feat: add batches API with OpenAI compatibility

Add complete batches API implementation with protocol, providers, and tests:

Core Infrastructure:
- Add batches API protocol using OpenAI Batch types directly
- Add Api.batches enum value and protocol mapping in resolver
- Add OpenAI "batch" file purpose support
- Include proper error handling (ConflictError, ResourceNotFoundError)

Reference Provider:
- Add ReferenceBatchesImpl with full CRUD operations (create, retrieve, cancel, list)
- Implement background batch processing with configurable concurrency
- Add SQLite KVStore backend for persistence
- Support /v1/chat/completions endpoint with request validation

Comprehensive Test Suite:
- Add unit tests for provider implementation with validation
- Add integration tests for end-to-end batch processing workflows
- Add error handling tests for validation, malformed inputs, and edge cases

Configuration:
- Add max_concurrent_batches and max_concurrent_requests_per_batch options
- Add provider documentation with sample configurations

Test with -

```
$ uv run llama stack build --image-type venv --providers inference=YOU_PICK,files=inline::localfs,batches=inline::reference --run &
$ LLAMA_STACK_CONFIG=http://localhost:8321 uv run pytest tests/unit/providers/batches tests/integration/batches --text-model YOU_PICK
```

llama_stack/apis/batches/__init__.py

@@ -0,0 +1,9 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from .batches import Batches, BatchObject, CreateBatchRequest, ListBatchesResponse
+
+__all__ = ["Batches", "BatchObject", "CreateBatchRequest", "ListBatchesResponse"]

llama_stack/apis/batches/batches.py

@@ -0,0 +1,92 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import Any, Literal, Protocol, runtime_checkable
+
+from pydantic import BaseModel, Field
+
+from llama_stack.schema_utils import json_schema_type, webmethod
+
+try:
+    from openai.types import Batch as BatchObject
+except ImportError as e:
+    raise ImportError("OpenAI package is required for batches API. Please install it with: pip install openai") from e
+
+
+@json_schema_type
+class CreateBatchRequest(BaseModel):
+    """Request to create a new batch."""
+
+    input_file_id: str = Field(..., description="The ID of an uploaded file that contains requests for the new batch")
+    endpoint: str = Field(..., description="The endpoint to be used for all requests in the batch")
+    completion_window: str = Field(..., description="The time window within which the batch should be processed")
+    metadata: dict[str, Any] | None = Field(default=None, description="Optional metadata for the batch")
+
+
+@json_schema_type
+class ListBatchesResponse(BaseModel):
+    """Response containing a list of batch objects."""
+
+    object: Literal["list"] = "list"
+    data: list[BatchObject] = Field(..., description="List of batch objects")
+    first_id: str | None = Field(default=None, description="ID of the first batch in the list")
+    last_id: str | None = Field(default=None, description="ID of the last batch in the list")
+    has_more: bool = Field(default=False, description="Whether there are more batches available")
+
+
+@runtime_checkable
+class Batches(Protocol):
+    """Protocol for batch processing API operations."""
+
+    @webmethod(route="/openai/v1/batches", method="POST")
+    async def create_batch(
+        self,
+        input_file_id: str,
+        endpoint: str,
+        completion_window: str,
+        metadata: dict[str, str] | None = None,
+    ) -> BatchObject:
+        """Create a new batch for processing multiple API requests.
+
+        :param input_file_id: The ID of an uploaded file containing requests for the batch.
+        :param endpoint: The endpoint to be used for all requests in the batch.
+        :param completion_window: The time window within which the batch should be processed.
+        :param metadata: Optional metadata for the batch.
+        :returns: The created batch object.
+        """
+        ...
+
+    @webmethod(route="/openai/v1/batches/{batch_id}", method="GET")
+    async def retrieve_batch(self, batch_id: str) -> BatchObject:
+        """Retrieve information about a specific batch.
+
+        :param batch_id: The ID of the batch to retrieve.
+        :returns: The batch object.
+        """
+        ...
+
+    @webmethod(route="/openai/v1/batches/{batch_id}/cancel", method="POST")
+    async def cancel_batch(self, batch_id: str) -> BatchObject:
+        """Cancel a batch that is in progress.
+
+        :param batch_id: The ID of the batch to cancel.
+        :returns: The updated batch object.
+        """
+        ...
+
+    @webmethod(route="/openai/v1/batches", method="GET")
+    async def list_batches(
+        self,
+        after: str | None = None,
+        limit: int = 20,
+    ) -> ListBatchesResponse:
+        """List all batches for the current user.
+
+        :param after: A cursor for pagination; returns batches after this batch ID.
+        :param limit: Number of batches to return (default 20, max 100).
+        :returns: A list of batch objects.
+        """
+        ...

llama_stack/apis/common/errors.py

@@ -62,3 +62,10 @@ class SessionNotFoundError(ValueError):
     def __init__(self, session_name: str) -> None:
         message = f"Session '{session_name}' not found or access denied."
         super().__init__(message)
+
+
+class ConflictError(ValueError):
+    """raised when an operation cannot be performed due to a conflict with the current state"""
+
+    def __init__(self, message: str) -> None:
+        super().__init__(message)

llama_stack/apis/datatypes.py

@@ -86,6 +86,7 @@ class Api(Enum, metaclass=DynamicApiMeta):
     :cvar inference: Text generation, chat completions, and embeddings
     :cvar safety: Content moderation and safety shields
     :cvar agents: Agent orchestration and execution
+    :cvar batches: Batch processing for asynchronous API requests
     :cvar vector_io: Vector database operations and queries
     :cvar datasetio: Dataset input/output operations
     :cvar scoring: Model output evaluation and scoring
@@ -108,6 +109,7 @@ class Api(Enum, metaclass=DynamicApiMeta):
     inference = "inference"
     safety = "safety"
     agents = "agents"
+    batches = "batches"
     vector_io = "vector_io"
     datasetio = "datasetio"
     scoring = "scoring"

llama_stack/apis/files/files.py

@@ -22,6 +22,7 @@ class OpenAIFilePurpose(StrEnum):
     """
 
     ASSISTANTS = "assistants"
+    BATCH = "batch"
     # TODO: Add other purposes as needed