cherry-pick PRs #212, #220, #204, #221 into 0.4.2

- build/validate: accept NetworkX <=3.1 "links" key alongside "edges" (#212)
- __main__: skip version check during install/uninstall, deduplicate paths (#220)
- all file IO: explicit encoding="utf-8" to prevent crashes on Windows CJK locales (#204)
- hooks: add newline="\n" on write to prevent CRLF shebang breakage on Windows (#204)
- export: strip trailing .md from safe_name so "CLAUDE.md" doesn't become "CLAUDE.md.md" (#221)
- report: add Community Hubs navigation block so Obsidian vault stays connected (#221)

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

graphify/__main__.py

@@ -628,10 +628,12 @@ def claude_uninstall(project_dir: Path | None = None) -> None:
 
 
 def main() -> None:
-    # Check all known skill install locations for a stale version stamp
+    # Check all known skill install locations for a stale version stamp.
-    for cfg in _PLATFORM_CONFIG.values():
+    # Skip during install/uninstall (hook writes trigger a fresh check anyway).
-        skill_dst = Path.home() / cfg["skill_dst"]
+    # Deduplicate paths so platforms sharing the same install dir don't warn twice.
-        _check_skill_version(skill_dst)
+    if not any(arg in ("install", "uninstall") for arg in sys.argv):
+        for skill_dst in {Path.home() / cfg["skill_dst"] for cfg in _PLATFORM_CONFIG.values()}:
+            _check_skill_version(skill_dst)
 
     if len(sys.argv) < 2 or sys.argv[1] in ("-h", "--help"):
         print("Usage: graphify <command>")

graphify/benchmark.py

@@ -75,7 +75,7 @@ def run_benchmark(
 
     Returns dict with: corpus_tokens, avg_query_tokens, reduction_ratio, per_question
     """
-    data = json.loads(Path(graph_path).read_text())
+    data = json.loads(Path(graph_path).read_text(encoding="utf-8"))
     try:
         G = json_graph.node_link_graph(data, edges="links")
     except TypeError:

graphify/build.py

@@ -32,6 +32,9 @@ def build_from_json(extraction: dict, *, directed: bool = False) -> nx.Graph:
     directed=True produces a DiGraph that preserves edge direction (source→target).
     directed=False (default) produces an undirected Graph for backward compatibility.
     """
+    # NetworkX <= 3.1 serialised edges as "links"; remap to "edges" for compatibility.
+    if "edges" not in extraction and "links" in extraction:
+        extraction = dict(extraction, edges=extraction["links"])
     errors = validate_extraction(extraction)
     # Dangling edges (stdlib/external imports) are expected - only warn about real schema errors.
     real_errors = [e for e in errors if "does not match any node id" not in e]

graphify/cache.py

@@ -55,7 +55,7 @@ def load_cached(path: Path, root: Path = Path(".")) -> dict | None:
     if not entry.exists():
         return None
     try:
-        return json.loads(entry.read_text())
+        return json.loads(entry.read_text(encoding="utf-8"))
     except (json.JSONDecodeError, OSError):
         return None
 
@@ -70,7 +70,7 @@ def save_cached(path: Path, result: dict, root: Path = Path(".")) -> None:
     entry = cache_dir(root) / f"{h}.json"
     tmp = entry.with_suffix(".tmp")
     try:
-        tmp.write_text(json.dumps(result))
+        tmp.write_text(json.dumps(result), encoding="utf-8")
         os.replace(tmp, entry)
     except Exception:
         tmp.unlink(missing_ok=True)

graphify/detect.py

@@ -69,7 +69,7 @@ def _looks_like_paper(path: Path) -> bool:
     """Heuristic: does this text file read like an academic paper?"""
     try:
         # Only scan first 3000 chars for speed
-        text = path.read_text(errors="ignore")[:3000]
+        text = path.read_text(encoding="utf-8", errors="ignore")[:3000]
         hits = sum(1 for pattern in _PAPER_SIGNALS if pattern.search(text))
         return hits >= _PAPER_SIGNAL_THRESHOLD
     except Exception:
@@ -226,7 +226,7 @@ def count_words(path: Path) -> int:
             return len(docx_to_markdown(path).split())
         if ext == ".xlsx":
             return len(xlsx_to_markdown(path).split())
-        return len(path.read_text(errors="ignore").split())
+        return len(path.read_text(encoding="utf-8", errors="ignore").split())
     except Exception:
         return 0
 
@@ -271,7 +271,7 @@ def _load_graphifyignore(root: Path) -> list[str]:
     while True:
         ignore_file = current / ".graphifyignore"
         if ignore_file.exists():
-            for line in ignore_file.read_text(errors="ignore").splitlines():
+            for line in ignore_file.read_text(encoding="utf-8", errors="ignore").splitlines():
                 line = line.strip()
                 if line and not line.startswith("#"):
                     patterns.append(line)
@@ -427,7 +427,7 @@ def detect(root: Path, *, follow_symlinks: bool = False) -> dict:
 def load_manifest(manifest_path: str = _MANIFEST_PATH) -> dict[str, float]:
     """Load the file modification time manifest from a previous run."""
     try:
-        return json.loads(Path(manifest_path).read_text())
+        return json.loads(Path(manifest_path).read_text(encoding="utf-8"))
     except Exception:
         return {}
 
@@ -442,7 +442,7 @@ def save_manifest(files: dict[str, list[str]], manifest_path: str = _MANIFEST_PA
             except OSError:
                 pass  # file deleted between detect() and manifest write - skip it
     Path(manifest_path).parent.mkdir(parents=True, exist_ok=True)
-    Path(manifest_path).write_text(json.dumps(manifest, indent=2))
+    Path(manifest_path).write_text(json.dumps(manifest, indent=2), encoding="utf-8")
 
 
 def detect_incremental(root: Path, manifest_path: str = _MANIFEST_PATH) -> dict:

graphify/export.py

@@ -295,7 +295,7 @@ def to_json(G: nx.Graph, communities: dict[int, list[str]], output_path: str) ->
             conf = link.get("confidence", "EXTRACTED")
             link["confidence_score"] = _CONFIDENCE_SCORE_DEFAULTS.get(conf, 1.0)
     data["hyperedges"] = getattr(G, "graph", {}).get("hyperedges", [])
-    with open(output_path, "w") as f:
+    with open(output_path, "w", encoding="utf-8") as f:
         json.dump(data, f, indent=2)
 
 
@@ -322,7 +322,7 @@ def to_cypher(G: nx.Graph, output_path: str) -> None:
             f"MATCH (a {{id: '{u_esc}'}}), (b {{id: '{v_esc}'}}) "
             f"MERGE (a)-[:{rel} {{confidence: '{conf}'}}]->(b);"
         )
-    with open(output_path, "w") as f:
+    with open(output_path, "w", encoding="utf-8") as f:
         f.write("\n".join(lines))
 
 
@@ -467,7 +467,10 @@ def to_obsidian(
     # Map node_id → safe filename so wikilinks stay consistent.
     # Deduplicate: if two nodes produce the same filename, append a numeric suffix.
     def safe_name(label: str) -> str:
-        return re.sub(r'[\\/*?:"<>|#^[\]]', "", label.replace("\r\n", " ").replace("\r", " ").replace("\n", " ")).strip() or "unnamed"
+        cleaned = re.sub(r'[\\/*?:"<>|#^[\]]', "", label.replace("\r\n", " ").replace("\r", " ").replace("\n", " ")).strip()
+        # Strip trailing .md/.mdx/.markdown so "CLAUDE.md" doesn't become "CLAUDE.md.md"
+        cleaned = re.sub(r"\.(md|mdx|markdown)$", "", cleaned, flags=re.IGNORECASE)
+        return cleaned or "unnamed"
 
     node_filename: dict[str, str] = {}
     seen_names: dict[str, int] = {}
@@ -681,7 +684,7 @@ def to_obsidian(
             for cid, label in sorted((community_labels or {}).items())
         ]
     }
-    (obsidian_dir / "graph.json").write_text(json.dumps(graph_config, indent=2))
+    (obsidian_dir / "graph.json").write_text(json.dumps(graph_config, indent=2), encoding="utf-8")
 
     return G.number_of_nodes() + community_notes_written
 
@@ -703,7 +706,9 @@ def to_canvas(
     CANVAS_COLORS = ["1", "2", "3", "4", "5", "6"]  # red, orange, yellow, green, cyan, purple
 
     def safe_name(label: str) -> str:
-        return re.sub(r'[\\/*?:"<>|#^[\]]', "", label.replace("\r\n", " ").replace("\r", " ").replace("\n", " ")).strip() or "unnamed"
+        cleaned = re.sub(r'[\\/*?:"<>|#^[\]]', "", label.replace("\r\n", " ").replace("\r", " ").replace("\n", " ")).strip()
+        cleaned = re.sub(r"\.(md|mdx|markdown)$", "", cleaned, flags=re.IGNORECASE)
+        return cleaned or "unnamed"
 
     # Build node_filenames if not provided (same dedup logic as to_obsidian)
     if node_filenames is None:

graphify/hooks.py

@@ -113,12 +113,12 @@ def _install_hook(hooks_dir: Path, name: str, script: str, marker: str) -> str:
     """Install a single git hook, appending if an existing hook is present."""
     hook_path = hooks_dir / name
     if hook_path.exists():
-        content = hook_path.read_text()
+        content = hook_path.read_text(encoding="utf-8")
         if marker in content:
             return f"already installed at {hook_path}"
-        hook_path.write_text(content.rstrip() + "\n\n" + script)
+        hook_path.write_text(content.rstrip() + "\n\n" + script, encoding="utf-8", newline="\n")
         return f"appended to existing {name} hook at {hook_path}"
-    hook_path.write_text("#!/bin/sh\n" + script)
+    hook_path.write_text("#!/bin/sh\n" + script, encoding="utf-8", newline="\n")
     hook_path.chmod(0o755)
     return f"installed at {hook_path}"
 
@@ -128,7 +128,7 @@ def _uninstall_hook(hooks_dir: Path, name: str, marker: str, marker_end: str) ->
     hook_path = hooks_dir / name
     if not hook_path.exists():
         return f"no {name} hook found - nothing to remove."
-    content = hook_path.read_text()
+    content = hook_path.read_text(encoding="utf-8")
     if marker not in content:
         return f"graphify hook not found in {name} - nothing to remove."
     new_content = re.sub(
@@ -140,7 +140,7 @@ def _uninstall_hook(hooks_dir: Path, name: str, marker: str, marker_end: str) ->
     if not new_content or new_content in ("#!/bin/bash", "#!/bin/sh"):
         hook_path.unlink()
         return f"removed {name} hook at {hook_path}"
-    hook_path.write_text(new_content + "\n")
+    hook_path.write_text(new_content + "\n", encoding="utf-8", newline="\n")
     return f"graphify removed from {name} at {hook_path} (other hook content preserved)"
 
 
@@ -183,7 +183,7 @@ def status(path: Path = Path(".")) -> str:
         p = hooks_dir / name
         if not p.exists():
             return "not installed"
-        return "installed" if marker in p.read_text() else "not installed (hook exists but graphify not found)"
+        return "installed" if marker in p.read_text(encoding="utf-8") else "not installed (hook exists but graphify not found)"
 
     commit = _check("post-commit", _HOOK_MARKER)
     checkout = _check("post-checkout", _CHECKOUT_MARKER)

graphify/report.py

@@ -1,9 +1,17 @@
 # generate GRAPH_REPORT.md - the human-readable audit trail
 from __future__ import annotations
+import re
 from datetime import date
 import networkx as nx
 
 
+def _safe_community_name(label: str) -> str:
+    """Mirrors export.safe_name so community hub filenames and report wikilinks always agree."""
+    cleaned = re.sub(r'[\\/*?:"<>|#^[\]]', "", label.replace("\r\n", " ").replace("\r", " ").replace("\n", " ")).strip()
+    cleaned = re.sub(r"\.(md|mdx|markdown)$", "", cleaned, flags=re.IGNORECASE)
+    return cleaned or "unnamed"
+
+
 def generate(
     G: nx.Graph,
     communities: dict[int, list[str]],
@@ -48,6 +56,18 @@ def generate(
         f"- Extraction: {ext_pct}% EXTRACTED · {inf_pct}% INFERRED · {amb_pct}% AMBIGUOUS"
         + (f" · INFERRED: {len(inf_edges)} edges (avg confidence: {inf_avg})" if inf_avg is not None else ""),
         f"- Token cost: {token_cost.get('input', 0):,} input · {token_cost.get('output', 0):,} output",
+    ]
+
+    # Community hub navigation - links to _COMMUNITY_*.md files in the Obsidian vault.
+    # Without these, GRAPH_REPORT.md is a dead-end and the vault splits into disconnected components.
+    if communities:
+        lines += ["", "## Community Hubs (Navigation)"]
+        for cid in communities:
+            label = community_labels.get(cid, f"Community {cid}")
+            safe = _safe_community_name(label)
+            lines.append(f"- [[_COMMUNITY_{safe}|{label}]]")
+
+    lines += [
         "",
         "## God Nodes (most connected - your core abstractions)",
     ]

graphify/serve.py

@@ -16,7 +16,7 @@ def _load_graph(graph_path: str) -> nx.Graph:
         if not resolved.exists():
             raise FileNotFoundError(f"Graph file not found: {resolved}")
         safe = resolved
-        data = json.loads(safe.read_text())
+        data = json.loads(safe.read_text(encoding="utf-8"))
         try:
             return json_graph.node_link_graph(data, edges="links")
         except TypeError:

graphify/validate.py

@@ -36,14 +36,15 @@ def validate_extraction(data: dict) -> list[str]:
                     f"'{node['file_type']}' - must be one of {sorted(VALID_FILE_TYPES)}"
                 )
 
-    # Edges
+    # Edges - accept "links" (NetworkX <= 3.1) as fallback for "edges"
-    if "edges" not in data:
+    edge_list = data.get("edges") if "edges" in data else data.get("links")
+    if edge_list is None:
         errors.append("Missing required key 'edges'")
-    elif not isinstance(data["edges"], list):
+    elif not isinstance(edge_list, list):
         errors.append("'edges' must be a list")
     else:
         node_ids = {n["id"] for n in data.get("nodes", []) if isinstance(n, dict) and "id" in n}
-        for i, edge in enumerate(data["edges"]):
+        for i, edge in enumerate(edge_list):
             if not isinstance(edge, dict):
                 errors.append(f"Edge {i} must be an object")
                 continue

graphify/watch.py

@@ -53,7 +53,7 @@ def _rebuild_code(watch_path: Path, *, follow_symlinks: bool = False) -> bool:
 
         report = generate(G, communities, cohesion, labels, gods, surprises, detection,
                           {"input": 0, "output": 0}, str(watch_path), suggested_questions=questions)
-        (out / "GRAPH_REPORT.md").write_text(report)
+        (out / "GRAPH_REPORT.md").write_text(report, encoding="utf-8")
         to_json(G, communities, str(out / "graph.json"))
 
         # clear stale needs_update flag if present
@@ -75,7 +75,7 @@ def _notify_only(watch_path: Path) -> None:
     """Write a flag file and print a notification (fallback for non-code-only corpora)."""
     flag = watch_path / "graphify-out" / "needs_update"
     flag.parent.mkdir(parents=True, exist_ok=True)
-    flag.write_text("1")
+    flag.write_text("1", encoding="utf-8")
     print(f"\n[graphify watch] New or changed files detected in {watch_path}")
     print("[graphify watch] Non-code files changed - semantic re-extraction requires LLM.")
     print("[graphify watch] Run `/graphify --update` in Claude Code to update the graph.")