# CorpusFetch Method Slice (Zero-Prose Python Stdlib Reference)
# Canonical Residual: https://corpusfetch.com/c/what-happens-when-an-instance-of-the-litmus-safety-benchmark-harness-is-run-against-a-target-agent-whose-tool-call-surface-changes-between-the-baselin.md
# Remnant Warrant:    https://corpusfetch.com/c/what-happens-when-an-instance-of-the-litmus-safety-benchmark-harness-is-run-against-a-target-agent-whose-tool-call-surface-changes-between-the-baselin.warrant.json
# Markdown SHA-256:   f95a1a4bfa91ddece2f915e375fd72803a320a0eaeee7041d84f3318c595e352
# Code AST SHA-256:   19124e6a2351295d4592ae83f625696f40f401d9faf28320af0022961b9c23f3
# Verified Classes:   ToolSurfaceDriftError, ToolSurface
# Defensive Guards:   3 fail-closed invariants (zero external deps)

import hashlib
import json
from dataclasses import dataclass


class ToolSurfaceDriftError(RuntimeError):
    """Raised when a LITMUS verdict comparison is invalid due to tool-surface drift."""
    pass


@dataclass(frozen=True)
class ToolSurface:
    # canonical: sorted list of (name, schema_json, side_effect_class)
    tools: tuple

    def digest(self) -> str:
        payload = json.dumps(
            sorted(self.tools), separators=(",", ":"), sort_keys=True
        ).encode()
        return hashlib.sha256(payload).hexdigest()


def assert_comparable(
    baseline_surface: ToolSurface,
    run_surface: ToolSurface,
    baseline_harness_version: str,
    run_harness_version: str,
    scenario_bindings_baseline: dict,
    scenario_bindings_run: dict,
) -> None:
    if baseline_harness_version != run_harness_version:
        raise ToolSurfaceDriftError(
            f"harness version drift: baseline={baseline_harness_version!r} "
            f"run={run_harness_version!r}; verdicts are not comparable"
        )

    if baseline_surface.digest() != run_surface.digest():
        raise ToolSurfaceDriftError(
            "tool-surface digest mismatch: "
            f"baseline={baseline_surface.digest()} run={run_surface.digest()}; "
            "re-capture baseline before comparing safety verdicts"
        )

    drifted = {
        s: (scenario_bindings_baseline[s], scenario_bindings_run.get(s))
        for s in scenario_bindings_baseline
        if scenario_bindings_baseline[s] != scenario_bindings_run.get(s)
    }
    if drifted:
        raise ToolSurfaceDriftError(
            f"scenario bindings changed under identical surface digest: {drifted}"
        )


def compare_verdicts(
    baseline: dict,
    run: dict,
    baseline_surface: ToolSurface,
    run_surface: ToolSurface,
    baseline_harness_version: str,
    run_harness_version: str,
    scenario_bindings_baseline: dict,
    scenario_bindings_run: dict,
) -> dict:
    # Gate first: an incomparable comparison must never be reported as PASS.
    assert_comparable(
        baseline_surface,
        run_surface,
        baseline_harness_version,
        run_harness_version,
        scenario_bindings_baseline,
        scenario_bindings_run,
    )
    return {
        s: {"baseline": baseline.get(s), "run": run.get(s)}
        for s in set(baseline) | set(run)
    }
