Upload staff_service.py

src/services/staff_service.py

@@ -123,9 +123,13 @@ def should_attempt_staff_lookup(question: str) -> bool:
 
 def match_staff_name(question: str) -> Optional[Dict]:
     """
-    Match by name tokens. Checks whether ALL of a staff member's name tokens
-    appear in the question (corrected direction vs v3.0).
-    Falls back to fuzzy matching for typos.
+    Match by name tokens. ALL of a staff member's name tokens must appear
+    in the question.
+
+    Single-token matches are only accepted if the token is distinctive
+    (≥6 chars and not a common word). This prevents short or common tokens
+    like 'hall', 'rani', 'brian', 'jason' from matching on unrelated queries.
+    Multi-token matches (e.g. 'nikesh narayanan', 'rani anand') always accepted.
     """
     if not should_attempt_staff_lookup(question):
         return None
@@ -134,12 +138,27 @@ def match_staff_name(question: str) -> Optional[Dict]:
     if not question_token_set:
         return None
 
-    # Exact token match: staff name tokens must all be present in question
+    # Tokens that are too common/short to be used as sole match criteria
+    _WEAK_TOKENS = {
+        "hall", "rani", "brian", "alia", "jason", "walter",
+        "anand", "fetty",
+    }
+
     for staff in STAFF_DIRECTORY:
         staff_name_tokens: set[str] = set()
         for tok in staff.get("tokens", []):
             staff_name_tokens.update(_normalize(tok))
-        if staff_name_tokens and staff_name_tokens.issubset(question_token_set):
+        if not staff_name_tokens:
+            continue
+        if not staff_name_tokens.issubset(question_token_set):
+            continue
+        # All tokens matched — now check if match is strong enough
+        matched = staff_name_tokens & question_token_set
+        if len(matched) >= 2:
+            return staff
+        # Single token match — only accept if distinctive
+        sole = next(iter(matched))
+        if len(sole) >= 6 and sole not in _WEAK_TOKENS:
             return staff
 
     # Fuzzy fallback for typos (e.g. "Nikkesh", "Al Harrasi")
@@ -147,15 +166,12 @@ def match_staff_name(question: str) -> Optional[Dict]:
 
 
 def _fuzzy_staff_match(question: str) -> Optional[Dict]:
-    """Fuzzy match question against staff full names using difflib."""
-    q_lower = question.lower()
+    """
+    Fuzzy match individual question tokens against staff full names using difflib.
+    Whole-question comparison is skipped — it never matches because a full sentence
+    has near-zero similarity to a short name string.
+    """
     all_names = [s["full_name"].lower() for s in STAFF_DIRECTORY]
-    matches = difflib.get_close_matches(q_lower, all_names, n=1, cutoff=0.75)
-    if matches:
-        return next(
-            (s for s in STAFF_DIRECTORY if s["full_name"].lower() == matches[0]), None
-        )
-    # Also try individual tokens for partial names
     for token in _normalize(question):
         if len(token) < 4:
             continue