kami
64e5f3bdc1
The nudge fixture only covered nudges. The shared persona block now goes into five prompts, and the three conversational ones were unmeasured — those are the long free-form replies where a persona break is most likely. Adds talk_v1.json (27 Russian cases, 9 per path) and ScoreTalk, reporting per-path as well as per-check so a chat regression can be told apart from a knowledge one. Reuses the persona checks; the nudge-only ones (length, mood, no questions) are left out, since a chat reply is allowed 1-3 sentences and a follow-up question. The LLM run is opt-in on MAVEN_LLM_URL as before. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01CGeSZxh1DCtRxmFVSYVGvJ