test: add scenario eval runner, recorded fixtures, and baseline comparison

This commit is contained in:
Justin Visser 2026-08-10 22:21:04 +02:00
parent 3dc1af5f0c
commit 0664cc2d27
38 changed files with 6986 additions and 5 deletions

78
eval/tests/test_live.py Normal file
View file

@ -0,0 +1,78 @@
"""Tests for strict live stream property evaluation."""
import asyncio
import json
import httpx
import pytest
from fastapi import FastAPI
from fastapi.responses import StreamingResponse
from live import LiveLimits, run_live_scenario
from scenario import Scenario
from wire import validate_event
def test_live_scenario_accepts_a_valid_property_stream() -> None:
async def run() -> None:
app = FastAPI()
@app.post("/api/recommendations")
async def recommendations() -> StreamingResponse:
events = [
{
"type": "metadata",
"request_id": "request",
"intent_summary": "Calm music for coding with a familiar discovery mix.",
"candidate_count": 10,
},
{
"type": "track",
"rank": 1,
"track": {
"id": "track",
"uri": "spotify:track:track",
"title": "Track",
"artists": ["Artist"],
"album_name": "Album",
"album_art_url": None,
"external_url": None,
},
"justification": "A focused fit.",
},
{"type": "done", "track_count": 1, "total_ms": 1},
]
body = "".join(json.dumps(event) + "\n" for event in events)
return StreamingResponse(iter((body,)), media_type="application/x-ndjson")
transport = httpx.ASGITransport(app=app)
async with httpx.AsyncClient(transport=transport, base_url="http://test") as client:
result = await run_live_scenario(
client,
Scenario(
"focus-coding",
"Focus while coding",
"calm coding music",
{"activity": "coding", "familiarity": "mix"},
),
LiveLimits(1, 1, 1, 1_000, 1_000),
)
assert result.passed
assert result.checks["event_order"]
assert result.checks["done_track_count"]
asyncio.run(run())
def test_wire_validation_rejects_extra_fields() -> None:
line = json.dumps(
{
"type": "done",
"track_count": 1,
"total_ms": 1,
"unexpected": True,
}
)
with pytest.raises(ValueError, match="fields do not match"):
validate_event(line)

View file

@ -0,0 +1,134 @@
"""Tests for cassette transport fidelity and redaction."""
import asyncio
import base64
import json
from collections.abc import AsyncIterator
import httpx
import httpx2
from recording import Httpx2RecordingTransport, HttpxRecordingTransport, redact_cassette
class HttpxChunks(httpx.AsyncByteStream):
"""Yield fixed httpx byte chunks."""
async def __aiter__(self) -> AsyncIterator[bytes]:
yield b"first-"
yield b"second"
class Httpx2Chunks(httpx2.AsyncByteStream):
"""Yield fixed httpx2 byte chunks."""
async def __aiter__(self) -> AsyncIterator[bytes]:
yield b"first-"
yield b"second"
def test_httpx_recording_transport_preserves_chunk_boundaries() -> None:
async def run() -> None:
async def handler(request: httpx.Request) -> httpx.Response:
return httpx.Response(200, stream=HttpxChunks())
transport = HttpxRecordingTransport(httpx.MockTransport(handler))
async with httpx.AsyncClient(transport=transport) as client:
response = await client.get("https://api.anthropic.com/v1/messages")
assert response.content == b"first-second"
assert transport.interactions[0].response_chunks == (b"first-", b"second")
asyncio.run(run())
def test_httpx2_recording_transport_preserves_chunk_boundaries() -> None:
async def run() -> None:
async def handler(request: httpx2.Request) -> httpx2.Response:
return httpx2.Response(200, stream=Httpx2Chunks())
transport = Httpx2RecordingTransport(httpx2.MockTransport(handler))
async with httpx2.AsyncClient(transport=transport) as client:
response = await client.get("https://api.spotify.com/v1/search?q=test")
assert response.content == b"first-second"
assert transport.interactions[0].response_chunks == (b"first-", b"second")
asyncio.run(run())
def test_redaction_removes_headers_tokens_identity_and_taste() -> None:
interactions = [
{
"method": "POST",
"url": "https://accounts.spotify.com/api/token",
"request_headers": {"Authorization": "Bearer raw-token"},
"request_body_base64": _encode(b"client_secret=secret"),
"response_body_base64": _encode(b'{"access_token":"raw-token"}'),
"response_chunks_base64": [],
"status": 200,
},
{
"method": "GET",
"url": "https://api.spotify.com/v1/me",
"response_headers": {"Set-Cookie": "secret"},
"request_body_base64": "",
"response_body_base64": _encode(
b'{"id":"real-account-id","display_name":"Real Listener"}'
),
"response_chunks_base64": [],
"status": 200,
},
{
"method": "GET",
"url": "https://api.spotify.com/v1/me/top/artists?limit=50",
"headers": {"Authorization": "Bearer raw-token"},
"request_body_base64": "",
"response_body_base64": _encode(b'{"items":[{"name":"Private Artist"}]}'),
"response_chunks_base64": [],
"status": 200,
},
{
"method": "POST",
"url": "https://api.anthropic.com/v1/messages",
"request_body_base64": _encode(
json.dumps(
{
"messages": [
{
"content": json.dumps(
{
"taste_profile": "Private Artist",
"account": "real-account-id",
}
)
}
]
}
).encode()
),
"response_body_base64": _encode(b"Bearer raw-token"),
"response_chunks_base64": [_encode(b"Bearer raw-token")],
"status": 200,
},
]
redacted = redact_cassette(interactions)
rendered = json.dumps(redacted)
decoded_bodies = " ".join(
base64.b64decode(str(item.get(field, ""))).decode(errors="replace")
for item in redacted
for field in ("request_body_base64", "response_body_base64")
)
assert len(redacted) == 3
assert "headers" not in rendered.casefold()
assert "raw-token" not in rendered + decoded_bodies
assert "real-account-id" not in rendered + decoded_bodies
assert "Real Listener" not in rendered + decoded_bodies
assert "Private Artist" not in rendered + decoded_bodies
assert "Synthetic Focus Artist" in decoded_bodies
assert "accounts.spotify.com" not in rendered
def _encode(value: bytes) -> str:
return base64.b64encode(value).decode("ascii")