AI activity in conversation
How the AI handled the conversation: recent runs with decision, reply text, knowledge used and every tool call with its arguments and result.
bearer conversations:readAuthorizationBearer <token>API key (rsl_live_…) from Settings → Developers.
Scope: conversations:read
conversationId*stringConversation id with channel prefix, e.g. chat_k57… or email_j97….
^(chat|email)_[a-z0-9]+$limit?integerNewest runs to return (default 5).
1 <= value <= 305runId?stringReturn only this run, with untruncated tool results.
length <= 64compact?booleanDrop repeated guidance texts (e.g. aiGuidance) from tool results and cap each result at 1500 characters.
falseSuccess
application/json- response
data*array<>curl -X GET "https://example.com/conversations/string/ai-runs"{ "data": [ { "id": "string", "status": "string", "isDebug": true, "reply": "string", "model": "string", "failure": { "reason": "string", "detail": "string" }, "attachmentFindings": [ { "file": "string", "observed": "string", "skipped": "string" } ], "tools": [ "string" ], "toolCalls": [ { "tool": "string", "arguments": "string", "result": "string", "status": "string", "durationMs": 0 } ], "knowledge": [ "string" ], "createdAt": 0 } ]}Update contact PATCH
Update a contact's name, email, phone, order number or internal notes.
Re-run AI (debug) POST
Re-run the AI on the latest customer message as a debug run: nothing is sent; lookup (read) skills run live, action skills (refill, restart…) are only recorded with their arguments, never executed. Review it with conversation_ai_trace and send it with conversation_ai_send.