Files
openteam/server/internal/store/models.go
Sakurasan 04dfb4285d feat: 会话亲和粘住缓存渠道;透传 opaque 字段;用量记思考/1h 缓存写/实际模型
会话亲和(proxy/affinity.go):同一会话粘住上次应答的渠道,命中上游提示词
缓存而非被加权随机打散后全价重算。会话身份 = 密钥 + 模型 + 请求文本稳定前缀
摘要,不依赖各客户端会话头;TTL 默认 5m(OT_PROXY_AFFINITY_TTL,0=关闭),
成功应答刷新。亲和渠道必须在候选集内(健康/未冷却/绑定),否则回退加权随机。
proxyOne 增加 served 返回值区分「应答成功」与「已终结但失败」。

opaque 透传(convert):chat↔responses 互转原样携带 metadata、service_tier、
parallel_tool_calls。此前逐字段重建请求体会丢它们,而中转上游会校验/使用。

用量细化(proxy+store):usage_logs 新增 reasoning_tokens(展示口径,不重复
计费)、cache_write_1h_tokens(Anthropic 1h 缓存写按 2× 输入价,此前统一
1.25× 少算 60%)、served_model(上游实际应答模型,映射/聚合商场景对账)。
schema v6→v7。

验证:go vet ./... 干净;go test ./... 与 go test -race ./... 全绿;
新增测试覆盖亲和粘性与冷却回退、opaque 双向透传、reasoning 不重复计费、
1h/5m 缓存写分开计价、served_model 提取(非流式与流式)。
2026-10-30 11:41:51 +08:00

287 lines
14 KiB
Go
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
// Package store 数据模型与仓储层(GORM)。
// 字段设计对应 PLANNING.md §6:金额/价格 numeric(20,8),token bigint,时间 UTC。
package store
import (
"regexp"
"strings"
"time"
)
// 角色 / 状态枚举(字符串存库,便于阅读与迁移)
const (
RoleUser = "user"
RoleAdmin = "admin"
UserStatusActive = "active"
UserStatusDisabled = "disabled"
KeyStatusActive = "active"
KeyStatusRevoked = "revoked"
ChannelProviderOpenAI = "openai"
ChannelProviderAnthropic = "anthropic"
ChannelProviderCompatible = "compatible"
ChannelHealthHealthy = "healthy"
ChannelHealthDegraded = "degraded"
ChannelHealthCooldown = "cooldown"
// 渠道原生支持的协议格式
FormatChat = "chat" // OpenAI Chat Completions
FormatResponses = "responses" // OpenAI Responses API
FormatMessages = "messages" // Anthropic Messages
UsageStatusSuccess = "success"
UsageStatusError = "error"
UsageStatusCanceled = "canceled"
BalanceTypeRecharge = "recharge"
BalanceTypeUsage = "usage"
BalanceTypeRefund = "refund"
BalanceTypeAdminAdjust = "admin_adjust"
RechargeStatusPending = "pending"
RechargeStatusCredited = "credited"
RechargeStatusRejected = "rejected"
RechargeMethodManual = "manual"
RechargeMethodOnline = "online"
)
// User 用户(PLANNING §6.1)
type User struct {
ID uint64 `gorm:"primaryKey;autoIncrement" json:"id"`
Username string `gorm:"uniqueIndex;size:64;not null" json:"username"`
Email string `gorm:"uniqueIndex;size:255;not null" json:"email"`
PasswordHash string `gorm:"size:255;not null" json:"-"`
Role string `gorm:"size:16;not null;default:user" json:"role"`
Balance float64 `gorm:"type:numeric(20,8);not null;default:0" json:"balance"`
Status string `gorm:"size:16;not null;default:active" json:"status"`
TokenVersion int `gorm:"not null;default:0" json:"-"` // 会话版本:改密/登出递增,低于当前版本的 token 全部失效
AllowedModels []string `gorm:"type:jsonb;serializer:json" json:"allowed_models,omitempty"` // 用户级模型白名单(空=不限制)
DeniedModels []string `gorm:"type:jsonb;serializer:json" json:"denied_models,omitempty"` // 用户级模型黑名单
InviteCode *string `json:"invite_code,omitempty"`
LastLoginAt *time.Time `json:"last_login_at,omitempty"`
CreatedAt time.Time `json:"created_at"`
UpdatedAt time.Time `json:"updated_at"`
}
// APIKey 密钥(PLANNING §6.2):库中只存 SHA-256 哈希 + 展示前缀
type APIKey struct {
ID uint64 `gorm:"primaryKey;autoIncrement" json:"id"`
UserID uint64 `gorm:"index;not null" json:"user_id"`
Name string `gorm:"size:64;not null" json:"name"`
KeyHash string `gorm:"uniqueIndex;size:64;not null" json:"-"`
KeyPrefix string `gorm:"size:32;not null" json:"key_prefix"`
QuotaTokensPerDay *int64 `json:"quota_tokens_per_day,omitempty"`
QuotaRequestsPerDay *int `json:"quota_requests_per_day,omitempty"`
AllowedModels []string `gorm:"type:jsonb;serializer:json" json:"allowed_models,omitempty"`
ExpiresAt *time.Time `json:"expires_at,omitempty"`
Status string `gorm:"size:16;not null;default:active" json:"status"`
LastUsedAt *time.Time `json:"last_used_at,omitempty"`
CreatedAt time.Time `json:"created_at"`
UpdatedAt time.Time `json:"updated_at"`
}
// Channel 上游渠道(PLANNING §6.3)
type Channel struct {
ID uint64 `gorm:"primaryKey;autoIncrement" json:"id"`
Name string `gorm:"uniqueIndex;size:64;not null" json:"name"`
Provider string `gorm:"size:16;not null" json:"provider"` // openai|anthropic|compatible(供应商/默认格式)
Formats []string `gorm:"type:jsonb;serializer:json" json:"formats,omitempty"` // 原生支持的协议格式 chat|responses|messages
BaseURL string `gorm:"size:255;not null" json:"base_url"`
BaseURLs map[string]string `gorm:"type:jsonb;serializer:json" json:"base_urls,omitempty"` // 分协议 base_url 覆盖(chat/responses/messages)
APIKeyEnc string `gorm:"size:1024;not null" json:"-"` // AES-GCM 密文
Weight int `gorm:"not null;default:1" json:"weight"`
Priority int `gorm:"not null;default:0" json:"priority"` // 数值小优先
TimeoutMS int `gorm:"not null;default:300000" json:"timeout_ms"`
MaxConcurrency int `gorm:"not null;default:16" json:"max_concurrency"`
HealthStatus string `gorm:"size:16;not null;default:healthy" json:"health_status"`
Enabled bool `gorm:"not null;default:true" json:"enabled"`
CreatedAt time.Time `json:"created_at"`
UpdatedAt time.Time `json:"updated_at"`
}
// FormatsEffective 返回渠道实际支持的原生协议;未显式配置时按 provider 推断。
func (c *Channel) FormatsEffective() []string {
if len(c.Formats) > 0 {
return c.Formats
}
switch c.Provider {
case ChannelProviderAnthropic:
return []string{FormatMessages}
case ChannelProviderOpenAI:
return []string{FormatChat, FormatResponses}
default: // compatible
return []string{FormatChat}
}
}
// versionSegRe 匹配末尾版本前缀,如 /v1、/v2、/v4。
var versionSegRe = regexp.MustCompile(`/v[0-9]+/?$`)
// UpstreamURL 按协议选 base_url(分协议覆盖优先),再按版本前缀拼资源路径(path 不含 /v1)。
// - proto 有 BaseURLs 覆盖时用覆盖值,否则用主 BaseURL
// - base 已以资源路径结尾 → 原样
// - base 含版本前缀(如 /v1、/v4) → base + path
// - 否则 → base + /v1 + path(默认补 OpenAI/Anthropic 的 /v1)
func (c *Channel) UpstreamURL(proto, path string) string {
base := c.BaseURL
if len(c.BaseURLs) > 0 && c.BaseURLs[proto] != "" {
base = c.BaseURLs[proto]
}
base = strings.TrimRight(base, "/")
if base == "" {
return path
}
if strings.HasSuffix(base, path) {
return base
}
if versionSegRe.MatchString(base) {
return base + path
}
return base + "/v1" + path
}
// Model 全局模型 + 定价(PLANNING §6.4,价格按每百万 token,USD)
type Model struct {
ID uint64 `gorm:"primaryKey;autoIncrement" json:"id"`
Name string `gorm:"uniqueIndex;size:128;not null" json:"name"`
InputPrice float64 `gorm:"type:numeric(20,8);not null;default:0" json:"input_price"`
OutputPrice float64 `gorm:"type:numeric(20,8);not null;default:0" json:"output_price"`
CacheReadPrice float64 `gorm:"type:numeric(20,8);not null;default:0" json:"cache_read_price"`
// 缓存写价(每百万 token)。为 0 时按输入价 ×1.25 计(Anthropic 5m 口径),
// 显式配置它才能支持 1h 缓存(×2)这类不同倍率。
CacheWritePrice float64 `gorm:"type:numeric(20,8);not null;default:0" json:"cache_write_price"`
ContextLength int `gorm:"not null;default:0" json:"context_length"` // 上下文窗口(token),0=未知
SupportsTools bool `gorm:"not null;default:false" json:"supports_tools"`
SupportsVision bool `gorm:"not null;default:false" json:"supports_vision"`
SupportsReasoning bool `gorm:"not null;default:false" json:"supports_reasoning"`
Enabled bool `gorm:"not null;default:true" json:"enabled"`
Sort int `gorm:"not null;default:0" json:"sort"`
CreatedAt time.Time `json:"created_at"`
UpdatedAt time.Time `json:"updated_at"`
}
// CacheWritePriceOr 返回缓存写价;未配置时回退到输入价×1.25(Anthropic 5m 口径)。
func (m *Model) CacheWritePriceOr() float64 {
if m.CacheWritePrice > 0 {
return m.CacheWritePrice
}
return m.InputPrice * 1.25
}
// ChannelModelBinding 渠道↔模型绑定(多对多,PLANNING §6.4)
type ChannelModelBinding struct {
ID uint64 `gorm:"primaryKey;autoIncrement" json:"id"`
ChannelID uint64 `gorm:"index:idx_ch_model,unique;not null" json:"channel_id"`
ModelID uint64 `gorm:"index:idx_ch_model,unique;not null" json:"model_id"`
UpstreamModel string `gorm:"size:255;not null" json:"upstream_model"`
Weight int `gorm:"not null;default:1" json:"weight"`
Channel Channel `gorm:"foreignKey:ChannelID" json:"-"`
Model Model `gorm:"foreignKey:ModelID" json:"-"`
}
// UsageLog 请求级用量明细(PLANNING §6.5)
type UsageLog struct {
ID uint64 `gorm:"primaryKey;autoIncrement" json:"id"`
RequestID string `gorm:"size:128" json:"request_id"` // 上游 request id
TraceID string `gorm:"size:64;index" json:"trace_id"`
UserID uint64 `gorm:"index:idx_user_created,priority:1;not null" json:"user_id"`
KeyID uint64 `gorm:"index" json:"key_id"`
ChannelID uint64 `gorm:"index:idx_channel_created,priority:1" json:"channel_id"`
ModelID uint64 `json:"model_id"`
ModelName string `gorm:"size:128" json:"model_name"`
Protocol string `gorm:"size:32" json:"protocol"` // responses|chat|messages
InputTokens int64 `json:"input_tokens"`
OutputTokens int64 `json:"output_tokens"`
CacheReadTokens int64 `json:"cache_read_tokens"`
CacheCreationTokens int64 `json:"cache_creation_tokens"`
ReasoningTokens int64 `json:"reasoning_tokens"` // 思考 token(上游已计入 output,展示口径不重复计费)
CacheWrite1hTokens int64 `json:"cache_write_1h_tokens"` // Anthropic 1h 缓存写 token(计价 2× 输入)
ServedModel string `gorm:"size:128" json:"served_model"` // 上游实际应答的模型名(映射/聚合商场景与请求名不同)
InputPrice float64 `gorm:"type:numeric(20,8)" json:"input_price"` // 快照
OutputPrice float64 `gorm:"type:numeric(20,8)" json:"output_price"` // 快照
CacheReadPrice float64 `gorm:"type:numeric(20,8)" json:"cache_read_price"` // 快照
Cost float64 `gorm:"type:numeric(20,8)" json:"cost"`
LatencyMS int `json:"latency_ms"`
Status string `gorm:"size:16;not null" json:"status"`
ErrorCode *string `json:"error_code,omitempty"`
RawRequest string `gorm:"type:text" json:"raw_request"` // 客户端原始请求体(未转换)
RawResponse string `gorm:"type:text" json:"raw_response"` // 上游原始响应(未转换;流式为全部 SSE 事件)
// CreatedAt 同时参与 user/channel 两个复合索引(时间窗过滤),自身单列索引保留给全表时间扫
CreatedAt time.Time `gorm:"index;index:idx_user_created,priority:2;index:idx_channel_created,priority:2" json:"created_at"`
}
// UsageDaily 日粒度预聚合(PLANNING §6.6)
type UsageDaily struct {
ID uint64 `gorm:"primaryKey;autoIncrement" json:"id"`
UserID uint64 `gorm:"index:idx_daily_user_model,unique" json:"user_id"`
ModelID uint64 `gorm:"index:idx_daily_user_model,unique" json:"model_id"`
Date string `gorm:"size:10;index:idx_daily_user_model,unique" json:"date"` // YYYY-MM-DD (UTC)
Requests int64 `json:"requests"`
InputTokens int64 `json:"input_tokens"`
OutputTokens int64 `json:"output_tokens"`
CacheReadTokens int64 `json:"cache_read_tokens"`
Cost float64 `gorm:"type:numeric(20,8)" json:"cost"`
}
// RechargeOrder 充值订单(PLANNING §6.7,预留:首版不做充值)
type RechargeOrder struct {
ID uint64 `gorm:"primaryKey;autoIncrement" json:"id"`
UserID uint64 `gorm:"index;not null" json:"user_id"`
Amount float64 `gorm:"type:numeric(20,8);not null" json:"amount"`
Status string `gorm:"size:16;not null;default:pending" json:"status"`
Method string `gorm:"size:16;not null;default:manual" json:"method"`
TransactionID string `gorm:"size:128" json:"transaction_id,omitempty"`
ReviewedBy *uint64 `json:"reviewed_by,omitempty"`
ReviewedAt *time.Time `json:"reviewed_at,omitempty"`
Remark string `gorm:"size:512" json:"remark,omitempty"`
CreatedAt time.Time `json:"created_at"`
UpdatedAt time.Time `json:"updated_at"`
}
// BalanceLog 余额流水(PLANNING §6.8,幂等:ref_id + type 唯一)
type BalanceLog struct {
ID uint64 `gorm:"primaryKey;autoIncrement" json:"id"`
UserID uint64 `gorm:"index:idx_balance_user;not null" json:"user_id"`
Change float64 `gorm:"type:numeric(20,8);not null" json:"change"`
BalanceAfter float64 `gorm:"type:numeric(20,8);not null" json:"balance_after"`
Type string `gorm:"size:16;not null" json:"type"`
RefID string `gorm:"size:128;index:idx_balance_ref,unique" json:"ref_id"`
Remark string `gorm:"size:512" json:"remark,omitempty"`
CreatedAt time.Time `json:"created_at"`
}
// Passkey WebAuthn 凭据(passkey 绑定/登录)
type Passkey struct {
ID uint64 `gorm:"primaryKey;autoIncrement" json:"id"`
UserID uint64 `gorm:"index;not null" json:"user_id"`
Name string `gorm:"size:64" json:"name"`
CredentialID []byte `gorm:"size:255;not null" json:"-"` // credential.ID
Credential []byte `gorm:"type:blob;not null" json:"-"` // json.Marshal(webauthn.Credential)
CreatedAt time.Time `json:"created_at"`
}
// SystemConfig 系统配置(PLANNING §6.9)
type SystemConfig struct {
Key string `gorm:"primaryKey;size:64" json:"key"`
Value string `gorm:"type:jsonb;not null" json:"value"`
}
// AllModels 迁移顺序(外键依赖在后)
func AllModels() []any {
return []any{
&User{},
&APIKey{},
&Channel{},
&Model{},
&ChannelModelBinding{},
&UsageLog{},
&UsageDaily{},
&RechargeOrder{},
&BalanceLog{},
&Passkey{},
&SystemConfig{},
}
}