feat: write leafs incrementally without rebuilding the graph.

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).

bin/brain/add.go

@@ -0,0 +1,21 @@
+//usr/bin/env go run -tags=brain_add "$0" "$@"; exit
+//go:build brain_add
+//
+// bin/brain/add.go - incremental leaf write (Python kblib, no rebuild).
+//
+//	./bin/brain/add.go --text T --root facts --source "a.md x b.md"
+//	./bin/brain/add.go --json
+//
+// D6: write stays Python. Does not delete var/kb.lbug.
+// NOTE: never run `gofmt -w` on this file — it breaks the shebang.
+package main
+
+import (
+	"os"
+
+	"github.com/eSlider/2dph/internal/cmdbin"
+)
+
+func main() {
+	os.Exit(cmdbin.ExecFile("bin/kb/add", os.Args[1:]))
+}

bin/brain/index.go

@@ -7,8 +7,8 @@
 //	./bin/brain/index.go --rebuild --with-mail
 //	./bin/brain/index.go --dry-run --with-mail
 //
-// v1 write is always a rebuild when mail is included (live FTS/HNSW + bulk
-// insert corrupts Ladybug 0.19 WAL). `add` is v2.
+// v1 write: bin/brain/add.go for one/few leafs (indexes may already exist).
+// Bulk mail/corpus still --rebuild (fresh file, indexes last).
 // NOTE: never run `gofmt -w` on this file — it breaks the shebang.
 package main
 

bin/kb/add

@@ -0,0 +1,114 @@
+#!/usr/bin/env python3
+"""kb/add - incremental leaf write (no rebuild).
+
+  bin/kb/add --text T --root facts|info --source S
+  bin/kb/add --json                 # stdin: one object or {"leafs":[...]}
+  bin/kb/add --db PATH --json
+
+Writes facts+info in one Ladybug transaction. Does not delete kb.lbug.
+Embedding is used when provided; otherwise model2vec encodes the text.
+"""
+from __future__ import annotations
+
+import json
+import sys
+from pathlib import Path
+
+ROOT = Path(__file__).resolve().parents[2]
+sys.path.insert(0, str(ROOT / "bin" / "tools"))
+
+from kblib import (  # noqa: E402
+    EMBED_DIM,
+    add_leafs,
+    connect,
+    ensure_indexes,
+    init_schema,
+)
+
+
+def _as_leafs(payload: object) -> list[dict]:
+    if isinstance(payload, list):
+        return [dict(x) for x in payload]
+    if isinstance(payload, dict):
+        if "leafs" in payload:
+            return [dict(x) for x in payload["leafs"]]
+        return [dict(payload)]
+    raise ValueError("json must be an object, a list, or {leafs:[...]}")
+
+
+def _embed_missing(leafs: list[dict]) -> None:
+    missing = [lf for lf in leafs if not lf.get("embedding")]
+    if not missing:
+        return
+    from model2vec import StaticModel
+
+    model = StaticModel.from_pretrained("minishlab/potion-multilingual-128M")
+    for lf in missing:
+        text = str(lf.get("text") or "")
+        vec = model.encode([text])[0].astype(float).tolist()
+        if len(vec) != EMBED_DIM:
+            vec = (vec + [0.0] * EMBED_DIM)[:EMBED_DIM]
+        lf["embedding"] = vec
+
+
+def main(argv: list[str]) -> int:
+    import argparse
+
+    p = argparse.ArgumentParser(description="add leafs without rebuilding the brain")
+    p.add_argument("--db", default="", help="path to kb.lbug (default var/kb.lbug)")
+    p.add_argument("--json", action="store_true", help="read leaf JSON from stdin")
+    p.add_argument("--text", default="", help="leaf text")
+    p.add_argument("--root", default="info", choices=("facts", "info"))
+    p.add_argument("--source", default="")
+    p.add_argument("--confidence", default="confirmed")
+    p.add_argument("--source-rev", default="working-tree")
+    p.add_argument("--how", default="brain/add")
+    p.add_argument("--loc", default="")
+    p.add_argument("--type", default="reference", dest="type_")
+    args = p.parse_args(argv)
+
+    if args.json:
+        raw = sys.stdin.read()
+        if not raw.strip():
+            print("kb/add: empty stdin", file=sys.stderr)
+            return 2
+        leafs = _as_leafs(json.loads(raw))
+    else:
+        if not args.text or not args.source:
+            print("kb/add: --text and --source are required (or --json)", file=sys.stderr)
+            return 2
+        leafs = [{
+            "text": args.text,
+            "root": args.root,
+            "source": args.source,
+            "confidence": args.confidence,
+            "source_rev": args.source_rev,
+            "how": args.how,
+            "loc": args.loc or args.source,
+            "type": args.type_,
+        }]
+
+    for lf in leafs:
+        if not lf.get("text") or not lf.get("source"):
+            print("kb/add: each leaf needs text and source", file=sys.stderr)
+            return 2
+
+    _embed_missing(leafs)
+
+    from kblib import DB_PATH, VAR
+
+    dbpath = Path(args.db) if args.db else DB_PATH
+    dbpath.parent.mkdir(parents=True, exist_ok=True)
+    VAR.mkdir(exist_ok=True)
+    db, conn = connect(dbpath, read_only=False)
+    init_schema(conn)
+    ids = add_leafs(conn, leafs)
+    ensure_indexes(conn)
+    conn.close()
+    db.close()
+    print(json.dumps({"mode": "add", "ids": ids, "db": str(dbpath)}))
+    return 0
+
+
+if __name__ == "__main__":
+    sys.exit(main(sys.argv[1:]))

bin/tools/kblib.py

@@ -4,7 +4,7 @@ Single embedded graph `var/kb.lbug`. Two roots: facts (assertions backed by
 >=2 independent sources) and info (narrative leafs). Hybrid retrieval: BM25
 (FTS extension) + HNSW cosine (VECTOR extension) + Cypher graph hops.
 
-All access is read-only unless `--rebuild` is passed to kb/index.
+All access is read-only unless `--rebuild` (kb/index) or `kb/add`.
 """
 from __future__ import annotations
 
@@ -118,6 +118,50 @@ def upsert_leaf(conn: ladybug.Connection, *, text: str, root: str, confidence: s
     return lid
 
 
+def add_leafs(conn: ladybug.Connection, leafs: list[dict]) -> list[str]:
+    """Write facts+info leafs in one transaction. Safe while FTS/HNSW exist.
+
+    Each leaf dict: text, source, optional root/confidence/source_rev/how/loc/type/embedding.
+    Does not delete the database file. Measured on Ladybug 0.19: MERGE of new
+    ids (and updates) stays FTS+HNSW queryable; DROP INDEX is the fatal path.
+    """
+    if not leafs:
+        return []
+    started = False
+    try:
+        conn.execute("BEGIN TRANSACTION")
+        started = True
+    except Exception:
+        started = False
+    ids: list[str] = []
+    try:
+        for lf in leafs:
+            ids.append(
+                upsert_leaf(
+                    conn,
+                    text=str(lf["text"]),
+                    root=str(lf.get("root") or ROOT_INFO),
+                    confidence=str(lf.get("confidence") or CONF_CONFIRMED),
+                    source=str(lf["source"]),
+                    source_rev=str(lf.get("source_rev") or "working-tree"),
+                    how=str(lf.get("how") or "brain/add"),
+                    loc=str(lf.get("loc") or lf.get("source") or ""),
+                    type_=str(lf.get("type") or lf.get("type_") or "reference"),
+                    embedding=lf.get("embedding"),
+                )
+            )
+        if started:
+            conn.execute("COMMIT")
+    except Exception:
+        if started:
+            try:
+                conn.execute("ROLLBACK")
+            except Exception:
+                pass
+        raise
+    return ids
+
+
 def leaf_index_names(conn: ladybug.Connection) -> set[str]:
     """Return index names on the Leaf table (e.g. {'id', 'Leaf_vec', '_PK'})."""
     rows = conn.execute("CALL SHOW_INDEXES() RETURN *").get_all()

bin/tools/test_bin_layout.py

@@ -75,9 +75,20 @@ class BinLayoutTest(unittest.TestCase):
         )
 
     def test_brain_methods_are_shebangs(self) -> None:
-        for method in ("index.go", "get.go", "stats.go", "eval.go", "watch.go"):
+        for method in ("index.go", "add.go", "get.go", "stats.go", "eval.go", "watch.go"):
             self._assert_shebang(f"bin/brain/{method}")
 
+    def test_brain_add_is_python_write_not_rebuild(self) -> None:
+        self._assert_shebang("bin/brain/add.go")
+        text = (ROOT / "bin" / "brain" / "add.go").read_text()
+        self.assertIn("cmdbin.ExecFile", text)
+        self.assertIn("bin/kb/add", text)
+        self.assertNotIn("--rebuild", text)
+        py = (ROOT / "bin" / "kb" / "add").read_text()
+        self.assertIn("add_leafs", py)
+        self.assertIn("--json", py)
+        self.assertNotIn("unlink", py.lower())
+
     def test_brain_get_stats_eval_are_not_python_exec(self) -> None:
         for method in ("get.go", "stats.go", "eval.go"):
             text = (ROOT / "bin" / "brain" / method).read_text()

bin/tools/test_kb_add.py

@@ -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()

bin/tools/test_kblib.py

@@ -71,6 +71,69 @@ class KblibTest(unittest.TestCase):
         self.assertTrue(hits)
         self.assertIn("Leaf_vec", kblib.leaf_index_names(self.conn))
 
+    def test_add_after_indexes_keeps_fts_queryable(self):
+        """Incremental add after FTS+HNSW must find the new leaf on both indexes."""
+        kblib.upsert_leaf(self.conn, text="seed fox leaf", root="info",
+                          confidence="confirmed", source="s", source_rev="r1",
+                          how="test", loc="/tmp", type_="reference",
+                          embedding=make_emb(0.1))
+        kblib.ensure_indexes(self.conn)
+        ids = kblib.add_leafs(self.conn, [{
+            "text": "added zebra after index",
+            "root": "facts",
+            "confidence": "confirmed",
+            "source": "a.md x b.md",
+            "source_rev": "r1",
+            "how": "test",
+            "loc": "/tmp",
+            "type": "fact",
+            "embedding": make_emb(0.9),
+        }])
+        self.assertEqual(len(ids), 1)
+        fts = kblib.query_fts(self.conn, "zebra", 5)
+        self.assertTrue(fts)
+        self.assertIn("zebra", fts[0]["text"])
+        self.assertEqual(fts[0]["root"], "facts")
+        vec = kblib.query_vector(self.conn, make_emb(0.9), 5)
+        self.assertTrue(any("zebra" in h["text"] for h in vec))
+        fox = kblib.query_fts(self.conn, "fox", 5)
+        self.assertTrue(fox)
+        self.assertIn("fox", fox[0]["text"])
+
+    def test_add_facts_and_info_one_transaction(self):
+        """D12: facts and info land in the same transaction."""
+        kblib.ensure_indexes(self.conn)
+        ids = kblib.add_leafs(self.conn, [
+            {
+                "text": "tx fact leaf two-source",
+                "root": "facts",
+                "confidence": "confirmed",
+                "source": "compose.yml x docker ps",
+                "source_rev": "r1",
+                "how": "test",
+                "loc": "/tmp",
+                "type": "fact",
+                "embedding": make_emb(0.4),
+            },
+            {
+                "text": "tx info narrative",
+                "root": "info",
+                "confidence": "confirmed",
+                "source": "note.md",
+                "source_rev": "r1",
+                "how": "test",
+                "loc": "/tmp",
+                "type": "reference",
+                "embedding": make_emb(0.5),
+            },
+        ])
+        self.assertEqual(len(ids), 2)
+        stats = kblib.stats(self.conn)
+        self.assertEqual(stats["by_root"].get("facts"), 1)
+        self.assertEqual(stats["by_root"].get("info"), 1)
+        self.assertTrue(kblib.query_fts(self.conn, "two-source", 5))
+        self.assertTrue(kblib.query_fts(self.conn, "narrative", 5))
+
     def test_drop_vector_then_create_raises_clear_error(self):
         """DROP INDEX leaves ghost catalog; create_fts_and_vector must raise."""
         kblib.upsert_leaf(self.conn, text="seed", root="info",