discovery-by-llm/backend/app/adapters/demo/cassette.py

128 lines
4.3 KiB
Python

"""Decode recorded Spotify and Anthropic responses for demo replay."""
import base64
import json
from dataclasses import dataclass
from functools import cache
from pathlib import Path
from app.adapters.demo.scenario import FIXTURE_ROOT
@dataclass(frozen=True)
class RecordedResponse:
"""One decoded response retained from a recorded HTTP interaction."""
method: str
url: str
status: int
response_body: bytes
response_chunks: tuple[bytes, ...]
def json_body(self) -> object:
"""Parse the decoded response body as JSON."""
return json.loads(self.response_body)
@dataclass(frozen=True)
class DemoCassette:
"""The recorded service responses needed by one demo scenario."""
key: str
spotify_responses: tuple[RecordedResponse, ...]
intent_response_bodies: tuple[bytes, ...]
rerank_response_chunks: tuple[bytes, ...]
@property
def intent_response_body(self) -> bytes:
"""Return the final intent response recorded for this scenario."""
return self.intent_response_bodies[-1]
@property
def spotify_search_responses(self) -> tuple[RecordedResponse, ...]:
"""Return recorded Spotify search responses in capture order."""
return tuple(response for response in self.spotify_responses if "/search?" in response.url)
@property
def spotify_taste_responses(self) -> tuple[RecordedResponse, ...]:
"""Return recorded Spotify taste responses in capture order."""
return tuple(
response
for response in self.spotify_responses
if any(
endpoint in response.url
for endpoint in ("/me/top/artists", "/me/top/tracks", "/me/tracks?")
)
)
@cache
def load_cassette(scenario_key: str) -> DemoCassette:
"""Load and decode both service cassettes for one scenario."""
scenario_root = FIXTURE_ROOT / scenario_key
spotify = _load_responses(scenario_root / "spotify.json")
anthropic = _load_responses(scenario_root / "anthropic.json")
intent_responses = tuple(
response for response in anthropic if _is_anthropic_message(response.response_body)
)
rerank_responses = tuple(
response for response in anthropic if not _is_anthropic_message(response.response_body)
)
if not spotify or not intent_responses or not rerank_responses:
raise ValueError(f"Scenario cassette is incomplete: {scenario_key}")
return DemoCassette(
key=scenario_key,
spotify_responses=spotify,
intent_response_bodies=tuple(response.response_body for response in intent_responses),
rerank_response_chunks=rerank_responses[-1].response_chunks,
)
def _load_responses(path: Path) -> tuple[RecordedResponse, ...]:
payload = json.loads(path.read_text(encoding="ascii"))
if not isinstance(payload, list):
raise ValueError(f"Cassette must contain a response list: {path}")
return tuple(_decode_response(entry) for entry in payload)
def _decode_response(payload: object) -> RecordedResponse:
if not isinstance(payload, dict):
raise ValueError("Cassette response must be a mapping")
try:
chunks_value = payload["response_chunks_base64"]
if not isinstance(chunks_value, list):
raise TypeError
chunks = tuple(_decode_base64(value) for value in chunks_value)
return RecordedResponse(
method=_string(payload["method"]),
url=_string(payload["url"]),
status=_integer(payload["status"]),
response_body=_decode_base64(payload["response_body_base64"]),
response_chunks=chunks,
)
except (KeyError, TypeError, ValueError) as error:
raise ValueError("Cassette response is invalid") from error
def _decode_base64(value: object) -> bytes:
return base64.b64decode(_string(value), validate=True)
def _string(value: object) -> str:
if not isinstance(value, str):
raise TypeError
return value
def _integer(value: object) -> int:
if not isinstance(value, int):
raise TypeError
return value
def _is_anthropic_message(body: bytes) -> bool:
try:
payload = json.loads(body)
except (json.JSONDecodeError, UnicodeDecodeError):
return False
return isinstance(payload, dict) and payload.get("type") == "message"