From a26f24ef7bd5cb27f71adb9ddd23dd3bb2dbedcf Mon Sep 17 00:00:00 2001
From: Safi <safishamsi98@gmail.com>
Date: Tue, 26 May 2026 14:53:36 +0100
Subject: [PATCH] fix stale nodes persisting after file deletion when manifest
 uses absolute paths

prune_set in build_merge now includes relative-path variants of each deleted file
so manifest absolute paths (e.g. /home/user/corpus/module_b/utils.py) match graph
node source_file values (e.g. module_b/utils.py) regardless of OS or run context.
Fixes #1007.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 graphify/build.py   | 11 +++++++++++
 tests/test_build.py | 30 ++++++++++++++++++++++++++++++
 2 files changed, 41 insertions(+)

diff --git a/graphify/build.py b/graphify/build.py
index 245fea29..579d7a35 100644
--- a/graphify/build.py
+++ b/graphify/build.py
@@ -338,6 +338,17 @@ def build_merge(
     # Prune nodes and edges from deleted source files
     if prune_sources:
         prune_set = set(prune_sources)
+        # Manifest stores absolute paths; graph nodes store relative paths.
+        # Add relative variants so both formats match regardless of OS or
+        # whether paths were relativized at build time (#1007).
+        if root is not None:
+            import os as _os
+            _root = Path(root)
+            for p in list(prune_sources):
+                try:
+                    prune_set.add(str(Path(p).relative_to(_root)).replace(_os.sep, "/"))
+                except ValueError:
+                    pass
         to_remove = [
             n for n, d in G.nodes(data=True)
             if d.get("source_file") in prune_set
diff --git a/tests/test_build.py b/tests/test_build.py
index 58f2863c..7552aa6a 100644
--- a/tests/test_build.py
+++ b/tests/test_build.py
@@ -346,6 +346,36 @@ def test_build_from_json_relative_source_file_unchanged(tmp_path):
     assert G.nodes["foo_bar"]["source_file"] == "src/foo.py"
 
 
+def test_build_merge_prune_absolute_paths_match_relative_nodes(tmp_path):
+    """#1007: manifest stores absolute paths, graph nodes store relative paths.
+    prune_sources with absolute paths must still remove the right nodes."""
+    import json
+    from graphify.export import to_json
+
+    root = tmp_path / "corpus"
+    root.mkdir()
+    graph_path = tmp_path / "graph.json"
+
+    # Simulate a graph with relative source_file paths (as built normally)
+    chunk = {"nodes": [
+        {"id": "n1", "label": "login", "file_type": "code", "source_file": "module_a/auth.py"},
+        {"id": "n2", "label": "format_date", "file_type": "code", "source_file": "module_b/utils.py"},
+    ], "edges": []}
+    G0 = build([chunk], dedup=False)
+    import networkx as nx
+    graph_path.write_text(
+        json.dumps(nx.node_link_data(G0, edges="edges")), encoding="utf-8"
+    )
+
+    # prune_sources from manifest — absolute paths
+    deleted_abs = [str(root / "module_b" / "utils.py")]
+    G1 = build_merge([], graph_path, prune_sources=deleted_abs, dedup=False, root=root)
+
+    node_labels = {d["label"] for _, d in G1.nodes(data=True)}
+    assert "format_date" not in node_labels, "stale node from deleted file should be pruned"
+    assert "login" in node_labels, "unrelated node must survive"
+
+
 def test_build_merge_rejects_oversized_existing_graph(monkeypatch, tmp_path):
     """#F4: build_merge must refuse to read an existing graph.json that
     exceeds the size cap, rather than json.loads-ing it into memory."""