docs/user_guide/en/modules/tooling/README.md
DevAll currently exposes two tool binding modes for agent nodes:
functions/function_calling/, with JSON Schema auto-generated from type hints.All tooling configs hang off AgentConfig.tooling:
nodes:
- id: solve
type: agent
config:
provider: openai
model: gpt-4o-mini
prompt_template: solver
tooling:
type: function
config:
tools:
- name: describe_available_files
- name: load_file
auto_load: true
timeout: 20
ToolingConfig selects FunctionToolConfig, McpRemoteConfig, or McpLocalConfig based on type. Field definitions live in entity/configs/tooling.py._context (attachment store, workspace paths, etc.) for Function tools or forwards the request through MCP.load_file).| Dimension | Function | MCP |
|---|---|---|
| Deployment | In-process Python functions shipped with the backend. | Remote: call an HTTP MCP endpoint. Local: launch a process and talk over stdio. |
| Schemas | Derived from annotations + ParamMeta. | Provided by the MCP server's JSON Schema. |
| Context | _context provides attachments + workspace helpers automatically. | Depends on the MCP server implementation. |
| Typical use | File I/O, local scripts, internal APIs. | Third-party tool suites, browsers, database agents. |
wait_for_log + timeouts to detect readiness.code_workspace/ should respect the lifecycle described in the Attachment guide (Chinese for now) to avoid leaking artifacts.