fix(db): stop billing cache writes twice in profile cost

Norma normalizes InputTokens to input + cache read + cache write, so both cache buckets are subsets of it. The fresh share billed at the input price is now input minus reads minus writes, still clamped at zero for gateways that report disjoint buckets.

db/llm_usage.go

@@ -341,11 +341,12 @@ func applyCostEur(d *DB, out []ProfileUsage) error {
 		if !ok || (pr.in == 0 && pr.outp == 0 && pr.cr == 0 && pr.cw == 0) {
 			continue
 		}
-		// InputTokens includes the cached subset (Anthropic and OpenAI usage
-		// semantics), so the fresh share is input minus cache reads; charging
-		// both buckets at full input price double-counts the cache. Clamped at
-		// zero for gateways that report the buckets disjointly.
-		fresh := out[i].InputTokens - out[i].CacheReadTokens
+		// InputTokens already includes both cached subsets: Norma normalizes it to
+		// input + cache read + cache write (OpenAI prompt_tokens semantics). The
+		// fresh share is therefore input minus cache reads minus cache writes;
+		// charging either subset at full input price as well bills it twice.
+		// Clamped at zero for gateways that report the buckets disjointly.
+		fresh := out[i].InputTokens - out[i].CacheReadTokens - out[i].CacheWriteTokens
 		if fresh < 0 {
 			fresh = 0
 		}

db/llm_usage_cost_test.go

@@ -0,0 +1,125 @@
+package db
+
+import (
+	"fmt"
+	"math"
+	"testing"
+	"time"
+)
+
+// costProfiles saves a priced profile (EUR per million tokens: input 2.00,
+// output 4.00, cache read 0.20, cache write 2.50) and an unpriced one.
+func costProfiles(t *testing.T, d *DB) (priced, unpriced string) {
+	t.Helper()
+	suffix := time.Now().UnixNano()
+	priced, unpriced = fmt.Sprintf("t-cost-priced-%d", suffix), fmt.Sprintf("t-cost-unpriced-%d", suffix)
+	for _, p := range []*LLMProfile{
+		{Name: priced, Format: "anthropic", Model: "m", APIKey: "k",
+			PriceInputPerM: 2, PriceOutputPerM: 4, PriceCacheReadPerM: 0.2, PriceCacheWritePerM: 2.5},
+		{Name: unpriced, Format: "anthropic", Model: "m", APIKey: "k"},
+	} {
+		id, err := d.SaveProfile(p)
+		if err != nil {
+			t.Fatal(err)
+		}
+		t.Cleanup(func() { d.Exec(`DELETE FROM llm_profiles WHERE id=$1`, id) })
+	}
+	return priced, unpriced
+}
+
+func assertCost(t *testing.T, got *float64, want float64) {
+	t.Helper()
+	if got == nil {
+		t.Fatalf("cost=nil, want %.2f", want)
+	}
+	if math.Abs(*got-want) > 1e-9 {
+		t.Fatalf("cost=%.4f, want %.2f", *got, want)
+	}
+}
+
+// InputTokens already includes the cache read and cache write subsets, so only
+// the remainder is billed at the input price.
+func TestCostSeparatesFreshReadAndWriteBuckets(t *testing.T) {
+	d, err := Open(testDSN(t))
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer d.Close()
+	priced, unpriced := costProfiles(t, d)
+	// Every case adds 100k output tokens: 0.1 × 4.00 = 0.40.
+	for _, tc := range []struct {
+		name            string
+		in, read, write int
+		want            float64
+	}{
+		{"fresh", 1_000_000, 0, 0, 2.40},                          // 1M×2.00 + 0.40
+		{"read_only", 1_000_000, 1_000_000, 0, 0.60},              // 0 fresh + 1M×0.20 + 0.40
+		{"write_only", 1_000_000, 0, 1_000_000, 2.90},             // 0 fresh + 1M×2.50 + 0.40
+		{"mixed", 1_000_000, 200_000, 300_000, 2.19},              // 500k×2.00 + 200k×0.20 + 300k×2.50 + 0.40
+		{"inconsistent_gateway", 100_000, 200_000, 300_000, 1.19}, // fresh clamped to 0 + 0.04 + 0.75 + 0.40
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			out := []ProfileUsage{
+				{ProfileName: priced, InputTokens: tc.in, CacheReadTokens: tc.read, CacheWriteTokens: tc.write, OutputTokens: 100_000},
+				{ProfileName: unpriced, InputTokens: tc.in, CacheReadTokens: tc.read, CacheWriteTokens: tc.write, OutputTokens: 100_000},
+				{ProfileName: "t-cost-unknown-profile", InputTokens: tc.in, OutputTokens: 100_000},
+			}
+			if err := applyCostEur(d, out); err != nil {
+				t.Fatal(err)
+			}
+			assertCost(t, out[0].CostEur, tc.want)
+			if out[1].CostEur != nil || out[2].CostEur != nil {
+				t.Fatalf("unpriced usage got a cost: %v %v", out[1].CostEur, out[2].CostEur)
+			}
+		})
+	}
+}
+
+// Several ledger rows of one profile are summed before pricing; with no clamp
+// involved the profile cost equals the sum of the per-row costs.
+func TestUsageByProfileCostAggregatesRows(t *testing.T) {
+	d, err := Open(testDSN(t))
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer d.Close()
+	priced, unpriced := costProfiles(t, d)
+	t.Cleanup(func() { d.Exec(`DELETE FROM llm_usage WHERE profile_name IN ($1,$2)`, priced, unpriced) })
+	rows := []LLMUsage{
+		// fresh 400k×2.00 + 200k×0.20 + 40k×4.00 = 0.80 + 0.04 + 0.16 = 1.00
+		{InputTokens: 600_000, CacheRead: 200_000, OutputTokens: 40_000},
+		// fresh 100k×2.00 + 300k×2.50 + 60k×4.00 = 0.20 + 0.75 + 0.24 = 1.19
+		{InputTokens: 400_000, CacheWrite: 300_000, OutputTokens: 60_000},
+	}
+	for _, profile := range []string{priced, unpriced} {
+		for _, r := range rows {
+			r.ProfileName, r.Model, r.Status = profile, "m", "ok"
+			if err := d.InsertLLMUsage(&r); err != nil {
+				t.Fatal(err)
+			}
+		}
+	}
+	usage, err := d.UsageByProfile()
+	if err != nil {
+		t.Fatal(err)
+	}
+	found := 0
+	for _, p := range usage {
+		switch p.ProfileName {
+		case priced:
+			found++
+			if p.Calls != 2 || p.InputTokens != 1_000_000 || p.CacheReadTokens != 200_000 || p.CacheWriteTokens != 300_000 || p.OutputTokens != 100_000 {
+				t.Fatalf("aggregate %+v", p)
+			}
+			assertCost(t, p.CostEur, 2.19) // = 1.00 + 1.19, the mixed case
+		case unpriced:
+			found++
+			if p.Calls != 2 || p.CostEur != nil {
+				t.Fatalf("unpriced aggregate %+v", p)
+			}
+		}
+	}
+	if found != 2 {
+		t.Fatalf("profiles missing from UsageByProfile: found %d of 2", found)
+	}
+}