Metadata-Version: 2.4
Name: agent-testing-cli
Version: 0.1.3
Summary: TestMu A2A CLI for testing chat, voice, and phone caller agents
Requires-Python: >=3.10
Description-Content-Type: text/markdown
Requires-Dist: httpx<1,>=0.27
Requires-Dist: keyring<26,>=25
Requires-Dist: pydantic<3,>=2.7
Requires-Dist: rich<14,>=13.7
Requires-Dist: textual<1,>=0.60
Requires-Dist: typer<1,>=0.12
Provides-Extra: dev
Requires-Dist: pytest<9,>=8; extra == "dev"
Requires-Dist: pytest-asyncio<1,>=0.23; extra == "dev"
Requires-Dist: respx<1,>=0.21; extra == "dev"
Provides-Extra: build
Requires-Dist: pyinstaller<7,>=6.5; extra == "build"

# TestMu A2A CLI

TestMu A2A CLI is a command-line tool for testing AI agents from your
terminal. Use it to discover projects and test suites, run agent tests, and
retrieve test results.

The CLI supports chat agents, voice agents, and Phone Caller inbound and
outbound agents.

## Requirements

- Python 3.10 or newer

## Install

```sh
python -m pip install agent-testing-cli
```

Check the available commands:

```sh
agent-testing-cli --help
```

## Authenticate

Sign in locally and check the active profile:

```sh
agent-testing-cli login
agent-testing-cli auth status
```

For CI, set both environment variables:

```sh
export LT_USERNAME="your-username"
export LT_ACCESS_KEY="your-access-key"
```

## Discover projects and suites

```sh
agent-testing-cli projects
agent-testing-cli agents --project PROJECT_ID
agent-testing-cli scenarios --project PROJECT_ID
agent-testing-cli suites --project PROJECT_ID
agent-testing-cli endpoint-profiles --project PROJECT_ID
```

Use `--json` when another program or a CI job reads the output.

## Run tests

Run a Phone Caller suite:

```sh
agent-testing-cli run --project PROJECT_ID --suite SUITE_ID --yes
```

Wait for the final Phone Caller result:

```sh
agent-testing-cli run --project PROJECT_ID --suite SUITE_ID --yes --wait
```

Run a Chat evaluation:

```sh
agent-testing-cli run \
  --project PROJECT_ID \
  --workflow WORKFLOW_ID \
  --suite SUITE_ID \
  --yes
```

Do not use `--wait` for Chat evaluations.

Run a test from a result URL:

```sh
agent-testing-cli run --url RESULT_URL --yes
```

Validate a suite file without starting a test:

```sh
agent-testing-cli run --file SUITES.json --dry-run
```

## Retrieve results

```sh
agent-testing-cli results --suite SUITE_ID
agent-testing-cli call --id CALL_ID
```

## Interactive terminal interface

```sh
agent-testing-cli tui
```

Use `agent-testing-cli --help` for the complete command and option reference.
