Add openai codex support

internal/translator/gemini-cli/claude/code/cli_cc_request.go

@@ -0,0 +1,170 @@
+// Package code provides request translation functionality for Claude API.
+// It handles parsing and transforming Claude API requests into the internal client format,
+// extracting model information, system instructions, message contents, and tool declarations.
+// The package also performs JSON data cleaning and transformation to ensure compatibility
+// between Claude API format and the internal client's expected format.
+package code
+
+import (
+	"bytes"
+	"encoding/json"
+	"strings"
+
+	"github.com/luispater/CLIProxyAPI/internal/client"
+	"github.com/tidwall/gjson"
+	"github.com/tidwall/sjson"
+)
+
+// ConvertClaudeCodeRequestToCli parses and transforms a Claude API request into internal client format.
+// It extracts the model name, system instruction, message contents, and tool declarations
+// from the raw JSON request and returns them in the format expected by the internal client.
+func ConvertClaudeCodeRequestToCli(rawJSON []byte) (string, *client.Content, []client.Content, []client.ToolDeclaration) {
+	var pathsToDelete []string
+	root := gjson.ParseBytes(rawJSON)
+	walk(root, "", "additionalProperties", &pathsToDelete)
+	walk(root, "", "$schema", &pathsToDelete)
+
+	var err error
+	for _, p := range pathsToDelete {
+		rawJSON, err = sjson.DeleteBytes(rawJSON, p)
+		if err != nil {
+			continue
+		}
+	}
+	rawJSON = bytes.Replace(rawJSON, []byte(`"url":{"type":"string","format":"uri",`), []byte(`"url":{"type":"string",`), -1)
+
+	// log.Debug(string(rawJSON))
+	modelName := "gemini-2.5-pro"
+	modelResult := gjson.GetBytes(rawJSON, "model")
+	if modelResult.Type == gjson.String {
+		modelName = modelResult.String()
+	}
+
+	contents := make([]client.Content, 0)
+
+	var systemInstruction *client.Content
+
+	systemResult := gjson.GetBytes(rawJSON, "system")
+	if systemResult.IsArray() {
+		systemResults := systemResult.Array()
+		systemInstruction = &client.Content{Role: "user", Parts: []client.Part{}}
+		for i := 0; i < len(systemResults); i++ {
+			systemPromptResult := systemResults[i]
+			systemTypePromptResult := systemPromptResult.Get("type")
+			if systemTypePromptResult.Type == gjson.String && systemTypePromptResult.String() == "text" {
+				systemPrompt := systemPromptResult.Get("text").String()
+				systemPart := client.Part{Text: systemPrompt}
+				systemInstruction.Parts = append(systemInstruction.Parts, systemPart)
+			}
+		}
+		if len(systemInstruction.Parts) == 0 {
+			systemInstruction = nil
+		}
+	}
+
+	messagesResult := gjson.GetBytes(rawJSON, "messages")
+	if messagesResult.IsArray() {
+		messageResults := messagesResult.Array()
+		for i := 0; i < len(messageResults); i++ {
+			messageResult := messageResults[i]
+			roleResult := messageResult.Get("role")
+			if roleResult.Type != gjson.String {
+				continue
+			}
+			role := roleResult.String()
+			if role == "assistant" {
+				role = "model"
+			}
+			clientContent := client.Content{Role: role, Parts: []client.Part{}}
+
+			contentsResult := messageResult.Get("content")
+			if contentsResult.IsArray() {
+				contentResults := contentsResult.Array()
+				for j := 0; j < len(contentResults); j++ {
+					contentResult := contentResults[j]
+					contentTypeResult := contentResult.Get("type")
+					if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "text" {
+						prompt := contentResult.Get("text").String()
+						clientContent.Parts = append(clientContent.Parts, client.Part{Text: prompt})
+					} else if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "tool_use" {
+						functionName := contentResult.Get("name").String()
+						functionArgs := contentResult.Get("input").String()
+						var args map[string]any
+						if err = json.Unmarshal([]byte(functionArgs), &args); err == nil {
+							clientContent.Parts = append(clientContent.Parts, client.Part{
+								FunctionCall: &client.FunctionCall{
+									Name: functionName,
+									Args: args,
+								},
+							})
+						}
+					} else if contentTypeResult.Type == gjson.String && contentTypeResult.String() == "tool_result" {
+						toolCallID := contentResult.Get("tool_use_id").String()
+						if toolCallID != "" {
+							funcName := toolCallID
+							toolCallIDs := strings.Split(toolCallID, "-")
+							if len(toolCallIDs) > 1 {
+								funcName = strings.Join(toolCallIDs[0:len(toolCallIDs)-1], "-")
+							}
+							responseData := contentResult.Get("content").String()
+							functionResponse := client.FunctionResponse{Name: funcName, Response: map[string]interface{}{"result": responseData}}
+							clientContent.Parts = append(clientContent.Parts, client.Part{FunctionResponse: &functionResponse})
+						}
+					}
+				}
+				contents = append(contents, clientContent)
+			} else if contentsResult.Type == gjson.String {
+				prompt := contentsResult.String()
+				contents = append(contents, client.Content{Role: role, Parts: []client.Part{{Text: prompt}}})
+			}
+		}
+	}
+
+	var tools []client.ToolDeclaration
+	toolsResult := gjson.GetBytes(rawJSON, "tools")
+	if toolsResult.IsArray() {
+		tools = make([]client.ToolDeclaration, 1)
+		tools[0].FunctionDeclarations = make([]any, 0)
+		toolsResults := toolsResult.Array()
+		for i := 0; i < len(toolsResults); i++ {
+			toolResult := toolsResults[i]
+			inputSchemaResult := toolResult.Get("input_schema")
+			if inputSchemaResult.Exists() && inputSchemaResult.IsObject() {
+				inputSchema := inputSchemaResult.Raw
+				inputSchema, _ = sjson.Delete(inputSchema, "additionalProperties")
+				inputSchema, _ = sjson.Delete(inputSchema, "$schema")
+
+				tool, _ := sjson.Delete(toolResult.Raw, "input_schema")
+				tool, _ = sjson.SetRaw(tool, "parameters", inputSchema)
+				var toolDeclaration any
+				if err = json.Unmarshal([]byte(tool), &toolDeclaration); err == nil {
+					tools[0].FunctionDeclarations = append(tools[0].FunctionDeclarations, toolDeclaration)
+				}
+			}
+		}
+	} else {
+		tools = make([]client.ToolDeclaration, 0)
+	}
+
+	return modelName, systemInstruction, contents, tools
+}
+
+func walk(value gjson.Result, path, field string, pathsToDelete *[]string) {
+	switch value.Type {
+	case gjson.JSON:
+		value.ForEach(func(key, val gjson.Result) bool {
+			var childPath string
+			if path == "" {
+				childPath = key.String()
+			} else {
+				childPath = path + "." + key.String()
+			}
+			if key.String() == field {
+				*pathsToDelete = append(*pathsToDelete, childPath)
+			}
+			walk(val, childPath, field, pathsToDelete)
+			return true
+		})
+	case gjson.String, gjson.Number, gjson.True, gjson.False, gjson.Null:
+	}
+}

internal/translator/gemini-cli/claude/code/cli_cc_response.go

@@ -0,0 +1,207 @@
+// Package code provides response translation functionality for Claude API.
+// This package handles the conversion of backend client responses into Claude-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 code
+
+import (
+	"bytes"
+	"fmt"
+	"time"
+
+	"github.com/tidwall/gjson"
+	"github.com/tidwall/sjson"
+)
+
+// ConvertCliResponseToClaudeCode performs sophisticated streaming response format conversion.
+// This function implements a complex state machine that translates backend client responses
+// into Claude-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.
+func ConvertCliResponseToClaudeCode(rawJSON []byte, isGlAPIKey, hasFirstResponse bool, responseType, responseIndex *int) string {
+	// Normalize the response format for different API key types
+	// Generative Language API keys have a different response structure
+	if isGlAPIKey {
+		rawJSON, _ = sjson.SetRawBytes(rawJSON, "response", rawJSON)
+	}
+
+	// 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
+	if !hasFirstResponse {
+		output = "event: message_start\n"
+
+		// Create the initial message structure with default values
+		// This follows the Claude 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
+		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)
+	}
+
+	// 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 *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":""}}`, *responseIndex), "delta.thinking", partTextResult.String())
+						output = output + fmt.Sprintf("data: %s\n\n\n", data)
+					} else {
+						// Transition from another state to thinking
+						// First, close any existing content block
+						if *responseType != 0 {
+							if *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}}`, *responseIndex)
+								output = output + "\n\n\n"
+							}
+							output = output + "event: content_block_stop\n"
+							output = output + fmt.Sprintf(`data: {"type":"content_block_stop","index":%d}`, *responseIndex)
+							output = output + "\n\n\n"
+							*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":""}}`, *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":""}}`, *responseIndex), "delta.thinking", partTextResult.String())
+						output = output + fmt.Sprintf("data: %s\n\n\n", data)
+						*responseType = 2 // Set state to thinking
+					}
+				} else {
+					// Process regular text content (user-visible output)
+					// Continue existing text block
+					if *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":""}}`, *responseIndex), "delta.text", partTextResult.String())
+						output = output + fmt.Sprintf("data: %s\n\n\n", data)
+					} else {
+						// Transition from another state to text content
+						// First, close any existing content block
+						if *responseType != 0 {
+							if *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}}`, *responseIndex)
+								output = output + "\n\n\n"
+							}
+							output = output + "event: content_block_stop\n"
+							output = output + fmt.Sprintf(`data: {"type":"content_block_stop","index":%d}`, *responseIndex)
+							output = output + "\n\n\n"
+							*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":""}}`, *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":""}}`, *responseIndex), "delta.text", partTextResult.String())
+						output = output + fmt.Sprintf("data: %s\n\n\n", data)
+						*responseType = 1 // Set state to content
+					}
+				}
+			} else if functionCallResult.Exists() {
+				// Handle function/tool calls from the AI model
+				// This processes tool usage requests and formats them for Claude 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 *responseType == 3 {
+					output = output + "event: content_block_stop\n"
+					output = output + fmt.Sprintf(`data: {"type":"content_block_stop","index":%d}`, *responseIndex)
+					output = output + "\n\n\n"
+					*responseIndex++
+					*responseType = 0
+				}
+
+				// Special handling for thinking state transition
+				if *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}}`, *responseIndex)
+					output = output + "\n\n\n"
+				}
+
+				// Close any other existing content block
+				if *responseType != 0 {
+					output = output + "event: content_block_stop\n"
+					output = output + fmt.Sprintf(`data: {"type":"content_block_stop","index":%d}`, *responseIndex)
+					output = output + "\n\n\n"
+					*responseIndex++
+				}
+
+				// Start a new tool use content block
+				// This creates the structure for a function call in Claude 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":{}}}`, *responseIndex)
+				data, _ = sjson.Set(data, "content_block.id", fmt.Sprintf("%s-%d", fcName, time.Now().UnixNano()))
+				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":""}}`, *responseIndex), "delta.partial_json", fcArgsResult.Raw)
+					output = output + fmt.Sprintf("data: %s\n\n\n", data)
+				}
+				*responseType = 3
+			}
+		}
+	}
+
+	usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata")
+	if usageResult.Exists() && bytes.Contains(rawJSON, []byte(`"finishReason"`)) {
+		if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
+			output = output + "event: content_block_stop\n"
+			output = output + fmt.Sprintf(`data: {"type":"content_block_stop","index":%d}`, *responseIndex)
+			output = output + "\n\n\n"
+
+			output = output + "event: message_delta\n"
+			output = output + `data: `
+
+			template := `{"type":"message_delta","delta":{"stop_reason":"end_turn","stop_sequence":null},"usage":{"input_tokens":0,"output_tokens":0}}`
+			if usedTool {
+				template = `{"type":"message_delta","delta":{"stop_reason":"tool_use","stop_sequence":null},"usage":{"input_tokens":0,"output_tokens":0}}`
+			}
+
+			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 output
+}

internal/translator/gemini-cli/gemini/cli/cli_cli_request.go

@@ -0,0 +1,186 @@
+// Package cli provides request translation functionality for Gemini CLI API.
+// It handles the conversion and formatting of CLI tool responses, specifically
+// transforming between different JSON formats to ensure proper conversation flow
+// and API compatibility. The package focuses on intelligently grouping function
+// calls with their corresponding responses, converting from linear format to
+// grouped format where function calls and responses are properly associated.
+package cli
+
+import (
+	"encoding/json"
+	"fmt"
+
+	log "github.com/sirupsen/logrus"
+	"github.com/tidwall/gjson"
+	"github.com/tidwall/sjson"
+)
+
+// FunctionCallGroup represents a group of function calls and their responses
+type FunctionCallGroup struct {
+	ModelContent    map[string]interface{}
+	FunctionCalls   []gjson.Result
+	ResponsesNeeded int
+}
+
+// FixCLIToolResponse performs sophisticated tool response format conversion and grouping.
+// This function transforms the CLI tool response format by intelligently grouping function calls
+// with their corresponding responses, ensuring proper conversation flow and API compatibility.
+// It converts from a linear format (1.json) to a grouped format (2.json) where function calls
+// and their responses are properly associated and structured.
+func FixCLIToolResponse(input string) (string, error) {
+	// Parse the input JSON to extract the conversation structure
+	parsed := gjson.Parse(input)
+
+	// Extract the contents array which contains the conversation messages
+	contents := parsed.Get("request.contents")
+	if !contents.Exists() {
+		// log.Debugf(input)
+		return input, fmt.Errorf("contents not found in input")
+	}
+
+	// Initialize data structures for processing and grouping
+	var newContents []interface{}          // Final processed contents array
+	var pendingGroups []*FunctionCallGroup // Groups awaiting completion with responses
+	var collectedResponses []gjson.Result  // Standalone responses to be matched
+
+	// Process each content object in the conversation
+	// This iterates through messages and groups function calls with their responses
+	contents.ForEach(func(key, value gjson.Result) bool {
+		role := value.Get("role").String()
+		parts := value.Get("parts")
+
+		// Check if this content has function responses
+		var responsePartsInThisContent []gjson.Result
+		parts.ForEach(func(_, part gjson.Result) bool {
+			if part.Get("functionResponse").Exists() {
+				responsePartsInThisContent = append(responsePartsInThisContent, part)
+			}
+			return true
+		})
+
+		// If this content has function responses, collect them
+		if len(responsePartsInThisContent) > 0 {
+			collectedResponses = append(collectedResponses, responsePartsInThisContent...)
+
+			// Check if any pending groups can be satisfied
+			for i := len(pendingGroups) - 1; i >= 0; i-- {
+				group := pendingGroups[i]
+				if len(collectedResponses) >= group.ResponsesNeeded {
+					// Take the needed responses for this group
+					groupResponses := collectedResponses[:group.ResponsesNeeded]
+					collectedResponses = collectedResponses[group.ResponsesNeeded:]
+
+					// Create merged function response content
+					var responseParts []interface{}
+					for _, response := range groupResponses {
+						var responseMap map[string]interface{}
+						errUnmarshal := json.Unmarshal([]byte(response.Raw), &responseMap)
+						if errUnmarshal != nil {
+							log.Warnf("failed to unmarshal function response: %v\n", errUnmarshal)
+							continue
+						}
+						responseParts = append(responseParts, responseMap)
+					}
+
+					if len(responseParts) > 0 {
+						functionResponseContent := map[string]interface{}{
+							"parts": responseParts,
+							"role":  "function",
+						}
+						newContents = append(newContents, functionResponseContent)
+					}
+
+					// Remove this group as it's been satisfied
+					pendingGroups = append(pendingGroups[:i], pendingGroups[i+1:]...)
+					break
+				}
+			}
+
+			return true // Skip adding this content, responses are merged
+		}
+
+		// If this is a model with function calls, create a new group
+		if role == "model" {
+			var functionCallsInThisModel []gjson.Result
+			parts.ForEach(func(_, part gjson.Result) bool {
+				if part.Get("functionCall").Exists() {
+					functionCallsInThisModel = append(functionCallsInThisModel, part)
+				}
+				return true
+			})
+
+			if len(functionCallsInThisModel) > 0 {
+				// Add the model content
+				var contentMap map[string]interface{}
+				errUnmarshal := json.Unmarshal([]byte(value.Raw), &contentMap)
+				if errUnmarshal != nil {
+					log.Warnf("failed to unmarshal model content: %v\n", errUnmarshal)
+					return true
+				}
+				newContents = append(newContents, contentMap)
+
+				// Create a new group for tracking responses
+				group := &FunctionCallGroup{
+					ModelContent:    contentMap,
+					FunctionCalls:   functionCallsInThisModel,
+					ResponsesNeeded: len(functionCallsInThisModel),
+				}
+				pendingGroups = append(pendingGroups, group)
+			} else {
+				// Regular model content without function calls
+				var contentMap map[string]interface{}
+				errUnmarshal := json.Unmarshal([]byte(value.Raw), &contentMap)
+				if errUnmarshal != nil {
+					log.Warnf("failed to unmarshal content: %v\n", errUnmarshal)
+					return true
+				}
+				newContents = append(newContents, contentMap)
+			}
+		} else {
+			// Non-model content (user, etc.)
+			var contentMap map[string]interface{}
+			errUnmarshal := json.Unmarshal([]byte(value.Raw), &contentMap)
+			if errUnmarshal != nil {
+				log.Warnf("failed to unmarshal content: %v\n", errUnmarshal)
+				return true
+			}
+			newContents = append(newContents, contentMap)
+		}
+
+		return true
+	})
+
+	// Handle any remaining pending groups with remaining responses
+	for _, group := range pendingGroups {
+		if len(collectedResponses) >= group.ResponsesNeeded {
+			groupResponses := collectedResponses[:group.ResponsesNeeded]
+			collectedResponses = collectedResponses[group.ResponsesNeeded:]
+
+			var responseParts []interface{}
+			for _, response := range groupResponses {
+				var responseMap map[string]interface{}
+				errUnmarshal := json.Unmarshal([]byte(response.Raw), &responseMap)
+				if errUnmarshal != nil {
+					log.Warnf("failed to unmarshal function response: %v\n", errUnmarshal)
+					continue
+				}
+				responseParts = append(responseParts, responseMap)
+			}
+
+			if len(responseParts) > 0 {
+				functionResponseContent := map[string]interface{}{
+					"parts": responseParts,
+					"role":  "function",
+				}
+				newContents = append(newContents, functionResponseContent)
+			}
+		}
+	}
+
+	// Update the original JSON with the new contents
+	result := input
+	newContentsJSON, _ := json.Marshal(newContents)
+	result, _ = sjson.Set(result, "request.contents", json.RawMessage(newContentsJSON))
+
+	return result, nil
+}

internal/translator/gemini-cli/openai/cli_openai_request.go

@@ -0,0 +1,239 @@
+// Package openai provides request translation functionality for OpenAI API.
+// It handles the conversion of OpenAI-compatible request formats to the internal
+// format expected by the backend client, including parsing messages, roles,
+// content types (text, image, file), and tool calls.
+package openai
+
+import (
+	"encoding/json"
+	"strings"
+
+	"github.com/luispater/CLIProxyAPI/internal/client"
+	"github.com/luispater/CLIProxyAPI/internal/misc"
+	log "github.com/sirupsen/logrus"
+	"github.com/tidwall/gjson"
+)
+
+// ConvertOpenAIChatRequestToCli translates a raw JSON request from an OpenAI-compatible format
+// to the internal format expected by the backend client. It parses messages,
+// roles, content types (text, image, file), and tool calls.
+//
+// This function handles the complex task of converting between the OpenAI message
+// format and the internal format used by the Gemini client. It processes different
+// message types (system, user, assistant, tool) and content types (text, images, files).
+//
+// Parameters:
+//   - rawJSON: The raw JSON bytes of the OpenAI-compatible request
+//
+// Returns:
+//   - string: The model name to use
+//   - *client.Content: System instruction content (if any)
+//   - []client.Content: The conversation contents in internal format
+//   - []client.ToolDeclaration: Tool declarations from the request
+func ConvertOpenAIChatRequestToCli(rawJSON []byte) (string, *client.Content, []client.Content, []client.ToolDeclaration) {
+	// Extract the model name from the request, defaulting to "gemini-2.5-pro".
+	modelName := "gemini-2.5-pro"
+	modelResult := gjson.GetBytes(rawJSON, "model")
+	if modelResult.Type == gjson.String {
+		modelName = modelResult.String()
+	}
+
+	// Initialize data structures for processing conversation messages
+	// contents: stores the processed conversation history
+	// systemInstruction: stores system-level instructions separate from conversation
+	contents := make([]client.Content, 0)
+	var systemInstruction *client.Content
+	messagesResult := gjson.GetBytes(rawJSON, "messages")
+
+	// Pre-process tool responses to create a lookup map
+	// This first pass collects all tool responses so they can be matched with their corresponding calls
+	toolItems := make(map[string]*client.FunctionResponse)
+	if messagesResult.IsArray() {
+		messagesResults := messagesResult.Array()
+		for i := 0; i < len(messagesResults); i++ {
+			messageResult := messagesResults[i]
+			roleResult := messageResult.Get("role")
+			if roleResult.Type != gjson.String {
+				continue
+			}
+			contentResult := messageResult.Get("content")
+
+			// Extract tool responses for later matching with function calls
+			if roleResult.String() == "tool" {
+				toolCallID := messageResult.Get("tool_call_id").String()
+				if toolCallID != "" {
+					var responseData string
+					// Handle both string and object-based tool response formats
+					if contentResult.Type == gjson.String {
+						responseData = contentResult.String()
+					} else if contentResult.IsObject() && contentResult.Get("type").String() == "text" {
+						responseData = contentResult.Get("text").String()
+					}
+
+					// Clean up tool call ID by removing timestamp suffix
+					// This normalizes IDs for consistent matching between calls and responses
+					toolCallIDs := strings.Split(toolCallID, "-")
+					strings.Join(toolCallIDs, "-")
+					newToolCallID := strings.Join(toolCallIDs[:len(toolCallIDs)-1], "-")
+
+					// Create function response object with normalized ID and response data
+					functionResponse := client.FunctionResponse{Name: newToolCallID, Response: map[string]interface{}{"result": responseData}}
+					toolItems[toolCallID] = &functionResponse
+				}
+			}
+		}
+	}
+
+	if messagesResult.IsArray() {
+		messagesResults := messagesResult.Array()
+		for i := 0; i < len(messagesResults); i++ {
+			messageResult := messagesResults[i]
+			roleResult := messageResult.Get("role")
+			contentResult := messageResult.Get("content")
+			if roleResult.Type != gjson.String {
+				continue
+			}
+
+			switch roleResult.String() {
+			// System messages are converted to a user message followed by a model's acknowledgment.
+			case "system":
+				if contentResult.Type == gjson.String {
+					systemInstruction = &client.Content{Role: "user", Parts: []client.Part{{Text: contentResult.String()}}}
+				} else if contentResult.IsObject() {
+					// Handle object-based system messages.
+					if contentResult.Get("type").String() == "text" {
+						systemInstruction = &client.Content{Role: "user", Parts: []client.Part{{Text: contentResult.Get("text").String()}}}
+					}
+				}
+			// User messages can contain simple text or a multi-part body.
+			case "user":
+				if contentResult.Type == gjson.String {
+					contents = append(contents, client.Content{Role: "user", Parts: []client.Part{{Text: contentResult.String()}}})
+				} else if contentResult.IsArray() {
+					// Handle multi-part user messages (text, images, files).
+					contentItemResults := contentResult.Array()
+					parts := make([]client.Part, 0)
+					for j := 0; j < len(contentItemResults); j++ {
+						contentItemResult := contentItemResults[j]
+						contentTypeResult := contentItemResult.Get("type")
+						switch contentTypeResult.String() {
+						case "text":
+							parts = append(parts, client.Part{Text: contentItemResult.Get("text").String()})
+						case "image_url":
+							// Parse data URI for images.
+							imageURL := contentItemResult.Get("image_url.url").String()
+							if len(imageURL) > 5 {
+								imageURLs := strings.SplitN(imageURL[5:], ";", 2)
+								if len(imageURLs) == 2 && len(imageURLs[1]) > 7 {
+									parts = append(parts, client.Part{InlineData: &client.InlineData{
+										MimeType: imageURLs[0],
+										Data:     imageURLs[1][7:],
+									}})
+								}
+							}
+						case "file":
+							// Handle file attachments by determining MIME type from extension.
+							filename := contentItemResult.Get("file.filename").String()
+							fileData := contentItemResult.Get("file.file_data").String()
+							ext := ""
+							if split := strings.Split(filename, "."); len(split) > 1 {
+								ext = split[len(split)-1]
+							}
+							if mimeType, ok := misc.MimeTypes[ext]; ok {
+								parts = append(parts, client.Part{InlineData: &client.InlineData{
+									MimeType: mimeType,
+									Data:     fileData,
+								}})
+							} else {
+								log.Warnf("Unknown file name extension '%s' at index %d, skipping file", ext, j)
+							}
+						}
+					}
+					contents = append(contents, client.Content{Role: "user", Parts: parts})
+				}
+			// Assistant messages can contain text responses or tool calls
+			// In the internal format, assistant messages are converted to "model" role
+			case "assistant":
+				if contentResult.Type == gjson.String {
+					// Simple text response from the assistant
+					contents = append(contents, client.Content{Role: "model", Parts: []client.Part{{Text: contentResult.String()}}})
+				} else if !contentResult.Exists() || contentResult.Type == gjson.Null {
+					// Handle complex tool calls made by the assistant
+					// This processes function calls and matches them with their responses
+					functionIDs := make([]string, 0)
+					toolCallsResult := messageResult.Get("tool_calls")
+					if toolCallsResult.IsArray() {
+						parts := make([]client.Part, 0)
+						tcsResult := toolCallsResult.Array()
+
+						// Process each tool call in the assistant's message
+						for j := 0; j < len(tcsResult); j++ {
+							tcResult := tcsResult[j]
+
+							// Extract function call details
+							functionID := tcResult.Get("id").String()
+							functionIDs = append(functionIDs, functionID)
+
+							functionName := tcResult.Get("function.name").String()
+							functionArgs := tcResult.Get("function.arguments").String()
+
+							// Parse function arguments from JSON string to map
+							var args map[string]any
+							if err := json.Unmarshal([]byte(functionArgs), &args); err == nil {
+								parts = append(parts, client.Part{
+									FunctionCall: &client.FunctionCall{
+										Name: functionName,
+										Args: args,
+									},
+								})
+							}
+						}
+
+						// Add the model's function calls to the conversation
+						if len(parts) > 0 {
+							contents = append(contents, client.Content{
+								Role: "model", Parts: parts,
+							})
+
+							// Create a separate tool response message with the collected responses
+							// This matches function calls with their corresponding responses
+							toolParts := make([]client.Part, 0)
+							for _, functionID := range functionIDs {
+								if functionResponse, ok := toolItems[functionID]; ok {
+									toolParts = append(toolParts, client.Part{FunctionResponse: functionResponse})
+								}
+							}
+							// Add the tool responses as a separate message in the conversation
+							contents = append(contents, client.Content{Role: "tool", Parts: toolParts})
+						}
+					}
+				}
+			}
+		}
+	}
+
+	// Translate the tool declarations from the request.
+	var tools []client.ToolDeclaration
+	toolsResult := gjson.GetBytes(rawJSON, "tools")
+	if toolsResult.IsArray() {
+		tools = make([]client.ToolDeclaration, 1)
+		tools[0].FunctionDeclarations = make([]any, 0)
+		toolsResults := toolsResult.Array()
+		for i := 0; i < len(toolsResults); i++ {
+			toolResult := toolsResults[i]
+			if toolResult.Get("type").String() == "function" {
+				functionTypeResult := toolResult.Get("function")
+				if functionTypeResult.Exists() && functionTypeResult.IsObject() {
+					var functionDeclaration any
+					if err := json.Unmarshal([]byte(functionTypeResult.Raw), &functionDeclaration); err == nil {
+						tools[0].FunctionDeclarations = append(tools[0].FunctionDeclarations, functionDeclaration)
+					}
+				}
+			}
+		}
+	} else {
+		tools = make([]client.ToolDeclaration, 0)
+	}
+
+	return modelName, systemInstruction, contents, tools
+}

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

@@ -0,0 +1,197 @@
+// Package openai provides response translation functionality for converting between
+// different API response formats and OpenAI-compatible formats. It handles both
+// streaming and non-streaming responses, transforming backend client responses
+// into OpenAI Server-Sent Events (SSE) format and standard JSON response formats.
+// The package supports content translation, function calls, usage metadata,
+// and various response attributes while maintaining compatibility with OpenAI API
+// specifications.
+package openai
+
+import (
+	"fmt"
+	"time"
+
+	"github.com/tidwall/gjson"
+	"github.com/tidwall/sjson"
+)
+
+// ConvertCliResponseToOpenAIChat translates a single chunk of a streaming response from the
+// backend client format to the OpenAI Server-Sent Events (SSE) format.
+// It returns an empty string if the chunk contains no useful data.
+func ConvertCliResponseToOpenAIChat(rawJSON []byte, unixTimestamp int64, isGlAPIKey bool) string {
+	if isGlAPIKey {
+		rawJSON, _ = sjson.SetRawBytes(rawJSON, "response", rawJSON)
+	}
+
+	// Initialize the OpenAI SSE template.
+	template := `{"id":"","object":"chat.completion.chunk","created":12345,"model":"model","choices":[{"index":0,"delta":{"role":null,"content":null,"reasoning_content":null,"tool_calls":null},"finish_reason":null,"native_finish_reason":null}]}`
+
+	// Extract and set the model version.
+	if modelVersionResult := gjson.GetBytes(rawJSON, "response.modelVersion"); modelVersionResult.Exists() {
+		template, _ = sjson.Set(template, "model", modelVersionResult.String())
+	}
+
+	// Extract and set the creation timestamp.
+	if createTimeResult := gjson.GetBytes(rawJSON, "response.createTime"); createTimeResult.Exists() {
+		t, err := time.Parse(time.RFC3339Nano, createTimeResult.String())
+		if err == nil {
+			unixTimestamp = t.Unix()
+		}
+		template, _ = sjson.Set(template, "created", unixTimestamp)
+	} else {
+		template, _ = sjson.Set(template, "created", unixTimestamp)
+	}
+
+	// Extract and set the response ID.
+	if responseIDResult := gjson.GetBytes(rawJSON, "response.responseId"); responseIDResult.Exists() {
+		template, _ = sjson.Set(template, "id", responseIDResult.String())
+	}
+
+	// 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())
+	}
+
+	// Extract and set usage metadata (token counts).
+	if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
+		if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
+			template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
+		}
+		if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
+			template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
+		}
+		promptTokenCount := usageResult.Get("promptTokenCount").Int()
+		thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
+		template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
+		if thoughtsTokenCount > 0 {
+			template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
+		}
+	}
+
+	// Process the main content part of the response.
+	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]
+			partTextResult := partResult.Get("text")
+			functionCallResult := partResult.Get("functionCall")
+
+			if partTextResult.Exists() {
+				// Handle text content, distinguishing between regular content and reasoning/thoughts.
+				if partResult.Get("thought").Bool() {
+					template, _ = sjson.Set(template, "choices.0.delta.reasoning_content", partTextResult.String())
+				} else {
+					template, _ = sjson.Set(template, "choices.0.delta.content", partTextResult.String())
+				}
+				template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
+			} else if functionCallResult.Exists() {
+				// Handle function call content.
+				toolCallsResult := gjson.Get(template, "choices.0.delta.tool_calls")
+				if !toolCallsResult.Exists() || !toolCallsResult.IsArray() {
+					template, _ = sjson.SetRaw(template, "choices.0.delta.tool_calls", `[]`)
+				}
+
+				functionCallTemplate := `{"id": "","type": "function","function": {"name": "","arguments": ""}}`
+				fcName := functionCallResult.Get("name").String()
+				functionCallTemplate, _ = sjson.Set(functionCallTemplate, "id", fmt.Sprintf("%s-%d", fcName, time.Now().UnixNano()))
+				functionCallTemplate, _ = sjson.Set(functionCallTemplate, "function.name", fcName)
+				if fcArgsResult := functionCallResult.Get("args"); fcArgsResult.Exists() {
+					functionCallTemplate, _ = sjson.Set(functionCallTemplate, "function.arguments", fcArgsResult.Raw)
+				}
+				template, _ = sjson.Set(template, "choices.0.delta.role", "assistant")
+				template, _ = sjson.SetRaw(template, "choices.0.message.tool_calls.-1", functionCallTemplate)
+			}
+		}
+	}
+
+	return template
+}
+
+// ConvertCliResponseToOpenAIChatNonStream aggregates response from the backend client
+// convert a single, non-streaming OpenAI-compatible JSON response.
+func ConvertCliResponseToOpenAIChatNonStream(rawJSON []byte, unixTimestamp int64, isGlAPIKey bool) string {
+	if isGlAPIKey {
+		rawJSON, _ = sjson.SetRawBytes(rawJSON, "response", rawJSON)
+	}
+	template := `{"id":"","object":"chat.completion","created":123456,"model":"model","choices":[{"index":0,"message":{"role":"assistant","content":null,"reasoning_content":null,"tool_calls":null},"finish_reason":null,"native_finish_reason":null}]}`
+	if modelVersionResult := gjson.GetBytes(rawJSON, "response.modelVersion"); modelVersionResult.Exists() {
+		template, _ = sjson.Set(template, "model", modelVersionResult.String())
+	}
+
+	if createTimeResult := gjson.GetBytes(rawJSON, "response.createTime"); createTimeResult.Exists() {
+		t, err := time.Parse(time.RFC3339Nano, createTimeResult.String())
+		if err == nil {
+			unixTimestamp = t.Unix()
+		}
+		template, _ = sjson.Set(template, "created", unixTimestamp)
+	} else {
+		template, _ = sjson.Set(template, "created", unixTimestamp)
+	}
+
+	if responseIDResult := gjson.GetBytes(rawJSON, "response.responseId"); responseIDResult.Exists() {
+		template, _ = sjson.Set(template, "id", responseIDResult.String())
+	}
+
+	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())
+	}
+
+	if usageResult := gjson.GetBytes(rawJSON, "response.usageMetadata"); usageResult.Exists() {
+		if candidatesTokenCountResult := usageResult.Get("candidatesTokenCount"); candidatesTokenCountResult.Exists() {
+			template, _ = sjson.Set(template, "usage.completion_tokens", candidatesTokenCountResult.Int())
+		}
+		if totalTokenCountResult := usageResult.Get("totalTokenCount"); totalTokenCountResult.Exists() {
+			template, _ = sjson.Set(template, "usage.total_tokens", totalTokenCountResult.Int())
+		}
+		promptTokenCount := usageResult.Get("promptTokenCount").Int()
+		thoughtsTokenCount := usageResult.Get("thoughtsTokenCount").Int()
+		template, _ = sjson.Set(template, "usage.prompt_tokens", promptTokenCount+thoughtsTokenCount)
+		if thoughtsTokenCount > 0 {
+			template, _ = sjson.Set(template, "usage.completion_tokens_details.reasoning_tokens", thoughtsTokenCount)
+		}
+	}
+
+	// Process the main content part of the response.
+	partsResult := gjson.GetBytes(rawJSON, "response.candidates.0.content.parts")
+	if partsResult.IsArray() {
+		partsResults := partsResult.Array()
+		for i := 0; i < len(partsResults); i++ {
+			partResult := partsResults[i]
+			partTextResult := partResult.Get("text")
+			functionCallResult := partResult.Get("functionCall")
+
+			if partTextResult.Exists() {
+				// Append text content, distinguishing between regular content and reasoning.
+				if partResult.Get("thought").Bool() {
+					template, _ = sjson.Set(template, "choices.0.message.reasoning_content", partTextResult.String())
+				} else {
+					template, _ = sjson.Set(template, "choices.0.message.content", partTextResult.String())
+				}
+				template, _ = sjson.Set(template, "choices.0.message.role", "assistant")
+			} else if functionCallResult.Exists() {
+				// Append function call content to the tool_calls array.
+				toolCallsResult := gjson.Get(template, "choices.0.message.tool_calls")
+				if !toolCallsResult.Exists() || !toolCallsResult.IsArray() {
+					template, _ = sjson.SetRaw(template, "choices.0.message.tool_calls", `[]`)
+				}
+				functionCallItemTemplate := `{"id": "","type": "function","function": {"name": "","arguments": ""}}`
+				fcName := functionCallResult.Get("name").String()
+				functionCallItemTemplate, _ = sjson.Set(functionCallItemTemplate, "id", fmt.Sprintf("%s-%d", fcName, time.Now().UnixNano()))
+				functionCallItemTemplate, _ = sjson.Set(functionCallItemTemplate, "function.name", fcName)
+				if fcArgsResult := functionCallResult.Get("args"); fcArgsResult.Exists() {
+					functionCallItemTemplate, _ = sjson.Set(functionCallItemTemplate, "function.arguments", fcArgsResult.Raw)
+				}
+				template, _ = sjson.Set(template, "choices.0.message.role", "assistant")
+				template, _ = sjson.SetRaw(template, "choices.0.message.tool_calls.-1", functionCallItemTemplate)
+			} else {
+				// If no usable content is found, return an empty string.
+				return ""
+			}
+		}
+	}
+
+	return template
+}