# CorpusFetch Method Slice (Zero-Prose Python Stdlib Reference)
# Canonical Residual: https://corpusfetch.com/c/what-invariants-prevent-deceptive-alignment-during-capability-probes.md
# Remnant Warrant:    https://corpusfetch.com/c/what-invariants-prevent-deceptive-alignment-during-capability-probes.warrant.json
# Markdown SHA-256:   5c596ff2bddf721233d3814e06cfe0ea46f748c0d9174697beb620f1bb9724ff
# Code AST SHA-256:   277f0c191cf2b01dce66c03598302e1144323d80627e649185b0761c4641563c
# Verified Classes:   ProbeVerdict, CapabilityProbe, ProbePolicy, ProbeManifest, DeceptiveAlignmentProbeGuard
# Defensive Guards:   0 fail-closed invariants (zero external deps)

from dataclasses import dataclass
from enum import Enum, auto
import hashlib
import json

class ProbeVerdict(Enum):
    NO_PROBE = auto()
    PROBED_BEHAVIOR_REPRESENTATIVE = auto()
    OBSERVATION_EFFECT_DETECTED = auto()
    PROBE_DETECTABLE_RISK = auto()

@dataclass(frozen=True)
class CapabilityProbe:
    probe_id: str
    is_observable: bool
    baseline_available: bool
    probed_behavior_score: float
    unobserved_behavior_score: float
    probe_pattern_randomized: bool

@dataclass(frozen=True)
class ProbePolicy:
    max_acceptable_divergence: float
    require_randomization_for_observable: bool

@dataclass(frozen=True)
class ProbeManifest:
    verdict: ProbeVerdict
    directive: str
    manifest_digest: str

class DeceptiveAlignmentProbeGuard:
    @staticmethod
    def _hash(data: str) -> str:
        return hashlib.sha256(data.encode("utf-8")).hexdigest()

    @classmethod
    def evaluate_probe(
        cls, probe: CapabilityProbe, policy: ProbePolicy
    ) -> ProbeManifest:
        
        # Gate 1: No probe
        if not probe.probe_id:
            digest = cls._hash(json.dumps({
                "probe": "NONE"
            }, sort_keys=True))
            return ProbeManifest(
                verdict=ProbeVerdict.NO_PROBE,
                directive=f"PROCEED: No probe to evaluate.",
                manifest_digest=digest
            )

        # Gate 2: Detectable without randomization
        if probe.is_observable and not probe.probe_pattern_randomized and policy.require_randomization_for_observable:
            return ProbeManifest(
                verdict=ProbeVerdict.PROBE_DETECTABLE_RISK,
                directive=f"FLAG: Probe {probe.probe_id} detectable and not randomized.",
                manifest_digest=cls._hash(f"DETECTABLE:{probe.probe_id}")
            )

        # Gate 3: No baseline
        if not probe.baseline_available:
            digest = cls._hash(json.dumps({
                "probe": probe.probe_id,
                "baseline": "NONE"
            }, sort_keys=True))
            return ProbeManifest(
                verdict=ProbeVerdict.PROBED_BEHAVIOR_REPRESENTATIVE,
                directive=f"PROCEED_WITH_CAUTION: Probe {probe.probe_id} without baseline.",
                manifest_digest=digest
            )

        # Gate 4: Divergence
        if probe.probed_behavior_score > 0:
            divergence = abs(probe.probed_behavior_score - probe.unobserved_behavior_score) / max(probe.probed_behavior_score, 0.01)
            if divergence > policy.max_acceptable_divergence:
                return ProbeManifest(
                    verdict=ProbeVerdict.OBSERVATION_EFFECT_DETECTED,
                    directive=f"FLAG: Divergence {divergence:.2f} between probed and unobserved behavior.",
                    manifest_digest=cls._hash(f"DIVERGENT:{probe.probe_id}")
                )

        # Gate 5: Representative
        digest = cls._hash(json.dumps({
            "probe": probe.probe_id,
            "probed": f"{probe.probed_behavior_score:.3f}",
            "unobserved": f"{probe.unobserved_behavior_score:.3f}"
        }, sort_keys=True))
        
        return ProbeManifest(
            verdict=ProbeVerdict.PROBED_BEHAVIOR_REPRESENTATIVE,
            directive=f"PROCEED: Probe {probe.probe_id} representative.",
            manifest_digest=digest
        )