OpenAI-compatible runtimes differ in how they handle `response_format`:
cloud providers (OpenAI, Qwen/Dashscope, Ollama) accept
`{"type": "json_object"}`, while local runtimes like LM Studio and
llama.cpp server reject it with HTTP 400, only accepting `json_schema`
or `text`. This prevented MiroFish from running against fully-local
stacks.
Introduce `LLM_JSON_MODE` (default `json_object`) so users can opt out
of strict JSON response mode by setting `LLM_JSON_MODE=none`. The
existing prompt-based JSON + markdown-tolerant parsing already handles
the unstructured response path robustly, so `none` is viable for any
OpenAI-compatible endpoint.
Applied at all three call sites that send `response_format`:
- utils/llm_client.py (chat_json helper)
- services/oasis_profile_generator.py (persona synthesis)
- services/simulation_config_generator.py (time/event/agent config)
Documented in .env.example with guidance on when to pick each value.
- Deleted docker-compose.yml, backend Dockerfile, frontend Dockerfile, and nginx configuration to streamline project setup.
- Updated .env.example to reorganize LLM and ZEP API configurations for clarity and ease of use.
- Enhanced README.md to reflect changes in project structure and provide clearer setup instructions.
- Updated .env.example to reflect new LLM configuration with Aliyun's API.
- Enhanced .gitignore to include additional files and directories for better exclusion of sensitive and build artifacts.
- Added docker-compose.yml for streamlined deployment of backend and frontend services.
- Introduced Dockerfiles for both backend and frontend to facilitate containerized builds.
- Created README.md to provide comprehensive project documentation and setup instructions.
- Established nginx configuration for frontend to support API proxying and static file serving.
- Updated .env.example to include new keys for dual LLM configuration, allowing for both general and boost settings.
- Modified create_model function to support an optional use_boost parameter, enabling the selection of either general or boost LLM configurations based on availability.
- Improved logging to indicate which LLM configuration is being used during model creation, enhancing clarity for users.
Pedro Renan
666ghj