- Change REDIS_DB_CELERY_BROKER default from 1 to 3
- Change REDIS_DB_CELERY_BACKEND default from 2 to 4
- Add documentation comments explaining DB isolation strategy
- Prevent task interference when multiple developers share same Redis instance
1. From the model square to the model list, the added models are initially set to be inactive. When manually activating them, a mandatory API key configuration is required.
2. Copying of applications (agent, workflow, multi_agent)
- Replace BROKER_URL and RESULT_BACKEND with REDIS_DB_CELERY_BROKER and REDIS_DB_CELERY_BACKEND in README.md
- Replace BROKER_URL and RESULT_BACKEND with REDIS_DB_CELERY_BROKER and REDIS_DB_CELERY_BACKEND in README_CN.md
- Update api/env.example with new variable names and add deprecation notice
- Add reference to celery-env-bug-report.md documentation explaining why old variable names are avoided
- Prevents environment variable hijacking by Celery CLI when using standard naming conventions
- Rename CELERY_BROKER and CELERY_BACKEND to REDIS_DB_CELERY_BROKER and REDIS_DB_CELERY_BACKEND to avoid Celery CLI prefix matching hijacking
- Build canonical broker and backend URLs and force them into os.environ to prevent override by stray environment variables
- Add logging for Celery app initialization with sanitized connection details
- Update celery_app.py to use pre-built URL variables instead of inline construction
- Add documentation reference to celery-env-bug-report.md explaining the environment variable naming convention
- Prevents Celery CLI's Click framework from intercepting broker/backend configuration through environment variables
1. Increase support for visual models and multimodal models;
2. The application and workflow can input various multimodal files such as images, documents, audio, and videos.
* [fix] Revising the judgment method for the interest analysis tags
* [fix] Revising the judgment method for the interest analysis tags
* [add] Set cache for the distribution of interest tags
* [fix] Revising the judgment method for the interest analysis tags
* [add] Set cache for the distribution of interest tags
* [changes] 1.Use structured logs;
2.Align the type and default value of "end_user_id" with the semantic meaning of "required".