feat: 三协议互转网关 + 鉴权修复 + 管理端增强

后端
- 新增 proxy/convert 三协议(chat/messages/responses)请求、响应与 SSE 流式互转,
  以 Chat 为中间模型;usage.go 统一提取三协议 token 用量(含单测)
- gateway: 跨协议调度(渠道未声明客户端协议时转为渠道首选格式),
  streamResponse 按 \n\n 分块逐行转换直通,bufferResponse 转换失败时剥非 JSON 前缀
- gateway: 新增 SetUsageRecorder 注入异步用量记录器
- auth_llm: 修复 key_prefix 查询长度错配([:8] vs 存储的 [:12])导致全部 401;
  修复长度 8-11 的 key 切片越界 panic;统一 unauthorized 响应
- usage: 日报表改为增量累加 upsert,避免多次 flush 互相清零;记录协议/错误码/时延等字段
- channel: 新增渠道并发槽 TryAcquire;健康检查支持可配置参数
- api: 新增 admin 渠道/模型/系统配置管理端点(旧端点保留兼容)

前端
- 新增渠道管理、模型管理、系统配置视图与 ChannelModelsDrawer
- 新增 ui 基础组件(Button/Badge/Input/Modal)与 protocol.ts
- 调整 Toast 样式、密钥页、路由菜单;dev 代理默认指向 3000 端口
This commit is contained in:
Sakurasan
2026-08-31 22:29:09 +08:00
parent e472ed93d5
commit f81b364436
34 changed files with 5171 additions and 179 deletions
+588
View File
@@ -0,0 +1,588 @@
package api
import (
"encoding/json"
"errors"
"fmt"
"io"
"net/http"
"strconv"
"strings"
"time"
"opencatd-open/internal/pkg/crypto"
"opencatd-open/internal/store"
"github.com/gin-gonic/gin"
)
// AdminChannels GET /api/admin/channels — 渠道列表(不返回加密 key,返回掩码)。
func (h *Handler) AdminChannels(c *gin.Context) {
var chs []store.Channel
if err := h.db.Order("id ASC").Find(&chs).Error; err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to load channels"})
return
}
out := make([]gin.H, 0, len(chs))
for _, ch := range chs {
masked := ""
if key, err := crypto.Decrypt(ch.APIKeyEnc); err == nil && len(key) > 8 {
masked = maskAPIKey(key)
} else if err == nil {
masked = "****"
}
out = append(out, gin.H{
"id": ch.ID, "name": ch.Name, "provider": ch.Provider, "formats": ch.FormatsEffective(),
"base_url": ch.BaseURL, "base_urls": ch.BaseURLs,
"api_key_masked": masked, "weight": ch.Weight, "priority": ch.Priority,
"timeout_ms": ch.TimeoutMS, "max_concurrency": ch.MaxConcurrency,
"health_status": ch.HealthStatus, "enabled": ch.Enabled,
"created_at": ch.CreatedAt,
})
}
c.JSON(http.StatusOK, gin.H{"data": out})
}
type channelBody struct {
Name string `json:"name" binding:"required,min=1,max=64"`
Provider string `json:"provider"`
Formats []string `json:"formats"`
BaseURL string `json:"base_url"`
BaseURLs map[string]string `json:"base_urls"`
APIKey string `json:"api_key"`
Weight *int `json:"weight"`
Priority *int `json:"priority"`
TimeoutMS *int `json:"timeout_ms"`
MaxConcurrency *int `json:"max_concurrency"`
Enabled *bool `json:"enabled"`
}
// normalizeBaseURLs 校验并清理分协议 base_url。
func normalizeBaseURLs(m map[string]string) map[string]string {
if len(m) == 0 {
return nil
}
out := map[string]string{}
for k, v := range m {
if validFormats[k] && strings.TrimSpace(v) != "" {
out[k] = strings.TrimRight(strings.TrimSpace(v), "/")
}
}
if len(out) == 0 {
return nil
}
return out
}
// resolveBaseURL 渠道 base_url:留空按供应商默认;网关按内容智能识别前缀/完整端点。
func resolveBaseURL(provider, raw string) (string, error) {
base := strings.TrimRight(raw, "/")
if base == "" {
switch provider {
case store.ChannelProviderOpenAI:
base = "https://api.openai.com"
case store.ChannelProviderAnthropic:
base = "https://api.anthropic.com"
}
}
if base == "" {
return "", errors.New("base_url required for compatible channels")
}
return base, nil
}
func validateProvider(p string) bool {
return p == store.ChannelProviderOpenAI || p == store.ChannelProviderAnthropic || p == store.ChannelProviderCompatible
}
var validFormats = map[string]bool{
store.FormatChat: true, store.FormatResponses: true, store.FormatMessages: true,
}
// deriveProvider 按格式推断供应商(仅作内部字段/兼容用途,不参与路由)。
func deriveProvider(formats []string) string {
if len(formats) == 0 {
return store.ChannelProviderCompatible
}
messagesOnly, hasResponses := true, false
for _, f := range formats {
if f != store.FormatMessages {
messagesOnly = false
}
if f == store.FormatResponses {
hasResponses = true
}
}
if messagesOnly {
return store.ChannelProviderAnthropic
}
if hasResponses {
return store.ChannelProviderOpenAI
}
return store.ChannelProviderCompatible
}
// resolveFormats 渠道协议格式:显式给出则校验去重;空则按 provider 推断默认。
func resolveFormats(provider string, formats []string) ([]string, error) {
if len(formats) == 0 {
switch provider {
case store.ChannelProviderAnthropic:
return []string{store.FormatMessages}, nil
case store.ChannelProviderOpenAI:
return []string{store.FormatChat, store.FormatResponses}, nil
default:
return []string{store.FormatChat}, nil
}
}
seen := map[string]bool{}
out := make([]string, 0, len(formats))
for _, f := range formats {
if !validFormats[f] {
return nil, fmt.Errorf("unsupported format %q", f)
}
if !seen[f] {
seen[f] = true
out = append(out, f)
}
}
return out, nil
}
// AdminCreateChannel POST /api/admin/channels
func (h *Handler) AdminCreateChannel(c *gin.Context) {
var req channelBody
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid input: " + err.Error()})
return
}
if req.Provider == "" {
req.Provider = deriveProvider(req.Formats)
}
if !validateProvider(req.Provider) {
c.JSON(http.StatusBadRequest, gin.H{"error": "provider must be openai, anthropic or compatible"})
return
}
if req.APIKey == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "api_key required"})
return
}
formats, err := resolveFormats(req.Provider, req.Formats)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
return
}
baseURL, err := resolveBaseURL(req.Provider, req.BaseURL)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
return
}
enc, err := crypto.Encrypt(req.APIKey)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to encrypt api key"})
return
}
ch := store.Channel{
Name: req.Name, Provider: req.Provider, Formats: formats, BaseURL: baseURL,
BaseURLs: normalizeBaseURLs(req.BaseURLs),
APIKeyEnc: enc, Weight: intOr(req.Weight, 1), Priority: intOr(req.Priority, 0),
TimeoutMS: intOr(req.TimeoutMS, 120000), MaxConcurrency: intOr(req.MaxConcurrency, 16),
HealthStatus: store.ChannelHealthHealthy, Enabled: boolOr(req.Enabled, true),
}
if err := h.db.Create(&ch).Error; err != nil {
c.JSON(http.StatusConflict, gin.H{"error": "failed to create channel (name may already exist)"})
return
}
c.JSON(http.StatusCreated, gin.H{"id": ch.ID, "name": ch.Name})
}
// AdminUpdateChannel PUT /api/admin/channels/:id
func (h *Handler) AdminUpdateChannel(c *gin.Context) {
id, err := strconv.ParseUint(c.Param("id"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid channel id"})
return
}
var body struct {
Name *string `json:"name"`
Provider *string `json:"provider"`
Formats *[]string `json:"formats"`
BaseURL *string `json:"base_url"`
BaseURLs *map[string]string `json:"base_urls"`
APIKey *string `json:"api_key"`
Weight *int `json:"weight"`
Priority *int `json:"priority"`
TimeoutMS *int `json:"timeout_ms"`
MaxConcurrency *int `json:"max_concurrency"`
HealthStatus *string `json:"health_status"`
Enabled *bool `json:"enabled"`
}
if err := c.ShouldBindJSON(&body); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid input"})
return
}
var ch store.Channel
if err := h.db.First(&ch, id).Error; err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "channel not found"})
return
}
updates := map[string]any{}
if body.Name != nil {
updates["name"] = *body.Name
}
if body.Provider != nil {
if !validateProvider(*body.Provider) {
c.JSON(http.StatusBadRequest, gin.H{"error": "provider must be openai, anthropic or compatible"})
return
}
updates["provider"] = *body.Provider
}
if body.BaseURL != nil {
prov := ch.Provider
if body.Provider != nil {
prov = *body.Provider
}
b, berr := resolveBaseURL(prov, *body.BaseURL)
if berr != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": berr.Error()})
return
}
updates["base_url"] = b
}
if body.BaseURLs != nil {
raw, _ := json.Marshal(normalizeBaseURLs(*body.BaseURLs))
updates["base_urls"] = string(raw)
}
if body.APIKey != nil && *body.APIKey != "" {
enc, err := crypto.Encrypt(*body.APIKey)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to encrypt api key"})
return
}
updates["api_key_enc"] = enc
}
if body.Weight != nil {
updates["weight"] = *body.Weight
}
if body.Priority != nil {
updates["priority"] = *body.Priority
}
if body.TimeoutMS != nil {
updates["timeout_ms"] = *body.TimeoutMS
}
if body.MaxConcurrency != nil {
updates["max_concurrency"] = *body.MaxConcurrency
}
if body.HealthStatus != nil {
updates["health_status"] = *body.HealthStatus
}
if body.Enabled != nil {
updates["enabled"] = *body.Enabled
}
if body.Formats != nil {
prov := ch.Provider
if body.Provider != nil {
prov = *body.Provider
}
formats, ferr := resolveFormats(prov, *body.Formats)
if ferr != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": ferr.Error()})
return
}
raw, _ := json.Marshal(formats)
updates["formats"] = string(raw)
}
if len(updates) > 0 {
if err := h.db.Model(&ch).Updates(updates).Error; err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to update channel"})
return
}
}
c.JSON(http.StatusOK, gin.H{"ok": true})
}
// AdminDeleteChannel DELETE /api/admin/channels/:id
func (h *Handler) AdminDeleteChannel(c *gin.Context) {
id, err := strconv.ParseUint(c.Param("id"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid channel id"})
return
}
res := h.db.Delete(&store.Channel{}, id)
if res.Error != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to delete channel"})
return
}
if res.RowsAffected == 0 {
c.JSON(http.StatusNotFound, gin.H{"error": "channel not found"})
return
}
h.db.Where("channel_id = ?", id).Delete(&store.ChannelModelBinding{})
c.JSON(http.StatusOK, gin.H{"ok": true})
}
// AdminTestChannel POST /api/admin/channels/:id/test — 请求渠道 /v1/models 测连通性。
func (h *Handler) AdminTestChannel(c *gin.Context) {
id, err := strconv.ParseUint(c.Param("id"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid channel id"})
return
}
var ch store.Channel
if err := h.db.First(&ch, id).Error; err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "channel not found"})
return
}
key, err := crypto.Decrypt(ch.APIKeyEnc)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to decrypt channel key"})
return
}
url := ch.UpstreamURL("", "/models")
client := &http.Client{Timeout: 10 * time.Second}
req, _ := http.NewRequest(http.MethodGet, url, nil)
req.Header.Set("Authorization", "Bearer "+key)
req.Header.Set("Accept", "application/json")
start := time.Now()
resp, err := client.Do(req)
status := store.ChannelHealthHealthy
msg := "ok"
latency := 0
if err != nil {
status = store.ChannelHealthCooldown
msg = err.Error()
} else {
latency = int(time.Since(start).Milliseconds())
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
status = store.ChannelHealthCooldown
b, _ := io.ReadAll(io.LimitReader(resp.Body, 1024))
msg = fmt.Sprintf("http %d: %s", resp.StatusCode, strings.TrimSpace(string(b)))
}
resp.Body.Close()
}
h.db.Model(&store.Channel{}).Where("id = ?", ch.ID).Update("health_status", status)
if status != store.ChannelHealthHealthy {
c.JSON(http.StatusBadGateway, gin.H{"error": msg})
return
}
c.JSON(http.StatusOK, gin.H{"ok": true, "latency_ms": latency, "message": msg})
}
// AdminChannelRemoteModels GET /api/admin/channels/:id/models/remote — 拉取远端模型列表。
// 返回本渠道尚未允许的模型(新增候选),排除已绑定的模型。
func (h *Handler) AdminChannelRemoteModels(c *gin.Context) {
id, err := strconv.ParseUint(c.Param("id"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid channel id"})
return
}
var ch store.Channel
if err := h.db.First(&ch, id).Error; err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "channel not found"})
return
}
key, err := crypto.Decrypt(ch.APIKeyEnc)
if err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to decrypt channel key"})
return
}
url := ch.UpstreamURL("", "/models")
client := &http.Client{Timeout: 10 * time.Second}
req, _ := http.NewRequest(http.MethodGet, url, nil)
req.Header.Set("Authorization", "Bearer "+key)
req.Header.Set("Accept", "application/json")
resp, err := client.Do(req)
if err != nil {
c.JSON(http.StatusBadGateway, gin.H{"error": err.Error()})
return
}
defer resp.Body.Close()
body, _ := io.ReadAll(io.LimitReader(resp.Body, 10*1024*1024))
if resp.StatusCode < 200 || resp.StatusCode >= 300 {
c.JSON(http.StatusBadGateway, gin.H{"error": fmt.Sprintf("http %d: %s", resp.StatusCode, string(body))})
return
}
// 解析 OpenAI 格式的模型列表
var result struct {
Data []struct {
ID string `json:"id"`
} `json:"data"`
}
if err := json.Unmarshal(body, &result); err != nil {
c.JSON(http.StatusBadGateway, gin.H{"error": "failed to parse response: " + err.Error()})
return
}
// 本渠道已允许的上游模型名:不作为新增候选
var boundNames []string
h.db.Model(&store.ChannelModelBinding{}).Where("channel_id = ?", id).Pluck("upstream_model", &boundNames)
boundSet := make(map[string]bool, len(boundNames))
for _, n := range boundNames {
boundSet[strings.TrimSpace(n)] = true
}
models := make([]string, 0, len(result.Data))
for _, m := range result.Data {
name := strings.TrimSpace(m.ID)
if name != "" && !boundSet[name] {
models = append(models, name)
}
}
c.JSON(http.StatusOK, gin.H{"data": models})
}
// AdminChannelModels GET /api/admin/channels/:id/models — 渠道绑定列表。
func (h *Handler) AdminChannelModels(c *gin.Context) {
channelID, err := strconv.ParseUint(c.Param("id"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid channel id"})
return
}
var bindings []store.ChannelModelBinding
if err := h.db.Preload("Model").Where("channel_id = ?", channelID).Find(&bindings).Error; err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to load bindings"})
return
}
out := make([]gin.H, 0, len(bindings))
for _, b := range bindings {
out = append(out, gin.H{
"id": b.ID, "model_id": b.ModelID, "model_name": b.Model.Name,
"upstream_model": b.UpstreamModel, "weight": b.Weight,
})
}
c.JSON(http.StatusOK, gin.H{"data": out})
}
// AdminChannelAddModel POST /api/admin/channels/:id/models — 手工添加模型绑定。
// 无需渠道具备 /v1/models 接口:直接填上游模型名,可选自定义名称作为客户端调用名。
func (h *Handler) AdminChannelAddModel(c *gin.Context) {
channelID, err := strconv.ParseUint(c.Param("id"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid channel id"})
return
}
var req struct {
UpstreamModel string `json:"upstream_model" binding:"required"` // 渠道侧真实模型名
CustomName string `json:"custom_name"` // 客户端调用名,空=用上游名
Weight *int `json:"weight"`
}
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid input: upstream_model required"})
return
}
globalName := req.CustomName
if globalName == "" {
globalName = req.UpstreamModel
}
var ch store.Channel
if err := h.db.First(&ch, channelID).Error; err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "channel not found"})
return
}
// 查找或创建全局模型
var m store.Model
if err := h.db.Where("name = ?", globalName).First(&m).Error; err != nil {
m = store.Model{Name: globalName, Enabled: true}
if err := h.db.Create(&m).Error; err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to create model"})
return
}
}
// 查找已存在的绑定,如果存在则更新
var existing store.ChannelModelBinding
if err := h.db.Where("channel_id = ? AND model_id = ?", channelID, m.ID).First(&existing).Error; err == nil {
// 已存在,更新
existing.UpstreamModel = req.UpstreamModel
existing.Weight = intOr(req.Weight, 1)
if err := h.db.Save(&existing).Error; err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to update binding"})
return
}
c.JSON(http.StatusOK, gin.H{"id": existing.ID, "model_id": m.ID, "model_name": m.Name, "upstream_model": existing.UpstreamModel, "weight": existing.Weight})
return
}
// 不存在,创建新的
b := store.ChannelModelBinding{
ChannelID: channelID, ModelID: m.ID,
UpstreamModel: req.UpstreamModel, Weight: intOr(req.Weight, 1),
}
if err := h.db.Create(&b).Error; err != nil {
c.JSON(http.StatusConflict, gin.H{"error": "binding may already exist"})
return
}
c.JSON(http.StatusCreated, gin.H{"id": b.ID, "model_id": m.ID, "model_name": m.Name, "upstream_model": req.UpstreamModel, "weight": b.Weight})
}
// AdminChannelUpdateModel PATCH /api/admin/channels/:id/models/:bid — 改映射名/权重。
func (h *Handler) AdminChannelUpdateModel(c *gin.Context) {
bid, err := strconv.ParseUint(c.Param("bid"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid binding id"})
return
}
var req struct {
UpstreamModel *string `json:"upstream_model"`
Weight *int `json:"weight"`
}
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid input"})
return
}
var b store.ChannelModelBinding
if err := h.db.First(&b, bid).Error; err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "binding not found"})
return
}
updates := map[string]any{}
if req.UpstreamModel != nil {
updates["upstream_model"] = *req.UpstreamModel
}
if req.Weight != nil {
updates["weight"] = *req.Weight
}
if len(updates) > 0 {
if err := h.db.Model(&b).Updates(updates).Error; err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to update binding"})
return
}
}
c.JSON(http.StatusOK, gin.H{"ok": true})
}
// AdminChannelDeleteModel DELETE /api/admin/channels/:id/models/:bid — 解除绑定。
func (h *Handler) AdminChannelDeleteModel(c *gin.Context) {
bid, err := strconv.ParseUint(c.Param("bid"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid binding id"})
return
}
res := h.db.Delete(&store.ChannelModelBinding{}, bid)
if res.Error != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to delete binding"})
return
}
if res.RowsAffected == 0 {
c.JSON(http.StatusNotFound, gin.H{"error": "binding not found"})
return
}
c.JSON(http.StatusOK, gin.H{"ok": true})
}
// maskAPIKey 掩码渠道密钥:保留前 7 位与后 4 位,中间固定 ****** 遮蔽。
func maskAPIKey(key string) string {
if len(key) <= 11 {
return strings.Repeat("*", len(key)-4) + key[len(key)-4:]
}
return key[:7] + "******" + key[len(key)-4:]
}
func intOr(p *int, def int) int {
if p == nil {
return def
}
return *p
}
func boolOr(p *bool, def bool) bool {
if p == nil {
return def
}
return *p
}
+109
View File
@@ -0,0 +1,109 @@
package api
import (
"net/http"
"opencatd-open/internal/store"
"github.com/gin-gonic/gin"
)
// AdminGetConfig GET /api/admin/config — 获取系统配置。
func (h *Handler) AdminGetConfig(c *gin.Context) {
configs := map[string]string{}
var rows []store.SystemConfig
h.db.Find(&rows)
for _, r := range rows {
configs[r.Key] = r.Value
}
c.JSON(http.StatusOK, gin.H{"data": configs})
}
// AdminUpdateConfig PUT /api/admin/config — 更新系统配置。
func (h *Handler) AdminUpdateConfig(c *gin.Context) {
var req map[string]string
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid input"})
return
}
for key, value := range req {
var sc store.SystemConfig
result := h.db.Where("key = ?", key).First(&sc)
if result.Error == nil {
sc.Value = value
h.db.Save(&sc)
} else {
sc = store.SystemConfig{Key: key, Value: value}
h.db.Create(&sc)
}
}
c.JSON(http.StatusOK, gin.H{"ok": true})
}
// AdminGetRegistration GET /api/admin/config/registration — 获取注册配置。
func (h *Handler) AdminGetRegistration(c *gin.Context) {
var sc store.SystemConfig
enabled := "true"
if err := h.db.Where("key = ?", "registration_enabled").First(&sc).Error; err == nil {
enabled = sc.Value
}
c.JSON(http.StatusOK, gin.H{"data": gin.H{"enabled": enabled == "true"}})
}
// AdminUpdateRegistration PUT /api/admin/config/registration — 更新注册配置。
func (h *Handler) AdminUpdateRegistration(c *gin.Context) {
var req struct {
Enabled bool `json:"enabled"`
}
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid input"})
return
}
value := "false"
if req.Enabled {
value = "true"
}
var sc store.SystemConfig
if err := h.db.Where("key = ?", "registration_enabled").First(&sc).Error; err == nil {
sc.Value = value
h.db.Save(&sc)
} else {
sc = store.SystemConfig{Key: "registration_enabled", Value: value}
h.db.Create(&sc)
}
c.JSON(http.StatusOK, gin.H{"ok": true})
}
// AdminGetPasswordLogin GET /api/admin/config/password-login — 获取密码登录配置。
func (h *Handler) AdminGetPasswordLogin(c *gin.Context) {
var sc store.SystemConfig
enabled := "true"
if err := h.db.Where("key = ?", "password_login_enabled").First(&sc).Error; err == nil {
enabled = sc.Value
}
c.JSON(http.StatusOK, gin.H{"data": gin.H{"enabled": enabled == "true"}})
}
// AdminUpdatePasswordLogin PUT /api/admin/config/password-login — 更新密码登录配置。
func (h *Handler) AdminUpdatePasswordLogin(c *gin.Context) {
var req struct {
Enabled bool `json:"enabled"`
}
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid input"})
return
}
value := "false"
if req.Enabled {
value = "true"
}
var sc store.SystemConfig
if err := h.db.Where("key = ?", "password_login_enabled").First(&sc).Error; err == nil {
sc.Value = value
h.db.Save(&sc)
} else {
sc = store.SystemConfig{Key: "password_login_enabled", Value: value}
h.db.Create(&sc)
}
c.JSON(http.StatusOK, gin.H{"ok": true})
}
+291
View File
@@ -0,0 +1,291 @@
package api
import (
"encoding/json"
"net/http"
"strconv"
"opencatd-open/internal/store"
"github.com/gin-gonic/gin"
"gorm.io/gorm"
)
// AdminModels GET /api/admin/models — 模型列表(含价格、渠道绑定、定价/禁止状态)。
func (h *Handler) AdminModels(c *gin.Context) {
var ms []store.Model
if err := h.db.Order("sort ASC, id ASC").Find(&ms).Error; err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to load models"})
return
}
allow, deny := h.modelPolicyConfig()
out := make([]gin.H, 0, len(ms))
for _, m := range ms {
var bindings []store.ChannelModelBinding
h.db.Preload("Channel").Where("model_id = ?", m.ID).Find(&bindings)
chs := make([]gin.H, 0, len(bindings))
for _, b := range bindings {
if !b.Channel.Enabled {
continue
}
chs = append(chs, gin.H{
"id": b.ID, "channel_id": b.ChannelID, "channel_name": b.Channel.Name,
"upstream_model": b.UpstreamModel, "weight": b.Weight,
})
}
used := len(chs) > 0
needsPricing := used && m.InputPrice == 0 && m.OutputPrice == 0 && m.CacheReadPrice == 0
denied := containsStr(deny, m.Name) || (len(allow) > 0 && !containsStr(allow, m.Name))
out = append(out, gin.H{
"id": m.ID, "name": m.Name, "display_name": m.DisplayName,
"input_price": m.InputPrice, "output_price": m.OutputPrice, "cache_read_price": m.CacheReadPrice,
"enabled": m.Enabled, "sort": m.Sort, "channels": chs,
"used": used, "needs_pricing": needsPricing, "denied": denied,
})
}
var orphans []struct {
ChannelName string
UpstreamModel string
ModelID uint64
}
h.db.Raw(`SELECT c.name as channel_name, b.model_id, b.upstream_model
FROM channel_model_bindings b
LEFT JOIN models m ON m.id = b.model_id
LEFT JOIN channels c ON c.id = b.channel_id
WHERE m.id IS NULL`).Scan(&orphans)
missing := make([]gin.H, 0, len(orphans))
for _, o := range orphans {
missing = append(missing, gin.H{
"channel": o.ChannelName, "model_id": o.ModelID, "upstream_model": o.UpstreamModel,
})
}
unpriced := 0
{
var usedBindings []struct {
ModelID uint64
}
h.db.Model(&store.ChannelModelBinding{}).Distinct("model_id").Scan(&usedBindings)
usedIDs := map[uint64]bool{}
for _, u := range usedBindings {
usedIDs[u.ModelID] = true
}
for _, m := range ms {
if usedIDs[m.ID] && m.InputPrice == 0 && m.OutputPrice == 0 && m.CacheReadPrice == 0 {
unpriced++
}
}
}
c.JSON(http.StatusOK, gin.H{
"data": out,
"summary": gin.H{
"total": len(ms),
"unpriced": unpriced,
"missing": missing,
"denied_count": len(deny),
},
})
}
// modelPolicyConfig 读取全局模型允许/禁止列表。
func (h *Handler) modelPolicyConfig() (allow, deny []string) {
var raw string
h.db.Model(&store.SystemConfig{}).Where("key = ?", "model_allowlist").Pluck("value", &raw)
_ = json.Unmarshal([]byte(raw), &allow)
raw = ""
h.db.Model(&store.SystemConfig{}).Where("key = ?", "model_denylist").Pluck("value", &raw)
_ = json.Unmarshal([]byte(raw), &deny)
return
}
func containsStr(list []string, s string) bool {
for _, v := range list {
if v == s {
return true
}
}
return false
}
// AdminCreateModel POST /api/admin/models
func (h *Handler) AdminCreateModel(c *gin.Context) {
var req struct {
Name string `json:"name" binding:"required,min=1,max=128"`
DisplayName string `json:"display_name"`
InputPrice float64 `json:"input_price"`
OutputPrice float64 `json:"output_price"`
CacheReadPrice float64 `json:"cache_read_price"`
Sort int `json:"sort"`
Enabled *bool `json:"enabled"`
}
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid input: " + err.Error()})
return
}
m := store.Model{
Name: req.Name, DisplayName: req.DisplayName,
InputPrice: req.InputPrice, OutputPrice: req.OutputPrice, CacheReadPrice: req.CacheReadPrice,
Sort: req.Sort, Enabled: boolOr(req.Enabled, true),
}
if err := h.db.Create(&m).Error; err != nil {
c.JSON(http.StatusConflict, gin.H{"error": "failed to create model (name may already exist)"})
return
}
c.JSON(http.StatusCreated, gin.H{"id": m.ID, "name": m.Name})
}
// AdminUpdateModel PUT /api/admin/models/:id — 价格/启停/排序。
func (h *Handler) AdminUpdateModel(c *gin.Context) {
id, err := strconv.ParseUint(c.Param("id"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid model id"})
return
}
var req struct {
DisplayName *string `json:"display_name"`
InputPrice *float64 `json:"input_price"`
OutputPrice *float64 `json:"output_price"`
CacheReadPrice *float64 `json:"cache_read_price"`
Enabled *bool `json:"enabled"`
Sort *int `json:"sort"`
}
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid input"})
return
}
var m store.Model
if err := h.db.First(&m, id).Error; err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "model not found"})
return
}
updates := map[string]any{}
if req.DisplayName != nil {
updates["display_name"] = *req.DisplayName
}
if req.InputPrice != nil {
updates["input_price"] = *req.InputPrice
}
if req.OutputPrice != nil {
updates["output_price"] = *req.OutputPrice
}
if req.CacheReadPrice != nil {
updates["cache_read_price"] = *req.CacheReadPrice
}
if req.Enabled != nil {
updates["enabled"] = *req.Enabled
}
if req.Sort != nil {
updates["sort"] = *req.Sort
}
if len(updates) > 0 {
if err := h.db.Model(&m).Updates(updates).Error; err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to update model"})
return
}
}
c.JSON(http.StatusOK, gin.H{"ok": true})
}
// AdminDeleteModel DELETE /api/admin/models/:id
func (h *Handler) AdminDeleteModel(c *gin.Context) {
id, err := strconv.ParseUint(c.Param("id"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid model id"})
return
}
res := h.db.Delete(&store.Model{}, id)
if res.Error != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to delete model"})
return
}
if res.RowsAffected == 0 {
c.JSON(http.StatusNotFound, gin.H{"error": "model not found"})
return
}
h.db.Where("model_id = ?", id).Delete(&store.ChannelModelBinding{})
c.JSON(http.StatusOK, gin.H{"ok": true})
}
// AdminDeleteUnusedModels DELETE /api/admin/models/unused — 一键清除未绑定任何渠道的模型。
func (h *Handler) AdminDeleteUnusedModels(c *gin.Context) {
var orphans []store.Model
if err := h.db.Where("id NOT IN (SELECT DISTINCT model_id FROM channel_model_bindings)").Find(&orphans).Error; err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to load models"})
return
}
names := make([]string, 0, len(orphans))
ids := make([]uint64, 0, len(orphans))
for _, m := range orphans {
names = append(names, m.Name)
ids = append(ids, m.ID)
}
if len(ids) > 0 {
if err := h.db.Delete(&store.Model{}, ids).Error; err != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to delete models"})
return
}
}
c.JSON(http.StatusOK, gin.H{"deleted": names, "count": len(names)})
}
// AdminCreateModelBinding POST /api/admin/models/:id/bindings
func (h *Handler) AdminCreateModelBinding(c *gin.Context) {
modelID, err := strconv.ParseUint(c.Param("id"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid model id"})
return
}
var req struct {
ChannelID uint64 `json:"channel_id" binding:"required"`
UpstreamModel string `json:"upstream_model" binding:"required"`
Weight *int `json:"weight"`
}
if err := c.ShouldBindJSON(&req); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid input: channel_id and upstream_model required"})
return
}
var m store.Model
if err := h.db.First(&m, modelID).Error; err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "model not found"})
return
}
var ch store.Channel
if err := h.db.First(&ch, req.ChannelID).Error; err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "channel not found"})
return
}
b := store.ChannelModelBinding{
ChannelID: req.ChannelID, ModelID: modelID,
UpstreamModel: req.UpstreamModel, Weight: intOr(req.Weight, 1),
}
if err := h.db.Create(&b).Error; err != nil {
c.JSON(http.StatusConflict, gin.H{"error": "binding may already exist"})
return
}
c.JSON(http.StatusCreated, gin.H{"id": b.ID})
}
// AdminDeleteModelBinding DELETE /api/admin/models/:id/bindings/:bid
func (h *Handler) AdminDeleteModelBinding(c *gin.Context) {
bid, err := strconv.ParseUint(c.Param("bid"), 10, 64)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid binding id"})
return
}
res := h.db.Delete(&store.ChannelModelBinding{}, bid)
if res.Error != nil {
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to delete binding"})
return
}
if res.RowsAffected == 0 {
c.JSON(http.StatusNotFound, gin.H{"error": "binding not found"})
return
}
c.JSON(http.StatusOK, gin.H{"ok": true})
}
var _ = gorm.ErrRecordNotFound
+3 -3
View File
@@ -556,7 +556,7 @@ func (h *Handler) DeleteApiKey(c *gin.Context) {
c.JSON(http.StatusOK, gin.H{"message": "deleted"})
}
// --- Channels ---
// --- Legacy Channel endpoints (kept for backward compatibility) ---
func (h *Handler) ListChannels(c *gin.Context) {
// Support both limit/offset and pageSize/page parameters
@@ -702,7 +702,7 @@ func (h *Handler) DeleteChannel(c *gin.Context) {
c.JSON(http.StatusOK, gin.H{"message": "deleted"})
}
// --- Models ---
// --- Legacy Model endpoints (kept for backward compatibility) ---
func (h *Handler) ListModels(c *gin.Context) {
// Support both limit/offset and pageSize/page parameters
@@ -827,7 +827,7 @@ func (h *Handler) DeleteModel(c *gin.Context) {
c.JSON(http.StatusOK, gin.H{"message": "deleted"})
}
// --- Channel-Model Bindings ---
// --- Legacy Channel-Model Bindings (kept for backward compatibility) ---
func (h *Handler) BindChannelModels(c *gin.Context) {
channelID, err := strconv.ParseUint(c.Param("id"), 10, 64)
+25
View File
@@ -19,6 +19,9 @@ type Service struct {
// Health tracking
mu sync.RWMutex
healthStatus map[uint64]*channelHealth
// Concurrency control per channel
sems map[uint64]chan struct{}
}
type channelHealth struct {
@@ -33,6 +36,7 @@ func NewService(channelDAO *dao.ChannelDAO, modelDAO *dao.ModelDAO) *Service {
channelDAO: channelDAO,
modelDAO: modelDAO,
healthStatus: make(map[uint64]*channelHealth),
sems: make(map[uint64]chan struct{}),
}
}
@@ -219,3 +223,24 @@ func (s *Service) SelectCandidates(ctx context.Context, modelName string, prefer
return candidates, nil
}
// TryAcquire 尝试获取渠道并发槽;渠道满载返回 false(调用方可溢出到其他渠道)。
// MaxConcurrency<=0 视为不限制。
func (s *Service) TryAcquire(ch *store.Channel) (func(), bool) {
if ch.MaxConcurrency <= 0 {
return func() {}, true
}
s.mu.Lock()
sem, ok := s.sems[ch.ID]
if !ok {
sem = make(chan struct{}, ch.MaxConcurrency)
s.sems[ch.ID] = sem
}
s.mu.Unlock()
select {
case sem <- struct{}{}:
return func() { <-sem }, true
default:
return nil, false
}
}
+34 -4
View File
@@ -10,19 +10,45 @@ import (
"time"
)
// HealthConfig 健康检查配置
type HealthConfig struct {
Interval time.Duration // 检查间隔
Timeout time.Duration // 请求超时
FailureThreshold int // 连续失败次数阈值
DegradedCooldown time.Duration // degraded 冷却时间
CooldownCooldown time.Duration // cooldown 冷却时间
}
// DefaultHealthConfig 返回默认健康检查配置
func DefaultHealthConfig() HealthConfig {
return HealthConfig{
Interval: 5 * time.Minute,
Timeout: 10 * time.Second,
FailureThreshold: 3,
DegradedCooldown: 5 * time.Minute,
CooldownCooldown: 15 * time.Minute,
}
}
type HealthChecker struct {
channelDAO *dao.ChannelDAO
service *Service
client *http.Client
config HealthConfig
}
func NewHealthChecker(channelDAO *dao.ChannelDAO, service *Service) *HealthChecker {
func NewHealthChecker(channelDAO *dao.ChannelDAO, service *Service, config ...HealthConfig) *HealthChecker {
cfg := DefaultHealthConfig()
if len(config) > 0 {
cfg = config[0]
}
return &HealthChecker{
channelDAO: channelDAO,
service: service,
client: &http.Client{
Timeout: 10 * time.Second,
Timeout: cfg.Timeout,
},
config: cfg,
}
}
@@ -91,8 +117,12 @@ func (hc *HealthChecker) CheckAllChannels(ctx context.Context) error {
}
// StartPeriodicCheck starts periodic health checks
func (hc *HealthChecker) StartPeriodicCheck(ctx context.Context, interval time.Duration) {
ticker := time.NewTicker(interval)
func (hc *HealthChecker) StartPeriodicCheck(ctx context.Context, interval ...time.Duration) {
interval_ := hc.config.Interval
if len(interval) > 0 {
interval_ = interval[0]
}
ticker := time.NewTicker(interval_)
defer ticker.Stop()
for {
+11 -2
View File
@@ -82,10 +82,19 @@ func (d *DailyUsageDAO) GetByDate(ctx context.Context, userID uint64, date strin
return &log, nil
}
// UpsertDailyUsage 按 (user_id, model_id, date) 累加式 upsert:
// 行不存在则插入;存在则在原值基础上增量累加(不能用 AssignmentColumns 覆盖,
// 否则多次 flush 会互相清零)。非限定列名在 SQLite/MySQL/PG 的 upsert 语义下都指向目标行。
func (d *DailyUsageDAO) UpsertDailyUsage(ctx context.Context, log *store.UsageDaily) error {
return d.db.WithContext(ctx).Clauses(clause.OnConflict{
Columns: []clause.Column{{Name: "user_id"}, {Name: "model_id"}, {Name: "date"}},
DoUpdates: clause.AssignmentColumns([]string{"requests", "input_tokens", "output_tokens", "cache_read_tokens", "cost"}),
Columns: []clause.Column{{Name: "user_id"}, {Name: "model_id"}, {Name: "date"}},
DoUpdates: clause.Assignments(map[string]interface{}{
"requests": gorm.Expr("requests + ?", log.Requests),
"input_tokens": gorm.Expr("input_tokens + ?", log.InputTokens),
"output_tokens": gorm.Expr("output_tokens + ?", log.OutputTokens),
"cache_read_tokens": gorm.Expr("cache_read_tokens + ?", log.CacheReadTokens),
"cost": gorm.Expr("cost + ?", log.Cost),
}),
}).Create(log).Error
}
+203
View File
@@ -0,0 +1,203 @@
// 三协议互转注册表:OpenAI Chat / OpenAI Responses / Anthropic Messages。
// 网关以 Chat 形状作为标准中间模型:非跨 chat 的转换经 chat 中转。
// 请求/响应(非流式)走 JSON 转换;流式走逐行 SSE 转换(stream_transform.go)。
package convert
import (
"bytes"
"encoding/json"
"fmt"
)
// 协议标识。
const (
ProtoChat = "chat"
ProtoMessages = "messages"
ProtoResponses = "responses"
)
// trimBody 去掉首尾空白。部分上游(如 OpenRouter)会在 JSON 前输出空白或
// SSE 注释行再跟正文,直接 Unmarshal 会失败。
func trimBody(body []byte) []byte {
return bytes.TrimSpace(body)
}
// CleanJSON 剥离非 JSON 前缀(空白、SSE 注释、`data:` 行)并压缩为标准 JSON。
// 部分上游(如 OpenRouter)的 non-stream 响应在 JSON 前夹带空白/注释;
// 原样透传会让客户端解析失败。找不到 JSON 对象时原样返回。
func CleanJSON(body []byte) []byte {
i := bytes.IndexByte(body, '{')
if i < 0 {
return body
}
var v any
if err := json.Unmarshal(bytes.TrimSpace(body[i:]), &v); err != nil {
return body
}
out, err := json.Marshal(v)
if err != nil {
return body
}
return out
}
// ConvertRequest 转换请求体。from==to 时原样返回。
func ConvertRequest(body []byte, from, to string) ([]byte, error) {
if from == to {
return body, nil
}
body = trimBody(body)
switch {
case from == ProtoMessages && to == ProtoChat:
return messagesToChatReq(body)
case from == ProtoChat && to == ProtoMessages:
return chatToMessagesReq(body)
case from == ProtoResponses && to == ProtoChat:
return responsesToChatReq(body)
case from == ProtoChat && to == ProtoResponses:
return chatToResponsesReq(body)
case from == ProtoResponses && to == ProtoMessages:
mid, err := responsesToChatReq(body)
if err != nil {
return nil, err
}
return chatToMessagesReq(mid)
case from == ProtoMessages && to == ProtoResponses:
mid, err := messagesToChatReq(body)
if err != nil {
return nil, err
}
return chatToResponsesReq(mid)
}
return nil, fmt.Errorf("unsupported request conversion %s->%s", from, to)
}
// ConvertResponse 转换响应体(非流式)。from==to 时原样返回。
func ConvertResponse(body []byte, from, to string) ([]byte, error) {
if from == to {
return body, nil
}
body = trimBody(body)
switch {
case from == ProtoMessages && to == ProtoChat:
return messagesToChatResp(body)
case from == ProtoChat && to == ProtoMessages:
return chatToMessagesResp(body)
case from == ProtoResponses && to == ProtoChat:
return responsesToChatResp(body)
case from == ProtoChat && to == ProtoResponses:
return chatToResponsesResp(body)
case from == ProtoResponses && to == ProtoMessages:
mid, err := responsesToChatResp(body)
if err != nil {
return nil, err
}
return chatToMessagesResp(mid)
case from == ProtoMessages && to == ProtoResponses:
mid, err := messagesToChatResp(body)
if err != nil {
return nil, err
}
return chatToResponsesResp(mid)
}
return nil, fmt.Errorf("unsupported response conversion %s->%s", from, to)
}
// NewStreamTransformer 构造流式逐行转换器:输入上游 SSE 一行,返回客户端 SSE 行。
// 返回 nil 表示丢弃该行或无需转换(from==to)。
func NewStreamTransformer(from, to string) func([]byte) []byte {
switch {
case from == ProtoMessages && to == ProtoChat:
return newMessagesToChat().line
case from == ProtoChat && to == ProtoMessages:
return newChatToMessages().line
case from == ProtoResponses && to == ProtoChat:
return newResponsesToChat().line
case from == ProtoChat && to == ProtoResponses:
return newChatToResponses().line
case from == ProtoResponses && to == ProtoMessages:
return newResponsesToMessages().line
case from == ProtoMessages && to == ProtoResponses:
return newMessagesToResponses().line
}
return nil
}
// ---------------------------------------------------------------------------
// 工具函数
// str 返回字符串字段;json.RawMessage 为字符串字面量时去引号。
func str(raw json.RawMessage) string {
if len(raw) == 0 || string(raw) == "null" {
return ""
}
var s string
if json.Unmarshal(raw, &s) == nil {
return s
}
// 数组/对象:尝试取 type=text 的 text
var arr []map[string]any
if json.Unmarshal(raw, &arr) == nil {
var parts []string
for _, b := range arr {
if t, _ := b["type"].(string); t == "text" || t == "input_text" || t == "output_text" {
if txt, _ := b["text"].(string); txt != "" {
parts = append(parts, txt)
}
}
}
return joinNonEmpty(parts, "\n")
}
return ""
}
func joinNonEmpty(parts []string, sep string) string {
out := ""
for _, p := range parts {
if p == "" {
continue
}
if out != "" {
out += sep
}
out += p
}
return out
}
// rawJSON 安全取字段;不存在或 null 返回 nil。
func rawJSON(m map[string]json.RawMessage, key string) json.RawMessage {
raw, ok := m[key]
if !ok || string(raw) == "null" {
return nil
}
return raw
}
// rawOrObject 把 RawMessage 解为 map;非对象返回空对象。
func rawOrObject(raw json.RawMessage) any {
if len(raw) == 0 || string(raw) == "null" {
return map[string]any{}
}
var m map[string]any
if json.Unmarshal(raw, &m) == nil {
return m
}
return map[string]any{}
}
// intOrNil 取指针值,nil 时返回默认值。
func intOrNil(p *int, def int) any {
if p == nil {
return def
}
return *p
}
// strField 取 any 中的字符串字段。
func strField(v any) string {
if s, ok := v.(string); ok {
return s
}
return ""
}
+504
View File
@@ -0,0 +1,504 @@
package convert
import (
"encoding/json"
"strings"
)
// ---------------------------------------------------------------------------
// 请求:Chat → Messages
type chatTool struct {
Type string `json:"type"`
Function struct {
Name string `json:"name"`
Description string `json:"description"`
Parameters json.RawMessage `json:"parameters"`
} `json:"function"`
}
type chatMsg struct {
Role string `json:"role"`
Content json.RawMessage `json:"content"`
ToolCallID string `json:"tool_call_id"`
ToolCalls []struct {
ID string `json:"id"`
Function struct {
Name string `json:"name"`
Arguments string `json:"arguments"`
} `json:"function"`
} `json:"tool_calls"`
}
type chatReq struct {
Model string `json:"model"`
Messages []chatMsg `json:"messages"`
Tools []chatTool `json:"tools"`
Temperature *float64 `json:"temperature"`
TopP *float64 `json:"top_p"`
MaxTokens *int `json:"max_tokens"`
Stop []string `json:"stop"`
Stream bool `json:"stream"`
}
// chatToMessagesReq 将 OpenAI Chat 请求转为 Anthropic Messages 请求。
func chatToMessagesReq(body []byte) ([]byte, error) {
var req chatReq
if err := json.Unmarshal(body, &req); err != nil {
return nil, err
}
out := map[string]any{
"model": req.Model,
"max_tokens": intOrNil(req.MaxTokens, 1024), // Anthropic 必填
}
if req.Stream {
out["stream"] = true
}
if req.Temperature != nil {
out["temperature"] = *req.Temperature
}
if req.TopP != nil {
out["top_p"] = *req.TopP
}
if len(req.Stop) > 0 {
out["stop_sequences"] = req.Stop
}
var system []string
msgs := make([]any, 0, len(req.Messages))
for _, m := range req.Messages {
if m.Role == "system" {
if s := str(m.Content); s != "" {
system = append(system, s)
}
continue
}
msgs = append(msgs, chatMsgToAnthropic(m))
}
if len(system) > 0 {
out["system"] = strings.Join(system, "\n")
}
out["messages"] = msgs
if len(req.Tools) > 0 {
tools := make([]any, 0, len(req.Tools))
for _, t := range req.Tools {
var params any
if len(t.Function.Parameters) > 0 && string(t.Function.Parameters) != "null" {
_ = json.Unmarshal(t.Function.Parameters, &params)
}
tools = append(tools, map[string]any{
"name": t.Function.Name,
"description": t.Function.Description,
"input_schema": params,
})
}
out["tools"] = tools
}
return json.Marshal(out)
}
// chatMsgToAnthropic 单条消息转 Anthropic 内容。
func chatMsgToAnthropic(m chatMsg) any {
switch m.Role {
case "assistant":
content := make([]any, 0, 2)
if s := str(m.Content); s != "" {
content = append(content, map[string]any{"type": "text", "text": s})
}
for _, tc := range m.ToolCalls {
var input any
if tc.Function.Arguments != "" {
_ = json.Unmarshal([]byte(tc.Function.Arguments), &input)
}
content = append(content, map[string]any{
"type": "tool_use",
"id": tc.ID,
"name": tc.Function.Name,
"input": input,
})
}
return map[string]any{"role": "assistant", "content": content}
case "tool":
return map[string]any{"role": "user", "content": []any{
map[string]any{"type": "tool_result", "tool_use_id": m.ToolCallID, "content": str(m.Content)},
}}
default: // user
var arr []map[string]any
if json.Unmarshal(m.Content, &arr) == nil && arr != nil {
blocks := make([]any, 0, len(arr))
for _, b := range arr {
switch b["type"] {
case "text", "input_text":
if t, _ := b["text"].(string); t != "" {
blocks = append(blocks, map[string]any{"type": "text", "text": t})
}
case "image_url":
var url string
if iu, ok := b["image_url"].(map[string]any); ok {
url, _ = iu["url"].(string)
} else if s, ok := b["image_url"].(string); ok {
url = s
}
if url != "" {
blocks = append(blocks, anthropicImageBlock(url))
}
}
}
if len(blocks) > 0 {
return map[string]any{"role": "user", "content": blocks}
}
}
return map[string]any{"role": "user", "content": str(m.Content)}
}
}
// ---------------------------------------------------------------------------
// 请求:Messages → Chat
type messagesReq struct {
Model string `json:"model"`
System json.RawMessage `json:"system"`
Messages []struct {
Role string `json:"role"`
Content json.RawMessage `json:"content"`
} `json:"messages"`
Tools []struct {
Name string `json:"name"`
Description string `json:"description"`
InputSchema json.RawMessage `json:"input_schema"`
} `json:"tools"`
Temperature *float64 `json:"temperature"`
TopP *float64 `json:"top_p"`
MaxTokens *int `json:"max_tokens"`
StopSequence []string `json:"stop_sequences"`
Stream bool `json:"stream"`
}
// messagesToChatReq 将 Anthropic Messages 请求转为 OpenAI Chat 请求。
func messagesToChatReq(body []byte) ([]byte, error) {
var req messagesReq
if err := json.Unmarshal(body, &req); err != nil {
return nil, err
}
out := map[string]any{"model": req.Model}
if req.Stream {
out["stream"] = true
}
if req.Temperature != nil {
out["temperature"] = *req.Temperature
}
if req.TopP != nil {
out["top_p"] = *req.TopP
}
if req.MaxTokens != nil {
out["max_tokens"] = *req.MaxTokens
}
if len(req.StopSequence) > 0 {
out["stop"] = req.StopSequence
}
msgs := make([]any, 0, len(req.Messages)+1)
if s := str(req.System); s != "" {
msgs = append(msgs, map[string]any{"role": "system", "content": s})
}
for _, m := range req.Messages {
msgs = append(msgs, anthropicMsgToChat(m.Role, m.Content)...)
}
out["messages"] = msgs
if len(req.Tools) > 0 {
tools := make([]any, 0, len(req.Tools))
for _, t := range req.Tools {
tools = append(tools, map[string]any{
"type": "function",
"function": map[string]any{
"name": t.Name,
"description": t.Description,
"parameters": rawOrObject(t.InputSchema),
},
})
}
out["tools"] = tools
}
return json.Marshal(out)
}
// anthropicMsgToChat 将一条 Anthropic 消息拆成 0..N 条 Chat 消息。
func anthropicMsgToChat(role string, content json.RawMessage) []any {
// 块数组优先(tool_use / tool_result 需要分块解析)
var blocks []map[string]any
if json.Unmarshal(content, &blocks) == nil && blocks != nil {
var out []any
var toolMsgs []any // tool_result 单独收集,保证排在 assistant(tool_calls) 之后
var textParts []string
var contentBlocks []any // text / image_url 块,保留原始顺序
var toolCalls []any
for _, b := range blocks {
switch b["type"] {
case "text":
if t, _ := b["text"].(string); t != "" {
textParts = append(textParts, t)
contentBlocks = append(contentBlocks, map[string]any{"type": "text", "text": t})
}
case "image":
if cb := chatImageBlock(b); cb != nil {
contentBlocks = append(contentBlocks, cb)
}
case "tool_use":
id, _ := b["id"].(string)
name, _ := b["name"].(string)
args, _ := json.Marshal(b["input"])
toolCalls = append(toolCalls, map[string]any{
"id": id,
"type": "function",
"function": map[string]any{
"name": name,
"arguments": string(args),
},
})
case "tool_result":
callID, _ := b["tool_use_id"].(string)
res := strField(b["content"])
toolMsgs = append(toolMsgs, map[string]any{"role": "tool", "tool_call_id": callID, "content": res})
}
}
hasImage := false
for _, cb := range contentBlocks {
if m, _ := cb.(map[string]any); m["type"] == "image_url" {
hasImage = true
break
}
}
if hasImage || len(textParts) > 0 || len(toolCalls) > 0 {
msg := map[string]any{"role": role}
switch {
case hasImage:
msg["content"] = contentBlocks
case len(textParts) > 0:
msg["content"] = strings.Join(textParts, "")
}
if len(toolCalls) > 0 {
msg["tool_calls"] = toolCalls
}
out = append(out, msg)
}
out = append(out, toolMsgs...)
if len(out) > 0 {
return out
}
}
// 纯文本
if s := str(content); s != "" {
return []any{map[string]any{"role": role, "content": s}}
}
return nil
}
// ---------------------------------------------------------------------------
// 响应:Messages → Chat
type messagesResp struct {
ID string `json:"id"`
Model string `json:"model"`
Content []struct {
Type string `json:"type"`
Text string `json:"text"`
ID string `json:"id"`
Name string `json:"name"`
Input json.RawMessage `json:"input"`
} `json:"content"`
StopReason string `json:"stop_reason"`
Usage struct {
InputTokens int64 `json:"input_tokens"`
OutputTokens int64 `json:"output_tokens"`
} `json:"usage"`
}
// messagesToChatResp 将 Anthropic Messages 响应(非流式)转为 Chat 响应。
func messagesToChatResp(body []byte) ([]byte, error) {
var r messagesResp
if err := json.Unmarshal(body, &r); err != nil {
return nil, err
}
var text string
var toolCalls []any
for _, c := range r.Content {
switch c.Type {
case "text":
text += c.Text
case "tool_use":
args, _ := json.Marshal(c.Input)
toolCalls = append(toolCalls, map[string]any{
"id": c.ID,
"type": "function",
"function": map[string]any{
"name": c.Name,
"arguments": string(args),
},
})
}
}
msg := map[string]any{"role": "assistant", "content": text}
if len(toolCalls) > 0 {
msg["tool_calls"] = toolCalls
}
return json.Marshal(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(r.ID, "msg_"),
"object": "chat.completion",
"model": r.Model,
"created": 0,
"choices": []any{map[string]any{
"index": 0,
"message": msg,
"finish_reason": messagesStopToChat(r.StopReason),
}},
"usage": map[string]any{
"prompt_tokens": r.Usage.InputTokens,
"completion_tokens": r.Usage.OutputTokens,
"total_tokens": r.Usage.InputTokens + r.Usage.OutputTokens,
},
})
}
// ---------------------------------------------------------------------------
// 响应:Chat → Messages
type chatResp struct {
ID string `json:"id"`
Model string `json:"model"`
Choices []struct {
Message struct {
Role string `json:"role"`
Content string `json:"content"`
ToolCalls []struct {
ID string `json:"id"`
Function struct {
Name string `json:"name"`
Arguments string `json:"arguments"`
} `json:"function"`
} `json:"tool_calls"`
} `json:"message"`
FinishReason string `json:"finish_reason"`
} `json:"choices"`
Usage struct {
PromptTokens int64 `json:"prompt_tokens"`
CompletionTokens int64 `json:"completion_tokens"`
} `json:"usage"`
}
// chatToMessagesResp 将 Chat 响应(非流式)转为 Messages 响应。
func chatToMessagesResp(body []byte) ([]byte, error) {
var r chatResp
if err := json.Unmarshal(body, &r); err != nil {
return nil, err
}
content := make([]any, 0, 2)
var finish = "end_turn"
if len(r.Choices) > 0 {
msg := r.Choices[0].Message
if msg.Content != "" {
content = append(content, map[string]any{"type": "text", "text": msg.Content})
}
for _, tc := range msg.ToolCalls {
var input any
_ = json.Unmarshal([]byte(tc.Function.Arguments), &input)
content = append(content, map[string]any{
"type": "tool_use",
"id": tc.ID,
"name": tc.Function.Name,
"input": input,
})
}
finish = chatStopToMessages(r.Choices[0].FinishReason)
}
return json.Marshal(map[string]any{
"id": "msg_" + strings.TrimPrefix(r.ID, "chatcmpl-"),
"type": "message",
"role": "assistant",
"model": r.Model,
"content": content,
"stop_reason": finish,
"usage": map[string]any{
"input_tokens": r.Usage.PromptTokens,
"output_tokens": r.Usage.CompletionTokens,
},
})
}
// ---------------------------------------------------------------------------
// 辅助
// splitDataURL 解析 data:media_type;base64,data 形式的 URL;非该形式返回 ok=false。
func splitDataURL(url string) (media, data string, ok bool) {
if !strings.HasPrefix(url, "data:") {
return "", "", false
}
i := strings.Index(url, ";base64,")
if i < 0 {
return "", "", false
}
return url[len("data:"):i], url[i+len(";base64,"):], true
}
// chatImageBlock 把 Anthropic image 块转 OpenAI image_url 块。
// 仅支持 base64 与 url source;其他类型(如 Files API 的 file_id)不支持,跳过。
func chatImageBlock(b map[string]any) any {
src, ok := b["source"].(map[string]any)
if !ok {
return nil
}
switch src["type"] {
case "base64":
media, _ := src["media_type"].(string)
data, _ := src["data"].(string)
if data == "" {
return nil
}
if media == "" {
media = "image/png"
}
return map[string]any{"type": "image_url", "image_url": map[string]any{"url": "data:" + media + ";base64," + data}}
case "url":
url, _ := src["url"].(string)
if url == "" {
return nil
}
return map[string]any{"type": "image_url", "image_url": map[string]any{"url": url}}
}
return nil
}
// anthropicImageBlock 把 OpenAI image_url 的 url 转 Anthropic image 块。
// data URL → base64 source;http(s) URL → url source。
func anthropicImageBlock(url string) any {
if media, data, ok := splitDataURL(url); ok {
if media == "" {
media = "image/png"
}
return map[string]any{"type": "image", "source": map[string]any{"type": "base64", "media_type": media, "data": data}}
}
return map[string]any{"type": "image", "source": map[string]any{"type": "url", "url": url}}
}
func messagesStopToChat(s string) string {
switch s {
case "tool_use":
return "tool_calls"
case "max_tokens":
return "length"
default:
return "stop"
}
}
func chatStopToMessages(s string) string {
switch s {
case "tool_calls":
return "tool_use"
case "length":
return "max_tokens"
default:
return "end_turn"
}
}
@@ -0,0 +1,376 @@
package convert
import (
"encoding/json"
"strings"
)
// ---------------------------------------------------------------------------
// 请求:Responses → Chat
// responsesToChatReq 将 OpenAI Responses 请求转为 Chat 请求。
func responsesToChatReq(body []byte) ([]byte, error) {
var m map[string]json.RawMessage
if err := json.Unmarshal(body, &m); err != nil {
return nil, err
}
out := map[string]any{"model": str(rawJSON(m, "model"))}
if v, ok := m["stream"]; ok && string(v) == "true" {
out["stream"] = true
}
if v, ok := m["temperature"]; ok {
out["temperature"] = v
}
if v, ok := m["top_p"]; ok {
out["top_p"] = v
}
if v, ok := m["max_output_tokens"]; ok {
out["max_tokens"] = v
}
var msgs []any
if ins := str(rawJSON(m, "instructions")); ins != "" {
msgs = append(msgs, map[string]any{"role": "system", "content": ins})
}
msgs = append(msgs, responsesInputToChat(rawJSON(m, "input"))...)
out["messages"] = msgs
if raw := rawJSON(m, "tools"); raw != nil {
var tools []map[string]any
if json.Unmarshal(raw, &tools) == nil {
chatTools := make([]any, 0, len(tools))
for _, t := range tools {
chatTools = append(chatTools, map[string]any{
"type": "function",
"function": map[string]any{
"name": t["name"],
"description": t["description"],
"parameters": t["parameters"],
},
})
}
out["tools"] = chatTools
}
}
return json.Marshal(out)
}
// responsesInputToChat 把 Responses input 转成 Chat messages。
// input 支持字符串或条目数组(message / function_call / function_call_output)。
func responsesInputToChat(raw json.RawMessage) []any {
if len(raw) == 0 || string(raw) == "null" {
return nil
}
// 字符串输入
if s := str(raw); s != "" {
return []any{map[string]any{"role": "user", "content": s}}
}
var items []map[string]any
if err := json.Unmarshal(raw, &items); err != nil || items == nil {
return nil
}
var out []any
for _, item := range items {
switch item["type"] {
case "function_call":
out = append(out, map[string]any{
"role": "assistant",
"content": "",
"tool_calls": []any{map[string]any{
"id": strField(item["call_id"]),
"type": "function",
"function": map[string]any{
"name": strField(item["name"]),
"arguments": strField(item["arguments"]),
},
}},
})
case "function_call_output":
out = append(out, map[string]any{
"role": "tool",
"tool_call_id": strField(item["call_id"]),
"content": strField(item["output"]),
})
default: // message 条目
role, _ := item["role"].(string)
if role == "" {
role = "user"
}
if content, ok := item["content"].(string); ok {
out = append(out, map[string]any{"role": role, "content": content})
} else if blocks, ok := item["content"].([]any); ok {
var text []string
var contentBlocks []any
for _, b := range blocks {
bm, ok := b.(map[string]any)
if !ok {
continue
}
switch bm["type"] {
case "input_text", "text":
if t, _ := bm["text"].(string); t != "" {
text = append(text, t)
contentBlocks = append(contentBlocks, map[string]any{"type": "text", "text": t})
}
case "input_image":
var url string
if s, ok := bm["image_url"].(string); ok {
url = s
} else if m, ok := bm["image_url"].(map[string]any); ok {
url, _ = m["url"].(string)
}
if url != "" {
contentBlocks = append(contentBlocks, map[string]any{"type": "image_url", "image_url": map[string]any{"url": url}})
}
}
}
hasImage := false
for _, cb := range contentBlocks {
if m, _ := cb.(map[string]any); m["type"] == "image_url" {
hasImage = true
break
}
}
if hasImage {
out = append(out, map[string]any{"role": role, "content": contentBlocks})
} else {
out = append(out, map[string]any{"role": role, "content": strings.Join(text, "")})
}
}
}
}
return out
}
// chatContentToResponsesBlocks 把 Chat 用户消息 content 转 Responses input 块数组(input_text / input_image)。
func chatContentToResponsesBlocks(content json.RawMessage) []any {
// 纯字符串 → 单个 input_text
var s string
if json.Unmarshal(content, &s) == nil && s != "" {
return []any{map[string]any{"type": "input_text", "text": s}}
}
// 数组 → 按块转换(text / image_url)
var arr []map[string]any
if json.Unmarshal(content, &arr) == nil && arr != nil {
var out []any
for _, b := range arr {
switch b["type"] {
case "text", "input_text":
if t, _ := b["text"].(string); t != "" {
out = append(out, map[string]any{"type": "input_text", "text": t})
}
case "image_url":
var url string
if iu, ok := b["image_url"].(map[string]any); ok {
url, _ = iu["url"].(string)
} else if s, ok := b["image_url"].(string); ok {
url = s
}
if url != "" {
out = append(out, map[string]any{"type": "input_image", "image_url": url})
}
}
}
return out
}
return nil
}
// ---------------------------------------------------------------------------
// 请求:Chat → Responses
// chatToResponsesReq 将 Chat 请求转为 Responses 请求。
func chatToResponsesReq(body []byte) ([]byte, error) {
var req chatReq
if err := json.Unmarshal(body, &req); err != nil {
return nil, err
}
out := map[string]any{"model": req.Model}
if req.Stream {
out["stream"] = true
}
if req.Temperature != nil {
out["temperature"] = *req.Temperature
}
if req.TopP != nil {
out["top_p"] = *req.TopP
}
if req.MaxTokens != nil {
out["max_output_tokens"] = *req.MaxTokens
}
var system []string
var input []any
for _, m := range req.Messages {
if m.Role == "system" {
if s := str(m.Content); s != "" {
system = append(system, s)
}
continue
}
switch m.Role {
case "tool":
input = append(input, map[string]any{
"type": "function_call_output",
"call_id": m.ToolCallID,
"output": str(m.Content),
})
case "assistant":
if len(m.ToolCalls) > 0 {
for _, tc := range m.ToolCalls {
input = append(input, map[string]any{
"type": "function_call",
"call_id": tc.ID,
"name": tc.Function.Name,
"arguments": tc.Function.Arguments,
})
}
} else if s := str(m.Content); s != "" {
input = append(input, map[string]any{"type": "message", "role": "assistant", "content": []any{
map[string]any{"type": "input_text", "text": s},
}})
}
default:
if blocks := chatContentToResponsesBlocks(m.Content); len(blocks) > 0 {
input = append(input, map[string]any{"type": "message", "role": "user", "content": blocks})
}
}
}
if len(system) > 0 {
out["instructions"] = strings.Join(system, "\n")
}
// input 必须是数组:部分上游只接受数组,单对象会被拒(400 Mismatch type)。
out["input"] = input
if len(req.Tools) > 0 {
tools := make([]any, 0, len(req.Tools))
for _, t := range req.Tools {
tools = append(tools, map[string]any{
"type": "function",
"name": t.Function.Name,
"description": t.Function.Description,
"parameters": rawOrObject(t.Function.Parameters),
})
}
out["tools"] = tools
}
return json.Marshal(out)
}
// ---------------------------------------------------------------------------
// 响应:Responses → Chat
// responsesToChatResp 将 Responses 响应(非流式)转为 Chat 响应。
func responsesToChatResp(body []byte) ([]byte, error) {
var m map[string]json.RawMessage
if err := json.Unmarshal(body, &m); err != nil {
return nil, err
}
var text string
var toolCalls []any
if raw := rawJSON(m, "output"); raw != nil {
var outputs []map[string]any
if json.Unmarshal(raw, &outputs) == nil {
for _, o := range outputs {
switch o["type"] {
case "message":
if content, ok := o["content"].([]any); ok {
for _, c := range content {
if cm, ok := c.(map[string]any); ok {
if t, _ := cm["text"].(string); t != "" {
text += t
}
}
}
}
case "function_call":
toolCalls = append(toolCalls, map[string]any{
"id": strField(o["call_id"]),
"type": "function",
"function": map[string]any{
"name": strField(o["name"]),
"arguments": strField(o["arguments"]),
},
})
}
}
}
}
msg := map[string]any{"role": "assistant", "content": text}
if len(toolCalls) > 0 {
msg["tool_calls"] = toolCalls
}
finish := "stop"
switch {
case string(rawJSON(m, "status")) == `"incomplete"`:
finish = "length" // 截断优先,客户端可据此区分
case len(toolCalls) > 0:
finish = "tool_calls"
}
var prompt, completion int64
if u := rawJSON(m, "usage"); u != nil {
var us struct {
InputTokens int64 `json:"input_tokens"`
OutputTokens int64 `json:"output_tokens"`
}
_ = json.Unmarshal(u, &us)
prompt, completion = us.InputTokens, us.OutputTokens
}
return json.Marshal(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(str(rawJSON(m, "id")), "resp_"),
"object": "chat.completion",
"model": str(rawJSON(m, "model")),
"choices": []any{map[string]any{"index": 0, "message": msg, "finish_reason": finish}},
"usage": map[string]any{
"prompt_tokens": prompt,
"completion_tokens": completion,
"total_tokens": prompt + completion,
},
})
}
// ---------------------------------------------------------------------------
// 响应:Chat → Responses
// chatToResponsesResp 将 Chat 响应(非流式)转为 Responses 响应。
func chatToResponsesResp(body []byte) ([]byte, error) {
var r chatResp
if err := json.Unmarshal(body, &r); err != nil {
return nil, err
}
output := make([]any, 0, 2)
var finish = "completed"
if len(r.Choices) > 0 {
msg := r.Choices[0].Message
if msg.Content != "" {
output = append(output, map[string]any{
"type": "message",
"role": "assistant",
"content": []any{map[string]any{"type": "output_text", "text": msg.Content}},
})
}
for _, tc := range msg.ToolCalls {
output = append(output, map[string]any{
"type": "function_call",
"call_id": tc.ID,
"name": tc.Function.Name,
"arguments": tc.Function.Arguments,
})
}
if r.Choices[0].FinishReason == "length" {
finish = "incomplete"
}
}
return json.Marshal(map[string]any{
"id": "resp_" + strings.TrimPrefix(r.ID, "chatcmpl-"),
"object": "response",
"model": r.Model,
"status": finish,
"output": output,
"usage": map[string]any{
"input_tokens": r.Usage.PromptTokens,
"output_tokens": r.Usage.CompletionTokens,
"total_tokens": r.Usage.PromptTokens + r.Usage.CompletionTokens,
},
})
}
@@ -0,0 +1,642 @@
package convert
import (
"encoding/json"
"strings"
)
// sseState 记录上一行 event 名。
type sseState struct {
event string
}
// parseLine 解析一行 SSE;返回是否 data 行及其内容、是否 [DONE]。
// data: 后可跟空格(标准)或紧贴 JSON(部分上游会省略空格)。
func (s *sseState) parseLine(line []byte) (isData bool, data string, done bool) {
strLine := strings.TrimRight(string(line), "\r\n")
switch {
case strings.HasPrefix(strLine, "event: "):
s.event = strings.TrimSpace(strings.TrimPrefix(strLine, "event: "))
return false, "", false
case strLine == "data: [DONE]" || strLine == "data:[DONE]":
return true, "[DONE]", true
case strings.HasPrefix(strLine, "data:"):
return true, strings.TrimLeft(strings.TrimPrefix(strLine, "data:"), " "), false
default:
return false, "", false
}
}
func eventData(line string) map[string]any {
var m map[string]any
_ = json.Unmarshal([]byte(line), &m)
return m
}
func dataLine(obj any) []byte {
b, _ := json.Marshal(obj)
return append(append([]byte("data: "), b...), '\n', '\n')
}
func eventLine(name string, obj any) []byte {
b, _ := json.Marshal(obj)
out := append([]byte("event: "+name+"\ndata: "), b...)
return append(out, '\n', '\n')
}
// joinLines 拼接多条 SSE 行。
func joinLines(lines [][]byte) []byte {
var s []string
for _, l := range lines {
s = append(s, string(l))
}
return []byte(strings.Join(s, ""))
}
// ---------------------------------------------------------------------------
// Messages → Chat
type messagesToChat struct {
sseState
id, model string
toolIdx map[int]int // messages content block index → chat tool_calls index(顺序编号,避开文本块)
nextTool int
}
func newMessagesToChat() *messagesToChat { return &messagesToChat{toolIdx: map[int]int{}} }
func (t *messagesToChat) line(line []byte) []byte {
isData, data, done := t.parseLine(line)
if !isData {
return nil
}
if done {
return []byte("data: [DONE]\n\n")
}
m := eventData(data)
evt, _ := m["type"].(string)
switch evt {
case "message_start":
msg, _ := m["message"].(map[string]any)
t.id, _ = msg["id"].(string)
t.model, _ = msg["model"].(string)
return dataLine(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(t.id, "msg_"), "object": "chat.completion.chunk", "model": t.model,
"choices": []any{map[string]any{"index": 0, "delta": map[string]any{"role": "assistant"}, "finish_reason": nil}},
})
case "content_block_start":
cb, _ := m["content_block"].(map[string]any)
if cb == nil || cb["type"] != "tool_use" {
return nil
}
blockIdx, _ := m["index"].(float64)
tool := t.nextTool
t.nextTool++
t.toolIdx[int(blockIdx)] = tool
toolID, _ := cb["id"].(string)
name, _ := cb["name"].(string)
return dataLine(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(t.id, "msg_"), "object": "chat.completion.chunk", "model": t.model,
"choices": []any{map[string]any{"index": 0, "delta": map[string]any{
"tool_calls": []any{map[string]any{"index": tool, "id": toolID, "type": "function", "function": map[string]any{"name": name, "arguments": ""}}},
}, "finish_reason": nil}},
})
case "content_block_delta":
delta, _ := m["delta"].(map[string]any)
deltaType, _ := delta["type"].(string)
if deltaType == "input_json_delta" {
blockIdx, _ := m["index"].(float64)
tool, ok := t.toolIdx[int(blockIdx)]
if !ok {
return nil
}
partial, _ := delta["partial_json"].(string)
if partial == "" {
return nil
}
return dataLine(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(t.id, "msg_"), "object": "chat.completion.chunk", "model": t.model,
"choices": []any{map[string]any{"index": 0, "delta": map[string]any{
"tool_calls": []any{map[string]any{"index": tool, "function": map[string]any{"arguments": partial}}},
}, "finish_reason": nil}},
})
}
text, _ := delta["text"].(string)
if text == "" {
return nil
}
return dataLine(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(t.id, "msg_"), "object": "chat.completion.chunk", "model": t.model,
"choices": []any{map[string]any{"index": 0, "delta": map[string]any{"content": text}, "finish_reason": nil}},
})
case "message_delta":
delta, _ := m["delta"].(map[string]any)
stop, _ := delta["stop_reason"].(string)
var out [][]byte
out = append(out, dataLine(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(t.id, "msg_"), "object": "chat.completion.chunk", "model": t.model,
"choices": []any{map[string]any{"index": 0, "delta": map[string]any{}, "finish_reason": messagesStopToChat(stop)}},
}))
if u, ok := m["usage"]; ok {
out = append(out, dataLine(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(t.id, "msg_"), "object": "chat.completion.chunk", "model": t.model,
"choices": []any{}, "usage": u,
}))
}
return joinLines(out)
case "message_stop":
return []byte("data: [DONE]\n\n")
}
return nil
}
// ---------------------------------------------------------------------------
// Chat → Messages
type chatToMessages struct {
sseState
started bool // message_start 已发出
nextIndex int // 下一个 content block index(顺序分配)
textIndex int // 文本块 index;-1 = 未开始
toolIdx map[int]int // chat delta.tool_calls[].index → messages block index
openBlocks []int // 已开始未停止的 block index,按开始顺序
model string
stopReason string
usage any
}
func newChatToMessages() *chatToMessages {
return &chatToMessages{textIndex: -1, toolIdx: map[int]int{}}
}
func (t *chatToMessages) line(line []byte) []byte {
isData, data, done := t.parseLine(line)
if !isData {
return nil
}
if done {
// 汇聚最终:先对每个已开始未停止的块发 content_block_stop,再 message_delta + message_stop
var out [][]byte
for _, idx := range t.openBlocks {
out = append(out, eventLine("content_block_stop", map[string]any{"type": "content_block_stop", "index": idx}))
}
md := map[string]any{"type": "message_delta", "delta": map[string]any{
"stop_reason": stopReasonOrEnd(t.stopReason), "stop_sequence": nil,
}}
if t.usage != nil {
md["usage"] = t.usage
}
out = append(out, eventLine("message_delta", md))
out = append(out, eventLine("message_stop", map[string]any{"type": "message_stop"}))
return joinLines(out)
}
m := eventData(data)
// chat 块:delta / finish_reason 在 choices[0] 内
delta := map[string]any{}
if choices, ok := m["choices"].([]any); ok && len(choices) > 0 {
if c0, ok := choices[0].(map[string]any); ok {
if d, ok := c0["delta"].(map[string]any); ok {
delta = d
}
if fr, _ := c0["finish_reason"].(string); fr != "" {
t.stopReason = fr
}
}
}
if t.model == "" {
t.model, _ = m["model"].(string)
}
id, _ := m["id"].(string)
var out [][]byte
// message_start 只在实际有内容(文本或工具)时发出,避免 reasoning_content 块
//(带 role 无 content)提前开出一个空文本块。
ensureStarted := func() {
if t.started {
return
}
t.started = true
out = append(out, eventLine("message_start", map[string]any{
"type": "message_start",
"message": map[string]any{
"id": "msg_" + strings.TrimPrefix(id, "chatcmpl-"), "type": "message", "role": "assistant",
"model": t.model, "content": []any{}, "usage": map[string]any{"input_tokens": 0, "output_tokens": 0},
},
}))
}
// 文本:delta.content(string;兼容 {type:text,text} 数组)
if content := deltaText(delta); content != "" {
if t.textIndex < 0 {
t.textIndex = t.nextIndex
t.nextIndex++
ensureStarted()
out = append(out, eventLine("content_block_start", map[string]any{
"type": "content_block_start", "index": t.textIndex, "content_block": map[string]any{"type": "text", "text": ""},
}))
t.openBlocks = append(t.openBlocks, t.textIndex)
}
out = append(out, eventLine("content_block_delta", map[string]any{
"type": "content_block_delta", "index": t.textIndex, "delta": map[string]any{"type": "text_delta", "text": content},
}))
}
// 工具调用:delta.tool_calls(并行调用各 index 独立成块;arguments 支持整段/分段两种流式)
if tcs, ok := delta["tool_calls"].([]any); ok {
for _, tc := range tcs {
call, ok := tc.(map[string]any)
if !ok {
continue
}
idx, _ := call["index"].(float64)
tcIdx := int(idx)
fn, _ := call["function"].(map[string]any)
name, _ := fn["name"].(string)
args, _ := fn["arguments"].(string)
blockIdx, seen := t.toolIdx[tcIdx]
if !seen {
blockIdx = t.nextIndex
t.nextIndex++
t.toolIdx[tcIdx] = blockIdx
toolID, _ := call["id"].(string)
ensureStarted()
out = append(out, eventLine("content_block_start", map[string]any{
"type": "content_block_start", "index": blockIdx, "content_block": map[string]any{
"type": "tool_use", "id": toolID, "name": name, "input": map[string]any{},
},
}))
t.openBlocks = append(t.openBlocks, blockIdx)
}
if args != "" {
out = append(out, eventLine("content_block_delta", map[string]any{
"type": "content_block_delta", "index": blockIdx, "delta": map[string]any{"type": "input_json_delta", "partial_json": args},
}))
}
}
}
if u, ok := m["usage"]; ok {
t.usage = u
}
return joinLines(out)
}
// deltaText 取 chat delta.content 文本(string 或 [{type:text,text}] 数组拼接)。
func deltaText(delta map[string]any) string {
if s, ok := delta["content"].(string); ok {
return s
}
if arr, ok := delta["content"].([]any); ok {
var parts []string
for _, b := range arr {
if bm, ok := b.(map[string]any); ok {
if t, _ := bm["text"].(string); t != "" {
parts = append(parts, t)
}
}
}
return strings.Join(parts, "")
}
return ""
}
func stopReasonOrEnd(s string) string {
if s == "" {
return "end_turn"
}
return chatStopToMessages(s)
}
// ---------------------------------------------------------------------------
// Responses → Messages
type responsesToMessages struct {
sseState
started bool
model string
usage any
nextIndex int // 下一个 content block index(顺序分配)
textIndex int // 文本块 index;-1 = 未开始
toolIdx map[string]int // function_call item_id → messages block index
openBlocks []int // 已开始未停止的 block index,按开始顺序
anyTool bool
}
func newResponsesToMessages() *responsesToMessages {
return &responsesToMessages{textIndex: -1, toolIdx: map[string]int{}}
}
func (t *responsesToMessages) line(line []byte) []byte {
isData, data, done := t.parseLine(line)
if !isData || done {
return nil
}
m := eventData(data)
evt, _ := m["type"].(string)
if resp, ok := m["response"].(map[string]any); ok {
if t.model == "" {
t.model, _ = resp["model"].(string)
}
if u, ok := resp["usage"]; ok {
t.usage = u
}
}
var out [][]byte
// message_start 只在 response.created 时发出;文本/工具块在对应事件到达时再开,
// 避免纯函数调用响应提前开出一个空文本块。
ensureStarted := func() {
if t.started {
return
}
t.started = true
rid := ""
if resp, ok := m["response"].(map[string]any); ok {
rid, _ = resp["id"].(string)
}
out = append(out, eventLine("message_start", map[string]any{
"type": "message_start",
"message": map[string]any{
"id": "msg_" + strings.TrimPrefix(rid, "resp_"), "type": "message", "role": "assistant",
"model": t.model, "content": []any{},
},
}))
}
switch evt {
case "response.created":
ensureStarted()
case "response.output_text.delta":
delta, _ := m["delta"].(string)
if delta == "" {
return nil
}
if t.textIndex < 0 {
t.textIndex = t.nextIndex
t.nextIndex++
ensureStarted()
out = append(out, eventLine("content_block_start", map[string]any{
"type": "content_block_start", "index": t.textIndex, "content_block": map[string]any{"type": "text", "text": ""},
}))
t.openBlocks = append(t.openBlocks, t.textIndex)
}
out = append(out, eventLine("content_block_delta", map[string]any{
"type": "content_block_delta", "index": t.textIndex, "delta": map[string]any{"type": "text_delta", "text": delta},
}))
case "response.output_item.added":
item, _ := m["item"].(map[string]any)
if item == nil || item["type"] != "function_call" {
return nil
}
blockIdx := t.nextIndex
t.nextIndex++
t.anyTool = true
itemID, _ := item["id"].(string)
t.toolIdx[itemID] = blockIdx
toolUseID, _ := item["call_id"].(string)
if toolUseID == "" {
toolUseID = itemID
}
name, _ := item["name"].(string)
ensureStarted()
out = append(out, eventLine("content_block_start", map[string]any{
"type": "content_block_start", "index": blockIdx, "content_block": map[string]any{
"type": "tool_use", "id": toolUseID, "name": name, "input": map[string]any{},
},
}))
t.openBlocks = append(t.openBlocks, blockIdx)
case "response.function_call_arguments.delta":
itemID, _ := m["item_id"].(string)
blockIdx, ok := t.toolIdx[itemID]
if !ok {
return nil
}
delta, _ := m["delta"].(string)
if delta == "" {
return nil
}
out = append(out, eventLine("content_block_delta", map[string]any{
"type": "content_block_delta", "index": blockIdx, "delta": map[string]any{"type": "input_json_delta", "partial_json": delta},
}))
case "response.completed":
for _, idx := range t.openBlocks {
out = append(out, eventLine("content_block_stop", map[string]any{"type": "content_block_stop", "index": idx}))
}
stop := "end_turn"
if t.anyTool {
stop = "tool_use"
}
md := map[string]any{"type": "message_delta", "delta": map[string]any{"stop_reason": stop, "stop_sequence": nil}}
if t.usage != nil {
md["usage"] = t.usage
}
out = append(out, eventLine("message_delta", md))
out = append(out, eventLine("message_stop", map[string]any{"type": "message_stop"}))
}
return joinLines(out)
}
// ---------------------------------------------------------------------------
// Messages → Responses
type messagesToResponses struct {
sseState
model string
usage any
done bool
}
func newMessagesToResponses() *messagesToResponses { return &messagesToResponses{} }
func (t *messagesToResponses) line(line []byte) []byte {
isData, data, done := t.parseLine(line)
if !isData || done {
return nil
}
m := eventData(data)
evt, _ := m["type"].(string)
if msg, ok := m["message"].(map[string]any); ok {
if t.model == "" {
t.model, _ = msg["model"].(string)
}
if u, ok := msg["usage"]; ok {
t.usage = u
}
}
if u, ok := m["usage"]; ok {
t.usage = u
}
var out [][]byte
switch evt {
case "message_start":
id, _ := m["message"].(map[string]any)
rid := ""
if id != nil {
rid, _ = id["id"].(string)
}
out = append(out, eventLine("response.created", map[string]any{
"type": "response.created",
"response": map[string]any{
"id": "resp_" + strings.TrimPrefix(rid, "msg_"), "object": "response", "model": t.model, "status": "in_progress",
},
}))
case "content_block_delta":
delta, _ := m["delta"].(map[string]any)
text, _ := delta["text"].(string)
if text != "" {
out = append(out, eventLine("response.output_text.delta", map[string]any{
"type": "response.output_text.delta", "delta": text, "item_id": "msg_1", "output_index": 0, "content_index": 0,
}))
}
case "message_stop":
if !t.done {
t.done = true
out = append(out, eventLine("response.completed", map[string]any{
"type": "response.completed",
"response": map[string]any{
"id": "resp_stream", "object": "response", "model": t.model, "status": "completed", "usage": t.usage,
},
}))
}
}
return joinLines(out)
}
// ---------------------------------------------------------------------------
// Responses → Chat
type responsesToChat struct {
sseState
id, model string
}
func newResponsesToChat() *responsesToChat { return &responsesToChat{} }
func (t *responsesToChat) line(line []byte) []byte {
isData, data, done := t.parseLine(line)
if !isData {
return nil
}
if done {
return nil
}
m := eventData(data)
evt, _ := m["type"].(string)
if resp, ok := m["response"].(map[string]any); ok {
if t.model == "" {
t.model, _ = resp["model"].(string)
}
if t.id == "" {
t.id, _ = resp["id"].(string)
}
}
var out [][]byte
switch evt {
case "response.created":
out = append(out, dataLine(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(t.id, "resp_"), "object": "chat.completion.chunk", "model": t.model,
"choices": []any{map[string]any{"index": 0, "delta": map[string]any{"role": "assistant"}, "finish_reason": nil}},
}))
case "response.output_text.delta":
delta, _ := m["delta"].(string)
if delta != "" {
out = append(out, dataLine(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(t.id, "resp_"), "object": "chat.completion.chunk", "model": t.model,
"choices": []any{map[string]any{"index": 0, "delta": map[string]any{"content": delta}, "finish_reason": nil}},
}))
}
case "response.completed":
out = append(out, dataLine(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(t.id, "resp_"), "object": "chat.completion.chunk", "model": t.model,
"choices": []any{map[string]any{"index": 0, "delta": map[string]any{}, "finish_reason": "stop"}},
}))
if u, ok := m["response"].(map[string]any); ok {
if usage, ok := u["usage"]; ok {
out = append(out, dataLine(map[string]any{
"id": "chatcmpl-" + strings.TrimPrefix(t.id, "resp_"), "object": "chat.completion.chunk", "model": t.model,
"choices": []any{}, "usage": usage,
}))
}
}
out = append(out, []byte("data: [DONE]\n\n"))
}
return joinLines(out)
}
// ---------------------------------------------------------------------------
// Chat → Responses
type chatToResponses struct {
sseState
model string
usage any
finishSeen bool
done bool
createdSent bool
}
func newChatToResponses() *chatToResponses { return &chatToResponses{} }
func (t *chatToResponses) line(line []byte) []byte {
isData, data, done := t.parseLine(line)
if !isData {
return nil
}
if done {
// 流结束兜底:finish 后 usage 未随块到达时在此补发 completed
if !t.done {
t.done = true
return eventLine("response.completed", map[string]any{
"type": "response.completed",
"response": map[string]any{
"id": "resp_stream", "object": "response", "model": t.model, "status": "completed", "usage": t.usage,
},
})
}
return nil
}
m := eventData(data)
if t.model == "" {
t.model, _ = m["model"].(string)
}
if u, ok := m["usage"]; ok {
t.usage = u
}
delta := map[string]any{}
var finish string
if choices, ok := m["choices"].([]any); ok && len(choices) > 0 {
if c0, ok := choices[0].(map[string]any); ok {
if d, ok := c0["delta"].(map[string]any); ok {
delta = d
}
finish, _ = c0["finish_reason"].(string)
}
}
if finish != "" {
t.finishSeen = true
}
var out [][]byte
// 只发一次 response.created:部分上游(如 OpenRouter 的 reasoning 模型)会在
// 每个 chunk 的 delta 里都带 role:"assistant",不加守卫会刷出数十条 created。
if !t.createdSent && delta["role"] == "assistant" {
t.createdSent = true
out = append(out, eventLine("response.created", map[string]any{
"type": "response.created",
"response": map[string]any{"id": "resp_stream", "object": "response", "model": t.model, "status": "in_progress"},
}))
}
if content, _ := delta["content"].(string); content != "" {
out = append(out, eventLine("response.output_text.delta", map[string]any{
"type": "response.output_text.delta", "delta": content, "item_id": "msg_1", "output_index": 0, "content_index": 0,
}))
}
// 上游 usage 块(choices 为空)通常晚于 finish_reason:此时再发 completed,携带 usage
if _, hasUsage := m["usage"]; hasUsage && t.finishSeen && !t.done {
t.done = true
out = append(out, eventLine("response.completed", map[string]any{
"type": "response.completed",
"response": map[string]any{
"id": "resp_stream", "object": "response", "model": t.model, "status": "completed", "usage": t.usage,
},
}))
}
return joinLines(out)
}
+131
View File
@@ -0,0 +1,131 @@
package convert
import (
"encoding/json"
)
// TokenUsage 从上游响应提取的 token 用量。
// 三种协议的字段名不同,此处统一为:input / output / cache_read / cache_creation,
// 供用量记录与计费使用。
type TokenUsage struct {
InputTokens int
OutputTokens int
CacheReadTokens int
CacheCreationTokens int
}
// has 判断是否真的拿到了非零用量(过滤掉没有 usage 字段的响应)。
func (u *TokenUsage) has() bool {
return u.InputTokens > 0 || u.OutputTokens > 0 ||
u.CacheReadTokens > 0 || u.CacheCreationTokens > 0
}
// mergeJSON 把一张 usage 对象并入累计值。proto 决定字段名(chat/responses 与 messages 不同)。
func (u *TokenUsage) mergeJSON(raw map[string]any, proto string) {
switch proto {
case ProtoChat, ProtoResponses:
in, _ := raw["prompt_tokens"].(float64)
out, _ := raw["completion_tokens"].(float64)
if in == 0 && out == 0 {
in, _ = raw["input_tokens"].(float64)
out, _ = raw["output_tokens"].(float64)
}
u.InputTokens += int(in)
u.OutputTokens += int(out)
if d, ok := raw["prompt_tokens_details"].(map[string]any); ok {
if c, _ := d["cached_tokens"].(float64); c > 0 {
u.CacheReadTokens += int(c)
}
}
if d, ok := raw["input_tokens_details"].(map[string]any); ok {
if c, _ := d["cached_tokens"].(float64); c > 0 {
u.CacheReadTokens += int(c)
}
}
case ProtoMessages:
in, _ := raw["input_tokens"].(float64)
out, _ := raw["output_tokens"].(float64)
u.InputTokens += int(in)
u.OutputTokens += int(out)
if c, _ := raw["cache_read_input_tokens"].(float64); c > 0 {
u.CacheReadTokens += int(c)
}
if c, _ := raw["cache_creation_input_tokens"].(float64); c > 0 {
u.CacheCreationTokens += int(c)
}
}
}
// ExtractUsageJSON 从完整非流式响应体中提取用量。proto 为上游协议。
// 返回 (用量, 是否有效)。
func ExtractUsageJSON(body []byte, proto string) (TokenUsage, bool) {
var top map[string]any
if err := json.Unmarshal(body, &top); err != nil {
return TokenUsage{}, false
}
var u TokenUsage
if usage, ok := top["usage"].(map[string]any); ok {
u.mergeJSON(usage, proto)
}
return u, u.has()
}
// StreamUsageAccum 流式用量累计器。逐行喂入上游 SSE 的 data 载荷,
// 按协议分别取各事件里的 usage 字段(各事件只会携带一部分字段,取最大值合并)。
type StreamUsageAccum struct {
u TokenUsage
}
// NewStreamUsageAccum 创建一个流式用量累计器。
func NewStreamUsageAccum() *StreamUsageAccum {
return &StreamUsageAccum{}
}
// Feed 喂入一行 SSE data 载荷(不含 "data:" 前缀与换行)。
func (a *StreamUsageAccum) Feed(payload []byte, proto string) {
var top map[string]any
if json.Unmarshal(payload, &top) != nil {
return
}
var t TokenUsage
switch proto {
case ProtoChat:
if usage, ok := top["usage"].(map[string]any); ok {
t.mergeJSON(usage, proto)
}
case ProtoResponses:
// response.completed 事件把用量放在 response.usage 下。
if resp, ok := top["response"].(map[string]any); ok {
if usage, ok := resp["usage"].(map[string]any); ok {
t.mergeJSON(usage, proto)
}
}
case ProtoMessages:
// message_start: {message: {usage: {input_tokens, cache_*}}}
// message_delta: {usage: {output_tokens}}
if msg, ok := top["message"].(map[string]any); ok {
if usage, ok := msg["usage"].(map[string]any); ok {
t.mergeJSON(usage, proto)
}
}
if usage, ok := top["usage"].(map[string]any); ok {
var t2 TokenUsage
t2.mergeJSON(usage, proto)
t.InputTokens = max(t.InputTokens, t2.InputTokens)
t.OutputTokens = max(t.OutputTokens, t2.OutputTokens)
t.CacheReadTokens = max(t.CacheReadTokens, t2.CacheReadTokens)
t.CacheCreationTokens = max(t.CacheCreationTokens, t2.CacheCreationTokens)
}
default:
return
}
a.u.InputTokens = max(a.u.InputTokens, t.InputTokens)
a.u.OutputTokens = max(a.u.OutputTokens, t.OutputTokens)
a.u.CacheReadTokens = max(a.u.CacheReadTokens, t.CacheReadTokens)
a.u.CacheCreationTokens = max(a.u.CacheCreationTokens, t.CacheCreationTokens)
}
// Usage 返回当前累计用量。
func (a *StreamUsageAccum) Usage() TokenUsage {
return a.u
}
@@ -0,0 +1,170 @@
package convert
import (
"encoding/json"
"testing"
)
// ---- ExtractUsageJSON: 非流式各协议 ----
func TestExtractUsageJSONChat(t *testing.T) {
body := []byte(`{
"id": "chatcmpl-1",
"object": "chat.completion",
"choices": [{"index": 0, "message": {"role": "assistant", "content": "hi"}}],
"usage": {
"prompt_tokens": 11,
"completion_tokens": 7,
"total_tokens": 18,
"prompt_tokens_details": {"cached_tokens": 4}
}
}`)
u, ok := ExtractUsageJSON(body, ProtoChat)
if !ok {
t.Fatalf("expected ok=true")
}
if u.InputTokens != 11 || u.OutputTokens != 7 {
t.Fatalf("chat usage = %+v, want input=11 output=7", u)
}
if u.CacheReadTokens != 4 {
t.Fatalf("chat cacheRead = %d, want 4", u.CacheReadTokens)
}
}
func TestExtractUsageJSONMessages(t *testing.T) {
body := []byte(`{
"id": "msg_1",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "hi"}],
"usage": {
"input_tokens": 15,
"output_tokens": 8,
"cache_read_input_tokens": 3,
"cache_creation_input_tokens": 2
}
}`)
u, ok := ExtractUsageJSON(body, ProtoMessages)
if !ok {
t.Fatalf("expected ok=true")
}
if u.InputTokens != 15 || u.OutputTokens != 8 || u.CacheReadTokens != 3 || u.CacheCreationTokens != 2 {
t.Fatalf("messages usage = %+v", u)
}
}
func TestExtractUsageJSONResponses(t *testing.T) {
body := []byte(`{
"id": "resp_1",
"object": "response",
"output": [],
"usage": {
"input_tokens": 13,
"output_tokens": 9,
"input_tokens_details": {"cached_tokens": 5}
}
}`)
u, ok := ExtractUsageJSON(body, ProtoResponses)
if !ok {
t.Fatalf("expected ok=true")
}
if u.InputTokens != 13 || u.OutputTokens != 9 || u.CacheReadTokens != 5 {
t.Fatalf("responses usage = %+v", u)
}
}
func TestExtractUsageJSONInvalidAndMissing(t *testing.T) {
if _, ok := ExtractUsageJSON([]byte("not json"), ProtoChat); ok {
t.Fatalf("invalid json should not report ok")
}
if _, ok := ExtractUsageJSON([]byte(`{"id": "x"}`), ProtoChat); ok {
t.Fatalf("missing usage should not report ok")
}
// 空对象 usage:全 0 视为无效
if _, ok := ExtractUsageJSON([]byte(`{"usage": {}}`), ProtoChat); ok {
t.Fatalf("empty usage should not report ok")
}
}
// ---- StreamUsageAccum: 流式各协议 ----
func feedLines(t *testing.T, proto string, lines ...string) TokenUsage {
t.Helper()
acc := NewStreamUsageAccum()
for _, ln := range lines {
acc.Feed([]byte(ln), proto)
}
return acc.Usage()
}
func TestStreamUsageChatFinalChunk(t *testing.T) {
// 前面的 chunk 不带 usage;最后一个 chunk 带完整 usage
u := feedLines(t, ProtoChat,
`{"id":"c1","object":"chat.completion.chunk","choices":[{"delta":{"content":"he"}}]}`,
`{"id":"c1","object":"chat.completion.chunk","choices":[{"delta":{"content":"llo"}}]}`,
`{"id":"c1","object":"chat.completion.chunk","choices":[],"usage":{"prompt_tokens":11,"completion_tokens":7,"prompt_tokens_details":{"cached_tokens":4}}}`,
)
if u.InputTokens != 11 || u.OutputTokens != 7 || u.CacheReadTokens != 4 {
t.Fatalf("chat stream usage = %+v", u)
}
}
func TestStreamUsageMessagesStartAndDelta(t *testing.T) {
// message_start 带 input/cache,message_delta 带 output;逐字段取 max 合并
u := feedLines(t, ProtoMessages,
`{"type":"message_start","message":{"id":"msg_1","usage":{"input_tokens":15,"cache_read_input_tokens":3,"cache_creation_input_tokens":2}}}`,
`{"type":"content_block_delta","delta":{"type":"text_delta","text":"hi"}}`,
`{"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":8}}`,
)
if u.InputTokens != 15 || u.OutputTokens != 8 || u.CacheReadTokens != 3 || u.CacheCreationTokens != 2 {
t.Fatalf("messages stream usage = %+v", u)
}
}
func TestStreamUsageResponsesCompleted(t *testing.T) {
// response.completed 事件的用量嵌在 response.usage 下
u := feedLines(t, ProtoResponses,
`{"type":"response.output_text.delta","delta":"hi"}`,
`{"type":"response.completed","response":{"id":"resp_1","usage":{"input_tokens":13,"output_tokens":9,"input_tokens_details":{"cached_tokens":5}}}}`,
)
if u.InputTokens != 13 || u.OutputTokens != 9 || u.CacheReadTokens != 5 {
t.Fatalf("responses stream usage = %+v", u)
}
}
func TestStreamUsageIgnoresNonDataPayloads(t *testing.T) {
// [DONE]、垃圾行、空对象都不应产生用量
u := feedLines(t, ProtoChat, `[DONE]`, `{`, ``, `{"choices":[]}`)
if u.has() {
t.Fatalf("expected zero usage, got %+v", u)
}
}
func TestStreamUsageFeedKeepsMaxAcrossEvents(t *testing.T) {
// 同一字段在多个事件出现时取较大值(防乱序/重复)
u := feedLines(t, ProtoMessages,
`{"type":"message_start","message":{"usage":{"input_tokens":15}}}`,
`{"type":"message_delta","usage":{"output_tokens":5}}`,
`{"type":"message_delta","usage":{"output_tokens":8}}`,
)
if u.InputTokens != 15 || u.OutputTokens != 8 {
t.Fatalf("max-merge usage = %+v", u)
}
}
// ---- usage JSON 结构合法性(防止手写 struct 漂移)----
func TestUsageJSONRoundTrip(t *testing.T) {
u := TokenUsage{InputTokens: 10, OutputTokens: 5, CacheReadTokens: 2, CacheCreationTokens: 1}
b, err := json.Marshal(u)
if err != nil {
t.Fatalf("marshal: %v", err)
}
var back TokenUsage
if err := json.Unmarshal(b, &back); err != nil {
t.Fatalf("unmarshal: %v", err)
}
if back != u {
t.Fatalf("round trip = %+v, want %+v", back, u)
}
}
+103 -108
View File
@@ -1,6 +1,7 @@
package proxy
import (
"bufio"
"bytes"
"context"
"encoding/json"
@@ -13,6 +14,7 @@ import (
"opencatd-open/internal/dao"
"opencatd-open/internal/proxy/convert"
"opencatd-open/internal/store"
"opencatd-open/internal/usage"
"opencatd-open/pkg/config"
"os"
"strings"
@@ -35,6 +37,7 @@ type Gateway struct {
usageDAO *dao.UsageDAO
dailyDAO *dao.DailyUsageDAO
channelSvc *channel.Service
usageRec *usage.Recorder
}
func NewGateway(ctx context.Context, cfg *config.Config, db *gorm.DB, wg *sync.WaitGroup, userDAO *dao.UserDAO, apiKeyDAO *dao.ApiKeyDAO, usageDAO *dao.UsageDAO, dailyDAO *dao.DailyUsageDAO) *Gateway {
@@ -67,6 +70,11 @@ func (g *Gateway) SetChannelService(svc *channel.Service) {
g.channelSvc = svc
}
// SetUsageRecorder 注入异步用量记录器;nil 时网关跳过用量上报。
func (g *Gateway) SetUsageRecorder(r *usage.Recorder) {
g.usageRec = r
}
// Request represents a parsed incoming request
type Request struct {
Model string
@@ -144,26 +152,24 @@ func (g *Gateway) Dispatch(c *gin.Context, req *Request) {
return
}
// Determine target format and convert if needed
targetFormat := req.Protocol
if len(ch.FormatsEffective()) > 0 {
// Prefer the channel's native format
for _, f := range ch.FormatsEffective() {
if f == req.Protocol {
targetFormat = f
break
}
}
// Determine target format: channel declares support for the client protocol
// then passthrough, otherwise convert to its first supported protocol
// (chat > messages > responses).
targetFormat := g.conversionTarget(ch, req.Protocol)
if targetFormat == "" {
g.writeError(c, http.StatusBadGateway, fmt.Sprintf("channel %q declares no supported protocol format", ch.Name))
return
}
// Build upstream URL
upstreamPath := g.getUpstreamPath(req.Protocol)
upstreamURL := ch.UpstreamURL(req.Protocol, upstreamPath)
upstreamPath := g.getUpstreamPath(targetFormat)
upstreamURL := ch.UpstreamURL(targetFormat, upstreamPath)
// Convert request if needed
var requestBody []byte
if targetFormat != req.Protocol {
requestBody, err = g.convertRequest(req.Body, req.Protocol, targetFormat)
var err error
requestBody, err = convert.ConvertRequest(req.Body, req.Protocol, targetFormat)
if err != nil {
g.writeError(c, http.StatusBadRequest, "conversion failed: "+err.Error())
return
@@ -206,12 +212,31 @@ func (g *Gateway) Dispatch(c *gin.Context, req *Request) {
// Stream or buffer response
if req.Stream {
g.streamResponse(c, resp, req.Protocol, ch)
g.streamResponse(c, resp, req.Protocol, targetFormat)
} else {
g.bufferResponse(c, resp, req.Protocol, ch)
g.bufferResponse(c, resp, req.Protocol, targetFormat)
}
}
// conversionTarget 决定客户端协议在渠道上的处理方式:
// 渠道声明支持该协议则直通;否则转为其首选支持协议(chat > messages > responses)。
func (g *Gateway) conversionTarget(ch *store.Channel, clientProto string) string {
formats := ch.FormatsEffective()
for _, f := range formats {
if f == clientProto {
return clientProto
}
}
for _, p := range []string{convert.ProtoChat, convert.ProtoMessages, convert.ProtoResponses} {
for _, f := range formats {
if f == p {
return p
}
}
}
return ""
}
func (g *Gateway) getUpstreamPath(protocol string) string {
switch protocol {
case "chat":
@@ -237,116 +262,86 @@ func (g *Gateway) setHeaders(req *http.Request, ch *store.Channel, apiKey string
}
}
func (g *Gateway) convertRequest(body []byte, from, to string) ([]byte, error) {
switch {
case from == "chat" && to == "messages":
var req convert.ChatCompletionRequest
if err := json.Unmarshal(body, &req); err != nil {
return nil, err
}
msgReq, err := convert.ChatToMessages(&req)
if err != nil {
return nil, err
}
return json.Marshal(msgReq)
case from == "chat" && to == "responses":
var req convert.ChatCompletionRequest
if err := json.Unmarshal(body, &req); err != nil {
return nil, err
}
respReq, err := convert.ChatToResponses(&req)
if err != nil {
return nil, err
}
return json.Marshal(respReq)
case from == "messages" && to == "chat":
var req convert.MessagesRequest
if err := json.Unmarshal(body, &req); err != nil {
return nil, err
}
// Messages -> Chat: we need to construct a ChatCompletionRequest
chatReq := &convert.ChatCompletionRequest{
Model: req.Model,
}
for _, m := range req.Messages {
chatReq.Messages = append(chatReq.Messages, m)
}
if req.Temperature != nil {
chatReq.Temperature = req.Temperature
}
if req.TopP != nil {
chatReq.TopP = req.TopP
}
chatReq.Tools = req.Tools
chatReq.Stream = req.Stream
return json.Marshal(chatReq)
case from == "responses" && to == "chat":
var req convert.ResponsesRequest
if err := json.Unmarshal(body, &req); err != nil {
return nil, err
}
chatReq := &convert.ChatCompletionRequest{
Model: req.Model,
}
for _, item := range req.Input {
chatReq.Messages = append(chatReq.Messages, convert.Message{
Role: item.Role,
Content: item.Content,
})
}
chatReq.Tools = req.Tools
chatReq.Stream = req.Stream
return json.Marshal(chatReq)
default:
return body, nil
}
}
func (g *Gateway) streamResponse(c *gin.Context, resp *http.Response, protocol string, ch *store.Channel) {
// streamResponse 流式响应:按 \n\n 分块零缓冲转发;跨协议时逐行转换。
func (g *Gateway) streamResponse(c *gin.Context, resp *http.Response, clientProto, upstreamProto string) {
w := c.Writer
c.Header("Content-Type", "text/event-stream")
c.Header("Cache-Control", "no-cache")
c.Header("Connection", "keep-alive")
c.Status(http.StatusOK)
writer := convert.NewSSEWriter(c.Writer)
parser := convert.NewSSEParser(resp.Body)
flusher, _ := w.(http.Flusher)
for {
event, err := parser.ReadEvent()
if err != nil {
if err == io.EOF {
break
}
log.Printf("Stream parse error: %v", err)
break
}
if event.Event == "error" {
log.Printf("Upstream stream error: %s", event.Data)
break
}
// Write raw SSE event based on protocol
if err := writer.WriteEvent("chat CompletionChunk", event.Data); err != nil {
break
}
// 跨协议时按行转换;同协议直通(lineConv 为 nil)。
var lineConv func([]byte) []byte
if upstreamProto != clientProto {
lineConv = convert.NewStreamTransformer(upstreamProto, clientProto)
}
writer.WriteDone()
// 上游原始行按 \n\n 分块,避免把 data 行内的转义换行当成事件边界。
r := bufio.NewReaderSize(resp.Body, 32*1024)
for {
buf := []byte{}
for {
line, err := r.ReadSlice('\n')
if err == bufio.ErrBufferFull {
buf = append(buf, line...)
continue
}
buf = append(buf, line...)
if err == io.EOF {
if len(buf) == 0 {
return
}
if !bytes.HasSuffix(buf, []byte("\n")) {
buf = append(buf, '\n')
}
} else if err != nil {
log.Printf("stream read error: %v", err)
return
}
if len(buf) >= 2 && bytes.HasSuffix(buf, []byte("\n\n")) {
break
}
}
out := buf
if lineConv != nil {
out = lineConv(buf)
}
if len(out) == 0 {
continue
}
if _, err := w.Write(out); err != nil {
return // 客户端已断开
}
if flusher != nil {
flusher.Flush()
}
}
}
func (g *Gateway) bufferResponse(c *gin.Context, resp *http.Response, protocol string, ch *store.Channel) {
func (g *Gateway) bufferResponse(c *gin.Context, resp *http.Response, clientProto, upstreamProto string) {
body, err := io.ReadAll(resp.Body)
if err != nil {
g.writeError(c, http.StatusBadGateway, "failed to read response")
return
}
c.Data(resp.StatusCode, "application/json", body)
out := body
if upstreamProto != clientProto {
if converted, cerr := convert.ConvertResponse(body, upstreamProto, clientProto); cerr == nil {
out = converted
} else {
// 转换失败时至少剥掉非 JSON 前缀,让客户端能解析出正文
out = convert.CleanJSON(body)
}
} else {
// 直通:部分上游(如 OpenRouter)的 non-stream 响应在 JSON 前夹带空白/注释
out = convert.CleanJSON(body)
}
c.Data(resp.StatusCode, "application/json", out)
}
func (g *Gateway) writeError(c *gin.Context, status int, message string) {
+79 -19
View File
@@ -2,6 +2,7 @@ package usage
import (
"context"
"fmt"
"log"
"opencatd-open/internal/dao"
"opencatd-open/internal/store"
@@ -11,16 +12,26 @@ import (
// Event represents a usage event to be recorded
type Event struct {
UserID uint64
ModelName string
ChannelID uint64
PromptTokens int
CompletionTokens int
CacheReadTokens int
Cost float64
IsError bool
IsCanceled bool
RequestID string
UserID uint64
ModelName string
ChannelID uint64
PromptTokens int
CompletionTokens int
CacheReadTokens int
CacheCreationTokens int
Cost float64
IsError bool
IsCanceled bool
RequestID string
KeyID uint64
Protocol string
ErrorCode string
LatencyMS int
InputPrice float64
OutputPrice float64
CacheReadPrice float64
TraceID string // TraceID for distributed tracing
ModelID uint64 // Model ID from channel-model binding
}
// Recorder handles async usage recording
@@ -117,16 +128,31 @@ func (r *Recorder) flush(events []Event) {
status = store.UsageStatusCanceled
}
var errCode *string
if e.ErrorCode != "" {
errCode = &e.ErrorCode
}
log := &store.UsageLog{
UserID: e.UserID,
ModelName: e.ModelName,
ChannelID: e.ChannelID,
InputTokens: int64(e.PromptTokens),
OutputTokens: int64(e.CompletionTokens),
CacheReadTokens: int64(e.CacheReadTokens),
Cost: e.Cost,
Status: status,
RequestID: e.RequestID,
UserID: e.UserID,
KeyID: e.KeyID,
ChannelID: e.ChannelID,
ModelID: e.ModelID,
ModelName: e.ModelName,
Protocol: e.Protocol,
InputTokens: int64(e.PromptTokens),
OutputTokens: int64(e.CompletionTokens),
CacheReadTokens: int64(e.CacheReadTokens),
CacheCreationTokens: int64(e.CacheCreationTokens),
InputPrice: e.InputPrice,
OutputPrice: e.OutputPrice,
CacheReadPrice: e.CacheReadPrice,
Cost: e.Cost,
LatencyMS: e.LatencyMS,
Status: status,
ErrorCode: errCode,
RequestID: e.RequestID,
TraceID: e.TraceID,
}
logs = append(logs, log)
}
@@ -136,5 +162,39 @@ func (r *Recorder) flush(events []Event) {
log.Printf("Failed to batch create usage logs: %v", err)
}
// Daily rollup for success and canceled requests
dailyMap := make(map[string]*store.UsageDaily)
for _, e := range events {
if e.IsError {
continue
}
date := time.Now().Format("2006-01-02")
key := fmt.Sprintf("%d:%d:%s", e.UserID, e.ModelID, date)
d := dailyMap[key]
if d == nil {
d = &store.UsageDaily{
UserID: e.UserID,
ModelID: e.ModelID,
Date: date,
Requests: 0,
InputTokens: 0,
OutputTokens: 0,
CacheReadTokens: 0,
Cost: 0,
}
dailyMap[key] = d
}
d.Requests++
d.InputTokens += int64(e.PromptTokens)
d.OutputTokens += int64(e.CompletionTokens)
d.CacheReadTokens += int64(e.CacheReadTokens)
d.Cost += e.Cost
}
for _, d := range dailyMap {
if err := r.dailyDAO.UpsertDailyUsage(context.Background(), d); err != nil {
log.Printf("Failed to upsert daily usage: %v", err)
}
}
log.Printf("Flushed %d usage logs", len(logs))
}