One row per process-level record (session-scoped records are not listed): its kind, name,
source (builtin:<name>, plugin:<name>, user, project), rank, state (lazy, active,
overridden, disabled), the estimated tokens its declaration costs, and whether the kind is
experimental. With diagnostics = TRUE, the redacted diagnostics log instead.
Value
A gptr_registry data frame (columns kind, name, source, rank, state,
tokens, experimental), or a gptr_diagnostics data frame (columns time, source,
event, class, message).
Examples
gptr_registry("tool")
#> <gptr_registry> 21 record(s)
#> kind name source rank state tokens experimental
#> tool app builtin:artifacts 6 active 94 FALSE
#> tool py builtin:lang 6 active 75 FALSE
#> tool sql builtin:lang 6 active 50 FALSE
#> tool knit builtin:lang 6 active 117 FALSE
#> tool sh builtin:bridges 6 active 69 FALSE
#> tool script builtin:bridges 6 active 116 FALSE
#> tool bg builtin:bridges 6 active 73 FALSE
#> tool jobs builtin:bridges 6 active 33 FALSE
#> tool read builtin:tools 6 active 218 FALSE
#> tool edit builtin:tools 6 active 397 FALSE
#> tool write builtin:tools 6 active 139 FALSE
#> tool grep builtin:tools 6 active 70 FALSE
#> tool find builtin:tools 6 active 30 FALSE
#> tool ls builtin:tools 6 active 30 FALSE
#> tool help builtin:tools 6 active 65 FALSE
#> tool search builtin:tools 6 active 40 FALSE
#> tool describe builtin:tools 6 active 40 FALSE
#> tool plot builtin:tools 6 active 68 FALSE
#> tool out builtin:tools 6 active 46 FALSE
#> tool r builtin:r 6 active 131 FALSE
#> tool ask builtin:ask 6 active 218 FALSE
gptr_registry(diagnostics = TRUE)
#> <gptr_diagnostics> 0 row(s)