feat: refuse silent v3->v2 downgrade; monthly retrain timer with staged promote

B4L/Northern-Thailand-Ping-River-Monitor

train_all() now raises RainUnavailableError when use_rain=True and the
Open-Meteo history cannot be loaded, instead of logging a warning and
writing gauge-only (v2) bundles over the deployed v3 set -- which is what
the 2026-09-01 server retrain did unnoticed. --no-rain remains the explicit
way to get v2. CLI exits 2 with a one-line error. Three tests cover the
guard, the opt-out, and the v3 happy path.

scripts/retrain.sh trains into models/.staging, refuses to promote unless
metrics.json shows hgb-v3+ and >=14 trained stations, then renames bundles
into place (previous generation kept in models/.previous). No API restart:
predict.py reloads by mtime on the hourly precompute.

water-monitor-retrain.{service,timer}: 1st of each month 03:30, Persistent,
OMP_NUM_THREADS=4, Nice=15, same sandbox as the API unit. install.sh now
does `uv sync` into .venv (one env rule; removes a stale venv/) and enables
the timer. water-monitor.service in the repo matched neither the deployed
unit nor the uv env; it now does (run.py --web-api, .venv, EnvironmentFile).

This commit is contained in:

grabowski

2026-09-11 21:37:11 +02:00

parent 0a4bf843ff

commit 764764e07e

11 changed files with 326 additions and 26 deletions

									
										scripts/train_flood_model.py
									
		+2
		-2
	
												View File
												
				@@ -11,7 +11,7 @@ import sys

				sys.path.insert(0, os.path.join(os.path.dirname(__file__), ".."))

				from src.ml.train import main

				from src.ml.train import cli

				if __name__ == "__main__":

				    main()

				    raise SystemExit(cli())