internal/translator/gemini-cli/claude/gemini-cli_claude_response.go

// Package claude provides response translation functionality for Claude Code API compatibility.
// This package handles the conversion of backend client responses into Claude Code-compatible
// Server-Sent Events (SSE) format, implementing a sophisticated state machine that manages
// different response types including text content, thinking processes, and function calls.
// The translation ensures proper sequencing of SSE events and maintains state across
// multiple response chunks to provide a seamless streaming experience.
package claude

import (
	"bytes"
	"context"
	"fmt"
	"strings"
	"sync/atomic"
	"time"

	"github.com/tidwall/gjson"
	"github.com/tidwall/sjson"
)

// Params holds parameters for response conversion and maintains state across streaming chunks.
// This structure tracks the current state of the response translation process to ensure
// proper sequencing of SSE events and transitions between different content types.
type Params struct {
	HasFirstResponse bool // Indicates if the initial message_start event has been sent
	ResponseType     int  // Current response type: 0=none, 1=content, 2=thinking, 3=function
	ResponseIndex    int  // Index counter for content blocks in the streaming response
	HasContent       bool // Tracks whether any content (text, thinking, or tool use) has been output
}

// toolUseIDCounter provides a process-wide unique counter for tool use identifiers.
var toolUseIDCounter uint64

// ConvertGeminiCLIResponseToClaude performs sophisticated streaming response format conversion.
// This function implements a complex state machine that translates backend client responses
// into Claude Code-compatible Server-Sent Events (SSE) format. It manages different response types
// and handles state transitions between content blocks, thinking processes, and function calls.
//
// Response type states: 0=none, 1=content, 2=thinking, 3=function
// The function maintains state across multiple calls to ensure proper SSE event sequencing.
//
// Parameters:
//   - ctx: The context for the request, used for cancellation and timeout handling
//   - modelName: The name of the model being used for the response (unused in current implementation)
//   - rawJSON: The raw JSON response from the Gemini CLI API
//   - param: A pointer to a parameter object for maintaining state between calls
//
// Returns:
//   - []string: A slice of strings, each containing a Claude Code-compatible JSON response
func ConvertGeminiCLIResponseToClaude(_ context.Context, _ string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, param *any) []string {
	if *param == nil {
		*param = &Params{
			HasFirstResponse: false,
			ResponseType:     0,
			ResponseIndex:    0,
		}
	}

	if bytes.Equal(rawJSON, []byte("[DONE]")) {
		// Only send message_stop if we have actually output content
		if (*param).(*Params).HasContent {
			return []string{
				"event: message_stop\ndata: {\"type\":\"message_stop\"}\n\n\n",
			}
		}
		return []string{}
	}

	// Track whether tools are being used in this response chunk
	usedTool := false
	output := ""

	// Initialize the streaming session with a message_start event
	// This is only sent for the very first response chunk to establish the streaming session
	if !(*param).(*Params).HasFirstResponse {
		output = "event: message_start\n"

		// Create the initial message structure with default values according to Claude Code API specification
		// This follows the Claude Code API specification for streaming message initialization
		messageStartTemplate := `{"type": "message_start", "message": {"id": "msg_1nZdL29xx5MUA1yADyHTEsnR8uuvGzszyY", "type": "message", "role": "assistant", "content": [], "model": "claude-3-5-sonnet-20241022", "stop_reason": null, "stop_sequence": null, "usage": {"input_tokens": 0, "output_tokens": 0}}}`

		// Override default values with actual response metadata if available from the Gemini CLI response
		if modelVersionResult := gjson.GetBytes(rawJSON, "response.modelVersion"); modelVersionResult.Exists() {
			messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.model", modelVersionResult.String())
		}
		if responseIDResult := gjson.GetBytes(rawJSON, "response.responseId"); responseIDResult.Exists() {
			messageStartTemplate, _ = sjson.Set(messageStartTemplate, "message.id", responseIDResult.String())
		}
		output = output + fmt.Sprintf("data: %s\n\n\n", messageStartTemplate)

		(*param).(*Params).HasFirstResponse = true
	}

	// Process the response parts array from the backend client
	// Each part can contain text content, thinking content, or function calls
	partsResult := gjson.GetBytes(rawJSON, "response.candidates.0.content.parts")
	if partsResult.IsArray() {
		partResults := partsResult.Array()
		for i := 0; i < len(partResults); i++ {
			partResult := partResults[i]

			// Extract the different types of content from each part
			partTextResult := partResult.Get("text")
			functionCallResult := partResult.Get("functionCall")

			// Handle text content (both regular content and thinking)
			if partTextResult.Exists() {
				// Process thinking content (internal reasoning)
				if partResult.Get("thought").Bool() {
					// Continue existing thinking block if already in thinking state
					if (*param).(*Params).ResponseType == 2 {
						output = output + "event: content_block_delta\n"
						data, _ := sjson.Set(fmt.Sprintf(`{"type":"content_block_delta","index":%d,"delta":{"type":"thinking_delta","thinking":""}}`, (*param).(*Params).ResponseIndex), "delta.thinking", partTextResult.String())
						output = output + fmt.Sprintf("data: %s\n\n\n", data)
						(*param).(*Params).HasContent = true
					} else {
						// Transition from another state to thinking
						// First, close any existing content block
						if (*param).(*Params).ResponseType != 0 {
							if (*param).(*Params).ResponseType == 2 {
								// output = output + "event: content_block_delta\n"
								// output = output + fmt.Sprintf(`data: {"type":"content_block_delta","index":%d,"delta":{"type":"signature_delta","signature":null}}`, (*param).(*Params).ResponseIndex)
								// output = output + "\n\n\n"
							}
							output = output + "event: content_block_stop\n"
							output = output + fmt.Sprintf(`data: {"type":"content_block_stop","index":%d}`, (*param).(*Params).ResponseIndex)
							output = output + "\n\n\n"
							(*param).(*Params).ResponseIndex++
						}

						// Start a new thinking content block
						output = output + "event: content_block_start\n"
						output = output + fmt.Sprintf(`data: {"type":"content_block_start","index":%d,"content_block":{"type":"thinking","thinking":""}}`, (*param).(*Params).ResponseIndex)
						output = output + "\n\n\n"
						output = output + "event: content_block_delta\n"
						data, _ := sjson.Set(fmt.Sprintf(`{"type":"content_block_delta","index":%d,"delta":{"type":"thinking_delta","thinking":""}}`, (*param).(*Params).ResponseIndex), "delta.thinking", partTextResult.String())
						output = output + fmt.Sprintf("data: %s\n\n\n", data)
						(*param).(*Params).ResponseType = 2 // Set state to thinking
						(*param).(*Params).HasContent = true
					}
				} else {
					// Process regular text content (user-visible output)
					// Continue existing text block if already in content state
					if (*param).(*Params).ResponseType == 1 {
						output = output + "event: content_block_delta\n"
						data, _ := sjson.Set(fmt.Sprintf(`{"type":"content_block_delta","index":%d,"delta":{"type":"text_delta","text":""}}`, (*param).(*Params).ResponseIndex), "delta.text", partTextResult.String())
						output = output + fmt.Sprintf("data: %s\n\n\n", data)
						(*param).(*Params).HasContent = true
					} else {
						// Transition from another state to text content
						// First, close any existing content block
						if (*param).(*Params).ResponseType != 0 {
							if (*param).(*Params).ResponseType == 2 {
								// output = output + "event: content_block_delta\n"
								// output = output + fmt.Sprintf(`data: {"type":"content_block_delta","index":%d,"delta":{"type":"signature_delta","signature":null}}`, (*param).(*Params).ResponseIndex)
								// output = output + "\n\n\n"
							}
							output = output + "event: content_block_stop\n"
							output = output + fmt.Sprintf(`data: {"type":"content_block_stop","index":%d}`, (*param).(*Params).ResponseIndex)
							output = output + "\n\n\n"
							(*param).(*Params).ResponseIndex++
						}

						// Start a new text content block
						output = output + "event: content_block_start\n"
						output = output + fmt.Sprintf(`data: {"type":"content_block_start","index":%d,"content_block":{"type":"text","text":""}}`, (*param).(*Params).ResponseIndex)
						output = output + "\n\n\n"
						output = output + "event: content_block_delta\n"
						data, _ := sjson.Set(fmt.Sprintf(`{"type":"content_block_delta","index":%d,"delta":{"type":"text_delta","text":""}}`, (*param).(*Params).ResponseIndex), "delta.text", partTextResult.String())
						output = output + fmt.Sprintf("data: %s\n\n\n", data)
						(*param).(*Params).ResponseType = 1 // Set state to content
						(*param).(*Params).HasContent = true
					}
				}
			} else if functionCallResult.Exists() {
				// Handle function/tool calls from the AI model
				// This processes tool usage requests and formats them for Claude Code API compatibility
				usedTool = true
				fcName := functionCallResult.Get("name").String()

				// Handle state transitions when switching to function calls
				// Close any existing function call block first
				if (*param).(*Params).ResponseType == 3 {
					output = output + "event: content_block_stop\n"
					output = output + fmt.Sprintf(`data: {"type":"content_block_stop","index":%d}`, (*param).(*Params).ResponseIndex)
					output = output + "\n\n\n"
					(*param).(*Params).ResponseIndex++
					(*param).(*Params).ResponseType = 0
				}

				// Special handling for thinking state transition
				if (*param).(*Params).ResponseType == 2 {
					// output = output + "event: content_block_delta\n"
					// output = output + fmt.Sprintf(`data: {"type":"content_block_delta","index":%d,"delta":{"type":"signature_delta","signature":null}}`, (*param).(*Params).ResponseIndex)
					// output = output + "\n\n\n"
				}

				// Close any other existing content block
				if (*param).(*Params).ResponseType != 0 {
					output = output + "event: content_block_stop\n"
					output = output + fmt.Sprintf(`data: {"type":"content_block_stop","index":%d}`, (*param).(*Params).ResponseIndex)
					output = output + "\n\n\n"
					(*param).(*Params).ResponseIndex++
				}

				// Start a new tool use content block
				// This creates the structure for a function call in Claude Code format
				output = output + "event: content_block_start\n"

				// Create the tool use block with unique ID and function details
				data := fmt.Sprintf(`{"type":"content_block_start","index":%d,"content_block":{"type":"tool_use","id":"","name":"","input":{}}}`, (*param).(*Params).ResponseIndex)
				data, _ = sjson.Set(data, "content_block.id", fmt.Sprintf("%s-%d-%d", fcName, time.Now().UnixNano(), atomic.AddUint64(&toolUseIDCounter, 1)))
				data, _ = sjson.Set(data, "content_block.name", fcName)
				output = output + fmt.Sprintf("data: %s\n\n\n", data)

				if fcArgsResult := functionCallResult.Get("args"); fcArgsResult.Exists() {
					output = output + "event: content_block_delta\n"
					data, _ = sjson.Set(fmt.Sprintf(`{"type":"content_block_delta","index":%d,"delta":{"type":"input_json_delta","partial_json":""}}`, (*param).(*Params).ResponseIndex), "delta.partial_json", fcArgsResult.Raw)
					output = output + fmt.Sprintf("data: %s\n\n\n", data)
				}
				(*param).(*Params).ResponseType = 3
				(*param).(*Params).HasContent = true
			}
		}
	}

	usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata")
	// Process usage metadata and finish reason when present in the response
	if usageResult.Exists() && bytes.Contains(rawJSON, []byte(`"finishReason"`)) {
		if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
			// Only send final events if we have actually output content
			if (*param).(*Params).HasContent {
				// Close the final content block
				output = output + "event: content_block_stop\n"
				output = output + fmt.Sprintf(`data: {"type":"content_block_stop","index":%d}`, (*param).(*Params).ResponseIndex)
				output = output + "\n\n\n"

				// Send the final message delta with usage information and stop reason
				output = output + "event: message_delta\n"
				output = output + `data: `

				// Create the message delta template with appropriate stop reason
				template := `{"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":0,"output_tokens":0}}`
				// Set tool_use stop reason if tools were used in this response
				if usedTool {
					template = `{"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":0,"output_tokens":0}}`
				}

				// Include thinking tokens in output token count if present
				thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
				template, _ = sjson.Set(template, "usage.output_tokens", candidatesTokenCountResult.Int()+thoughtsTokenCount)
				template, _ = sjson.Set(template, "usage.input_tokens", usageResult.Get("promptTokenCount").Int())

				output = output + template + "\n\n\n"
			}
		}
	}

	return []string{output}
}

// ConvertGeminiCLIResponseToClaudeNonStream converts a non-streaming Gemini CLI response to a non-streaming Claude response.
//
// Parameters:
//   - ctx: The context for the request.
//   - modelName: The name of the model.
//   - rawJSON: The raw JSON response from the Gemini CLI API.
//   - param: A pointer to a parameter object for the conversion.
//
// Returns:
//   - string: A Claude-compatible JSON response.
func ConvertGeminiCLIResponseToClaudeNonStream(_ context.Context, _ string, originalRequestRawJSON, requestRawJSON, rawJSON []byte, _ *any) string {
	_ = originalRequestRawJSON
	_ = requestRawJSON

	root := gjson.ParseBytes(rawJSON)

	out := `{"id":"","type":"message","role":"assistant","model":"","content":[],"stop_reason":null,"stop_sequence":null,"usage":{"input_tokens":0,"output_tokens":0}}`
	out, _ = sjson.Set(out, "id", root.Get("response.responseId").String())
	out, _ = sjson.Set(out, "model", root.Get("response.modelVersion").String())

	inputTokens := root.Get("response.usageMetadata.promptTokenCount").Int()
	outputTokens := root.Get("response.usageMetadata.candidatesTokenCount").Int() + root.Get("response.usageMetadata.thoughtsTokenCount").Int()
	out, _ = sjson.Set(out, "usage.input_tokens", inputTokens)
	out, _ = sjson.Set(out, "usage.output_tokens", outputTokens)

	parts := root.Get("response.candidates.0.content.parts")
	textBuilder := strings.Builder{}
	thinkingBuilder := strings.Builder{}
	toolIDCounter := 0
	hasToolCall := false

	flushText := func() {
		if textBuilder.Len() == 0 {
			return
		}
		block := `{"type":"text","text":""}`
		block, _ = sjson.Set(block, "text", textBuilder.String())
		out, _ = sjson.SetRaw(out, "content.-1", block)
		textBuilder.Reset()
	}

	flushThinking := func() {
		if thinkingBuilder.Len() == 0 {
			return
		}
		block := `{"type":"thinking","thinking":""}`
		block, _ = sjson.Set(block, "thinking", thinkingBuilder.String())
		out, _ = sjson.SetRaw(out, "content.-1", block)
		thinkingBuilder.Reset()
	}

	if parts.IsArray() {
		for _, part := range parts.Array() {
			if text := part.Get("text"); text.Exists() && text.String() != "" {
				if part.Get("thought").Bool() {
					flushText()
					thinkingBuilder.WriteString(text.String())
					continue
				}
				flushThinking()
				textBuilder.WriteString(text.String())
				continue
			}

			if functionCall := part.Get("functionCall"); functionCall.Exists() {
				flushThinking()
				flushText()
				hasToolCall = true

				name := functionCall.Get("name").String()
				toolIDCounter++
				toolBlock := `{"type":"tool_use","id":"","name":"","input":{}}`
				toolBlock, _ = sjson.Set(toolBlock, "id", fmt.Sprintf("tool_%d", toolIDCounter))
				toolBlock, _ = sjson.Set(toolBlock, "name", name)
				inputRaw := "{}"
				if args := functionCall.Get("args"); args.Exists() && gjson.Valid(args.Raw) && args.IsObject() {
					inputRaw = args.Raw
				}
				toolBlock, _ = sjson.SetRaw(toolBlock, "input", inputRaw)
				out, _ = sjson.SetRaw(out, "content.-1", toolBlock)
				continue
			}
		}
	}

	flushThinking()
	flushText()

	stopReason := "end_turn"
	if hasToolCall {
		stopReason = "tool_use"
	} else {
		if finish := root.Get("response.candidates.0.finishReason"); finish.Exists() {
			switch finish.String() {
			case "MAX_TOKENS":
				stopReason = "max_tokens"
			case "STOP", "FINISH_REASON_UNSPECIFIED", "UNKNOWN":
				stopReason = "end_turn"
			default:
				stopReason = "end_turn"
			}
		}
	}
	out, _ = sjson.Set(out, "stop_reason", stopReason)

	if inputTokens == int64(0) && outputTokens == int64(0) && !root.Get("response.usageMetadata").Exists() {
		out, _ = sjson.Delete(out, "usage")
	}

	return out
}

func ClaudeTokenCount(ctx context.Context, count int64) string {
	return fmt.Sprintf(`{"input_tokens":%d}`, count)
}