AI agent usage logs

One row per LLM call a Chatwoot/iframe/specialist agent turn made — README_AIAGENTUSAGE_TOKENS.md. `bots/engine.py::run_bot_turn` already computes `usage` (token buckets) and `cost_usd` (real cost under the provider's pricing) for every turn, but until this model existed that number only ever reached a `logger.info` line ("bots.cost: ...") and was discarded — there was no way to answer "how much did agent X spend last week" without grepping raw server logs with no `agent_key` in the line. Written best-effort right after each `run_bot_turn` call (see `bots/usage_tracking.py::record`) — a failure saving this row must never break the reply the customer is waiting for.

Header api token: X-API-TOKEN

Obtener api token en Su configuración de cuenta

Métodos API permitidos: GET, POST, PUT, PATCH, OPCIONES


                
                    List URL: /api/v1/ai_chat_s/aiagentusagelog/
                    Detail URL: /api/v1/ai_chat_s/aiagentusagelog/:id/

Parámetros

_page_size: (int) Número de resultados por página
_page: (str|int) Número de páginas a consultar, coloque __all__ para obtener todos los resultados sin paginar
_ordering: (str) Campo para ordenar, si es descendente colocar '-', Ej: -nombre_del_campo
_fields: (str) Lista de los campos a devolver, separados por coma

Usted puede usar cualquer otro parametro de django para filtrar los datos

Muestra el método OPTIONS

 Cargando opciones de API ...