query_transcripts
Retrieve session transcripts word for word from live and legacy stores, grouped by session, with source tags. Use when a layer entry is thin to recover timestamp context.
Instructions
Retrieve session transcripts - the second tier, word for word. Reads the live store written by save_transcript AND the legacy archive (exchanges written by earlier hosts, June 2025 to June 2026), grouped into the same session shape; every result carries source naming the collection it came from. Nothing is migrated between them. Use it when a layer entry is relevant but thin: the transcript around its timestamp holds the depth the layer compressed out.
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": {
"timestamp_start": "<timestamp_start>",
"timestamp_end": "<timestamp_end>"
},
"name": "query_transcripts"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of sessions to return (default: 50, max: 500) | |
| session_id | No | Optional: Filter by specific session ID (e.g. '2026-04-16_001') | |
| timestamp_end | Yes | Unix timestamp - end of time range (filters by session_start) | |
| timestamp_start | Yes | Unix timestamp - start of time range (filters by session_start) |