Merge pull request 'feat(lint): wire Vale as deterministic prefilter for skill-audit/agent-audit' (#85) from feat/84-vale-audit-prefilter into main

Reviewed-on: https://git.dev.rkdr.net/Defame1297/holocron/pulls/85
Reviewed-by: Defame1297 <gitea@rkdr.net>

plugins/gitea/.claude-plugin/plugin.json

@@ -15,5 +15,5 @@
   ],
   "license": "MIT",
   "name": "gitea",
-  "version": "1.3.2"
+  "version": "1.3.3"
 }

plugins/gitea/plugin.json

@@ -20,5 +20,5 @@
   "skills": [
     "skills/"
   ],
-  "version": "1.3.2"
+  "version": "1.3.3"
 }

scripts/check-vale-style-sync.sh

@@ -10,11 +10,17 @@ set -euo pipefail
 # only one of the two. Run from repo root or pass REPO_ROOT as arg.
 
 REPO_ROOT="${1:-$(git rev-parse --show-toplevel 2>/dev/null || pwd)}"
+# A nonexistent REPO_ROOT must fail loudly, not fall through to the "neither
+# copy present" no-op below — that guard exists for a repo that legitimately
+# has no kyberforge plugin installed, not for a typo'd or stale path, and a
+# clean exit 0 here would read as "checked, in sync" when nothing ran at all.
+if [[ ! -d "$REPO_ROOT" ]]; then
+  echo "Vale style sync check failed: REPO_ROOT '$REPO_ROOT' is not a directory." >&2
+  exit 1
+fi
 # Absolutized because the glob probe below `cd`s into a scratch tree, where a
 # relative --config path would stop resolving.
-if [[ -d "$REPO_ROOT" ]]; then
-  REPO_ROOT="$(cd "$REPO_ROOT" && pwd)"
-fi
+REPO_ROOT="$(cd "$REPO_ROOT" && pwd)"
 FAIL=0
 
 err() { echo "  FAIL: $1" >&2; FAIL=$((FAIL + 1)); }
@@ -81,21 +87,26 @@ done
 # $1's vale-wrap.sh. Records are delimited by their `- id:` line, so the check
 # does not depend on `entry:` preceding `files:` within a record.
 #
-# Cached per skill (in HOOK_REGEX_CACHE, populated lazily) because the final
-# validation loop below probes agent-audit twice — once for its CC agent-file
-# shape, once for its Copilot .agent.md shape — and both probes need the same
-# regex set. Without the cache, that pair of calls would each re-parse both
-# manifest files from scratch for no new information. HOOK_REGEX_CACHE_SEEN is
-# a separate array so a skill with no matching hooks (empty result) is still
-# recognized as already computed, rather than re-parsed every call.
-declare -A HOOK_REGEX_CACHE=()
-declare -A HOOK_REGEX_CACHE_SEEN=()
+# Cached per skill (parallel HOOK_REGEX_CACHE_KEYS/_VALS arrays, populated
+# lazily) because the final validation loop below probes agent-audit twice —
+# once for its CC agent-file shape, once for its Copilot .agent.md shape — and
+# both probes need the same regex set. Without the cache, that pair of calls
+# would each re-parse both manifest files from scratch for no new information.
+# Plain indexed arrays, not `declare -A`: associative arrays are bash 4.0+ and
+# this script must run on macOS's stock bash 3.2. Only ${#arr[@]} (always safe
+# on an empty/unset array under `set -u`) and index access are used below —
+# never a bare `${arr[@]}` expansion, which aborts on bash < 4.4 under nounset.
+HOOK_REGEX_CACHE_KEYS=()
+HOOK_REGEX_CACHE_VALS=()
 hook_file_regexes() {
-  local skill="$1" manifest raw result
-  if [[ -n "${HOOK_REGEX_CACHE_SEEN[$skill]:-}" ]]; then
-    printf '%s' "${HOOK_REGEX_CACHE[$skill]}"
+  local skill="$1" manifest raw result idx=0
+  while [[ $idx -lt ${#HOOK_REGEX_CACHE_KEYS[@]} ]]; do
+    if [[ "${HOOK_REGEX_CACHE_KEYS[$idx]}" == "$skill" ]]; then
+      printf '%s' "${HOOK_REGEX_CACHE_VALS[$idx]}"
       return
     fi
+    idx=$((idx + 1))
+  done
   result="$(
     for manifest in "$REPO_ROOT/.pre-commit-hooks.yaml" "$REPO_ROOT/.pre-commit-config.yaml"; do
       [[ -f "$manifest" ]] || continue
@@ -116,8 +127,8 @@ hook_file_regexes() {
       printf '%s\n' "$raw"
     done
   )"
-  HOOK_REGEX_CACHE[$skill]="$result"
-  HOOK_REGEX_CACHE_SEEN[$skill]=1
+  HOOK_REGEX_CACHE_KEYS[${#HOOK_REGEX_CACHE_KEYS[@]}]="$skill"
+  HOOK_REGEX_CACHE_VALS[${#HOOK_REGEX_CACHE_VALS[@]}]="$result"
   printf '%s' "$result"
 }
 

tests/test-check-vale-style-sync.sh

@@ -123,6 +123,19 @@ else
   fail "exited non-zero when skill-audit/agent-audit are simply absent"
 fi
 
+# --- 5b. Exits 1 when REPO_ROOT does not exist ---
+# A nonexistent path used to fall through to the "neither copy present" no-op
+# (test 5 above) and exit 0 — indistinguishable from a real, verified in-sync
+# result. That guard is for a repo legitimately missing kyberforge, not a
+# typo'd or stale path.
+echo ""
+echo "--- exits 1 when REPO_ROOT does not exist ---"
+if bash "$SCRIPT" "/nonexistent/path/$(date +%s)-$$" > /dev/null 2>&1; then
+  fail "exited 0 for a nonexistent REPO_ROOT — expected exit 1"
+else
+  pass "exits non-zero for a nonexistent REPO_ROOT"
+fi
+
 # --- 6. Exits 1 when only one of the two copies is present ---
 # The no-op guard used `||`, so a single missing copy also exited 0 — a deleted
 # or renamed copy passed the sync check silently.

tests/test-vale-wrap.sh

@@ -447,7 +447,10 @@ fi
 # scripts, and the test runner AGENTS.md tells contributors to run by hand.
 # `mapfile` is checked alongside, because it is bash 4.0+ and the expansion scan
 # cannot see it — run-tests.sh carried one until it was replaced with a
-# `while read` loop, and nothing would have caught its return.
+# `while read` loop, and nothing would have caught its return. `declare -A`
+# (bash 4.0+ associative arrays) is checked for the same reason — the
+# expansion scan cannot see it, and check-vale-style-sync.sh carried a pair of
+# them until they were replaced with index-scanned plain arrays.
 echo ""
 echo "--- no unguarded array expansion remains in the macOS-facing scripts ---"
 unguarded_expansions() {
@@ -474,6 +477,7 @@ for BASH32_SCRIPT in \
   "$SCRIPT" \
   "$REPO_ROOT/scripts/skill-size-check.sh" \
   "$REPO_ROOT/scripts/check-release-needed.sh" \
+  "$REPO_ROOT/scripts/check-vale-style-sync.sh" \
   "$REPO_ROOT/tests/run-tests.sh"; do
   FOUND16="$(unguarded_expansions "$BASH32_SCRIPT")"
   if [[ -n "$FOUND16" ]]; then
@@ -486,6 +490,15 @@ for BASH32_SCRIPT in \
   if [[ -n "$FOUND16B" ]]; then
     HAZARDS16+="${BASH32_SCRIPT##*/}:$FOUND16B "
   fi
+  # `declare -A` (associative arrays) is bash 4.0+ with no 3.2 fallback. The
+  # flag cluster can carry other letters in any order (-Ag, -rA, ...); what
+  # matters is a literal uppercase A appearing in it, so match on that rather
+  # than the exact string "-A".
+  FOUND16C="$(awk '{ if ($0 ~ /^[[:space:]]*#/) print ""; else print }' "$BASH32_SCRIPT" \
+    | grep -nE '(^|[^[:alnum:]_])declare[[:space:]]+-[a-zA-Z]*A[a-zA-Z]*([[:space:]]|$)' || true)"
+  if [[ -n "$FOUND16C" ]]; then
+    HAZARDS16+="${BASH32_SCRIPT##*/}:$FOUND16C "
+  fi
 done
 if [[ -n "$HAZARDS16" ]]; then
   fail "unguarded array expansion(s) abort on bash < 4.4 under set -u: $(echo "$HAZARDS16" | tr '\n' ' ')"