MaxOutputTokens reports the resolved output-token cap applied to each advisor call. NewRuntime validates that this value is positive and that it matches ModelConfig.MaxOutputTokens when both are set, so the accessor always returns the value the runtime will actually send.
()
| 126 | // it matches ModelConfig.MaxOutputTokens when both are set, so the |
| 127 | // accessor always returns the value the runtime will actually send. |
| 128 | func (rt *Runtime) MaxOutputTokens() int64 { |
| 129 | if rt == nil { |
| 130 | return 0 |
| 131 | } |
| 132 | return rt.cfg.MaxOutputTokens |
| 133 | } |
| 134 | |
| 135 | // ProviderOptions reports the resolved provider options applied to each |
| 136 | // advisor call. NewRuntime clones the supplied options so the returned |
no outgoing calls