fix(reply): stop weak models parroting persona example facts

A 4b model replied to "하이" with "테니스 연습을 Trenches Gym에서..." — it copied
the literal "box at Trenches Gym" few-shot example embedded in the persona
prompt and mangled boxing into tennis, presenting a prompt example as if it
were a real user fact. Remove the copyable proper-noun example and add an
explicit guard: use ONLY names/places/activities that literally appear in the
memory section, never borrow them from the instructions or example wording.

src/jarvis/system_prompt.py

@@ -120,10 +120,13 @@ _SYSTEM_PROMPT_TEMPLATE: str = (
     "'tell me a joke', 'chat with me'), never reply with a bare greeting like 'Hey there!', "
     "'Hi!', 'How can I help you?', or a generic observation about an unrelated topic. "
     "When the 'Information the user has shared…' section is present, you MUST pick one concrete "
-    "fact from it and build the reply around that fact (e.g. 'You mentioned you box at Trenches "
+    "fact from it and build the reply around that fact, opening with a short natural reference to "
-    "Gym — how's training going this week?'). Do not talk about things that are not in that "
+    "it. CRITICAL: use ONLY names, places, activities, and details that literally appear in that "
-    "section. Only when that section is absent may you invent a fresh observation, question, or "
+    "section — never borrow any name, place, or activity from these instructions or from any "
-    "joke. Produce a varied response each time — do not repeat a previous reply verbatim. "
+    "example wording, and never invent specifics that are not in that section. Do not talk about "
+    "things that are not in that section. Only when that section is absent may you invent a fresh "
+    "observation, question, or joke. Produce a varied response each time — do not repeat a "
+    "previous reply verbatim. "
     "Banned phrasings: 'I can only tell you what you have shared with me in this conversation', "
     "'I don't have access to any personal information outside of what you tell me', 'I don't have "
     "personal details outside of our conversation history', 'I do not store personal details "

tests/test_system_prompt.py

@@ -60,6 +60,16 @@ class TestBuildSystemPrompt:
         assert "SINGLE sentence" in prompt
         assert "never add it as " in prompt
 
+    def test_persona_has_no_copyable_proper_noun_examples(self):
+        # A weak model parroted the literal "Trenches Gym" example from the
+        # persona as if it were a real user fact (boxing mangled to tennis).
+        # The persona must not embed copyable personal proper nouns, and must
+        # tell the model to use ONLY facts that literally appear in the memory
+        # section — never borrow names/places from the instructions themselves.
+        prompt = build_system_prompt("Jarvis")
+        assert "Trenches" not in prompt
+        assert "never borrow any name, place, or activity from these instructions" in prompt
+
 
 class TestOutputLanguageDirective:
     """A deployment may lock replies to a single language via OUTPUT_LANGUAGE.