Python SDK for Lightcurve voice-agent sandbox tests, Lightcurve rooms, and experiment suites.
Project description
Lightcurve Python SDK
Python client for running Lightcurve voice-agent sandbox tests from CI, notebooks, or backend automation.
Install:
pip install use-lightcurve
Basic usage:
from lightcurve import Lightcurve, providers
lc = Lightcurve(
base_url="https://app.uselightcurve.com",
api_key="lc_..." # or LIGHTCURVE_API_KEY
)
result = lc.run_suite(
name="booking-agent-release-gate",
scenario_ids=["email-capture-001", "booking-reschedule-1570"],
**providers.agent_replica(
instructions="Confirm dates, guest count, room choice, and final price before booking."
),
)
print(result["mos"], result["taskCompletion"])
Create a Lightcurve room test:
room_test = lc.create_lightcurve_room_test(
name="one-off-room-check",
scenario_ids=["email-capture-001"],
)
print(room_test["room"]["roomName"])
print(room_test["room"]["liveKitUrl"])
print(room_test["room"]["agentToken"])
Phone-realism check through a customer-owned Vapi account:
result = lc.run_suite(
name="failed-cases-phone-check",
scenario_ids=["refund-angry-001"],
**providers.phone_realism_vapi(
agent_phone_number="+14155550123",
outbound_caller_number_id="vapi-phone-number-uuid",
api_key="customer-vapi-api-key",
),
)
Environment variables:
LIGHTCURVE_API_KEY: server-side Lightcurve API key.LIGHTCURVE_BASE_URL: defaults tohttps://app.uselightcurve.com.
This package is intentionally small and uses only Python's standard library.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file use_lightcurve-0.3.0.tar.gz.
File metadata
- Download URL: use_lightcurve-0.3.0.tar.gz
- Upload date:
- Size: 5.2 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
be67e51cdfd8185a0dc3f17d709d9e8a228d2345839c9e764fd8e7c10c5a2251
|
|
| MD5 |
5d971916a8deeb4035e5f20fc794c68f
|
|
| BLAKE2b-256 |
a37971978c2ba7252bae7ba28c595694deaa57601f8ee69f76333cebc83f2df3
|
File details
Details for the file use_lightcurve-0.3.0-py3-none-any.whl.
File metadata
- Download URL: use_lightcurve-0.3.0-py3-none-any.whl
- Upload date:
- Size: 6.0 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/6.2.0 CPython/3.13.1
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
5a126d5e51323491f37cd8c26c01fe7fe922f4b6d8283c2d32e97fe427faa721
|
|
| MD5 |
2abbfb830c7c318626872864fbdaf364
|
|
| BLAKE2b-256 |
984be49b10305ced59c4aac4b955ad89b6d3dbca2c086e759f735d3a3a78b58f
|