feat: add review effort accounting and budget governor

tests/pilot/review_tests/ai_review_test.py

@@ -429,6 +429,41 @@ def test_parse_repo_config_static_message_ignores_blank():
     assert "static_message" not in parse_repo_config(json.dumps({"static_message": 42}))
 
 
+def test_parse_repo_config_sanitizes_budget_limits():
+    cfg = parse_repo_config(json.dumps({
+        "budget": {
+            "max_steps": "20",
+            "max_total_tokens": 120000,
+            "max_output_tokens": 20000,
+            "max_duration_seconds": 480,
+            "max_lenses": 4,
+            "max_equivalent_cost_usd": "1.25",
+            "unknown": 99,
+        }
+    }))
+    assert cfg["budget"] == {
+        "max_steps": 20,
+        "max_total_tokens": 120000,
+        "max_output_tokens": 20000,
+        "max_duration_seconds": 480,
+        "max_lenses": 4,
+        "max_equivalent_cost_usd": 1.25,
+    }
+
+
+def test_parse_repo_config_drops_invalid_budget_values():
+    cfg = parse_repo_config(json.dumps({
+        "budget": {
+            "max_steps": 0,
+            "max_total_tokens": 999999999,
+            "max_duration_seconds": -1,
+            "max_lenses": 99,
+            "max_equivalent_cost_usd": 0,
+        }
+    }))
+    assert "budget" not in cfg
+
+
 def test_parse_repo_config_reads_model_override():
     # Per-repo override is validated against cost_model.PRICES. Only keys
     # the cost model knows about can override the review engine.
@@ -2148,4 +2183,3 @@ def test_format_review_body_confidence_clamps_out_of_range():
     assert "Merge confidence: 5/5 🟢" in body_hi
     body_lo = format_review_body("- x", "glm-5.2:cloud", "abcdef1234567890", confidence=0)
     assert "Merge confidence: 1/5 🔴" in body_lo
-