@minded-ai/mindedjs 2.0.36-beta.4 → 2.0.36-beta.6

package/docs/low-code-editor/nodes.md

@@ -48,6 +48,8 @@ Trigger nodes are entry points that start your flows and initialize them with me
 
 ### Trigger Implementation
 
+Handle triggers in your agent code:
+
 ```ts
 import { events } from 'mindedjs/src/index';
 import { HumanMessage } from '@langchain/core/messages';
@@ -55,109 +57,77 @@ import { HumanMessage } from '@langchain/core/messages';
 agent.on(events.TRIGGER_EVENT, async ({ triggerName, triggerBody }) => {
   if (triggerName === 'customer-support-request') {
     return {
-      memory: {
-        customerQuery: triggerBody,
-        timestamp: new Date().toISOString(),
-      },
+      memory: { customerQuery: triggerBody, timestamp: new Date().toISOString() },
       messages: [new HumanMessage(triggerBody)],
     };
   }
+  // Return { isQualified: false } to prevent flow execution
 });
 ```
 
-#### Disqualifying Triggers
-
-Return an object with `isQualified: false` to prevent flow execution:
+## Prompt Nodes
 
-```ts
-agent.on(events.TRIGGER_EVENT, async ({ triggerName, triggerBody }) => {
-  // Only process during business hours
-  const hour = new Date().getHours();
-  if (hour < 9 || hour > 17) {
-    return { isQualified: false };
-  }
+Prompt nodes process input through LLM to generate intelligent responses or invoke tools. 
 
-  return {
-    isQualified: true,
-    memory: { businessHours: true },
-    messages: [new HumanMessage(triggerBody)],
-  };
-});
-```
+### Context
+- Prompt nodes automatically have access to previous nodes' output as context.
+- You can also inject context from the memory object using the {memory.propertyName} placeholder.
 
-## Prompt Nodes
+### Properties
+- `humanInTheLoop?: boolean` - When `true`, pauses execution after this node for human input before continuing. Use this property only if you need to gather an input from the user.
+- `canStayOnNode?: boolean` - When `true`, allows the node to route back to itself for iterative processing. Usually combined with `humanInTheLoop: true` to allow for iteration over human input.
 
-Prompt nodes process input through LLM to generate intelligent responses or invoke tools.
+### Limitations
+- Prompt nodes can not save information to memory directly. Rather the user & agent messages are stored in the messages array of the state object. Making user's input available to the next prompt nodes or tools in the form of input schema.
+- Image recognition is only supported when a user attaches an image to the message. If you need to extract information from an image, use a tool with agent.llm to process the image. Return the result in the tool response so following prompt nodes can use it.
 
-**Optional Properties:**
+### Common Prompt Patterns
 
-- `humanInTheLoop?: boolean` - When `true`, pauses execution after this node for human input before continuing
-- `canStayOnNode?: boolean` - When `true`, allows the node to route back to itself for iterative processing. Usually combined with `humanInTheLoop: true` to allow for iteration over human input.
+#### Extract Information from User
 
-**Example Usage:**
+Use `humanInTheLoop: true` and `canStayOnNode: true` with `promptCondition` edges for iterative information gathering:
 
 ```yaml
 - type: promptNode
-  name: content-reviewer
-  displayName: Content Reviewer
-  prompt: 'Ask user to review the content and approve or request changes.'
-  humanInTheLoop: true # Pause for human approval before proceeding
+  name: collect-customer-info
+  displayName: Collect Customer Information
+  prompt: 'Ask the user for their contact information (name, email, phone).'
+  humanInTheLoop: true
+  canStayOnNode: true
 
-- type: promptNode
-  name: research-assistant
-  displayName: Research Assistant
-  prompt: 'Request user for more information until you have gathered all necessary information.'
-  canStayOnNode: true # Allow iterative research until complete
-  humanInTheLoop: true # Pause for human approval before proceeding
+edges:
+  - source: collect-customer-info
+    target: validate-info
+    type: promptCondition
+    prompt: 'Has all required information been collected?'
 ```
 
-### Basic Configuration
+#### Notify User
+
+Use standard prompt nodes with `stepForward` edges for one-way notifications:
 
 ```yaml
 - type: promptNode
-  name: customer-service-agent
-  displayName: Customer Service Agent
-  prompt: |
-    You are a helpful customer service representative.
-    Respond to customer inquiries professionally.
-
-    Customer: {memory.customerName}
-    Issue: {memory.issueCategory}
-    Current Time: {system.currentTime}
-  llmConfig:
-    name: ChatOpenAI
-    properties:
-      model: gpt-4o
-      temperature: 0.7
-      max_tokens: 500
-```
+  name: send-confirmation
+  displayName: Send Confirmation
+  prompt: 'Send confirmation: Order {memory.orderId}, Total: {memory.orderTotal}'
 
-### Placeholder Support
-
-Prompt nodes support the following placeholder syntax:
-
-- **Memory placeholders**: `{memory.propertyName}` - Access values from the agent's memory state
-- **Nested memory values**: `{memory.customer.name}` - Access nested properties in memory
-- **System placeholders**: `{system.currentTime}` - Access system values like the current ISO timestamp
+edges:
+  - source: process-order
+    target: send-confirmation
+    type: stepForward
+```
 
-### LLM Configuration Options
+### Custom LLM Configuration
+Provide a custom LLM configuration to the prompt node using the `llmConfig` property.
 
 ```yaml
-# OpenAI
 llmConfig:
-  name: ChatOpenAI
+  name: ChatOpenAI  # or ChatAnthropic
   properties:
-    model: gpt-4o        # or gpt-4o-mini, gpt-3.5-turbo
-    temperature: 0.7     # 0.0 (deterministic) to 1.0 (creative)
+    model: gpt-4o
+    temperature: 0.7
     max_tokens: 500
-
-# Anthropic Claude
-llmConfig:
-  name: ChatAnthropic
-  properties:
-    model: claude-3-sonnet-20240229
-    temperature: 0.5
-    max_tokens: 1000
 ```
 
 ## Tool Nodes
@@ -173,41 +143,6 @@ Tool nodes execute functions to perform actions like API calls or database queri
   toolName: lookupOrder
 ```
 
-### Tool Implementation
-
-```ts
-import { z } from 'zod';
-import { Tool } from 'mindedjs/src/types/Tools.types';
-
-const schema = z.object({
-  orderId: z.string(),
-  customerEmail: z.string().optional(),
-});
-
-const lookupOrderTool: Tool<typeof schema, Memory> = {
-  name: 'lookupOrder',
-  description: 'Look up order details by order ID',
-  input: schema,
-  execute: async ({ input, memory }) => {
-    const order = await fetchOrderById(input.orderId);
-
-    if (!order) {
-      throw new Error(`Order ${input.orderId} not found`);
-    }
-
-    return {
-      memory: {
-        orderInfo: order,
-        orderStatus: order.status,
-      },
-      result: `Found order ${order.id} - Status: ${order.status}`,
-    };
-  },
-};
-
-export default lookupOrderTool;
-```
-
 ## Junction Nodes
 
 Junction nodes provide flow control without processing, useful for organizing routing logic.
@@ -223,27 +158,19 @@ Junction nodes provide flow control without processing, useful for organizing ro
 ### Routing Example
 
 ```yaml
-nodes:
-  - type: junction
-    name: route-customer-request
-    displayName: Route Customer Request
-  - type: promptNode
-    name: vip-support
-    displayName: VIP Support
-  - type: promptNode
-    name: standard-support
-    displayName: Standard Support
+- type: junction
+  name: route-customer-request
+  displayName: Route Customer Request
 
 edges:
   - source: route-customer-request
     target: vip-support
     type: logicalCondition
-    condition: "({ memory }) => memory.customerTier === 'premium'"
-
+    condition: "state.memory.customerTier === 'premium'"
   - source: route-customer-request
     target: standard-support
     type: logicalCondition
-    condition: "({ memory }) => memory.customerTier === 'standard'"
+    condition: "state.memory.customerTier === 'standard'"
 ```
 
 ## Jump To Nodes
@@ -259,100 +186,29 @@ Jump To nodes provide direct navigation to specific nodes, enabling flow transit
   targetNodeId: process-customer-order
 ```
 
-### Subflow Navigation
+### Cross-Flow Navigation
 
-Jump To nodes are particularly useful for organizing complex workflows into multiple flows:
+Jump To nodes enable navigation between flows. Target nodes can exist in different flow files, and state is preserved during jumps:
 
 ```yaml
-# Main flow
+# flows/mainFlow.yaml
 - type: jumpToNode
-  name: jump-to-refund-subflow
-  displayName: Jump To Refund Subflow
-  targetNodeId: refund-processing-trigger
+  name: go-to-refund-flow
+  displayName: Go To Refund Flow
+  targetNodeId: refund-processor
 
-# In refund subflow
+# flows/refundFlow.yaml
 - type: trigger
-  name: refund-processing-trigger
-  displayName: Refund Processing Trigger
+  name: refund-processor
+  displayName: Refund Processor
   triggerType: manual
 ```
 
-### Multi-Flow Example
-
-```yaml
-# flows/mainFlow.yaml
-nodes:
-  - type: trigger
-    name: customer-request
-    displayName: Customer Request
-    triggerType: manual
-
-  - type: promptNode
-    name: classify-request
-    displayName: Classify Request
-    prompt: |
-      Classify the customer request as either 'refund' or 'support'.
-      Customer message: {{messages.last.content}}
-
-  - type: jumpToNode
-    name: go-to-refund-flow
-    displayName: Go To Refund Flow
-    targetNodeId: refund-processor
-
-# flows/refundFlow.yaml
-nodes:
-  - type: trigger
-    name: refund-processor
-    displayName: Refund Processor
-    triggerType: manual
-
-  - type: tool
-    name: process-refund
-    displayName: Process Refund
-    toolName: processRefund
-```
-
-### Implementation Notes
-
-- **Direct Navigation**: Jump To nodes create direct edges to their target nodes
-- **Cross-Flow Support**: Target nodes can exist in different flow files
-- **State Preservation**: Current memory and message state is maintained during jumps
-- **No Processing**: Jump To nodes perform no data processing, only navigation
-
 ## Best Practices
 
-### Use Descriptive Names
-
-```yaml
-# ✅ Good
-- type: promptNode
-  name: technical-support-specialist
-  displayName: Technical Support Specialist
-
-# ❌ Avoid
-- type: promptNode
-  name: agent-1
-  displayName: Agent 1
-```
-
-### Keep Prompts Focused
-
-```yaml
-# ✅ Good - Specific role and context
-- type: promptNode
-  name: order-refund-processor
-  displayName: Order Refund Processor
-  prompt: |
-    You process customer refund requests for e-commerce orders.
-    Order ID: {{memory.orderId}}
-    Determine if refund should be approved based on order status and timing.
-
-# ❌ Avoid - Too broad
-- type: promptNode
-  name: general-assistant
-  displayName: General Assistant
-  prompt: 'Help the customer with anything they need'
-```
+- **Use descriptive names**: `technical-support-specialist` not `agent-1`
+- **Keep prompts focused**: Define specific roles and context, avoid overly broad prompts
+- **Always include `displayName`**: Required for prompt nodes, recommended for all nodes
 
 ## Browser Task Nodes
 
@@ -367,20 +223,18 @@ Browser task nodes allow your agent to interact with web pages using AI-powered
   prompt: 'Go to amazon.com and search for wireless headphones under $100'
 ```
 
-### Browser Task with Custom Model
+### Custom Model
 
-You can specify which AI model to use for browser automation:
+Specify which AI model to use (default: `gpt-4o`):
 
 ```yaml
 - type: browserTask
-  name: complex_task
+  name: complex-task
   displayName: Complex Web Task
   prompt: 'Navigate to the support page and fill out the contact form'
-  model: 'gpt-4o' # Options: gpt-4o (default), gpt-4-turbo, claude-3-opus, etc.
+  model: 'gpt-4o' # Options: gpt-4o, gpt-4-turbo, claude-3-opus, etc.
 ```
 
-The browser task will execute the prompt using the browser-use CLI tool, which provides AI-powered browser automation capabilities.
-
 ## Next Steps
 
 - [**Edges**](edges.md) - Connect nodes with intelligent routing

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@minded-ai/mindedjs",
-  "version": "2.0.36-beta.4",
+  "version": "2.0.36-beta.6",
   "description": "MindedJS is a TypeScript library for building agents.",
   "main": "dist/index.js",
   "types": "dist/index.d.ts",