fix: preserve Gemini thought_signature in multi-turn tool calls

When using Gemini models with thinking/reasoning enabled through the
  AI SDK integration, the thought_signature was not preserved across
  multi-turn conversations with tool calls.

  The issue was that providerData was using result.providerMetadata
  (overall response metadata) instead of toolCall.providerMetadata
  (per-tool-call metadata containing thoughtSignature).

  Changes:
  - Non-streaming mode: Prioritize toolCall.providerMetadata over
    result.providerMetadata for function_call outputs
  - Streaming mode: Capture part.providerMetadata and include it
    as providerData in function_call outputs

  Reference: https://ai.google.dev/gemini-api/docs/thought-signatures
  Related: openai/openai-agents-python#2137

Author: shibu-web

packages/agents-extensions/src/aiSdk.ts

@@ -711,7 +711,9 @@ export class AiSdkModel implements Model {
             name: toolCall.toolName,
             arguments: toolCallArguments,
             status: 'completed',
-            providerData: hasToolCalls ? result.providerMetadata : undefined,
+            providerData:
+              toolCall.providerMetadata ??
+              (hasToolCalls ? result.providerMetadata : undefined),
           });
         }
 
@@ -916,6 +918,9 @@ export class AiSdkModel implements Model {
                 name: (part as any).toolName,
                 arguments: (part as any).input ?? '',
                 status: 'completed',
+                ...((part as any).providerMetadata
+                  ? { providerData: (part as any).providerMetadata }
+                  : {}),
               };
             }
             break;