Storage: configurable data dir for the external drive + daily DB prune

HOST_DATA_DIR in .env can now point /data at a host path (the 1TB
external drive) instead of the named volume, so odds history, caches
and snapshots stop eating the 128GB root disk. A daily prune drops
cache entries stale for over a week and ingest-log rows older than 14
days — faster polling no longer means unbounded DB growth.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

deploy/cup26.compose.yml

@@ -21,7 +21,11 @@ services:
       - ENABLE_SOFASCORE=${ENABLE_SOFASCORE:-false}
       - ENABLE_FOTMOB=${ENABLE_FOTMOB:-false}
     volumes:
-      - cup26-data:/data
+      # HOST_DATA_DIR (in .env) may point at a host path — e.g. the external
+      # 1TB drive — so the growing SQLite DB stays off the small root disk.
+      # An absolute path = bind mount; unset = the original named volume.
+      # The container runs as node (uid 1000): chown 1000:1000 the host dir.
+      - ${HOST_DATA_DIR:-cup26-data}:/data
     security_opt:
       - no-new-privileges:true
     mem_limit: 384m

server/src/db/db.ts

@@ -135,6 +135,19 @@ export function cacheSet(key: string, value: string, ttl: number): void {
     .run(key, value, Date.now(), ttl);
 }
 
+/** Bound DB growth: drop cache entries stale for >7 days (the breaker only ever
+ *  serves recent staleness) and ingest-log rows older than 14 days. Returns the
+ *  number of rows removed. Runs daily from the scheduler. */
+export function prune(now = Date.now()): number {
+  const cache = db()
+    .prepare('DELETE FROM kv_cache WHERE ? - fetched_at > ttl + 7 * 86400000')
+    .run(now);
+  const log = db()
+    .prepare('DELETE FROM ingest_log WHERE at < ?')
+    .run(now - 14 * 86400000);
+  return Number(cache.changes) + Number(log.changes);
+}
+
 // ---- source health / circuit breaker ----
 export interface SourceHealthRow {
   source: string;

server/src/ingest/scheduler.ts

@@ -4,7 +4,7 @@ import { fetchEspnScoreboard, fetchEspnSummary } from './espn';
 import { fetchEspnOdds } from './espnOdds';
 import { fetchFootballData } from '../footballData';
 import { fetchSofascore } from '../sofascore';
-import { setSourceMap, getSourceMap, setMatchExt, recordOdds, logIngest } from '../db/db';
+import { setSourceMap, getSourceMap, setMatchExt, recordOdds, logIngest, prune } from '../db/db';
 import type { Fixture } from '../../../src/lib/types';
 
 // The ingestion orchestrator. Replaces the old live loop: ESPN is the primary
@@ -161,6 +161,14 @@ export function startScheduler(
     oddsTimer = setTimeout(async () => { await oddsTick().catch(() => {}); scheduleOdds(); }, ODDS_MS);
   };
 
+  // Daily prune keeps the faster polling from growing kv_cache/ingest_log forever.
+  const pruneTimer = setInterval(() => {
+    try {
+      const n = prune();
+      if (n) console.log(`[db] pruned ${n} stale cache/log rows`);
+    } catch { /* non-fatal */ }
+  }, 24 * 60 * 60 * 1000);
+
   const scheduleLive = (): void => {
     if (stopped) return;
     const delay = pollDelay(state.hasLive(), state.hasLiveActivity(LIVE_WINDOW_MS));
@@ -188,5 +196,6 @@ export function startScheduler(
     if (liveTimer) clearTimeout(liveTimer);
     if (enrichTimer) clearTimeout(enrichTimer);
     if (oddsTimer) clearTimeout(oddsTimer);
+    clearInterval(pruneTimer);
   };
 }