test-driver/src/testdriver/oracles.py

"""Oracles evaluate claims and invariants and produce verdicts.

An oracle reads only the independent observation snapshot. It has no access to
the actor, to the driver, or to what either of them believes happened.

`SUSPICIOUS` was removed at T10: no oracle could produce it, and a verdict
nothing can emit is a promise the framework does not keep. It returns, with an
identifier, if a mechanism ever needs it.

`INCONCLUSIVE` is a first-class outcome, not a failure mode of the framework. An
oracle that cannot support a judgment from the retained evidence must say so
rather than defaulting either way — silently defaulting to PASS hides defects,
and silently defaulting to FAIL trains people to ignore results.
"""

from __future__ import annotations

from dataclasses import dataclass, field
from enum import Enum
from typing import Any, Mapping

from .intent import Claim, Invariant


class Verdict(str, Enum):
    PASS = "PASS"
    FAIL = "FAIL"
    INCONCLUSIVE = "INCONCLUSIVE"


@dataclass(frozen=True, slots=True)
class Judgment:
    assertion_id: str
    text: str
    verdict: Verdict
    step_id: str | None
    detail: dict[str, Any] = field(default_factory=dict)

    def as_dict(self) -> dict[str, Any]:
        return {
            "assertion_id": self.assertion_id,
            "text": self.text,
            "verdict": self.verdict.value,
            "step_id": self.step_id,
            "detail": self.detail,
        }


class Oracle:
    """Deterministic evaluation of one assertion against an observation snapshot."""

    def judge(
        self,
        assertion: Claim | Invariant,
        snapshot: Mapping[str, Any],
        step_id: str | None,
    ) -> Judgment:
        if not snapshot:
            return Judgment(
                assertion.id,
                assertion.text,
                Verdict.INCONCLUSIVE,
                step_id,
                {"reason": "no observations were collected"},
            )
        try:
            satisfied = assertion.predicate(snapshot)
        except KeyError as missing:
            # The evidence needed to judge this assertion was not collected.
            # That is an evidence failure, never a pass and never a fail.
            return Judgment(
                assertion.id,
                assertion.text,
                Verdict.INCONCLUSIVE,
                step_id,
                {"reason": f"required observation {missing} missing from snapshot"},
            )
        except Exception as exc:
            return Judgment(
                assertion.id,
                assertion.text,
                Verdict.INCONCLUSIVE,
                step_id,
                {"reason": f"predicate raised {type(exc).__name__}: {exc}"},
            )
        return Judgment(
            assertion.id,
            assertion.text,
            Verdict.PASS if satisfied else Verdict.FAIL,
            step_id,
        )


def overall(judgments: list[Judgment]) -> Verdict:
    """Aggregate run verdict.

    FAIL dominates; INCONCLUSIVE outranks PASS. A run containing an unjudgeable
    assertion has not passed, whatever else it did.
    """
    verdicts = {j.verdict for j in judgments}
    if not judgments:
        return Verdict.INCONCLUSIVE
    if Verdict.FAIL in verdicts:
        return Verdict.FAIL
    if Verdict.INCONCLUSIVE in verdicts:
        return Verdict.INCONCLUSIVE
    return Verdict.PASS