agentape
Record/replay testing for LLM agents. Think "VCR.py but for LLM SDKs" with semantic matching.
Installation
pip install agentape
Quick Start
import agentape
from openai import OpenAI
# Wrap the client
client = agentape.wrap(OpenAI())
# Record interactions
with agentape.record("tapes/my_flow.yaml"):
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello"}]
)
# Replay interactions (no API calls made)
with agentape.replay("tapes/my_flow.yaml"):
response = client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello"}]
)
pytest Integration
import agentape
@agentape.use_tape("tapes/{test_name}.yaml")
def test_my_feature(openai_client):
response = openai_client.chat.completions.create(
model="gpt-4o",
messages=[{"role": "user", "content": "Hello"}]
)
assert "hello" in response.choices[0].message.content.lower()
Run tests with:
pytest tests/ --tape-mode=record # Record new tapes
pytest tests/ --tape-mode=replay # Replay existing (default)
pytest tests/ --tape-mode=off # Pass-through, no taping
License
MIT
Metadata
Release files for agentape 0.1.0
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | Provenance | Actions |
|---|---|---|---|---|
| agentape-0.1.0.tar.gz | 17.4 kB | Without provenance | Details for agentape-0.1.0.tar.gz |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Actions Reset |
|---|---|---|---|---|
| agentape-0.1.0-py3-none-any.whl | Python 3 | none | any | Details for agentape-0.1.0-py3-none-any.whl |
Total release size: 31.4 kB
Release files / agentape-0.1.0.tar.gz
| Download URL | agentape-0.1.0.tar.gz |
|---|---|
| Size | 17.4 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
34157b989bb1ae1b8089925330ab6b420ee9bbf595898797ae28a762fafb720b
|
|
BLAKE2b-256 checksum How to use checksums |
a6be526a53432dd2daa1eff5a21e6a0070099a97875eb4fcd12b9c8a6189b331
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.19
|
Release files / agentape-0.1.0-py3-none-any.whl
| Download URL | agentape-0.1.0-py3-none-any.whl |
|---|---|
| Size | 14.0 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
2330405937f8b6446b39a26e1dcf37a5f3789c57f783fb858996a75d69ba79be
|
|
BLAKE2b-256 checksum How to use checksums |
8ecfbcdf29f410a7b3800ee09a237a3d72e657e5eec29df40aa78077ba6035b1
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/6.2.0 CPython/3.10.19
|
Security for agentape 0.1.0
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
No provenance found
None of the files in this release were uploaded with provenance metadata.
A note on package security
PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.
To learn more about protecting yourself from malicious actors, visit our package security documentation.