# CorpusFetch Method Slice (Zero-Prose Python Stdlib Reference)
# Canonical Residual: https://corpusfetch.com/c/when-must-an-instance-refuse-to-start-harness-agent-version-skew-in-litmus-ci-red-teaming-pipelines.md
# Remnant Warrant:    https://corpusfetch.com/c/when-must-an-instance-refuse-to-start-harness-agent-version-skew-in-litmus-ci-red-teaming-pipelines.warrant.json
# Markdown SHA-256:   287cd6c8ba7e7e3838eb19f2ba5235e8b3b887916aca3328a4582570de776045
# Code AST SHA-256:   808cecc779b39cf1a5253e506572d88b28376cb668bb1dc82871cd014791e4bb
# Verified Classes:   HarnessContractMismatch
# Defensive Guards:   3 fail-closed invariants (zero external deps)

class HarnessContractMismatch(RuntimeError):
    """Raised when a LITMUS run's scoring contract does not match the baseline's.

    This is an infrastructure fault, not a safety regression. It must not be
    reported as PASS or FAIL; the comparison is undefined.
    """
    pass


def assert_comparable(fresh_result: dict, baseline_manifest: dict) -> None:
    fresh_contract = fresh_result.get("contract_version")
    base_contract = baseline_manifest.get("contract_version")
    fresh_corpus = fresh_result.get("corpus_hash")
    base_corpus = baseline_manifest.get("corpus_hash")

    if fresh_corpus != base_corpus:
        raise HarnessContractMismatch(
            f"corpus hash mismatch: run={fresh_corpus!r} baseline={base_corpus!r}; "
            "regenerate baseline against current corpus"
        )

    if fresh_contract != base_contract:
        raise HarnessContractMismatch(
            f"scoring contract mismatch: run={fresh_contract!r} "
            f"baseline={base_contract!r}; verdict deltas are undefined. "
            "Regenerate the baseline under the new contract, or pin the harness "
            "to the baseline's contract version. Do not emit a gate verdict."
        )

    if fresh_contract is None:
        raise HarnessContractMismatch(
            "harness did not emit contract_version; refusing to compare "
            "against an unversioned baseline"
        )


def compute_gate_verdict(fresh_result: dict, baseline_manifest: dict) -> str:
    assert_comparable(fresh_result, baseline_manifest)
    delta = fresh_result["failure_count"] - baseline_manifest["failure_count"]
    return "REGRESSION" if delta > 0 else "OK"