airkjw/CLIProxyAPI
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Improved the /v1/models endpoint
Some checks failed
docker-image / docker (push) Has been cancelled
Details
goreleaser / goreleaser (push) Has been cancelled
Details

Browse Source
This commit is contained in:
Luis Pater
2025-08-27 20:30:17 +08:00
parent ed8873fbb0
commit dff31a7a4c
13 changed files with 757 additions and 136 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
internal/api/handlers/claude/code_handlers.go
View File

@@ -16,6 +16,7 @@ import (
"github.com/luispater/CLIProxyAPI/internal/api/handlers"
. "github.com/luispater/CLIProxyAPI/internal/constant"
"github.com/luispater/CLIProxyAPI/internal/interfaces"
"github.com/luispater/CLIProxyAPI/internal/registry"
log "github.com/sirupsen/logrus"
"github.com/tidwall/gjson"
)
@@ -47,7 +48,9 @@ func (h *ClaudeCodeAPIHandler) HandlerType() string {
// Models returns a list of models supported by this handler.
func (h *ClaudeCodeAPIHandler) Models() []map[string]any {
return make([]map[string]any, 0)
// Get dynamic models from the global registry
modelRegistry := registry.GetGlobalRegistry()
return modelRegistry.GetAvailableModels("claude")
}
// ClaudeMessages handles Claude-compatible streaming chat completions.
@@ -79,6 +82,17 @@ func (h *ClaudeCodeAPIHandler) ClaudeMessages(c *gin.Context) {
h.handleStreamingResponse(c, rawJSON)
}
// ClaudeModels handles the Claude models listing endpoint.
// It returns a JSON response containing available Claude models and their specifications.
//
// Parameters:
// - c: The Gin context for the request.
func (h *ClaudeCodeAPIHandler) ClaudeModels(c *gin.Context) {
c.JSON(http.StatusOK, gin.H{
"data": h.Models(),
})
}
// handleStreamingResponse streams Claude-compatible responses backed by Gemini.
// It sets up SSE, selects a backend client with rotation/quota logic,
// forwards chunks, and translates them to Claude CLI format.

60
internal/api/handlers/gemini/gemini_handlers.go
View File

@@ -16,6 +16,7 @@ import (
"github.com/luispater/CLIProxyAPI/internal/api/handlers"
. "github.com/luispater/CLIProxyAPI/internal/constant"
"github.com/luispater/CLIProxyAPI/internal/interfaces"
"github.com/luispater/CLIProxyAPI/internal/registry"
log "github.com/sirupsen/logrus"
)
@@ -40,62 +41,9 @@ func (h *GeminiAPIHandler) HandlerType() string {
// Models returns the Gemini-compatible model metadata supported by this handler.
func (h *GeminiAPIHandler) Models() []map[string]any {
return []map[string]any{
{
"name": "models/gemini-2.5-flash",
"version": "001",
"displayName": "Gemini 2.5 Flash",
"description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": []string{
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent",
},
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2,
"thinking": true,
},
{
"name": "models/gemini-2.5-pro",
"version": "2.5",
"displayName": "Gemini 2.5 Pro",
"description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
"inputTokenLimit": 1048576,
"outputTokenLimit": 65536,
"supportedGenerationMethods": []string{
"generateContent",
"countTokens",
"createCachedContent",
"batchGenerateContent",
},
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2,
"thinking": true,
},
{
"name": "gpt-5",
"version": "001",
"displayName": "GPT 5",
"description": "Stable version of GPT 5, The best model for coding and agentic tasks across domains.",
"inputTokenLimit": 400000,
"outputTokenLimit": 128000,
"supportedGenerationMethods": []string{
"generateContent",
},
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2,
"thinking": true,
},
}
// Get dynamic models from the global registry
modelRegistry := registry.GetGlobalRegistry()
return modelRegistry.GetAvailableModels("gemini")
}
// GeminiModels handles the Gemini models listing endpoint.

85
internal/api/handlers/openai/openai_handlers.go
View File

@@ -16,6 +16,7 @@ import (
"github.com/luispater/CLIProxyAPI/internal/api/handlers"
. "github.com/luispater/CLIProxyAPI/internal/constant"
"github.com/luispater/CLIProxyAPI/internal/interfaces"
"github.com/luispater/CLIProxyAPI/internal/registry"
log "github.com/sirupsen/logrus"
"github.com/tidwall/gjson"
)
@@ -47,90 +48,18 @@ func (h *OpenAIAPIHandler) HandlerType() string {
// Models returns the OpenAI-compatible model metadata supported by this handler.
func (h *OpenAIAPIHandler) Models() []map[string]any {
return []map[string]any{
{
"id": "gemini-2.5-pro",
"object": "model",
"version": "2.5",
"name": "Gemini 2.5 Pro",
"description": "Stable release (June 17th, 2025) of Gemini 2.5 Pro",
"context_length": 1_048_576,
"max_completion_tokens": 65_536,
"supported_parameters": []string{
"tools",
"temperature",
"top_p",
"top_k",
},
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2,
"thinking": true,
},
{
"id": "gemini-2.5-flash",
"object": "model",
"version": "001",
"name": "Gemini 2.5 Flash",
"description": "Stable version of Gemini 2.5 Flash, our mid-size multimodal model that supports up to 1 million tokens, released in June of 2025.",
"context_length": 1_048_576,
"max_completion_tokens": 65_536,
"supported_parameters": []string{
"tools",
"temperature",
"top_p",
"top_k",
},
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2,
"thinking": true,
},
{
"id": "gpt-5",
"object": "model",
"version": "gpt-5-2025-08-07",
"name": "GPT 5",
"description": "Stable version of GPT 5, The best model for coding and agentic tasks across domains.",
"context_length": 400_000,
"max_completion_tokens": 128_000,
"supported_parameters": []string{
"tools",
},
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2,
"thinking": true,
},
{
"id": "claude-opus-4-1-20250805",
"object": "model",
"version": "claude-opus-4-1-20250805",
"name": "Claude Opus 4.1",
"description": "Anthropic's most capable model.",
"context_length": 200_000,
"max_completion_tokens": 32_000,
"supported_parameters": []string{
"tools",
},
"temperature": 1,
"topP": 0.95,
"topK": 64,
"maxTemperature": 2,
"thinking": true,
},
}
// Get dynamic models from the global registry
modelRegistry := registry.GetGlobalRegistry()
return modelRegistry.GetAvailableModels("openai")
}
// OpenAIModels handles the /v1/models endpoint.
// It returns a hardcoded list of available AI models with their capabilities
// It returns a list of available AI models with their capabilities
// and specifications in OpenAI-compatible format.
func (h *OpenAIAPIHandler) OpenAIModels(c *gin.Context) {
c.JSON(http.StatusOK, gin.H{
"data": h.Models(),
"object": "list",
"data": h.Models(),
})
}

21
internal/api/server.go
View File

@@ -102,7 +102,7 @@ func (s *Server) setupRoutes() {
v1 := s.engine.Group("/v1")
v1.Use(AuthMiddleware(s.cfg))
{
v1.GET("/models", openaiHandlers.OpenAIModels)
v1.GET("/models", s.unifiedModelsHandler(openaiHandlers, claudeCodeHandlers))
v1.POST("/chat/completions", openaiHandlers.ChatCompletions)
v1.POST("/messages", claudeCodeHandlers.ClaudeMessages)
}
@@ -130,6 +130,25 @@ func (s *Server) setupRoutes() {
s.engine.POST("/v1internal:method", geminiCLIHandlers.CLIHandler)
}
// unifiedModelsHandler creates a unified handler for the /v1/models endpoint
// that routes to different handlers based on the User-Agent header.
// If User-Agent starts with "claude-cli", it routes to Claude handler,
// otherwise it routes to OpenAI handler.
func (s *Server) unifiedModelsHandler(openaiHandler *openai.OpenAIAPIHandler, claudeHandler *claude.ClaudeCodeAPIHandler) gin.HandlerFunc {
return func(c *gin.Context) {
userAgent := c.GetHeader("User-Agent")
// Route to Claude handler if User-Agent starts with "claude-cli"
if strings.HasPrefix(userAgent, "claude-cli") {
log.Debugf("Routing /v1/models to Claude handler for User-Agent: %s", userAgent)
claudeHandler.ClaudeModels(c)
} else {
log.Debugf("Routing /v1/models to OpenAI handler for User-Agent: %s", userAgent)
openaiHandler.OpenAIModels(c)
}
}
}
// Start begins listening for and serving HTTP requests.
// It's a blocking call and will only return on an unrecoverable error.
//