Add MiniMax AI as the 7th LLM provider, supporting chat (M2.7, M2.5,
M2.5-highspeed) and embedding (embo-01) models via OpenAI-compatible API.
Changes:
- Add MINIMAX enum to ChatModeType
- Add MinimaxServiceImpl chat provider (OpenAI-compat streaming)
- Add MinimaxEmbeddingProvider for vector embeddings
- Add SQL migration for provider and model registration
- Add 14 unit tests + 3 integration tests
- Update README/README_EN with MiniMax in provider list
This commit introduces a structured RAG troubleshooting guide based on a fixed 16-problem failure map.
Changes include:
1. Added a dedicated RAG troubleshooting document:
- docs/troubleshooting/rag-failures.md
- Includes full 16-problem map (No.1–No.16) with layer tags [IN]/[RE]/[ST]/[OP]
- Adds symptom-based entry points
- Adds layer-based diagnostics section
- Adds issue reporting template referencing No.X labels
2. Updated README.md:
- Added entry link under the "使用文档" section
- Direct link to the new RAG troubleshooting guide
- Keeps README structure and tone consistent
No functional changes.
Documentation only.
