Add NebiusLLMService with developer role and tool support fixes

- Add Nebius LLM service wrapping OpenAI-compatible Token Factory API
- Set supports_developer_role = False (Nebius rejects developer role)
- Default to openai/gpt-oss-120b model (supports function calling)
- Add Nebius function-calling example and env.example entry
- Fix Sarvam developer role support
- Update examples to use developer role for intro messages

scripts/evals/run-release-evals.py

@@ -169,8 +169,11 @@ TESTS_12 = [
 TESTS_14 = [
     ("14-function-calling.py", EVAL_WEATHER),
     ("14-function-calling.py", EVAL_WEATHER_AND_RESTAURANT),
+    ("14-function-calling-openai-responses.py", EVAL_WEATHER),
+    ("14-function-calling-openai-responses.py", EVAL_WEATHER_AND_RESTAURANT),
     ("14a-function-calling-anthropic.py", EVAL_WEATHER),
     ("14a-function-calling-anthropic.py", EVAL_WEATHER_AND_RESTAURANT),
+    ("14b-function-calling-openai.py", EVAL_WEATHER),
     ("14e-function-calling-google.py", EVAL_WEATHER),
     ("14e-function-calling-google.py", EVAL_WEATHER_AND_RESTAURANT),
     ("14f-function-calling-groq.py", EVAL_WEATHER),
@@ -186,13 +189,11 @@ TESTS_14 = [
     ("14r-function-calling-aws.py", EVAL_WEATHER),
     ("14s-function-calling-sambanova.py", EVAL_WEATHER),
     ("14r-function-calling-aws.py", EVAL_WEATHER_AND_RESTAURANT),
-    ("14v-function-calling-openai.py", EVAL_WEATHER),
+    ("14v-function-calling-nebius.py", EVAL_WEATHER),
     ("14w-function-calling-mistral.py", EVAL_WEATHER),
     ("14x-function-calling-openpipe.py", EVAL_WEATHER),
     ("14y-function-calling-sarvam.py", EVAL_WEATHER),
     ("14z-function-calling-novita.py", EVAL_WEATHER),
-    ("14-function-calling-openai-responses.py", EVAL_WEATHER),
-    ("14-function-calling-openai-responses.py", EVAL_WEATHER_AND_RESTAURANT),
     # Video
     ("14d-function-calling-anthropic-video.py", EVAL_VISION_CAMERA),
     ("14d-function-calling-aws-video.py", EVAL_VISION_CAMERA),