merging docker health monitor into main

.github/workflows/sandbox-integration.yml

@@ -22,7 +22,7 @@ jobs:
           python-version: "3.11"
 
       - name: Install slicks
-        run: pip install "slicks>=2.0.1"
+        run: pip install "slicks>=0.2.1"
 
       - name: Discover sensors for September 2025
         env:

.gitignore

@@ -219,3 +219,7 @@ installer/slackbot/*.jpeg
 
 # Generated CSV data files
 generated-days/
+
+# Node dependencies
+node_modules/
+.claude/settings.local.json

installer/data-downloader/.env.example

@@ -12,4 +12,12 @@ SENSOR_WINDOW_DAYS=7
 SENSOR_LOOKBACK_DAYS=30
 SCAN_INTERVAL_SECONDS=3600
 VITE_API_BASE_URL=http://localhost:8000
-ALLOWED_ORIGINS=http://localhost:3000,http://localhost:5173
+ALLOWED_ORIGINS=http://localhost:3000,http://localhost:5173,https://daq.westernformularacing.org
+
+# Health monitor (optional — defaults work for standard docker-compose stack)
+INFLUXDB_HEALTH_DATABASE=monitoring
+HEALTH_MONITOR_INTERVAL_SECONDS=60
+HEALTH_MONITOR_INFLUXDB_CONTAINER=influxdb3
+HEALTH_MONITOR_SCANNER_CONTAINER=data-downloader-scanner
+HEALTH_MONITOR_SCANNER_API_URL=http://data-downloader-api:8000
+HEALTH_MONITOR_INFLUXDB_VOLUME_SUFFIX=influxdb3-data

installer/data-downloader/backend/app.py

@@ -1,6 +1,10 @@
 from __future__ import annotations
 
-from datetime import datetime
+from datetime import datetime, timezone
+import logging
+from typing import List
+
+import docker
 
 from fastapi import BackgroundTasks, FastAPI, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
@@ -25,6 +29,7 @@ class DataQueryPayload(BaseModel):
 
 settings = get_settings()
 service = DataDownloaderService(settings)
+logger = logging.getLogger(__name__)
 
 app = FastAPI(title="DAQ Data Downloader API")
 app.add_middleware(
@@ -41,6 +46,36 @@ def healthcheck() -> dict:
     return {"status": "ok"}
 
 
+def _docker_container_running(container_name: str) -> bool:
+    """Return True if Docker container is in Running state."""
+    try:
+        docker_client = docker.from_env()
+        container = docker_client.containers.get(container_name)
+        return bool(container.attrs.get("State", {}).get("Running", False))
+    except docker.errors.NotFound:
+        return False
+    except Exception as e:
+        raise RuntimeError(f"Docker inspection failed for {container_name}: {e}") from e
+
+
+@app.get("/api/health-status")
+def health_status() -> dict:
+    """Container health derived from live Docker inspection."""
+    try:
+        scanner_status = service.get_scanner_status()
+        now = datetime.now(timezone.utc).isoformat()
+        return {
+            "influxdb3": _docker_container_running("influxdb3"),
+            "scanner": _docker_container_running("data-downloader-scanner"),
+            "last_updated": now,
+            "last_scan_duration_seconds": scanner_status.get("last_scan_duration_seconds"),
+        }
+    except HTTPException:
+        raise
+    except Exception as e:
+        raise HTTPException(status_code=503, detail=str(e))
+
+
 @app.get("/api/seasons")
 def list_seasons() -> List[dict]:
     return service.get_seasons()
@@ -70,8 +105,9 @@ def save_note(key: str, payload: NotePayload, season: str | None = None) -> dict
 
 
 @app.post("/api/scan")
-def trigger_scan(background_tasks: BackgroundTasks) -> dict:
-    background_tasks.add_task(service.run_full_scan, "manual")
+def trigger_scan(background_tasks: BackgroundTasks, season: str | None = None) -> dict:
+    season_names = [season] if season else None
+    background_tasks.add_task(service.run_full_scan, "manual", season_names)
     return {"status": "scheduled"}
 
 

installer/data-downloader/backend/config.py

@@ -13,17 +13,18 @@ def _parse_origins(raw: str | None) -> List[str]:
 
 
 class SeasonConfig(BaseModel):
-    name: str  # e.g. "WFR25"
-    year: int  # e.g. 2025
+    name: str      # e.g. "WFR25"
+    year: int      # e.g. 2025
     database: str  # e.g. "WFR25"
-    color: str | None = None # e.g. "222 76 153"
+    table: str     # e.g. "WFR25" — InfluxDB table name inside the database
+    color: str | None = None
 
 
 def _parse_seasons(raw: str | None) -> List[SeasonConfig]:
     """Parse SEASONS env var: "WFR25:2025:222 76 153,WFR26:2026:..."."""
     if not raw:
         # Default fallback if not set
-        return [SeasonConfig(name="WFR25", year=2025, database="WFR25", color="#DE4C99")]
+        return [SeasonConfig(name="WFR25", year=2025, database="WFR25", table="WFR25", color="#DE4C99")]
 
     seasons = []
     for part in raw.split(","):
@@ -45,13 +46,13 @@ def _parse_seasons(raw: str | None) -> List[SeasonConfig]:
 
             color = parts[2] if len(parts) > 2 else None
 
-            # Assume DB name matches Season Name
-            seasons.append(SeasonConfig(name=name, year=year, database=name, color=color))
+            # DB and table name both match season name by convention (WFR25→WFR25, WFR26→WFR26)
+            seasons.append(SeasonConfig(name=name, year=year, database=name, table=name, color=color))
         except ValueError:
             continue
 
     if not seasons:
-         return [SeasonConfig(name="WFR25", year=2025, database="WFR25")]
+         return [SeasonConfig(name="WFR25", year=2025, database="WFR25", table="WFR25")]
 
     # Sort by year descending (newest first)
     seasons.sort(key=lambda s: s.year, reverse=True)

installer/data-downloader/backend/periodic_worker.py

@@ -24,8 +24,9 @@ async def run_worker():
 
     while True:
         try:
-            logging.info("Running scheduled scan...")
-            service.run_full_scan(source="periodic")
+            active_season = settings.seasons[0]  # sorted descending by year; first = active
+            logging.info(f"Running scheduled scan for active season: {active_season.name}")
+            service.run_full_scan(source="periodic", season_names=[active_season.name])
             logging.info("Finished scheduled scan.")
 
             if daily_time:

installer/data-downloader/backend/requirements.txt

@@ -2,4 +2,5 @@ fastapi==0.115.4
 uvicorn[standard]==0.23.2
 influxdb3-python==0.16.0
 pydantic==2.9.2
-slicks>=0.2.0
+slicks>=0.2.1
+docker>=7.0.0

installer/data-downloader/backend/services.py

@@ -80,14 +80,15 @@ def get_seasons(self) -> List[dict]:
             for s in self.settings.seasons
         ]
 
-    def run_full_scan(self, source: str = "manual") -> Dict[str, dict]:
+    def run_full_scan(self, source: str = "manual", season_names: list[str] | None = None) -> Dict[str, dict]:
         self.status_repo.mark_start(source)
         results = {}
         errors = []
-        
+
         try:
-            # Sort seasons by year descending to ensure most recent is scanned first
             sorted_seasons = sorted(self.settings.seasons, key=lambda s: s.year, reverse=True)
+            if season_names is not None:
+                sorted_seasons = [s for s in sorted_seasons if s.name in season_names]
             for season in sorted_seasons:
                 try:
                     logger.info(f"Scanning season {season.name} (DB: {season.database})...")
@@ -97,7 +98,7 @@ def run_full_scan(self, source: str = "manual") -> Dict[str, dict]:
                             host=self.settings.influx_host,
                             token=self.settings.influx_token,
                             database=season.database,
-                            table=f"{self.settings.influx_schema}.{self.settings.influx_table}",
+                            table=f"{self.settings.influx_schema}.{season.table}",
                             year=season.year,
                             bin_size=self.settings.scanner_bin,
                             include_counts=self.settings.scanner_include_counts,
@@ -116,7 +117,7 @@ def run_full_scan(self, source: str = "manual") -> Dict[str, dict]:
                             token=self.settings.influx_token,
                             database=season.database,
                             schema=self.settings.influx_schema,
-                            table=self.settings.influx_table,
+                            table=season.table,
                             window_days=self.settings.sensor_window_days,
                             lookback_days=self.settings.sensor_lookback_days,
                             fallback_start=fallback_start,
@@ -136,13 +137,18 @@ def run_full_scan(self, source: str = "manual") -> Dict[str, dict]:
                     errors.append(f"{season.name}: {str(e)}")
                     # Continue scanning other seasons even if one fails
 
+            total_runs = sum(v["runs"] for v in results.values())
+            total_sensors = sum(v["sensors"] for v in results.values())
             if errors:
                 self.status_repo.mark_finish(success=False, error="; ".join(errors))
             else:
-                self.status_repo.mark_finish(success=True)
+                self.status_repo.mark_finish(
+                    success=True,
+                    runs_count=total_runs,
+                    sensors_count=total_sensors,
+                )
 
             return results
-
         except Exception as exc:
             self.status_repo.mark_finish(success=False, error=str(exc))
             raise

installer/data-downloader/backend/storage.py

@@ -69,7 +69,7 @@ def merge_scanned_runs(self, scanned: List[dict]) -> dict:
 
         # Keep runs that vanished but still have notes to preserve manual metadata
         for key, run in existing.items():
-            if key not in merged:
+            if key not in merged and run.get("note"):
                 merged[key] = run
 
         runs_list = sorted(
@@ -158,6 +158,11 @@ def __init__(self, data_dir: Path):
             "source": None,
             "last_result": None,
             "error": None,
+            "last_successful_job_timestamp": None,
+            "error_count": 0,
+            "last_scan_runs_count": None,
+            "last_scan_sensors_count": None,
+            "last_scan_duration_seconds": None,
         }
         self.store = JSONStore(data_dir / "scanner_status.json", default)
 
@@ -178,19 +183,41 @@ def mark_start(self, source: str) -> dict:
         self.store.write(payload)
         return payload
 
-    def mark_finish(self, success: bool, error: str | None = None) -> dict:
+    def mark_finish(
+        self,
+        success: bool,
+        error: str | None = None,
+        runs_count: int | None = None,
+        sensors_count: int | None = None,
+    ) -> dict:
         payload = self.store.read()
+        now = now_iso()
         payload.update(
             {
                 "scanning": False,
-                "finished_at": now_iso(),
+                "finished_at": now,
                 "last_result": "success" if success else "error",
             }
         )
         if success:
             payload.pop("error", None)
+            payload["last_successful_job_timestamp"] = now
+            if runs_count is not None:
+                payload["last_scan_runs_count"] = runs_count
+            if sensors_count is not None:
+                payload["last_scan_sensors_count"] = sensors_count
+            started_at = payload.get("started_at")
+            if started_at:
+                try:
+                    duration = (
+                        datetime.fromisoformat(now) - datetime.fromisoformat(started_at)
+                    ).total_seconds()
+                    payload["last_scan_duration_seconds"] = round(duration, 2)
+                except ValueError:
+                    pass
         else:
             payload["error"] = error or "scan failed"
-        payload["updated_at"] = now_iso()
+            payload["error_count"] = payload.get("error_count", 0) + 1
+        payload["updated_at"] = now
         self.store.write(payload)
         return payload

installer/data-downloader/frontend/src/App.tsx

@@ -24,6 +24,7 @@ export default function App() {
   const [noteDrafts, setNoteDrafts] = useState<Record<string, string>>({});
   const [savingKey, setSavingKey] = useState<string | null>(null);
   const [scanState, setScanState] = useState<ScanState>("idle");
+  const [scanSeason, setScanSeason] = useState<string>("");
   const [downloaderSelection, setDownloaderSelection] = useState<DownloaderSelection | null>(null);
   const [scannerStatus, setScannerStatus] = useState<ScannerStatus | null>(null);
   const sensorsSectionRef = useRef<HTMLElement | null>(null);
@@ -43,6 +44,7 @@ export default function App() {
         if (seasonsList.length > 0 && !currentSeason) {
           currentSeason = seasonsList[0].name;
           setSelectedSeason(currentSeason);
+          setScanSeason(currentSeason);
         }
       }
 
@@ -114,7 +116,7 @@ export default function App() {
       updated_at: new Date().toISOString()
     }));
     try {
-      await triggerScan();
+      await triggerScan(scanSeason || undefined);
       setScanState("success");
       if (typeof window !== "undefined") {
         window.setTimeout(() => {
@@ -259,6 +261,18 @@ export default function App() {
       )}
 
       <div className="actions">
+        {seasons.length > 1 && (
+          <select
+            value={scanSeason}
+            onChange={(e) => setScanSeason(e.target.value)}
+            disabled={scanButtonDisabled}
+            style={{ padding: "0.5rem", borderRadius: "4px", border: "1px solid #ccc", fontSize: "0.9rem" }}
+          >
+            {seasons.map(s => (
+              <option key={s.name} value={s.name}>{s.name}</option>
+            ))}
+          </select>
+        )}
         <button className="button" onClick={handleScan} disabled={scanButtonDisabled}>
           {scanButtonLabel}
         </button>

installer/data-downloader/frontend/src/api.ts

@@ -52,8 +52,9 @@ export function fetchScannerStatus(): Promise<ScannerStatus> {
   return request("/api/scanner-status");
 }
 
-export function triggerScan(): Promise<{ status: string }> {
-  return request("/api/scan", { method: "POST" });
+export function triggerScan(season?: string): Promise<{ status: string }> {
+  const query = season ? `?season=${encodeURIComponent(season)}` : "";
+  return request(`/api/scan${query}`, { method: "POST" });
 }
 
 export function updateNote(key: string, note: string, season?: string): Promise<RunRecord> {

installer/docker-compose.yml

@@ -199,6 +199,7 @@ services:
       - "8000:8000"
     volumes:
       - ./data-downloader/data:/app/data
+      - /var/run/docker.sock:/var/run/docker.sock
     restart: unless-stopped
     networks:
       - datalink
@@ -230,6 +231,28 @@ services:
       data-downloader-api:
         condition: service_started
 
+  health-monitor:
+    build: ./health-monitor
+    container_name: health-monitor
+    restart: unless-stopped
+    environment:
+      HEALTH_MONITOR_INTERVAL_SECONDS: "${HEALTH_MONITOR_INTERVAL_SECONDS:-60}"
+      INFLUXDB_URL: "${INFLUXDB_URL:-http://influxdb3:8181}"
+      INFLUXDB_ADMIN_TOKEN: "${INFLUXDB_ADMIN_TOKEN:-apiv3_dev-influxdb-admin-token}"
+      INFLUXDB_HEALTH_DATABASE: "${INFLUXDB_HEALTH_DATABASE:-monitoring}"
+      HEALTH_MONITOR_INFLUXDB_CONTAINER: "${HEALTH_MONITOR_INFLUXDB_CONTAINER:-influxdb3}"
+      HEALTH_MONITOR_SCANNER_CONTAINER: "${HEALTH_MONITOR_SCANNER_CONTAINER:-data-downloader-scanner}"
+      HEALTH_MONITOR_SCANNER_API_URL: "${HEALTH_MONITOR_SCANNER_API_URL:-http://data-downloader-api:8000}"
+    volumes:
+      - /var/run/docker.sock:/var/run/docker.sock
+    networks:
+      - datalink
+    depends_on:
+      influxdb3:
+        condition: service_healthy
+      data-downloader-api:
+        condition: service_started
+
   data-downloader-frontend:
     build:
       context: ./data-downloader