check_self_narration
Detect when a memory text contains assistant self-narration (AI reasoning, hedges, self-talk) rather than facts about the user or world. Returns a flag and markers to gate or rewrite before storage, preventing memory pollution.
Instructions
WRITE-TIME self-narration guard (read-only, no LLM): does this candidate memory read as the ASSISTANT narrating its own reasoning/state ("as an AI...", "I think...", "I remember that...") instead of a fact about the user/world? LLM memory-writers routinely store their own hedges and self-talk as if they were user facts, silently polluting the store. Returns {'self_narration': bool, 'markers': [...]} so you can gate or rewrite the write before remember(). Flags, never blocks.
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": {
"text": "<text>"
},
"name": "check_self_narration"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes |