mnemosyne/tests/test_admission.py

"""Tests for the admission control module.

Tests the AdmissionController scoring logic across all four axes:
type_score, novelty_score, utility_score, size_score, and the
threshold-based admit/reject decision.
"""

from __future__ import annotations

from mnemosyne.admission import AdmissionController, AdmissionScore, DEFAULT_THRESHOLD


# ── Type score ───────────────────────────────────────────────────────────


def test_admission_score_design_decision():
    """design_decision has the highest type weight (0.9)."""
    ctrl = AdmissionController()
    score = ctrl.score("x" * 300, "design_decision", has_duplicate=False)
    assert score.type_score == 0.9


def test_admission_score_conversation_phase():
    """conversation_phase has the lowest type weight (0.3)."""
    ctrl = AdmissionController()
    score = ctrl.score("x" * 300, "conversation_phase", has_duplicate=False)
    assert score.type_score == 0.3


def test_admission_unknown_type_default():
    """Unknown object types default to 0.3."""
    ctrl = AdmissionController()
    score = ctrl.score("x" * 300, "totally_unknown_type", has_duplicate=False)
    assert score.type_score == 0.3


# ── Novelty score ────────────────────────────────────────────────────────


def test_admission_duplicate_penalized():
    """Duplicates get novelty_score=0.2 instead of 1.0."""
    ctrl = AdmissionController()
    score_unique = ctrl.score("x" * 300, "file_context", has_duplicate=False)
    score_dup = ctrl.score("x" * 300, "file_context", has_duplicate=True)
    assert score_unique.novelty_score == 1.0
    assert score_dup.novelty_score == 0.2
    assert score_dup.total < score_unique.total


# ── Utility score ────────────────────────────────────────────────────────


def test_admission_utility_code_blocks():
    """Content with code blocks gets utility boost."""
    ctrl = AdmissionController()
    content_with_code = "Here is code:\n```python\ndef foo(): pass\n```\n" + "x" * 200
    content_plain = "Just some plain text without code blocks. " + "x" * 200
    score_code = ctrl.score(content_with_code, "file_context", has_duplicate=False)
    score_plain = ctrl.score(content_plain, "file_context", has_duplicate=False)
    assert score_code.utility_score > score_plain.utility_score


def test_admission_utility_entities():
    """Content with many key_entities gets utility boost."""
    ctrl = AdmissionController()
    entities = ["foo.py", "bar.py", "baz.py"]
    score_with = ctrl.score("x" * 300, "file_context", has_duplicate=False, key_entities=entities)
    score_without = ctrl.score("x" * 300, "file_context", has_duplicate=False, key_entities=[])
    assert score_with.utility_score > score_without.utility_score


# ── Size score ───────────────────────────────────────────────────────────


def test_admission_size_small_penalized():
    """Very small content (< 100 chars) gets penalized size_score."""
    ctrl = AdmissionController()
    score = ctrl.score("tiny", "file_context", has_duplicate=False)
    assert score.size_score < 1.0
    assert score.size_score == len("tiny") / 100


def test_admission_size_large_penalized():
    """Very large content (> 50k chars) gets penalized size_score."""
    ctrl = AdmissionController()
    score = ctrl.score("x" * 80000, "file_context", has_duplicate=False)
    assert score.size_score < 1.0
    assert score.size_score >= 0.3


def test_admission_size_normal():
    """Normal-sized content (100-50k chars) gets size_score=1.0."""
    ctrl = AdmissionController()
    score = ctrl.score("x" * 500, "file_context", has_duplicate=False)
    assert score.size_score == 1.0


# ── Threshold decisions ──────────────────────────────────────────────────


def test_admission_threshold_admit():
    """High-value content is admitted."""
    ctrl = AdmissionController()
    # design_decision (0.9 type) + unique (1.0 novelty) + code + entities + length
    content = "```python\ndef important(): pass\n```\n" + "x" * 300
    admitted, score = ctrl.should_admit(
        content,
        "design_decision",
        has_duplicate=False,
        key_entities=["foo.py", "bar.py", "baz.py"],
    )
    assert admitted is True
    assert score.total >= DEFAULT_THRESHOLD


def test_admission_threshold_reject():
    """Low-value duplicate conversation_phase is rejected."""
    ctrl = AdmissionController()
    # conversation_phase (0.3 type) + duplicate (0.2 novelty) + tiny content
    admitted, score = ctrl.should_admit("hi", "conversation_phase", has_duplicate=True)
    assert admitted is False
    assert score.total < DEFAULT_THRESHOLD


# ── Stats tracking ───────────────────────────────────────────────────────


def test_admission_stats_tracking():
    """Stats correctly count admitted and rejected objects."""
    ctrl = AdmissionController()
    assert ctrl.stats == {"admitted": 0, "rejected": 0}

    # Admit a high-value object
    ctrl.should_admit(
        "```python\ndef foo(): pass\n```\n" + "x" * 300,
        "design_decision",
        has_duplicate=False,
        key_entities=["a.py", "b.py", "c.py"],
    )
    assert ctrl.stats["admitted"] == 1

    # Reject a low-value object
    ctrl.should_admit("hi", "conversation_phase", has_duplicate=True)
    assert ctrl.stats["rejected"] == 1
    assert ctrl.stats["admitted"] == 1


# ── Edge cases ───────────────────────────────────────────────────────────


def test_admission_empty_content():
    """Empty content gets size_score=0 and low utility."""
    ctrl = AdmissionController()
    score = ctrl.score("", "file_context", has_duplicate=False)
    assert score.size_score == 0.0
    assert score.utility_score == 0.0