The default thinking budget tokens value was changed from 10000 to 1024 in base.py, and the minimum validation constraint was updated from 1024 to 1 in app_schema.py to allow smaller budgets while maintaining backward compatibility.
- Remove redundant `response_format` injection for VOLCANO provider since it's unsupported; rely on system prompt injection instead
- Extend system prompt JSON injection logic to cover VOLCANO and tool-enabled cases universally
- Simplify model parameter construction by removing redundant `params["model_kwargs"] = model_kwargs` assignments
- Refactor `CompatibleChatOpenAI._get_request_payload` to strip `response_format` when tools are present, avoiding strict validation errors in langchain_openai
- Fix timestamp calculation order in `datetime_tool.py` to avoid integer truncation before multiplication
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.
1. Add the "Skills" module;
2. The loading of the model square has been modified to be controlled through environment variables;
3. Dynamic scheduling of the skill binding tool;
4. Agent Integration Skills
Merge branch 'develop' into feature/20251219_myh
* feature/20251219_myh: (8 commits squashed)
- feat(workflow): update reranker model configuration for knowledge base retrieval
- fix(workflow): fix output issue in parameter extraction node
- fix(workflow): fix output issue in parameter extraction node
- feat(workflow): add user prompt to parameter extraction node
- perf(workflow): change grouped variable input to key-value format in variable aggregator
- feat(workflow): Add new cycle node for iterative workflow execution
- Introduce a new Loop/Iteration node in the workflow engine.
- Supports both conditional loops and iteration over lists.
- Allows parallel execution and flattening of iteration outputs.
- Maintains runtime state, node outputs, and loop variables for downstream nodes.
- Enhances workflow flexibility for complex, repeated operations.
- Merge branch 'develop' into feature/20251219_myh
# Conflicts:
#	api/app/core/workflow/nodes/configs.py
#	api/app/core/workflow/nodes/node_factory.py
- feat(workflow): Add new cycle node for iterative workflow execution
- Introduce a new Loop/Iteration node in the workflow engine.
- Supports both conditional loops and iteration over lists.
- Allows parallel execution and flattening of iteration outputs.
- Maintains runtime state, node outputs, and loop variables for downstream nodes.
- Enhances workflow flexibility for complex, repeated operations.
Signed-off-by: Eternity <1533512157@qq.com>
Reviewed-by: zhuwenhui5566@163.com <zhuwenhui5566@163.com>
Reviewed-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
Merged-by: aliyun6762716068 <accounts_68cb7c6b61f5dcc4200d6251@mail.teambition.com>
CR-link: https://codeup.aliyun.com/redbearai/python/redbear-mem-open/change/78
