Models in the internal catalog now carry explicit output token limits and an advisor ranking.
Details
max_output_tokens.defaultandmax_output_tokens.upperare now populated for each model (e.g., Haiku 3.5: 8192/8192; Haiku 4.5: 32000/64000)advisor_rankfield added to models eligible for the advisor tool; models without an advisor rank emit a clearer error message pointing toCLAUDE_CODE_ENABLE_EXPERIMENTAL_ADVISOR_TOOL=1
Evidence
(search for "max_output_tokens", "advisor_rank", "has no advisor rank in the model catalog")
Strings lifted out of the shipped bundle, so the claim above can be checked against them.