Add openai codex support

This commit is contained in:
Luis Pater
2025-08-08 15:44:00 +08:00
parent d2394b0be9
commit de7b8501cc
57 changed files with 7488 additions and 2478 deletions

View File

@@ -0,0 +1,199 @@
// 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 (
"crypto/rand"
"math/big"
"strings"
"github.com/luispater/CLIProxyAPI/internal/misc"
"github.com/tidwall/gjson"
"github.com/tidwall/sjson"
)
// PrepareClaudeRequest 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 ConvertGeminiRequestToCodex(rawJSON []byte) string {
// Base template
out := `{"model":"","instructions":"","input":[]}`
// Inject standard Codex instructions
instructions := misc.CodexInstructions
out, _ = sjson.SetRaw(out, "instructions", instructions)
root := gjson.ParseBytes(rawJSON)
// helper for generating paired call IDs in the form: call_<alphanum>
// Gemini uses sequential pairing across possibly multiple in-flight
// functionCalls, so we keep a FIFO queue of generated call IDs and
// consume them in order when functionResponses arrive.
var pendingCallIDs []string
// genCallID creates a random call id like: call_<8chars>
genCallID := func() string {
const letters = "abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ0123456789"
var b strings.Builder
// 8 chars random suffix
for i := 0; i < 24; i++ {
n, _ := rand.Int(rand.Reader, big.NewInt(int64(len(letters))))
b.WriteByte(letters[n.Int64()])
}
return "call_" + b.String()
}
// Model
if v := root.Get("model"); v.Exists() {
out, _ = sjson.Set(out, "model", v.Value())
}
// System instruction -> as a user message with input_text parts
sysParts := root.Get("system_instruction.parts")
if sysParts.IsArray() {
msg := `{"type":"message","role":"user","content":[]}`
arr := sysParts.Array()
for i := 0; i < len(arr); i++ {
p := arr[i]
if t := p.Get("text"); t.Exists() {
part := `{}`
part, _ = sjson.Set(part, "type", "input_text")
part, _ = sjson.Set(part, "text", t.String())
msg, _ = sjson.SetRaw(msg, "content.-1", part)
}
}
if len(gjson.Get(msg, "content").Array()) > 0 {
out, _ = sjson.SetRaw(out, "input.-1", msg)
}
}
// Contents -> messages and function calls/results
contents := root.Get("contents")
if contents.IsArray() {
items := contents.Array()
for i := 0; i < len(items); i++ {
item := items[i]
role := item.Get("role").String()
if role == "model" {
role = "assistant"
}
parts := item.Get("parts")
if !parts.IsArray() {
continue
}
parr := parts.Array()
for j := 0; j < len(parr); j++ {
p := parr[j]
// text part
if t := p.Get("text"); t.Exists() {
msg := `{"type":"message","role":"","content":[]}`
msg, _ = sjson.Set(msg, "role", role)
partType := "input_text"
if role == "assistant" {
partType = "output_text"
}
part := `{}`
part, _ = sjson.Set(part, "type", partType)
part, _ = sjson.Set(part, "text", t.String())
msg, _ = sjson.SetRaw(msg, "content.-1", part)
out, _ = sjson.SetRaw(out, "input.-1", msg)
continue
}
// function call from model
if fc := p.Get("functionCall"); fc.Exists() {
fn := `{"type":"function_call"}`
if name := fc.Get("name"); name.Exists() {
fn, _ = sjson.Set(fn, "name", name.String())
}
if args := fc.Get("args"); args.Exists() {
fn, _ = sjson.Set(fn, "arguments", args.Raw)
}
// generate a paired random call_id and enqueue it so the
// corresponding functionResponse can pop the earliest id
// to preserve ordering when multiple calls are present.
id := genCallID()
fn, _ = sjson.Set(fn, "call_id", id)
pendingCallIDs = append(pendingCallIDs, id)
out, _ = sjson.SetRaw(out, "input.-1", fn)
continue
}
// function response from user
if fr := p.Get("functionResponse"); fr.Exists() {
fno := `{"type":"function_call_output"}`
// Prefer a string result if present; otherwise embed the raw response as a string
if res := fr.Get("response.result"); res.Exists() {
fno, _ = sjson.Set(fno, "output", res.String())
} else if resp := fr.Get("response"); resp.Exists() {
fno, _ = sjson.Set(fno, "output", resp.Raw)
}
// fno, _ = sjson.Set(fno, "call_id", "call_W6nRJzFXyPM2LFBbfo98qAbq")
// attach the oldest queued call_id to pair the response
// with its call. If the queue is empty, generate a new id.
var id string
if len(pendingCallIDs) > 0 {
id = pendingCallIDs[0]
// pop the first element
pendingCallIDs = pendingCallIDs[1:]
} else {
id = genCallID()
}
fno, _ = sjson.Set(fno, "call_id", id)
out, _ = sjson.SetRaw(out, "input.-1", fno)
continue
}
}
}
}
// Tools mapping: Gemini functionDeclarations -> Codex tools
tools := root.Get("tools")
if tools.IsArray() {
out, _ = sjson.SetRaw(out, "tools", `[]`)
out, _ = sjson.Set(out, "tool_choice", "auto")
tarr := tools.Array()
for i := 0; i < len(tarr); i++ {
td := tarr[i]
fns := td.Get("functionDeclarations")
if !fns.IsArray() {
continue
}
farr := fns.Array()
for j := 0; j < len(farr); j++ {
fn := farr[j]
tool := `{}`
tool, _ = sjson.Set(tool, "type", "function")
if v := fn.Get("name"); v.Exists() {
tool, _ = sjson.Set(tool, "name", v.String())
}
if v := fn.Get("description"); v.Exists() {
tool, _ = sjson.Set(tool, "description", v.String())
}
if prm := fn.Get("parameters"); prm.Exists() {
// Remove optional $schema field if present
cleaned := prm.Raw
cleaned, _ = sjson.Delete(cleaned, "$schema")
cleaned, _ = sjson.Set(cleaned, "additionalProperties", false)
tool, _ = sjson.SetRaw(tool, "parameters", cleaned)
}
tool, _ = sjson.Set(tool, "strict", false)
out, _ = sjson.SetRaw(out, "tools.-1", tool)
}
}
}
// Fixed flags aligning with Codex expectations
out, _ = sjson.Set(out, "parallel_tool_calls", true)
out, _ = sjson.Set(out, "reasoning.effort", "low")
out, _ = sjson.Set(out, "reasoning.summary", "auto")
out, _ = sjson.Set(out, "stream", true)
out, _ = sjson.Set(out, "store", false)
out, _ = sjson.Set(out, "include", []string{"reasoning.encrypted_content"})
return out
}

View File

@@ -0,0 +1,251 @@
// Package code provides response translation functionality for Gemini API.
// This package handles the conversion of Codex backend responses into Gemini-compatible
// JSON format, transforming streaming events into single-line JSON responses that include
// thinking content, regular text content, and function calls in the format expected by
// Gemini API clients.
package code
import (
"encoding/json"
"time"
"github.com/tidwall/gjson"
"github.com/tidwall/sjson"
)
type ConvertCodexResponseToGeminiParams struct {
Model string
CreatedAt int64
ResponseID string
LastStorageOutput string
}
// ConvertCodexResponseToGemini converts Codex streaming response format to Gemini single-line JSON format.
// This function processes various Codex event types and transforms them into Gemini-compatible JSON responses.
// It handles thinking content, regular text content, and function calls, outputting single-line JSON
// that matches the Gemini API response format.
// The lastEventType parameter tracks the previous event type to handle consecutive function calls properly.
func ConvertCodexResponseToGemini(rawJSON []byte, param *ConvertCodexResponseToGeminiParams) []string {
rootResult := gjson.ParseBytes(rawJSON)
typeResult := rootResult.Get("type")
typeStr := typeResult.String()
// Base Gemini response template
template := `{"candidates":[{"content":{"role":"model","parts":[]}}],"usageMetadata":{"trafficType":"PROVISIONED_THROUGHPUT"},"modelVersion":"gemini-2.5-pro","createTime":"2025-08-15T02:52:03.884209Z","responseId":"06CeaPH7NaCU48APvNXDyA4"}`
if param.LastStorageOutput != "" && typeStr == "response.output_item.done" {
template = param.LastStorageOutput
} else {
template, _ = sjson.Set(template, "modelVersion", param.Model)
createdAtResult := rootResult.Get("response.created_at")
if createdAtResult.Exists() {
param.CreatedAt = createdAtResult.Int()
template, _ = sjson.Set(template, "createTime", time.Unix(param.CreatedAt, 0).Format(time.RFC3339Nano))
}
template, _ = sjson.Set(template, "responseId", param.ResponseID)
}
// Handle function call completion
if typeStr == "response.output_item.done" {
itemResult := rootResult.Get("item")
itemType := itemResult.Get("type").String()
if itemType == "function_call" {
// Create function call part
functionCall := `{"functionCall":{"name":"","args":{}}}`
functionCall, _ = sjson.Set(functionCall, "functionCall.name", itemResult.Get("name").String())
// Parse and set arguments
argsStr := itemResult.Get("arguments").String()
if argsStr != "" {
argsResult := gjson.Parse(argsStr)
if argsResult.IsObject() {
functionCall, _ = sjson.SetRaw(functionCall, "functionCall.args", argsStr)
}
}
template, _ = sjson.SetRaw(template, "candidates.0.content.parts.-1", functionCall)
template, _ = sjson.Set(template, "candidates.0.finishReason", "STOP")
param.LastStorageOutput = template
// Use this return to storage message
return []string{}
}
}
if typeStr == "response.created" { // Handle response creation - set model and response ID
template, _ = sjson.Set(template, "modelVersion", rootResult.Get("response.model").String())
template, _ = sjson.Set(template, "responseId", rootResult.Get("response.id").String())
param.ResponseID = rootResult.Get("response.id").String()
} else if typeStr == "response.reasoning_summary_text.delta" { // Handle reasoning/thinking content delta
part := `{"thought":true,"text":""}`
part, _ = sjson.Set(part, "text", rootResult.Get("delta").String())
template, _ = sjson.SetRaw(template, "candidates.0.content.parts.-1", part)
} else if typeStr == "response.output_text.delta" { // Handle regular text content delta
part := `{"text":""}`
part, _ = sjson.Set(part, "text", rootResult.Get("delta").String())
template, _ = sjson.SetRaw(template, "candidates.0.content.parts.-1", part)
} else if typeStr == "response.completed" { // Handle response completion with usage metadata
template, _ = sjson.Set(template, "usageMetadata.promptTokenCount", rootResult.Get("response.usage.input_tokens").Int())
template, _ = sjson.Set(template, "usageMetadata.candidatesTokenCount", rootResult.Get("response.usage.output_tokens").Int())
totalTokens := rootResult.Get("response.usage.input_tokens").Int() + rootResult.Get("response.usage.output_tokens").Int()
template, _ = sjson.Set(template, "usageMetadata.totalTokenCount", totalTokens)
} else {
return []string{}
}
if param.LastStorageOutput != "" {
return []string{param.LastStorageOutput, template}
} else {
return []string{template}
}
}
// ConvertCodexResponseToGeminiNonStream converts a completed Codex response to Gemini non-streaming format.
// This function processes the final response.completed event and transforms it into a complete
// Gemini-compatible JSON response that includes all content parts, function calls, and usage metadata.
func ConvertCodexResponseToGeminiNonStream(rawJSON []byte, model string) string {
rootResult := gjson.ParseBytes(rawJSON)
// Verify this is a response.completed event
if rootResult.Get("type").String() != "response.completed" {
return ""
}
// Base Gemini response template for non-streaming
template := `{"candidates":[{"content":{"role":"model","parts":[]},"finishReason":"STOP"}],"usageMetadata":{"trafficType":"PROVISIONED_THROUGHPUT"},"modelVersion":"","createTime":"","responseId":""}`
// Set model version
template, _ = sjson.Set(template, "modelVersion", model)
// Set response metadata from the completed response
responseData := rootResult.Get("response")
if responseData.Exists() {
// Set response ID
if responseId := responseData.Get("id"); responseId.Exists() {
template, _ = sjson.Set(template, "responseId", responseId.String())
}
// Set creation time
if createdAt := responseData.Get("created_at"); createdAt.Exists() {
template, _ = sjson.Set(template, "createTime", time.Unix(createdAt.Int(), 0).Format(time.RFC3339Nano))
}
// Set usage metadata
if usage := responseData.Get("usage"); usage.Exists() {
inputTokens := usage.Get("input_tokens").Int()
outputTokens := usage.Get("output_tokens").Int()
totalTokens := inputTokens + outputTokens
template, _ = sjson.Set(template, "usageMetadata.promptTokenCount", inputTokens)
template, _ = sjson.Set(template, "usageMetadata.candidatesTokenCount", outputTokens)
template, _ = sjson.Set(template, "usageMetadata.totalTokenCount", totalTokens)
}
// Process output content to build parts array
var parts []interface{}
hasToolCall := false
var pendingFunctionCalls []interface{}
flushPendingFunctionCalls := func() {
if len(pendingFunctionCalls) > 0 {
// Add all pending function calls as individual parts
// This maintains the original Gemini API format while ensuring consecutive calls are grouped together
for _, fc := range pendingFunctionCalls {
parts = append(parts, fc)
}
pendingFunctionCalls = nil
}
}
if output := responseData.Get("output"); output.Exists() && output.IsArray() {
output.ForEach(func(key, value gjson.Result) bool {
itemType := value.Get("type").String()
switch itemType {
case "reasoning":
// Flush any pending function calls before adding non-function content
flushPendingFunctionCalls()
// Add thinking content
if content := value.Get("content"); content.Exists() {
part := map[string]interface{}{
"thought": true,
"text": content.String(),
}
parts = append(parts, part)
}
case "message":
// Flush any pending function calls before adding non-function content
flushPendingFunctionCalls()
// Add regular text content
if content := value.Get("content"); content.Exists() && content.IsArray() {
content.ForEach(func(_, contentItem gjson.Result) bool {
if contentItem.Get("type").String() == "output_text" {
if text := contentItem.Get("text"); text.Exists() {
part := map[string]interface{}{
"text": text.String(),
}
parts = append(parts, part)
}
}
return true
})
}
case "function_call":
// Collect function call for potential merging with consecutive ones
hasToolCall = true
functionCall := map[string]interface{}{
"functionCall": map[string]interface{}{
"name": value.Get("name").String(),
"args": map[string]interface{}{},
},
}
// Parse and set arguments
if argsStr := value.Get("arguments").String(); argsStr != "" {
argsResult := gjson.Parse(argsStr)
if argsResult.IsObject() {
var args map[string]interface{}
if err := json.Unmarshal([]byte(argsStr), &args); err == nil {
functionCall["functionCall"].(map[string]interface{})["args"] = args
}
}
}
pendingFunctionCalls = append(pendingFunctionCalls, functionCall)
}
return true
})
// Handle any remaining pending function calls at the end
flushPendingFunctionCalls()
}
// Set the parts array
if len(parts) > 0 {
template, _ = sjson.SetRaw(template, "candidates.0.content.parts", mustMarshalJSON(parts))
}
// Set finish reason based on whether there were tool calls
if hasToolCall {
template, _ = sjson.Set(template, "candidates.0.finishReason", "STOP")
} else {
template, _ = sjson.Set(template, "candidates.0.finishReason", "STOP")
}
}
return template
}
// mustMarshalJSON marshals data to JSON, panicking on error (should not happen with valid data)
func mustMarshalJSON(v interface{}) string {
data, err := json.Marshal(v)
if err != nil {
panic(err)
}
return string(data)
}