test(baseline): add 3 Phase 2 invariant tests (audit gate baseline)

TIER-2 READ conductor/code_styleguides/error_handling.md end-to-end before Phase 2.

Phase 2 tests assert the BASELINE state:
1. test_phase2_baseline_audit_runs: audit --include-baseline --json exits 0
2. test_phase2_all_3_targets_have_migration_sites: each baseline file has >0 MIG
3. test_phase2_per_file_baseline_counts_match_inventory: counts = 46/33/9

Total: 7 tests pass (4 Phase 1 + 3 Phase 2).

tests/test_baseline_result.py

@@ -1,11 +1,11 @@
-"""Phase 1 invariant tests for result_migration_baseline_cleanup_20260620.
+"""Phase 1 + Phase 2 invariant tests for result_migration_baseline_cleanup_20260620.
 
-Asserts:
-1. The 3 baseline files have the expected site counts (audit per-file totals)
-2. Migration-target total = 88 (46 + 33 + 9)
-3. PHASE1_AUDIT_BASELINE.json + 3 inventory docs exist and have correct counts
+Phase 1: 4 tests assert the audit + inventory docs match expected counts.
+Phase 2: 3 tests assert the BASELINE state is correct (88 migration-target sites
+          in 3 files; the migration is starting from this exact state).
 """
 import json
+import subprocess
 from collections import Counter
 from pathlib import Path
 
@@ -23,8 +23,15 @@ EXPECTED = {
     "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"))
+
+
+# ============ Phase 1 tests (4) ============
+
 def test_phase1_audit_json_exists():
     assert AUDIT_PATH.exists(), f"missing audit json at {AUDIT_PATH}"
 
@@ -32,12 +39,11 @@ def test_phase1_audit_json_exists():
 def test_phase1_inventory_docs_exist():
     for p in [INV_MCP, INV_AI, INV_RAG]:
         assert p.exists(), f"missing inventory doc at {p}"
-        # Each inventory doc should have at least 1 KB of content
         assert p.stat().st_size > 500, f"inventory doc {p} too small"
 
 
 def test_phase1_total_migration_target_is_88():
-    data = json.loads(AUDIT_PATH.read_text(encoding="utf-8"))
+    data = _load_audit()
     files = {f["filename"]: f for f in data["files"]}
     total = 0
     for key in EXPECTED:
@@ -49,7 +55,7 @@ def test_phase1_total_migration_target_is_88():
 
 def test_phase1_per_file_site_counts():
     """mcp=46, ai=33, rag=9 = (BC, SS, OPT, RETHROW, UNCLEAR, total)"""
-    data = json.loads(AUDIT_PATH.read_text(encoding="utf-8"))
+    data = _load_audit()
     files = {f["filename"]: f for f in data["files"]}
     for key, expected in EXPECTED.items():
         findings = files[key]["findings"]
@@ -64,4 +70,46 @@ def test_phase1_per_file_site_counts():
             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():
+    """The audit --include-baseline --json command exits 0."""
+    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():
+    """Each of the 3 baseline files has at least 1 migration-target site."""
+    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():
+    """The baseline per-file counts match the Phase 1 inventory docs."""
+    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)} "
+            f"(a previous phase may have introduced a violation)"
         )