The conversation now ENDS when the persona makes a decision (option C), not when the
trainee clicks a button:
- persona_id replies carry {reply, decision(none/buy/walk), mood}; when decision is
buy/walk the session auto-finishes (won/lost) with a debrief that reveals latent
details + per-turn 'turning points'.
- personas have a tolerance (1-5, 'temper'): impatient personas walk away fast after
poor answers (fed via internal.misses on mood<=-1); tough 'wrong text' cases can
still be won by a strong, gentle response (judge realism).
- trainee 'Finish' button removed; if they leave mid-chat an active session is resumed
via /chat/resume (continue, not restart). One-shot lock still enforced once decided.
- mock/tests updated: persona deciding buy -> send auto-finishes won.
Rebuilt dist.
Backend:
- Channel/initiation now driven by a SCENARIO chosen at chat start, not baked into the
persona: social (customer opens), f2f_call (seller must open, proactive), recontact
(customer re-contacts after 1-3 months).
- /chat/start accepts {scenario}; session stores scenario + internal{turns,score}.
- persona_reply takes scenario + adapts tone; system-role transcript entries are fed to
the persona as hidden scene notes.
- JUDGE updated for realism: good response can WIN even in hard/tough-text scenarios;
long/no-close chats (turns >~12) lose; pushy/ignoring-need loses. Efficiency rewarded.
Frontend:
- Scenario picker before chat (choose Social / Face-to-face-call / Re-contact).
- Chat thread renders role=system as a centered time-lapse/scene note.
- Choose-scenario i18n (EN+TH).
Rebuilt dist.
The GroupBuilder sends the create form as multipart/form-data (FormData). The code
decided JSON vs form by checking — when no file was attached,
request.files was empty/falsy, so it tried get_json() on a multipart body and lost the
product field -> 400 'provide product info' even though the user filled the product name.
Fix: branch on the Content-Type (multipart/form-data -> request.form) instead of
request.files. Added a regression test (multipart create with product only -> 201).
Verified live: multipart product-only create now returns 201.
Tab 1 Admin overview (/): aggregate stats + DATE FILTER (?from&to), hardest personas,
admin quick actions (Users / + Add product).
Tab 2 My dashboard (/my/board): per-user win/lose/session summary (works for admin too).
Tab 3 Training (/training): product list w/ status + persona count; admins see all groups
(draft->analyze/edit), trainees see ready->personas; persona list shows DIFFICULTY (1-5
stars); admins get a Manage-personas button.
Settings (/settings): profile (name/email) via new PATCH /api/auth/profile + change
password + language.
Backend: analytics date filter; profile endpoint; /api/me/board + /api/chat/sessions
opened to any authed user.
Rebuilt frontend/dist.
Root cause of 'wrong password' right after logout->login (no redeploy): after first-run
setup sets an email, users naturally type their EMAIL in the login field, but verify()
only looked up by USERNAME -> user not found -> 'invalid credentials' shown as wrong
password. Now verify(ident) = get_user_or_none(username) OR by_email(ident). Verified:
login by username (200) and by email (200) both work with the new password.
Tests: m0/setup/e2e all pass.
