test(baseline): add 3 Phase 3 invariant tests (Batch A complete)

TIER-2 READ conductor/code_styleguides/error_handling.md end-to-end before Phase 3.

Phase 3 tests assert:
1. mcp_client BC count 40 -> 32 (Batch A migrated 8 sites)
2. Total MIG 88 -> 80 (88 - 8 Batch A)
3. PHASE1_AUDIT_BASELINE.json still has 88 baseline (immutable)

Total: 10 tests pass (4 Phase 1 + 3 Phase 2 + 3 Phase 3).

tests/test_baseline_result.py

@@ -1,8 +1,8 @@
-"""Phase 1 + Phase 2 invariant tests for result_migration_baseline_cleanup_20260620.
+"""Invariant tests for result_migration_baseline_cleanup_20260620.
 
-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).
+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
 """
 import json
 import subprocess
@@ -30,6 +30,15 @@ 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():
@@ -54,7 +63,6 @@ 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 = _load_audit()
     files = {f["filename"]: f for f in data["files"]}
     for key, expected in EXPECTED.items():
@@ -76,7 +84,6 @@ def test_phase1_per_file_site_counts():
 # ============ 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"],
@@ -89,7 +96,6 @@ def test_phase2_baseline_audit_runs():
 
 
 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:
@@ -99,17 +105,42 @@ def test_phase2_all_3_targets_have_migration_sites():
 
 
 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,
-    }
+    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)"
-        )
+        )
+
+
+# ============ Phase 3 tests (3) ============
+
+def test_phase3_mcp_client_broad_catch_decreased_from_40_to_32():
+    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 Batch A, got {bc}"
+
+
+def test_phase3_total_migration_target_decreased_to_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}"