fix(providers/ollama): drop tools from post-tool streaming call

Ollama ignores tool_choice (not in its supported fields), so vLLM/Fireworks'
tool_choice:'none' guard is a no-op here. Omit tools from the final streaming
payload instead so the summarization turn can't emit dropped tool calls.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

Author: waleedlatif1

apps/sim/providers/ollama/index.test.ts

@@ -336,6 +336,10 @@ describe('ollamaProvider.executeRequest', () => {
     expect(result.stream).toBe('OLLAMA_STREAM')
     expect(mockExecuteTool).toHaveBeenCalledTimes(1)
 
+    const finalCall = mockCreate.mock.calls[2][0]
+    expect(finalCall.tools).toBeUndefined()
+    expect(finalCall.tool_choice).toBeUndefined()
+
     streamOnComplete.current?.('final answer', {
       prompt_tokens: 2,
       completion_tokens: 4,

apps/sim/providers/ollama/index.ts

@@ -482,10 +482,11 @@ export const ollamaProvider: ProviderConfig = {
 
         const accumulatedCost = calculateCost(request.model, tokens.input, tokens.output)
 
+        const { tools: _tools, tool_choice: _toolChoice, ...streamPayload } = payload
+
         const streamingParams: ChatCompletionCreateParamsStreaming = {
-          ...payload,
+          ...streamPayload,
           messages: currentMessages,
-          tool_choice: 'auto',
           stream: true,
           stream_options: { include_usage: true },
         }