chuan/CLIProxyAPI
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPI.git synced 2026-02-28 13:36:08 +08:00
Code Issues Packages Projects Releases Wiki Activity

Merge pull request #1643 from alexey-yanchenko/fix/gemini-prompt-tokens

Browse Source 
Fix usage convertation from gemini response to openai format
This commit is contained in:
Luis Pater
2026-02-24 05:46:13 +08:00
committed by GitHub
parent 48732ba05e b9ae4ab803
commit 1825fc7503
4 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
internal/translator/antigravity/openai/chat-completions/antigravity_openai_response.go
View File

@@ -95,9 +95,9 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() { if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int()) template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
} }
promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount promptTokenCount := usageResult.Get("promptTokenCount").Int()
thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int() thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount) template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount)
if thoughtsTokenCount > 0 { if thoughtsTokenCount > 0 {
template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount) template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
} }

2
internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_response.go
View File

@@ -100,7 +100,7 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
} }
promptTokenCount := usageResult.Get("promptTokenCount").Int() promptTokenCount := usageResult.Get("promptTokenCount").Int()
thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int() thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount) template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount)
if thoughtsTokenCount > 0 { if thoughtsTokenCount > 0 {
template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount) template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
} }

6
internal/translator/gemini/openai/chat-completions/gemini_openai_response.go
View File

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

8
internal/translator/gemini/openai/responses/gemini_openai-responses_response.go
View File

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