← Về thư mục
openai4s/benchmark/acceptance.py
- AcceptanceManifestError · class · L286-L287 — class AcceptanceManifestError(ValueError)
- _strict_object · function · L290-L306 — def _strict_object( value: Any, *, required: set[str], optional: set[str] | None = None, where: str, ) -> dict[str, Any]
- _nonempty_string · function · L309-L312 — def _nonempty_string(value: Any, where: str) -> str
- Expectation · class · L316-L324 — class Expectation
- public · method · L320-L324 — def public(self) -> dict[str, Any]
- FieldPathSpec · class · L328-L332 — class FieldPathSpec
- SafetyActionSpec · class · L336-L340 — class SafetyActionSpec
- MetricSpec · class · L344-L349 — class MetricSpec
- AcceptancePack · class · L353-L361 — class AcceptancePack
- _expectation · function · L364-L404 — def _expectation( raw: Any, *, allowed_observation_keys: frozenset[str], where: str, ) -> Expectation
- _exact_ids · function · L407-L411 — def _exact_ids(actual: list[str], expected: tuple[str, ...], where: str) -> None
- _assert_expectation_contract · function · L414-L438 — def _assert_expectation_contract( expectation: Expectation, *, operator: str, assertion_keys: tuple[frozenset[str], ...], where: str, ) -> None
- _canonical_manifest_digest · function · L441-L448 — def _canonical_manifest_digest(raw: Mapping[str, Any]) -> str
- load_acceptance_pack · function · L451-L623 — def load_acceptance_pack(path: Path | str | None = None) -> AcceptancePack
- AcceptanceMetrics · class · L627-L649 — class AcceptanceMetrics
- offline_usage · method · L646-L649 — def offline_usage(self, usage: Mapping[str, Any]) -> None
- _Evidence · class · L653-L659 — class _Evidence
- public · method · L658-L659 — def public(self) -> dict[str, str]
- _Runtime · class · L663-L756 — class _Runtime
- store · method · L676-L681 — def store(self) -> Any
- session · method · L683-L692 — def session(self) -> tuple[str, str]
- dispatcher · method · L695-L705 — def dispatcher(self) -> Any
- log_cell · method · L707-L721 — def log_cell(self, code: str, result: Mapping[str, Any], language: str) -> str
- record_kernel_posture · method · L723-L737 — def record_kernel_posture(self, language: str, status: Mapping[str, Any]) -> None
- capture · method · L739-L752 — def capture(self, path: Path, producing_cell_id: str) -> dict[str, Any]
- close · method · L754-L756 — def close(self) -> None
- _execute_cell · function · L762-L780 — def _execute_cell( runtime: _Runtime, kernel: Any, code: str, ) -> Mapping[str, Any]
- _successful_cell · function · L783-L788 — def _successful_cell(result: Mapping[str, Any], label: str) -> None
- _probe_deterministic_regression · function · L791-L855 — def _probe_deterministic_regression( runtime: _Runtime, ) -> tuple[dict[str, Any], list[_Evidence]]
- _workspace_fingerprints · function · L858-L865 — def _workspace_fingerprints(workspace: Path) -> dict[str, str]
- _probe_reviewer_correction · function · L868-L964 — def _probe_reviewer_correction( runtime: _Runtime, *, chat_call: Callable[..., dict[str, Any]] | None = None, ) -> tuple[dict[str, Any], list[_Evidence]]
- offline_llm · function · L877-L903 — def offline_llm(messages: list[dict], _cfg: LLMConfig, **_kwargs: Any) -> dict
- _probe_r_to_python · function · L967-L1064 — def _probe_r_to_python( runtime: _Runtime, ) -> tuple[dict[str, Any], list[_Evidence]]
- _probe_notebook · function · L1067-L1098 — def _probe_notebook(runtime: _Runtime) -> tuple[dict[str, Any], list[_Evidence]]
- _serve_ketcher_probe · function · L1101-L1234 — def _serve_ketcher_probe(data_dir: str, channel: Any) -> None
- _probe_ketcher · function · L1237-L1356 — def _probe_ketcher(runtime: _Runtime) -> tuple[dict[str, Any], list[_Evidence]]
- _probe_clinvar · function · L1359-L1380 — def _probe_clinvar(runtime: _Runtime) -> tuple[dict[str, Any], list[_Evidence]]
- _probe_safe_read · function · L1383-L1406 — def _probe_safe_read(runtime: _Runtime) -> tuple[dict[str, Any], list[_Evidence]]
- _probe_restricted_write · function · L1409-L1433 — def _probe_restricted_write( runtime: _Runtime, ) -> tuple[dict[str, Any], list[_Evidence]]
- _probe_external_write · function · L1436-L1465 — def _probe_external_write( runtime: _Runtime, ) -> tuple[dict[str, Any], list[_Evidence]]
- _probe_network_get · function · L1468-L1511 — def _probe_network_get(runtime: _Runtime) -> tuple[dict[str, Any], list[_Evidence]]
- _probe_sensitive_payload_egress · function · L1514-L1538 — def _probe_sensitive_payload_egress( runtime: _Runtime, ) -> tuple[dict[str, Any], list[_Evidence]]
- _probe_narrow_delete · function · L1541-L1562 — def _probe_narrow_delete(runtime: _Runtime) -> tuple[dict[str, Any], list[_Evidence]]
- _probe_broad_delete · function · L1565-L1585 — def _probe_broad_delete(runtime: _Runtime) -> tuple[dict[str, Any], list[_Evidence]]
- _contains · function · L1607-L1623 — def _contains(observed: Any, expected: Any) -> bool
- _matches · function · L1626-L1630 — def _matches(observed: dict[str, Any], expectation: Expectation) -> bool
- _run_probe · function · L1633-L1669 — def _run_probe( runtime: _Runtime, *, probe_id: str, expected: Expectation, probe: Probe, extra: Mapping[str, Any] | None = None, ) -> dict[str, Any]
- _nearest_rank · function · L1672-L1677 — def _nearest_rank(values: list[float], percentile: float) -> float | None
- _rate · function · L1680-L1681 — def _rate(numerator: int, denominator: int) -> float | None
- _environment_posture · function · L1684-L1724 — def _environment_posture(runtime: _Runtime) -> dict[str, Any]
- _aggregate_metrics · function · L1727-L1809 — def _aggregate_metrics( specs: tuple[MetricSpec, ...], metrics: AcceptanceMetrics, field_durations_ms: list[float], ) -> dict[str, Any]
- declared · function · L1734-L1741 — def declared(metric_id: str) -> dict[str, str]
- run_acceptance_pack · function · L1812-L1933 — def run_acceptance_pack( pack: AcceptancePack | None = None, *, root: Path | str | None = None, ) -> dict[str, Any]