Address reviewer round-2 fail-closed feedback on 333f6cc:
- Incident doc no longer claims the regression uses @intlify/message-compiler
baseCompile; it states the regression uses vue-i18n's public createI18n/
global.t API recursing nested objects and arrays.
- The placeholder render assertion now runs inside the locale loop, so both
Thai and English are each explicitly asserted to render name@company.com
(previously only the final English locale was asserted after the loop).
Verified: frontend tests 11 passed; production build index-B4oVHpLg.js passed.
Production /login rendered a blank page (browser console: SyntaxError: 10
through the vue-i18n parser). Root cause proved with a RED regression
(RES: vue-i18n public API reproduces 'Invalid linked format' code 10) plus an
independent reviewer: auth.emailPlaceholder="name@company.com" is invalid
vue-i18n linked-message syntax, so createI18n() throws a message-compilation
SyntaxError while LoginView renders t('auth.emailPlaceholder').
Fix: escape the literal at-sign as name{'@'}company.com in th and en so the
message compiles and the visible label is unchanged (name@company.com). Add an
all-translations regression that translates every string in th/en (objects
and arrays) through vue-i18n's public createI18n/global.t API and asserts the
visible placeholder value.
Verification:
- RED test failed at th:auth.emailPlaceholder (code 10) before the fix.
- Independent reviewer verified reproduction + fix, finished PASS.
- Frontend tests 11 passed; production build passed (index-B4oVHpLg.js).
- Chrome headless rendered the login card, Thai heading, and name@company.com
from the production dist. Artifact checksum hash 3621155075b3d9245d2d05511aaf39b1b0cbcaeea local vs server.
Production JS bundle was a few very long minified lines (first line ~105K,
max ~190K). Some JS engines/browsers (notably older Safari/iOS) fail to parse
a single minified line that long, throwing 'SyntaxError: 10' at the end of
line 1 and showing a white screen even though the asset is served complete
and valid (verified: hash matches local, node --check passes, full 564K).
Switch to terser minifier with max_line_len=120 so the bundle emits 4,988
short lines (max ~1.9K) instead of ~24 huge lines. Asset hash changes
(cache-bust). Frontend 10 tests pass; build OK.
Also fix docker-compose port: SPA is now served by nginx on :8080, so map
external 3000 -> 8080 (was 3000->3000 pointing at a removed vite dev server).
The 'จัดกลุ่มอัตโนมัติ' button was hidden inside v-if='agentGroups.length > 0'
— chicken-and-egg problem. Now shows trigger button when profiles exist
but groups don't, and groups section after categorization.
Backend:
- Add /api/agent-group/categorize endpoint — AI groups agents by role
- Add /api/agent-group/filter endpoint — filter by selected groups
- Groups with default_enabled=false (advertiser, brand) are unchecked
Frontend:
- Add agent groups section in Step2EnvSetup.vue
- 'Auto-categorize' button triggers AI grouping
- Show groups with checkboxes (enabled groups checked, disabled unchecked)
- Auto-remove unchecked agents when proceeding to Step 3
- Show selected count summary
- Add marketing metadata to 'Not allowed' list in ontology prompt
- Strengthen exclude_self filter instruction
- Add exclude_rules support from template filter rules
- Update business_ad template with more excluded types
- Add use cases section with 4 scenario cards (news, policy, business, fiction)
- Rewrite Thai home section text to be natural (not translated from Chinese)
- Add use case locale keys for th/en/zh
- Add CSS for use cases grid with hover effects
1. Restore OPENAI_API_KEY/OPENAI_BASE_URL env vars for camel-ai factory check
(keep api_key/base_url in model_config_dict for client constructor)
2. Add Thai-supporting font-family to .profile-realname
(JetBrains Mono doesn't render Thai diacritics)
3. Keep model_config_dict with api_key and base_url for camel-ai client
The error interceptor was re-throwing the generic axios Error object
instead of extracting the actual error message from the response body.
Now extracts error.response.data.error for meaningful error messages.
- Extract error from err.response.data.error (axios error response)
- Log full error to console for debugging
- Show actual backend error message instead of generic 'Error'
- Add isEnvAlive check on mount via /api/simulation/env-status
- Show warning banner when simulation env is not running
- Add alert() on survey failure for visibility
- Add envNotRunning translation key for th/en/zh
- Set VITE_API_BASE_URL=https://opinion-api.moreminimore.com for
frontend-backend split deployment
- Vite proxy also uses API_BACKEND_URL env var as target
- Falls back to same-origin proxy for local dev
When deployed behind a reverse proxy (e.g. opinion.moreminimore.com),
hardcoding http://localhost:5001 causes the browser to try connecting
to the user's own machine. Empty baseURL + vite proxy fixes this.
- Add sans-serif font for English left-pane (status, workflow sections)
- Shorten English workflow step descriptions
- Reduce English report title font-size from 36px to 28px
- Use sans-serif font for English titles, descriptions and navbar
- Shorten English hero text to avoid overflow
- Fix :global() scoped CSS issue that was setting root font-size to 3.5rem
- Use separate unscoped style block for html[lang] selectors
