Fix usage convertation from gemini response to openai format

This commit is contained in:
Alexey Yanchenko
2026-02-19 15:34:59 +07:00
parent 1ff5de9a31
commit b9ae4ab803
4 changed files with 10 additions and 10 deletions

View File

@@ -100,9 +100,9 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
baseTemplate, _ = sjson.Set(baseTemplate, "usage.total_tokens", totalTokenCountResult.Int())
}
promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
promptTokenCount := usageResult.Get("promptTokenCount").Int()
thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
baseTemplate, _ = sjson.Set(baseTemplate, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
baseTemplate, _ = sjson.Set(baseTemplate, "usage.prompt_tokens", promptTokenCount)
if thoughtsTokenCount > 0 {
baseTemplate, _ = sjson.Set(baseTemplate, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
}
@@ -297,7 +297,7 @@ func ConvertGeminiResponseToOpenAINonStream(_ context.Context, _ string, origina
promptTokenCount := usageResult.Get("promptTokenCount").Int()
thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount)
if thoughtsTokenCount > 0 {
template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
}

View File

@@ -531,8 +531,8 @@ func ConvertGeminiResponseToOpenAIResponses(_ context.Context, modelName string,
// usage mapping
if um := root.Get("usageMetadata"); um.Exists() {
// input tokens = prompt + thoughts
input := um.Get("promptTokenCount").Int() + um.Get("thoughtsTokenCount").Int()
// input tokens = prompt only (thoughts go to output)
input := um.Get("promptTokenCount").Int()
completed, _ = sjson.Set(completed, "response.usage.input_tokens", input)
// cached token details: align with OpenAI "cached_tokens" semantics.
completed, _ = sjson.Set(completed, "response.usage.input_tokens_details.cached_tokens", um.Get("cachedContentTokenCount").Int())
@@ -737,8 +737,8 @@ func ConvertGeminiResponseToOpenAIResponsesNonStream(_ context.Context, _ string
// usage mapping
if um := root.Get("usageMetadata"); um.Exists() {
// input tokens = prompt + thoughts
input := um.Get("promptTokenCount").Int() + um.Get("thoughtsTokenCount").Int()
// input tokens = prompt only (thoughts go to output)
input := um.Get("promptTokenCount").Int()
resp, _ = sjson.Set(resp, "usage.input_tokens", input)
// cached token details: align with OpenAI "cached_tokens" semantics.
resp, _ = sjson.Set(resp, "usage.input_tokens_details.cached_tokens", um.Get("cachedContentTokenCount").Int())