Add new daemons and debug scripts for Sigenergy and Oracle functionalities

- Implement `sigen_daemon.py` to poll Sigenergy plant metrics and store snapshots.
- Create `web_daemon.py` for serving a web interface with various endpoints.
- Add debug scripts:
  - `debug_duplicates.py` to find duplicate target times in forecast data.
  - `debug_energy_forecast.py` to print baseline energy forecast curves.
  - `debug_oracle_evaluations.py` to run the oracle evaluator.
  - `debug_sigen.py` to inspect stored Sigenergy plant snapshots.
  - `debug_weather.py` to trace resolved truth data.
  - `modbus_test.py` for exploring Sigenergy plants or inverters over Modbus TCP.
- Introduce `oracle_evaluator.py` for evaluating stored oracle predictions against actuals.
- Add TCN training scripts in `tcn` directory for training usage sequence models.

gibil/scripts/debug/debug_energy_forecast.py

@@ -0,0 +1,67 @@
+#!/usr/bin/env python3
+"""Debug baseline energy forecast curves."""
+
+from __future__ import annotations
+
+import argparse
+from datetime import timezone
+
+from gibil.classes.oracle.builder import EnergyForecastBuilder
+from gibil.classes.env_loader import EnvLoader
+from gibil.classes.models import PowerForecastPoint
+
+
+def main() -> None:
+    EnvLoader().load()
+    args = parse_args()
+    solar_run, load_run, net_run = EnergyForecastBuilder.from_env().build()
+
+    print(
+        f"issued_at={net_run.issued_at.astimezone(timezone.utc).isoformat(timespec='seconds')}"
+    )
+    print(
+        f"solar_model={solar_run.model_version} "
+        f"load_model={load_run.model_version} points={len(net_run.points)}"
+    )
+    print(
+        "target_at                 solar_p10 solar_p50 solar_p90 "
+        "load_p10 load_p50 load_p90 net_p10 net_p50 net_p90"
+    )
+    solar_by_target = _by_target(solar_run.points)
+    load_by_target = _by_target(load_run.points)
+    for point in net_run.points[: args.limit]:
+        solar_point = solar_by_target[point.target_at]
+        load_point = load_by_target[point.target_at]
+        print(
+            f"{point.target_at.astimezone(timezone.utc).isoformat(timespec='minutes'):25} "
+            f"{solar_point.p10_power_w:9.0f} "
+            f"{solar_point.p50_power_w:9.0f} "
+            f"{solar_point.p90_power_w:9.0f} "
+            f"{load_point.p10_power_w:8.0f} "
+            f"{load_point.p50_power_w:8.0f} "
+            f"{load_point.p90_power_w:8.0f} "
+            f"{point.p10_net_power_w:7.0f} "
+            f"{point.p50_net_power_w:7.0f} "
+            f"{point.p90_net_power_w:7.0f}"
+        )
+
+
+def _by_target(points: list[PowerForecastPoint]) -> dict[object, PowerForecastPoint]:
+    return {point.target_at: point for point in points}
+
+
+def parse_args() -> argparse.Namespace:
+    parser = argparse.ArgumentParser(
+        description="Print baseline solar/load/net forecast curves."
+    )
+    parser.add_argument(
+        "--limit",
+        type=int,
+        default=24,
+        help="Number of forecast points to show. Defaults to 24.",
+    )
+    return parser.parse_args()
+
+
+if __name__ == "__main__":
+    main()