mirror of https://github.com/langgenius/dify.git
2d60be311d
The model_provider field in prompt generation traces was being incorrectly
extracted by parsing the model name (e.g., 'deepseek-chat'), which resulted
in an empty string when the model name didn't contain a '/' character.
Now extracts the provider directly from the model_config parameter, with
a fallback to the old parsing logic for backward compatibility.
Changes:
- Update _emit_prompt_generation_trace to accept model_config parameter
- Extract provider from model_config.get('provider') when available
- Update all 6 call sites to pass model_config
- Maintain backward compatibility with fallback logic
|
||
|---|---|---|
| .. | ||
| output_parser | ||
| __init__.py | ||
| entities.py | ||
| llm_generator.py | ||
| prompts.py | ||