Add gpt-4-turbo model; use for code changing (#416)

Without function calling, we need to use models that support
`json_object` as a response format.

At some point we should revisit function calling with the new client,
but it seems substantially more complicated than the old API. It also
appears to be deprecated in favor of "tool calling"":

> For function call sample, see [function
call](https://github.com/Azure/azure-sdk-for-java/tree/azure-ai-openai_1.0.0-beta.10/sdk/openai/azure-ai-openai/src/samples/java/com/azure/ai/openai/ChatCompletionsFunctionCall.java).
However, they are considered a legacy feature. Using tools is the
preferred way. For more details see sample [tool
calls](https://github.com/Azure/azure-sdk-for-java/blob/azure-ai-openai_1.0.0-beta.10/sdk/openai/azure-ai-openai/src/samples/java/com/azure/ai/openai/usage/GetChatCompletionsToolCallSample.java).


https://learn.microsoft.com/en-us/java/api/overview/azure/ai-openai-readme?view=azure-java-preview#chat-completions

Author: drdavella

core-codemods/src/main/java/io/codemodder/codemods/LogFailedLoginCodemod.java

@@ -68,7 +68,7 @@ public LogFailedLoginCodemod(
                   """
                     .replace('\n', ' '))),
         StandardModel.GPT_4O_2024_05_13,
-        StandardModel.GPT_4_0613);
+        StandardModel.GPT_4_TURBO_2024_04_09);
   }
 
   @Override

plugins/codemodder-plugin-llm/src/main/java/io/codemodder/plugins/llm/SarifToLLMForBinaryVerificationAndFixingCodemod.java

@@ -1,6 +1,6 @@
 package io.codemodder.plugins.llm;
 
-import static io.codemodder.plugins.llm.StandardModel.GPT_3_5_TURBO_0125;
+import static io.codemodder.plugins.llm.StandardModel.GPT_4_TURBO_2024_04_09;
 
 import com.azure.ai.openai.models.ChatRequestSystemMessage;
 import com.azure.ai.openai.models.ChatRequestUserMessage;
@@ -47,7 +47,7 @@ protected SarifToLLMForBinaryVerificationAndFixingCodemod(
    */
   protected SarifToLLMForBinaryVerificationAndFixingCodemod(
       final RuleSarif sarif, final OpenAIService openAI) {
-    this(sarif, openAI, GPT_3_5_TURBO_0125);
+    this(sarif, openAI, GPT_4_TURBO_2024_04_09);
   }
 
   @Override

plugins/codemodder-plugin-llm/src/main/java/io/codemodder/plugins/llm/SarifToLLMForMultiOutcomeCodemod.java

@@ -56,7 +56,7 @@ protected SarifToLLMForMultiOutcomeCodemod(
         openAI,
         remediationOutcomes,
         StandardModel.GPT_4O_2024_05_13,
-        StandardModel.GPT_4_0613);
+        StandardModel.GPT_4_TURBO_2024_04_09);
   }
 
   protected SarifToLLMForMultiOutcomeCodemod(

plugins/codemodder-plugin-llm/src/main/java/io/codemodder/plugins/llm/StandardModel.java

@@ -17,6 +17,12 @@ public int tokens(final List<String> messages) {
       return Tokens.countTokens(messages, 3, EncodingType.CL100K_BASE);
     }
   },
+  GPT_4_TURBO_2024_04_09("gpt-4-turbo-2024-04-09", 128_000) {
+    @Override
+    public int tokens(final List<String> messages) {
+      return Tokens.countTokens(messages, 3, EncodingType.CL100K_BASE);
+    }
+  },
   GPT_4O_2024_05_13("gpt-4o-2024-05-13", 128_000) {
     /**
      * This is wrong - we copy / pasted from GPT 3.5 while we await GPT-4o token counting support <a