@fieldwangai/agentflow 0.1.25

package/builtin/nodes/tool_get_env.md

@@ -0,0 +1,14 @@
+---
+# 内置节点：按 key 读取环境/配置
+description: Get environment variable value
+displayName: GetEnv
+input:
+  - type: text
+    name: key
+    default: ""
+output:
+  - type: text
+    name: value
+    default: ""
+---
+${USER_PROMPT}

package/builtin/nodes/tool_load_key.md

@@ -0,0 +1,20 @@
+---
+# 内置节点：按 key 读取
+description: Load key-value from global storage
+displayName: LoadKey
+input:
+  - type: node
+    name: prev
+    default: ""
+  - type: text
+    name: key
+    default: ""
+output:
+  - type: node
+    name: next
+    default: ""
+  - type: text
+    name: result
+    default: ""
+---
+${USER_PROMPT}

package/builtin/nodes/tool_nodejs.md

@@ -0,0 +1,40 @@
+---
+# 内置节点：执行 Node.js
+description: |
+  Execute Node.js script via agentflow apply -ai run-tool-nodejs.
+
+  **Success/Failure:** Determined by script process **exit code**—0 = success, non-0 = failed.
+  **Result Output:** Script stdout directly becomes result slot content (plain text, e.g., `console.log("hello")`).
+  When stdout is empty and exit code is non-0, stderr info will be written to failure message.
+
+  **JSON Compatible (Optional):** If stdout is `{"err_code":0,"message":{"result":"..."}}` format, err_code will override exit code semantics, message.result writes to result slot. Only use when needing different success/failure semantics than exit code.
+
+  **Direct Execution Mode (Recommended):** Set `script` field in flow.yaml instance, pipeline will skip AI and execute directly.
+  `script` supports ${} placeholders (workspaceRoot, flowName, runDir, flowDir and all input/output slots), values are auto shell-quoted.
+  flowDir is absolute path of current pipeline flow.yaml directory, can be used to reference scripts in same directory.
+  Example: `script: node ${flowDir}/scripts/my-check.mjs --root ${workspaceRoot} --input ${todo}`
+
+  **Pin Path Constraint (Important):** File paths read/written by script **must be passed via pins**, forbidden to construct output paths inside script.
+  - All input slots with type 'file' (e.g., `figma_tree`, `semantic_outline`) are parsed from upstream connections by pipeline, script receives via CLI args.
+  - All output slots with type 'file' (e.g., `restore_todolist`, `screenshot_map`) are generated by pipeline as absolute paths following `output/<instanceId>/node_<instanceId>_<slot>.md` convention, script receives via CLI args and writes directly.
+  - Use `${slotName}` in `script` field to get correct path, e.g., `--figma-tree ${figma_tree} --output ${restore_todolist}`.
+  - **Forbidden** to use `outDirForNode`, manually write `node_<instance>_xxx.json` etc. in script—this causes script output path mismatch with pipeline parser convention, downstream nodes cannot find files.
+
+  **AI Execution Mode (Legacy):** Without `script` field, AI agent reads body and manually executes commands.
+
+  **Underlying Usage:**
+  agentflow apply -ai run-tool-nodejs <workspaceRoot> <flowName> <uuid> <instanceId> [execId] -- <scriptCmd> [args...]
+displayName: NodeJs
+input:
+  - type: node
+    name: prev
+    default: ""
+output:
+  - type: node
+    name: next
+    default: ""
+  - type: text
+    name: result
+    default: ""
+---
+${USER_PROMPT}

package/builtin/nodes/tool_print.md

@@ -0,0 +1,14 @@
+---
+# 内置节点：醒目输出
+description: Output content to user with special font style
+displayName: Print
+input:
+  - type: node
+    name: prev
+    default: ""
+output:
+  - type: node
+    name: next
+    default: ""
+---
+${USER_PROMPT}

package/builtin/nodes/tool_save_key.md

@@ -0,0 +1,20 @@
+---
+# 内置节点：按 key 写入
+description: Save key-value pair to global storage
+displayName: SaveKey
+input:
+  - type: node
+    name: prev
+    default: ""
+  - type: text
+    name: key
+    default: ""
+  - type: text
+    name: value
+    default: ""
+output:
+  - type: node
+    name: next
+    default: ""
+---
+${USER_PROMPT}

package/builtin/nodes/tool_user_ask.md

@@ -0,0 +1,23 @@
+---
+# 内置节点：用户选择（Switch 分支）
+description: 等待用户从多个选项中选择一个，流程暂停；按用户选择沿对应出边分支继续。每个 output 槽位对应一条分支，槽位的 description 作为选项文案。
+displayName: UserAsk
+input:
+  - type: node
+    name: prev
+    default: ""
+  - type: file
+    name: question
+    description: 要展示给用户的问题（Markdown 格式，可选）
+    default: ""
+output:
+  - type: node
+    name: option_0
+    description: 选项 0
+    default: ""
+  - type: node
+    name: option_1
+    description: 选项 1
+    default: ""
+---
+${USER_PROMPT}

package/builtin/nodes/tool_user_check.md

@@ -0,0 +1,22 @@
+---
+# 内置节点：用户确认
+description: 等待用户确认，流程暂停。展示确认内容给用户，用户可编辑/AI修改后保存，回复 "继续" 后重启流程。
+displayName: UserCheck
+input:
+  - type: node
+    name: prev
+    default: ""
+  - type: file
+    name: content
+    description: 要展示给用户确认的内容（Markdown 格式）
+    default: ""
+output:
+  - type: node
+    name: next
+    default: ""
+  - type: file
+    name: content
+    description: 用户确认后的内容（可能已编辑/AI修改）
+    default: ""
+---
+${USER_PROMPT}