fix(hooks): definition detector covers all code, not a language shortlist (#2682)

ARM 1 extracted definitions with patterns for CSS/JS/TS/Python only —
the languages of the repo it was born in — so the local duplication
proof, and the #2664 record nudge gated on it, were structurally
unreachable in Go/Kotlin/Rust projects (Minstrel, FabledExchange):
precisely where recording was observed never to happen. One
modifier-strip plus a definition-keyword family (func/fun/fn/function/
def/sub, struct/trait/interface/enum/object/protocol/type, plus Go
method receivers) now covers them all; impl is excluded because several
impl blocks per type is normal Rust, and keyword-less declarations
(C/Java/Dart) are documented out of scope. Grep patterns mirror the
same forms so hits are definitions, never call sites. Parameterized
tests pin the coverage per language family. Plugin 0.1.30.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

plugin/.claude-plugin/plugin.json

@@ -1,7 +1,7 @@
 {
   "name": "scribe",
   "description": "Scribe system-of-record for Claude Code: MCP tools over your notes/tasks/projects/rules, a session-start push channel that surfaces your always-on rules + active-project context, process-skills (writing-plans, systematic-debugging, verification, brainstorming, reusing-code), and your saved Scribe Processes auto-surfaced as skills (/scribe:sync). Replaces superpowers + file-memory with one app-backed plugin.",
-  "version": "0.1.29",
+  "version": "0.1.30",
   "author": { "name": "Bryan Van Deusen" },
   "mcpServers": {
     "scribe": {

plugin/hooks/scribe_prior_art.sh

@@ -79,34 +79,57 @@ fi
 # Definition-shaped patterns only. Grepping for bare occurrences would match
 # every CALL site and drown the real finding — and a hint that is mostly noise
 # is one people learn to skip, which is worse than none.
+#
+# ALL code, not a language shortlist (#2682): the detector was born covering
+# only the languages of the repo it was written in, which silently amputated
+# this whole arm — and the record nudge gated on it — for every Go/Kotlin/Rust
+# project. Definitions are announced by a small keyword family across
+# languages (func/fun/fn/function/def/sub · class/struct/trait/interface/
+# enum/object/protocol/type), so one modifier-strip + keyword match covers
+# them all. Known out of scope: keyword-less declaration syntax (C/Java/Dart
+# `ReturnType name(...)`) needs a real parser, and `impl` blocks are excluded
+# because several per type is normal Rust, not duplication.
 # ---------------------------------------------------------------------------
 local_lines=""
 if [ -n "$repo_root" ] && [ -n "$code" ]; then
   # kind<TAB>name for each thing this payload DEFINES.
   names=$(printf '%s' "$code" | awk '
-    match($0, /^[[:space:]]*\.[A-Za-z][A-Za-z0-9_-]*[[:space:]]*[,{]/) {
-      t = $0; sub(/^[[:space:]]*\./, "", t); sub(/[[:space:]]*[,{].*$/, "", t);
-      if (t != "") print "css\t" t; next }
-    match($0, /^[[:space:]]*(export[[:space:]]+)?(default[[:space:]]+)?(async[[:space:]]+)?function[[:space:]]+[A-Za-z_$][A-Za-z0-9_$]*/) {
-      t = $0; sub(/^.*function[[:space:]]+/, "", t); sub(/[^A-Za-z0-9_$].*$/, "", t);
-      if (t != "") print "sym\t" t; next }
-    match($0, /^[[:space:]]*(export[[:space:]]+)?class[[:space:]]+[A-Za-z_$][A-Za-z0-9_$]*/) {
-      t = $0; sub(/^.*class[[:space:]]+/, "", t); sub(/[^A-Za-z0-9_$].*$/, "", t);
-      if (t != "") print "sym\t" t; next }
-    match($0, /^[[:space:]]*(async[[:space:]]+)?def[[:space:]]+[A-Za-z_][A-Za-z0-9_]*/) {
-      t = $0; sub(/^.*def[[:space:]]+/, "", t); sub(/[^A-Za-z0-9_].*$/, "", t);
-      if (t != "") print "sym\t" t; next }
-    match($0, /^[[:space:]]*(export[[:space:]]+)?(const|let)[[:space:]]+[A-Za-z_$][A-Za-z0-9_$]*[[:space:]]*=[[:space:]]*(async[[:space:]]*)?[(<]/) {
-      t = $0; sub(/^[[:space:]]*(export[[:space:]]+)?(const|let)[[:space:]]+/, "", t);
-      sub(/[^A-Za-z0-9_$].*$/, "", t);
-      if (t != "") print "sym\t" t; next }
+    {
+      # CSS class definition: .name { or .name,
+      if (match($0, /^[[:space:]]*\.[A-Za-z][A-Za-z0-9_-]*[[:space:]]*[,{]/)) {
+        t = $0; sub(/^[[:space:]]*\./, "", t); sub(/[[:space:]]*[,{].*$/, "", t)
+        if (t != "") print "css\t" t; next
+      }
+      line = $0; sub(/^[[:space:]]+/, "", line)
+      # Strip leading declaration modifiers so the definition keyword is the
+      # first word regardless of language (export/pub/private/suspend/...).
+      sub(/^((pub(\([a-z]+\))?|export|default|private|internal|protected|public|static|suspend|async|open|sealed|data|abstract|final|inline|unsafe|extern|override)[[:space:]]+)*/, "", line)
+      # Go method with receiver: func (r *T) Name(
+      if (match(line, /^func[[:space:]]*\([^)]*\)[[:space:]]*[A-Za-z_]/)) {
+        t = line; sub(/^func[[:space:]]*\([^)]*\)[[:space:]]*/, "", t)
+        sub(/[^A-Za-z0-9_].*$/, "", t)
+        if (t != "") print "sym\t" t; next
+      }
+      # Keyword-announced definitions, functions and named types alike.
+      if (match(line, /^(function|def|class|func|fun|fn|sub|struct|trait|interface|enum|object|protocol|type)[[:space:]]+[A-Za-z_$]/)) {
+        t = line; sub(/^[a-z]+[[:space:]]+/, "", t)
+        sub(/[^A-Za-z0-9_$].*$/, "", t)
+        if (t != "") print "sym\t" t; next
+      }
+      # Arrow/expression assignment: const name = (…) / let name = async (
+      if (match(line, /^(const|let)[[:space:]]+[A-Za-z_$][A-Za-z0-9_$]*[[:space:]]*=[[:space:]]*(async[[:space:]]*)?[(<]/)) {
+        t = line; sub(/^(const|let)[[:space:]]+/, "", t)
+        sub(/[^A-Za-z0-9_$].*$/, "", t)
+        if (t != "") print "sym\t" t; next
+      }
+    }
   ' 2>/dev/null | sort -u | head -12) || names=""
 
   while IFS=$'\t' read -r kind name; do
     [ -n "${name:-}" ] || continue
     case "$kind" in
       css) pat="^[[:space:]]*\.${name}[[:space:]]*[,{]" ;;
-      *)   pat="(function|class|def)[[:space:]]+${name}[^A-Za-z0-9_]|(const|let)[[:space:]]+${name}[[:space:]]*=" ;;
+      *)   pat="(function|def|class|func|fun|fn|sub|struct|trait|interface|enum|object|protocol|type)[[:space:]]+${name}[^A-Za-z0-9_]|func[[:space:]]*\([^)]*\)[[:space:]]*${name}[[:space:]]*\(|(const|let)[[:space:]]+${name}[[:space:]]*=" ;;
     esac
     # -I skips binaries; :(exclude) drops the file being written, which would
     # otherwise always match itself on an Edit.

tests/test_write_path_trigger.py

@@ -861,3 +861,52 @@ def test_hook_stays_quiet_about_recording_when_nothing_is_duplicated(tmp_path):
     )
     assert out.returncode == 0
     assert "create_snippet" not in out.stdout
+
+
+@pytest.mark.parametrize(
+    ("fname", "definition"),
+    [
+        ("scanner.go", "func Resolve(x int) error {\n\treturn nil\n}\n"),
+        ("scanner_m.go",
+         "func (s *Scanner) Resolve(x int) error {\n\treturn nil\n}\n"),
+        ("queue.kt", "suspend fun refreshQueue(id: Long) {\n}\n"),
+        ("fetch.rs", "pub async fn fetch_all() -> u32 {\n    0\n}\n"),
+        ("adapter.go", "type ForgeAdapter struct {\n\tname string\n}\n"),
+    ],
+    ids=["go-func", "go-method", "kotlin-fun", "rust-fn", "go-type"],
+)
+def test_local_arm_finds_duplicates_in_every_language_family(
+    tmp_path, fname, definition
+):
+    """#2682: the definition detector must cover ALL code, not the languages of
+    the repo it was born in. Its original CSS/JS/Python-only patterns silently
+    amputated the local arm — and the #2664 recording nudge gated on it — for
+    every Go/Kotlin/Rust project, which is exactly where the operator observed
+    recording never happening. Each case stages an existing copy and writes the
+    same definition to a second file; the hook must prove the duplication and
+    ask for the record."""
+    env = _hook_runtime_env()
+    repo = tmp_path / "repo"
+    repo.mkdir()
+    subprocess.run(["git", "init", "-q"], cwd=repo, check=True, env=env)
+    (repo / fname).write_text(definition)
+    subprocess.run(["git", "add", "."], cwd=repo, check=True, env=env)
+    ext = fname.rsplit(".", 1)[1]
+    out = subprocess.run(
+        ["bash", str(HOOK)],
+        input=json.dumps({
+            "session_id": f"s-lang-{ext}", "cwd": str(repo),
+            "tool_name": "Write",
+            "tool_input": {"file_path": str(repo / f"copy.{ext}"),
+                           "content": definition},
+        }),
+        capture_output=True, text=True, env=env,
+    )
+    assert out.returncode == 0
+    assert out.stdout.strip(), (
+        f"hook produced no output for {fname} — the local arm should have "
+        f"found the staged duplicate definition"
+    )
+    ctx = json.loads(out.stdout)["hookSpecificOutput"]["additionalContext"]
+    assert "already defined" in ctx
+    assert "create_snippet" in ctx