Fix transcript search snippet positioning (#6206)

src/session_search.py

@@ -67,15 +67,34 @@ def _snippet(content: str, query: str, radius: int = 60) -> str:
     if not query:
         return content[: radius * 2]
 
-    idx = content.lower().find(query.lower())
-    if idx == -1:
+    match_start = -1
+    match_length = 0
+    lowered_content = content.lower()
+    for candidate in _query_terms(query):
+        idx = lowered_content.find(candidate.lower())
+        if idx != -1 and (match_start == -1 or idx < match_start):
+            match_start = idx
+            match_length = len(candidate)
+
+    if match_start == -1:
         return content[: radius * 2]
 
-    start = max(0, idx - radius)
-    end = min(len(content), idx + len(query) + radius)
+    start = max(0, match_start - radius)
+    end = min(len(content), match_start + match_length + radius)
     return ("..." if start > 0 else "") + content[start:end] + ("..." if end < len(content) else "")
 
 
+def _query_terms(query: str) -> list[str]:
+    """Return meaningful quoted phrases and tokens in user-entered order."""
+    terms: list[str] = []
+    for match in re.finditer(r'"([^"]+)"|[\w][\w._-]*', query, flags=re.UNICODE):
+        term = match.group(1) if match.group(1) is not None else match.group(0).strip("._-")
+        term = term.strip()
+        if term:
+            terms.append(term)
+    return terms
+
+
 def _sanitize_fts_query(query: str) -> str | None:
     """Convert free text into a conservative FTS5 MATCH query.
 

tests/test_session_search.py

@@ -8,7 +8,7 @@ from sqlalchemy.orm import sessionmaker
 from core.database import Base
 from core.database import ChatMessage as DbChatMessage
 from core.database import Session as DbSession
-from src.session_search import SessionSearchResult, search_session_messages
+from src.session_search import SessionSearchResult, _snippet, search_session_messages
 
 
 def _db(with_fts=True):
@@ -61,6 +61,47 @@ def _has_fts(db):
     )
 
 
+def test_snippet_locates_quoted_phrase_instead_of_raw_query():
+    content = "A" * 100 + "The session search result is useful." + "Z" * 100
+
+    snippet = _snippet(content, '"session search"', radius=20)
+
+    assert "session search" in snippet
+    assert snippet.startswith("...")
+    assert snippet.endswith("...")
+
+
+def test_snippet_locates_punctuation_bearing_term_case_insensitively():
+    content = "A" * 100 + "Use FOO_BAR.py for routing." + "Z" * 100
+
+    snippet = _snippet(content, "foo_bar.py!", radius=20)
+
+    assert "FOO_BAR.py" in snippet
+
+
+def test_snippet_uses_first_meaningful_matching_term():
+    content = "A" * 100 + "second appears here; first appears later." + "Z" * 100
+
+    snippet = _snippet(content, "first second", radius=12)
+
+    assert "second appears" in snippet
+    assert "first appears" not in snippet
+
+
+def test_snippet_falls_back_to_content_start_when_no_term_matches():
+    content = "Beginning of the transcript, followed by more detail."
+
+    assert _snippet(content, '"missing phrase"', radius=10) == content[:20]
+
+
+def test_snippet_preserves_boundary_markers_and_truncation():
+    content = "A" * 50 + "target" + "Z" * 50
+
+    snippet = _snippet(content, "target", radius=5)
+
+    assert snippet == "...AAAAAtargetZZZZZ..."
+
+
 def test_session_search_uses_fts_and_returns_context():
     db = _db(with_fts=True)
     try: