fix: search analytics crashes recording when the JSON file predates a counter (#1224)

* refactor: single _default_analytics() instead of duplicated default dicts

* fix: merge analytics defaults so an old/partial file doesn't KeyError on record

* test: analytics load merges defaults; record survives a partial file

src/search/analytics.py

@@ -45,24 +45,8 @@ class RateLimitError(SearchEngineError):
 # ----------------------------------------------------------------------
 # Analytics helpers
 # ----------------------------------------------------------------------
-def _load_analytics() -> Dict[str, Any]:
-    """Load analytics data from the JSON file, creating defaults if missing."""
-    if not ANALYTICS_FILE.exists():
-        default = {
-            "total_queries": 0,
-            "successful_queries": 0,
-            "failed_queries": 0,
-            "cache_hits": 0,
-            "cache_misses": 0,
-            "query_patterns": {},
-        }
-        _save_analytics(default)
-        return default
-    try:
-        with open(ANALYTICS_FILE, "r", encoding="utf-8") as f:
-            return json.load(f)
-    except Exception as e:
-        logger.warning(f"Failed to load analytics file: {e}")
+def _default_analytics() -> Dict[str, Any]:
+    """A fresh analytics document with every counter present."""
     return {
         "total_queries": 0,
         "successful_queries": 0,
@@ -73,6 +57,27 @@ def _load_analytics() -> Dict[str, Any]:
     }
 
 
+def _load_analytics() -> Dict[str, Any]:
+    """Load analytics data from the JSON file, creating defaults if missing."""
+    if not ANALYTICS_FILE.exists():
+        default = _default_analytics()
+        _save_analytics(default)
+        return default
+    try:
+        with open(ANALYTICS_FILE, "r", encoding="utf-8") as f:
+            data = json.load(f)
+        # Merge over defaults so a file written by an older schema (or a
+        # partial write) still has every counter — _record_query indexes
+        # these keys directly and would otherwise raise KeyError.
+        merged = _default_analytics()
+        if isinstance(data, dict):
+            merged.update(data)
+        return merged
+    except Exception as e:
+        logger.warning(f"Failed to load analytics file: {e}")
+        return _default_analytics()
+
+
 def _save_analytics(data: Dict[str, Any]) -> None:
     """Persist analytics data to the JSON file."""
     try:

tests/test_search_analytics_defaults.py

@@ -0,0 +1,33 @@
+"""Tests for analytics default-merge on load (src/search/analytics.py)."""
+import json
+
+import src.search.analytics as analytics
+
+
+def test_load_merges_defaults_for_partial_file(tmp_path, monkeypatch):
+    # A file written by an older schema is missing most counters.
+    f = tmp_path / "search_analytics.json"
+    f.write_text(json.dumps({"total_queries": 5}), encoding="utf-8")
+    monkeypatch.setattr(analytics, "ANALYTICS_FILE", f)
+
+    data = analytics._load_analytics()
+
+    # Existing value preserved, every missing counter filled with its default.
+    assert data["total_queries"] == 5
+    assert data["query_patterns"] == {}
+    for key in ("successful_queries", "failed_queries", "cache_hits", "cache_misses"):
+        assert data[key] == 0
+
+
+def test_record_query_survives_partial_file(tmp_path, monkeypatch):
+    f = tmp_path / "search_analytics.json"
+    f.write_text(json.dumps({"total_queries": 1}), encoding="utf-8")
+    monkeypatch.setattr(analytics, "ANALYTICS_FILE", f)
+
+    # Before the fix this raised KeyError on the missing counters.
+    analytics._record_query("hello world", success=True, cache_hit=False)
+
+    data = analytics._load_analytics()
+    assert data["total_queries"] == 2
+    assert data["successful_queries"] == 1
+    assert data["query_patterns"]["hello world"]["count"] == 1