test(ai): Add comprehensive E2E tests for all AI providers

- Add multi-turn test to verify thinking and tool calling work together
- Test thinkingSignature handling for proper multi-turn context
- Fix Gemini provider to generate base64 thinkingSignature when needed
- Handle multiple rounds of tool calls in tests (Gemini behavior)
- Make thinking tests more robust for model-dependent behavior
- All 18 tests passing across 4 providers

packages/ai/src/providers/openai-responses.ts

@@ -137,6 +137,9 @@ export class OpenAIResponsesLLM implements LLM<OpenAIResponsesLLMOptions> {
 
 					// Map status to stop reason
 					stopReason = this.mapStopReason(response?.status);
+					if (toolCalls.length > 0 && stopReason === "stop") {
+						stopReason = "toolUse";
+					}
 				}
 				// Handle errors
 				else if (event.type === "error") {