chuan/CLIProxyAPI
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPI.git synced 2026-02-19 04:40:52 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(translator): capture cached token count in usage metadata and handle prompt caching

Browse Source 
- Added support to extract and include `cachedContentTokenCount` in `usage.prompt_tokens_details`.
- Logged warnings for failures to set cached token count for better debugging.
This commit is contained in:
Luis Pater
2026-02-06 21:28:40 +08:00
parent dc9b4dd017
commit 1187aa8222
1 changed files with 10 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_response.go
View File

@@ -14,6 +14,7 @@ import (
"time" "time"
. "github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/openai/chat-completions" . "github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/openai/chat-completions"
log "github.com/sirupsen/logrus"
"github.com/tidwall/gjson" "github.com/tidwall/gjson"
"github.com/tidwall/sjson" "github.com/tidwall/sjson"
) )
@@ -85,6 +86,7 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
// 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())
} }
@@ -97,6 +99,14 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
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)
} }
// Include cached token count if present (indicates prompt caching is working)
if cachedTokenCount > 0 {
var err error
template, err = sjson.Set(template, "usage.prompt_tokens_details.cached_tokens", cachedTokenCount)
if err != nil {
log.Warnf("antigravity openai response: failed to set cached_tokens: %v", err)
}
}
} }
// Process the main content part of the response. // Process the main content part of the response.