perseus_reflect
Recall relevant memories to answer a question, using an LLM to produce a grounded response with citations, or review the memory context yourself.
Instructions
Synthesize an insight from stored memories. Given a question, Perseus Vault recalls the most relevant memories and asks the configured LLM (your OpenAI/GPT-5.6 key by default) to produce a grounded answer citing them. If no LLM is configured, returns the assembled memory context so you can reason over it yourself.
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": {
"query": "<query>"
},
"name": "perseus_reflect"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | The question to reflect on, e.g. 'what are this project's conventions?' | |
| top_k | No | How many memories to ground the answer in (default 8). |