetime import datetime
from pathlib import Path
from typing import Any
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.
"""
def find_events(args: dict) -> dict:
search_city = args.get("city", "").lower()
search_month = args.get("month", "").capitalize()
@@ -28,33 +16,36 @@ def find_events(args: dict[str, Any]) -> dict[str, Any]:
except ValueError:
return {"error": "Invalid month provided."}
# 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
# 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]
# 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)
valid_months = get_adjacent_months(month_number)
matching_events = []
with open(file_path) as f:
data = json.load(f)
for city_name, events in data.items():
for city_name, events in json.load(open(file_path)).items():
if search_city and search_city not in city_name.lower():
continue
for event in events:
event_start = datetime.strptime(event["dateFrom"], "%Y-%m-%d")
event_end = datetime.strptime(event["dateTo"], "%Y-%m-%d")
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"
# 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,
@@ -62,10 +53,12 @@ def find_events(args: dict[str, Any]) -> dict[str, Any]:
"dateFrom": event["dateFrom"],
"dateTo": event["dateTo"],
"description": event["description"],
"month": month_context,
}
)
# Add top-level metadata if you wish
return {
"note": f"Returning events that overlap with {search_month} {target_year}.",
"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)}).",
"events": matching_events,
}

View File

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

2401
uv.lock generated

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, ToolDefinition
from models.tool_definitions import AgentGoal
from prompts.agent_prompt_generators import (
generate_missing_args_prompt,
generate_tool_completion_prompt,
@@ -21,19 +21,63 @@ LLM_ACTIVITY_SCHEDULE_TO_CLOSE_TIMEOUT = timedelta(minutes=30)
def is_mcp_tool(tool_name: str, goal: AgentGoal) -> bool:
"""Check if a tool should be dispatched via MCP."""
"""Check if a tool is an MCP tool based on the goal's MCP server definition"""
if not goal.mcp_server_definition:
return False
# 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
# 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,
)
try:
get_handler(tool_name)
return False
except ValueError:
return True
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
async def handle_tool_execution(
@@ -54,13 +98,6 @@ 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(