Spending and effort limits for an agent

Call, tool-call, and elapsed-time limits are checked before every model round. When one is exhausted, the agent raises a condition of class llmragent_budget_error without making the next call. max_tokens is a recorded-use gate: the agent stops before the next call once recorded usage reaches the limit, but one response can take the total past it because the response's token count is not known in advance.

Usage

budget(
  max_calls = Inf,
  max_tokens = Inf,
  max_tool_calls = Inf,
  max_seconds = Inf
)

Arguments

max_calls

Maximum number of model calls, counting chat exchanges, memory compactions, and retrieval-memory embedding operations.

max_tokens

Stop before the next model call once recorded sent and received tokens reach this value.

max_tool_calls

Maximum executed tool invocations.

max_seconds

Wall-clock ceiling, measured from the agent's first call.

Value

An object of class agent_budget.

Examples

b <- budget(max_calls = 10, max_tokens = 50000)

if (FALSE) { # \dontrun{
cfg <- LLMR::llm_config("groq", "openai/gpt-oss-20b")
frugal <- agent("Frugal", cfg, budget = budget(max_calls = 2))
frugal$chat("one")
frugal$chat("two")
tryCatch(frugal$chat("three"),
         llmragent_budget_error = function(e) "refused before spending")
} # }