Fix 6 bugs: hook exit code, token budget, file node detection, duplicate function, atomic cache writes, deleted file tracking

graphify/analyze.py

@@ -16,12 +16,16 @@ def _is_file_node(G: nx.Graph, node_id: str) -> bool:
     These are synthetic nodes created by the AST extractor and should be excluded
     from god nodes, surprising connections, and knowledge gap reporting.
     """
-    label = G.nodes[node_id].get("label", "")
+    attrs = G.nodes[node_id]
+    label = attrs.get("label", "")
     if not label:
         return False
-    # File-level hub: label is a filename with a code extension
-    if label.split(".")[-1] in ("py", "ts", "js", "go", "rs", "java", "rb", "cpp", "c", "h"):
-        return True
+    # File-level hub: label matches the actual source filename (not just any label ending in .py)
+    source_file = attrs.get("source_file", "")
+    if source_file:
+        from pathlib import Path as _Path
+        if label == _Path(source_file).name:
+            return True
     # Method stub: AST extractor labels methods as '.method_name()'
     if label.startswith(".") and label.endswith("()"):
         return True

graphify/cache.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 
 import hashlib
 import json
+import os
 from pathlib import Path
 
 
@@ -46,7 +47,13 @@ def save_cached(path: Path, result: dict, root: Path = Path(".")) -> None:
     """
     h = file_hash(path)
     entry = cache_dir(root) / f"{h}.json"
-    entry.write_text(json.dumps(result))
+    tmp = entry.with_suffix(".tmp")
+    try:
+        tmp.write_text(json.dumps(result))
+        os.replace(tmp, entry)
+    except Exception:
+        tmp.unlink(missing_ok=True)
+        raise
 
 
 def cached_files(root: Path = Path(".")) -> set[str]:

graphify/detect.py

@@ -266,9 +266,14 @@ def detect_incremental(root: Path, manifest_path: str = _MANIFEST_PATH) -> dict:
             else:
                 unchanged_files[ftype].append(f)
 
+    # Files in manifest that no longer exist - their cached nodes are now ghost nodes
+    current_files = {f for flist in full["files"].values() for f in flist}
+    deleted_files = [f for f in manifest if f not in current_files]
+
     new_total = sum(len(v) for v in new_files.values())
     full["incremental"] = True
     full["new_files"] = new_files
     full["unchanged_files"] = unchanged_files
     full["new_total"] = new_total
+    full["deleted_files"] = deleted_files
     return full

graphify/export.py

@@ -8,6 +8,7 @@ from pathlib import Path
 import networkx as nx
 from networkx.readwrite import json_graph
 from graphify.security import sanitize_label
+from graphify.analyze import _node_community_map
 
 COMMUNITY_COLORS = [
     "#4E79A7", "#F28E2B", "#E15759", "#76B7B2", "#59A14F",
@@ -17,11 +18,6 @@ COMMUNITY_COLORS = [
 MAX_NODES_FOR_VIZ = 5_000
 
 
-def _node_community_map(communities: dict[int, list[str]]) -> dict[str, int]:
-    """Invert communities dict: node_id -> community_id."""
-    return {n: cid for cid, nodes in communities.items() for n in nodes}
-
-
 def _html_styles() -> str:
     return """<style>
   * { box-sizing: border-box; margin: 0; padding: 0; }

graphify/hooks.py

@@ -40,7 +40,7 @@ try:
     _rebuild_code(Path('.'))
 except Exception as exc:
     print(f'[graphify hook] Rebuild failed: {exc}')
-    sys.exit(0)
+    sys.exit(1)
 "
 """
 
@@ -69,10 +69,12 @@ echo "[graphify] Branch switched - rebuilding knowledge graph (code files)..."
 python3 -c "
 from graphify.watch import _rebuild_code
 from pathlib import Path
+import sys
 try:
     _rebuild_code(Path('.'))
 except Exception as exc:
     print(f'[graphify] Rebuild failed: {exc}')
+    sys.exit(1)
 "
 """
 

graphify/serve.py

@@ -75,8 +75,8 @@ def _dfs(G: nx.Graph, start_nodes: list[str], depth: int) -> tuple[set[str], lis
 
 
 def _subgraph_to_text(G: nx.Graph, nodes: set[str], edges: list[tuple], token_budget: int = 2000) -> str:
-    """Render subgraph as text, cutting at token_budget (approx 4 chars/token)."""
-    char_budget = token_budget * 4
+    """Render subgraph as text, cutting at token_budget (approx 3 chars/token)."""
+    char_budget = token_budget * 3
     lines = []
     for nid in sorted(nodes, key=lambda n: G.degree(n), reverse=True):
         d = G.nodes[nid]