fix: cost ledger charges fresh input only (cache read is part of input tokens)

input_tokens includes the cached subset under Anthropic and OpenAI usage semantics, so pricing input and cache read at their full prices double-counted the cache. The fresh share is now input minus cache reads, clamped at zero for gateways reporting disjoint buckets.

db/llm_usage.go

@@ -371,7 +371,15 @@ func applyCostEur(d *DB, out []ProfileUsage) error {
 		if !ok || (pr.in == 0 && pr.outp == 0 && pr.cr == 0 && pr.cw == 0) {
 			continue
 		}
-		cost := float64(out[i].InputTokens)/1e6*pr.in + float64(out[i].OutputTokens)/1e6*pr.outp +
+		// 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
+		if fresh < 0 {
+			fresh = 0
+		}
+		cost := float64(fresh)/1e6*pr.in + float64(out[i].OutputTokens)/1e6*pr.outp +
 			float64(out[i].CacheReadTokens)/1e6*pr.cr + float64(out[i].CacheWriteTokens)/1e6*pr.cw
 		c := cost
 		out[i].CostEur = &c

server/cost_ledger_test.go

@@ -54,7 +54,7 @@ func TestCostLedgerEurOnUsage(t *testing.T) {
 	if got == nil {
 		t.Fatal("priced profile has no cost_eur")
 	}
-	want := 2.0*1.5 + 0.5*4.0 + 1.0*0.15 // 3.0 + 2.0 + 0.15 = 5.15
+	want := 1.0*1.5 + 0.5*4.0 + 1.0*0.15 // fresh input 1M (2M incl. 1M cached) + 0.5M out + 1M cache-read = 3.65
 	if d := *got - want; d > 0.001 || d < -0.001 {
 		t.Fatalf("cost_eur = %v, want %v", *got, want)
 	}