process_trace_update
Updates and monitors cognitive traces for AI agents by tracking actions, goals, and context, enabling metacognitive analysis with MCP Dual-Cycle Reasoner to detect reasoning loops and optimize decision-making.
Instructions
Process a cognitive trace update from the agent (main monitoring function)
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| current_context | No | Current environment context or state, in low dash format. Example: adding_product_item | |
| goal | Yes | Current goal being pursued | |
| last_action | Yes | Latest action name to be added to the accumulated action history | |
| window_size | No | Size of the monitoring window |
Input Schema (JSON Schema)
{
"$schema": "http://json-schema.org/draft-07/schema#",
"additionalProperties": false,
"properties": {
"current_context": {
"description": "Current environment context or state, in low dash format. Example: adding_product_item",
"type": "string"
},
"goal": {
"description": "Current goal being pursued",
"type": "string"
},
"last_action": {
"description": "Latest action name to be added to the accumulated action history",
"type": "string"
},
"window_size": {
"default": 10,
"description": "Size of the monitoring window",
"type": "number"
}
},
"required": [
"last_action",
"goal"
],
"type": "object"
}