workflow-ai-coding

1# Workflow AI Coding
2 
3## Operating Rules
4 
5Treat the ReachAI platform repository and live API responses as the source of truth. Do not edit `runtime_workflow` or `runtime_workflow_resource_binding` rows directly. All graph and binding changes go through Workflow AI Coding REST endpoints under `/api/workflows/.../ai-coding`.
6 
7凡是写入 ReachAI 或展示给业务用户的名称、标题、描述、说明、System Prompt、节点名称、审计原因、进度和结果，默认使用清晰的简体中文。不要仅因 API、Schema 或字段名为英文就生成英文业务文案。Token、MCP、AI、Agent、Supervisor、Workflow、Tool、API、SDK 等熟知专业术语，以及 keySlug、toolName、代码、路径、枚举值、协议字段和技术标识可保留英文；必要时使用“中文名称（英文术语）”。不要翻译或改写技术标识。
8 
9Core mental model:
10 
11- `GraphSpec` is runtime semantics; `canvas_json` is layout only.
12- Create projects and lays out canvas from GraphSpec; patch defaults `layout.autoLayout=true`. The `layered` policy uses LR flow, 88px inter-layer boundary gaps, 56px same-layer gaps, and cycle-safe component packing. Before reporting back, confirm `canvas_json.nodes[].position` is non-overlapping and aligned; do not patch GraphSpec only and skip canvas synchronization.
13- `START` and `END` are Studio-only virtual canvas nodes. They never appear in GraphSpec nodes or edges.
14- Every workflow must set `graphSpec.entryNodeId` to a real node id and list every terminal node in `graphSpec.exitNodeIds`.
15- Workflow AI Coding updates the **Working Copy** until an explicit publish request is made.
16…