fix(cli): multi-word and literal-wildcard search in odysseus-docs (#7007)

* fix(cli): multi-word and literal-wildcard search in odysseus-docs

odysseus-docs search wrapped the whole query in one `%{query}%` LIKE over title/current_content, so multi-word queries only matched the exact adjacent phrase and literal % / _ acted as SQL wildcards. Split on whitespace, AND per token, and escape LIKE wildcards with the shared escape_like_pattern() helper. Whitespace-only queries now match all documents, consistent with document-library search.

Fixes #2123.

Tests: tests/cli/test_docs_cli_search.py (5 tests; multi-word, %, _, backslash, whitespace); 4 fail pre-fix, 5 pass post-fix. tests/cli full suite: 82 passed.

* test(cli): name whitespace-query search test accurately

The test passes a whitespace-only query, not an empty one; the old name implied a different input. Behavior is unchanged.

scripts/odysseus-docs

@@ -27,6 +27,7 @@ from pathlib import Path
 
 try:
     from core.database import SessionLocal, Document, DocumentVersion
+    from src.session_search import escape_like_pattern
     quiet_logs()
 except ModuleNotFoundError as e:
     sys.stderr.write(f"error: {e}\nhint: run from repo root with venv active.\n")
@@ -139,10 +140,17 @@ def cmd_export(args):
 def cmd_search(args):
     db = SessionLocal()
     try:
-        like = f"%{args.query}%"
+        # Per-term AND search: a single `%foo bar%` LIKE only matched the
-        rows = db.query(Document).filter(
+        # exact phrase, so "machine learning" missed docs containing both
-            (Document.title.ilike(like)) | (Document.current_content.ilike(like))
+        # words apart. LIKE wildcards are escaped per token.
-        ).order_by(Document.updated_at.desc()).limit(args.limit).all()
+        q = db.query(Document)
+        for tok in args.query.split():
+            term = f"%{escape_like_pattern(tok)}%"
+            q = q.filter(
+                Document.title.ilike(term, escape="\\")
+                | Document.current_content.ilike(term, escape="\\")
+            )
+        rows = q.order_by(Document.updated_at.desc()).limit(args.limit).all()
         emit([_serialize(d) for d in rows], args)
     finally:
         db.close()

tests/cli/test_docs_cli_content_length.py

@@ -3,7 +3,7 @@ from tests.helpers.db_stubs import make_core_db_stub
 
 
 def test_text_len_ignores_non_string_values(monkeypatch):
-    make_core_db_stub(monkeypatch, models=["Document", "DocumentVersion"])
+    make_core_db_stub(monkeypatch, models=["Document", "DocumentVersion", "ChatMessage", "Session"])
     cli = load_script("odysseus-docs")
 
     assert cli._text_len("hello") == 5

tests/cli/test_docs_cli_search.py

@@ -0,0 +1,103 @@
+"""Regression for #2123 (CLI part): `odysseus-docs search` must match
+multi-word queries and treat % / _ literally.
+
+Old code built one ``%{query}%`` LIKE over title/current_content, so
+"machine learning" only matched the exact adjacent phrase, and a literal
+"%" matched every document.
+"""
+
+import json
+from types import SimpleNamespace
+
+from sqlalchemy import create_engine
+from sqlalchemy.orm import sessionmaker
+from sqlalchemy.pool import NullPool
+
+import core.database as cdb
+from core.database import Document
+from tests.helpers.cli_loader import load_script
+
+
+def _cli_with_documents(monkeypatch, tmp_path):
+    engine = create_engine(
+        f"sqlite:///{tmp_path / 'docs_cli_search.db'}",
+        connect_args={"check_same_thread": False},
+        poolclass=NullPool,
+    )
+    cdb.Base.metadata.create_all(engine)
+    session_factory = sessionmaker(bind=engine, autoflush=False, autocommit=False)
+
+    db = session_factory()
+    try:
+        db.add_all(
+            [
+                Document(
+                    id="doc-multiword",
+                    title="ML notes",
+                    current_content="machine notes on learning",
+                ),
+                Document(
+                    id="doc-percent",
+                    title="Fabric",
+                    current_content="100% cotton",
+                ),
+                Document(
+                    id="doc-underscore",
+                    title="sale_2024",
+                    current_content="spring campaign",
+                ),
+                Document(
+                    id="doc-backslash",
+                    title="Path",
+                    current_content=r"C:\photos\sunset",
+                ),
+            ]
+        )
+        db.commit()
+    finally:
+        db.close()
+
+    cli = load_script("odysseus-docs")
+    monkeypatch.setattr(cli, "SessionLocal", session_factory)
+    return cli
+
+
+def _search_ids(cli, capsys, query):
+    cli.cmd_search(SimpleNamespace(query=query, limit=50, pretty=False))
+    return {doc["id"] for doc in json.loads(capsys.readouterr().out)}
+
+
+def test_search_matches_words_in_any_order(monkeypatch, tmp_path, capsys):
+    cli = _cli_with_documents(monkeypatch, tmp_path)
+
+    assert _search_ids(cli, capsys, "machine learning") == {"doc-multiword"}
+
+
+def test_search_escapes_percent_wildcard(monkeypatch, tmp_path, capsys):
+    cli = _cli_with_documents(monkeypatch, tmp_path)
+
+    assert _search_ids(cli, capsys, "%") == {"doc-percent"}
+
+
+def test_search_escapes_underscore_wildcard(monkeypatch, tmp_path, capsys):
+    cli = _cli_with_documents(monkeypatch, tmp_path)
+
+    # Unescaped, "_" matches any single char so every document matches.
+    assert _search_ids(cli, capsys, "_") == {"doc-underscore"}
+
+
+def test_search_escapes_backslash(monkeypatch, tmp_path, capsys):
+    cli = _cli_with_documents(monkeypatch, tmp_path)
+
+    assert _search_ids(cli, capsys, "\\") == {"doc-backslash"}
+
+
+def test_search_whitespace_query_returns_all(monkeypatch, tmp_path, capsys):
+    cli = _cli_with_documents(monkeypatch, tmp_path)
+
+    assert _search_ids(cli, capsys, "   ") == {
+        "doc-multiword",
+        "doc-percent",
+        "doc-underscore",
+        "doc-backslash",
+    }