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

feat(registry): unify Gemini models and add AI Studio set

Browse Source
This commit is contained in:
hkfires
2025-10-28 19:00:25 +08:00
parent 5891785125
commit 5dced4c0a6
5 changed files with 106 additions and 164 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
internal/api/server.go
View File

@@ -225,7 +225,7 @@ func NewServer(cfg *config.Config, authManager *auth.Manager, accessManager *sdk
envManagementSecret := envAdminPasswordSet && envAdminPassword != ""
// Create server instance
providerNames := make([]string, 0, len(cfg.OpenAICompatibility))
providerNames := make([]string, 0, len(cfg.OpenAICompatibility))
for _, p := range cfg.OpenAICompatibility {
providerNames = append(providerNames, p.Name)
}
@@ -914,5 +914,3 @@ func AuthMiddleware(manager *sdkaccess.Manager) gin.HandlerFunc {
}
}
}
// legacy clientsToSlice removed; handlers no longer consume legacy client slices

138
internal/registry/model_definitions.go
View File

@@ -68,84 +68,8 @@ func GetClaudeModels() []*ModelInfo {
}
}
// GetGeminiModels returns the standard Gemini model definitions
func GetGeminiModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gemini-2.5-flash",
Object: "model",
Created: time.Now().Unix(),
OwnedBy: "google",
Type: "gemini",
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"},
},
{
ID: "gemini-2.5-pro",
Object: "model",
Created: time.Now().Unix(),
OwnedBy: "google",
Type: "gemini",
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"},
},
{
ID: "gemini-2.5-flash-lite",
Object: "model",
Created: time.Now().Unix(),
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-lite",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Lite",
Description: "Stable release (June 17th, 2025) of Gemini 2.5 Flash Lite",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
},
{
ID: "gemini-2.5-flash-image-preview",
Object: "model",
Created: time.Now().Unix(),
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-image-preview",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Image Preview",
Description: "State-of-the-art image generation and editing model.",
InputTokenLimit: 1048576,
OutputTokenLimit: 8192,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
},
{
ID: "gemini-2.5-flash-image",
Object: "model",
Created: time.Now().Unix(),
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-2.5-flash-image",
Version: "2.5",
DisplayName: "Gemini 2.5 Flash Image",
Description: "State-of-the-art image generation and editing model.",
InputTokenLimit: 1048576,
OutputTokenLimit: 8192,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
},
}
}
// GetGeminiCLIModels returns the standard Gemini model definitions
func GetGeminiCLIModels() []*ModelInfo {
// GeminiModels returns the shared base Gemini model set used by multiple providers.
func GeminiModels() []*ModelInfo {
return []*ModelInfo{
{
ID: "gemini-2.5-flash",
@@ -220,6 +144,63 @@ func GetGeminiCLIModels() []*ModelInfo {
}
}
// GetGeminiModels returns the standard Gemini model definitions
func GetGeminiModels() []*ModelInfo { return GeminiModels() }
// GetGeminiCLIModels returns the standard Gemini model definitions
func GetGeminiCLIModels() []*ModelInfo { return GeminiModels() }
// GetAIStudioModels returns the Gemini model definitions for AI Studio integrations
func GetAIStudioModels() []*ModelInfo {
models := make([]*ModelInfo, 0, 8)
models = append(models, GeminiModels()...)
models = append(models,
&ModelInfo{
ID: "gemini-pro-latest",
Object: "model",
Created: time.Now().Unix(),
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-pro-latest",
Version: "2.5",
DisplayName: "Gemini Pro Latest",
Description: "Latest release of Gemini Pro",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
},
&ModelInfo{
ID: "gemini-flash-latest",
Object: "model",
Created: time.Now().Unix(),
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-flash-latest",
Version: "2.5",
DisplayName: "Gemini Flash Latest",
Description: "Latest release of Gemini Flash",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
},
&ModelInfo{
ID: "gemini-flash-lite-latest",
Object: "model",
Created: time.Now().Unix(),
OwnedBy: "google",
Type: "gemini",
Name: "models/gemini-flash-lite-latest",
Version: "2.5",
DisplayName: "Gemini Flash-Lite Latest",
Description: "Latest release of Gemini Flash-Lite",
InputTokenLimit: 1048576,
OutputTokenLimit: 65536,
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
},
)
return models
}
// GetOpenAIModels returns the standard OpenAI model definitions
func GetOpenAIModels() []*ModelInfo {
return []*ModelInfo{
@@ -417,7 +398,6 @@ func GetIFlowModels() []*ModelInfo {
{ID: "qwen3-vl-plus", DisplayName: "Qwen3-VL-Plus", Description: "Qwen3 multimodal vision-language"},
{ID: "qwen3-max-preview", DisplayName: "Qwen3-Max-Preview", Description: "Qwen3 Max preview build"},
{ID: "kimi-k2-0905", DisplayName: "Kimi-K2-Instruct-0905", Description: "Moonshot Kimi K2 instruct 0905"},
{ID: "glm-4.5", DisplayName: "GLM-4.5", Description: "Zhipu GLM 4.5 general model"},
{ID: "glm-4.6", DisplayName: "GLM-4.6", Description: "Zhipu GLM 4.6 general model"},
{ID: "kimi-k2", DisplayName: "Kimi-K2", Description: "Moonshot Kimi K2 general model"},
{ID: "deepseek-v3.2", DisplayName: "DeepSeek-V3.2-Exp", Description: "DeepSeek V3.2 experimental"},

40
internal/runtime/executor/aistudio_executor.go
View File

@@ -19,27 +19,27 @@ import (
"github.com/tidwall/sjson"
)
// AistudioExecutor routes AI Studio requests through a websocket-backed transport.
type AistudioExecutor struct {
// AIStudioExecutor routes AI Studio requests through a websocket-backed transport.
type AIStudioExecutor struct {
provider string
relay *wsrelay.Manager
cfg *config.Config
}
// NewAistudioExecutor constructs a websocket executor for the provider name.
func NewAistudioExecutor(cfg *config.Config, provider string, relay *wsrelay.Manager) *AistudioExecutor {
return &AistudioExecutor{provider: strings.ToLower(provider), relay: relay, cfg: cfg}
// NewAIStudioExecutor constructs a websocket executor for the provider name.
func NewAIStudioExecutor(cfg *config.Config, provider string, relay *wsrelay.Manager) *AIStudioExecutor {
return &AIStudioExecutor{provider: strings.ToLower(provider), relay: relay, cfg: cfg}
}
// Identifier returns the provider key served by this executor.
func (e *AistudioExecutor) Identifier() string { return e.provider }
// Identifier returns the logical provider key for routing.
func (e *AIStudioExecutor) Identifier() string { return "aistudio" }
// PrepareRequest is a no-op because websocket transport already injects headers.
func (e *AistudioExecutor) PrepareRequest(_ *http.Request, _ *cliproxyauth.Auth) error {
func (e *AIStudioExecutor) PrepareRequest(_ *http.Request, _ *cliproxyauth.Auth) error {
return nil
}
func (e *AistudioExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (resp cliproxyexecutor.Response, err error) {
func (e *AIStudioExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (resp cliproxyexecutor.Response, err error) {
reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
defer reporter.trackFailure(ctx, &err)
@@ -66,7 +66,7 @@ func (e *AistudioExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth,
Method: http.MethodPost,
Headers: wsReq.Headers.Clone(),
Body: bytes.Clone(body.payload),
Provider: e.provider,
Provider: e.Identifier(),
AuthID: authID,
AuthLabel: authLabel,
AuthType: authType,
@@ -92,7 +92,7 @@ func (e *AistudioExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth,
return resp, nil
}
func (e *AistudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (stream <-chan cliproxyexecutor.StreamChunk, err error) {
func (e *AIStudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (stream <-chan cliproxyexecutor.StreamChunk, err error) {
reporter := newUsageReporter(ctx, e.Identifier(), req.Model, auth)
defer reporter.trackFailure(ctx, &err)
@@ -118,7 +118,7 @@ func (e *AistudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth
Method: http.MethodPost,
Headers: wsReq.Headers.Clone(),
Body: bytes.Clone(body.payload),
Provider: e.provider,
Provider: e.Identifier(),
AuthID: authID,
AuthLabel: authLabel,
AuthType: authType,
@@ -151,7 +151,7 @@ func (e *AistudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth
case wsrelay.MessageTypeStreamChunk:
if len(event.Payload) > 0 {
appendAPIResponseChunk(ctx, e.cfg, bytes.Clone(event.Payload))
filtered := filterAistudioUsageMetadata(event.Payload)
filtered := filterAIStudioUsageMetadata(event.Payload)
if detail, ok := parseGeminiStreamUsage(filtered); ok {
reporter.publish(ctx, detail)
}
@@ -188,7 +188,7 @@ func (e *AistudioExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth
return stream, nil
}
func (e *AistudioExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
func (e *AIStudioExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Auth, req cliproxyexecutor.Request, opts cliproxyexecutor.Options) (cliproxyexecutor.Response, error) {
_, body, err := e.translateRequest(req, opts, false)
if err != nil {
return cliproxyexecutor.Response{}, err
@@ -215,7 +215,7 @@ func (e *AistudioExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.A
Method: http.MethodPost,
Headers: wsReq.Headers.Clone(),
Body: bytes.Clone(body.payload),
Provider: e.provider,
Provider: e.Identifier(),
AuthID: authID,
AuthLabel: authLabel,
AuthType: authType,
@@ -241,7 +241,7 @@ func (e *AistudioExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.A
return cliproxyexecutor.Response{Payload: []byte(translated)}, nil
}
func (e *AistudioExecutor) Refresh(ctx context.Context, auth *cliproxyauth.Auth) (*cliproxyauth.Auth, error) {
func (e *AIStudioExecutor) Refresh(ctx context.Context, auth *cliproxyauth.Auth) (*cliproxyauth.Auth, error) {
_ = ctx
return auth, nil
}
@@ -252,7 +252,7 @@ type translatedPayload struct {
toFormat sdktranslator.Format
}
func (e *AistudioExecutor) translateRequest(req cliproxyexecutor.Request, opts cliproxyexecutor.Options, stream bool) ([]byte, translatedPayload, error) {
func (e *AIStudioExecutor) translateRequest(req cliproxyexecutor.Request, opts cliproxyexecutor.Options, stream bool) ([]byte, translatedPayload, error) {
from := opts.SourceFormat
to := sdktranslator.FromString("gemini")
payload := sdktranslator.TranslateRequest(from, to, req.Model, bytes.Clone(req.Payload), stream)
@@ -275,7 +275,7 @@ func (e *AistudioExecutor) translateRequest(req cliproxyexecutor.Request, opts c
return payload, translatedPayload{payload: payload, action: action, toFormat: to}, nil
}
func (e *AistudioExecutor) buildEndpoint(model, action, alt string) string {
func (e *AIStudioExecutor) buildEndpoint(model, action, alt string) string {
base := fmt.Sprintf("%s/%s/models/%s:%s", glEndpoint, glAPIVersion, model, action)
if action == "streamGenerateContent" {
if alt == "" {
@@ -289,9 +289,9 @@ func (e *AistudioExecutor) buildEndpoint(model, action, alt string) string {
return base
}
// filterAistudioUsageMetadata removes usageMetadata from intermediate SSE events so that
// filterAIStudioUsageMetadata removes usageMetadata from intermediate SSE events so that
// only the terminal chunk retains token statistics.
func filterAistudioUsageMetadata(payload []byte) []byte {
func filterAIStudioUsageMetadata(payload []byte) []byte {
if len(payload) == 0 {
return payload
}