feat(api)!: BREAKING CHANGE: support passing extra_body through to providers (#3777)

# What does this PR do?
Allows passing through extra_body parameters to inference providers.

With this, we removed the 2 vllm-specific parameters from completions
API into `extra_body`.
Before/After
<img width="1883" height="324" alt="image"
src="https://github.com/user-attachments/assets/acb27c08-c748-46c9-b1da-0de64e9908a1"
/>



closes #2720

## Test Plan
CI and added new test
```
❯ uv run pytest -s -v tests/integration/ --stack-config=server:starter --inference-mode=record -k 'not( builtin_tool or safety_with_image or code_interpreter or test_rag ) and test_openai_completion_guided_choice' --setup=vllm --suite=base --color=yes
Uninstalled 3 packages in 125ms
Installed 3 packages in 19ms
INFO     2025-10-10 14:29:54,317 tests.integration.conftest:118 tests: Applying setup 'vllm' for suite base
INFO     2025-10-10 14:29:54,331 tests.integration.conftest:47 tests: Test stack config type: server
         (stack_config=server:starter)
============================================================================================================== test session starts ==============================================================================================================
platform darwin -- Python 3.12.11, pytest-8.4.2, pluggy-1.6.0 -- /Users/erichuang/projects/llama-stack-1/.venv/bin/python
cachedir: .pytest_cache
metadata: {'Python': '3.12.11', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.2', 'pluggy': '1.6.0'}, 'Plugins': {'anyio': '4.9.0', 'html': '4.1.1', 'socket': '0.7.0', 'asyncio': '1.1.0', 'json-report': '1.5.0', 'timeout': '2.4.0', 'metadata': '3.1.1', 'cov': '6.2.1', 'nbval': '0.11.0'}}
rootdir: /Users/erichuang/projects/llama-stack-1
configfile: pyproject.toml
plugins: anyio-4.9.0, html-4.1.1, socket-0.7.0, asyncio-1.1.0, json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, cov-6.2.1, nbval-0.11.0
asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function
collected 285 items / 284 deselected / 1 selected

tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]
instantiating llama_stack_client
Starting llama stack server with config 'starter' on port 8321...
Waiting for server at http://localhost:8321... (0.0s elapsed)
Waiting for server at http://localhost:8321... (0.5s elapsed)
Waiting for server at http://localhost:8321... (5.1s elapsed)
Waiting for server at http://localhost:8321... (5.6s elapsed)
Waiting for server at http://localhost:8321... (10.1s elapsed)
Waiting for server at http://localhost:8321... (10.6s elapsed)
Server is ready at http://localhost:8321
llama_stack_client instantiated in 11.773s
PASSEDTerminating llama stack server process...
Terminating process 98444 and its group...
Server process and children terminated gracefully


============================================================================================================= slowest 10 durations ==============================================================================================================
11.88s setup    tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]
3.02s call     tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]
0.01s teardown tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]
================================================================================================ 1 passed, 284 deselected, 3 warnings in 16.21s =================================================================================================
```

llama_stack/providers/remote/inference/bedrock/bedrock.py

@@ -12,8 +12,8 @@ from botocore.client import BaseClient
 from llama_stack.apis.inference import (
     ChatCompletionRequest,
     Inference,
-    OpenAIChatCompletionRequest,
-    OpenAICompletionRequest,
+    OpenAIChatCompletionRequestWithExtraBody,
+    OpenAICompletionRequestWithExtraBody,
     OpenAIEmbeddingsResponse,
 )
 from llama_stack.apis.inference.inference import (
@@ -134,12 +134,12 @@ class BedrockInferenceAdapter(
 
     async def openai_completion(
         self,
-        params: OpenAICompletionRequest,
+        params: OpenAICompletionRequestWithExtraBody,
     ) -> OpenAICompletion:
         raise NotImplementedError("OpenAI completion not supported by the Bedrock provider")
 
     async def openai_chat_completion(
         self,
-        params: OpenAIChatCompletionRequest,
+        params: OpenAIChatCompletionRequestWithExtraBody,
     ) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
         raise NotImplementedError("OpenAI chat completion not supported by the Bedrock provider")

llama_stack/providers/remote/inference/databricks/databricks.py

@@ -8,7 +8,7 @@ from collections.abc import Iterable
 
 from databricks.sdk import WorkspaceClient
 
-from llama_stack.apis.inference import OpenAICompletion, OpenAICompletionRequest
+from llama_stack.apis.inference import OpenAICompletion, OpenAICompletionRequestWithExtraBody
 from llama_stack.log import get_logger
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
@@ -39,6 +39,6 @@ class DatabricksInferenceAdapter(OpenAIMixin):
 
     async def openai_completion(
         self,
-        params: OpenAICompletionRequest,
+        params: OpenAICompletionRequestWithExtraBody,
     ) -> OpenAICompletion:
         raise NotImplementedError()

llama_stack/providers/remote/inference/llama_openai_compat/llama.py

@@ -3,7 +3,12 @@
 #
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
-from llama_stack.apis.inference.inference import OpenAICompletion, OpenAICompletionRequest, OpenAIEmbeddingsResponse
+
+from llama_stack.apis.inference.inference import (
+    OpenAICompletion,
+    OpenAICompletionRequestWithExtraBody,
+    OpenAIEmbeddingsResponse,
+)
 from llama_stack.log import get_logger
 from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
@@ -29,7 +34,7 @@ class LlamaCompatInferenceAdapter(OpenAIMixin):
 
     async def openai_completion(
         self,
-        params: OpenAICompletionRequest,
+        params: OpenAICompletionRequestWithExtraBody,
     ) -> OpenAICompletion:
         raise NotImplementedError()
 

llama_stack/providers/remote/inference/passthrough/passthrough.py

@@ -13,9 +13,9 @@ from llama_stack.apis.inference import (
     Inference,
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
-    OpenAIChatCompletionRequest,
+    OpenAIChatCompletionRequestWithExtraBody,
     OpenAICompletion,
-    OpenAICompletionRequest,
+    OpenAICompletionRequestWithExtraBody,
     OpenAIEmbeddingsResponse,
 )
 from llama_stack.apis.models import Model
@@ -79,7 +79,7 @@ class PassthroughInferenceAdapter(Inference):
 
     async def openai_completion(
         self,
-        params: OpenAICompletionRequest,
+        params: OpenAICompletionRequestWithExtraBody,
     ) -> OpenAICompletion:
         client = self._get_client()
         model_obj = await self.model_store.get_model(params.model)
@@ -93,7 +93,7 @@ class PassthroughInferenceAdapter(Inference):
 
     async def openai_chat_completion(
         self,
-        params: OpenAIChatCompletionRequest,
+        params: OpenAIChatCompletionRequestWithExtraBody,
     ) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
         client = self._get_client()
         model_obj = await self.model_store.get_model(params.model)

llama_stack/providers/remote/inference/runpod/runpod.py

@@ -9,7 +9,7 @@ from collections.abc import AsyncIterator
 from llama_stack.apis.inference import (
     OpenAIChatCompletion,
     OpenAIChatCompletionChunk,
-    OpenAIChatCompletionRequest,
+    OpenAIChatCompletionRequestWithExtraBody,
 )
 from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin
 
@@ -31,7 +31,7 @@ class RunpodInferenceAdapter(OpenAIMixin):
 
     async def openai_chat_completion(
         self,
-        params: OpenAIChatCompletionRequest,
+        params: OpenAIChatCompletionRequestWithExtraBody,
     ) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
         """Override to add RunPod-specific stream_options requirement."""
         params = params.model_copy()

llama_stack/providers/remote/inference/vllm/vllm.py

@@ -14,7 +14,7 @@ from pydantic import ConfigDict
 
 from llama_stack.apis.inference import (
     OpenAIChatCompletion,
-    OpenAIChatCompletionRequest,
+    OpenAIChatCompletionRequestWithExtraBody,
     ToolChoice,
 )
 from llama_stack.log import get_logger
@@ -93,7 +93,7 @@ class VLLMInferenceAdapter(OpenAIMixin):
 
     async def openai_chat_completion(
         self,
-        params: OpenAIChatCompletionRequest,
+        params: OpenAIChatCompletionRequestWithExtraBody,
     ) -> OpenAIChatCompletion | AsyncIterator[OpenAIChatCompletionChunk]:
         params = params.model_copy()