Merge remote-tracking branch 'origin/main' into codex/project-resume-reuse

internal/multiagent/eino_run_usage_accumulator.go

@@ -13,6 +13,7 @@ type einoRunUsageSummary struct {
 	CompletionTokens int
 	TotalTokens      int
 	CachedTokens     int
+	CacheWriteTokens int
 	ReasoningTokens  int
 }
 
@@ -42,8 +43,13 @@ func (a *einoRunUsageAccumulator) AddUsage(usage *schema.TokenUsage) bool {
 	a.summary.ModelCalls++
 	a.summary.PromptTokens += usage.PromptTokens
 	a.summary.CompletionTokens += usage.CompletionTokens
-	a.summary.TotalTokens += usage.TotalTokens
+	total := usage.TotalTokens
+	if total == 0 {
+		total = usage.PromptTokens + usage.CompletionTokens
+	}
+	a.summary.TotalTokens += total
 	a.summary.CachedTokens += usage.PromptTokenDetails.CachedTokens
+	a.summary.CacheWriteTokens += usage.PromptTokenDetails.CacheWriteTokens
 	a.summary.ReasoningTokens += usage.CompletionTokensDetails.ReasoningTokens
 	return true
 }
@@ -88,6 +94,7 @@ func (a *einoRunUsageAccumulator) EmitOnce(
 		"completionTokens": s.CompletionTokens,
 		"totalTokens":      s.TotalTokens,
 		"cachedTokens":     s.CachedTokens,
+		"cacheWriteTokens": s.CacheWriteTokens,
 		"reasoningTokens":  s.ReasoningTokens,
 	}
 	if progress != nil {
@@ -104,6 +111,7 @@ func (a *einoRunUsageAccumulator) EmitOnce(
 			zap.Int("completionTokens", s.CompletionTokens),
 			zap.Int("totalTokens", s.TotalTokens),
 			zap.Int("cachedTokens", s.CachedTokens),
+			zap.Int("cacheWriteTokens", s.CacheWriteTokens),
 			zap.Int("reasoningTokens", s.ReasoningTokens),
 		)
 	}
@@ -129,6 +137,9 @@ func maxEinoTokenUsage(dst *schema.TokenUsage, src *schema.TokenUsage) *schema.T
 	if src.PromptTokenDetails.CachedTokens > dst.PromptTokenDetails.CachedTokens {
 		dst.PromptTokenDetails.CachedTokens = src.PromptTokenDetails.CachedTokens
 	}
+	if src.PromptTokenDetails.CacheWriteTokens > dst.PromptTokenDetails.CacheWriteTokens {
+		dst.PromptTokenDetails.CacheWriteTokens = src.PromptTokenDetails.CacheWriteTokens
+	}
 	if src.CompletionTokensDetails.ReasoningTokens > dst.CompletionTokensDetails.ReasoningTokens {
 		dst.CompletionTokensDetails.ReasoningTokens = src.CompletionTokensDetails.ReasoningTokens
 	}
@@ -149,5 +160,6 @@ func tokenUsageEmpty(u *schema.TokenUsage) bool {
 			u.CompletionTokens == 0 &&
 			u.TotalTokens == 0 &&
 			u.PromptTokenDetails.CachedTokens == 0 &&
+			u.PromptTokenDetails.CacheWriteTokens == 0 &&
 			u.CompletionTokensDetails.ReasoningTokens == 0)
 }

internal/multiagent/eino_run_usage_accumulator_test.go

@@ -79,3 +79,25 @@ func TestMaxEinoTokenUsageUsesLargestStreamChunkValues(t *testing.T) {
 		t.Fatalf("usage = %#v", got)
 	}
 }
+
+func TestEinoRunUsageCacheWriteDoesNotInflateTotal(t *testing.T) {
+	acc := newEinoRunUsageAccumulator()
+	var stream *schema.TokenUsage
+	for i := 0; i < 2; i++ {
+		stream = maxEinoTokenUsage(stream, &schema.TokenUsage{
+			PromptTokens: 100, CompletionTokens: 20,
+			PromptTokenDetails:      schema.PromptTokenDetails{CachedTokens: 40, CacheWriteTokens: 30},
+			CompletionTokensDetails: schema.CompletionTokensDetails{ReasoningTokens: 10},
+		})
+	}
+	acc.AddUsage(stream)
+	got := acc.Summary()
+	if got.ModelCalls != 1 || got.TotalTokens != 120 || got.CacheWriteTokens != 30 || got.CachedTokens != 40 || got.ReasoningTokens != 10 {
+		t.Fatalf("summary = %#v", got)
+	}
+	var emitted map[string]interface{}
+	acc.EmitOnce("conv", "deep", "final", "claude-test", func(_, _ string, data interface{}) { emitted = data.(map[string]interface{}) }, nil)
+	if emitted["cacheWriteTokens"] != 30 || emitted["totalTokens"] != 120 {
+		t.Fatalf("event = %#v", emitted)
+	}
+}