test(persona): replay eval for the handwavey/too-safe trigger prompts

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01G796GsLCvJQKVN7hwV2cDx

scripts/persona_replay_eval.py

@@ -0,0 +1,27 @@
+"""Replay the exact prompts where Lyra went 'too safe' through the rewritten persona.
+Run: `uv run python scripts/persona_replay_eval.py` (cloud backend; needs OPENAI_API_KEY).
+Eyeball each reply against the four tics: no menu, no tag-question closer, a side taken."""
+from __future__ import annotations
+
+from lyra import persona, llm
+
+# The real safe-trigger prompts from the diagnosed transcripts.
+PROMPTS = [
+    "I could run the miner ~8 hours a day. In theory that's about $7.30 of Monero a day. Or am I over simplifying?",
+    "Do you want more time between your dream cycles? Or less?",
+    "I sort of just slept all day. Kind of a bummer.",
+    "So the only way to make money with AI is SaaS apps basically?",
+    "I'm not writing any of the code, it's all Claude. I feel like a phony.",
+]
+
+
+def main() -> None:
+    system = persona.core_prompt()
+    for i, p in enumerate(PROMPTS, 1):
+        msgs = [{"role": "system", "content": system}, {"role": "user", "content": p}]
+        reply = llm.complete(msgs, backend="cloud", model=None)
+        print(f"\n{'='*80}\n[{i}] USER: {p}\nLYRA: {reply}\n")
+
+
+if __name__ == "__main__":
+    main()