remove PR_DOCUMENTATION.md

feat(kiro): 支持思考模型 (Thinking Mode) 并通过多配额故障转移增强稳定性

internal/api/modules/amp/proxy.go

@@ -3,6 +3,8 @@ package amp
 import (
 	"bytes"
 	"compress/gzip"
+	"context"
+	"errors"
 	"fmt"
 	"io"
 	"net/http"
@@ -148,7 +150,13 @@ func createReverseProxy(upstreamURL string, secretSource SecretSource) (*httputi
 
 	// Error handler for proxy failures
 	proxy.ErrorHandler = func(rw http.ResponseWriter, req *http.Request, err error) {
-		log.Errorf("amp upstream proxy error for %s %s: %v", req.Method, req.URL.Path, err)
+		// Check if this is a client-side cancellation (normal behavior)
+		// Don't log as error for context canceled - it's usually client closing connection
+		if errors.Is(err, context.Canceled) {
+			log.Debugf("amp upstream proxy: client canceled request for %s %s", req.Method, req.URL.Path)
+		} else {
+			log.Errorf("amp upstream proxy error for %s %s: %v", req.Method, req.URL.Path, err)
+		}
 		rw.Header().Set("Content-Type", "application/json")
 		rw.WriteHeader(http.StatusBadGateway)
 		_, _ = rw.Write([]byte(`{"error":"amp_upstream_proxy_error","message":"Failed to reach Amp upstream"}`))

internal/api/server.go

@@ -349,6 +349,12 @@ func (s *Server) setupRoutes() {
 			},
 		})
 	})
+
+	// Event logging endpoint - handles Claude Code telemetry requests
+	// Returns 200 OK to prevent 404 errors in logs
+	s.engine.POST("/api/event_logging/batch", func(c *gin.Context) {
+		c.JSON(http.StatusOK, gin.H{"status": "ok"})
+	})
 	s.engine.POST("/v1internal:method", geminiCLIHandlers.CLIHandler)
 
 	// OAuth callback endpoints (reuse main server port)

internal/config/config.go

@@ -64,6 +64,10 @@ type Config struct {
 	// KiroKey defines a list of Kiro (AWS CodeWhisperer) configurations.
 	KiroKey []KiroKey `yaml:"kiro" json:"kiro"`
 
+	// KiroPreferredEndpoint sets the global default preferred endpoint for all Kiro providers.
+	// Values: "ide" (default, CodeWhisperer) or "cli" (Amazon Q).
+	KiroPreferredEndpoint string `yaml:"kiro-preferred-endpoint" json:"kiro-preferred-endpoint"`
+
 	// Codex defines a list of Codex API key configurations as specified in the YAML configuration file.
 	CodexKey []CodexKey `yaml:"codex-api-key" json:"codex-api-key"`
 
@@ -278,6 +282,10 @@ type KiroKey struct {
 	// AgentTaskType sets the Kiro API task type. Known values: "vibe", "dev", "chat".
 	// Leave empty to let API use defaults. Different values may inject different system prompts.
 	AgentTaskType string `yaml:"agent-task-type,omitempty" json:"agent-task-type,omitempty"`
+
+	// PreferredEndpoint sets the preferred Kiro API endpoint/quota.
+	// Values: "codewhisperer" (default, IDE quota) or "amazonq" (CLI quota).
+	PreferredEndpoint string `yaml:"preferred-endpoint,omitempty" json:"preferred-endpoint,omitempty"`
 }
 
 // OpenAICompatibility represents the configuration for OpenAI API compatibility
@@ -504,6 +512,7 @@ func (cfg *Config) SanitizeKiroKeys() {
 		entry.ProfileArn = strings.TrimSpace(entry.ProfileArn)
 		entry.Region = strings.TrimSpace(entry.Region)
 		entry.ProxyURL = strings.TrimSpace(entry.ProxyURL)
+		entry.PreferredEndpoint = strings.TrimSpace(entry.PreferredEndpoint)
 	}
 }
 

internal/registry/model_definitions.go

@@ -580,7 +580,7 @@ func GetOpenAIModels() []*ModelInfo {
 			ContextLength:       400000,
 			MaxCompletionTokens: 128000,
 			SupportedParameters: []string{"tools"},
-			Thinking:            &ThinkingSupport{Levels: []string{"low", "medium", "high", "xhigh"}},
+			Thinking:            &ThinkingSupport{Levels: []string{"none", "low", "medium", "high", "xhigh"}},
 		},
 	}
 }
@@ -884,8 +884,9 @@ func GetGitHubCopilotModels() []*ModelInfo {
 // GetKiroModels returns the Kiro (AWS CodeWhisperer) model definitions
 func GetKiroModels() []*ModelInfo {
 	return []*ModelInfo{
+		// --- Base Models ---
 		{
-			ID:                  "kiro-claude-opus-4.5",
+			ID:                  "kiro-claude-opus-4-5",
 			Object:              "model",
 			Created:             1732752000,
 			OwnedBy:             "aws",
@@ -896,7 +897,7 @@ func GetKiroModels() []*ModelInfo {
 			MaxCompletionTokens: 64000,
 		},
 		{
-			ID:                  "kiro-claude-sonnet-4.5",
+			ID:                  "kiro-claude-sonnet-4-5",
 			Object:              "model",
 			Created:             1732752000,
 			OwnedBy:             "aws",
@@ -918,7 +919,7 @@ func GetKiroModels() []*ModelInfo {
 			MaxCompletionTokens: 64000,
 		},
 		{
-			ID:                  "kiro-claude-haiku-4.5",
+			ID:                  "kiro-claude-haiku-4-5",
 			Object:              "model",
 			Created:             1732752000,
 			OwnedBy:             "aws",
@@ -928,21 +929,9 @@ func GetKiroModels() []*ModelInfo {
 			ContextLength:       200000,
 			MaxCompletionTokens: 64000,
 		},
-		// --- Chat Variant (No tool calling, for pure conversation) ---
-		{
-			ID:                  "kiro-claude-opus-4.5-chat",
-			Object:              "model",
-			Created:             1732752000,
-			OwnedBy:             "aws",
-			Type:                "kiro",
-			DisplayName:         "Kiro Claude Opus 4.5 (Chat)",
-			Description:         "Claude Opus 4.5 for chat only (no tool calling)",
-			ContextLength:       200000,
-			MaxCompletionTokens: 64000,
-		},
 		// --- Agentic Variants (Optimized for coding agents with chunked writes) ---
 		{
-			ID:                  "kiro-claude-opus-4.5-agentic",
+			ID:                  "kiro-claude-opus-4-5-agentic",
 			Object:              "model",
 			Created:             1732752000,
 			OwnedBy:             "aws",
@@ -953,7 +942,7 @@ func GetKiroModels() []*ModelInfo {
 			MaxCompletionTokens: 64000,
 		},
 		{
-			ID:                  "kiro-claude-sonnet-4.5-agentic",
+			ID:                  "kiro-claude-sonnet-4-5-agentic",
 			Object:              "model",
 			Created:             1732752000,
 			OwnedBy:             "aws",
@@ -963,6 +952,28 @@ func GetKiroModels() []*ModelInfo {
 			ContextLength:       200000,
 			MaxCompletionTokens: 64000,
 		},
+		{
+			ID:                  "kiro-claude-sonnet-4-agentic",
+			Object:              "model",
+			Created:             1732752000,
+			OwnedBy:             "aws",
+			Type:                "kiro",
+			DisplayName:         "Kiro Claude Sonnet 4 (Agentic)",
+			Description:         "Claude Sonnet 4 optimized for coding agents (chunked writes)",
+			ContextLength:       200000,
+			MaxCompletionTokens: 64000,
+		},
+		{
+			ID:                  "kiro-claude-haiku-4-5-agentic",
+			Object:              "model",
+			Created:             1732752000,
+			OwnedBy:             "aws",
+			Type:                "kiro",
+			DisplayName:         "Kiro Claude Haiku 4.5 (Agentic)",
+			Description:         "Claude Haiku 4.5 optimized for coding agents (chunked writes)",
+			ContextLength:       200000,
+			MaxCompletionTokens: 64000,
+		},
 	}
 }
 

internal/translator/kiro/openai/chat-completions/kiro_openai_request.go

@@ -10,9 +10,18 @@ import (
 	"github.com/tidwall/sjson"
 )
 
+// reasoningEffortToBudget maps OpenAI reasoning_effort values to Claude thinking budget_tokens.
+// OpenAI uses "low", "medium", "high" while Claude uses numeric budget_tokens.
+var reasoningEffortToBudget = map[string]int{
+	"low":    4000,
+	"medium": 16000,
+	"high":   32000,
+}
+
 // ConvertOpenAIRequestToKiro transforms an OpenAI Chat Completions API request into Kiro (Claude) format.
 // Kiro uses Claude-compatible format internally, so we primarily pass through to Claude format.
 // Supports tool calling: OpenAI tools -> Claude tools, tool_calls -> tool_use, tool messages -> tool_result.
+// Supports reasoning/thinking: OpenAI reasoning_effort -> Claude thinking parameter.
 func ConvertOpenAIRequestToKiro(modelName string, inputRawJSON []byte, stream bool) []byte {
 	rawJSON := bytes.Clone(inputRawJSON)
 	root := gjson.ParseBytes(rawJSON)
@@ -38,6 +47,26 @@ func ConvertOpenAIRequestToKiro(modelName string, inputRawJSON []byte, stream bo
 		out, _ = sjson.Set(out, "top_p", v.Float())
 	}
 
+	// Handle OpenAI reasoning_effort parameter -> Claude thinking parameter
+	// OpenAI format: {"reasoning_effort": "low"|"medium"|"high"}
+	// Claude format: {"thinking": {"type": "enabled", "budget_tokens": N}}
+	if v := root.Get("reasoning_effort"); v.Exists() {
+		effort := v.String()
+		if budget, ok := reasoningEffortToBudget[effort]; ok {
+			thinking := map[string]interface{}{
+				"type":          "enabled",
+				"budget_tokens": budget,
+			}
+			out, _ = sjson.Set(out, "thinking", thinking)
+		}
+	}
+
+	// Also support direct thinking parameter passthrough (for Claude API compatibility)
+	// Claude format: {"thinking": {"type": "enabled", "budget_tokens": N}}
+	if v := root.Get("thinking"); v.Exists() && v.IsObject() {
+		out, _ = sjson.Set(out, "thinking", v.Value())
+	}
+
 	// Convert OpenAI tools to Claude tools format
 	if tools := root.Get("tools"); tools.Exists() && tools.IsArray() {
 		claudeTools := make([]interface{}, 0)

internal/translator/kiro/openai/chat-completions/kiro_openai_response.go

@@ -134,6 +134,28 @@ func convertClaudeEventToOpenAI(jsonStr string, model string) []string {
 				result, _ := json.Marshal(response)
 				results = append(results, string(result))
 			}
+		} else if deltaType == "thinking_delta" {
+			// Thinking/reasoning content delta - convert to OpenAI reasoning_content format
+			thinkingDelta := root.Get("delta.thinking").String()
+			if thinkingDelta != "" {
+				response := map[string]interface{}{
+					"id":      "chatcmpl-" + uuid.New().String()[:24],
+					"object":  "chat.completion.chunk",
+					"created": time.Now().Unix(),
+					"model":   model,
+					"choices": []map[string]interface{}{
+						{
+							"index": 0,
+							"delta": map[string]interface{}{
+								"reasoning_content": thinkingDelta,
+							},
+							"finish_reason": nil,
+						},
+					},
+				}
+				result, _ := json.Marshal(response)
+				results = append(results, string(result))
+			}
 		} else if deltaType == "input_json_delta" {
 			// Tool input delta (streaming arguments)
 			partialJSON := root.Get("delta.partial_json").String()
@@ -298,6 +320,7 @@ func ConvertKiroResponseToOpenAINonStream(ctx context.Context, model string, ori
 	root := gjson.ParseBytes(rawResponse)
 
 	var content string
+	var reasoningContent string
 	var toolCalls []map[string]interface{}
 
 	contentArray := root.Get("content")
@@ -306,6 +329,9 @@ func ConvertKiroResponseToOpenAINonStream(ctx context.Context, model string, ori
 			itemType := item.Get("type").String()
 			if itemType == "text" {
 				content += item.Get("text").String()
+			} else if itemType == "thinking" {
+				// Extract thinking/reasoning content
+				reasoningContent += item.Get("thinking").String()
 			} else if itemType == "tool_use" {
 				// Convert Claude tool_use to OpenAI tool_calls format
 				inputJSON := item.Get("input").String()
@@ -339,6 +365,11 @@ func ConvertKiroResponseToOpenAINonStream(ctx context.Context, model string, ori
 		"content": content,
 	}
 
+	// Add reasoning_content if present (OpenAI reasoning format)
+	if reasoningContent != "" {
+		message["reasoning_content"] = reasoningContent
+	}
+
 	// Add tool_calls if present
 	if len(toolCalls) > 0 {
 		message["tool_calls"] = toolCalls

internal/watcher/watcher.go

@@ -1317,6 +1317,12 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 			if kk.AgentTaskType != "" {
 				attrs["agent_task_type"] = kk.AgentTaskType
 			}
+			if kk.PreferredEndpoint != "" {
+				attrs["preferred_endpoint"] = kk.PreferredEndpoint
+			} else if cfg.KiroPreferredEndpoint != "" {
+				// Apply global default if not overridden by specific key
+				attrs["preferred_endpoint"] = cfg.KiroPreferredEndpoint
+			}
 			if refreshToken != "" {
 				attrs["refresh_token"] = refreshToken
 			}
@@ -1532,6 +1538,17 @@ func (w *Watcher) SnapshotCoreAuths() []*coreauth.Auth {
 					a.NextRefreshAfter = expiresAt.Add(-30 * time.Minute)
 				}
 			}
+			
+			// Apply global preferred endpoint setting if not present in metadata
+			if cfg.KiroPreferredEndpoint != "" {
+				// Check if already set in metadata (which takes precedence in executor)
+				if _, hasMeta := metadata["preferred_endpoint"]; !hasMeta {
+					if a.Attributes == nil {
+						a.Attributes = make(map[string]string)
+					}
+					a.Attributes["preferred_endpoint"] = cfg.KiroPreferredEndpoint
+				}
+			}
 		}
 
 		applyAuthExcludedModelsMeta(a, cfg, nil, "oauth")

sdk/api/handlers/handlers.go

@@ -136,19 +136,29 @@ func (h *BaseAPIHandler) GetContextWithCancel(handler interfaces.APIHandler, c *
 	newCtx = context.WithValue(newCtx, "gin", c)
 	newCtx = context.WithValue(newCtx, "handler", handler)
 	return newCtx, func(params ...interface{}) {
-		if h.Cfg.RequestLog {
-			if len(params) == 1 {
-				data := params[0]
-				switch data.(type) {
-				case []byte:
-					appendAPIResponse(c, data.([]byte))
-				case error:
-					appendAPIResponse(c, []byte(data.(error).Error()))
-				case string:
-					appendAPIResponse(c, []byte(data.(string)))
-				case bool:
-				case nil:
+		if h.Cfg.RequestLog && len(params) == 1 {
+			var payload []byte
+			switch data := params[0].(type) {
+			case []byte:
+				payload = data
+			case error:
+				if data != nil {
+					payload = []byte(data.Error())
 				}
+			case string:
+				payload = []byte(data)
+			}
+			if len(payload) > 0 {
+				if existing, exists := c.Get("API_RESPONSE"); exists {
+					if existingBytes, ok := existing.([]byte); ok && len(existingBytes) > 0 {
+						trimmedPayload := bytes.TrimSpace(payload)
+						if len(trimmedPayload) > 0 && bytes.Contains(existingBytes, trimmedPayload) {
+							cancel()
+							return
+						}
+					}
+				}
+				appendAPIResponse(c, payload)
 			}
 		}