fix(search): qualify ambiguous column names with table alias in FTS JOIN

Both log_fts and log_entries have timestamp_iso, severity, source_id, and
matched_patterns columns. After the JOIN, unqualified references to any of
these caused SQLite to raise 'ambiguous column name', silently falling back
to the non-FTS scan path on every time-filtered or severity-filtered query.

Prefix all filter conditions that touch FTS-mirror columns with f. to
resolve the ambiguity. The e. prefix on tenant_id was already correct since
tenant_id is not present in the FTS virtual table.

app/services/search.py

@@ -244,19 +244,19 @@ def _sqlite_fts_search(
     params: list = [fts_query, tid]
 
     if severity:
-        conditions.append("severity = ?")
+        conditions.append("f.severity = ?")
         params.append(severity.upper())
     if source_filter:
-        conditions.append("source_id LIKE ?")
+        conditions.append("f.source_id LIKE ?")
         params.append(f"%{source_filter}%")
     if pattern_filter:
-        conditions.append("matched_patterns LIKE ?")
+        conditions.append("f.matched_patterns LIKE ?")
         params.append(f'%"{pattern_filter}"%')
     if since:
-        conditions.append("timestamp_iso >= ?")
+        conditions.append("f.timestamp_iso >= ?")
         params.append(since)
     if until:
-        conditions.append("timestamp_iso <= ?")
+        conditions.append("f.timestamp_iso <= ?")
         params.append(until)
     if not include_repeats:
         conditions.append("f.repeat_count = 1")