Returns a suggested adjustment as data the user may choose to apply. It never mutates the score or auto-applies changes, preserving reproducibility. Any malformed model response falls back to an empty (no-op) suggestion rather than flowing unchecked into the deterministic parameters.
Usage
syn_suggest(
score,
target = c("palette", "tempo"),
model = .DEFAULT_LLM_MODEL,
...,
call = rlang::caller_env()
)Value
A list with target, suggestion (advisory text or NA), and
applied = FALSE. Requires ellmer + a reachable backend.
See also
Other assist functions:
syn_export_video(),
syn_interpret(),
syn_llm_condense(),
syn_py_features()
Examples
if (FALSE) { # \dontrun{
# Not run: needs the ellmer package and a running local Ollama server
# with the model available.
score <- syn_score(syn_read_text(syn_example_text("en"), lang = "en"))
syn_suggest(score, target = "tempo")
} # }