Local
Run Voxli tests against your local development environment for fast iteration without CI round-trips. The @voxli/cli package handles agent registration and polling automatically, you just provide a test command.
Using the cli helps with a few things.
- Registers an agent in voxli representing your computer (only visible to you).
- Allows triggering test runs from the Voxli web UI or via MCP.
- Simplifies authentication (no need for API keys).
Setup
Install the voxli cli
npm install -g @voxli/cli
Login with Voxli
voxli auth
This links your machine to your Voxli account. The CLI stores your credentials locally and injects them as the VOXLI_API_TOKEN environment variable when running your test command.
Write Your Test Command
The CLI passes these environment variables to your command:
VOXLI_API_TOKEN— your API token (injected automatically fromvoxli auth)VOXLI_TEST_RESULT_IDS— JSON array of test result IDs to run
This is the same contract as the GitHub integration, so if you already have a test script for CI you can reuse it directly.
"""Run Voxli test conversations.Environment variables:- VOXLI_API_TOKEN: Your API key (required)- VOXLI_TEST_RESULT_IDS: JSON array of test result IDs (required)"""import jsonimport osimport sysimport timeimport requestsdef get_agent_response(message: str) -> str:"""Replace this with your actual agent integration.Receives a message from the Voxli tester and returnsyour chatbot's response."""return "The meaning of life is 42."# In interactive sessions the tester is a person (or agent) typing, so `ready`# can stay false for minutes between turns — far longer than an automated run.# Voxli ends abandoned sessions on its side, but don't rely on that alone: this# runner is a billed CI job, so it holds its own deadline and turn cap and exits# on its own if the server never says end_chat.SESSION_DEADLINE_SECONDS = 90 * 60MAX_TURNS = 200POLL_INTERVAL_SECONDS = 2def poll_next_message(endpoint: str, headers: dict, deadline: float) -> str | None:"""Wait for the next tester message, or None once the chat is over.`deadline` is an absolute time covering the whole session, not one turn,so a long chat cannot extend the job indefinitely one turn at a time."""while True:response = requests.post(endpoint, headers=headers)response.raise_for_status()data = response.json()if data["ready"]:return None if data.get("end_chat") else data["message"]if time.time() > deadline:raise TimeoutError("Session deadline reached waiting for a message")time.sleep(POLL_INTERVAL_SECONDS)def run_test(test_result_id: str, api_key: str, base_url: str):headers = {"Authorization": f"Bearer {api_key}"}conversation_endpoint = f"{base_url}/test-results/{test_result_id}/conversation"generate_endpoint = f"{base_url}/test-results/{test_result_id}/next-message"deadline = time.time() + SESSION_DEADLINE_SECONDS# Get first message from Voxlitester_message = poll_next_message(generate_endpoint, headers, deadline)# Converse until Voxli ends the chat (end_chat=true), bounded by our own# deadline and turn cap so the job always terminates.for _ in range(MAX_TURNS):if tester_message is None:print(f"Test {test_result_id} completed")returnagent_response = get_agent_response(tester_message)# Record agent responseresponse = requests.post(conversation_endpoint, headers=headers, json={"type": "message", "content": agent_response})response.raise_for_status()# Get next message from Voxlitester_message = poll_next_message(generate_endpoint, headers, deadline)print(f"Test {test_result_id} stopped after {MAX_TURNS} turns")def main():api_key = os.getenv("VOXLI_API_TOKEN")test_result_ids_raw = os.getenv("VOXLI_TEST_RESULT_IDS")base_url = os.getenv("VOXLI_API_URL", "https://api.voxli.io")if not api_key or not test_result_ids_raw:print("Error: VOXLI_API_TOKEN and VOXLI_TEST_RESULT_IDS are required")sys.exit(1)test_result_ids = json.loads(test_result_ids_raw)for test_result_id in test_result_ids:run_test(test_result_id, api_key, base_url)if __name__ == "__main__":main()
Start Listening
voxli listen --command "python run_test.py"
The --command flag specifies the shell command the CLI runs when tests are assigned. It receives VOXLI_TEST_RESULT_IDS and VOXLI_API_TOKEN as environment variables.
Trigger a test run from the Voxli UI selecting your local agent — the CLI picks it up and runs your command.
How It Works
- The CLI registers your machine as a local agent in Voxli
- You trigger a test run from the Voxli UI
- The CLI picks up the work and runs your
--commandwithVOXLI_TEST_RESULT_IDSandVOXLI_API_TOKEN - Your script runs the tests and reports results back to Voxli using the API