Mnemostack Feedback
mnemostack_feedbackRecord explicit recall feedback to update source weights with Q-learning; pass retriever labels as sources, and signal='clicked' also logs inhibition-of-return exposure.
Instructions
Record explicit feedback for stateful recall learning.
Use signal='clicked' to also record inhibition-of-return exposure. Pass retriever labels from mnemostack_search results as sources so Q-learning can update source weights.
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": {
"hit_id": "<hit_id>",
"signal": "<signal>"
},
"name": "mnemostack_feedback"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Natural language question or keyword associated with the feedback | |
| hit_id | Yes | ||
| reward | No | ||
| signal | Yes | ||
| source | No | ||
| sources | No | ||
| query_type | No |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||