mirror of
https://github.com/router-for-me/CLIProxyAPI.git
synced 2026-02-17 03:40:52 +08:00
Compare commits
7 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c281f4cbaf | ||
|
|
3f50da85c1 | ||
|
|
8be06255f7 | ||
|
|
72274099aa | ||
|
|
dcae098e23 | ||
|
|
2eb05ec640 | ||
|
|
a00b79d9be |
@@ -114,6 +114,10 @@ CLI wrapper for instant switching between multiple Claude accounts and alternati
|
||||
|
||||
Native macOS GUI for managing CLIProxyAPI: configure providers, model mappings, and endpoints via OAuth - no API keys needed.
|
||||
|
||||
### [Quotio](https://github.com/nguyenphutrong/quotio)
|
||||
|
||||
Native macOS menu bar app that unifies Claude, Gemini, OpenAI, Qwen, and Antigravity subscriptions with real-time quota tracking and smart auto-failover for AI coding tools like Claude Code, OpenCode, and Droid - no API keys needed.
|
||||
|
||||
> [!NOTE]
|
||||
> If you developed a project based on CLIProxyAPI, please open a PR to add it to this list.
|
||||
|
||||
|
||||
@@ -113,6 +113,10 @@ CLI 封装器,用于通过 CLIProxyAPI OAuth 即时切换多个 Claude 账户
|
||||
|
||||
基于 macOS 平台的原生 CLIProxyAPI GUI:配置供应商、模型映射以及OAuth端点,无需 API 密钥。
|
||||
|
||||
### [Quotio](https://github.com/nguyenphutrong/quotio)
|
||||
|
||||
原生 macOS 菜单栏应用,统一管理 Claude、Gemini、OpenAI、Qwen 和 Antigravity 订阅,提供实时配额追踪和智能自动故障转移,支持 Claude Code、OpenCode 和 Droid 等 AI 编程工具,无需 API 密钥。
|
||||
|
||||
> [!NOTE]
|
||||
> 如果你开发了基于 CLIProxyAPI 的项目,请提交一个 PR(拉取请求)将其添加到此列表中。
|
||||
|
||||
|
||||
@@ -482,12 +482,16 @@ func StripUsageMetadataFromJSON(rawJSON []byte) ([]byte, bool) {
|
||||
cleaned := jsonBytes
|
||||
var changed bool
|
||||
|
||||
if gjson.GetBytes(cleaned, "usageMetadata").Exists() {
|
||||
if usageMetadata = gjson.GetBytes(cleaned, "usageMetadata"); usageMetadata.Exists() {
|
||||
// Rename usageMetadata to cpaUsageMetadata in the message_start event of Claude
|
||||
cleaned, _ = sjson.SetRawBytes(cleaned, "cpaUsageMetadata", []byte(usageMetadata.Raw))
|
||||
cleaned, _ = sjson.DeleteBytes(cleaned, "usageMetadata")
|
||||
changed = true
|
||||
}
|
||||
|
||||
if gjson.GetBytes(cleaned, "response.usageMetadata").Exists() {
|
||||
if usageMetadata = gjson.GetBytes(cleaned, "response.usageMetadata"); usageMetadata.Exists() {
|
||||
// Rename usageMetadata to cpaUsageMetadata in the message_start event of Claude
|
||||
cleaned, _ = sjson.SetRawBytes(cleaned, "response.cpaUsageMetadata", []byte(usageMetadata.Raw))
|
||||
cleaned, _ = sjson.DeleteBytes(cleaned, "response.usageMetadata")
|
||||
changed = true
|
||||
}
|
||||
|
||||
@@ -99,6 +99,14 @@ func ConvertAntigravityResponseToClaude(_ context.Context, _ string, originalReq
|
||||
// This follows the Claude Code API specification for streaming message initialization
|
||||
messageStartTemplate := `{"type": "message_start", "message": {"id": "msg_1nZdL29xx5MUA1yADyHTEsnR8uuvGzszyY", "type": "message", "role": "assistant", "content": [], "model": "claude-3-5-sonnet-20241022", "stop_reason": null, "stop_sequence": null, "usage": {"input_tokens": 0, "output_tokens": 0}}}`
|
||||
|
||||
// Use cpaUsageMetadata within the message_start event for Claude.
|
||||
if promptTokenCount := gjson.GetBytes(rawJSON, "response.cpaUsageMetadata.promptTokenCount"); promptTokenCount.Exists() {
|
||||
messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.usage.input_tokens", promptTokenCount.Int())
|
||||
}
|
||||
if candidatesTokenCount := gjson.GetBytes(rawJSON, "response.cpaUsageMetadata.candidatesTokenCount"); candidatesTokenCount.Exists() {
|
||||
messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.usage.output_tokens", candidatesTokenCount.Int())
|
||||
}
|
||||
|
||||
// Override default values with actual response metadata if available from the Gemini CLI response
|
||||
if modelVersionResult := gjson.GetBytes(rawJSON, "response.modelVersion"); modelVersionResult.Exists() {
|
||||
messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.model", modelVersionResult.String())
|
||||
|
||||
@@ -205,9 +205,12 @@ func ConvertClaudeResponseToOpenAI(_ context.Context, modelName string, original
|
||||
if usage := root.Get("usage"); usage.Exists() {
|
||||
inputTokens := usage.Get("input_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.total_tokens", inputTokens+outputTokens)
|
||||
template, _ = sjson.Set(template, "usage.prompt_tokens_details.cached_tokens", cacheReadInputTokens)
|
||||
}
|
||||
return []string{template}
|
||||
|
||||
@@ -281,8 +284,6 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
|
||||
var messageID string
|
||||
var model string
|
||||
var createdAt int64
|
||||
var inputTokens, outputTokens int64
|
||||
var reasoningTokens int64
|
||||
var stopReason string
|
||||
var contentParts []string
|
||||
var reasoningParts []string
|
||||
@@ -299,9 +300,6 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
|
||||
messageID = message.Get("id").String()
|
||||
model = message.Get("model").String()
|
||||
createdAt = time.Now().Unix()
|
||||
if usage := message.Get("usage"); usage.Exists() {
|
||||
inputTokens = usage.Get("input_tokens").Int()
|
||||
}
|
||||
}
|
||||
|
||||
case "content_block_start":
|
||||
@@ -364,11 +362,14 @@ func ConvertClaudeResponseToOpenAINonStream(_ context.Context, _ string, origina
|
||||
}
|
||||
}
|
||||
if usage := root.Get("usage"); usage.Exists() {
|
||||
outputTokens = usage.Get("output_tokens").Int()
|
||||
// Estimate reasoning tokens from accumulated thinking content
|
||||
if len(reasoningParts) > 0 {
|
||||
reasoningTokens = int64(len(strings.Join(reasoningParts, "")) / 4) // Rough estimation
|
||||
}
|
||||
inputTokens := usage.Get("input_tokens").Int()
|
||||
outputTokens := usage.Get("output_tokens").Int()
|
||||
cacheReadInputTokens := usage.Get("cache_read_input_tokens").Int()
|
||||
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))
|
||||
}
|
||||
|
||||
// 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
|
||||
}
|
||||
|
||||
@@ -114,13 +114,16 @@ func ConvertOpenAIResponsesRequestToClaude(modelName string, inputRawJSON []byte
|
||||
var builder strings.Builder
|
||||
if parts := item.Get("content"); parts.Exists() && parts.IsArray() {
|
||||
parts.ForEach(func(_, part gjson.Result) bool {
|
||||
text := part.Get("text").String()
|
||||
textResult := part.Get("text")
|
||||
text := textResult.String()
|
||||
if builder.Len() > 0 && text != "" {
|
||||
builder.WriteByte('\n')
|
||||
}
|
||||
builder.WriteString(text)
|
||||
return true
|
||||
})
|
||||
} else if parts.Type == gjson.String {
|
||||
builder.WriteString(parts.String())
|
||||
}
|
||||
instructionsText = builder.String()
|
||||
if instructionsText != "" {
|
||||
@@ -207,6 +210,8 @@ func ConvertOpenAIResponsesRequestToClaude(modelName string, inputRawJSON []byte
|
||||
}
|
||||
return true
|
||||
})
|
||||
} else if parts.Type == gjson.String {
|
||||
textAggregate.WriteString(parts.String())
|
||||
}
|
||||
|
||||
// Fallback to given role if content types not decisive
|
||||
|
||||
@@ -263,7 +263,6 @@ func (m *Manager) Execute(ctx context.Context, providers []string, req cliproxye
|
||||
return cliproxyexecutor.Response{}, &Error{Code: "provider_not_found", Message: "no provider supplied"}
|
||||
}
|
||||
rotated := m.rotateProviders(req.Model, normalized)
|
||||
defer m.advanceProviderCursor(req.Model, normalized)
|
||||
|
||||
retryTimes, maxWait := m.retrySettings()
|
||||
attempts := retryTimes + 1
|
||||
@@ -302,7 +301,6 @@ func (m *Manager) ExecuteCount(ctx context.Context, providers []string, req clip
|
||||
return cliproxyexecutor.Response{}, &Error{Code: "provider_not_found", Message: "no provider supplied"}
|
||||
}
|
||||
rotated := m.rotateProviders(req.Model, normalized)
|
||||
defer m.advanceProviderCursor(req.Model, normalized)
|
||||
|
||||
retryTimes, maxWait := m.retrySettings()
|
||||
attempts := retryTimes + 1
|
||||
@@ -341,7 +339,6 @@ func (m *Manager) ExecuteStream(ctx context.Context, providers []string, req cli
|
||||
return nil, &Error{Code: "provider_not_found", Message: "no provider supplied"}
|
||||
}
|
||||
rotated := m.rotateProviders(req.Model, normalized)
|
||||
defer m.advanceProviderCursor(req.Model, normalized)
|
||||
|
||||
retryTimes, maxWait := m.retrySettings()
|
||||
attempts := retryTimes + 1
|
||||
@@ -640,13 +637,20 @@ func (m *Manager) normalizeProviders(providers []string) []string {
|
||||
return result
|
||||
}
|
||||
|
||||
// rotateProviders returns a rotated view of the providers list starting from the
|
||||
// current offset for the model, and atomically increments the offset for the next call.
|
||||
// This ensures concurrent requests get different starting providers.
|
||||
func (m *Manager) rotateProviders(model string, providers []string) []string {
|
||||
if len(providers) == 0 {
|
||||
return nil
|
||||
}
|
||||
m.mu.RLock()
|
||||
|
||||
// Atomic read-and-increment: get current offset and advance cursor in one lock
|
||||
m.mu.Lock()
|
||||
offset := m.providerOffsets[model]
|
||||
m.mu.RUnlock()
|
||||
m.providerOffsets[model] = (offset + 1) % len(providers)
|
||||
m.mu.Unlock()
|
||||
|
||||
if len(providers) > 0 {
|
||||
offset %= len(providers)
|
||||
}
|
||||
@@ -662,19 +666,6 @@ func (m *Manager) rotateProviders(model string, providers []string) []string {
|
||||
return rotated
|
||||
}
|
||||
|
||||
func (m *Manager) advanceProviderCursor(model string, providers []string) {
|
||||
if len(providers) == 0 {
|
||||
m.mu.Lock()
|
||||
delete(m.providerOffsets, model)
|
||||
m.mu.Unlock()
|
||||
return
|
||||
}
|
||||
m.mu.Lock()
|
||||
current := m.providerOffsets[model]
|
||||
m.providerOffsets[model] = (current + 1) % len(providers)
|
||||
m.mu.Unlock()
|
||||
}
|
||||
|
||||
func (m *Manager) retrySettings() (int, time.Duration) {
|
||||
if m == nil {
|
||||
return 0, 0
|
||||
|
||||
Reference in New Issue
Block a user