navi-places: place_cache TTL (default 30 days) (#33)

When PR #30 (wikivoyage name-based discovery) landed, every place cached before
the fix kept returning stale (no-wikivoyage) responses until a manual TRUNCATE of
place_cache. A TTL makes enrichment changes propagate automatically.

- place_cache.py: cache_get now treats a hit older than the TTL as a miss, so the
  caller refetches + re-enriches and cache_put overwrites the row (no delete on
  read). TTL is NAVI_PLACE_CACHE_TTL_DAYS (default 30), via _ttl_seconds(). Entries
  with unknown age (cached_at 0/NULL, e.g. legacy rows) are treated as expired.
- No column migration needed: the schema already has cached_at INTEGER NOT NULL and
  cache_put already writes now(). Added an idempotent guard in get_conn anyway
  (PRAGMA table_info check -> ALTER TABLE ADD COLUMN cached_at INTEGER DEFAULT 0)
  so a hypothetical legacy on-disk DB predating the column self-heals; on the live
  DB and fresh DBs it is a no-op since CREATE TABLE already includes cached_at.

Tests (test_place.py): within-TTL hit served from cache (no refetch); past-TTL hit
refetches + refreshes cached_at; NAVI_PLACE_CACHE_TTL_DAYS=1 override expires a
2-day-old entry. Full navi-places suite: 21 passed.

Co-authored-by: Matt <mj@k7zvx.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

backend/services/navi_places/place_cache.py

@@ -15,9 +15,25 @@ import time
 
 DEFAULT_DB_PATH = '/var/lib/navi-backend/place_cache.db'
 
+# Cache entries older than this are treated as a miss so enrichment changes (new
+# wiki rewrites, etc.) propagate without a manual truncate. Override with the
+# NAVI_PLACE_CACHE_TTL_DAYS env var (days; default 30).
+DEFAULT_TTL_DAYS = 30
+
 _db_conn = None
 
 
+def _ttl_seconds():
+    """Cache entry lifetime in seconds (NAVI_PLACE_CACHE_TTL_DAYS, default 30 days)."""
+    raw = os.environ.get('NAVI_PLACE_CACHE_TTL_DAYS')
+    if raw is None:
+        return DEFAULT_TTL_DAYS * 86400
+    try:
+        return float(raw) * 86400
+    except ValueError:
+        return DEFAULT_TTL_DAYS * 86400
+
+
 def db_path():
     return os.environ.get('NAVI_PLACE_CACHE_DB', DEFAULT_DB_PATH)
 
@@ -56,6 +72,12 @@ def get_conn():
             call_count INTEGER NOT NULL DEFAULT 0
         )
     """)
+    # Idempotent TTL-column guard for any legacy DB predating cached_at (the CREATE
+    # above always includes it, so this only fires on an older on-disk DB). Existing
+    # rows get cached_at=0 -> treated as expired -> refreshed on next access.
+    cols = {r[1] for r in _db_conn.execute("PRAGMA table_info(place_cache)")}
+    if 'cached_at' not in cols:
+        _db_conn.execute("ALTER TABLE place_cache ADD COLUMN cached_at INTEGER DEFAULT 0")
     _db_conn.commit()
     return _db_conn
 
@@ -72,19 +94,28 @@ def reset_cache():
 
 
 def cache_get(osm_type, osm_id):
-    """Return cached place dict or None."""
+    """Return a cached place dict, or None on miss / TTL expiry.
+
+    A hit older than the TTL (NAVI_PLACE_CACHE_TTL_DAYS, default 30 days) is treated
+    as a miss so the caller refetches + re-enriches; the row is left in place and the
+    rewrite (cache_put) overwrites it. Entries with an unknown age (cached_at 0/NULL,
+    e.g. legacy rows) are likewise treated as expired.
+    """
     db = get_conn()
     row = db.execute(
-        "SELECT data FROM place_cache WHERE osm_type=? AND osm_id=?",
+        "SELECT data, cached_at FROM place_cache WHERE osm_type=? AND osm_id=?",
         (osm_type, osm_id)
     ).fetchone()
-    if row and row[0]:
+    if not row or not row[0]:
+        return None
+    cached_at = row[1]
+    if not cached_at or (time.time() - cached_at) > _ttl_seconds():
+        return None
     try:
         result = json.loads(row[0])
         result['source'] = 'cache'
         return result
     except (json.JSONDecodeError, TypeError):
-            pass
         return None
 
 

backend/services/navi_places/tests/test_place.py

@@ -301,3 +301,48 @@ def test_wiki_enrich_via_local_db_merges_fields(tmp_path, monkeypatch):
     d = client.get('/api/place/W/123').get_json()
     assert d['wiki_summary'] == 'A city.'
     assert d['wiki_url'] == 'https://en.wikipedia.org/wiki/Filer'
+
+
+# ── place_cache TTL ──
+
+def test_cache_hit_within_ttl_no_refetch(client, monkeypatch):
+    # Fresh entry (cached_at=now) is within the default 30-day TTL -> served from
+    # cache, no upstream call (FakeHTTP raises if hit).
+    place_cache.cache_put('N', 555, {'name': 'Fresh', 'extratags': {}}, 'nominatim_local')
+    monkeypatch.setattr(pd, 'http_requests', FakeHTTP())  # raises if called
+    d = client.get('/api/place/N/555').get_json()
+    assert d['name'] == 'Fresh' and d['source'] == 'cache'
+
+
+def test_cache_hit_past_ttl_refetches_and_updates(client, monkeypatch):
+    import time
+    # Seed a stale entry and backdate it well past the 30-day TTL.
+    place_cache.cache_put('W', 123, {'name': 'Stale', 'extratags': {}}, 'nominatim_local')
+    old = int(time.time()) - 31 * 86400
+    conn = place_cache.get_conn()
+    conn.execute("UPDATE place_cache SET cached_at=? WHERE osm_type='W' AND osm_id=123", (old,))
+    conn.commit()
+    # Past TTL -> treated as a miss -> refetch from (mocked) Nominatim + re-cache.
+    monkeypatch.setattr(pd, 'http_requests', FakeHTTP(get=lambda url, **kw: FakeResp(200, NOMINATIM_CAFE)))
+    d = client.get('/api/place/W/123').get_json()
+    assert d['name'] == 'Test Cafe'          # fresh upstream value, not 'Stale'
+    assert d['source'] == 'nominatim_local'  # refetched, not 'cache'
+    # cached_at refreshed to ~now (no longer the backdated value)
+    cached_at = conn.execute(
+        "SELECT cached_at FROM place_cache WHERE osm_type='W' AND osm_id=123").fetchone()[0]
+    assert cached_at > old and (time.time() - cached_at) < 60
+
+
+def test_cache_ttl_env_override(client, monkeypatch):
+    import time
+    # A 1-day TTL expires an entry aged 2 days -> refetch.
+    monkeypatch.setenv('NAVI_PLACE_CACHE_TTL_DAYS', '1')
+    place_cache.cache_put('N', 777, {'name': 'Old', 'extratags': {}}, 'nominatim_local')
+    conn = place_cache.get_conn()
+    conn.execute("UPDATE place_cache SET cached_at=? WHERE osm_type='N' AND osm_id=777",
+                 (int(time.time()) - 2 * 86400,))
+    conn.commit()
+    nom = {**NOMINATIM_CAFE, 'osm_type': 'N', 'osm_id': 777}
+    monkeypatch.setattr(pd, 'http_requests', FakeHTTP(get=lambda url, **kw: FakeResp(200, nom)))
+    d = client.get('/api/place/N/777').get_json()
+    assert d['source'] == 'nominatim_local'   # expired under the 1-day override