chuan/CLIProxyAPI
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPI.git synced 2026-02-03 04:50:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fixed: #696

Browse Source 
fix(translators): adjust prompt token calculation by subtracting cached tokens across Gemini, OpenAI, and Claude handlers
This commit is contained in:
Luis Pater
2025-12-24 23:29:18 +08:00
parent b7409dd2de
commit 06ad527e8c
3 changed files with 6 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
internal/translator/antigravity/claude/antigravity_claude_response.go
View File

@@ -271,11 +271,11 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() { if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
params.HasUsageMetadata = true params.HasUsageMetadata = true
params.PromptTokenCount = usageResult.Get("promptTokenCount").Int() params.CachedTokenCount = usageResult.Get("cachedContentTokenCount").Int()
params.PromptTokenCount = usageResult.Get("promptTokenCount").Int() - params.CachedTokenCount
params.CandidatesTokenCount = usageResult.Get("candidatesTokenCount").Int() params.CandidatesTokenCount = usageResult.Get("candidatesTokenCount").Int()
params.ThoughtsTokenCount = usageResult.Get("thoughtsTokenCount").Int() params.ThoughtsTokenCount = usageResult.Get("thoughtsTokenCount").Int()
params.TotalTokenCount = usageResult.Get("totalTokenCount").Int() params.TotalTokenCount = usageResult.Get("totalTokenCount").Int()
params.CachedTokenCount = usageResult.Get("cachedContentTokenCount").Int()
if params.CandidatesTokenCount == 0 && params.TotalTokenCount > 0 { if params.CandidatesTokenCount == 0 && params.TotalTokenCount > 0 {
params.CandidatesTokenCount = params.TotalTokenCount - params.PromptTokenCount - params.ThoughtsTokenCount params.CandidatesTokenCount = params.TotalTokenCount - params.PromptTokenCount - params.ThoughtsTokenCount
if params.CandidatesTokenCount < 0 { if params.CandidatesTokenCount < 0 {

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

@@ -87,15 +87,15 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
// Extract and set usage metadata (token counts). // Extract and set usage metadata (token counts).
if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() { if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() { if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int()) template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
} }
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() promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").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+thoughtsTokenCount)
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)

4
internal/translator/gemini/openai/chat-completions/gemini_openai_response.go
View File

@@ -89,15 +89,15 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
// Extract and set usage metadata (token counts). // Extract and set usage metadata (token counts).
if usageResult := gjson.GetBytes(rawJSON, "usageMetadata"); usageResult.Exists() { if usageResult := gjson.GetBytes(rawJSON, "usageMetadata"); usageResult.Exists() {
cachedTokenCount := usageResult.Get("cachedContentTokenCount").Int()
if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() { if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int()) template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
} }
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() promptTokenCount := usageResult.Get("promptTokenCount").Int() - cachedTokenCount
thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").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+thoughtsTokenCount)
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)