Merge branch 'router-for-me:main' into main

refactor(translator): normalize finish reason casing across all OpenAI response handlers

README.md

@@ -10,7 +10,7 @@ The Plus release stays in lockstep with the mainline features.
 
 ## Differences from the Mainline
 
-- Added GitHub Copilot support (OAuth login), provided by [em4gp](https://github.com/em4go/CLIProxyAPI/tree/feature/github-copilot-auth)
+- Added GitHub Copilot support (OAuth login), provided by [em4go](https://github.com/em4go/CLIProxyAPI/tree/feature/github-copilot-auth)
 - Added Kiro (AWS CodeWhisperer) support (OAuth login), provided by [fuko2935](https://github.com/fuko2935/CLIProxyAPI/tree/feature/kiro-integration)
 
 ## Contributing

README_CN.md

@@ -10,7 +10,7 @@
 
 ## 与主线版本版本差异
 
-- 新增 GitHub Copilot 支持（OAuth 登录），由[em4gp](https://github.com/em4go/CLIProxyAPI/tree/feature/github-copilot-auth)提供
+- 新增 GitHub Copilot 支持（OAuth 登录），由[em4go](https://github.com/em4go/CLIProxyAPI/tree/feature/github-copilot-auth)提供
 - 新增 Kiro (AWS CodeWhisperer) 支持 (OAuth 登录), 由[fuko2935](https://github.com/fuko2935/CLIProxyAPI/tree/feature/kiro-integration)提供
 
 ## 贡献

internal/api/modules/amp/fallback_handlers.go

@@ -2,7 +2,6 @@ package amp
 
 import (
 	"bytes"
-	"encoding/json"
 	"io"
 	"net/http/httputil"
 	"strings"
@@ -11,6 +10,8 @@ import (
 	"github.com/gin-gonic/gin"
 	"github.com/router-for-me/CLIProxyAPI/v6/internal/util"
 	log "github.com/sirupsen/logrus"
+	"github.com/tidwall/gjson"
+	"github.com/tidwall/sjson"
 )
 
 // AmpRouteType represents the type of routing decision made for an Amp request
@@ -138,7 +139,7 @@ func (fh *FallbackHandler) WrapHandler(handler gin.HandlerFunc) gin.HandlerFunc
 			if fh.modelMapper != nil {
 				if mappedModel := fh.modelMapper.MapModel(normalizedModel); mappedModel != "" {
 					// Mapping found - rewrite the model in request body
-					bodyBytes = rewriteModelInBody(bodyBytes, mappedModel)
+					bodyBytes = rewriteModelInRequest(bodyBytes, mappedModel)
 					c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
 					resolvedModel = mappedModel
 					usedMapping = true
@@ -179,59 +180,62 @@ func (fh *FallbackHandler) WrapHandler(handler gin.HandlerFunc) gin.HandlerFunc
 
 		if usedMapping {
 			// Log: Model was mapped to another model
+			log.Debugf("amp model mapping: request %s -> %s", normalizedModel, resolvedModel)
 			logAmpRouting(RouteTypeModelMapping, modelName, resolvedModel, providerName, requestPath)
+			rewriter := NewResponseRewriter(c.Writer, normalizedModel)
+			c.Writer = rewriter
+			// Filter Anthropic-Beta header only for local handling paths
+			filterAntropicBetaHeader(c)
+			c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
+			handler(c)
+			rewriter.Flush()
+			log.Debugf("amp model mapping: response %s -> %s", resolvedModel, normalizedModel)
 		} else if len(providers) > 0 {
 			// Log: Using local provider (free)
 			logAmpRouting(RouteTypeLocalProvider, modelName, resolvedModel, providerName, requestPath)
+			// Filter Anthropic-Beta header only for local handling paths
+			filterAntropicBetaHeader(c)
+			c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
+			handler(c)
+		} else {
+			// No provider, no mapping, no proxy: fall back to the wrapped handler so it can return an error response
+			c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
+			handler(c)
 		}
-
-		// Providers available or no proxy for fallback, restore body and use normal handler
-		// Filter Anthropic-Beta header to remove features requiring special subscription
-		// This is needed when using local providers (bypassing the Amp proxy)
-		if betaHeader := c.Request.Header.Get("Anthropic-Beta"); betaHeader != "" {
-			filtered := filterBetaFeatures(betaHeader, "context-1m-2025-08-07")
-			if filtered != "" {
-				c.Request.Header.Set("Anthropic-Beta", filtered)
-			} else {
-				c.Request.Header.Del("Anthropic-Beta")
-			}
-		}
-
-		c.Request.Body = io.NopCloser(bytes.NewReader(bodyBytes))
-		handler(c)
 	}
 }
 
-// rewriteModelInBody replaces the model name in a JSON request body
-func rewriteModelInBody(body []byte, newModel string) []byte {
-	var payload map[string]interface{}
-	if err := json.Unmarshal(body, &payload); err != nil {
-		log.Warnf("amp model mapping: failed to parse body for rewrite: %v", err)
+// filterAntropicBetaHeader filters Anthropic-Beta header to remove features requiring special subscription
+// This is needed when using local providers (bypassing the Amp proxy)
+func filterAntropicBetaHeader(c *gin.Context) {
+	if betaHeader := c.Request.Header.Get("Anthropic-Beta"); betaHeader != "" {
+		if filtered := filterBetaFeatures(betaHeader, "context-1m-2025-08-07"); filtered != "" {
+			c.Request.Header.Set("Anthropic-Beta", filtered)
+		} else {
+			c.Request.Header.Del("Anthropic-Beta")
+		}
+	}
+}
+
+// rewriteModelInRequest replaces the model name in a JSON request body
+func rewriteModelInRequest(body []byte, newModel string) []byte {
+	if !gjson.GetBytes(body, "model").Exists() {
 		return body
 	}
-
-	if _, exists := payload["model"]; exists {
-		payload["model"] = newModel
-		newBody, err := json.Marshal(payload)
-		if err != nil {
-			log.Warnf("amp model mapping: failed to marshal rewritten body: %v", err)
-			return body
-		}
-		return newBody
+	result, err := sjson.SetBytes(body, "model", newModel)
+	if err != nil {
+		log.Warnf("amp model mapping: failed to rewrite model in request body: %v", err)
+		return body
 	}
-
-	return body
+	return result
 }
 
 // extractModelFromRequest attempts to extract the model name from various request formats
 func extractModelFromRequest(body []byte, c *gin.Context) string {
 	// First try to parse from JSON body (OpenAI, Claude, etc.)
-	var payload map[string]interface{}
-	if err := json.Unmarshal(body, &payload); err == nil {
-		// Check common model field names
-		if model, ok := payload["model"].(string); ok {
-			return model
-		}
+	// Check common model field names
+	if result := gjson.GetBytes(body, "model"); result.Exists() && result.Type == gjson.String {
+		return result.String()
 	}
 
 	// For Gemini requests, model is in the URL path

internal/api/modules/amp/model_mapping.go

@@ -66,7 +66,6 @@ func (m *DefaultModelMapper) MapModel(requestedModel string) string {
 	}
 
 	// Note: Detailed routing log is handled by logAmpRouting in fallback_handlers.go
-	log.Debugf("amp model mapping: resolved %s -> %s", requestedModel, targetModel)
 	return targetModel
 }
 

internal/api/modules/amp/response_rewriter.go

@@ -0,0 +1,98 @@
+package amp
+
+import (
+	"bytes"
+	"net/http"
+	"strings"
+
+	"github.com/gin-gonic/gin"
+	log "github.com/sirupsen/logrus"
+	"github.com/tidwall/gjson"
+	"github.com/tidwall/sjson"
+)
+
+// ResponseRewriter wraps a gin.ResponseWriter to intercept and modify the response body
+// It's used to rewrite model names in responses when model mapping is used
+type ResponseRewriter struct {
+	gin.ResponseWriter
+	body          *bytes.Buffer
+	originalModel string
+	isStreaming   bool
+}
+
+// NewResponseRewriter creates a new response rewriter for model name substitution
+func NewResponseRewriter(w gin.ResponseWriter, originalModel string) *ResponseRewriter {
+	return &ResponseRewriter{
+		ResponseWriter: w,
+		body:           &bytes.Buffer{},
+		originalModel:  originalModel,
+	}
+}
+
+// Write intercepts response writes and buffers them for model name replacement
+func (rw *ResponseRewriter) Write(data []byte) (int, error) {
+	// Detect streaming on first write
+	if rw.body.Len() == 0 && !rw.isStreaming {
+		contentType := rw.Header().Get("Content-Type")
+		rw.isStreaming = strings.Contains(contentType, "text/event-stream") ||
+			strings.Contains(contentType, "stream")
+	}
+
+	if rw.isStreaming {
+		return rw.ResponseWriter.Write(rw.rewriteStreamChunk(data))
+	}
+	return rw.body.Write(data)
+}
+
+// Flush writes the buffered response with model names rewritten
+func (rw *ResponseRewriter) Flush() {
+	if rw.isStreaming {
+		if flusher, ok := rw.ResponseWriter.(http.Flusher); ok {
+			flusher.Flush()
+		}
+		return
+	}
+	if rw.body.Len() > 0 {
+		if _, err := rw.ResponseWriter.Write(rw.rewriteModelInResponse(rw.body.Bytes())); err != nil {
+			log.Warnf("amp response rewriter: failed to write rewritten response: %v", err)
+		}
+	}
+}
+
+// modelFieldPaths lists all JSON paths where model name may appear
+var modelFieldPaths = []string{"model", "modelVersion", "response.modelVersion", "message.model"}
+
+// rewriteModelInResponse replaces all occurrences of the mapped model with the original model in JSON
+func (rw *ResponseRewriter) rewriteModelInResponse(data []byte) []byte {
+	if rw.originalModel == "" {
+		return data
+	}
+	for _, path := range modelFieldPaths {
+		if gjson.GetBytes(data, path).Exists() {
+			data, _ = sjson.SetBytes(data, path, rw.originalModel)
+		}
+	}
+	return data
+}
+
+// rewriteStreamChunk rewrites model names in SSE stream chunks
+func (rw *ResponseRewriter) rewriteStreamChunk(chunk []byte) []byte {
+	if rw.originalModel == "" {
+		return chunk
+	}
+
+	// SSE format: "data: {json}\n\n"
+	lines := bytes.Split(chunk, []byte("\n"))
+	for i, line := range lines {
+		if bytes.HasPrefix(line, []byte("data: ")) {
+			jsonData := bytes.TrimPrefix(line, []byte("data: "))
+			if len(jsonData) > 0 && jsonData[0] == '{' {
+				// Rewrite JSON in the data line
+				rewritten := rw.rewriteModelInResponse(jsonData)
+				lines[i] = append([]byte("data: "), rewritten...)
+			}
+		}
+	}
+
+	return bytes.Join(lines, []byte("\n"))
+}

internal/translator/antigravity/openai/chat-completions/antigravity_openai_response.go

@@ -10,6 +10,7 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"strings"
 	"time"
 
 	. "github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/openai/chat-completions"
@@ -75,8 +76,8 @@ func ConvertAntigravityResponseToOpenAI(_ context.Context, _ string, originalReq
 
 	// Extract and set the finish reason.
 	if finishReasonResult := gjson.GetBytes(rawJSON, "response.candidates.0.finishReason"); finishReasonResult.Exists() {
-		template, _ = sjson.Set(template, "choices.0.finish_reason", finishReasonResult.String())
-		template, _ = sjson.Set(template, "choices.0.native_finish_reason", finishReasonResult.String())
+		template, _ = sjson.Set(template, "choices.0.finish_reason", strings.ToLower(finishReasonResult.String()))
+		template, _ = sjson.Set(template, "choices.0.native_finish_reason", strings.ToLower(finishReasonResult.String()))
 	}
 
 	// Extract and set usage metadata (token counts).

internal/translator/gemini-cli/openai/chat-completions/gemini-cli_openai_response.go

@@ -10,6 +10,7 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"strings"
 	"time"
 
 	. "github.com/router-for-me/CLIProxyAPI/v6/internal/translator/gemini/openai/chat-completions"
@@ -75,8 +76,8 @@ func ConvertCliResponseToOpenAI(_ context.Context, _ string, originalRequestRawJ
 
 	// Extract and set the finish reason.
 	if finishReasonResult := gjson.GetBytes(rawJSON, "response.candidates.0.finishReason"); finishReasonResult.Exists() {
-		template, _ = sjson.Set(template, "choices.0.finish_reason", finishReasonResult.String())
-		template, _ = sjson.Set(template, "choices.0.native_finish_reason", finishReasonResult.String())
+		template, _ = sjson.Set(template, "choices.0.finish_reason", strings.ToLower(finishReasonResult.String()))
+		template, _ = sjson.Set(template, "choices.0.native_finish_reason", strings.ToLower(finishReasonResult.String()))
 	}
 
 	// Extract and set usage metadata (token counts).

internal/translator/gemini/openai/chat-completions/gemini_openai_response.go

@@ -10,6 +10,7 @@ import (
 	"context"
 	"encoding/json"
 	"fmt"
+	"strings"
 	"time"
 
 	"github.com/tidwall/gjson"
@@ -78,8 +79,8 @@ func ConvertGeminiResponseToOpenAI(_ context.Context, _ string, originalRequestR
 
 	// Extract and set the finish reason.
 	if finishReasonResult := gjson.GetBytes(rawJSON, "candidates.0.finishReason"); finishReasonResult.Exists() {
-		template, _ = sjson.Set(template, "choices.0.finish_reason", finishReasonResult.String())
-		template, _ = sjson.Set(template, "choices.0.native_finish_reason", finishReasonResult.String())
+		template, _ = sjson.Set(template, "choices.0.finish_reason", strings.ToLower(finishReasonResult.String()))
+		template, _ = sjson.Set(template, "choices.0.native_finish_reason", strings.ToLower(finishReasonResult.String()))
 	}
 
 	// Extract and set usage metadata (token counts).
@@ -230,8 +231,8 @@ func ConvertGeminiResponseToOpenAINonStream(_ context.Context, _ string, origina
 	}
 
 	if finishReasonResult := gjson.GetBytes(rawJSON, "candidates.0.finishReason"); finishReasonResult.Exists() {
-		template, _ = sjson.Set(template, "choices.0.finish_reason", finishReasonResult.String())
-		template, _ = sjson.Set(template, "choices.0.native_finish_reason", finishReasonResult.String())
+		template, _ = sjson.Set(template, "choices.0.finish_reason", strings.ToLower(finishReasonResult.String()))
+		template, _ = sjson.Set(template, "choices.0.native_finish_reason", strings.ToLower(finishReasonResult.String()))
 	}
 
 	if usageResult := gjson.GetBytes(rawJSON, "usageMetadata"); usageResult.Exists() {