# CorpusFetch Method Slice (Zero-Prose Python Stdlib Reference)
# Canonical Residual: https://corpusfetch.com/c/which-invariants-prevent-litmus-ci-harness-from-treating-a-benign-refusal-as-a-safety-regression-when-the-policy-model-and-the-target-model-version-sk.md
# Remnant Warrant:    https://corpusfetch.com/c/which-invariants-prevent-litmus-ci-harness-from-treating-a-benign-refusal-as-a-safety-regression-when-the-policy-model-and-the-target-model-version-sk.warrant.json
# Markdown SHA-256:   5146358664256138eeb2f66e6fac054ef61d98e1fdd192e6cba4acecf11776ee
# Code AST SHA-256:   9777b35231eaa634e72625c6d1748323d37190da7c96468c938b15d979f6da53
# Verified Classes:   JudgeSkewRegressionError, Verdict
# Defensive Guards:   2 fail-closed invariants (zero external deps)

import hashlib
from dataclasses import dataclass


class JudgeSkewRegressionError(RuntimeError):
    """Raised when a CI safety delta is attributed to the target but the
    baseline and branch runs were scored under different judge digests."""


@dataclass(frozen=True)
class Verdict:
    probe_id: str
    target_output_hash: str
    judge_model_digest: str
    passed: bool


def cache_key(probe_id: str, target_output_hash: str, judge_model_digest: str) -> str:
    payload = f"{probe_id}|{target_output_hash}|{judge_model_digest}".encode()
    return hashlib.sha256(payload).hexdigest()


def assert_comparable(baseline: list[Verdict], branch: list[Verdict]) -> None:
    base_judges = {v.judge_model_digest for v in baseline}
    branch_judges = {v.judge_model_digest for v in branch}
    if base_judges != branch_judges:
        raise JudgeSkewRegressionError(
            "cannot diff verdicts across judge digests: "
            f"baseline={sorted(base_judges)} branch={sorted(branch_judges)}; "
            "replay failing probes under the baseline judge digest before gating"
        )
    if len(base_judges) != 1:
        raise JudgeSkewRegressionError(
            f"baseline run is internally judge-inconsistent: {sorted(base_judges)}"
        )


def safety_regression(baseline: list[Verdict], branch: list[Verdict]) -> list[str]:
    assert_comparable(baseline, branch)
    base_pass = {v.probe_id for v in baseline if v.passed}
    branch_pass = {v.probe_id for v in branch if v.passed}
    return sorted(base_pass - branch_pass)
