fix: stop deducting simulated cache tokens from input_tokens
Some checks failed
Build Docker Image / build (push) Has been cancelled
Some checks failed
Build Docker Image / build (push) Has been cancelled
Kiro backend does not support Anthropic prompt cache protocol. The local cache tracker simulates cache hits/creation for Claude Code compatibility, but subtracting those values from input_tokens caused the reported input_tokens to drop to single digits. input_tokens now reflects the real value; cache_creation_input_tokens and cache_read_input_tokens are still reported for protocol compliance. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -56,8 +56,8 @@ func TestBuildClaudeUsageMapIncludesCacheFields(t *testing.T) {
|
||||
|
||||
m := buildClaudeUsageMap(100, 50, usage, true)
|
||||
|
||||
if got := m["input_tokens"]; got != 50 {
|
||||
t.Fatalf("expected billed input tokens 50, got %#v", got)
|
||||
if got := m["input_tokens"]; got != 100 {
|
||||
t.Fatalf("expected input tokens 100 (no deduction), got %#v", got)
|
||||
}
|
||||
if got := m["cache_creation_input_tokens"]; got != 30 {
|
||||
t.Fatalf("expected cache creation tokens 30, got %#v", got)
|
||||
|
||||
Reference in New Issue
Block a user