plur_session_end
End a session by reviewing the conversation, extracting corrections, preferences, patterns, and technical facts into reusable memory suggestions, ensuring nothing learned is lost.
Instructions
End a session. BEFORE calling this tool, review the conversation and extract learnings:
Corrections the user made ("no, use X not Y") → type: behavioral
Preferences stated ("always X", "never Y") → type: behavioral
Codebase patterns discovered (naming, structure, conventions) → type: architectural
Technical facts learned (API quirks, config, gotchas) → type: procedural
Terminology defined or clarified → type: terminological
Include at least one engram_suggestion if ANYTHING was learned. An empty suggestions array means nothing worth remembering happened — this should be rare.
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": {
"summary": "<summary>",
"engram_suggestions": "<engram_suggestions>"
},
"name": "plur_session_end"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| summary | Yes | What happened in this session (1-3 sentences) | |
| session_id | No | Session ID from plur_session_start | |
| engram_suggestions | Yes | Learnings from this session. Preferred shape is {statement: "...", type?: "..."}; bare strings are also accepted and treated as the statement. Review the conversation for corrections, preferences, patterns, and technical facts before calling. |