Update dependency com.azure:azure-ai-openai to v1.0.0-beta.16 (#498)

This PR contains the following updates:

| Package | Change | Age | Adoption | Passing | Confidence |
|---|---|---|---|---|---|
|
[com.azure:azure-ai-openai](https://redirect.github.com/Azure/azure-sdk-for-java)
| `1.0.0-beta.10` -> `1.0.0-beta.16` |
[![age](https://developer.mend.io/api/mc/badges/age/maven/com.azure:azure-ai-openai/1.0.0-beta.16?slim=true)](https://docs.renovatebot.com/merge-confidence/)
|
[![adoption](https://developer.mend.io/api/mc/badges/adoption/maven/com.azure:azure-ai-openai/1.0.0-beta.16?slim=true)](https://docs.renovatebot.com/merge-confidence/)
|
[![passing](https://developer.mend.io/api/mc/badges/compatibility/maven/com.azure:azure-ai-openai/1.0.0-beta.10/1.0.0-beta.16?slim=true)](https://docs.renovatebot.com/merge-confidence/)
|
[![confidence](https://developer.mend.io/api/mc/badges/confidence/maven/com.azure:azure-ai-openai/1.0.0-beta.10/1.0.0-beta.16?slim=true)](https://docs.renovatebot.com/merge-confidence/)
|

---

### Configuration

📅 **Schedule**: Branch creation - At any time (no schedule defined),
Automerge - At any time (no schedule defined).

🚦 **Automerge**: Disabled by config. Please merge this manually once you
are satisfied.

♻ **Rebasing**: Whenever PR is behind base branch, or you tick the
rebase/retry checkbox.

🔕 **Ignore**: Close this PR and you won't be reminded about this update
again.

---

- [ ] <!-- rebase-check -->If you want to rebase/retry this PR, check
this box

---

This PR was generated by [Mend Renovate](https://mend.io/renovate/).
View the [repository job
log](https://developer.mend.io/github/pixee/codemodder-java).

<!--renovate-debug:eyJjcmVhdGVkSW5WZXIiOiI0MC41MC4wIiwidXBkYXRlZEluVmVyIjoiNDAuNTAuMCIsInRhcmdldEJyYW5jaCI6Im1haW4iLCJsYWJlbHMiOltdfQ==-->

---------

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: Arshan Dabirsiaghi <[email protected]>

Author: renovate[bot]

framework/codemodder-base/build.gradle.kts

@@ -29,7 +29,7 @@ dependencies {
     api(libs.javaparser.symbolsolver.model)
     api(libs.javadiff)
     api(libs.jtokkit)
-    api("com.azure:azure-ai-openai:1.0.0-beta.10")
+    api("com.azure:azure-ai-openai:1.0.0-beta.16")
     api("io.github.classgraph:classgraph:4.8.160")
 
     implementation(libs.tuples)

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

@@ -151,7 +151,8 @@ private BinaryThreatAnalysis analyzeThreat(
     // If the estimated token count, which doesn't include the function (~100 tokens) or the reply
     // (~200 tokens), is close to the max, then assume the code is safe (for now).
     int tokenCount =
-        model.tokens(List.of(systemMessage.getContent(), userMessage.getContent().toString()));
+        model.tokens(
+            List.of(systemMessage.getStringContent(), userMessage.getContent().toString()));
     if (tokenCount > model.contextWindow() - 300) {
       return new BinaryThreatAnalysis(
           "Ignoring file: estimated prompt token count (" + tokenCount + ") is too high.",

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

@@ -201,7 +201,8 @@ private boolean estimatedToExceedContextWindow(final CodemodInvocationContext co
       int tokenCount =
           model.tokens(
               List.of(
-                  getSystemMessage().getContent(), estimatedUserMessage.getContent().toString()));
+                  getSystemMessage().getStringContent(),
+                  estimatedUserMessage.getContent().toString()));
       // estimated token count doesn't include the function (~100 tokens) or the reply
       // (~200 tokens) so add those estimates before checking against window size
       tokenCount += 300;