fix(auq): harden error-fallback hook + harness per adversarial review

Codex pre-landing review found three real issues:
- The PostToolUse fallback hook shared source 'plan-tune-cathedral' with the
  question-log hook (same event+matcher); gstack-settings-hook replaces the entry,
  so it would have clobbered plan-tune capture. Give it its own 'auq-error-fallback'
  source (separate entry, both run); ALREADY_INSTALLED now requires both sources.
- isErrorResponse triggered on any string containing 'internal error'/'is_error',
  so a real answer or a {"is_error": false} payload could fire the fallback after a
  successful question. Narrow it to the missing-result sentinel + boolean is_error.
- The SDK runner mutated process.env.GSTACK_HEADLESS process-wide (leaked headless
  into later tests). Removed; GSTACK_HEADLESS=1 now lives in the eval package.json
  scripts, scoped to the invocation and inherited by the SDK child.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

setup

@@ -1325,9 +1325,13 @@ if [ "$NO_TEAM_MODE" -ne 1 ] \
    && [ -x "$PLAN_TUNE_LOG_HOOK" ] \
    && [ -x "$PLAN_TUNE_PREF_HOOK" ]; then
 
-  # Already installed? Check the settings.json for our source tag.
+  # Already installed? Require BOTH the plan-tune source AND the AUQ-error-fallback
+  # source — so an existing install that predates the fallback hook re-runs the
+  # install (which is idempotent for the plan-tune hooks) and picks up the new one.
   ALREADY_INSTALLED=0
-  if "$SETTINGS_HOOK" list-sources 2>/dev/null | grep -q "plan-tune-cathedral"; then
+  _HOOK_SOURCES=$("$SETTINGS_HOOK" list-sources 2>/dev/null || true)
+  if printf '%s' "$_HOOK_SOURCES" | grep -q "plan-tune-cathedral" \
+     && printf '%s' "$_HOOK_SOURCES" | grep -q "auq-error-fallback"; then
     ALREADY_INSTALLED=1
   fi
 
@@ -1365,15 +1369,19 @@ if [ "$NO_TEAM_MODE" -ne 1 ] \
       --command "$PLAN_TUNE_PREF_HOOK" \
       --source plan-tune-cathedral \
       --timeout 5
-    # AUQ-failure prose-fallback reliability hook (OV3:B). Fires only when an
-    # AskUserQuestion call returns an error/missing result; inert on success and
-    # inert if the platform doesn't invoke PostToolUse on tool errors.
+    # AskUserQuestion-failure prose-fallback reliability hook (OV3:B). Fires only when
+    # an AskUserQuestion call returns an error/missing result; inert on success and
+    # inert if the platform doesn't invoke PostToolUse on tool errors. MUST use its
+    # OWN source tag: gstack-settings-hook dedupes by (event, matcher, source) and
+    # REPLACES the entry's hooks, so sharing 'plan-tune-cathedral' would overwrite the
+    # question-log capture hook (same event+matcher). A distinct source = a second
+    # PostToolUse entry; both run in parallel.
     if [ -x "$AUQ_ERROR_FALLBACK_HOOK" ]; then
       "$SETTINGS_HOOK" add-event \
         --event PostToolUse \
         --matcher '(AskUserQuestion|mcp__.*__AskUserQuestion)' \
         --command "$AUQ_ERROR_FALLBACK_HOOK" \
-        --source plan-tune-cathedral \
+        --source auq-error-fallback \
         --timeout 5
     fi
   }