From f87d0649c5e88d9451b5e8d91b6bbcd61d506159 Mon Sep 17 00:00:00 2001
From: azizur100389 <azizur100389@gmail.com>
Date: Sun, 3 May 2026 00:46:46 +0100
Subject: [PATCH] fix: silence "invalid file_type 'None'" warning on legacy
 graphs (#660)

Users running `graphify update .` against a graph that contains nodes
preserved from older graphify versions see the warning:

  [graphify] Extraction warning (31 issues): Node 1661 (id='telepathy_app')
  has invalid file_type 'None' - must be one of [...]

The cause: `_rebuild_code` in watch.py preserves nodes from the existing
graph.json that aren't in the new AST output. Some of those nodes
(stubs, semantic concepts created before file_type was always
populated) have file_type=null in the on-disk JSON, which becomes
Python None on load. The validator in validate.py:33 then flags every
such node.

Add a normalization step in `build_from_json` next to the existing
`source` -> `source_file` legacy canonicalization: if a node's
file_type is None or empty, default it to "concept" before validation.
This silences the false positive while keeping the validator strict for
genuinely invalid values like "weird_type".
---
 graphify/build.py   | 10 ++++++++-
 tests/test_build.py | 53 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 62 insertions(+), 1 deletion(-)

diff --git a/graphify/build.py b/graphify/build.py
index 2c2c773bb..af7349891 100644
--- a/graphify/build.py
+++ b/graphify/build.py
@@ -51,7 +51,9 @@ def build_from_json(extraction: dict, *, directed: bool = False) -> nx.Graph:
 
     # Canonicalize legacy node/edge schema before validation.
     for node in extraction.get("nodes", []):
-        if isinstance(node, dict) and "source" in node and "source_file" not in node:
+        if not isinstance(node, dict):
+            continue
+        if "source" in node and "source_file" not in node:
             # Count edges that reference this node so the warning is actionable (#479)
             node_id = node.get("id", "?")
             affected_edges = sum(
@@ -65,6 +67,12 @@ def build_from_json(extraction: dict, *, directed: bool = False) -> nx.Graph:
                 file=sys.stderr,
             )
             node["source_file"] = node.pop("source")
+        # Default missing/None file_type to "concept" so legacy graph.json
+        # entries (and stub nodes preserved by `_rebuild_code` from older
+        # graphify versions that didn't always populate file_type) don't
+        # trigger spurious "invalid file_type 'None'" validator warnings (#660).
+        if node.get("file_type") in (None, ""):
+            node["file_type"] = "concept"
 
     errors = validate_extraction(extraction)
     # Dangling edges (stdlib/external imports) are expected - only warn about real schema errors.
diff --git a/tests/test_build.py b/tests/test_build.py
index 2b47bc86d..3750b57d7 100644
--- a/tests/test_build.py
+++ b/tests/test_build.py
@@ -60,3 +60,56 @@ def test_build_merges_multiple_extractions():
     G = build([ext1, ext2])
     assert G.number_of_nodes() == 2
     assert G.number_of_edges() == 1
+
+
+def test_none_file_type_defaults_to_concept(capsys):
+    """Legacy nodes with file_type=None (e.g. preserved from older graph.json
+    by `_rebuild_code`) must not trigger 'invalid file_type None' warnings (#660)."""
+    ext = {
+        "nodes": [
+            {"id": "n1", "label": "Stub", "file_type": None, "source_file": "a.py"},
+            {"id": "n2", "label": "Real", "file_type": "code", "source_file": "b.py"},
+        ],
+        "edges": [],
+        "input_tokens": 0,
+        "output_tokens": 0,
+    }
+    G = build_from_json(ext)
+    err = capsys.readouterr().err
+    assert "invalid file_type" not in err
+    # The legacy node still exists in the graph and has been canonicalized
+    assert G.nodes["n1"]["file_type"] == "concept"
+    assert G.nodes["n2"]["file_type"] == "code"
+
+
+def test_missing_file_type_defaults_to_concept(capsys):
+    """Nodes missing file_type entirely should also be canonicalized to 'concept'."""
+    ext = {
+        "nodes": [
+            {"id": "n1", "label": "Bare", "source_file": "a.py"},
+        ],
+        "edges": [],
+        "input_tokens": 0,
+        "output_tokens": 0,
+    }
+    G = build_from_json(ext)
+    err = capsys.readouterr().err
+    assert "invalid file_type" not in err
+    assert "missing required field 'file_type'" not in err
+    assert G.nodes["n1"]["file_type"] == "concept"
+
+
+def test_real_invalid_file_type_still_warns(capsys):
+    """Truly invalid file_type values (not None, not empty) must still warn."""
+    ext = {
+        "nodes": [
+            {"id": "n1", "label": "Bad", "file_type": "weird_type", "source_file": "a.py"},
+        ],
+        "edges": [],
+        "input_tokens": 0,
+        "output_tokens": 0,
+    }
+    build_from_json(ext)
+    err = capsys.readouterr().err
+    assert "invalid file_type" in err
+    assert "weird_type" in err