Implement phase 1 of the file module migration by moving workflow-facing file primitives to core.workflow.file while keeping core.file as a temporary compatibility layer.
What this commit changes
- Add core.workflow.file package (constants/enums/models/helpers/file_manager/tool_file_parser).
- Add protocol-based runtime binding in core.workflow.file.runtime and core.workflow.file.protocols.
- Add application adapter core.app.workflow.file_runtime and bind runtime in extensions.ext_storage.init_app.
- Bind runtime in tests via tests/conftest.py.
- Migrate workflow-only imports from core.file.* to core.workflow.file.* across workflow runtime/nodes/entry/encoder and workflow node factory.
- Update workflow unit tests to patch/import the new workflow file namespace.
- Remove workflow-external-imports ignore_imports entries related to core.file from .importlinter.
Compatibility guarantee for phase split
- Keep core.file import path available in this phase by replacing core/file/*.py with forwarding bridge modules that re-export core.workflow.file symbols.
- Preserve runtime behavior and isinstance(File) identity consistency while non-workflow modules are still on legacy import paths.
Notes
- This commit intentionally does not remove core.file. Full repository replacement and bridge removal are handled in phase 2.
Enhance `LLMNode` with multimodal capability, introducing support for
image outputs.
This implementation extracts base64-encoded images from LLM responses,
saves them to the storage service, and records the file metadata in the
`ToolFile` table. In conversations, these images are rendered as
markdown-based inline images.
Additionally, the images are included in the LLMNode's output as
file variables, enabling subsequent nodes in the workflow to utilize them.
To integrate file outputs into workflows, adjustments to the frontend code
are necessary.
For multimodal output functionality, updates to related model configurations
are required. Currently, this capability has been applied exclusively to
Google's Gemini models.
Close#15814.
Signed-off-by: -LAN- <laipz8200@outlook.com>
Co-authored-by: -LAN- <laipz8200@outlook.com>
