Each persona is one-shot (chat once = win/lose locked). To keep training repeatable:
- New endpoint POST /api/groups/<gid>/personas/<pid>/variant creates a NEW persona that is
a fresh incarnation of the source: LOCKS pain points, objections, negotiation levers,
tolerance, special/recontact, goal, budget, difficulty, tier, product_context — but VARYS
name/profession/age/location/background/personality/opener so it isn't an identical copy.
- Added to the same group as a distinct persona (fresh not_tried, so chat-able again).
- UI: on the Personas page, a finished (won/lost) persona gets a
'สร้างบุคคลต้นแบบจากต้นแบบนี้' button; reload shows the variant.
All 10 backend suites pass. Rebuilt dist.
- recontact persona now opens as a NORMAL customer (no 'I asked before' in the opening);
the mid-chat time-lapse system note (turn 2) makes them re-engage warmer instead.
- channel default changed facebook->social everywhere (create/analyze/store/simulator/me).
- 15 personas auto-generated (TARGET=15); removed the 'สร้างบุคคลต้นแบบเพิ่มเติม' button/guide.
All 9 backend suites pass. Rebuilt dist.
Live test found: deepseek returned 14/15 personas -> whole analyze 500'd, breaking the
'กดสร้าง -> auto-analyze' flow. Now generate() retries up to 3x with a nudge, and accepts
a short result (>=8 personas) instead of crashing — admin can top up the rest with
'สร้างบุคคลต้นแบบเพิ่มเติม'. Also default tolerance/recontact on generated personas.
All backend suites pass.
- llm.complete_conversation now maps internal roles (customer->assistant, seller->user,
system->system) before the API call — fixes 'Unknown role: customer' (501).
- Re-contact personality: the customer now chats normally, at turn 2 goes quiet and a
system time-lapse note is shown ('⏳ ผ่านไป 2-3 สัปดาห์...'), then re-engages warmer —
instead of 'pretending you asked before' at start. Driven by persona.recontact trait.
All 9 backend suites pass. Rebuilt dist.
- Scenario picker now has only social + f2f_call (removed recontact) in backend
_scenarios, start_session validation, and Chat.vue picker.
- 'ลูกค้ากลับมาติดต่อ' is no longer a scenario: it's now a PERSONA trait. Persona prompt
generates ~1-in-4 personas with recontact=true (asked before, now returns warmer/ready);
store shape gets recontact field; simulator injects a re-contact note into the persona's
system prompt so it plays as a returning customer naturally.
- test_scenario updated: unknown scenario defaults to social; recontact shown as a
generated persona trait.
All 9 backend suites pass. Rebuilt dist.
- list_groups returns lightweight summaries (id/title/status/persona_count + product) —
never the full personas array, so Training no longer shows a long JSON blob.
- PersonaForm toLines extracts .description/.text from pain/objection objects (fixes
'[object Object]'); save re-wraps pains as {description}.
- GroupEdit persona cards get a 'แชท' (MessageSquare) button so you can start chatting
right where you land after creating (chat was only on Personas page before).
- channel: default neutral 'social', removed facebook/line validation + removed from
revealable_view (scenario now sets the tone, not fb/line).
All 9 backend suites pass. Rebuilt dist.
- Backend DELETE /api/groups/<gid> (admin, own-org enforced via _get_owned_group);
cascades removal of the group's sessions. GroupStore.delete added.
- Training.vue: each group card gets a trash (Trash2 line icon) delete button shown only
to admins (auth.isAdmin); confirm dialog; @click.stop so it doesn't navigate. Card
restructured so the delete button is not inside the clickable router-link.
- test_user_journey: trainee cannot delete (403), admin deletes, group gone (404).
All suites pass. Rebuilt dist.
Per product-idea focus:
- GroupBuilder: 'สินค้า/บริการ/ไอเดีย' label; removed the channel select (channel is now
chosen at chat time as a scenario, not at persona create). Create now auto-runs analyze
so personas are generated immediately (no separate Analyze button).
- GroupEdit: analyze button becomes 'สร้างบุคคลต้นแบบเพิ่มเติม' which APPENDS more personas
(backend analyze?append=true reuses sales kit + keeps existing instead of replacing).
- i18n product label updated.
- User-journey test asserts append adds personas (15->30) and existing kept.
All 9 backend suites pass. Rebuilt dist.
Phase 1 (tenant isolation):
- g.org_id set on require_auth; assert_tenant()/current_org_id() choke-point helpers.
- Multi-org provisioning: POST /api/admin/users {new_org:true} (super_admin) creates a
new org + its first admin; GET /api/admin/orgs (super_admin sees all, admin own).
- Fixed latent create_org double-id bug (dict id != store key).
- test_saas_tenant.py: org2 admin blocked from org1 group (403), can't list org1
groups/users, sees only own org; super_admin sees all.
Phase 2 (hardening):
- Rate limit login (per-IP + per-username) + chat send (per-user) to protect LLM cost
and slow brute force; services/rate_limit.py (in-memory + disk, no external deps).
- Audit log data/audit/audit.jsonl on org.create, user.promote_super_admin, analytics.export.
- CSV export now org-scoped (admin exports only own org).
All 8 backend suites pass.
Backend:
- SCENARIOS localized (th/en): scenario preamble + persona tone adaptation follow the
trainee's locale; start accepts {locale} and stores it on the session; send/auto-finish
use it so debrief text (why/coaching/turning points) is in the active language.
- /api/analytics/export returns per-trainee finished-session CSV (admin).
Frontend:
- Scenario picker labels localize by i18n.locale.
- New /guide page (non-IT how-to), linked from Training.
- Analytics: date-filter bar uses line icon + 'Download CSV' button (fetch w/ auth).
Rebuilt dist.
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.
