Skip to contents

Composes a short, citable account of a run: a design header (kind, run id, the participating agents, and a compact workflow summary), the model and token paragraph drafted by LLMR::llm_methods_text() over the run's call-level rows, and a one-line limits note. When no calibration is attached and the run is not a calibrated inference, the note states that the results are model-conditioned and are not estimates of a human population.

Usage

# S3 method for class 'agent_run'
report(x, ...)

Arguments

x

An object accepted by as_agent_run().

...

May include task, a one-clause description of what the model was asked to do (spliced into the methods paragraph).

Value

An object of class agent_report: a character vector with a print method that cat()s the lines.

Examples

if (FALSE) { # \dontrun{
a <- agent("Aria", LLMR::llm_config("groq", "openai/gpt-oss-20b"))
a$chat("Hello")
report(a, task = "to answer a factual question")
} # }