Files
Calcium-Ion 86ac0f7745 refactor: extract protocol conversion layer into standalone relaykit module (#6369)
* test(relayconvert): add golden snapshot matrix and relaykit boundary guard

Phase 0 of the relaykit extraction plan: pin byte-level output of every
registered (from,to) request/response/stream conversion route, and
forbid kit-bound packages from growing host-only imports.

* wip(relayconvert): drop gin.Context from converter signatures; add convmeta draft

Phase 1 in progress: relayconvert now takes context.Context; host media
resolver adapts gin.Context back at the service boundary.

* refactor(relayconvert): decouple converters from RelayInfo, gin, and settings

Phase 1 of the relaykit extraction plan:
- converters now depend on convmeta.Meta (implemented by RelayInfo) instead
  of *relaycommon.RelayInfo; ClaudeConvertInfo and the format guesser move
  to convmeta with aliases left behind
- host settings reach converters via a convmeta.Options snapshot built in
  RelayInfo.ConvOptions; no more model_setting/reasoning global reads inside
  the conversion layer
- effort-suffix helpers move to service/relayconvert/reasoning (old package
  forwards); chat-to-responses upgrade policy moves to service (host routing
  logic, not conversion)
- golden conversion matrix unchanged

* test(relayconvert): tighten boundary — kit packages now free of gin/setting imports

* refactor(dto): drop gin and logger dependencies

Phase 2 (part 1): dto.Request.IsStream now takes *http.Request instead of
*gin.Context (Gemini's impl reads query/path off the std request); dto's
three logger calls become common.SysError. Boundary test allowlist is now
empty — kit-bound packages import no gin/setting/logger/model.

* refactor(kit): extract dependency-free kitutil; dto/types/relayconvert stop importing common

Phase 2 of the relaykit extraction plan:
- new service/relayconvert/kitutil holds the pure helpers the kit needs
  (JSON wrappers, pointer/string/uuid/timestamp utils, MaskSensitiveInfo,
  pluggable LogInfo/LogError hooks, Debug flag)
- dto, types, and all relayconvert packages now use kitutil; their only
  remaining internal deps are dto/types/constant
- common keeps every original symbol (MaskSensitiveInfo delegates to
  kitutil) so host code is untouched; main.go routes kit logging into
  common.SysLog/SysError and mirrors DebugEnabled
- golden conversion matrix unchanged

* refactor(kit): move EndpointType/FinishReason to types; OpenRouter dialect via Options

Kit packages (dto/types/relayconvert/reasonmap) no longer import constant:
- EndpointType and finish-reason values live in types; constant re-exports
- the OpenRouter special-case in claude->openai request conversion reads
  Options.OpenRouterDialect, set by the host from the channel type;
  InitChannelMeta invalidates the cached snapshot on channel switch

* refactor: extract relaykit submodule (dto/types/relayconvert/reasonmap)

Phase 3 of the relaykit extraction plan:
- new go module github.com/QuantumNous/new-api/relaykit containing dto
  (minus task family), types, relayconvert (with convmeta/kitutil/reasoning),
  and reasonmap; host consumes it via require + replace, go.work for dev
- task-family dto (task/suno/midjourney/video) stays in the host dto
  package; dual-consumer host files alias it as taskdto
- relaykit builds and tests standalone (GOWORK=off): no host imports,
  no gin, no DB, no settings
- golden conversion matrix unchanged

* build(docker): copy relaykit/go.mod before go mod download

The local-replace submodule's go.mod must exist inside the build context
for the main module graph to resolve.

* fix: address relaykit extraction regressions

* fix: address relaykit review regressions

* docs: document Meta nil receiver contract

* fix(relaykit): fail OpenAI→Claude conversion without max_tokens; reject negative default_max_tokens

The Claude Messages API requires max_tokens (omitting it is a 400
"Field required"), but with a nil Options.Claude.DefaultMaxTokens hook
the converters silently emitted a request the upstream is guaranteed to
reject. Both OpenAI Chat and Responses → Claude conversions now return
sharedclaude.ErrMissingMaxTokens when no path (client value, default
hook, thinking-adapter floor) supplied one. Unreachable in the host,
which always configures the hook.

Host side, claude.default_max_tokens now rejects negative values at the
option API before persisting — they would wrap into huge unsigned values
during conversion. Zero stays allowed: the current API treats
max_tokens: 0 as cache pre-warming.

* fix: make Gemini safety settings read path race-free
2026-07-27 15:56:21 +08:00

213 lines
5.4 KiB
Go
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package service
import (
"bytes"
"fmt"
"image"
_ "image/gif"
_ "image/jpeg"
_ "image/png"
"io"
"net/http"
"strings"
"github.com/QuantumNous/new-api/common"
"github.com/QuantumNous/new-api/logger"
"github.com/QuantumNous/new-api/relaykit/types"
"github.com/gin-gonic/gin"
)
// GetFileTypeFromUrl 获取文件类型,返回 mime type 例如 image/jpeg, image/png, image/gif, image/bmp, image/tiff, application/pdf
// 如果获取失败,返回 application/octet-stream
func GetFileTypeFromUrl(c *gin.Context, url string, reason ...string) (string, error) {
response, err := DoDownloadRequest(url, []string{"get_mime_type", strings.Join(reason, ", ")}...)
if err != nil {
common.SysLog(fmt.Sprintf("fail to get file type from url: %s, error: %s", url, err.Error()))
return "", err
}
defer response.Body.Close()
if response.StatusCode != 200 {
logger.LogError(c, fmt.Sprintf("failed to download file from %s, status code: %d", url, response.StatusCode))
return "", fmt.Errorf("failed to download file, status code: %d", response.StatusCode)
}
if headerType := strings.TrimSpace(response.Header.Get("Content-Type")); headerType != "" {
if i := strings.Index(headerType, ";"); i != -1 {
headerType = headerType[:i]
}
if headerType != "application/octet-stream" {
return headerType, nil
}
}
if cd := response.Header.Get("Content-Disposition"); cd != "" {
parts := strings.Split(cd, ";")
for _, part := range parts {
part = strings.TrimSpace(part)
if strings.HasPrefix(strings.ToLower(part), "filename=") {
name := strings.TrimSpace(strings.TrimPrefix(part, "filename="))
if len(name) > 2 && name[0] == '"' && name[len(name)-1] == '"' {
name = name[1 : len(name)-1]
}
if dot := strings.LastIndex(name, "."); dot != -1 && dot+1 < len(name) {
ext := strings.ToLower(name[dot+1:])
if ext != "" {
mt := GetMimeTypeByExtension(ext)
if mt != "application/octet-stream" {
return mt, nil
}
}
}
break
}
}
}
cleanedURL := url
if q := strings.Index(cleanedURL, "?"); q != -1 {
cleanedURL = cleanedURL[:q]
}
if slash := strings.LastIndex(cleanedURL, "/"); slash != -1 && slash+1 < len(cleanedURL) {
last := cleanedURL[slash+1:]
if dot := strings.LastIndex(last, "."); dot != -1 && dot+1 < len(last) {
ext := strings.ToLower(last[dot+1:])
if ext != "" {
mt := GetMimeTypeByExtension(ext)
if mt != "application/octet-stream" {
return mt, nil
}
}
}
}
var readData []byte
limits := []int{512, 8 * 1024, 24 * 1024, 64 * 1024}
for _, limit := range limits {
logger.LogDebug(c, "Trying to read %d bytes to determine file type", limit)
if len(readData) < limit {
need := limit - len(readData)
tmp := make([]byte, need)
n, _ := io.ReadFull(response.Body, tmp)
if n > 0 {
readData = append(readData, tmp[:n]...)
}
}
if len(readData) == 0 {
continue
}
sniffed := http.DetectContentType(readData)
if sniffed != "" && sniffed != "application/octet-stream" {
return sniffed, nil
}
// Try HEIF/HEIC detection (Go standard library doesn't recognize it)
if heifMime := detectHEIF(readData); heifMime != "" {
return heifMime, nil
}
if _, format, err := image.DecodeConfig(bytes.NewReader(readData)); err == nil {
switch strings.ToLower(format) {
case "jpeg", "jpg":
return "image/jpeg", nil
case "png":
return "image/png", nil
case "gif":
return "image/gif", nil
case "bmp":
return "image/bmp", nil
case "tiff":
return "image/tiff", nil
default:
if format != "" {
return "image/" + strings.ToLower(format), nil
}
}
}
}
// Fallback
return "application/octet-stream", nil
}
// GetFileBase64FromUrl 从 URL 获取文件的 base64 编码数据
// Deprecated: 请使用 GetBase64Data 配合 types.NewURLFileSource 替代
// 此函数保留用于向后兼容,内部已重构为调用统一的文件服务
func GetFileBase64FromUrl(c *gin.Context, url string, reason ...string) (*types.LocalFileData, error) {
source := types.NewURLFileSource(url)
cachedData, err := LoadFileSource(c, source, reason...)
if err != nil {
return nil, err
}
// 转换为旧的 LocalFileData 格式以保持兼容
base64Data, err := cachedData.GetBase64Data()
if err != nil {
return nil, err
}
return &types.LocalFileData{
Base64Data: base64Data,
MimeType: cachedData.MimeType,
Size: cachedData.Size,
Url: url,
}, nil
}
func GetMimeTypeByExtension(ext string) string {
// Convert to lowercase for case-insensitive comparison
ext = strings.ToLower(ext)
switch ext {
// Text files
case "txt", "md", "markdown", "csv", "json", "xml", "html", "htm":
return "text/plain"
// Image files
case "jpg", "jpeg":
return "image/jpeg"
case "png":
return "image/png"
case "gif":
return "image/gif"
case "jfif":
return "image/jpeg"
case "heic":
return "image/heic"
case "heif":
return "image/heif"
// Audio files
case "mp3":
return "audio/mp3"
case "wav":
return "audio/wav"
case "mpeg":
return "audio/mpeg"
// Video files
case "mp4":
return "video/mp4"
case "wmv":
return "video/wmv"
case "flv":
return "video/flv"
case "mov":
return "video/mov"
case "mpg":
return "video/mpg"
case "avi":
return "video/avi"
case "mpegps":
return "video/mpegps"
// Document files
case "pdf":
return "application/pdf"
default:
return "application/octet-stream" // Default for unknown types
}
}