mirror of
https://gitcode.com/JianFeeeee/ModelRouter.git
synced 2026-10-03 23:54:06 +00:00
## 插件管理后端
- PUT /api/plugins/{name} {"enabled":bool} 启用/禁用
- GET /api/plugins/{name} 读源码(编辑器用,与 /state 区分)
- GET /api/plugins 的 on_disk 字段 列出目录里所有 .lua 及其加载态
- validPluginName 提取为共享函数,install/remove/read 三处共用,防止检查漂移
禁用是**运行态开关,不删文件**:插件把线上网关搞坏了、但离修好只差一行时,
运维需要把它移出请求路径而不丢失它(同 systemd mask 而非 remove 的道理)。
它**不跨重启保留**——一个悄悄比操作者意图活得更久的"禁用"本身就是个意外。
Builtin 的判定是「加载的源码与内嵌版本逐字节相同」,而不是「名字匹配」:
被改过的 billing.lua 不能被标成 builtin,否则 UI 会提供覆盖用户改动的操作。
on_disk 列表包含**加载失败**的插件。否则一个语法错误的插件在 UI 上直接消失,
运维看到的现象是"插件不见了"而不是"插件报错了"。
## 峰谷 / 时段定价
commandcode 的 DeepSeek V4 系列就是高峰 01-04 & 06-10 UTC 工作日 2 倍价
(非高峰 17h/天)。静态价目表达不了,而算错方向是**静默**的。
价目条目可带 peak = {multiplier, windows=[{days, hours}]}。命中任一窗口即乘。
★ 用 `os.date("!%H")` 取 **UTC** 小时:provider 费率表按 UTC 标注,而网关跑在
本地时区(本机 Asia/Hong_Kong)。混用本地小时会让峰谷整体偏移 8 小时,
白天算成夜间——比不做峰谷还糟。
## ★ 实现与注释不一致,被判据抓住
applyPeak 最初直接 `price.prompt = price.prompt * m`,注释写「缓存读不翻倍」。
但 costFor 里**缓存读价是从 price.prompt 派生的**,所以原地翻倍会把缓存读
也翻倍——两个折扣被叠在一起,而 provider 从没打算叠。
改成 applyPeak 只**记录**乘数,由 costFor 分段应用:fresh prompt 与 completion
翻倍,cache read 那一项不动。
只靠注释说明意图是不够的:TestBillingPeakDoesNotDoubleCacheRead 立刻红了
(0.006 vs 期望 0.003)。变异回原实现仍是红的。
## 判据(21 个计费测试全绿,新增 5 个峰谷)
窗口恒命中 ×2 / 窗口永不命中保持静态价 / 星期不匹配不命中
(这条正是防"用本地时区整体偏移 8 小时")/ 无 peak 规则向后兼容
/ 缓存读不随峰谷翻倍
后端部分:构建/vet/gofmt 干净,8 个包全绿。
679 lines
25 KiB
Go
679 lines
25 KiB
Go
package lua
|
||
|
||
import (
|
||
"encoding/json"
|
||
"os"
|
||
"path/filepath"
|
||
"strings"
|
||
"testing"
|
||
)
|
||
|
||
// The billing plugin ships with the gateway, so its arithmetic is a contract:
|
||
// a wrong price silently produces wrong money. These tests drive it through the
|
||
// real hook path and check the NUMBERS, not merely that it loads.
|
||
|
||
func billingVM(t *testing.T) (*Plugins, string) {
|
||
t.Helper()
|
||
dir := filepath.Join(t.TempDir(), "adapters")
|
||
vm := NewVM(dir)
|
||
if err := vm.Start(); err != nil {
|
||
t.Fatalf("vm: %v", err)
|
||
}
|
||
t.Cleanup(vm.Stop)
|
||
pdir := filepath.Join(t.TempDir(), "plugins")
|
||
ps := NewPlugins(vm, pdir)
|
||
if err := ps.SeedBundled(); err != nil {
|
||
t.Fatalf("seed: %v", err)
|
||
}
|
||
if err := ps.LoadDir(); err != nil {
|
||
t.Fatalf("load: %v", err)
|
||
}
|
||
return ps, pdir
|
||
}
|
||
|
||
// stateOf reads the plugin's published state as a generic map.
|
||
func stateOf(t *testing.T, ps *Plugins) map[string]interface{} {
|
||
t.Helper()
|
||
raw := ps.State("billing")
|
||
if raw == nil {
|
||
t.Fatal("billing published no state")
|
||
}
|
||
b, err := json.Marshal(raw)
|
||
if err != nil {
|
||
t.Fatal(err)
|
||
}
|
||
var out map[string]interface{}
|
||
if err := json.Unmarshal(b, &out); err != nil {
|
||
t.Fatal(err)
|
||
}
|
||
return out
|
||
}
|
||
|
||
func approx(t *testing.T, name string, got, want float64) {
|
||
t.Helper()
|
||
d := got - want
|
||
if d < 0 {
|
||
d = -d
|
||
}
|
||
if d > 1e-9 {
|
||
t.Errorf("%s = %v, want %v (delta %v)", name, got, want, d)
|
||
}
|
||
}
|
||
|
||
// TestBillingZeroPricesIsSafe: with no configuration the plugin must still run
|
||
// and report volume. A nil-price crash here would take out every request.
|
||
func TestBillingZeroPricesIsSafe(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "m", "source": "s", "key": "***aaaaaa", "ok": true,
|
||
"prompt_tokens": 100, "completion_tokens": 50, "time": 1750000000000,
|
||
})
|
||
st := stateOf(t, ps)
|
||
total := st["total"].(map[string]interface{})
|
||
if total["requests"].(float64) != 1 {
|
||
t.Errorf("requests = %v, want 1", total["requests"])
|
||
}
|
||
approx(t, "cost with no prices", total["cost"].(float64), 0)
|
||
}
|
||
|
||
// TestBillingModelTokenPricing: the core case. prompt and completion are priced
|
||
// SEPARATELY, which is how providers publish and how the total must come out.
|
||
func TestBillingModelTokenPricing(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
// Setting prices must NOT disturb the (still empty) totals, which is the
|
||
// whole point of the prices/state split.
|
||
if err := ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"currency": "USD",
|
||
"models": map[string]interface{}{
|
||
"gpt-5.4": map[string]interface{}{"prompt": 1.25e-6, "completion": 1e-5},
|
||
},
|
||
},
|
||
}); err != nil {
|
||
t.Fatal(err)
|
||
}
|
||
// 1000 prompt * 1.25e-6 = 0.00125 ; 500 completion * 1e-5 = 0.005
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "gpt-5.4", "source": "up", "key": "***aaaaaa", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 500, "time": 1750000000000,
|
||
})
|
||
st := stateOf(t, ps)
|
||
approx(t, "total cost", st["total"].(map[string]interface{})["cost"].(float64), 0.00625)
|
||
byModel := st["by_model"].(map[string]interface{})["gpt-5.4"].(map[string]interface{})
|
||
approx(t, "model cost", byModel["cost"].(float64), 0.00625)
|
||
if byModel["completion_tokens"].(float64) != 500 {
|
||
t.Errorf("completion_tokens = %v, want 500", byModel["completion_tokens"])
|
||
}
|
||
}
|
||
|
||
// TestBillingPerRequestAndTokenCombine: a flat fee is ADDED to the token cost,
|
||
// which is how an image model can be "tokens + fixed fee".
|
||
func TestBillingPerRequestAndTokenCombine(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
if err := ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"kolors": map[string]interface{}{"prompt": 1e-6, "completion": 2e-6, "per_request": 0.04},
|
||
},
|
||
},
|
||
}); err != nil {
|
||
t.Fatal(err)
|
||
}
|
||
// 100*1e-6 + 50*2e-6 + 0.04 = 0.0402
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "kolors", "source": "sf", "key": "***bbbbbb", "ok": true,
|
||
"prompt_tokens": 100, "completion_tokens": 50, "time": 1750000000000,
|
||
})
|
||
st := stateOf(t, ps)
|
||
approx(t, "total", st["total"].(map[string]interface{})["cost"].(float64), 0.0402)
|
||
}
|
||
|
||
// TestBillingPrecedence: keys > models > default for token prices.
|
||
func TestBillingPrecedence(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"default": map[string]interface{}{"prompt": 9e-6, "completion": 9e-6},
|
||
"models": map[string]interface{}{"m": map[string]interface{}{"prompt": 2e-6, "completion": 3e-6}},
|
||
"keys": map[string]interface{}{"***cccccc": map[string]interface{}{"prompt": 1e-6, "completion": 1.5e-6}},
|
||
},
|
||
})
|
||
|
||
// No key match -> model price.
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "m", "source": "s", "key": "***other", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 1000, "time": 1750000000000,
|
||
})
|
||
// Key match -> key price wins.
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "m", "source": "s", "key": "***cccccc", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 1000, "time": 1750000000000,
|
||
})
|
||
st := stateOf(t, ps)
|
||
// 1000*2e-6 + 1000*3e-6 = 0.005 ; 1000*1e-6 + 1000*1.5e-6 = 0.0025
|
||
approx(t, "total (model + key)", st["total"].(map[string]interface{})["cost"].(float64), 0.0075)
|
||
|
||
// An unpriced model falls back to default.
|
||
ps2, _ := billingVM(t)
|
||
_ = ps2.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"default": map[string]interface{}{"prompt": 9e-6, "completion": 9e-6},
|
||
},
|
||
})
|
||
ps2.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "unknown", "source": "s", "key": "***d", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 1000, "time": 1750000000000,
|
||
})
|
||
approx(t, "default fallback", stateOf(t, ps2)["total"].(map[string]interface{})["cost"].(float64), 0.018)
|
||
}
|
||
|
||
// TestBillingAggregatesEveryDimension: one request must land in all four
|
||
// rollups plus the daily bucket. A missing dimension is the kind of bug a
|
||
// dashboard hides (it just renders an empty table).
|
||
func TestBillingAggregatesEveryDimension(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"models": map[string]interface{}{"m1": map[string]interface{}{"prompt": 1e-6, "completion": 1e-6}},
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "m1", "source": "srcA", "key": "***key01", "ok": true,
|
||
"prompt_tokens": 100, "completion_tokens": 100, "time": 1750000000000,
|
||
})
|
||
st := stateOf(t, ps)
|
||
for _, dim := range []string{"by_source", "by_model", "by_key", "by_day"} {
|
||
m, ok := st[dim].(map[string]interface{})
|
||
if !ok || len(m) == 0 {
|
||
t.Errorf("%s is empty; a dimension is missing", dim)
|
||
}
|
||
}
|
||
if _, ok := st["by_source"].(map[string]interface{})["srcA"]; !ok {
|
||
t.Error("by_source lacks srcA")
|
||
}
|
||
if _, ok := st["by_key"].(map[string]interface{})["***key01"]; !ok {
|
||
t.Error("by_key lacks the gateway key")
|
||
}
|
||
// Milliseconds must be converted, not used as seconds: a raw 1750000000000
|
||
// would land in a year-57000 bucket.
|
||
days := st["by_day"].(map[string]interface{})
|
||
found := false
|
||
for k := range days {
|
||
if len(k) == 10 && strings.Contains(k, "-") {
|
||
found = true
|
||
}
|
||
if strings.HasPrefix(k, "5") && len(k) > 6 {
|
||
t.Errorf("by_day key %q suggests millisecond timestamps were not converted", k)
|
||
}
|
||
}
|
||
if !found {
|
||
t.Errorf("by_day has no YYYY-MM-DD key: %v", days)
|
||
}
|
||
}
|
||
|
||
// TestBillingFailedRequestPolicy: a failed request keeps its token cost (tokens
|
||
// really were consumed) but drops the flat per_request fee (never charged).
|
||
func TestBillingFailedRequestPolicy(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"m": map[string]interface{}{"prompt": 1e-6, "completion": 1e-6, "per_request": 0.5},
|
||
},
|
||
},
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "m", "source": "s", "key": "***e", "ok": false, "status": 500,
|
||
"prompt_tokens": 1000, "completion_tokens": 0, "time": 1750000000000,
|
||
})
|
||
st := stateOf(t, ps)
|
||
// 1000*1e-6 = 0.001, flat dropped.
|
||
approx(t, "failed request", st["total"].(map[string]interface{})["cost"].(float64), 0.001)
|
||
if st["total"].(map[string]interface{})["failures"].(float64) != 1 {
|
||
t.Error("failures not counted")
|
||
}
|
||
}
|
||
|
||
// TestBillingStateAPIReplace: the admin price update must actually change
|
||
// subsequent pricing (not just be stored).
|
||
func TestBillingStateAPIReplace(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{"m": map[string]interface{}{"prompt": 1e-6, "completion": 0}},
|
||
},
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "m", "source": "s", "key": "***f", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 0, "time": 1750000000000,
|
||
})
|
||
approx(t, "before reprice", stateOf(t, ps)["total"].(map[string]interface{})["cost"].(float64), 0.001)
|
||
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{"m": map[string]interface{}{"prompt": 2e-6, "completion": 0}},
|
||
},
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "m", "source": "s", "key": "***f", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 0, "time": 1750000000000,
|
||
})
|
||
// 0.001 (old) + 0.002 (new price)
|
||
approx(t, "after reprice", stateOf(t, ps)["total"].(map[string]interface{})["cost"].(float64), 0.003)
|
||
}
|
||
|
||
// TestBillingPluginDeclaresUI: the shipped plugin must ship its dashboard, or
|
||
// "billing is enabled" would be true while showing the user nothing.
|
||
func TestBillingPluginDeclaresUI(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
for _, row := range ps.List() {
|
||
if row["name"] != "billing" {
|
||
continue
|
||
}
|
||
ui, ok := row["ui"].(map[string]interface{})
|
||
if !ok {
|
||
t.Fatal("billing declares no ui")
|
||
}
|
||
if page, _ := ui["page"].(string); page != "billing" {
|
||
t.Errorf("ui.page = %v, want \"billing\"", ui["page"])
|
||
}
|
||
if n, _ := ui["elements"].(int); n < 1 {
|
||
t.Error("billing contributes no element to an existing page")
|
||
}
|
||
return
|
||
}
|
||
t.Fatal("billing plugin is not loaded")
|
||
}
|
||
|
||
// TestBillingPluginLoadedByDefault: the shipped plugin must load with no
|
||
// configuration, since seeding only happens on a fresh plugin dir.
|
||
func TestBillingPluginLoadedByDefault(t *testing.T) {
|
||
ps, pdir := billingVM(t)
|
||
if ps.Count() != 1 {
|
||
t.Fatalf("expected 1 bundled plugin, got %d", ps.Count())
|
||
}
|
||
if _, err := os.Stat(filepath.Join(pdir, "billing.lua")); err != nil {
|
||
t.Errorf("billing.lua was not written to the plugin dir: %v", err)
|
||
}
|
||
}
|
||
|
||
// TestBillingCountsDegradations: the plugin must distinguish a request that had
|
||
// to drop below the top tier from one the top tier served. Without the chain
|
||
// trace these were identical in the accounts, so a quietly degraded gateway
|
||
// looked healthy while spending more per request.
|
||
func TestBillingCountsDegradations(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"hi-tier": map[string]interface{}{"prompt": 1e-5, "completion": 1e-5},
|
||
"lo-tier": map[string]interface{}{"prompt": 1e-6, "completion": 1e-6},
|
||
},
|
||
},
|
||
})
|
||
|
||
// Request 1: degraded. tier 1 hard-failed, tier 2 served it.
|
||
ps.Fire(StageChainStep, map[string]interface{}{
|
||
"kind": "slot_fail", "tier": 1, "source": "t1", "model": "hi-tier",
|
||
})
|
||
ps.Fire(StageChainStep, map[string]interface{}{
|
||
"kind": "selected", "tier": 2, "source": "t2", "model": "lo-tier",
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "lo-tier", "source": "t2", "key": "***d1", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 1000,
|
||
"degraded": true, "tier_served": 2, "time": 1750000000000,
|
||
})
|
||
|
||
// Request 2: clean, served by the top tier.
|
||
ps.Fire(StageChainStep, map[string]interface{}{
|
||
"kind": "selected", "tier": 1, "source": "t1", "model": "hi-tier",
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "hi-tier", "source": "t1", "key": "***d1", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 1000,
|
||
"degraded": false, "tier_served": 1, "time": 1750000000000,
|
||
})
|
||
|
||
st := stateOf(t, ps)
|
||
if got := st["degraded_reqs"].(float64); got != 1 {
|
||
t.Errorf("degraded_reqs = %v, want 1 (one of the two requests dropped a tier)", got)
|
||
}
|
||
tiers := st["by_tier_served"].(map[string]interface{})
|
||
if tiers["2"].(float64) != 1 {
|
||
t.Errorf("by_tier_served[2] = %v, want 1", tiers["2"])
|
||
}
|
||
if tiers["1"].(float64) != 1 {
|
||
t.Errorf("by_tier_served[1] = %v, want 1", tiers["1"])
|
||
}
|
||
// Cost reflects the model actually served, not the one that should have been.
|
||
// 1000*1e-6*2 = 0.002 for the degraded one, 1000*1e-5*2 = 0.02 for the clean one.
|
||
approx(t, "total", st["total"].(map[string]interface{})["cost"].(float64), 0.022)
|
||
}
|
||
|
||
// TestBillingAggregatesSkipReasons: skip reasons are the actionable diagnostic
|
||
// ("no schedulable slot (cooling or quota exhausted)"), so they must be
|
||
// counted. The wait time is normalised, otherwise a fresh row per request would
|
||
// appear whenever the busy-wait text varies.
|
||
func TestBillingAggregatesSkipReasons(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
ps.Fire(StageChainStep, map[string]interface{}{
|
||
"kind": "tier_skip", "tier": 1, "reason": "no schedulable slot (cooling or quota exhausted)",
|
||
})
|
||
ps.Fire(StageChainStep, map[string]interface{}{
|
||
"kind": "tier_busy", "tier": 2, "reason": "no free slot within 2s",
|
||
})
|
||
ps.Fire(StageChainStep, map[string]interface{}{
|
||
"kind": "tier_busy", "tier": 3, "reason": "no free slot within 2.0001s",
|
||
})
|
||
st := stateOf(t, ps)
|
||
reasons := st["skip_reasons"].(map[string]interface{})
|
||
if len(reasons) != 2 {
|
||
t.Errorf("skip_reasons = %v, want 2 (the two variable waits must collapse to one)", reasons)
|
||
}
|
||
busy, ok := reasons["no free slot within <wait>"]
|
||
if !ok {
|
||
t.Errorf("busy reason missing; got %v", reasons)
|
||
} else if busy.(float64) != 2 {
|
||
t.Errorf("busy count = %v, want 2 (two different wait texts, one cause)", busy)
|
||
}
|
||
}
|
||
|
||
// ---- prompt-cache pricing -------------------------------------------------
|
||
//
|
||
// A cached prompt token is not a fresh one. Charging the full prompt rate made a
|
||
// 1M-token request of which 900k were cache reads cost 10 USD instead of ~1.9
|
||
// — an order of magnitude, on exactly the traffic the cache exists to make
|
||
// cheap. Agent traffic replays long shared prefixes constantly, so this was the
|
||
// single largest source of over-billing in the plugin.
|
||
|
||
func TestBillingCacheHitsAreDiscounted(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"m": map[string]interface{}{"prompt": 1e-5, "completion": 1e-5},
|
||
},
|
||
},
|
||
})
|
||
// 1M prompt of which 900k cached, default discount 0.1
|
||
// 100k fresh * 1e-5 = 1.0 ; 900k cached * 1e-5 * 0.1 = 0.9
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "m", "source": "s", "key": "***c", "ok": true,
|
||
"prompt_tokens": 1000000, "completion_tokens": 0,
|
||
"cache_hit_tokens": 900000, "time": 1750000000000,
|
||
})
|
||
approx(t, "cache-discounted cost", stateOf(t, ps)["total"].(map[string]interface{})["cost"].(float64), 1.9)
|
||
}
|
||
|
||
// A per-model discount overrides the global one, because the ratio is a
|
||
// per-provider fact, not a constant.
|
||
func TestBillingCacheDiscountIsPerModel(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"free-cache": map[string]interface{}{
|
||
"prompt": 1e-5, "completion": 0, "cache_discount": 0,
|
||
},
|
||
"flat": map[string]interface{}{
|
||
"prompt": 1e-5, "completion": 0, "cache_discount": 1,
|
||
},
|
||
},
|
||
},
|
||
})
|
||
for _, m := range []string{"free-cache", "flat"} {
|
||
ps2, _ := billingVM(t)
|
||
_ = ps2.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
m: map[string]interface{}{"prompt": 1e-5, "completion": 0, "cache_discount": map[bool]float64{true: 0, false: 1}[m == "free-cache"]},
|
||
},
|
||
},
|
||
})
|
||
ps2.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": m, "source": "s", "key": "***c", "ok": true,
|
||
"prompt_tokens": 1000000, "cache_hit_tokens": 1000000,
|
||
"time": 1750000000000,
|
||
})
|
||
want := 0.0
|
||
if m == "flat" {
|
||
want = 10.0
|
||
}
|
||
approx(t, m+" (all cached)", stateOf(t, ps2)["total"].(map[string]interface{})["cost"].(float64), want)
|
||
}
|
||
}
|
||
|
||
// A misbehaving adapter reporting more cache hits than prompt tokens must not
|
||
// produce negative fresh tokens.
|
||
func TestBillingCacheHitClampedToPrompt(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{"m": map[string]interface{}{"prompt": 1e-5, "completion": 0}},
|
||
},
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "m", "source": "s", "key": "***c", "ok": true,
|
||
"prompt_tokens": 100, "completion_tokens": 0,
|
||
"cache_hit_tokens": 999999, // nonsense from a broken adapter
|
||
"time": 1750000000000,
|
||
})
|
||
// Clamped to 100 cached, 0 fresh => 100 * 1e-5 * 0.1
|
||
got := stateOf(t, ps)["total"].(map[string]interface{})["cost"].(float64)
|
||
if got < 0 {
|
||
t.Errorf("cost = %v, must never be negative", got)
|
||
}
|
||
approx(t, "clamped cost", got, 0.0001)
|
||
}
|
||
|
||
// ---- unpriced traffic -----------------------------------------------------
|
||
|
||
// An unpriced model silently costing 0 is the most dangerous failure a cost
|
||
// plugin has: the bill still adds up, it just quietly under-reports, and
|
||
// nothing looks broken. It must be counted and named.
|
||
func TestBillingCountsUnpricedTraffic(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"priced": map[string]interface{}{"prompt": 1e-5},
|
||
},
|
||
},
|
||
})
|
||
// 100k+100k tokens on a model with no price entry.
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "MYSTERY-MODEL", "source": "s", "key": "***u", "ok": true,
|
||
"prompt_tokens": 100000, "completion_tokens": 100000, "time": 1750000000000,
|
||
})
|
||
// A priced one, to prove the counter is selective.
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "priced", "source": "s", "key": "***u", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 0, "time": 1750000000000,
|
||
})
|
||
st := stateOf(t, ps)
|
||
if got := st["unpriced_reqs"].(float64); got != 1 {
|
||
t.Errorf("unpriced_reqs = %v, want 1 (only the mystery model)", got)
|
||
}
|
||
models := st["unpriced_models"].(map[string]interface{})
|
||
if models["MYSTERY-MODEL"].(float64) != 1 {
|
||
t.Errorf("unpriced_models = %v, want MYSTERY-MODEL counted", models)
|
||
}
|
||
if _, present := models["priced"]; present {
|
||
t.Error("a priced model was counted as unpriced")
|
||
}
|
||
// The traffic is still recorded: "unpriced" must not mean "invisible".
|
||
if got := st["total"].(map[string]interface{})["requests"].(float64); got != 2 {
|
||
t.Errorf("total requests = %v, want 2 (unpriced traffic is still traffic)", got)
|
||
}
|
||
}
|
||
|
||
// A source-only or key-only price counts as priced: any dimension covering the
|
||
// request is enough.
|
||
func TestBillingAnyDimensionCountsAsPriced(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"sources": map[string]interface{}{"flat-fee": map[string]interface{}{"per_request": 0.02}},
|
||
},
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "any-model", "source": "flat-fee", "key": "***p", "ok": true,
|
||
"prompt_tokens": 10, "completion_tokens": 0, "time": 1750000000000,
|
||
})
|
||
st := stateOf(t, ps)
|
||
if got := st["unpriced_reqs"].(float64); got != 0 {
|
||
t.Errorf("unpriced_reqs = %v, want 0 (the source price covers it)", got)
|
||
}
|
||
approx(t, "flat fee", st["total"].(map[string]interface{})["cost"].(float64), 0.02)
|
||
}
|
||
|
||
// ---- 峰谷 / 时段定价 ---------------------------------------------------
|
||
//
|
||
// commandcode 的 DeepSeek V4 系列就是这么定价的:非高峰 17h/天,高峰 01-04 &
|
||
// 06-10 UTC 工作日,价格恰好 2 倍。这类规则用静态价目无法表达,而算错方向是
|
||
// 静默的——不会报错,只会一直算错。
|
||
//
|
||
// 时间判据的可测性:os.date("!%H") 取 UTC 小时。测试通过选择"确定落在窗口内"
|
||
// 与"确定落在窗口外"的时段来判定,不去伪造时钟(Lua 侧没有可注入的时钟,
|
||
// 伪造反而会让测试与真实行为脱节)。
|
||
|
||
func TestBillingPeakWindowDoublesOutsidePeak(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"dsv41": map[string]interface{}{
|
||
"prompt": 1.5e-7, "completion": 6e-7,
|
||
"peak": map[string]interface{}{
|
||
"multiplier": 2,
|
||
// 全部 7 天全部 24 小时 ⇒ 永远命中
|
||
"windows": []interface{}{
|
||
map[string]interface{}{
|
||
"days": []interface{}{0, 1, 2, 3, 4, 5, 6},
|
||
"hours": []interface{}{[]interface{}{0, 23}},
|
||
},
|
||
},
|
||
},
|
||
},
|
||
},
|
||
},
|
||
})
|
||
// 1000 prompt + 1000 completion,非高峰 0.00075 → 命中峰谷 ×2 = 0.0015
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "dsv41", "source": "commandcode", "key": "***pk", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 1000, "time": 1750000000000,
|
||
})
|
||
got := stateOf(t, ps)["total"].(map[string]interface{})["cost"].(float64)
|
||
want := (1000*1.5e-7 + 1000*6e-7) * 2
|
||
approx(t, "always-peak cost", got, want)
|
||
}
|
||
|
||
// 一个不存在的窗口(UTC 25 点不存在)⇒ 永不命中 ⇒ 静态价。
|
||
func TestBillingPeakWindowNotHit(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"dsv41": map[string]interface{}{
|
||
"prompt": 1.5e-7, "completion": 6e-7,
|
||
"peak": map[string]interface{}{
|
||
"multiplier": 2,
|
||
// 星期 = {0..6} 但小时窗写成 [99,100]:永远不可能命中
|
||
"windows": []interface{}{
|
||
map[string]interface{}{
|
||
"days": []interface{}{0, 1, 2, 3, 4, 5, 6},
|
||
"hours": []interface{}{[]interface{}{99, 100}},
|
||
},
|
||
},
|
||
},
|
||
},
|
||
},
|
||
},
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "dsv41", "source": "commandcode", "key": "***pk", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 1000, "time": 1750000000000,
|
||
})
|
||
got := stateOf(t, ps)["total"].(map[string]interface{})["cost"].(float64)
|
||
approx(t, "never-peak cost", got, 1000*1.5e-7+1000*6e-7)
|
||
}
|
||
|
||
// 星期不匹配 ⇒ 不命中。这一条正是"用本地时区算会整体偏移"要防的东西:
|
||
// 周日按 UTC 算,用本地时区可能算成周六而错误地命中工作日窗口。
|
||
func TestBillingPeakWindowDayMismatch(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"dsv41": map[string]interface{}{
|
||
"prompt": 1.5e-7, "completion": 6e-7,
|
||
"peak": map[string]interface{}{
|
||
"multiplier": 2,
|
||
// 只在"不存在的星期 7"上开窗(os.date %w 只到 0..6)
|
||
"windows": []interface{}{
|
||
map[string]interface{}{
|
||
"days": []interface{}{7},
|
||
"hours": []interface{}{[]interface{}{0, 23}},
|
||
},
|
||
},
|
||
},
|
||
},
|
||
},
|
||
},
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "dsv41", "source": "commandcode", "key": "***pk", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 1000, "time": 1750000000000,
|
||
})
|
||
got := stateOf(t, ps)["total"].(map[string]interface{})["cost"].(float64)
|
||
if got > (1000*1.5e-7+1000*6e-7)*1.5 {
|
||
t.Errorf("cost = %v: a non-matching weekday must not trigger the peak multiplier", got)
|
||
}
|
||
}
|
||
|
||
// 没有 peak 规则的条目完全不受影响(向后兼容)。
|
||
func TestBillingNoPeakRuleIsUnaffected(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"plain": map[string]interface{}{"prompt": 1e-6, "completion": 2e-6},
|
||
},
|
||
},
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "plain", "source": "s", "key": "***n", "ok": true,
|
||
"prompt_tokens": 1000, "completion_tokens": 1000, "time": 1750000000000,
|
||
})
|
||
approx(t, "no-peak cost", stateOf(t, ps)["total"].(map[string]interface{})["cost"].(float64), 1000*1e-6+1000*2e-6)
|
||
}
|
||
|
||
// 缓存读价【不】跟着峰谷翻倍:它是另一条上游费率,观测到的非峰谷价里已经含了
|
||
// 自己的折扣,跟着翻倍会把两个折扣叠在一起。
|
||
func TestBillingPeakDoesNotDoubleCacheRead(t *testing.T) {
|
||
ps, _ := billingVM(t)
|
||
_ = ps.SetState("billing", map[string]interface{}{
|
||
"prices": map[string]interface{}{
|
||
"models": map[string]interface{}{
|
||
"dsv41": map[string]interface{}{
|
||
"prompt": 1.5e-7, "completion": 6e-7, "cache_discount": 0.02,
|
||
"peak": map[string]interface{}{
|
||
"multiplier": 2,
|
||
"windows": []interface{}{map[string]interface{}{
|
||
"days": []interface{}{0, 1, 2, 3, 4, 5, 6},
|
||
"hours": []interface{}{[]interface{}{0, 23}},
|
||
}},
|
||
},
|
||
},
|
||
},
|
||
},
|
||
})
|
||
ps.Fire(StageRequestEnd, map[string]interface{}{
|
||
"model": "dsv41", "source": "commandcode", "key": "***c", "ok": true,
|
||
"prompt_tokens": 1000000, "completion_tokens": 0,
|
||
"cache_hit_tokens": 1000000, "time": 1750000000000,
|
||
})
|
||
// 全部缓存命中 ⇒ 只按 cache 价 = prompt * 0.02,且不翻倍
|
||
got := stateOf(t, ps)["total"].(map[string]interface{})["cost"].(float64)
|
||
approx(t, "cache-only cost (not doubled)", got, 1e6*1.5e-7*0.02)
|
||
}
|