fix: address pre-push review findings

tests/test_backtest_cache.py

@@ -27,9 +27,11 @@ def test_run_backtest_caches_by_input_file_signature(monkeypatch, tmp_path):
     second = engine.run_backtest()
     ml_first = engine.run_backtest(ml_mode=True)
     ml_second = engine.run_backtest(ml_mode=True)
+    classic_after_ml = engine.run_backtest()
 
     assert first == second == {"ml_mode": False, "calls": 1}
     assert ml_first == ml_second == {"ml_mode": True, "calls": 2}
+    assert classic_after_ml == first
     assert calls == [False, True]
 
     history.write_text('{"changed": true}')

tests/test_backtest_data_quality.py

@@ -51,3 +51,11 @@ def test_live_and_backtest_outputs_publish_panel_and_coverage_metadata():
         "panel_count": 9,
     }
     assert metadata["staleness_days"] == backtest.METRIC_MAX_AGE_DAYS
+
+
+def test_chart_data_exposes_metric_values_under_frontend_contract():
+    result = backtest.run_backtest()
+    entries = [entry for entry in result["chart_data"] if entry.get("metric_values")]
+
+    assert entries
+    assert all("metrics" not in entry for entry in entries)

tests/test_backtest_statistics.py

@@ -43,3 +43,19 @@ def test_backtest_brackets_publish_bootstrap_confidence_intervals():
     assert stats["median_90d"] == 2.5
     assert stats["win_rate_90d"] == 50.0
     assert stats["avg_90d_ci_low"] <= stats["avg_90d"] <= stats["avg_90d_ci_high"]
+
+
+def test_long_horizon_returns_use_a_matching_dependence_block(monkeypatch):
+    observed = {}
+
+    def fake_summary(values, *, block_size, n_resamples):
+        observed.update(block_size=block_size, n_resamples=n_resamples)
+        return {
+            "mean": 1.0, "median": 1.0, "win_rate": 100.0,
+            "mean_ci_low": 0.5, "mean_ci_high": 1.5, "n": len(values),
+        }
+
+    monkeypatch.setattr(engine, "summarize_returns", fake_summary)
+    engine._add_return_statistics({}, "365d", [1.0] * 500)
+
+    assert observed == {"block_size": 365, "n_resamples": 400}

tests/test_reliability_persistence.py

@@ -87,6 +87,28 @@ def test_merge_observation_records_metadata_for_fresh_value():
     assert merged["last_error"] is None
 
 
+def test_merge_observation_rejects_error_only_payload_as_fresh_data():
+    old = {
+        "value": 1.25,
+        "observed_at": "2026-07-25T12:00:00+00:00",
+        "source": "lookintobitcoin",
+        "stale": False,
+        "last_error": None,
+    }
+
+    merged = merge_observation(
+        old,
+        {"value": None, "error": "No data returned"},
+        source="lookintobitcoin",
+        error="metric missing from scrape",
+    )
+
+    assert merged["value"] == 1.25
+    assert merged["observed_at"] == old["observed_at"]
+    assert merged["stale"] is True
+    assert merged["last_error"] == "No data returned"
+
+
 @pytest.mark.parametrize("timestamp", [None, "", "not-a-time"])
 def test_onchain_refresh_due_when_timestamp_is_missing_or_invalid(timestamp):
     assert onchain_refresh_due(timestamp, now=datetime(2026, 7, 26, tzinfo=timezone.utc)) is True