Backend — Setup and Run Guide
Follow these steps from the repository root. Commands shown for both Windows (cmd/Powershell) and Unix-like shells where applicable.
1) Clone the repository
git clone https://CTS-AI@dev.azure.com/CTS-AI/IDC_Family_Safety_Agent/_git/IDC_Family_Safety_Agent
cd IDC_Family_Safety_Agent
2) Enter the backend directory
cd backend
3) Prerequisites
- Install Python 3.12 and ensure
python/python3is on your PATH. - (Recommended) Create and activate a virtual environment:
- Windows (cmd):
python -m venv .venv&\.venv\Scripts\activate - Unix/macOS:
python3 -m venv .venv&source .venv/bin/activate
- Windows (cmd):
4) Install Python dependencies
pip install -r requirements.txt
If you need to install some packages manually, you can also run:
pip install playwright python-dotenv openai azure-storage-blob flask flask-cors pandas jinja2 openpyxl msal requests tldextract transformers
5) Install Playwright browsers
Run this from the same environment where Playwright is installed:
playwright install
On some systems you may also need playwright install-deps.
6) Configure environment variables
- Copy the example environment file and update values:
- Windows (cmd):
copy .env_example .env - Unix-like:
cp .env_example .env
- Windows (cmd):
- Edit
.envand set the required values (examples):ADO_PLAN_IDADO_SUITE_IDAPP_PATH(local path to the Microsoft Teams app executable)ADO_ORGADO_PROJECTADO_PAT- Optional:
LOGIN_EMAIL,LOGIN_PASSWORD, Azure OpenAI/Blob settings, etc.
7) Run the agent
From the backend directory run:
python run_natural_tests.py
This will start the agent and execute tests according to the configured ADO plan/suite or local test JSON fallback.
Notes
- Ensure
APP_PATHpoints to the correct Teams executable for your OS. - Updating ADO settings (
ADO_PLAN_ID,ADO_SUITE_ID,ADO_ORG,ADO_PROJECT,ADO_PAT) changes which test cases are fetched. - Generated reports, screenshots and videos are placed under
backend/reporting/reports/consolidated reports. If Azure Blob is configured, report links may be uploaded and shared.
Report formatting flags
- If
HCLTech_TestCaseId=false, the final report shows only theTest Case IDcolumn. - If
HCLTech_TestCaseId=true, the final report shows bothTest Case IDandHCLTech ADO IDcolumns.
Release files for ai-regression-agent 0.2.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| ai_regression_agent-0.2.1.tar.gz | 78.2 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| ai_regression_agent-0.2.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 172.0 kB
Release files / ai_regression_agent-0.2.1.tar.gz
| Download URL | ai_regression_agent-0.2.1.tar.gz |
|---|---|
| Size | 78.2 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
0b820f6d2c5e1e43dd871970ec1c109ee02c749b801f5cdc5bf5b84c3fd7cd46
|
|
BLAKE2b-256 checksum How to use checksums |
a73ad109fb3b52edc5a2e97eb0ab5220afbd1ff19731039df36f4a7d15d31b34
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.10
|
Release files / ai_regression_agent-0.2.1-py3-none-any.whl
| Download URL | ai_regression_agent-0.2.1-py3-none-any.whl |
|---|---|
| Size | 93.8 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
1c5e17fcf9c1027aa9d325f39a9f9c54d9e2c958d2ce5f2a6a228643f0d90e09
|
|
BLAKE2b-256 checksum How to use checksums |
3e38b55e3ba2adf90818be565b655eff9853db96c7cfe07ceffa36e13d88e362
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.12.10
|