From 6255930d0d29c0e489ccc80bbab2dd2fe24afa19 Mon Sep 17 00:00:00 2001 From: qian Date: Mon, 17 Aug 2026 07:44:56 +0800 Subject: [PATCH] =?UTF-8?q?feat(model):=E6=B7=BB=E5=8A=A0=E6=B8=A0?= =?UTF-8?q?=E9=81=93=E7=9B=91=E6=8E=A7?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit --- api/admin/v1/monitor.go | 4 + internal/logic/monitor/api_metrics.go | 128 ++++++++++++++++-- internal/logic/monitor/api_metrics_test.go | 48 +++++++ internal/logic/monitor/monitor.go | 3 +- .../views/monitor/ModelPerformancePage.vue | 77 ++++++++++- 5 files changed, 246 insertions(+), 14 deletions(-) diff --git a/api/admin/v1/monitor.go b/api/admin/v1/monitor.go index 9d9688e..f6e44e1 100644 --- a/api/admin/v1/monitor.go +++ b/api/admin/v1/monitor.go @@ -37,6 +37,10 @@ type MonitorModelPerformanceReq struct { g.Meta `path:"/monitor/model-performance" method:"get" mime:"json" tags:"管理后台-监控" summary:"模型性能指标"` StartDate string `json:"start_date" in:"query"` // YYYY-MM-DD，缺省=近30天起点 EndDate string `json:"end_date" in:"query"` // YYYY-MM-DD，缺省=今天 + // 可选渠道筛选：0=全部渠道（选定渠道后当天数据改从 bil_usage_logs 明细实时聚合；0 哨兵被占用，无法筛「无渠道」） + ChannelId int64 `json:"channel_id" in:"query" d:"0"` + // 可选模型筛选：空=全部模型（与 bil_usage_daily.model_name 同口径） + ModelName string `json:"model_name" in:"query"` } type MonitorModelPerformanceRes struct { diff --git a/internal/logic/monitor/api_metrics.go b/internal/logic/monitor/api_metrics.go index 9433ea1..130cbbb 100644 --- a/internal/logic/monitor/api_metrics.go +++ b/internal/logic/monitor/api_metrics.go @@ -156,13 +156,17 @@ type perfModelAgg struct { cacheHitRequests int64 } -// GetModelPerformance 从 bil_usage_daily 按模型聚合历史性能指标，并合并当日 Redis 实时热桶 -// （见 common.RecordModelPerfMetrics，桶粒度小时），使页面当天即可看到最新数据，不再滞后一天。 +// GetModelPerformance 从 bil_usage_daily 按模型聚合历史性能指标，并合并当日实时数据， +// 支持可选的渠道（channelID，0=全部）与模型（modelName，空=全部）过滤：选定渠道后可查看 +// 该渠道下各模型的性能。历史段经 bil_usage_daily（唯一键含 channel_id）过滤； +// 当天段在渠道过滤下改走 bil_usage_logs 明细实时聚合（热桶无渠道维度），两段口径一致。 // 指标口径与 bil_usage_daily 一致：延迟按 SUM 求和、视图以 SUM/COUNT 求均值（分位数不可跨桶加，p95/p99 留后续）。 -func GetModelPerformance(ctx context.Context, startDate, endDate string) (any, error) { +func GetModelPerformance(ctx context.Context, startDate, endDate string, channelID int64, modelName string) (any, error) { today := time.Now().Format("2006-01-02") - // 历史段：stat_date < today（当天由 Redis 热桶实时提供，避免与每日 01:00 的日聚合重复/滞后） + // 历史段：stat_date < today（当天由实时数据提供，避免与每日 01:00 的日聚合重复/滞后）。 + // 渠道/模型过滤用「参数=哨兵值 OR 等值匹配」写法保持 SQL 常量字符串，未筛选时等价于无条件； + // $4/$5 显式转型规避 PostgreSQL 对 OR 两侧参数的类型推断歧义。 const query = ` SELECT model_name, @@ -178,27 +182,131 @@ func GetModelPerformance(ctx context.Context, startDate, endDate string) (any, e COALESCE(SUM(cache_hit_request_count), 0) AS cache_hit_request_count FROM bil_usage_daily WHERE stat_date >= $1 AND stat_date <= $2 AND stat_date < $3 AND model_name <> 'unknown' + AND ($4::bigint = 0 OR channel_id = $4) + AND ($5::text = '' OR model_name = $5) GROUP BY model_name ` var rows []modelPerfRow - if err := g.DB().Ctx(ctx).Raw(query, startDate, endDate, today).Scan(&rows); err != nil { + if err := g.DB().Ctx(ctx).Raw(query, startDate, endDate, today, channelID, modelName).Scan(&rows); err != nil { return nil, err } - // 当日 Redis 热桶（best-effort：仅当查询窗口包含今天时参与；Redis 异常则忽略当日数据，退化为历史日表） + // 当天段（best-effort：仅当查询窗口包含今天时参与；数据源失败则忽略当日数据，退化为历史日表）： + // - 选定渠道：Redis 热桶无渠道维度，改从 bil_usage_logs 当天明细实时聚合（输出同构，合并逻辑复用） + // - 未选渠道：保持热桶路径与现状一致；仅选模型时热桶键即模型名，按键过滤 todayCounts := map[string]common.ModelPerfCounter{} if endDate == today { - tc, err := common.GetModelPerfMetricsToday(ctx, today) - if err != nil { - g.Log().Warningf(ctx, "model performance today redis read failed, fallback to daily only: %v", err) + if channelID > 0 { + tc, err := getModelPerfTodayFromLogs(ctx, today, channelID, modelName) + if err != nil { + g.Log().Warningf(ctx, "model performance today logs aggregate failed, fallback to daily only: %v", err) + } else { + todayCounts = tc + } } else { - todayCounts = tc + tc, err := common.GetModelPerfMetricsToday(ctx, today) + if err != nil { + g.Log().Warningf(ctx, "model performance today redis read failed, fallback to daily only: %v", err) + } else { + todayCounts = filterTodayCounts(tc, modelName) + } } } return map[string]any{"list": buildModelPerformanceList(rows, todayCounts)}, nil } +// filterTodayCounts 热桶结果按模型过滤（热桶键即模型名；modelName 空 = 原样返回）。 +// 未命中返回 nil，交给合并层按空处理。 +func filterTodayCounts(tc map[string]common.ModelPerfCounter, modelName string) map[string]common.ModelPerfCounter { + if modelName == "" { + return tc + } + if c, ok := tc[modelName]; ok { + return map[string]common.ModelPerfCounter{modelName: c} + } + return nil +} + +// modelPerfTodayRow 当天明细聚合行（bil_usage_logs 按模型分组，仅渠道筛选路径使用）。 +// 列名对齐 common.ModelPerfCounter 语义；口径与 usage_aggregation 写入 bil_usage_daily 一致： +// ok=成功请求、ttft=Σ首Token（无首Token请求计 0）、ttft_n=有首Token样本数、chit=命中缓存的请求数。 +type modelPerfTodayRow struct { + ModelName string `json:"model_name"` + Req int64 `json:"req"` + Ok int64 `json:"ok"` + Lat int64 `json:"lat"` + Ttft int64 `json:"ttft"` + TtftN int64 `json:"ttft_n"` + Tin int64 `json:"tin"` + Tout int64 `json:"tout"` + TotalCost float64 `json:"total_cost"` + CacheCreation int64 `json:"cache_creation"` + CacheRead int64 `json:"cache_read"` + Chit int64 `json:"chit"` +} + +// getModelPerfTodayFromLogs 渠道筛选下的当天数据源：从 bil_usage_logs 明细按模型实时聚合。 +// Redis 热桶（perf_model:{model}:{hour}）无渠道维度，选定渠道后当天必须回明细表； +// 时间区间沿用日聚合的半开区间口径 [today 00:00, tomorrow 00:00)，命中 created_at 的 BRIN 索引 +// （tomorrow 从 today 参数推导而非另取 now，避免跨午夜瞬间的边界漂移）。 +// 输出与 common.GetModelPerfMetricsToday 同构，合并逻辑复用不分叉。 +func getModelPerfTodayFromLogs(ctx context.Context, today string, channelID int64, modelName string) (map[string]common.ModelPerfCounter, error) { + dayStart, err := time.ParseInLocation("2006-01-02", today, time.Local) + if err != nil { + return nil, err + } + start := today + " 00:00:00" + end := dayStart.AddDate(0, 0, 1).Format("2006-01-02") + " 00:00:00" + const query = ` + SELECT + model_name AS model_name, + COUNT(*) AS req, + COUNT(*) FILTER (WHERE status = 'success') AS ok, + COALESCE(SUM(latency_ms), 0) AS lat, + COALESCE(SUM(first_token_ms), 0) AS ttft, + COUNT(*) FILTER (WHERE first_token_ms > 0) AS ttft_n, + COALESCE(SUM(input_tokens), 0) AS tin, + COALESCE(SUM(output_tokens), 0) AS tout, + COALESCE(SUM(total_cost), 0) AS total_cost, + COALESCE(SUM(cache_creation_tokens), 0) AS cache_creation, + COALESCE(SUM(cache_read_tokens), 0) AS cache_read, + COUNT(*) FILTER (WHERE cache_read_tokens > 0) AS chit + FROM bil_usage_logs + WHERE created_at >= $1 AND created_at < $2 AND channel_id = $3 + AND ($4::text = '' OR model_name = $4) + GROUP BY model_name + ` + var rows []modelPerfTodayRow + if err := g.DB().Ctx(ctx).Raw(query, start, end, channelID, modelName).Scan(&rows); err != nil { + return nil, err + } + return rowsToTodayCounters(rows), nil +} + +// rowsToTodayCounters 当天明细聚合行 → 热桶同构计数。 +// total_cost 以 float 聚合后转整数 micro-USD（common.microFromUSD 未导出，此处同式内联）， +// 合并侧统一经 billing.FromMicro 还原 USD，保证两条当天数据路径口径一致。 +func rowsToTodayCounters(rows []modelPerfTodayRow) map[string]common.ModelPerfCounter { + out := make(map[string]common.ModelPerfCounter, len(rows)) + for _, r := range rows { + out[r.ModelName] = common.ModelPerfCounter{ + Req: r.Req, + Ok: r.Ok, + Lat: r.Lat, + Ttft: r.Ttft, + TtftN: r.TtftN, + Tin: r.Tin, + Tout: r.Tout, + CostMicro: int64(math.Round(r.TotalCost * 1e6)), + CacheCreation: r.CacheCreation, + CacheRead: r.CacheRead, + CacheHitReq: r.Chit, + } + } + return out +} + // buildModelPerformanceList 将历史日表聚合行与当日 Redis 热桶合并为统一的模型性能列表， // 统一重算派生指标（成功率/均延迟/均首Token/TPS/分级/缓存命中率）并按模型名称升序输出。 func buildModelPerformanceList(rows []modelPerfRow, todayCounts map[string]common.ModelPerfCounter) []map[string]any { diff --git a/internal/logic/monitor/api_metrics_test.go b/internal/logic/monitor/api_metrics_test.go index aa4414a..2ad1544 100644 --- a/internal/logic/monitor/api_metrics_test.go +++ b/internal/logic/monitor/api_metrics_test.go @@ -137,6 +137,54 @@ func TestBuildModelPerformanceList_CacheEdgeCases(t *testing.T) { assertPerfField(t, list, "text-embedding-3", "cache_hit_request_rate", 0.0, 0) } +// 当天明细聚合行 → 热桶同构计数：字段映射、cost 转 micro（math.Round）、条件计数透传，并与合并层贯通。 +func TestRowsToTodayCounters(t *testing.T) { + rows := []modelPerfTodayRow{ + {ModelName: "gpt-4o", Req: 30, Ok: 28, Lat: 15000, Ttft: 4200, TtftN: 25, Tin: 3000, Tout: 6000, + TotalCost: 0.123456, CacheCreation: 100, CacheRead: 900, Chit: 20}, + {ModelName: "tiny", Req: 2, Ok: 2, TotalCost: 0.0000004}, + } + m := rowsToTodayCounters(rows) + c := m["gpt-4o"] + if c.Req != 30 || c.Ok != 28 || c.Lat != 15000 || c.Ttft != 4200 || c.TtftN != 25 || + c.Tin != 3000 || c.Tout != 6000 || c.CostMicro != 123456 || + c.CacheCreation != 100 || c.CacheRead != 900 || c.CacheHitReq != 20 { + t.Errorf("unexpected counter: %+v", c) + } + // 极小金额四舍五入到 0 micro（对齐 common.microFromUSD 的 math.Round 语义） + if m["tiny"].CostMicro != 0 { + t.Errorf("CostMicro = %d, want 0", m["tiny"].CostMicro) + } + // 与合并层贯通：明细行经转换后与热桶路径产出等价（USD 还原一致） + list := buildModelPerformanceList(nil, m) + assertPerfField(t, list, "gpt-4o", "request_count", 0, 30) + assertPerfField(t, list, "gpt-4o", "total_cost", 0.123456, 0) + assertPerfField(t, list, "gpt-4o", "cache_hit_request_count", 0, 20) +} + +func TestRowsToTodayCounters_Empty(t *testing.T) { + if m := rowsToTodayCounters(nil); len(m) != 0 { + t.Errorf("expected empty map, got %v", m) + } +} + +// 热桶路径的模型过滤：命中只留一键；未命中返回空；空模型名原样返回。 +func TestFilterTodayCounts(t *testing.T) { + tc := map[string]common.ModelPerfCounter{ + "gpt-4o": {Req: 3}, + "claude-3-5-sonnet": {Req: 5}, + } + if got := filterTodayCounts(tc, ""); len(got) != 2 { + t.Errorf("empty model should keep all, got %v", got) + } + if got := filterTodayCounts(tc, "gpt-4o"); len(got) != 1 || got["gpt-4o"].Req != 3 { + t.Errorf("unexpected filtered map: %v", got) + } + if got := filterTodayCounts(tc, "no-such-model"); len(got) != 0 { + t.Errorf("miss should be empty, got %v", got) + } +} + func TestBuildModelPerformanceList_FilterUnknownAndEmpty(t *testing.T) { rows := []modelPerfRow{ {ModelName: "unknown", RequestCount: 999, SuccessCount: 0}, diff --git a/internal/logic/monitor/monitor.go b/internal/logic/monitor/monitor.go index 788faf9..a2bf509 100644 --- a/internal/logic/monitor/monitor.go +++ b/internal/logic/monitor/monitor.go @@ -71,7 +71,8 @@ func (s *sMonitor) ModelPerformance(ctx context.Context, req *v1.MonitorModelPer return nil, err } startDate, endDate := normalizeMonitorDateRange(req.StartDate, req.EndDate) - data, err := GetModelPerformance(ctx, startDate, endDate) + // 渠道/模型为可选过滤（channel_id=0、model_name 空 = 不过滤），透传给聚合层拼 SQL 条件 + data, err := GetModelPerformance(ctx, startDate, endDate, req.ChannelId, req.ModelName) if err != nil { return nil, err } diff --git a/web/admin/src/views/monitor/ModelPerformancePage.vue b/web/admin/src/views/monitor/ModelPerformancePage.vue index c2121fe..e2e1197 100644 --- a/web/admin/src/views/monitor/ModelPerformancePage.vue +++ b/web/admin/src/views/monitor/ModelPerformancePage.vue @@ -15,6 +15,51 @@ const dateRange = ref<[string, string] | null>(defaultRange(0)) // 指标说明弹窗 const showMetricsGuide = ref(false) +// 渠道/模型可选筛选：选定渠道后按渠道查看其下各模型性能；清空下拉 = 全部 +const filterChannelId = ref(undefined) +const filterModelName = ref(undefined) +const channelOptions = ref<{ label: string; value: number }[]>([]) +const modelOptions = ref<{ label: string; value: string }[]>([]) + +// 渠道下拉数据：渠道量级为几十，一次性拉全量（page_size 放大即可） +async function fetchChannelOptions() { + try { + const res: any = await request.get('/admin/channels', { params: { page: 1, page_size: 200 } }) + channelOptions.value = (res.data?.data?.list || res.data?.list || []).map((c: any) => ({ + label: c.name ? `${c.name} (#${c.id})` : `#${c.id}`, + value: c.id, + })) + } catch { + channelOptions.value = [] + } +} + +// 模型下拉数据：专用不分页接口 /admin/models/options（model_id 与统计口径 model_name 同名） +async function fetchModelOptions() { + try { + const res: any = await request.get('/admin/models/options') + modelOptions.value = (res.data?.data?.list || res.data?.list || []).map((m: any) => ({ + label: m.model_name ? `${m.model_name} (${m.model_id})` : m.model_id, + value: m.model_id, + })) + } catch { + modelOptions.value = [] + } +} + +// 页头描述：追加当前筛选提示，避免「跨渠道」文案与实际筛选状态不符 +const pageDescription = computed(() => { + const base = + '各模型跨渠道的成功率 / 延迟 / 吞吐 / 缓存命中（历史数据源自 bil_usage_daily 每日聚合，当天实时统计；延迟为总延迟/总请求数均值。Token 命中率对 OpenAI 原生渠道为保守值）' + const parts: string[] = [] + if (filterChannelId.value) { + const ch = channelOptions.value.find((c) => c.value === filterChannelId.value) + parts.push(`渠道：${ch ? ch.label : `#${filterChannelId.value}`}`) + } + if (filterModelName.value) parts.push(`模型：${filterModelName.value}`) + return parts.length ? `${base}。当前筛选 — ${parts.join('，')}` : base +}) + function toDateStr(d: Date): string { const m = `${d.getMonth() + 1}`.padStart(2, '0') const day = `${d.getDate()}`.padStart(2, '0') @@ -196,11 +241,14 @@ const stats = computed(() => { async function fetchData() { loading.value = true try { - const params: Record = {} + const params: Record = {} if (dateRange.value && dateRange.value.length === 2) { params.start_date = dateRange.value[0] params.end_date = dateRange.value[1] } + // 可选筛选：清空下拉（undefined）即不传参 = 全部 + if (filterChannelId.value) params.channel_id = filterChannelId.value + if (filterModelName.value) params.model_name = filterModelName.value const res = await request.get('/admin/monitor/model-performance', { params }) data.value = res.data?.data?.data?.list || [] } catch { @@ -212,13 +260,35 @@ async function fetchData() { onMounted(() => { fetchData() + // 下拉数据与列表并行加载，失败仅选项为空，不影响主列表 + fetchChannelOptions() + fetchModelOptions() })