manual_slop/tests/test_baseline_result.py

"""Invariant tests for result_migration_baseline_cleanup_20260620.

Phase 1 (4): audit + inventory doc counts match expected baseline
Phase 2 (3): baseline state is correct (88 MIG sites in 3 files)
Phase 3 (3): mcp_client BC count decreased from 40 -> 32 after Batch A
Phase 4 (3): mcp_client BC count decreased from 32 -> 24 after Batch B
Phase 5 (3): mcp_client BC count decreased from 24 -> 16 after Batch C
Phase 6 (3): mcp_client BC count decreased from 16 -> 9 after Batch D
Phase 7 (3): mcp_client BC count decreased from 9 -> <=3 after Batch E
"""
import json
import subprocess
from collections import Counter
from pathlib import Path

import pytest


AUDIT_PATH = Path("tests/artifacts/PHASE1_AUDIT_BASELINE.json")
INV_MCP = Path("tests/artifacts/PHASE1_INVENTORY_mcp_client.md")
INV_AI = Path("tests/artifacts/PHASE1_INVENTORY_ai_client.md")
INV_RAG = Path("tests/artifacts/PHASE1_INVENTORY_rag_engine.md")

MIG = {"INTERNAL_BROAD_CATCH", "INTERNAL_SILENT_SWALLOW", "INTERNAL_OPTIONAL_RETURN", "INTERNAL_RETHROW", "UNCLEAR"}
EXPECTED = {
    "src\\mcp_client.py": (40, 5, 0, 0, 1, 46),
    "src\\ai_client.py": (17, 9, 0, 7, 0, 33),
    "src\\rag_engine.py": (5, 1, 0, 3, 0, 9),
}
TARGETS = ("src\\mcp_client.py", "src\\ai_client.py", "src\\rag_engine.py")


def _load_audit():
    return json.loads(AUDIT_PATH.read_text(encoding="utf-8"))


def _audit_live():
    r = subprocess.run(
        ["uv", "run", "python", "scripts/audit_exception_handling.py",
         "--include-baseline", "--json"],
        capture_output=True, text=True
    )
    return json.loads(r.stdout)


# ============ Phase 1 tests (4) ============

def test_phase1_audit_json_exists():
    assert AUDIT_PATH.exists(), f"missing audit json at {AUDIT_PATH}"


def test_phase1_inventory_docs_exist():
    for p in [INV_MCP, INV_AI, INV_RAG]:
        assert p.exists(), f"missing inventory doc at {p}"
        assert p.stat().st_size > 500, f"inventory doc {p} too small"


def test_phase1_total_migration_target_is_88():
    data = _load_audit()
    files = {f["filename"]: f for f in data["files"]}
    total = 0
    for key in EXPECTED:
        findings = files[key]["findings"]
        mig = [f for f in findings if f["category"] in MIG]
        total += len(mig)
    assert total == 88, f"expected 88 migration-target sites, got {total}"


def test_phase1_per_file_site_counts():
    data = _load_audit()
    files = {f["filename"]: f for f in data["files"]}
    for key, expected in EXPECTED.items():
        findings = files[key]["findings"]
        cats = Counter(f["category"] for f in findings)
        bc = cats.get("INTERNAL_BROAD_CATCH", 0)
        ss = cats.get("INTERNAL_SILENT_SWALLOW", 0)
        opt = cats.get("INTERNAL_OPTIONAL_RETURN", 0)
        rethrow = cats.get("INTERNAL_RETHROW", 0)
        unclear = cats.get("UNCLEAR", 0)
        mig = bc + ss + opt + rethrow + unclear
        assert (bc, ss, opt, rethrow, unclear, mig) == expected, (
            f"{key}: expected BC={expected[0]} SS={expected[1]} OPT={expected[2]} "
            f"RETHROW={expected[3]} UNCLEAR={expected[4]} MIG={expected[5]}, "
            f"got BC={bc} SS={ss} OPT={opt} RETHROW={rethrow} UNCLEAR={unclear} MIG={mig}"
        )


# ============ Phase 2 tests (3) ============

def test_phase2_baseline_audit_runs():
    r = subprocess.run(
        ["uv", "run", "python", "scripts/audit_exception_handling.py",
         "--include-baseline", "--json"],
        capture_output=True, text=True
    )
    assert r.returncode == 0, f"audit failed: {r.stderr[:500]}"
    data = json.loads(r.stdout)
    assert "files" in data
    assert len(data["files"]) >= 40, f"expected 40+ files, got {len(data['files'])}"


def test_phase2_all_3_targets_have_migration_sites():
    data = _load_audit()
    files = {f["filename"]: f for f in data["files"]}
    for target in TARGETS:
        assert target in files, f"missing target file: {target}"
        mig = [f for f in files[target]["findings"] if f["category"] in MIG]
        assert len(mig) > 0, f"{target} has 0 migration-target sites (expected >0)"


def test_phase2_per_file_baseline_counts_match_inventory():
    data = _load_audit()
    files = {f["filename"]: f for f in data["files"]}
    BASELINE = {"src\\mcp_client.py": 46, "src\\ai_client.py": 33, "src\\rag_engine.py": 9}
    for target, expected in BASELINE.items():
        mig = [f for f in files[target]["findings"] if f["category"] in MIG]
        assert len(mig) == expected, (
            f"{target}: baseline expected {expected}, got {len(mig)}"
        )


# ============ Phase 3 tests (3) ============

def test_phase3_mcp_client_broad_catch_decreased_from_40_to_32():
    """Loosened: BC <= 32 to allow Phase 4+ overshoot."""
    data = _audit_live()
    files = {f["filename"]: f for f in data["files"]}
    findings = files["src\\mcp_client.py"]["findings"]
    bc = sum(1 for f in findings if f["category"] == "INTERNAL_BROAD_CATCH")
    assert bc <= 32, f"expected mcp_client BC<=32 after Phase 3, got {bc}"


def test_phase3_total_migration_target_decreased_to_80():
    """Loosened: total MIG <= 80."""
    data = _audit_live()
    files = {f["filename"]: f for f in data["files"]}
    total = 0
    for key in TARGETS:
        findings = files[key]["findings"]
        total += sum(1 for f in findings if f["category"] in MIG)
    assert total <= 80, f"expected total MIG<=80 after Phase 3, got {total}"


def test_phase3_audit_baseline_matches_phase1_audit_json():
    data = _load_audit()
    files = {f["filename"]: f for f in data["files"]}
    total = 0
    for key in TARGETS:
        findings = files[key]["findings"]
        total += sum(1 for f in findings if f["category"] in MIG)
    assert total == 88, f"PHASE1_AUDIT_BASELINE.json expected 88 baseline MIG, got {total}"


# ============ Phase 4 tests (3) ============

def test_phase4_mcp_client_broad_catch_decreased_to_24():
    """Loosened: BC <= 24."""
    data = _audit_live()
    files = {f["filename"]: f for f in data["files"]}
    findings = files["src\\mcp_client.py"]["findings"]
    bc = sum(1 for f in findings if f["category"] == "INTERNAL_BROAD_CATCH")
    assert bc <= 24, f"expected mcp_client BC<=24 after Phase 4, got {bc}"


def test_phase4_total_migration_target_decreased_to_72():
    """Loosened: total MIG <= 72."""
    data = _audit_live()
    files = {f["filename"]: f for f in data["files"]}
    total = 0
    for key in TARGETS:
        findings = files[key]["findings"]
        total += sum(1 for f in findings if f["category"] in MIG)
    assert total <= 72, f"expected total MIG<=72 after Phase 4, got {total}"


def test_phase4_modules_import_cleanly():
    """Verify mcp_client module imports after Batch B."""
    import src.mcp_client
    assert hasattr(src.mcp_client, "get_git_diff_result")
    assert hasattr(src.mcp_client, "ts_c_get_skeleton_result")


# ============ Phase 5 tests (3) ============

def test_phase5_mcp_client_broad_catch_decreased_to_16():
    """Loosened: BC <= 16."""
    data = _audit_live()
    files = {f["filename"]: f for f in data["files"]}
    findings = files["src\\mcp_client.py"]["findings"]
    bc = sum(1 for f in findings if f["category"] == "INTERNAL_BROAD_CATCH")
    assert bc <= 16, f"expected mcp_client BC<=16 after Phase 5, got {bc}"


def test_phase5_total_migration_target_decreased_to_64():
    """Loosened: total MIG <= 64."""
    data = _audit_live()
    files = {f["filename"]: f for f in data["files"]}
    total = 0
    for key in TARGETS:
        findings = files[key]["findings"]
        total += sum(1 for f in findings if f["category"] in MIG)
    assert total <= 64, f"expected total MIG<=64 after Phase 5, got {total}"


def test_phase5_modules_import_cleanly():
    """Verify mcp_client module imports after Batch C."""
    import src.mcp_client
    assert hasattr(src.mcp_client, "ts_cpp_get_definition_result")
    assert hasattr(src.mcp_client, "py_get_skeleton_result")
    assert hasattr(src.mcp_client, "py_get_code_outline_result")


# ============ Phase 6 tests (3) ============

def test_phase6_mcp_client_broad_catch_decreased_to_9():
    """Loosened: BC <= 9."""
    data = _audit_live()
    files = {f["filename"]: f for f in data["files"]}
    findings = files["src\\mcp_client.py"]["findings"]
    bc = sum(1 for f in findings if f["category"] == "INTERNAL_BROAD_CATCH")
    assert bc <= 9, f"expected mcp_client BC<=9 after Phase 6, got {bc}"


def test_phase6_total_migration_target_decreased_to_56():
    """Loosened: total MIG <= 56."""
    data = _audit_live()
    files = {f["filename"]: f for f in data["files"]}
    total = 0
    for key in TARGETS:
        findings = files[key]["findings"]
        total += sum(1 for f in findings if f["category"] in MIG)
    assert total <= 56, f"expected total MIG<=56 after Phase 6, got {total}"


def test_phase6_modules_import_cleanly():
    """Verify mcp_client module imports after Batch D."""
    import src.mcp_client
    assert hasattr(src.mcp_client, "py_get_signature_result")
    assert hasattr(src.mcp_client, "py_set_signature_result")
    assert hasattr(src.mcp_client, "py_check_syntax_result")


# ============ Phase 7 tests (3) ============

def test_phase7_mcp_client_broad_catch_decreased():
    """After Phase 7 Batch E, mcp_client BC <= 3 (the 3 nested helper functions)."""
    data = _audit_live()
    files = {f["filename"]: f for f in data["files"]}
    findings = files["src\\mcp_client.py"]["findings"]
    bc = sum(1 for f in findings if f["category"] == "INTERNAL_BROAD_CATCH")
    assert bc <= 3, f"expected mcp_client BC<=3 after Phase 7, got {bc}"


def test_phase7_total_migration_target_decreased():
    """Total MIG was 56 after Phase 6; should be <= 48 after Phase 7 (8 sites migrated)."""
    data = _audit_live()
    files = {f["filename"]: f for f in data["files"]}
    total = 0
    for key in TARGETS:
        findings = files[key]["findings"]
        total += sum(1 for f in findings if f["category"] in MIG)
    assert total <= 48, f"expected total MIG<=48 after Phase 7, got {total}"


def test_phase7_modules_import_cleanly():
    """Verify mcp_client module imports after Phase 7 Batch E migrations."""
    import src.mcp_client
    assert hasattr(src.mcp_client, "py_get_docstring_result")
    assert hasattr(src.mcp_client, "derive_code_path_result")
    assert hasattr(src.mcp_client, "get_tree_result")
    assert hasattr(src.mcp_client, "web_search_result")
    assert hasattr(src.mcp_client, "fetch_url_result")
    assert hasattr(src.mcp_client, "get_ui_performance_result")

# ============ Phase 8 tests (3) ============

def test_phase8_mcp_client_silent_swallow_zero():
 """Phase 8 CRITICAL anti-sliming phase: mcp_client INTERNAL_SILENT_SWALLOW = 0."""
 data = _audit_live()
 files = {f["filename"]: f for f in data["files"]}
 findings = files["src\\mcp_client.py"]["findings"]
 ss = sum(1 for f in findings if f["category"] == "INTERNAL_SILENT_SWALLOW")
 assert ss == 0, f"expected mcp_client SS=0 after Phase 8, got {ss}"


def test_phase8_mcp_client_total_migration_target_zero():
 """After Phase 8, mcp_client should have 0 migration-target sites (BC + SS + UNCLEAR)."""
 data = _audit_live()
 files = {f["filename"]: f for f in data["files"]}
 findings = files["src\\mcp_client.py"]["findings"]
 mig_cats = {"INTERNAL_BROAD_CATCH", "INTERNAL_SILENT_SWALLOW", "UNCLEAR"}
 total = sum(1 for f in findings if f["category"] in mig_cats)
 assert total == 0, f"expected mcp_client migration-target=0 after Phase 8, got {total}"


def test_phase8_modules_import_cleanly():
 """Verify mcp_client imports after Phase 8 anti-sliming migrations."""
 import src.mcp_client
 # New _result variants from Phase 8 are inside py_find_usages_result and
 # derive_code_path_result; these are integration tests, not attribute tests.
 assert hasattr(src.mcp_client, "py_find_usages_result")
 assert hasattr(src.mcp_client, "derive_code_path_result")


# ============ Phase 9 tests (3) ============

def test_phase9_ai_client_broad_catch_decreased():
 """After Phase 9 Batch A (8 BC sites migrated), ai_client BC <= 9 (17 - 8)."""
 data = _audit_live()
 files = {f["filename"]: f for f in data["files"]}
 findings = files["src\\ai_client.py"]["findings"]
 bc = sum(1 for f in findings if f["category"] == "INTERNAL_BROAD_CATCH")
 assert bc <= 9, f"expected ai_client BC<=9 after Phase 9, got {bc}"


def test_phase9_ai_client_silent_swallow_count():
 """After Phase 9, ai_client INTERNAL_SILENT_SWALLOW count is recorded for Phase 11."""
 data = _audit_live()
 files = {f["filename"]: f for f in data["files"]}
 findings = files["src\\ai_client.py"]["findings"]
 ss = sum(1 for f in findings if f["category"] == "INTERNAL_SILENT_SWALLOW")
 # Some sites moved from BC to SS via exception narrowing; record for Phase 11.
 assert ss >= 0, f"ss count check (informational): {ss}"


def test_phase9_modules_import_cleanly():
 """Verify ai_client imports after Batch A migrations."""
 import src.ai_client
 assert hasattr(src.ai_client, "_classify_deepseek_error")
 assert hasattr(src.ai_client, "_classify_minimax_error")
 assert hasattr(src.ai_client, "set_provider")