Search Agent Conversations
search_agent_conversationsSearch and filter LLM agent conversations by query, time, project, or environment to view summaries with cost, token, call-count, and preview data.
Instructions
Search Sentry agent conversations (formerly AI conversations): one summary row per LLM agent conversation with title, cost, tokens, call counts, and previews. For one conversation's transcript, use get_agent_conversation_details.
Tool call template
This tool declares no required parameters. Add optional parameters from the input schema as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {},
"name": "search_agent_conversations"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| end | No | End of the search window; requires start. | |
| fresh | No | Bypass cached reads. | |
| limit | No | ||
| query | No | Search filter for conversations. | |
| start | No | Start of the search window; requires end and overrides period. | |
| cursor | No | Pagination cursor from a previous response. | |
| period | No | Relative time window, e.g. `30m`, `24h`, `7d`, `90d`. | 30d |
| project | No | Project slug or numeric project ID, or an array of projects. | |
| regionUrl | No | The organization's region URL from `find_organizations`, e.g. `https://us.sentry.io`. Omit for self-hosted Sentry. | |
| environment | No | Environment name, or an array of environments. | |
| organizationSlug | No | The organization slug, from `find_organizations`. In `org/project` notation, the part before the slash. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| count | Yes | ||
| searchUrl | Yes | ||
| nextCursor | Yes | ||
| conversations | Yes | ||
| organizationSlug | Yes |