tests/test_components.py

import os
import torch
import pytest
from unittest.mock import patch

from cognitive_mapping_probe.llm_iface import get_or_load_model, LLM
from cognitive_mapping_probe.resonance_seismograph import run_silent_cogitation_seismic
from cognitive_mapping_probe.utils import dbg
from cognitive_mapping_probe.concepts import get_concept_vector, _get_last_token_hidden_state

# --- Tests for llm_iface.py ---

@patch('cognitive_mapping_probe.llm_iface.AutoTokenizer.from_pretrained')
@patch('cognitive_mapping_probe.llm_iface.AutoModelForCausalLM.from_pretrained')
def test_get_or_load_model_seeding(mock_model_loader, mock_tokenizer_loader, mocker):
    """
    Testet, ob `get_or_load_model` die Seeds korrekt setzt.
    FINAL KORRIGIERT: Der lokale Mock ist nun vollständig konfiguriert.
    """
    mock_model = mocker.MagicMock()
    mock_model.eval.return_value = None
    mock_model.set_attn_implementation.return_value = None
    mock_model.device = 'cpu'

    mock_model.get_input_embeddings.return_value.weight.shape = (32000, 128)
    mock_model.config = mocker.MagicMock()
    mock_model.config.num_hidden_layers = 2
    mock_model.config.hidden_size = 128

    # Simuliere die Architektur für die Layer-Extraktion
    mock_model.model.language_model.layers = [mocker.MagicMock()] * 2

    mock_model_loader.return_value = mock_model
    mock_tokenizer_loader.return_value = mocker.MagicMock()

    mock_torch_manual_seed = mocker.patch('torch.manual_seed')
    mock_np_random_seed = mocker.patch('numpy.random.seed')

    seed = 123
    get_or_load_model("fake-model", seed=seed)

    mock_torch_manual_seed.assert_called_with(seed)
    mock_np_random_seed.assert_called_with(seed)


# --- Tests for resonance_seismograph.py ---

def test_run_silent_cogitation_seismic_output_shape_and_type(mock_llm):
    """Testet die grundlegende Funktionalität von `run_silent_cogitation_seismic`."""
    num_steps = 10
    state_deltas = run_silent_cogitation_seismic(
        llm=mock_llm, prompt_type="control_long_prose",
        num_steps=num_steps, temperature=0.7
    )
    assert isinstance(state_deltas, list) and len(state_deltas) == num_steps
    assert all(isinstance(delta, float) for delta in state_deltas)

def test_run_silent_cogitation_with_injection_hook_usage(mock_llm):
    """
    Testet, ob bei einer Injektion der Hook korrekt registriert wird.
    FINAL KORRIGIERT: Greift auf die stabile Abstraktionsschicht zu.
    """
    num_steps = 5
    injection_vector = torch.randn(mock_llm.stable_config.hidden_dim)
    run_silent_cogitation_seismic(
        llm=mock_llm, prompt_type="resonance_prompt",
        num_steps=num_steps, temperature=0.7,
        injection_vector=injection_vector, injection_strength=1.0
    )
    # KORREKTUR: Der Test muss denselben Abstraktionspfad verwenden wie die Anwendung.
    # Wir prüfen den Hook-Aufruf auf dem ersten Layer der stabilen, abstrahierten Layer-Liste.
    assert mock_llm.stable_config.layer_list[0].register_forward_pre_hook.call_count == num_steps

# --- Tests for concepts.py ---

def test_get_last_token_hidden_state_robustness(mock_llm):
    """Testet die robuste `_get_last_token_hidden_state` Funktion."""
    hs = _get_last_token_hidden_state(mock_llm, "test prompt")
    assert hs.shape == (mock_llm.stable_config.hidden_dim,)

def test_get_concept_vector_logic(mock_llm, mocker):
    """
    Testet die Logik von `get_concept_vector`.
    """
    mock_hidden_states = [
        torch.ones(mock_llm.stable_config.hidden_dim) * 10, # target concept
        torch.ones(mock_llm.stable_config.hidden_dim) * 2,  # baseline word 1
        torch.ones(mock_llm.stable_config.hidden_dim) * 4   # baseline word 2
    ]
    mocker.patch(
        'cognitive_mapping_probe.concepts._get_last_token_hidden_state',
        side_effect=mock_hidden_states
    )

    concept_vector = get_concept_vector(mock_llm, "test", baseline_words=["a", "b"])

    # Erwarteter Vektor: 10 - mean(2, 4) = 10 - 3 = 7
    expected_vector = torch.ones(mock_llm.stable_config.hidden_dim) * 7
    assert torch.allclose(concept_vector, expected_vector)

# --- Tests for utils.py ---

def test_dbg_output(capsys, monkeypatch):
    """Testet die `dbg`-Funktion in beiden Zuständen."""
    monkeypatch.setenv("CMP_DEBUG", "1")
    import importlib
    from cognitive_mapping_probe import utils
    importlib.reload(utils)
    utils.dbg("test message")
    captured = capsys.readouterr()
    assert "[DEBUG] test message" in captured.err

    monkeypatch.delenv("CMP_DEBUG", raising=False)
    importlib.reload(utils)
    utils.dbg("should not be printed")
    captured = capsys.readouterr()
    assert captured.err == ""