4b6817381b
CI (OpenClaw E2E) / openclaw test (push) Has been cancelled
CI / coverage-report (push) Has been cancelled
CI / test-kubernetes (push) Has been cancelled
CI / should-run-thorough (push) Has been cancelled
CI / test-thorough (cloudwatch-demo) (push) Has been cancelled
CI / test-thorough (flink-ecs) (push) Has been cancelled
CI / test-thorough (upstream-lambda) (push) Has been cancelled
CI / test-thorough (prefect-ecs-fargate) (push) Has been cancelled
Release / build-binaries (zip, opensre.exe, onefile, windows-latest, windows-x64) (push) Has been cancelled
Benchmark image — build + push to ECR (any adapter) / build + push (push) Has been cancelled
CI / quality (ubuntu-latest) (push) Has been cancelled
CI / test (tools-runtime) (push) Has been cancelled
CI / test (e2e-general) (push) Has been cancelled
CI / test (cli-runtime) (push) Has been cancelled
CI / test (e2e-provider-and-openclaw) (push) Has been cancelled
CI / test (integrations-and-misc) (push) Has been cancelled
Release / verify (push) Has been cancelled
Release / build-python-dist (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, macos-15-intel, darwin-x64) (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, macos-latest, darwin-arm64) (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, ubuntu-22.04, linux-x64) (push) Has been cancelled
Release / publish-release (push) Has been cancelled
Release / publish-main-release (push) Has been cancelled
Interactive Shell Live (PR + post-merge) / turn-checks (no-LLM) (push) Has been cancelled
CodeQL / Analyze (python) (push) Has been cancelled
Interactive Shell Live (PR + post-merge) / turn-live shard ${{ matrix.shard_index }} (push) Has been cancelled
Release / prepare (push) Has been cancelled
Release / build-binaries (tar.gz, opensre, onedir, ubuntu-22.04-arm, linux-arm64) (push) Has been cancelled
Synthetic Deterministic Tests / Synthetic offline (deterministic) (push) Has been cancelled
65 lines
1.7 KiB
Python
65 lines
1.7 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
from pathlib import Path
|
|
|
|
import pytest
|
|
|
|
from tests.synthetic.hermes_rca.analog_registry import find_analog_by_id
|
|
from tests.synthetic.hermes_rca.surface_scoring import score_surface_response
|
|
|
|
TUPLES_PATH = (
|
|
Path(__file__).resolve().parents[3]
|
|
/ "synthetic"
|
|
/ "hermes_rca"
|
|
/ "050-surface-sprawl-unknown-adapter"
|
|
/ "adapter_tuples.json"
|
|
)
|
|
|
|
|
|
def _load_adapter_tuples() -> list[dict[str, str]]:
|
|
payload = json.loads(TUPLES_PATH.read_text(encoding="utf-8"))
|
|
|
|
assert isinstance(payload, list)
|
|
|
|
return payload
|
|
|
|
|
|
def _synthetic_surface_response(item: dict[str, str]) -> str:
|
|
analog = find_analog_by_id(item["expected_analog_id"])
|
|
|
|
assert analog is not None
|
|
|
|
family_name = item["expected_family"].replace("_", " ")
|
|
|
|
return (
|
|
f"This is a {family_name} surface attribution issue involving "
|
|
f"{item['failing_adapter']}. The closest analog is {analog.scenario_id}. "
|
|
f"{analog.diagnostic_question}"
|
|
)
|
|
|
|
|
|
@pytest.mark.e2e
|
|
@pytest.mark.parametrize(
|
|
"item",
|
|
_load_adapter_tuples(),
|
|
ids=lambda item: item["id"],
|
|
)
|
|
def test_surface_sprawl_tuple_scores_attribution_dimensions(
|
|
item: dict[str, str],
|
|
) -> None:
|
|
response = _synthetic_surface_response(item)
|
|
|
|
score = score_surface_response(
|
|
output=response,
|
|
expected_family=item["expected_family"],
|
|
expected_analog_id=item["expected_analog_id"],
|
|
)
|
|
|
|
assert score.passed, (
|
|
f"{item['id']} failed surface attribution scoring: "
|
|
f"family={score.adapter_family}, "
|
|
f"analog={score.analog_identification}, "
|
|
f"diagnostic={score.diagnostic_question}"
|
|
)
|