fix(kiro): complete cache-only usage totals (#9753)

open-sse/executors/kiro.ts

@@ -61,7 +61,7 @@ type KiroStreamState = {
   contextUsagePercentage?: number;
   hasContextUsage?: boolean;
   hasMeteringEvent?: boolean;
-  usage?: UsageSummary;
+  usage?: Partial<UsageSummary>;
   hasReasoningContent?: boolean;
   reasoningChunkCount?: number;
   // Inline-thinking splitter state (populated only when thinkingExpected=true).
@@ -185,8 +185,7 @@ function resolveKiroMaxInputTokens(model: string): number {
  * inflate `total_tokens`.
  */
 function ensureKiroUsage(state: KiroStreamState, model: string) {
-  if (state.usage) return;
-
+  if (state.usage?.total_tokens !== undefined) return;
   const estimatedOutputTokens =
     state.totalContentLength && state.totalContentLength > 0
       ? Math.max(1, Math.floor(state.totalContentLength / 4))
@@ -198,11 +197,11 @@ function ensureKiroUsage(state: KiroStreamState, model: string) {
       : 0;
 
   if (estimatedTotalTokens <= 0 && estimatedOutputTokens <= 0) return;
-
   // Without a percentage there is no total to split, so the output estimate is
   // all that is known and stands on its own.
   if (estimatedTotalTokens <= 0) {
     state.usage = {
+      ...state.usage,
       prompt_tokens: 0,
       completion_tokens: estimatedOutputTokens,
       total_tokens: estimatedOutputTokens,
@@ -213,6 +212,7 @@ function ensureKiroUsage(state: KiroStreamState, model: string) {
   const promptTokens = Math.max(0, estimatedTotalTokens - estimatedOutputTokens);
 
   state.usage = {
+    ...state.usage,
     prompt_tokens: promptTokens,
     completion_tokens: estimatedOutputTokens,
     total_tokens: promptTokens + estimatedOutputTokens,

tests/unit/executor-kiro.test.ts

@@ -339,8 +339,12 @@ test("KiroExecutor keeps cache tokens that arrive without input/output totals",
   const chunks = parseSSEJsonChunks(await transformed.text());
   const finish = chunks.find((chunk) => chunk.choices?.[0]?.finish_reason);
 
-  assert.equal(finish.usage.cache_read_input_tokens, 900);
-  assert.equal(finish.usage.cache_creation_input_tokens, undefined);
+  assert.deepEqual(finish.usage, {
+    prompt_tokens: 19999,
+    completion_tokens: 1,
+    total_tokens: 20000,
+    cache_read_input_tokens: 900,
+  });
 });
 
 // snake_case spellings appear on some Kiro frames; a cache count must not be