feat: index facts extract and chats markdown on rebuild. (#31)

--with-facts / --facts-json write root=facts leafs; --with-chats picks up var/chats/md as info. WhatsApp sync stays out of v1 (Gitea #18).
2026-08-14 10:57:40 +01:00
parent a88dbb490c
commit c5be3f19be
10 changed files with 169 additions and 31 deletions
@@ -39,3 +39,59 @@ class IndexAdapterTest(unittest.TestCase):
        self.assertTrue(msg.get("dry_run"))
        self.assertGreaterEqual(msg.get("corpus_total", 0), 1)
        self.assertFalse(lbug.exists(), "dry-run must not create a Ladybug file")
+
+    def test_facts_json_and_chats_land_on_rebuild(self) -> None:
+        """Gitea #18: facts (2-source) + chats markdown become leafs on rebuild."""
+        tmp = Path(tempfile.mkdtemp())
+        dbpath = tmp / "kb.lbug"
+        chats = tmp / "chats"
+        chats.mkdir()
+        (chats / "alice.md").write_text(
+            "# Chat\n\n## Alice and Bob\n\nhello from chats fixture unique-chat-token\n",
+            encoding="utf-8",
+        )
+        facts_path = tmp / "facts.json"
+        facts_path.write_text(json.dumps([{
+            "text": "container 'brain' unique-fact-token is running and declared in compose.yaml",
+            "source": "docker ps x compose.yaml",
+            "loc": "compose.yaml:brain",
+            "how": "facts/extract",
+        }]), encoding="utf-8")
+        venv_py = ROOT / ".venv" / "bin" / "python"
+        py = str(venv_py) if venv_py.is_file() else sys.executable
+        proc = subprocess.run(
+            [
+                py, str(ROOT / "bin" / "kb" / "index"),
+                "--rebuild", "--db", str(dbpath), "--no-defaults",
+                "--with-chats", str(chats),
+                "--facts-json", str(facts_path),
+                "--json",
+            ],
+            cwd=ROOT,
+            capture_output=True,
+            text=True,
+            env=os.environ.copy(),
+            check=False,
+        )
+        self.assertEqual(proc.returncode, 0, proc.stderr)
+        msg = json.loads(proc.stdout)
+        self.assertGreaterEqual(msg.get("facts_leafs", 0), 1)
+        self.assertGreaterEqual(msg.get("chat_leafs", 0), 1)
+        self.assertTrue(dbpath.exists())
+        sys.path.insert(0, str(ROOT / "bin" / "tools"))
+        import kblib
+        db, conn = kblib.connect(dbpath, read_only=True)
+        try:
+            stats = kblib.stats(conn)
+            self.assertGreaterEqual(stats["by_root"].get("facts", 0), 1)
+            fts = kblib.query_fts(conn, "unique-chat-token", 5)
+            self.assertTrue(fts, "chats markdown must be FTS-searchable")
+            fact_hits = kblib.query_fts(conn, "unique-fact-token", 5)
+            self.assertTrue(any(h.get("root") == "facts" for h in fact_hits))
+            src = conn.execute(
+                "MATCH (l:Leaf {root:'facts'}) RETURN l.source"
+            ).get_all()
+            self.assertTrue(any(" x " in str(r[0]) for r in src))
+        finally:
+            conn.close()
+            db.close()