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
-

tests/pilot/review_tests/budget_test.py

@@ -0,0 +1,49 @@
+"""Budget policy and accounting tests."""
+
+import os
+import sys
+import json
+
+ROOT = os.path.abspath(os.path.join(os.path.dirname(__file__), "..", "..", ".."))
+sys.path.insert(0, os.path.join(ROOT, "pilot"))
+
+from review.budget import Budget, BudgetState  # noqa: E402
+from review import opencode_runtime  # noqa: E402
+from review.opencode import parse_opencode_events  # noqa: E402
+
+
+def test_budget_reads_config_over_environment(monkeypatch):
+    monkeypatch.setenv("PRAGENT_MAX_REVIEW_STEPS", "3")
+    budget = Budget.from_config({"budget": {"max_steps": 7}})
+    assert budget.max_steps == 7
+
+
+def test_budget_state_stops_at_token_limit():
+    state = BudgetState(Budget(max_steps=20, max_total_tokens=100))
+    assert state.record({"steps": 1, "total": 60, "output": 10}) == ""
+    assert state.record({"steps": 1, "total": 40, "output": 10}) == "max_total_tokens"
+    assert state.snapshot()["cap_hit"] is True
+
+
+def test_budget_state_tracks_cost_cap():
+    state = BudgetState(Budget(max_equivalent_cost_usd=1.0))
+    assert state.record({"steps": 1, "total": 1}, 0.75) == ""
+    assert state.record({"steps": 1, "total": 1}, 0.25) == "max_equivalent_cost_usd"
+
+
+def test_process_terminates_after_step_budget():
+    code = (
+        "import json,time; "
+        "print(json.dumps({'type':'step_finish','part':{'tokens':{"
+        "'input':1,'output':1,'total':2}}}), flush=True); "
+        "time.sleep(30)"
+    )
+    budget = Budget(max_steps=1, max_duration_seconds=10)
+    state = BudgetState(budget)
+    proc = opencode_runtime._run_process(
+        [sys.executable, "-u", "-c", code], cwd=".", env=os.environ.copy(),
+        timeout=10, parse_events=parse_opencode_events, budget=budget,
+        budget_state=state, model="glm-5.2:cloud", runner=None,
+    )
+    assert state.snapshot()["cap_reason"] == "max_steps"
+    assert proc.stdout.count("step_finish") == 1

tests/pilot/review_tests/opencode_workspace_test.py

@@ -201,6 +201,13 @@ def test_parse_events_text_and_usage_summed():
     assert usage["cache_write"] == 1
     assert usage["total"] == 150
     assert abs(usage["cost"] - 0.01) < 1e-9
+    assert usage["tool_calls"] == 0
+    assert usage["iterations"] == [
+        {"step": 1, "input": 90, "output": 10, "reasoning": 0,
+         "cache_read": 5, "cache_write": 0, "total": 100, "cost": 0.0},
+        {"step": 2, "input": 40, "output": 10, "reasoning": 2,
+         "cache_read": 0, "cache_write": 1, "total": 50, "cost": 0.01},
+    ]
 
 
 def test_parse_events_no_step_finish_returns_none_usage():
@@ -481,4 +488,3 @@ def test_committed_config_has_no_private_address():
 # ---------------------------------------------------------------------------
 # Multi-lens orchestration
 # ---------------------------------------------------------------------------
-