From 91f4d120b630ee35c79bf3c75ccd186870a808f9 Mon Sep 17 00:00:00 2001
From: Safi <safishamsi98@gmail.com>
Date: Thu, 14 May 2026 23:03:21 +0100
Subject: [PATCH] fix worktree hook crash, prune isolated code nodes, restore
 rationale-node prohibition

- hooks.py: use git rev-parse --git-path hooks so install/status/uninstall
  work in linked worktrees where .git is a file not a directory (fixes #865)
- build.py: prune degree-0 code nodes after graph assembly to remove
  bundled/synthetic symbols with no connections (fixes #728)
- skill.md: restore explicit rule prohibiting file_type:"rationale" nodes
  and remind model to store rationale as an attribute instead (fixes #751)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 graphify/build.py |  9 +++++++++
 graphify/hooks.py | 15 ++++++++++++++-
 graphify/skill.md |  5 ++++-
 3 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/graphify/build.py b/graphify/build.py
index 0975d7a5..ca3c0f8f 100644
--- a/graphify/build.py
+++ b/graphify/build.py
@@ -28,6 +28,15 @@ def build_from_json(extraction: dict) -> nx.Graph:
     hyperedges = extraction.get("hyperedges", [])
     if hyperedges:
         G.graph["hyperedges"] = hyperedges
+    # Strip degree-0 code nodes — they are bundled/synthetic symbols with no
+    # connections and only inflate god-node centrality and clustering noise.
+    # Document, paper, and image nodes are kept even when isolated since they
+    # may be leaf concepts intentionally referenced by the skill.
+    isolated_code = [
+        n for n in list(G.nodes())
+        if G.degree(n) == 0 and G.nodes[n].get("file_type") == "code"
+    ]
+    G.remove_nodes_from(isolated_code)
     return G
 
 
diff --git a/graphify/hooks.py b/graphify/hooks.py
index 0c86f969..f66c60cc 100644
--- a/graphify/hooks.py
+++ b/graphify/hooks.py
@@ -75,8 +75,21 @@ def _hooks_dir(root: Path) -> Path:
                 return p
     except (OSError, FileNotFoundError):
         pass
+    # In a linked worktree .git is a file not a directory, so we ask git
+    # for the real hooks path rather than constructing it ourselves.
+    try:
+        result = subprocess.run(
+            ["git", "-C", str(root), "rev-parse", "--path-format=absolute", "--git-path", "hooks"],
+            capture_output=True, text=True,
+        )
+        if result.returncode == 0:
+            d = Path(result.stdout.strip())
+            d.mkdir(parents=True, exist_ok=True)
+            return d
+    except (OSError, FileNotFoundError):
+        pass
     d = root / ".git" / "hooks"
-    d.mkdir(exist_ok=True)
+    d.mkdir(parents=True, exist_ok=True)
     return d
 
 
diff --git a/graphify/skill.md b/graphify/skill.md
index 865b3429..c9683689 100644
--- a/graphify/skill.md
+++ b/graphify/skill.md
@@ -195,7 +195,10 @@ Rules:
 
 Code files: focus on semantic edges AST cannot find (call relationships, shared data, arch patterns).
   Do not re-extract imports - AST already has those.
-Doc/paper files: extract named concepts, entities, citations.
+Doc/paper files: extract named concepts, entities, citations. For rationale (WHY decisions were made,
+  trade-offs, design intent): store as a `rationale` attribute on the relevant concept node — do NOT
+  create a separate rationale node. Valid `file_type` values are ONLY `code|document|paper|image` —
+  never emit `file_type:"rationale"` or `file_type:"concept"`.
 Image files: use vision to understand what the image IS - do not just OCR.
   UI screenshot: layout patterns, design decisions, key elements, purpose.
   Chart: metric, trend/insight, data source.