Compare commits
6 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
c8cee547fd | ||
|
|
36755421fe | ||
|
|
6c17dbc4da | ||
|
|
ee6429cc75 | ||
|
|
a4a26d978e | ||
|
|
ed9f6e897e |
@@ -181,5 +181,3 @@ func (m *AmpModule) OnConfigUpdated(cfg *config.Config) error {
|
||||
log.Debug("Amp config updated (restart required for URL changes)")
|
||||
return nil
|
||||
}
|
||||
|
||||
|
||||
|
||||
@@ -83,7 +83,7 @@ func createReverseProxy(upstreamURL string, secretSource SecretSource) (*httputi
|
||||
// Peek at first 2 bytes to detect gzip magic bytes
|
||||
header := make([]byte, 2)
|
||||
n, _ := io.ReadFull(originalBody, header)
|
||||
|
||||
|
||||
// Check for gzip magic bytes (0x1f 0x8b)
|
||||
// If n < 2, we didn't get enough bytes, so it's not gzip
|
||||
if n >= 2 && header[0] == 0x1f && header[1] == 0x8b {
|
||||
@@ -97,7 +97,7 @@ func createReverseProxy(upstreamURL string, secretSource SecretSource) (*httputi
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
|
||||
// Reconstruct complete gzipped data
|
||||
gzippedData := append(header[:n], rest...)
|
||||
|
||||
@@ -129,8 +129,8 @@ func createReverseProxy(upstreamURL string, secretSource SecretSource) (*httputi
|
||||
resp.ContentLength = int64(len(decompressed))
|
||||
|
||||
// Update headers to reflect decompressed state
|
||||
resp.Header.Del("Content-Encoding") // No longer compressed
|
||||
resp.Header.Del("Content-Length") // Remove stale compressed length
|
||||
resp.Header.Del("Content-Encoding") // No longer compressed
|
||||
resp.Header.Del("Content-Length") // Remove stale compressed length
|
||||
resp.Header.Set("Content-Length", strconv.FormatInt(resp.ContentLength, 10)) // Set decompressed length
|
||||
|
||||
log.Debugf("amp proxy: decompressed gzip response (%d -> %d bytes)", len(gzippedData), len(decompressed))
|
||||
|
||||
@@ -440,52 +440,52 @@ func TestIsStreamingResponse(t *testing.T) {
|
||||
|
||||
func TestFilterBetaFeatures(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
header string
|
||||
name string
|
||||
header string
|
||||
featureToRemove string
|
||||
expected string
|
||||
expected string
|
||||
}{
|
||||
{
|
||||
name: "Remove context-1m from middle",
|
||||
header: "fine-grained-tool-streaming-2025-05-14,context-1m-2025-08-07,oauth-2025-04-20",
|
||||
name: "Remove context-1m from middle",
|
||||
header: "fine-grained-tool-streaming-2025-05-14,context-1m-2025-08-07,oauth-2025-04-20",
|
||||
featureToRemove: "context-1m-2025-08-07",
|
||||
expected: "fine-grained-tool-streaming-2025-05-14,oauth-2025-04-20",
|
||||
expected: "fine-grained-tool-streaming-2025-05-14,oauth-2025-04-20",
|
||||
},
|
||||
{
|
||||
name: "Remove context-1m from start",
|
||||
header: "context-1m-2025-08-07,fine-grained-tool-streaming-2025-05-14",
|
||||
name: "Remove context-1m from start",
|
||||
header: "context-1m-2025-08-07,fine-grained-tool-streaming-2025-05-14",
|
||||
featureToRemove: "context-1m-2025-08-07",
|
||||
expected: "fine-grained-tool-streaming-2025-05-14",
|
||||
expected: "fine-grained-tool-streaming-2025-05-14",
|
||||
},
|
||||
{
|
||||
name: "Remove context-1m from end",
|
||||
header: "fine-grained-tool-streaming-2025-05-14,context-1m-2025-08-07",
|
||||
name: "Remove context-1m from end",
|
||||
header: "fine-grained-tool-streaming-2025-05-14,context-1m-2025-08-07",
|
||||
featureToRemove: "context-1m-2025-08-07",
|
||||
expected: "fine-grained-tool-streaming-2025-05-14",
|
||||
expected: "fine-grained-tool-streaming-2025-05-14",
|
||||
},
|
||||
{
|
||||
name: "Feature not present",
|
||||
header: "fine-grained-tool-streaming-2025-05-14,oauth-2025-04-20",
|
||||
name: "Feature not present",
|
||||
header: "fine-grained-tool-streaming-2025-05-14,oauth-2025-04-20",
|
||||
featureToRemove: "context-1m-2025-08-07",
|
||||
expected: "fine-grained-tool-streaming-2025-05-14,oauth-2025-04-20",
|
||||
expected: "fine-grained-tool-streaming-2025-05-14,oauth-2025-04-20",
|
||||
},
|
||||
{
|
||||
name: "Only feature to remove",
|
||||
header: "context-1m-2025-08-07",
|
||||
name: "Only feature to remove",
|
||||
header: "context-1m-2025-08-07",
|
||||
featureToRemove: "context-1m-2025-08-07",
|
||||
expected: "",
|
||||
expected: "",
|
||||
},
|
||||
{
|
||||
name: "Empty header",
|
||||
header: "",
|
||||
name: "Empty header",
|
||||
header: "",
|
||||
featureToRemove: "context-1m-2025-08-07",
|
||||
expected: "",
|
||||
expected: "",
|
||||
},
|
||||
{
|
||||
name: "Header with spaces",
|
||||
header: "fine-grained-tool-streaming-2025-05-14, context-1m-2025-08-07 , oauth-2025-04-20",
|
||||
name: "Header with spaces",
|
||||
header: "fine-grained-tool-streaming-2025-05-14, context-1m-2025-08-07 , oauth-2025-04-20",
|
||||
featureToRemove: "context-1m-2025-08-07",
|
||||
expected: "fine-grained-tool-streaming-2025-05-14,oauth-2025-04-20",
|
||||
expected: "fine-grained-tool-streaming-2025-05-14,oauth-2025-04-20",
|
||||
},
|
||||
}
|
||||
|
||||
|
||||
@@ -6,11 +6,11 @@ import (
|
||||
"strings"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
|
||||
"github.com/router-for-me/CLIProxyAPI/v6/sdk/api/handlers"
|
||||
"github.com/router-for-me/CLIProxyAPI/v6/sdk/api/handlers/claude"
|
||||
"github.com/router-for-me/CLIProxyAPI/v6/sdk/api/handlers/gemini"
|
||||
"github.com/router-for-me/CLIProxyAPI/v6/sdk/api/handlers/openai"
|
||||
"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
|
||||
log "github.com/sirupsen/logrus"
|
||||
)
|
||||
|
||||
|
||||
@@ -32,15 +32,6 @@ func GetClaudeModels() []*ModelInfo {
|
||||
DisplayName: "Claude 4.5 Sonnet Thinking",
|
||||
Thinking: &ThinkingSupport{Min: 1024, Max: 100000, ZeroAllowed: false, DynamicAllowed: true},
|
||||
},
|
||||
{
|
||||
ID: "gemini-claude-sonnet-4-5-thinking",
|
||||
Object: "model",
|
||||
Created: 1759104000, // 2025-09-29
|
||||
OwnedBy: "anthropic",
|
||||
Type: "claude",
|
||||
DisplayName: "Gemini Claude 4.5 Sonnet Thinking",
|
||||
Thinking: &ThinkingSupport{Min: 1024, Max: 100000, ZeroAllowed: false, DynamicAllowed: true},
|
||||
},
|
||||
{
|
||||
ID: "claude-opus-4-5-thinking",
|
||||
Object: "model",
|
||||
@@ -194,6 +185,20 @@ func GetGeminiModels() []*ModelInfo {
|
||||
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
|
||||
Thinking: &ThinkingSupport{Min: 128, Max: 32768, ZeroAllowed: false, DynamicAllowed: true},
|
||||
},
|
||||
{
|
||||
ID: "gemini-3-pro-image-preview",
|
||||
Object: "model",
|
||||
Created: 1737158400,
|
||||
OwnedBy: "google",
|
||||
Type: "gemini",
|
||||
Name: "models/gemini-3-pro-image-preview",
|
||||
Version: "3.0",
|
||||
DisplayName: "Gemini 3 Pro Image Preview",
|
||||
Description: "Gemini 3 Pro Image Preview",
|
||||
InputTokenLimit: 1048576,
|
||||
OutputTokenLimit: 65536,
|
||||
SupportedGenerationMethods: []string{"generateContent", "countTokens", "createCachedContent", "batchGenerateContent"},
|
||||
},
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
@@ -826,7 +826,6 @@ func (r *ModelRegistry) CleanupExpiredQuotas() {
|
||||
}
|
||||
}
|
||||
|
||||
|
||||
// GetFirstAvailableModel returns the first available model for the given handler type.
|
||||
// It prioritizes models by their creation timestamp (newest first) and checks if they have
|
||||
// available clients that are not suspended or over quota.
|
||||
|
||||
@@ -62,7 +62,7 @@ func (e *ClaudeExecutor) Execute(ctx context.Context, auth *cliproxyauth.Auth, r
|
||||
body = e.injectThinkingConfig(req.Model, body)
|
||||
|
||||
if !strings.HasPrefix(modelForUpstream, "claude-3-5-haiku") {
|
||||
// body, _ = sjson.SetRawBytes(body, "system", []byte(misc.ClaudeCodeInstructions))
|
||||
body = checkSystemInstructions(body)
|
||||
}
|
||||
body = applyPayloadConfig(e.cfg, req.Model, body)
|
||||
|
||||
@@ -162,7 +162,7 @@ func (e *ClaudeExecutor) ExecuteStream(ctx context.Context, auth *cliproxyauth.A
|
||||
}
|
||||
// Inject thinking config based on model suffix for thinking variants
|
||||
body = e.injectThinkingConfig(req.Model, body)
|
||||
// body, _ = sjson.SetRawBytes(body, "system", []byte(misc.ClaudeCodeInstructions))
|
||||
body = checkSystemInstructions(body)
|
||||
body = applyPayloadConfig(e.cfg, req.Model, body)
|
||||
|
||||
// Extract betas from body and convert to header
|
||||
@@ -295,7 +295,7 @@ func (e *ClaudeExecutor) CountTokens(ctx context.Context, auth *cliproxyauth.Aut
|
||||
}
|
||||
|
||||
if !strings.HasPrefix(modelForUpstream, "claude-3-5-haiku") {
|
||||
// body, _ = sjson.SetRawBytes(body, "system", []byte(misc.ClaudeCodeInstructions))
|
||||
body = checkSystemInstructions(body)
|
||||
}
|
||||
|
||||
// Extract betas from body and convert to header (for count_tokens too)
|
||||
@@ -676,3 +676,22 @@ func claudeCreds(a *cliproxyauth.Auth) (apiKey, baseURL string) {
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
func checkSystemInstructions(payload []byte) []byte {
|
||||
system := gjson.GetBytes(payload, "system")
|
||||
claudeCodeInstructions := `[{"type":"text","text":"You are Claude Code, Anthropic's official CLI for Claude."}]`
|
||||
if system.IsArray() {
|
||||
if gjson.GetBytes(payload, "system.0.text").String() != "You are Claude Code, Anthropic's official CLI for Claude." {
|
||||
system.ForEach(func(_, part gjson.Result) bool {
|
||||
if part.Get("type").String() == "text" {
|
||||
claudeCodeInstructions, _ = sjson.SetRaw(claudeCodeInstructions, "-1", part.Raw)
|
||||
}
|
||||
return true
|
||||
})
|
||||
payload, _ = sjson.SetRawBytes(payload, "system", []byte(claudeCodeInstructions))
|
||||
}
|
||||
} else {
|
||||
payload, _ = sjson.SetRawBytes(payload, "system", []byte(claudeCodeInstructions))
|
||||
}
|
||||
return payload
|
||||
}
|
||||
|
||||
@@ -105,14 +105,19 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
|
||||
partTextResult := partResult.Get("text")
|
||||
functionCallResult := partResult.Get("functionCall")
|
||||
thoughtSignatureResult := partResult.Get("thoughtSignature")
|
||||
if !thoughtSignatureResult.Exists() {
|
||||
thoughtSignatureResult = partResult.Get("thought_signature")
|
||||
}
|
||||
inlineDataResult := partResult.Get("inlineData")
|
||||
if !inlineDataResult.Exists() {
|
||||
inlineDataResult = partResult.Get("inline_data")
|
||||
}
|
||||
|
||||
// Handle thoughtSignature - this is encrypted reasoning content that should not be exposed to the client
|
||||
if thoughtSignatureResult.Exists() && thoughtSignatureResult.String() != "" {
|
||||
// Skip thoughtSignature processing - it's internal encrypted data
|
||||
hasThoughtSignature := thoughtSignatureResult.Exists() && thoughtSignatureResult.String() != ""
|
||||
hasContentPayload := partTextResult.Exists() || functionCallResult.Exists() || inlineDataResult.Exists()
|
||||
|
||||
// Ignore encrypted thoughtSignature but keep any actual content in the same part.
|
||||
if hasThoughtSignature && !hasContentPayload {
|
||||
continue
|
||||
}
|
||||
|
||||
|
||||
@@ -105,14 +105,19 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
|
||||
partTextResult := partResult.Get("text")
|
||||
functionCallResult := partResult.Get("functionCall")
|
||||
thoughtSignatureResult := partResult.Get("thoughtSignature")
|
||||
if !thoughtSignatureResult.Exists() {
|
||||
thoughtSignatureResult = partResult.Get("thought_signature")
|
||||
}
|
||||
inlineDataResult := partResult.Get("inlineData")
|
||||
if !inlineDataResult.Exists() {
|
||||
inlineDataResult = partResult.Get("inline_data")
|
||||
}
|
||||
|
||||
// Handle thoughtSignature - this is encrypted reasoning content that should not be exposed to the client
|
||||
if thoughtSignatureResult.Exists() && thoughtSignatureResult.String() != "" {
|
||||
// Skip thoughtSignature processing - it's internal encrypted data
|
||||
hasThoughtSignature := thoughtSignatureResult.Exists() && thoughtSignatureResult.String() != ""
|
||||
hasContentPayload := partTextResult.Exists() || functionCallResult.Exists() || inlineDataResult.Exists()
|
||||
|
||||
// Ignore encrypted thoughtSignature but keep any actual content in the same part.
|
||||
if hasThoughtSignature && !hasContentPayload {
|
||||
continue
|
||||
}
|
||||
|
||||
|
||||
@@ -116,8 +116,11 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
|
||||
thoughtSignatureResult = partResult.Get("thought_signature")
|
||||
}
|
||||
|
||||
// Skip thoughtSignature parts (encrypted reasoning not exposed downstream).
|
||||
if thoughtSignatureResult.Exists() && thoughtSignatureResult.String() != "" {
|
||||
hasThoughtSignature := thoughtSignatureResult.Exists() && thoughtSignatureResult.String() != ""
|
||||
hasContentPayload := partTextResult.Exists() || functionCallResult.Exists() || inlineDataResult.Exists()
|
||||
|
||||
// Skip pure thoughtSignature parts but keep any actual payload in the same part.
|
||||
if hasThoughtSignature && !hasContentPayload {
|
||||
continue
|
||||
}
|
||||
|
||||
|
||||
@@ -69,6 +69,27 @@ func (h *GeminiAPIHandler) GeminiGetHandler(c *gin.Context) {
|
||||
return
|
||||
}
|
||||
switch request.Action {
|
||||
case "gemini-3-pro-preview":
|
||||
c.JSON(http.StatusOK, gin.H{
|
||||
"name": "models/gemini-3-pro-preview",
|
||||
"version": "3",
|
||||
"displayName": "Gemini 3 Pro Preview",
|
||||
"description": "Gemini 3 Pro Preview",
|
||||
"inputTokenLimit": 1048576,
|
||||
"outputTokenLimit": 65536,
|
||||
"supportedGenerationMethods": []string{
|
||||
"generateContent",
|
||||
"countTokens",
|
||||
"createCachedContent",
|
||||
"batchGenerateContent",
|
||||
},
|
||||
"temperature": 1,
|
||||
"topP": 0.95,
|
||||
"topK": 64,
|
||||
"maxTemperature": 2,
|
||||
"thinking": true,
|
||||
},
|
||||
)
|
||||
case "gemini-2.5-pro":
|
||||
c.JSON(http.StatusOK, gin.H{
|
||||
"name": "models/gemini-2.5-pro",
|
||||
|
||||
Reference in New Issue
Block a user