fix: OpenCode project path, hook loop guard, deterministic output, Amp platform, punctuation search, builtin god-node filter, .svh Verilog (#1040, #1018, #1037, #948, #994, #916, #1042)

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

CHANGELOG.md

@@ -2,6 +2,17 @@
 
 Full release notes with details on each version: [GitHub Releases](https://github.com/safishamsi/graphify/releases)
 
+## 0.8.21 (2026-05-27)
+
+- Fix: `graphify update` (no `--changed` flag) no longer leaves ghost nodes from files deleted between runs — full re-extraction path now reconciles the existing graph against current disk state and evicts any node whose `source_file` no longer exists; `_norm_source_file` used on both sides to guarantee path format consistency (#1007)
+- Fix: `graphify install --platform opencode --project` now writes `SKILL.md` to `.opencode/skills/graphify/SKILL.md` (discoverable by OpenCode) instead of the incorrect `.config/opencode/skills/` path; git-add hint updated accordingly (#1040)
+- Fix: post-commit hook no longer triggers rebuild when only `graphify-out/` files were committed (avoids infinite dirty-tree loop when graph outputs are tracked in git); `GRAPHIFY_SKIP_HOOK=1` env var added for one-off skip; hook rebuild log now appends (`>>`) instead of overwriting (`>`) (#1018, #1037)
+- Fix: graph output is now byte-for-byte deterministic across runs — edges sorted by `(source, target, relation)` in `build_from_json`; `PYTHONHASHSEED=0` exported in hook scripts to stabilize Louvain community ordering (#1010)
+- Feat: Amp (ampcode.com) platform support — `graphify amp install/uninstall` installs the skill into `.amp/skills/graphify/SKILL.md` (#948)
+- Fix: query punctuation no longer breaks node matching — `"what calls extract?"` correctly finds the `extract` node; `_search_tokens` helper strips punctuation from search terms in `_query_terms`, `_score_nodes`, and `_find_node` (#994, #978)
+- Fix: language built-in globals (`String`, `Number`, `Boolean`, `Object`, `Array`, etc.) no longer accumulate spurious call edges — filtered at same-file and cross-file resolution in the AST extractor, eliminating god-node pollution from constructor-style calls (#916, #726)
+- Feat: SystemVerilog header files (`.svh`) now extracted using the Verilog parser alongside `.v` and `.sv` (#1042)
+
 ## 0.8.20 (2026-05-26)
 
 - Fix: stale nodes persist after `graphify update` when files are deleted on Windows — `deleted_paths` and `evict_sources` in `_rebuild_code` now use `.as_posix()` for consistent forward-slash paths; `_relativize_source_files` called on the existing graph before eviction (not after); `_relativize_source_files` itself now produces forward slashes (#1007)

graphify/__main__.py

@@ -77,6 +77,11 @@ def _platform_skill_destination(platform_name: str, *, project: bool = False, pr
             return Path.home() / ".agents" / "skills" / "graphify" / "SKILL.md"
         return Path.home() / ".gemini" / "skills" / "graphify" / "SKILL.md"
 
+    if platform_name == "opencode":
+        if project:
+            return (project_dir or Path(".")) / ".opencode" / "skills" / "graphify" / "SKILL.md"
+        return Path.home() / ".config" / "opencode" / "skills" / "graphify" / "SKILL.md"
+
     if platform_name == "devin":
         if project:
             return (project_dir or Path(".")) / ".devin" / "skills" / "graphify" / "SKILL.md"
@@ -289,6 +294,11 @@ _PLATFORM_CONFIG: dict[str, dict] = {
         "skill_dst": Path(".kimi") / "skills" / "graphify" / "SKILL.md",
         "claude_md": False,
     },
+    "amp": {
+        "skill_file": "skill-amp.md",
+        "skill_dst": Path(".amp") / "skills" / "graphify" / "SKILL.md",
+        "claude_md": False,
+    },
     "devin": {
         "skill_file": "skill-devin.md",
         # User scope: ~/.config/devin/skills/graphify/SKILL.md
@@ -1120,7 +1130,7 @@ def _project_install(platform_name: str, project_dir: Path | None = None) -> Non
     elif platform_name == "kiro":
         _kiro_install(project_dir)
         _print_project_git_add_hint([project_dir / ".kiro"])
-    elif platform_name in ("aider", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes"):
+    elif platform_name in ("aider", "amp", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes"):
         skill_dst = _copy_skill_file(platform_name, project=True, project_dir=project_dir)
         _agents_install(project_dir, platform_name)
         hint_paths = [_project_scope_root(skill_dst, project_dir), project_dir / "AGENTS.md"]
@@ -1153,7 +1163,7 @@ def _project_uninstall(platform_name: str, project_dir: Path | None = None) -> N
         _cursor_uninstall(project_dir)
     elif platform_name == "kiro":
         _kiro_uninstall(project_dir)
-    elif platform_name in ("aider", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes"):
+    elif platform_name in ("aider", "amp", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes"):
         _remove_skill_file(platform_name, project=True, project_dir=project_dir)
         _agents_uninstall(project_dir, platform=platform_name)
         if platform_name == "codex":
@@ -1729,7 +1739,7 @@ def main() -> None:
         else:
             print("Usage: graphify pi [install|uninstall]", file=sys.stderr)
             sys.exit(1)
-    elif cmd in ("aider", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes"):
+    elif cmd in ("aider", "amp", "codex", "opencode", "claw", "droid", "trae", "trae-cn", "hermes"):
         subcmd = sys.argv[2] if len(sys.argv) > 2 else ""
         if subcmd == "install":
             if "--project" in sys.argv[3:]:

graphify/detect.py

@@ -25,7 +25,7 @@ class FileType(str, Enum):
 
 _MANIFEST_PATH = "graphify-out/manifest.json"
 
-CODE_EXTENSIONS = {'.py', '.ts', '.tsx', '.js', '.jsx', '.mjs', '.ejs', '.ets', '.go', '.rs', '.java', '.groovy', '.gradle', '.cpp', '.cc', '.cxx', '.c', '.h', '.hpp', '.rb', '.swift', '.kt', '.kts', '.cs', '.scala', '.php', '.lua', '.luau', '.toc', '.zig', '.ps1', '.ex', '.exs', '.m', '.mm', '.jl', '.vue', '.svelte', '.astro', '.dart', '.v', '.sv', '.sql', '.r', '.f', '.F', '.f90', '.F90', '.f95', '.F95', '.f03', '.F03', '.f08', '.F08', '.pas', '.pp', '.dpr', '.dpk', '.lpr', '.inc', '.dfm', '.lfm', '.lpk', '.sh', '.bash', '.json', '.sln', '.csproj', '.fsproj', '.vbproj', '.razor', '.cshtml'}
+CODE_EXTENSIONS = {'.py', '.ts', '.tsx', '.js', '.jsx', '.mjs', '.ejs', '.ets', '.go', '.rs', '.java', '.groovy', '.gradle', '.cpp', '.cc', '.cxx', '.c', '.h', '.hpp', '.rb', '.swift', '.kt', '.kts', '.cs', '.scala', '.php', '.lua', '.luau', '.toc', '.zig', '.ps1', '.ex', '.exs', '.m', '.mm', '.jl', '.vue', '.svelte', '.astro', '.dart', '.v', '.sv', '.svh', '.sql', '.r', '.f', '.F', '.f90', '.F90', '.f95', '.F95', '.f03', '.F03', '.f08', '.F08', '.pas', '.pp', '.dpr', '.dpk', '.lpr', '.inc', '.dfm', '.lfm', '.lpk', '.sh', '.bash', '.json', '.sln', '.csproj', '.fsproj', '.vbproj', '.razor', '.cshtml'}
 DOC_EXTENSIONS = {'.md', '.mdx', '.qmd', '.txt', '.rst', '.html', '.yaml', '.yml'}
 PAPER_EXTENSIONS = {'.pdf'}
 IMAGE_EXTENSIONS = {'.png', '.jpg', '.jpeg', '.gif', '.webp', '.svg'}

graphify/extract.py

@@ -14,6 +14,32 @@ from .mcp_ingest import extract_mcp_config, is_mcp_config_path
 
 _RECURSION_LIMIT = 10_000
 
+# Language built-in globals that AST may classify as call targets when used as
+# constructors or coercion functions (e.g. String(x), Number(x), Boolean(x)).
+# Without this filter they become god-nodes accumulating spurious edges from
+# every call site. Filter applied at same-file and cross-file resolution.
+# See issue #726.
+_LANGUAGE_BUILTIN_GLOBALS: frozenset[str] = frozenset({
+    # JavaScript / TypeScript ECMAScript built-ins
+    "String", "Number", "Boolean", "Object", "Array", "Symbol", "BigInt",
+    "Date", "RegExp", "Error", "TypeError", "RangeError", "SyntaxError",
+    "ReferenceError", "EvalError", "URIError",
+    "Promise", "Map", "Set", "WeakMap", "WeakSet", "JSON", "Math",
+    "Reflect", "Proxy", "Intl",
+    "parseInt", "parseFloat", "isNaN", "isFinite",
+    "encodeURIComponent", "decodeURIComponent", "encodeURI", "decodeURI",
+    # Browser / Node common globals
+    "URL", "URLSearchParams", "FormData", "Blob", "File",
+    "Headers", "Request", "Response", "AbortController", "AbortSignal",
+    "TextEncoder", "TextDecoder", "console",
+    # Python built-in callables
+    "str", "int", "float", "bool", "list", "dict", "set", "tuple", "bytes",
+    "len", "range", "enumerate", "zip", "map", "filter", "sum", "min", "max",
+    "print", "open", "isinstance", "type", "super", "sorted", "reversed",
+    "any", "all", "abs", "round", "next", "iter", "hash", "id", "repr",
+    "callable", "getattr", "setattr", "hasattr", "delattr", "vars", "dir",
+})
+
 
 def _raise_recursion_limit() -> None:
     if sys.getrecursionlimit() < _RECURSION_LIMIT:
@@ -2285,7 +2311,7 @@ def _extract_generic(path: Path, config: LanguageConfig) -> dict:
                         # Try reading the node directly (e.g. Java name field is the callee)
                         callee_name = _read_text(func_node, source)
 
-            if callee_name:
+            if callee_name and callee_name not in _LANGUAGE_BUILTIN_GLOBALS:
                 tgt_nid = label_to_nid.get(callee_name)
                 if tgt_nid and tgt_nid != caller_nid:
                     pair = (caller_nid, tgt_nid)
@@ -4136,7 +4162,7 @@ def extract_go(path: Path) -> dict:
                     is_member_call = receiver_name not in go_imported_pkgs
                     if field:
                         callee_name = _read_text(field, source)
-            if callee_name:
+            if callee_name and callee_name not in _LANGUAGE_BUILTIN_GLOBALS:
                 tgt_nid = label_to_nid.get(callee_name)
                 if tgt_nid and tgt_nid != caller_nid:
                     pair = (caller_nid, tgt_nid)
@@ -4337,7 +4363,7 @@ def extract_rust(path: Path) -> dict:
                     name = func_node.child_by_field_name("name")
                     if name:
                         callee_name = _read_text(name, source)
-            if callee_name:
+            if callee_name and callee_name not in _LANGUAGE_BUILTIN_GLOBALS:
                 tgt_nid = label_to_nid.get(callee_name)
                 if tgt_nid and tgt_nid != caller_nid:
                     pair = (caller_nid, tgt_nid)
@@ -6456,7 +6482,7 @@ def extract_elixir(path: Path) -> dict:
             if child.type == "identifier":
                 callee_name = source[child.start_byte:child.end_byte].decode("utf-8", errors="replace")
                 break
-        if callee_name:
+        if callee_name and callee_name not in _LANGUAGE_BUILTIN_GLOBALS:
             tgt_nid = label_to_nid.get(callee_name)
             if tgt_nid and tgt_nid != caller_nid:
                 pair = (caller_nid, tgt_nid)
@@ -8245,6 +8271,7 @@ _DISPATCH: dict[str, Any] = {
     ".dart": extract_dart,
     ".v": extract_verilog,
     ".sv": extract_verilog,
+    ".svh": extract_verilog,
     ".sql": extract_sql,
     ".md": extract_markdown,
     ".mdx": extract_markdown,
@@ -8630,6 +8657,8 @@ def extract(
         callee = rc.get("callee", "")
         if not callee:
             continue
+        if callee in _LANGUAGE_BUILTIN_GLOBALS:
+            continue
         # Skip member-call callees: obj.log() → "log" has no import evidence
         # and collides with any top-level function named "log" in the corpus.
         if rc.get("is_member_call"):

graphify/hooks.py

@@ -60,11 +60,19 @@ GIT_DIR=$(git rev-parse --git-dir 2>/dev/null)
 [ -f "$GIT_DIR/MERGE_HEAD" ] && exit 0
 [ -f "$GIT_DIR/CHERRY_PICK_HEAD" ] && exit 0
 
+[ "${GRAPHIFY_SKIP_HOOK:-0}" = "1" ] && exit 0
+
 CHANGED=$(git diff --name-only HEAD~1 HEAD 2>/dev/null || git diff --name-only HEAD 2>/dev/null)
 if [ -z "$CHANGED" ]; then
     exit 0
 fi
 
+# Skip when only graphify-out/ artifacts changed (avoids rebuild loop when graph outputs are tracked in git)
+_NON_GRAPH=$(echo "$CHANGED" | grep -v '^graphify-out/' || true)
+if [ -z "$_NON_GRAPH" ]; then
+    exit 0
+fi
+
 """ + _PYTHON_DETECT + """
 export GRAPHIFY_CHANGED="$CHANGED"
 
@@ -100,7 +108,7 @@ except TimeoutError as exc:
 except Exception as exc:
     print(f'[graphify hook] Rebuild failed: {exc}')
     sys.exit(1)
-" > "$_GRAPHIFY_LOG" 2>&1 < /dev/null &
+" >> "$_GRAPHIFY_LOG" 2>&1 < /dev/null &
 disown 2>/dev/null || true
 # graphify-hook-end
 """
@@ -162,7 +170,7 @@ except TimeoutError as exc:
 except Exception as exc:
     print(f'[graphify] Rebuild failed: {exc}')
     sys.exit(1)
-" > "$_GRAPHIFY_LOG" 2>&1 < /dev/null &
+" >> "$_GRAPHIFY_LOG" 2>&1 < /dev/null &
 disown 2>/dev/null || true
 # graphify-checkout-hook-end
 """

graphify/serve.py

@@ -2,6 +2,7 @@
 from __future__ import annotations
 import json
 import math
+import re
 import sys
 from pathlib import Path
 import networkx as nx
@@ -56,6 +57,11 @@ def _strip_diacritics(text: str) -> str:
     return "".join(c for c in nfkd if not unicodedata.combining(c))
 
 
+def _search_tokens(text: str) -> list[str]:
+    """Split text into word tokens, stripping punctuation and diacritics."""
+    return re.findall(r"\w+", _strip_diacritics(str(text)).lower())
+
+
 def _has_chinese(text: str) -> bool:
     return any("一" <= ch <= "鿿" for ch in text)
 
@@ -82,14 +88,16 @@ def _query_terms(question: str) -> list[str]:
     """Split a query into searchable terms, segmenting Chinese text."""
     terms: list[str] = []
     for raw in question.split():
-        term = raw.lower().strip()
-        if not term:
-            continue
-        candidates = _segment_chinese(term) if _has_chinese(term) else [term]
-        for seg in candidates:
-            seg = seg.strip()
-            if seg and _is_searchable(seg):
-                terms.append(seg)
+        if _has_chinese(raw):
+            for seg in _segment_chinese(raw.lower().strip()):
+                seg = seg.strip()
+                if seg and _is_searchable(seg):
+                    terms.append(seg)
+        else:
+            # Strip punctuation without touching Unicode characters (avoid NFKD mangling non-Latin scripts)
+            for tok in re.findall(r"\w+", raw.lower()):
+                if _is_searchable(tok):
+                    terms.append(tok)
     return terms
 
 
@@ -126,7 +134,7 @@ def _compute_idf(G: nx.Graph, terms: list[str]) -> dict[str, float]:
 
 def _score_nodes(G: nx.Graph, terms: list[str]) -> list[tuple[float, str]]:
     scored = []
-    norm_terms = [_strip_diacritics(t).lower() for t in terms]
+    norm_terms = [tok for t in terms for tok in _search_tokens(t)]
     idf = _compute_idf(G, norm_terms)
     for nid, data in G.nodes(data=True):
         norm_label = data.get("norm_label") or _strip_diacritics(data.get("label") or "").lower()
@@ -415,7 +423,9 @@ def _find_node(G: nx.Graph, label: str) -> list[str]:
     Results are ordered by three-tier precedence: exact match, then prefix match,
     then substring match. Node-ID exact matches are grouped with label exact matches.
     """
-    term = _strip_diacritics(label).lower()
+    term = " ".join(_search_tokens(label))
+    if not term:
+        return []
     exact: list[str] = []
     prefix: list[str] = []
     substring: list[str] = []

pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "graphifyy"
-version = "0.8.20"
+version = "0.8.21"
 description = "AI coding assistant skill (Claude Code, Codex, OpenCode, Cursor, Gemini CLI, Aider, OpenClaw, Factory Droid, Trae, Hermes, Kiro, Pi, Devin CLI, Google Antigravity) - turn any folder of code, docs, papers, images, or videos into a queryable knowledge graph"
 readme = "README.md"
 license = { file = "LICENSE" }
@@ -97,7 +97,7 @@ packages = ["graphify"]
 include-package-data = false
 
 [tool.setuptools.package-data]
-graphify = ["skill.md", "skill-codex.md", "skill-opencode.md", "skill-aider.md", "skill-copilot.md", "skill-claw.md", "skill-windows.md", "skill-droid.md", "skill-trae.md", "skill-kiro.md", "skill-vscode.md", "skill-pi.md", "skill-devin.md"]
+graphify = ["skill.md", "skill-codex.md", "skill-opencode.md", "skill-aider.md", "skill-amp.md", "skill-copilot.md", "skill-claw.md", "skill-windows.md", "skill-droid.md", "skill-trae.md", "skill-kiro.md", "skill-vscode.md", "skill-pi.md", "skill-devin.md"]
 
 [tool.pytest.ini_options]
 testpaths = ["tests"]

tests/test_serve.py

@@ -11,6 +11,7 @@ from graphify.serve import (
     _pick_seeds,
     _bfs,
     _dfs,
+    _find_node,
     _filter_graph_by_context,
     _infer_context_filters,
     _query_terms,
@@ -80,6 +81,21 @@ def test_score_nodes_source_file_partial():
     assert "n2" in nids
 
 
+def test_score_nodes_ignores_trailing_punctuation():
+    G = _make_graph()
+    scored = _score_nodes(G, ["extract?"])
+    assert scored[0][1] == "n1"
+
+
+def test_find_node_ignores_trailing_punctuation():
+    G = _make_graph()
+    assert _find_node(G, "extract?") == ["n1"]
+
+
+def test_query_terms_strips_search_punctuation():
+    assert _query_terms("what calls extract?") == ["what", "calls", "extract"]
+
+
 def test_query_terms_filters_only_short_english_terms(monkeypatch):
     import graphify.serve as serve_mod