feat(billing): 长上下文阶梯定价（边际费率，与缓存折扣/峰段可叠加）

## 影响面实测

审计里 1000 条请求：**883 条（88.3%）prompt 超过 128k**，中位数 246849，
p90 298179，最大 354251。这不是小众场景，是 agent 负载的主流形态。

按「模型 × 源」拆开：其中真正按 token 计价的只有 alittokenplan 的 10 次
（deepseek-v4.1-flash，约 350k prompt），其余走 $70 套餐（commandcode）或
免费源（localzen），记 0 是正确的，对阶梯无影响。

那 10 次当前少算 54.9%（$0.3148 → $0.4877）。绝对值不大，但比例严重，
而且这个偏差只会随上下文变长而变大。

## 边际而非混合平均

阶梯只对**超过阈值的部分**重新计价，不是把整段按高价算。理由是可叠加性：
缓存读取同时享受缓存折扣**和**长上下文阶梯价，这与供应商的计费方式一致。
混合平均必须二选一，选错就正好低估「缓存命中的长请求」——而这恰是缓存
存在的意义所在（本部署缓存命中率 88%）。

超出部分按缓存/新鲜的比例拆分，不重不漏。

## DSL 两种写法

供应商两种发布方式都支持：绝对费率（OpenAI 报 \$3.00/M past 200k）和
倍数（DeepSeek 报 2x past 128k）。两者都缺必须报错 —— 一个没有费率的阶梯
会编译成一条「看起来处理了长上下文、实际没处理」的规则，静默少算且无迹可寻。
两者都给时以绝对费率为准，因为那是供应商真正报出的数字。

## 判据

Lua 侧两条（边际性、与缓存折扣叠加）+ Go 侧一条（两种写法与拒绝规则）。
变异自证三次：整段按高价 / 缓存部分不叠加折扣 / 缓存部分不计阶梯，
分别命中 0.40 vs 0.272、0.165 vs 0.2325、0.09 vs 0.2325。

规则编辑器加了三个输入（阈值 + 绝对费率 + 倍数），三项都留空 = 无阶梯 ——
与「阶梯费率为 0」刻意区分，所以是三个独立输入而不是从 0 推断是否存在阶梯。

Co-Authored-By: ModelRouter <noreply@modelrouter.dev>

internal/billing/compile.go

@@ -207,6 +207,24 @@ func applyRule(prices map[string]interface{}, rule *config.BillingRule, srcName
 				}
 				entry["reasoning_price"] = rp
 			}
+			if lc := t.LongContext; lc != nil {
+				if lc.Above <= 0 {
+					return fmt.Errorf("model %q long_context: above must be > 0", modelID)
+				}
+				above, err := longContextRate(lc, prompt)
+				if err != nil {
+					return fmt.Errorf("model %q long_context: %w", modelID, err)
+				}
+				entry["long_context"] = map[string]interface{}{
+					"above": lc.Above,
+					// Marginal, not blended. The plugin charges the tokens past the
+					// threshold at this rate and the rest at the base rate, so the
+					// threshold composes with a cache discount (which applies to the
+					// cached portion) instead of forcing the plugin to guess how
+					// the two interact.
+					"prompt": above,
+				}
+			}
 			if rule.Peak != nil {
 				entry["peak"] = compilePeak(rule.Peak)
 			}
@@ -274,3 +292,32 @@ func compilePeak(p *config.BillingPeak) map[string]interface{} {
 	}
 	return out
 }
+
+// longContextRate resolves the marginal per-token rate for the tokens ABOVE a
+// threshold, given the model's base per-million prompt price.
+//
+// Two ways to express it are supported because providers publish both: an
+// absolute rate (OpenAI quotes \$3.00/M past 200k) and a multiple (DeepSeek
+// quotes exactly 2x past 128k). Neither may be missing: a step with no rate is a
+// silent no-op, and an operator who wrote one meant something.
+func longContextRate(lc *config.BillingLongContext, basePerToken float64) (float64, error) {
+	hasPrompt := strings.TrimSpace(lc.Prompt) != ""
+	hasMult := lc.Multiplier > 0
+	switch {
+	case hasPrompt && hasMult:
+		p, err := usdPerM(lc.Prompt)
+		if err != nil {
+			return 0, err
+		}
+		// Both given: the absolute rate wins, because it is the one the provider
+		// actually quotes. Silently multiplying instead would produce a number
+		// the operator never wrote.
+		return p, nil
+	case hasPrompt:
+		return usdPerM(lc.Prompt)
+	case hasMult:
+		return basePerToken * lc.Multiplier, nil
+	default:
+		return 0, fmt.Errorf("needs either prompt or multiplier")
+	}
+}

internal/billing/wildcard_test.go

@@ -147,3 +147,68 @@ func TestReasoningPriceIsOmittedUnlessSet(t *testing.T) {
 		t.Error("a non-numeric reasoning rate must fail the compile")
 	}
 }
+
+// TestLongContextStepCompiles pins the long-context step's two accepted forms
+// and its rejection of a step that would silently do nothing.
+//
+// Providers publish both shapes — DeepSeek says "2x past 128k", OpenAI quotes
+// an absolute "$3.00/M past 200k" — so both must compile. Neither may be
+// missing: a step with no rate is a rule that LOOKS like it handles long
+// context and does not, which under-bills without any visible sign.
+func TestLongContextStepCompiles(t *testing.T) {
+	sources := []config.Source{{Name: "up", BaseURL: "https://up.example/v1"}}
+
+	compile := func(lc config.BillingLongContext) (map[string]interface{}, error) {
+		p := &config.BillingProfile{ID: "p", Rules: []config.BillingRule{{
+			URL: "https://up.example/v1", Mode: "token",
+			Models: map[string]config.BillingToken{
+				"m": {Prompt: "1.00", Completion: "2.00", LongContext: &lc},
+			},
+		}}}
+		prices, err := Compile(p, sources)
+		if err != nil {
+			return nil, err
+		}
+		e := prices["models"].(map[string]interface{})["m"].(map[string]interface{})
+		return e["long_context"].(map[string]interface{}), nil
+	}
+
+	// Absolute rate (OpenAI's published shape).
+	lc1, err := compile(config.BillingLongContext{Above: 200000, Prompt: "3.00"})
+	if err != nil {
+		t.Fatalf("absolute long_context rate rejected: %v", err)
+	}
+	if lc1["above"] != 200000 || lc1["prompt"] != 3e-6 {
+		t.Errorf("absolute step = %#v, want above=200000 prompt=3e-6", lc1)
+	}
+
+	// Multiplier (DeepSeek's shape): 2x of the 1.00/M base.
+	lc2, err := compile(config.BillingLongContext{Above: 128000, Multiplier: 2})
+	if err != nil {
+		t.Fatalf("multiplier long_context rejected: %v", err)
+	}
+	if lc2["prompt"] != 2e-6 {
+		t.Errorf("multiplier step = %#v, want prompt=2e-6", lc2)
+	}
+
+	// Both given: the absolute rate wins, because that is the number the
+	// provider quotes. Multiplying instead would produce a figure the operator
+	// never wrote.
+	lc3, err := compile(config.BillingLongContext{Above: 128000, Prompt: "5.00", Multiplier: 2})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if lc3["prompt"] != 5e-6 {
+		t.Errorf("both given = %#v, want the quoted absolute rate 5e-6", lc3)
+	}
+
+	// Neither: a no-op step must fail, not compile into a rule that silently
+	// bills long context at the base rate.
+	if _, err := compile(config.BillingLongContext{Above: 128000}); err == nil {
+		t.Error("a step with neither prompt nor multiplier must be rejected")
+	}
+	// A zero threshold would make every request "long".
+	if _, err := compile(config.BillingLongContext{Above: 0, Multiplier: 2}); err == nil {
+		t.Error("above=0 must be rejected")
+	}
+}