feat: write leafs incrementally without rebuilding the graph. (#29)

Ladybug 0.19 stays FTS/HNSW queryable on MERGE of new ids; DROP INDEX was the fatal path. bin/brain/add.go and POST /ingest land facts+info in one transaction so watch/mail/git can become leafs now (Gitea #14).
2026-08-14 10:46:59 +01:00
parent 8b5be9b659
commit 9d1a3f3c70
21 changed files with 487 additions and 55 deletions
@@ -0,0 +1,69 @@
+"""Incremental add writes leafs without deleting kb.lbug."""
+from __future__ import annotations
+
+import json
+import os
+import subprocess
+import sys
+import tempfile
+import unittest
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[2]
+
+
+class KbAddCLITest(unittest.TestCase):
+    def test_json_add_does_not_delete_db(self) -> None:
+        tmp = Path(tempfile.mkdtemp())
+        dbpath = tmp / "kb.lbug"
+        py = sys.executable
+        venv_py = ROOT / ".venv" / "bin" / "python"
+        if venv_py.is_file():
+            py = str(venv_py)
+        payload = {
+            "text": "cli zebra leaf",
+            "root": "info",
+            "source": "cli-test",
+            "confidence": "confirmed",
+            "how": "test",
+            "loc": str(tmp),
+            "type": "reference",
+            "embedding": [0.0] * 256,
+        }
+        payload["embedding"][0] = 0.3
+        proc = subprocess.run(
+            [py, str(ROOT / "bin" / "kb" / "add"), "--db", str(dbpath), "--json"],
+            cwd=ROOT,
+            input=json.dumps(payload),
+            capture_output=True,
+            text=True,
+            env=os.environ.copy(),
+            check=False,
+        )
+        self.assertEqual(proc.returncode, 0, proc.stderr)
+        self.assertTrue(dbpath.exists(), "add must create the db, not skip write")
+        out = json.loads(proc.stdout)
+        self.assertEqual(out.get("mode"), "add")
+        self.assertEqual(len(out.get("ids") or []), 1)
+        again = subprocess.run(
+            [py, str(ROOT / "bin" / "kb" / "add"), "--db", str(dbpath), "--json"],
+            cwd=ROOT,
+            input=json.dumps({
+                **payload,
+                "text": "second moose leaf",
+                "source": "cli-test-2",
+            }),
+            capture_output=True,
+            text=True,
+            env=os.environ.copy(),
+            check=False,
+        )
+        self.assertEqual(again.returncode, 0, again.stderr)
+        self.assertTrue(dbpath.exists())
+        second = json.loads(again.stdout)
+        self.assertEqual(len(second.get("ids") or []), 1)
+        self.assertNotEqual(out["ids"][0], second["ids"][0])
+
+
+if __name__ == "__main__":
+    unittest.main()