feat: search --hop walks FROM_FILE to Person.
Tests / Test (push) Skipped
Tests / Release (semver) (push) Skipped
Tests / Test (pull_request) Failing after 3s
Tests / Release (semver) (pull_request) Skipped

Parser no longer errors; hop 1 returns File, hop 3 reaches Person.
Rebuild writes Leaf-[:FROM_FILE]->File so the walk is not empty
on a fresh index (Gitea #17).
This commit is contained in:
2026-08-14 10:48:22 +01:00
parent 9d1a3f3c70
commit 9a32dce0ca
17 changed files with 261 additions and 59 deletions
+47
View File
@@ -162,6 +162,53 @@ def add_leafs(conn: ladybug.Connection, leafs: list[dict]) -> list[str]:
return ids
def file_id(repo: str, path: str) -> str:
"""Stable File.id matching gitimport (`repo:path`)."""
return f"{repo}:{path}" if repo else path
def link_from_file(conn: ladybug.Connection, leaf_id: str, path: str,
repo: str = "", mtime: str = "") -> str:
"""MERGE File and Leaf-[:FROM_FILE]->File so --hop 1 can walk."""
fid = file_id(repo, path)
conn.execute(
"MERGE (f:File {id:$id}) SET f.path=$path, f.repo=$repo, f.mtime=$mtime",
parameters={"id": fid, "path": path, "repo": repo, "mtime": mtime},
)
conn.execute(
"MATCH (l:Leaf {id:$lid}), (f:File {id:$fid}) "
"MERGE (l)-[:FROM_FILE]->(f)",
parameters={"lid": leaf_id, "fid": fid},
)
return fid
HOP_STMTS = {
1: "MATCH (l:Leaf {id:$id})-[:FROM_FILE]->(f:File) RETURN f.id, f.path, 1",
2: ("MATCH (l:Leaf {id:$id})-[:FROM_FILE]->(f:File)-[:HAS_VERSION]->(c:Commit) "
"RETURN c.id, c.subject, 2"),
3: ("MATCH (l:Leaf {id:$id})-[:FROM_FILE]->(f:File)-[:HAS_VERSION]->(c:Commit)"
"-[:AUTHORED]->(p:Person) RETURN p.id, p.name, 3"),
}
HOP_LABELS = {1: "File", 2: "Commit", 3: "Person"}
def hop_walk(conn: ladybug.Connection, leaf_id: str, n: int) -> list[dict]:
"""Walk Leaf → File → Commit → Person up to n hops (max 3)."""
depth = min(max(int(n), 0), 3)
out: list[dict] = []
for d in range(1, depth + 1):
rows = conn.execute(HOP_STMTS[d], parameters={"id": leaf_id}).get_all()
for row in rows:
out.append({
"id": row[0],
"label": HOP_LABELS[d],
"name": row[1],
"depth": int(row[2]),
})
return out
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()
+33
View File
@@ -161,6 +161,39 @@ class KblibTest(unittest.TestCase):
self.assertEqual(stats["total"], 2)
self.assertEqual(stats["by_root"], {"facts": 1, "info": 1})
def test_hop_1_returns_file_hop_3_reaches_person(self):
"""--hop walks FROM_FILE / HAS_VERSION / AUTHORED (Gitea #17)."""
import gitimport
lid = kblib.upsert_leaf(
self.conn, text="readme hop fixture", root="info",
confidence="confirmed", source="README.md", source_rev="r1",
how="test", loc="README.md", type_="reference",
embedding=make_emb(0.3),
)
kblib.link_from_file(self.conn, lid, "README.md", repo="sample-repo")
gitimport.index_commits(self.conn, [gitimport.Commit(
sha="a1b2c3d",
author="Ada Lovelace",
email="ada@example.com",
date="2026-08-10T12:00:00Z",
subject="feat: first commit",
files=["README.md"],
)], "sample-repo")
hop1 = kblib.hop_walk(self.conn, lid, 1)
self.assertEqual(len(hop1), 1)
self.assertEqual(hop1[0]["label"], "File")
self.assertEqual(hop1[0]["name"], "README.md")
self.assertEqual(hop1[0]["depth"], 1)
hop3 = kblib.hop_walk(self.conn, lid, 3)
labels = {n["label"] for n in hop3}
self.assertIn("File", labels)
self.assertIn("Commit", labels)
self.assertIn("Person", labels)
person = [n for n in hop3 if n["label"] == "Person"][0]
self.assertEqual(person["name"], "Ada Lovelace")
self.assertEqual(person["depth"], 3)
if __name__ == "__main__":
unittest.main()
+7 -11
View File
@@ -1,7 +1,6 @@
"""Published docs must match live commands (Gitea SoT, brain/search, no fake --hop)."""
"""Published docs must match live commands (Gitea SoT, brain/search)."""
from __future__ import annotations
import re
import unittest
from pathlib import Path
@@ -139,24 +138,21 @@ class PublishedDocsTest(unittest.TestCase):
skill = (ROOT / "skills" / "brain" / "SKILL.md").read_text()
self.assertIn("`web` block", skill)
def test_docs_do_not_claim_hop_walks(self) -> None:
def test_docs_say_hop_walks_from_file(self) -> None:
paths = [
ROOT / "README.md",
ROOT / "docs" / "design.md",
ROOT / "skills" / "brain" / "SKILL.md",
ROOT / "skills" / "diataxis-docs" / "SKILL.md",
ROOT / "docs" / "runbook.md",
ROOT / "docs" / "README.md",
ROOT / "docs" / "roadmap.md",
]
# Command-style `--hop 1` / `--hop N` plus follow/walk = the old lie.
# Honest "not implemented" notes must not match.
lie = re.compile(r"--hop (?:N|1).*(?:follow|walk)", re.I | re.S)
for path in paths:
text = path.read_text()
self.assertIsNone(
lie.search(text),
f"{path.relative_to(ROOT)} still claims --hop walks the graph",
self.assertIn("--hop", text, f"{path.relative_to(ROOT)} must document --hop")
self.assertNotIn(
"not implemented",
text.lower(),
f"{path.relative_to(ROOT)} still says hop is not implemented",
)
def test_docs_are_portable_diataxis(self) -> None: