fix(providers): Sakana streaming usage + filtered-tools stream guard

- Pass stream_options: { include_usage: true } on both streaming calls so
  token/cost data is captured (the shared OpenAI-compatible stream helper
  only fills usage from chunk usage, which the API omits without the flag).
- Include !hasActiveTools in the early-stream guard so requests whose tools
  are all filtered out (e.g. usageControl 'none') still take the fast
  streaming path instead of the tool-loop path. Mirrors LiteLLM.

Author: waleedlatif1

apps/sim/providers/sakana/index.ts

@@ -130,13 +130,14 @@ export const sakanaProvider: ProviderConfig = {
         payload.response_format = responseFormatPayload
       }
 
-      if (request.stream && (!tools || tools.length === 0)) {
+      if (request.stream && (!tools || tools.length === 0 || !hasActiveTools)) {
         logger.info('Using streaming response for Sakana request (no tools)')
 
         const streamResponse = await sakana.chat.completions.create(
           {
             ...payload,
             stream: true,
+            stream_options: { include_usage: true },
           },
           request.abortSignal ? { signal: request.abortSignal } : undefined
         )
@@ -452,6 +453,7 @@ export const sakanaProvider: ProviderConfig = {
           messages: currentMessages,
           tool_choice: 'none',
           stream: true,
+          stream_options: { include_usage: true },
         }
         if (deferResponseFormat && responseFormatPayload) {
           streamingPayload.response_format = responseFormatPayload