camel-ai's OpenAI model reads OPENAI_BASE_URL, not OPENAI_API_BASE_URL.
This caused all simulation LLM calls to go to api.openai.com instead of
the configured provider (DeepSeek, Xiaomi Mimo, etc), resulting in 401.
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
- Time config: translate all Chinese instructions and field descriptions
- Event config: translate hot topics/narrative direction instructions
- Agent config: translate entity type descriptions and field labels
- Profile generator: translate all persona prompt fields and instructions
- Country field: changed from 'use Chinese' to 'use English'
- simulation_config_generator.py: translate all LLM prompts and system messages
- oasis_profile_generator.py: translate profile generation prompts
Ensures get_language_instruction() controls output language instead of
being overridden by Chinese prompt context.
- Interview prompt prefix: Chinese -> English
- Sub-query decomposition: Chinese -> English
- Agent selection: Chinese -> English
- Interview questions: Chinese -> English
- Interview summary: Chinese -> English
- Error messages: Chinese -> English
- to_text() labels: Chinese -> English
This ensures get_language_instruction() actually controls output language
instead of being overridden by Chinese prompt context.
- Add locales/th.json with 629 translated keys
- Add Thai to languages.json with llmInstruction for report generation
- Backend auto-loads new locale files from locales/ directory
- 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.
The Shanda sponsor logo's alt text was `666ghj%2MiroFish | Shanda`,
missing the `F` from the URL-encoded `/`. Every other badge in both
READMEs uses the correct `666ghj%2FMiroFish`. Bring this one in line
with the rest.
- Add return type annotation (list[str]) to Config.validate()
- Add type annotations (msg: str, -> None) to logger convenience functions
- Add FileParser.is_supported() classmethod for checking file format support
- 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
Background threads (graph building, simulation prep, report generation,
profile generation) now inherit the requesting user's locale preference.
Previously these fell back to 'zh' because Flask request context was
unavailable in spawned threads.
Ensure poster_type stays PascalCase English and stance stays English enum
values regardless of language setting. Only natural language fields follow
the user's language preference.
The language instruction was causing LLM to change entity/relation naming
conventions. Now explicitly enforce PascalCase/UPPER_SNAKE_CASE for technical
identifiers while only applying language preference to description fields.
