Tool Details: agent_reload_context

Basic Information

Tool Name:agent_reload_context
Asset Name:Reload Agent Session Context
Description:Explicitly invalidates one idle session's cached provider prefix so its next cached inference rebuilds the system prompt, fixed tools, skill catalog and pinned context from current agent configuration and sources. Conversation history and loaded context are preserved exactly. Changed declarative config already triggers this on the next inference; use this operation to force a same-config refresh. Uncached models retain no prefix, so this is a harmless no-op for them.
Adapter:agent
Asset Hash:0xec2dbc684a76088f842b2b0e42a2a176fd2428b4cc9fb9b0ca591401c14f743e
Input
PropertyTypeDescription
sessionId*stringHex ID of the idle session whose provider prefix should be rebuilt, with or without a 0x prefix
agentId*stringAgent reference: a bare name for the caller's agent, g/<id>, /g/<id>, or <ownerDID>/g/<id>
Output
PropertyTypeDescription
reloadedbooleanTrue when a materialised prefix was cleared
agentIdstring-
addressstring-
sessionIdstring-
framesintegerNumber of frame prefixes cleared

MCP Tool Usage Examples

This tool can be called via the MCP (Model Context Protocol) endpoint. Here are examples of how to use it:

JSON-RPC Call Example:

POST to https://venue-2.covia.ai/mcp

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "agent_reload_context",
    "arguments": {
      "input": "your input here"
    }
  }
}
cURL Example:
curl -X POST https://venue-2.covia.ai/mcp \\
  -H "Content-Type: application/json" \\
  -d '{
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "agent_reload_context",
      "arguments": {
        "input": "your input here"
      }
    }
  }'
Python Example:
import requests
import json

url = "https://venue-2.covia.ai/mcp"
payload = {
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
        "name": "agent_reload_context",
        "arguments": {
            "input": "your input here"
        }
    }
}

response = requests.post(url, json=payload)
result = response.json()
print(result)
JavaScript/Node.js Example:
const fetch = require('node-fetch');

const url = 'https://venue-2.covia.ai/mcp';
const payload = {
    jsonrpc: '2.0',
    id: 1,
    method: 'tools/call',
    params: {
        name: 'agent_reload_context',
        arguments: {
            input: 'your input here'
        }
    }
};

fetch(url, {
    method: 'POST',
    headers: {
        'Content-Type': 'application/json'
    },
    body: JSON.stringify(payload)
})
.then(response => response.json())
.then(data => console.log(data));

Asset Metadata

{
	"name": "Reload Agent Session Context",
	"description": "Explicitly invalidates one idle session's cached provider prefix so its next cached inference rebuilds the system prompt, fixed tools, skill catalog and pinned context from current agent configuration and sources. Conversation history and loaded context are preserved exactly. Changed declarative config already triggers this on the next inference; use this operation to force a same-config refresh. Uncached models retain no prefix, so this is a harmless no-op for them.",
	"dateCreated": "2026-08-29T00:00:00Z",
	"operation": {
		"adapter": "agent:reloadContext",
		"readOnly": false,
		"internal": false,
		"toolName": "agent_reload_context",
		"input": {
			"type": "object",
			"properties": {
				"agentId": { "type": "string", "description": "Agent reference: a bare name for the caller's agent, g/<id>, /g/<id>, or <ownerDID>/g/<id>" },
				"sessionId": { "type": "string", "description": "Hex ID of the idle session whose provider prefix should be rebuilt, with or without a 0x prefix" }
			},
			"required": ["agentId", "sessionId"]
		},
		"output": {
			"type": "object",
			"properties": {
				"agentId": { "type": "string" },
				"address": { "type": "string" },
				"sessionId": { "type": "string" },
				"reloaded": { "type": "boolean", "description": "True when a materialised prefix was cleared" },
				"frames": { "type": "integer", "description": "Number of frame prefixes cleared" }
			}
		}
	}
}

Navigation

Back to adapter details

Back to all adapters

Back to index