query_local_llm_stateful
Continue an existing local LLM conversation by passing a previous response ID. Preserves context server-side for efficient follow-ups.
Instructions
Follow-up: Use this ONLY for continuing an existing conversation when you have a previous_response_id. It is faster and preserves context server-side.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"input": "<input>"
},
"name": "query_local_llm_stateful"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| input | Yes | The user prompt. | |
| model | No | ||
| top_p | No | ||
| max_tokens | No | ||
| temperature | No | ||
| presence_penalty | No | ||
| reasoning_effort | No | Optional: Control for reasoning models. | |
| frequency_penalty | No | ||
| previous_response_id | No | Optional: ID from a previous response to continue the conversation. |