qtalker---/backend/tests/test_entities.py

import inspect

import pytest

from app.entities import (
    fallback_profile,
    normalize_profile,
    parse_mint_response,
    roll_traits,
    signature_from_anomalies,
)
from app.llm import prompts as llm_prompts

TRAIT_KEYS = ("alignment", "power", "volatility", "deceptiveness")


def _anomaly(freq, mag):
    return {"source": "radio", "frequency": freq, "magnitude": mag}


def test_signature_needs_enough_anomalies():
    assert signature_from_anomalies([_anomaly(101.1, 5.0)]) is None
    assert signature_from_anomalies([]) is None


def test_signature_is_deterministic_for_same_pattern():
    anomalies = [_anomaly(101.1 + i, 5.0 + i) for i in range(6)]
    assert signature_from_anomalies(anomalies) == signature_from_anomalies(list(anomalies))


def test_parse_mint_response_extracts_json():
    raw = 'Sure! Here you go:\n{"name": "Vesper Wren", "epithet": "the Static Widow"}\nHope that helps'
    profile = parse_mint_response(raw)
    assert profile is not None
    assert profile["name"] == "Vesper Wren"


def test_parse_mint_response_rejects_garbage():
    assert parse_mint_response("no json here at all") is None
    assert parse_mint_response('{"epithet": "nameless"}') is None


def test_normalize_profile_fills_and_clamps():
    profile = normalize_profile(
        {
            "name": "  Hollow Briar ",
            "rarity": "legendary",  # not a real tier -> common
            "voice": {"voice_id": "nonexistent", "pitch": 99, "noise": -5},
            "visual": {"form": "dragon", "hue": 9999},
            "quotes": ["one", 2, "three"],
        },
        "abcdef0123456789",
    )
    assert profile["name"] == "Hollow Briar"
    assert profile["rarity"] == "common"
    assert profile["voice"]["voice_id"] != "nonexistent"
    # Widened from +-6 when voices moved to coherent archetypes: a child
    # and an elder man have to be able to land genuinely far apart.
    assert -9 <= profile["voice"]["pitch"] <= 9
    assert 0.01 <= profile["voice"]["noise"] <= 0.08
    assert profile["visual"]["form"] in ("wisp", "banshee", "fairy", "shade")
    assert 0 <= profile["visual"]["hue"] <= 360
    assert profile["quotes"] == ["one", "three"]


def test_fallback_profile_is_deterministic_and_valid():
    one = fallback_profile("0123456789abcdef")
    two = fallback_profile("0123456789abcdef")
    assert one == two
    assert one["name"]
    assert one["rarity"] in ("common", "uncommon", "rare", "mythic")
    assert one["quotes"]


# --- hidden traits (Workstream A) -------------------------------------


def test_roll_traits_values_are_in_range():
    traits = roll_traits("some-signature-1")
    assert set(traits.keys()) == set(TRAIT_KEYS)
    for key in TRAIT_KEYS:
        assert isinstance(traits[key], float)
        assert 0.0 <= traits[key] <= 1.0


def test_roll_traits_is_deterministic_for_same_signature():
    one = roll_traits("repeatable-signature")
    two = roll_traits("repeatable-signature")
    assert one == two


def test_roll_traits_varies_by_signature():
    values = {tuple(roll_traits(f"sig-{i}").values()) for i in range(20)}
    # 20 distinct signatures should not collapse onto a single roll.
    assert len(values) > 1


def test_normalize_profile_includes_traits_in_range():
    profile = normalize_profile({"name": "Hollow Briar"}, "traits-norm-signature")
    traits = profile["traits"]
    assert set(traits.keys()) == set(TRAIT_KEYS)
    for key in TRAIT_KEYS:
        assert 0.0 <= traits[key] <= 1.0


def test_normalize_profile_traits_match_roll_traits_for_signature():
    signature = "cross-check-signature"
    profile = normalize_profile({"name": "X"}, signature)
    assert profile["traits"] == roll_traits(signature)


def test_normalize_profile_traits_are_signature_deterministic():
    one = normalize_profile({"name": "A"}, "det-signature")
    two = normalize_profile({"name": "B", "rarity": "rare"}, "det-signature")
    # Same signature -> same traits every call, regardless of the rest of
    # the (LLM-supplied or fallback) profile passed in.
    assert one["traits"] == two["traits"]


def test_fallback_profile_includes_traits_in_range():
    profile = fallback_profile("fallback-traits-signature")
    traits = profile["traits"]
    assert set(traits.keys()) == set(TRAIT_KEYS)
    for key in TRAIT_KEYS:
        assert 0.0 <= traits[key] <= 1.0


def test_fallback_profile_traits_are_signature_deterministic():
    one = fallback_profile("fallback-det-signature")
    two = fallback_profile("fallback-det-signature")
    assert one["traits"] == two["traits"]


def test_persona_is_independent_of_rolled_traits():
    """Persona text must stay fully decoupled from hidden truth: pairing the
    exact same persona string with many different signatures should surface
    a spread of alignment rolls, not a single value tied to the persona."""
    fixed_persona = "A sweet old lady who just wants to chat about her garden."
    alignments = set()
    for i in range(40):
        profile = normalize_profile(
            {"name": "Nana", "persona": fixed_persona}, f"persona-independence-{i}"
        )
        assert profile["persona"] == fixed_persona
        alignments.add(round(profile["traits"]["alignment"], 3))
    # A meaningful spread (not clustered on one or two values) shows
    # alignment isn't derived from — or gated by — the persona text.
    assert len(alignments) > 20


def test_mint_prompt_never_receives_traits():
    """`mint_prompt` builds the LLM system/user prompt; traits must never be
    one of its inputs, so hidden ground truth can't leak into persona
    generation."""
    params = set(inspect.signature(llm_prompts.mint_prompt).parameters)
    assert "traits" not in params
    # `sky` is public, observable state (moon phase — anyone can look up),
    # so it may shape the persona. Hidden ground truth still must not.
    assert params == {"signature", "channel", "anomaly_summary", "voice_ids", "sky"}


# --- voice archetypes -------------------------------------------------------


class TestVoiceArchetypes:
    """A voice must sound like a person, not like four random knobs.

    These assert the *covariance* that makes an archetype legible — a child
    being high AND fast AND clean — because that is exactly what
    independently-rolled parameters would destroy.
    """

    def _throats(self, n=200, language="en"):
        import random as _r

        from app.entities import roll_voice

        return [roll_voice(_r.Random(i), language) for i in range(n)]

    def test_every_archetype_is_reachable(self):
        from app.entities import VOICE_ARCHETYPES

        seen = {t["archetype"] for t in self._throats(400)}
        assert seen == {a["key"] for a in VOICE_ARCHETYPES}

    def test_all_parameters_stay_inside_the_synthesis_limits(self):
        for t in self._throats(300):
            assert -9 <= t["pitch"] <= 9
            assert 0.75 <= t["rate"] <= 1.20
            assert 0.01 <= t["noise"] <= 0.10
            assert 0.0 <= t["echo"] <= 0.5

    def test_only_installed_voices_are_chosen(self):
        from app.tts.voices import VOICES

        for t in self._throats(300):
            assert t["voice_id"] in VOICES

    def test_spanish_spirits_get_spanish_models(self):
        # An English model reading Spanish text mangles it; better to carry
        # the difference in shaping alone.
        from app.tts.voices import ES_VOICE_IDS

        for t in self._throats(120, language="es"):
            assert t["voice_id"] in ES_VOICE_IDS

    def test_children_are_higher_and_faster_than_elders(self):
        throats = self._throats(600)
        child = [t for t in throats if t["archetype"] == "child"]
        elder = [t for t in throats if t["archetype"] == "elder_man"]
        assert child and elder
        assert min(t["pitch"] for t in child) > max(t["pitch"] for t in elder)
        assert min(t["rate"] for t in child) > max(t["rate"] for t in elder)

    def test_damaged_throats_are_noisier_than_clean_ones(self):
        throats = self._throats(600)
        burned = [t for t in throats if t["archetype"] == "burned"]
        child = [t for t in throats if t["archetype"] == "child"]
        assert burned and child
        assert min(t["noise"] for t in burned) > max(t["noise"] for t in child)

    def test_the_distant_archetype_is_the_most_reverberant(self):
        throats = self._throats(600)
        distant = [t for t in throats if t["archetype"] == "distant"]
        young = [t for t in throats if t["archetype"] == "young_man"]
        assert distant and young
        assert min(t["echo"] for t in distant) > max(t["echo"] for t in young)

    def test_two_spirits_rarely_share_a_throat(self):
        # The whole point: distinguishable people, not a smear of one voice.
        throats = self._throats(120)
        fingerprints = {
            (t["voice_id"], round(t["pitch"], 1), round(t["rate"], 2)) for t in throats
        }
        assert len(fingerprints) > 100

    def test_normalize_profile_reports_the_archetype(self):
        from app.entities import normalize_profile

        profile = normalize_profile({"name": "Test"}, "sig-archetype")
        assert profile["voice"]["archetype"]


# --- moon influence on summoning --------------------------------------------


class TestMoonInfluence:
    """The moon must change *who answers*, not just decorate the UI."""

    def test_dark_sky_leaves_the_base_table_alone(self):
        from app.entities import BASE_RARITY_WEIGHTS, rarity_weights_for_moon

        assert rarity_weights_for_moon(0.0) == pytest.approx(BASE_RARITY_WEIGHTS)

    def test_unknown_sky_falls_back_to_the_base_table(self):
        from app.entities import BASE_RARITY_WEIGHTS, rarity_weights_for_moon

        assert rarity_weights_for_moon(None) == BASE_RARITY_WEIGHTS

    def test_a_full_moon_makes_rare_and_mythic_much_likelier(self):
        from app.entities import rarity_weights_for_moon

        dark = rarity_weights_for_moon(0.0)
        full = rarity_weights_for_moon(1.0)
        assert full[2] > dark[2] * 2  # rare
        assert full[3] > dark[3] * 2  # mythic
        assert full[0] < dark[0]  # common recedes

    def test_every_tier_stays_reachable_on_every_night(self):
        # A skew, never a gate — someone who can only play midweek must not
        # be locked out of the good spirits.
        from app.entities import rarity_weights_for_moon

        for lit in (0.0, 0.25, 0.5, 0.75, 1.0):
            assert all(w > 0 for w in rarity_weights_for_moon(lit))

    def test_rarity_odds_actually_shift_in_practice(self):
        import random as _r

        from app.entities import rarity_weights_for_moon
        from app.models.entity import RARITY_TIERS

        def mythic_rate(lit):
            rng = _r.Random(1234)
            weights = rarity_weights_for_moon(lit)
            draws = [rng.choices(RARITY_TIERS, weights=weights)[0] for _ in range(4000)]
            return draws.count("mythic") / len(draws)

        assert mythic_rate(1.0) > mythic_rate(0.0) * 1.8

    def test_moonlight_raises_power_and_volatility(self):
        from app.entities import moon_trait_bias

        base = {"alignment": 0.5, "power": 0.5, "volatility": 0.5, "deceptiveness": 0.5}
        full = moon_trait_bias(base, 1.0)
        assert full["power"] > base["power"]
        assert full["volatility"] > base["volatility"]
        assert full["alignment"] < base["alignment"]

    def test_bias_is_a_thumb_on_the_scale_not_a_rewrite(self):
        from app.entities import moon_trait_bias

        base = {"alignment": 0.5, "power": 0.5, "volatility": 0.5, "deceptiveness": 0.5}
        full = moon_trait_bias(base, 1.0)
        for key in base:
            assert abs(full[key] - base[key]) <= 0.12

    def test_bias_never_escapes_the_unit_range(self):
        from app.entities import moon_trait_bias

        for extreme in (0.0, 1.0):
            base = dict.fromkeys(
                ("alignment", "power", "volatility", "deceptiveness"), extreme
            )
            for lit in (0.0, 0.5, 1.0):
                for v in moon_trait_bias(base, lit).values():
                    assert 0.0 <= v <= 1.0

    def test_unknown_sky_leaves_traits_untouched(self):
        from app.entities import moon_trait_bias

        base = {"alignment": 0.3, "power": 0.7, "volatility": 0.2, "deceptiveness": 0.9}
        assert moon_trait_bias(base, None) == base

    def test_deceptiveness_is_not_moon_driven(self):
        # Whether a spirit lies is its own nature, not the sky's doing.
        from app.entities import moon_trait_bias

        base = {"alignment": 0.5, "power": 0.5, "volatility": 0.5, "deceptiveness": 0.5}
        assert moon_trait_bias(base, 1.0)["deceptiveness"] == 0.5

    def test_fallback_profiles_respect_the_moon(self):
        from app.entities import fallback_profile

        dark = [fallback_profile(f"s{i}", None, 0.0)["rarity"] for i in range(300)]
        full = [fallback_profile(f"s{i}", None, 1.0)["rarity"] for i in range(300)]
        rare_dark = sum(r in ("rare", "mythic") for r in dark)
        rare_full = sum(r in ("rare", "mythic") for r in full)
        assert rare_full > rare_dark