Changeset 0.10.0 (#56)

server/handlers/stream_loop.go

@@ -15,8 +15,12 @@ import (
 // streamResult holds the accumulated output from a streaming completion
 // with tool execution. Callers are responsible for persistence.
 type streamResult struct {
-	Content      string
-	ToolActivity []map[string]interface{}
+	Content             string
+	ToolActivity        []map[string]interface{}
+	InputTokens         int
+	OutputTokens        int
+	CacheCreationTokens int
+	CacheReadTokens     int
 }
 
 // streamWithToolLoop is the single, canonical streaming implementation.
@@ -100,6 +104,11 @@ func streamWithToolLoop(
 			if event.Done {
 				if event.FinishReason == "tool_calls" && len(event.ToolCalls) > 0 {
 					toolCalls = event.ToolCalls
+					// Accumulate tokens from this tool-call iteration
+					result.InputTokens += event.InputTokens
+					result.OutputTokens += event.OutputTokens
+					result.CacheCreationTokens += event.CacheCreationTokens
+					result.CacheReadTokens += event.CacheReadTokens
 				} else {
 					// Normal completion — send finish event
 					finishReason := event.FinishReason
@@ -110,6 +119,11 @@ func streamWithToolLoop(
 						result.Content += "<think>" + iterReasoning + "</think>"
 					}
 					result.Content += iterContent
+					// Accumulate final tokens
+					result.InputTokens += event.InputTokens
+					result.OutputTokens += event.OutputTokens
+					result.CacheCreationTokens += event.CacheCreationTokens
+					result.CacheReadTokens += event.CacheReadTokens
 					sendSSE(fmt.Sprintf(
 						`{"choices":[{"delta":{},"finish_reason":%q}],"model":%q}`,
 						finishReason, model))