chuan/CLIProxyAPI
1
0
Fork 0
mirror of https://github.com/router-for-me/CLIProxyAPI.git synced 2026-02-18 20:30:51 +08:00
Code Issues Packages Projects Releases Wiki Activity

Fixed: #738

Browse Source 
fix(translators): refine prompt token calculation by incorporating cached tokens in Claude response handling
This commit is contained in:
Luis Pater
2025-12-27 03:56:11 +08:00
parent dcae098e23
commit 72274099aa
1 changed files with 12 additions and 22 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
internal/translator/claude/openai/chat-completions/claude_openai_response.go
View File

@@ -205,9 +205,12 @@ func ConvertClaudeResponseToOpenAI(_ context.Context, modelName string, original
if usage := root.Get("usage"); usage.Exists() { if usage := root.Get("usage"); usage.Exists() {
inputTokens := usage.Get("input_tokens").Int() inputTokens := usage.Get("input_tokens").Int()
outputTokens := usage.Get("output_tokens").Int() outputTokens := usage.Get("output_tokens").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", inputTokens) cacheReadInputTokens := usage.Get("cache_read_input_tokens").Int()
cacheCreationInputTokens := usage.Get("cache_creation_input_tokens").Int()
template, _ = sjson.Set(template, "usage.prompt_tokens", inputTokens+cacheCreationInputTokens)
template, _ = sjson.Set(template, "usage.completion_tokens", outputTokens) template, _ = sjson.Set(template, "usage.completion_tokens", outputTokens)
template, _ = sjson.Set(template, "usage.total_tokens", inputTokens+outputTokens) template, _ = sjson.Set(template, "usage.total_tokens", inputTokens+outputTokens)
template, _ = sjson.Set(template, "usage.prompt_tokens_details.cached_tokens", cacheReadInputTokens)
} }
return []string{template} return []string{template}
@@ -281,8 +284,6 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
var messageID string var messageID string
var model string var model string
var createdAt int64 var createdAt int64
var inputTokens, outputTokens int64
var reasoningTokens int64
var stopReason string var stopReason string
var contentParts []string var contentParts []string
var reasoningParts []string var reasoningParts []string
@@ -299,9 +300,6 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
messageID = message.Get("id").String() messageID = message.Get("id").String()
model = message.Get("model").String() model = message.Get("model").String()
createdAt = time.Now().Unix() createdAt = time.Now().Unix()
if usage := message.Get("usage"); usage.Exists() {
inputTokens = usage.Get("input_tokens").Int()
}
} }
case "content_block_start": case "content_block_start":
@@ -364,11 +362,14 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
} }
} }
if usage := root.Get("usage"); usage.Exists() { if usage := root.Get("usage"); usage.Exists() {
outputTokens = usage.Get("output_tokens").Int() inputTokens := usage.Get("input_tokens").Int()
// Estimate reasoning tokens from accumulated thinking content outputTokens := usage.Get("output_tokens").Int()
if len(reasoningParts) > 0 { cacheReadInputTokens := usage.Get("cache_read_input_tokens").Int()
reasoningTokens = int64(len(strings.Join(reasoningParts, "")) / 4) // Rough estimation cacheCreationInputTokens := usage.Get("cache_creation_input_tokens").Int()
} out, _ = sjson.Set(out, "usage.prompt_tokens", inputTokens+cacheCreationInputTokens)
out, _ = sjson.Set(out, "usage.completion_tokens", outputTokens)
out, _ = sjson.Set(out, "usage.total_tokens", inputTokens+outputTokens)
out, _ = sjson.Set(out, "usage.prompt_tokens_details.cached_tokens", cacheReadInputTokens)
} }
} }
} }
@@ -427,16 +428,5 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
out, _ = sjson.Set(out, "choices.0.finish_reason", mapAnthropicStopReasonToOpenAI(stopReason)) out, _ = sjson.Set(out, "choices.0.finish_reason", mapAnthropicStopReasonToOpenAI(stopReason))
} }
// Set usage information including prompt tokens, completion tokens, and total tokens
totalTokens := inputTokens + outputTokens
out, _ = sjson.Set(out, "usage.prompt_tokens", inputTokens)
out, _ = sjson.Set(out, "usage.completion_tokens", outputTokens)
out, _ = sjson.Set(out, "usage.total_tokens", totalTokens)
// Add reasoning tokens to usage details if any reasoning content was processed
if reasoningTokens > 0 {
out, _ = sjson.Set(out, "usage.completion_tokens_details.reasoning_tokens", reasoningTokens)
}
return out return out
} }