LLMMessageListRead
Lightweight LLM message log entry returned by the dialogue LLM-message list endpoint. The full instructions text is intentionally omitted.
Unique numeric identifier of the record.
ID of the product (workspace) that owns this record. Most endpoints scope access by product.
ID of the agent (a configured AI assistant / bot persona) this record belongs to.
ID of the dialogue (conversation) this record relates to.
Possible values: [chatbot, classification, document, calendar, ping, stm_agent, meetings_reminder_agent, subagent_routing_agent, summarizer_agent, rag_subpromps_selector_agent, retrieval_mode_classifier, retrieval_query_rewriter, retrieval_reranker, knowledge_unit_context_generator, scrape_url_selector, scrape_page_normalizer, input_sanitizer_agent, input_misuse_agent, email_auto_reply_classifier, customer_support_resolution_classifier, customer_support_csi_classifier, customer_support_request_category_matcher, customer_support_request_category_proposer, refusal_reason_matcher, refusal_reason_proposer, silent_refusal_classifier, lead_timezone_collector_agent, reaction_picker_agent, is_message_for_agent_resolver, incoming_dialogue_router, rl_loop_contrast_analyst, rl_loop_hypothesis_generator, rl_loop_synthesis_agent, rl_loop_ab_test_suggester, rl_loop_prompt_variant_editor, initial_outreach, calendar_service_extractor, tags_extractor, crm_fields_extractor, language_extractor, stage_reset_agent, human_clarification_reset_agent, success_stage_movement_agent, dq_stage_movement_agent, refused_stage_movement_agent, escalated_stage_movement_agent, pending_stage_movement_agent, redirected_stage_movement_agent, stage_movement_arbiter_agent, pending_until_extractor, custom_follow_up_stage_movement_agent, custom_follow_up_datetime_extractor, pending_follow_up_agent, human_clarification_follow_up_agent, human_clarification_question_reformulator, human_clarification_recall_agent, redirect_contacts_extractor, crm_contact_fields_extractor, redirect_follow_up_agent, refiner_agent, output_formatter, tree_nodes_check_agent, tree_nodes_arbiter_agent, redirect_intent_agent]
Possible values: [request, response]
llm_model_name object
- string
- null
provider_name object
- string
- null
00000Creation time (UTC, ISO 8601).
after_bot_messages_sequence_id object
- string
- null
Whether this LLM message has a non-empty instructions value that can be fetched through the per-message instructions endpoint.
falsefalseclient_tool_calls object[]
Client-tool trace links found in this LLM message. Use call_id to open the corresponding tool trace for the same agent.
Client-tools trace call identifier. This is the path parameter for the trace endpoints and is not the LLM message row id.
Provider-level tool-call identifier inside the persisted LLM message parts.
Name of the client tool invoked by the model.
{
"id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"product_id": 0,
"agent_id": 0,
"dialogue_id": 0,
"run_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"llm_type": "chatbot",
"kind": "request",
"parts": [
{}
],
"llm_model_name": "string",
"provider_name": "string",
"input_tokens": 0,
"output_tokens": 0,
"total_tokens": 0,
"cache_write_tokens": 0,
"cache_read_tokens": 0,
"created_at": "2024-07-29T15:51:28.071Z",
"seq": 0,
"after_bot_messages_sequence_id": "string",
"has_instructions": false,
"is_client_tool_call": false,
"client_tool_calls": [
{
"call_id": "3fa85f64-5717-4562-b3fc-2c963f66afa6",
"tool_call_id": "string",
"tool_name": "string"
}
]
}