fix: distinguish reflection questions from factual claims

Do not treat past-action wording inside a question as an asserted user biography.

src/compliment_forest/quality.py

@@ -242,6 +242,23 @@ def _action_roots(text: str) -> set[str]:
     return {root for form, root in _ACTION_LOOKUP.items() if form in tokens}
 
 
+def _match_is_in_question(text: str, start: int) -> bool:
+    sentence_start = max(
+        text.rfind(".", 0, start),
+        text.rfind("!", 0, start),
+        text.rfind("?", 0, start),
+    )
+    sentence_end_candidates = [
+        position
+        for punctuation in ".!?"
+        if (position := text.find(punctuation, start)) >= 0
+    ]
+    if not sentence_end_candidates:
+        return False
+    sentence_end = min(sentence_end_candidates)
+    return text[sentence_start + 1 : sentence_end + 1].strip().endswith("?")
+
+
 def unsupported_specificity(text: str, situation: str) -> set[str]:
     """Find concrete claims in generated prose that the user did not provide."""
 
@@ -266,6 +283,8 @@ def unsupported_specificity(text: str, situation: str) -> set[str]:
     )
     for pattern, lookup in past_claims:
         for match in pattern.finditer(text):
+            if _match_is_in_question(text, match.start()):
+                continue
             root = lookup[match.group("verb").casefold()]
             if root not in situation_actions:
                 issues.add("unsupported_past_claim")