launch: add plan-aware model gating (#16027)

2026-05-06 14:34:26 -07:00
parent 7c2c36bda2
commit bab59072fb
17 changed files with 1747 additions and 138 deletions
--- a/api/types.go
+++ b/api/types.go
@@ -814,6 +814,7 @@ type ModelRecommendation struct {
 	ContextLength   int    `json:"context_length,omitempty"`
 	MaxOutputTokens int    `json:"max_output_tokens,omitempty"`
 	VRAMBytes       int64  `json:"vram_bytes,omitempty"`
+	RequiredPlan    string `json:"required_plan,omitempty"`
 }

 // ProcessResponse is the response from [Client.Process].