fix(gemini): handle minimal reasoning effort budget
- Add minimal case to clampThinkingBudgetByEffort to avoid defaulting to full thinking budget
This commit is contained in:
@@ -13,6 +13,7 @@ import (
|
||||
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
||||
"github.com/QuantumNous/new-api/relay/constant"
|
||||
"github.com/QuantumNous/new-api/setting/model_setting"
|
||||
"github.com/QuantumNous/new-api/setting/reasoning"
|
||||
"github.com/QuantumNous/new-api/types"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
@@ -137,7 +138,7 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
|
||||
info.UpstreamModelName = strings.TrimSuffix(info.UpstreamModelName, "-thinking")
|
||||
} else if strings.HasSuffix(info.UpstreamModelName, "-nothinking") {
|
||||
info.UpstreamModelName = strings.TrimSuffix(info.UpstreamModelName, "-nothinking")
|
||||
} else if baseModel, level := parseThinkingLevelSuffix(info.UpstreamModelName); level != "" {
|
||||
} else if baseModel, level, ok := reasoning.TrimEffortSuffix(info.UpstreamModelName); ok && level != "" {
|
||||
info.UpstreamModelName = baseModel
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user