This landing page helps operators, workflow authors, and extension developers find the right documentation for DevAll backend components. Use the table below as your navigation map; drill into the linked chapters for full procedures and examples.
| Topic | Highlights |
|---|---|
| Web UI Quick Start | Frontend interface operations, workflow execution, human review, troubleshooting. |
| Workflow Authoring | YAML structure, node types, provider/edge conditions, template export, CLI execution. |
| Graph Execution Logic | DAG/cyclic graph execution, Tarjan cycle detection, super node construction, recursive cycle execution. |
| Dynamic Parallel Execution | Map/Tree modes, split strategies, parallel processing and hierarchical reduction. |
| Memory Module | Memory list architecture, built-in simple/file/blackboard behaviors, embedding config, troubleshooting. |
| Thinking Module | Reasoning enhancement, self-reflection mode, extending custom thinking modes. |
| Tooling Module | Function/MCP modes, context injection, built-in function catalog, MCP launch patterns. |
| Node Types Reference | Agent, Python, Human, Subgraph, Passthrough, Literal, Loop Counter node configurations. |
| Attachment & Artifact APIs | Upload/list/download endpoints, manifest schema, cleanup strategies, security constraints. |
FIELD_SPECS Standard |
Field metadata contract that powers UI forms and template export—required reading before customizing modules. |
| Config Schema API Contract | /api/config/schema(*) request examples and breadcrumbs protocol (mostly for frontend/IDE integrations). |
- Workflow orchestration engine: Parses YAML DAGs, coordinates
model,python,tooling, andhumannodes inside a shared context, and writes node outputs intoWareHouse/<session>/. - Provider abstraction: The
runtime/node/agent/providers/layer encapsulates OpenAI, Gemini, and other APIs so each node can swap models, base URLs, credentials, plus optionalthinkingandmemoriessettings. - Real-time observability: FastAPI + WebSocket streams node states, stdout/stderr, and artifact events to the Web UI, while structured logs land in
logs/for centralized collection. - Run asset management: Every execution creates an isolated session; attachments, Python workspace, context snapshots, and summary outputs are downloadable for later review.
- Entry: Web UI and CLI call the FastAPI server exposed via
server_main.py(e.g.,/api/workflow/execute). - Validation/queueing:
WorkflowRunServicevalidates YAML, creates a session, preparescode_workspace/attachments/, then hands the DAG to the scheduler inworkflow/. - Execution: Node executors resolve dependencies, propagate context, call tools, and retrieve memories;
MemoryManager,ToolingConfig, andThinkingManagertrigger inside agent nodes as needed. - Observability: WebSocket pushes states, logs, and artifact events; JSON logs stay in
logs/, andWareHouse/stores run assets. - Cleanup & download: After completion you can bundle the session for download or fetch files individually via the attachment APIs; retention policies are deployment-specific.
- Solutions/Prompt Engineers: Begin with Workflow Authoring; read the Memory and Tooling module docs when you need context memories or custom tools.
- Extension Developers: Combine
FIELD_SPECSwith the Tooling module guide to register new components; reference config_schema_contract.md if you need to debug schema-driven UI.
- Session: Unique ID (timestamp + name) for a single run, used across the Web UI, backend, and
WareHouse/. - code_workspace: Shared directory for Python nodes at
WareHouse/<session>/code_workspace/, synchronized with relevant attachments. - Attachment: Files uploaded by users or generated during runs; list/download via REST or WebSocket APIs.
- Memory Store / Attachment: Stores define persistence backends; memory attachments describe how agent nodes read/write those stores across phases.
- Tooling: Execution environment bound to agent nodes (Function or MCP implementations).
If you spot gaps or outdated instructions, open an issue/PR or edit the docs directly (remember to keep Chinese and English versions in sync).