Files
Manuel GanterandClaude Opus 5 1cb6369282 feat: mirror tag-vocabulary summary and note-type validation
Ports two changes from the knowledge-base vault this skeleton is extracted
from, keeping the shared scripts byte-identical across the pair:

- `graph_summary` reports `by_tag` and `tag_count`, sized by `topTags`, and
  drops the `by_type`/`by_status` breakdowns. An MCP-only agent could not
  otherwise discover the tag spellings that `graph_search_nodes` matches
  verbatim.
- `generate-graph.py --validate` now enforces a controlled vocabulary for a
  note's `type`, which is where the drift signal `by_type` used to give now
  lives. `AGENT_QUERY_GUIDE.md`, both skills and the-knowing-one quote the
  enforced enum.

`tests/test_generate_graph.py` is new; `make test` is 50 tests. Regenerating
the graph also drops a stale `GLOBAL_AGENTS` node for a file this skeleton
does not carry.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-14 11:37:02 +02:00

107 lines
3.6 KiB
Python

#!/usr/bin/env python3
"""Tests for the graph generator's validation gate.
`--validate` is the only thing standing between a typo in a note's frontmatter
and a vault whose facets quietly stop meaning anything, so these tests pin the
controlled vocabularies it enforces: the edge relationship types and the node
`type` enum. Each filesystem test builds a throwaway vault, never the real one.
"""
from __future__ import annotations
import importlib
import subprocess
import sys
import tempfile
import unittest
from pathlib import Path
SCRIPTS = Path(__file__).resolve().parents[1] / "scripts"
sys.path.insert(0, str(SCRIPTS))
gen = importlib.import_module("generate-graph")
def _node(node_id: str, note_type: str) -> dict:
return {"id": node_id, "path": f"{node_id}.md", "type": note_type}
class TestNoteTypeVocabulary(unittest.TestCase):
"""The node `type` enum is the drift signal; it has to be enforced."""
def test_covers_every_type_the_taxonomy_documents(self) -> None:
self.assertLessEqual(
{
"hub",
"project",
"area",
"guideline",
"policy",
"feature",
"roadmap",
"decision",
"note",
"meta",
"reference",
},
gen.NOTE_TYPES,
)
def test_accepts_a_graph_whose_nodes_are_all_in_the_vocabulary(self) -> None:
graph = {"nodes": [_node("a", "note"), _node("b", "area")], "edges": []}
self.assertEqual(gen.find_invalid_node_types(graph), [])
def test_reports_a_node_whose_type_is_outside_the_vocabulary(self) -> None:
graph = {"nodes": [_node("a", "note"), _node("b", "refrence")], "edges": []}
invalid = gen.find_invalid_node_types(graph)
self.assertEqual([n["id"] for n in invalid], ["b"])
class TestValidateExitCode(unittest.TestCase):
"""--validate must fail the run, not just print, on an unknown node type."""
def setUp(self) -> None:
self._tmp = tempfile.TemporaryDirectory()
self.root = Path(self._tmp.name).resolve() / "vault"
(self.root / "scripts").mkdir(parents=True)
(self.root / "03_resources").mkdir()
(self.root / "scripts" / "generate-graph.py").write_text(
(SCRIPTS / "generate-graph.py").read_text(encoding="utf-8"),
encoding="utf-8",
)
def tearDown(self) -> None:
self._tmp.cleanup()
def write_note(self, name: str, note_type: str) -> None:
(self.root / "03_resources" / name).write_text(
f"---\nid: {name[:-3]}\ntitle: {name}\ntype: {note_type}\n---\n\n# {name}\n",
encoding="utf-8",
)
def validate(self) -> subprocess.CompletedProcess:
return subprocess.run(
[sys.executable, "scripts/generate-graph.py", "--validate"],
cwd=self.root,
capture_output=True,
text=True,
)
def test_passes_on_a_vault_of_known_types(self) -> None:
self.write_note("good.md", "decision")
proc = self.validate()
self.assertEqual(proc.returncode, 0, proc.stdout + proc.stderr)
self.assertIn("all node types are in the controlled vocabulary", proc.stdout)
def test_fails_and_names_the_offending_note(self) -> None:
self.write_note("good.md", "decision")
self.write_note("bad.md", "descision")
proc = self.validate()
self.assertEqual(proc.returncode, 1)
self.assertIn("descision", proc.stdout)
self.assertIn("bad", proc.stdout)
if __name__ == "__main__":
unittest.main()