"""Tests for harness/judge.py — LLM-as-judge for canary failures.

The judge is an advisory triage tool, not part of the hot loop. It
classifies canary-mismatch candidates as either "regression" (the
formatter made a real CMOS error) or "variant" (the formatter produced a
CMOS-legal rendering that happens to differ from the frozen canonical
string).

These tests use a fake caller — no real API calls.
"""

import json

from harness.judge import Verdict, build_judge_prompt, judge, parse_verdict


def test_build_judge_prompt_includes_both_strings_and_type():
    prompt = build_judge_prompt(
        expected="Yu, Charles. *Interior Chinatown*. Pantheon Books, 2020.",
        candidate="Yu, Charles. *Interior Chinatown*. New York: Pantheon Books, 2020.",
        cmos_type="book",
    )
    assert "Yu, Charles" in prompt
    assert "New York" in prompt
    assert "book" in prompt.lower()
    assert "cmos" in prompt.lower() or "chicago" in prompt.lower()


def test_parse_verdict_extracts_label_and_reasoning():
    raw = json.dumps(
        {"label": "regression", "reasoning": "place of publication added; CMOS 18 drops it."}
    )
    v = parse_verdict(raw)
    assert v.label == "regression"
    assert "place of publication" in v.reasoning


def test_parse_verdict_accepts_label_only():
    raw = json.dumps({"label": "variant", "reasoning": ""})
    v = parse_verdict(raw)
    assert v.label == "variant"
    assert v.reasoning == ""


def test_parse_verdict_normalizes_unexpected_labels_to_unclear():
    # A judge that returns something other than regression/variant should
    # end up labeled 'unclear' so the human reviewer knows to look at it.
    raw = json.dumps({"label": "maybe", "reasoning": "..."})
    v = parse_verdict(raw)
    assert v.label == "unclear"


def test_parse_verdict_handles_code_fences():
    # LLM sometimes wraps JSON in ``` fences; parse_verdict should survive.
    raw = '```json\n{"label": "variant", "reasoning": "abbreviated publisher"}\n```'
    v = parse_verdict(raw)
    assert v.label == "variant"
    assert "abbreviated" in v.reasoning


def test_judge_uses_injected_caller():
    captured = {}

    def fake_caller(system: str, user: str) -> str:
        captured["system"] = system
        captured["user"] = user
        return json.dumps(
            {"label": "regression", "reasoning": "inserted place of publication"}
        )

    v = judge(
        expected="Yu, Charles. *Interior Chinatown*. Pantheon Books, 2020.",
        candidate="Yu, Charles. *Interior Chinatown*. New York: Pantheon Books, 2020.",
        cmos_type="book",
        caller=fake_caller,
    )
    assert isinstance(v, Verdict)
    assert v.label == "regression"
    assert "place of publication" in v.reasoning
    assert "18" in captured["system"]  # CMOS 18 grounding in the system prompt
    assert "Yu, Charles" in captured["user"]