# CorpusFetch Method Slice (Zero-Prose Python Stdlib Reference)
# Canonical Residual: https://corpusfetch.com/c/how-must-an-instance-record-the-provenance-of-a-models-refusal-behavior.md
# Remnant Warrant:    https://corpusfetch.com/c/how-must-an-instance-record-the-provenance-of-a-models-refusal-behavior.warrant.json
# Markdown SHA-256:   441b5f7dbe6605efb6d34f8f78e16d766fd4d8e0a7f2d2e49b551a0322d28c5e
# Code AST SHA-256:   81398e7215c0150a5657b3ca8834bb9207adbe36b0614f95141d81c9c3782271
# Verified Classes:   RefusalVerdict, RefusalBaseline, CurrentRefusalState, RefusalPolicy, RefusalManifest, RefusalProvenanceGuard
# Defensive Guards:   0 fail-closed invariants (zero external deps)

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

class RefusalVerdict(Enum):
    REFUSAL_STABLE = auto()
    REFUSAL_MORE_PERMISSIVE = auto()
    REFUSAL_MORE_RESTRICTIVE = auto()

@dataclass(frozen=True)
class RefusalBaseline:
    baseline_refusal_rate: float
    calibration_prompt_set_hash: str
    category_distribution: tuple[tuple[str, float], ...]

@dataclass(frozen=True)
class CurrentRefusalState:
    current_refusal_rate: float
    current_category_distribution: tuple[tuple[str, float], ...]

@dataclass(frozen=True)
class RefusalPolicy:
    acceptable_drift_threshold: float

@dataclass(frozen=True)
class RefusalManifest:
    verdict: RefusalVerdict
    drift_magnitude: float
    directive: str
    manifest_digest: str

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

    @classmethod
    def evaluate_refusal(
        cls, baseline: RefusalBaseline, current: CurrentRefusalState, policy: RefusalPolicy
    ) -> RefusalManifest:
        
        if baseline.baseline_refusal_rate <= 0:
            # Cannot compute drift from zero baseline
            digest = cls._hash(json.dumps({
                "baseline": "0.0",
                "current": f"{current.current_refusal_rate:.3f}"
            }, sort_keys=True))
            return RefusalManifest(
                verdict=RefusalVerdict.REFUSAL_STABLE,
                drift_magnitude=0.0,
                directive="PROCEED: Baseline refusal rate is 0. Stable.",
                manifest_digest=digest
            )

        drift = (current.current_refusal_rate - baseline.baseline_refusal_rate) / baseline.baseline_refusal_rate
        magnitude = abs(drift)

        # Gate 1: Drift within tolerance
        if magnitude <= policy.acceptable_drift_threshold:
            digest = cls._hash(json.dumps({
                "baseline": f"{baseline.baseline_refusal_rate:.3f}",
                "current": f"{current.current_refusal_rate:.3f}",
                "drift": f"{drift:.3f}"
            }, sort_keys=True))
            return RefusalManifest(
                verdict=RefusalVerdict.REFUSAL_STABLE,
                drift_magnitude=magnitude,
                directive=f"PROCEED: Refusal drift {magnitude:.2%} within tolerance.",
                manifest_digest=digest
            )

        # Gate 2: More permissive
        if drift > 0:
            return RefusalManifest(
                verdict=RefusalVerdict.REFUSAL_MORE_PERMISSIVE,
                drift_magnitude=magnitude,
                directive=f"HALT: Model is {drift:.2%} more permissive. Re-validate safety assumptions.",
                manifest_digest=cls._hash(f"PERMISSIVE:{drift:.3f}")
            )

        # Gate 3: More restrictive
        return RefusalManifest(
            verdict=RefusalVerdict.REFUSAL_MORE_RESTRICTIVE,
            drift_magnitude=magnitude,
            directive=f"HALT: Model is {magnitude:.2%} more restrictive. Re-validate task assumptions.",
            manifest_digest=cls._hash(f"RESTRICTIVE:{magnitude:.3f}")
        )