diff --git a/enterprise/dist/litellm_enterprise-0.1.29-py3-none-any.whl b/enterprise/dist/litellm_enterprise-0.1.29-py3-none-any.whl new file mode 100644 index 00000000000..0895ecbc427 Binary files /dev/null and b/enterprise/dist/litellm_enterprise-0.1.29-py3-none-any.whl differ diff --git a/enterprise/dist/litellm_enterprise-0.1.29.tar.gz b/enterprise/dist/litellm_enterprise-0.1.29.tar.gz new file mode 100644 index 00000000000..6781cf26cc9 Binary files /dev/null and b/enterprise/dist/litellm_enterprise-0.1.29.tar.gz differ diff --git a/enterprise/pyproject.toml b/enterprise/pyproject.toml index 0d86460a649..c5aaa0a3407 100644 --- a/enterprise/pyproject.toml +++ b/enterprise/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "litellm-enterprise" -version = "0.1.28" +version = "0.1.29" description = "Package for LiteLLM Enterprise features" authors = ["BerriAI"] readme = "README.md" @@ -22,7 +22,7 @@ requires = ["poetry-core"] build-backend = "poetry.core.masonry.api" [tool.commitizen] -version = "0.1.28" +version = "0.1.29" version_files = [ "pyproject.toml:version", "../requirements.txt:litellm-enterprise==", diff --git a/litellm/__init__.py b/litellm/__init__.py index 112d58d49d8..f857e10eed3 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -1378,6 +1378,7 @@ if TYPE_CHECKING: from .llms.topaz.image_variations.transformation import TopazImageVariationConfig as TopazImageVariationConfig from litellm.llms.openai.completion.transformation import OpenAITextCompletionConfig as OpenAITextCompletionConfig from .llms.groq.chat.transformation import GroqChatConfig as GroqChatConfig + from .llms.a2a.chat.transformation import A2AConfig as A2AConfig from .llms.voyage.embedding.transformation import VoyageEmbeddingConfig as VoyageEmbeddingConfig from .llms.voyage.embedding.transformation_contextual import VoyageContextualEmbeddingConfig as VoyageContextualEmbeddingConfig from .llms.infinity.embedding.transformation import InfinityEmbeddingConfig as InfinityEmbeddingConfig diff --git a/litellm/_lazy_imports_registry.py b/litellm/_lazy_imports_registry.py index 0e52e9a59eb..a01fe9c11db 100644 --- a/litellm/_lazy_imports_registry.py +++ b/litellm/_lazy_imports_registry.py @@ -213,6 +213,7 @@ LLM_CONFIG_NAMES = ( "TopazImageVariationConfig", "OpenAITextCompletionConfig", "GroqChatConfig", + "A2AConfig", "GenAIHubOrchestrationConfig", "VoyageEmbeddingConfig", "VoyageContextualEmbeddingConfig", @@ -850,6 +851,7 @@ _LLM_CONFIGS_IMPORT_MAP = { "OpenAITextCompletionConfig", ), "GroqChatConfig": (".llms.groq.chat.transformation", "GroqChatConfig"), + "A2AConfig": (".llms.a2a.chat.transformation", "A2AConfig"), "GenAIHubOrchestrationConfig": ( ".llms.sap.chat.transformation", "GenAIHubOrchestrationConfig", diff --git a/litellm/llms/a2a/__init__.py b/litellm/llms/a2a/__init__.py new file mode 100644 index 00000000000..043efa5e8bf --- /dev/null +++ b/litellm/llms/a2a/__init__.py @@ -0,0 +1,6 @@ +""" +A2A (Agent-to-Agent) Protocol Provider for LiteLLM +""" +from .chat.transformation import A2AConfig + +__all__ = ["A2AConfig"] diff --git a/litellm/llms/a2a/chat/__init__.py b/litellm/llms/a2a/chat/__init__.py new file mode 100644 index 00000000000..76bf4dd71d9 --- /dev/null +++ b/litellm/llms/a2a/chat/__init__.py @@ -0,0 +1,6 @@ +""" +A2A Chat Completion Implementation +""" +from .transformation import A2AConfig + +__all__ = ["A2AConfig"] diff --git a/litellm/llms/a2a/chat/streaming_iterator.py b/litellm/llms/a2a/chat/streaming_iterator.py new file mode 100644 index 00000000000..84b6fffaa31 --- /dev/null +++ b/litellm/llms/a2a/chat/streaming_iterator.py @@ -0,0 +1,103 @@ +""" +A2A Streaming Response Iterator +""" +from typing import Optional, Union + +from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator +from litellm.types.utils import GenericStreamingChunk, ModelResponseStream + +from ..common_utils import extract_text_from_a2a_response + + +class A2AModelResponseIterator(BaseModelResponseIterator): + """ + Iterator for parsing A2A streaming responses. + + Converts A2A JSON-RPC streaming chunks to OpenAI-compatible format. + """ + + def __init__( + self, + streaming_response, + sync_stream: bool, + json_mode: Optional[bool] = False, + model: str = "a2a/agent", + ): + super().__init__( + streaming_response=streaming_response, + sync_stream=sync_stream, + json_mode=json_mode, + ) + self.model = model + + def chunk_parser(self, chunk: dict) -> Union[GenericStreamingChunk, ModelResponseStream]: + """ + Parse A2A streaming chunk to OpenAI format. + + A2A chunk format: + { + "jsonrpc": "2.0", + "id": "request-id", + "result": { + "message": { + "parts": [{"kind": "text", "text": "content"}] + } + } + } + + Or for tasks: + { + "jsonrpc": "2.0", + "result": { + "kind": "task", + "status": {"state": "running"}, + "artifacts": [{"parts": [{"kind": "text", "text": "content"}]}] + } + } + """ + try: + # Extract text from A2A response + text = extract_text_from_a2a_response(chunk) + + # Determine finish reason + finish_reason = self._get_finish_reason(chunk) + + # Return generic streaming chunk + return GenericStreamingChunk( + text=text, + is_finished=bool(finish_reason), + finish_reason=finish_reason or "", + usage=None, + index=0, + tool_use=None, + ) + except Exception: + # Return empty chunk on parse error + return GenericStreamingChunk( + text="", + is_finished=False, + finish_reason="", + usage=None, + index=0, + tool_use=None, + ) + + def _get_finish_reason(self, chunk: dict) -> Optional[str]: + """Extract finish reason from A2A chunk""" + result = chunk.get("result", {}) + + # Check for task completion + if isinstance(result, dict): + status = result.get("status", {}) + if isinstance(status, dict): + state = status.get("state") + if state == "completed": + return "stop" + elif state == "failed": + return "error" + + # Check for [DONE] marker + if chunk.get("done") is True: + return "stop" + + return None diff --git a/litellm/llms/a2a/chat/transformation.py b/litellm/llms/a2a/chat/transformation.py new file mode 100644 index 00000000000..243fba63719 --- /dev/null +++ b/litellm/llms/a2a/chat/transformation.py @@ -0,0 +1,303 @@ +""" +A2A Protocol Transformation for LiteLLM +""" +import uuid +from typing import Any, Dict, Iterator, List, Optional, Union, cast + +import httpx +from pydantic import BaseModel + +from litellm.llms.base_llm.base_model_iterator import BaseModelResponseIterator +from litellm.llms.base_llm.chat.transformation import BaseConfig, BaseLLMException +from litellm.types.llms.openai import AllMessageValues +from litellm.types.utils import Choices, Message, ModelResponse + +from ..common_utils import ( + A2AError, + convert_messages_to_prompt, + extract_text_from_a2a_response, +) +from .streaming_iterator import A2AModelResponseIterator + + +class A2AConfig(BaseConfig): + """ + Configuration for A2A (Agent-to-Agent) Protocol. + + Handles transformation between OpenAI and A2A JSON-RPC 2.0 formats. + """ + + def get_supported_openai_params(self, model: str) -> List[str]: + """Return list of supported OpenAI parameters""" + return [ + "stream", + "temperature", + "max_tokens", + "top_p", + ] + + def map_openai_params( + self, + non_default_params: dict, + optional_params: dict, + model: str, + drop_params: bool, + ) -> dict: + """ + Map OpenAI parameters to A2A parameters. + + For A2A protocol, we don't need to map most parameters since + they're handled in the transform_request method. + """ + return optional_params + + def validate_environment( + self, + headers: dict, + model: str, + messages: List[AllMessageValues], + optional_params: dict, + litellm_params: dict, + api_key: Optional[str] = None, + api_base: Optional[str] = None, + ) -> dict: + """ + Validate environment and set headers for A2A requests. + + Args: + headers: Request headers dict + model: Model name + messages: Messages list + optional_params: Optional parameters + litellm_params: LiteLLM parameters + api_key: API key (optional for A2A) + api_base: API base URL + + Returns: + Updated headers dict + """ + # Ensure Content-Type is set to application/json for JSON-RPC 2.0 + if "content-type" not in headers and "Content-Type" not in headers: + headers["Content-Type"] = "application/json" + + # Add Authorization header if API key is provided + if api_key is not None: + headers["Authorization"] = f"Bearer {api_key}" + + return headers + + def get_complete_url( + self, + api_base: Optional[str], + api_key: Optional[str], + model: str, + optional_params: dict, + litellm_params: dict, + stream: Optional[bool] = None, + ) -> str: + """ + Get the complete A2A agent endpoint URL. + + A2A agents use JSON-RPC 2.0 at the base URL, not specific paths. + The method (message/send or message/stream) is specified in the + JSON-RPC request body, not in the URL. + + Args: + api_base: Base URL of the A2A agent (e.g., "http://0.0.0.0:9999") + api_key: API key (not used for URL construction) + model: Model name (not used for A2A, agent determined by api_base) + optional_params: Optional parameters + litellm_params: LiteLLM parameters + stream: Whether this is a streaming request (affects JSON-RPC method) + + Returns: + Complete URL for the A2A endpoint (base URL) + """ + if api_base is None: + raise ValueError("api_base is required for A2A provider") + + # A2A uses JSON-RPC 2.0 at the base URL + # Remove trailing slash for consistency + return api_base.rstrip("/") + + def transform_request( + self, + model: str, + messages: List[AllMessageValues], + optional_params: dict, + litellm_params: dict, + headers: dict, + ) -> dict: + """ + Transform OpenAI request to A2A JSON-RPC 2.0 format. + + Args: + model: Model name + messages: List of OpenAI messages + optional_params: Optional parameters + litellm_params: LiteLLM parameters + headers: Request headers + + Returns: + A2A JSON-RPC 2.0 request dict + """ + # Generate request ID + request_id = str(uuid.uuid4()) + + if not messages: + raise ValueError("At least one message is required for A2A completion") + + # Convert all messages to maintain conversation history + # Use helper to format conversation with role prefixes + full_context = convert_messages_to_prompt(messages) + + # Create single A2A message with full conversation context + a2a_message = { + "role": "user", + "parts": [{"kind": "text", "text": full_context}], + "messageId": str(uuid.uuid4()), + } + + # Build JSON-RPC 2.0 request + # For A2A protocol, the method is "message/send" for non-streaming + # and "message/stream" for streaming (handled by optional_params["stream"]) + method = "message/stream" if optional_params.get("stream") else "message/send" + + request_data = { + "jsonrpc": "2.0", + "id": request_id, + "method": method, + "params": { + "message": a2a_message + } + } + + return request_data + + def transform_response( + self, + model: str, + raw_response: httpx.Response, + model_response: ModelResponse, + logging_obj: Any, + request_data: dict, + messages: List[AllMessageValues], + optional_params: dict, + litellm_params: dict, + encoding: Any, + api_key: Optional[str] = None, + json_mode: Optional[bool] = None, + ) -> ModelResponse: + """ + Transform A2A JSON-RPC 2.0 response to OpenAI format. + + Args: + model: Model name + raw_response: HTTP response from A2A agent + model_response: Model response object to populate + logging_obj: Logging object + request_data: Original request data + messages: Original messages + optional_params: Optional parameters + litellm_params: LiteLLM parameters + encoding: Encoding object + api_key: API key + json_mode: JSON mode flag + + Returns: + Populated ModelResponse object + """ + try: + response_json = raw_response.json() + except Exception as e: + raise A2AError( + status_code=raw_response.status_code, + message=f"Failed to parse A2A response: {str(e)}", + headers=dict(raw_response.headers), + ) + + # Check for JSON-RPC error + if "error" in response_json: + error = response_json["error"] + raise A2AError( + status_code=raw_response.status_code, + message=f"A2A error: {error.get('message', 'Unknown error')}", + headers=dict(raw_response.headers), + ) + + # Extract text from A2A response + text = extract_text_from_a2a_response(response_json) + + # Populate model response + model_response.choices = [ + Choices( + finish_reason="stop", + index=0, + message=Message( + content=text, + role="assistant", + ), + ) + ] + + # Set model + model_response.model = model + + # Set ID from response + model_response.id = response_json.get("id", str(uuid.uuid4())) + + return model_response + + def get_model_response_iterator( + self, + streaming_response: Union[Iterator, Any], + sync_stream: bool, + json_mode: Optional[bool] = False, + ) -> BaseModelResponseIterator: + """ + Get streaming iterator for A2A responses. + + Args: + streaming_response: Streaming response iterator + sync_stream: Whether this is a sync stream + json_mode: JSON mode flag + + Returns: + A2A streaming iterator + """ + return A2AModelResponseIterator( + streaming_response=streaming_response, + sync_stream=sync_stream, + json_mode=json_mode, + ) + + def _openai_message_to_a2a_message(self, message: Dict[str, Any]) -> Dict[str, Any]: + """ + Convert OpenAI message to A2A message format. + + Args: + message: OpenAI message dict + + Returns: + A2A message dict + """ + content = message.get("content", "") + role = message.get("role", "user") + + return { + "role": role, + "parts": [{"kind": "text", "text": str(content)}], + "messageId": str(uuid.uuid4()), + } + + def get_error_class( + self, error_message: str, status_code: int, headers: Union[dict, httpx.Headers] + ) -> BaseLLMException: + """Return appropriate error class for A2A errors""" + # Convert headers to dict if needed + headers_dict = dict(headers) if isinstance(headers, httpx.Headers) else headers + return A2AError( + status_code=status_code, + message=error_message, + headers=headers_dict, + ) diff --git a/litellm/llms/a2a/common_utils.py b/litellm/llms/a2a/common_utils.py new file mode 100644 index 00000000000..4c7da78b42f --- /dev/null +++ b/litellm/llms/a2a/common_utils.py @@ -0,0 +1,134 @@ +""" +Common utilities for A2A (Agent-to-Agent) Protocol +""" +from typing import Any, Dict, List + +from pydantic import BaseModel + +from litellm.litellm_core_utils.prompt_templates.common_utils import ( + convert_content_list_to_str, +) +from litellm.llms.base_llm.chat.transformation import BaseLLMException +from litellm.types.llms.openai import AllMessageValues + + +class A2AError(BaseLLMException): + """Base exception for A2A protocol errors""" + + def __init__( + self, + status_code: int, + message: str, + headers: Dict[str, Any] = {}, + ): + super().__init__( + status_code=status_code, + message=message, + headers=headers, + ) + + +def convert_messages_to_prompt(messages: List[AllMessageValues]) -> str: + """ + Convert OpenAI messages to a single prompt string for A2A agent. + + Formats each message as "{role}: {content}" and joins with newlines + to preserve conversation history. Handles both string and list content. + + Args: + messages: List of OpenAI-format messages + + Returns: + Formatted prompt string with full conversation context + """ + conversation_parts = [] + for msg in messages: + # Use LiteLLM's helper to extract text from content (handles both str and list) + content_text = convert_content_list_to_str(message=msg) + + # Get role + if isinstance(msg, BaseModel): + role = msg.model_dump().get("role", "user") + elif isinstance(msg, dict): + role = msg.get("role", "user") + else: + role = dict(msg).get("role", "user") # type: ignore + + if content_text: + conversation_parts.append(f"{role}: {content_text}") + + return "\n".join(conversation_parts) + + +def extract_text_from_a2a_message( + message: Dict[str, Any], depth: int = 0, max_depth: int = 10 +) -> str: + """ + Extract text content from A2A message parts. + + Args: + message: A2A message dict with 'parts' containing text parts + depth: Current recursion depth (internal use) + max_depth: Maximum recursion depth to prevent infinite loops + + Returns: + Concatenated text from all text parts + """ + if message is None or depth >= max_depth: + return "" + + parts = message.get("parts", []) + text_parts: List[str] = [] + + for part in parts: + if part.get("kind") == "text": + text_parts.append(part.get("text", "")) + # Handle nested parts if they exist + elif "parts" in part: + nested_text = extract_text_from_a2a_message(part, depth + 1, max_depth) + if nested_text: + text_parts.append(nested_text) + + return " ".join(text_parts) + + +def extract_text_from_a2a_response( + response_dict: Dict[str, Any], max_depth: int = 10 +) -> str: + """ + Extract text content from A2A response result. + + Args: + response_dict: A2A response dict with 'result' containing message + max_depth: Maximum recursion depth to prevent infinite loops + + Returns: + Text from response message parts + """ + result = response_dict.get("result", {}) + if not isinstance(result, dict): + return "" + + # A2A response can have different formats: + # 1. Direct message: {"result": {"kind": "message", "parts": [...]}} + # 2. Nested message: {"result": {"message": {"parts": [...]}}} + # 3. Task with artifacts: {"result": {"kind": "task", "artifacts": [{"parts": [...]}]}} + + # Check if result itself has parts (direct message) + if "parts" in result: + return extract_text_from_a2a_message(result, depth=0, max_depth=max_depth) + + # Check for nested message + message = result.get("message") + if message: + return extract_text_from_a2a_message(message, depth=0, max_depth=max_depth) + + # Handle task result with artifacts + artifacts = result.get("artifacts", []) + if artifacts and len(artifacts) > 0: + first_artifact = artifacts[0] + return extract_text_from_a2a_message( + first_artifact, depth=0, max_depth=max_depth + ) + + return "" diff --git a/litellm/main.py b/litellm/main.py index 7d591f76882..60c889ab1d0 100644 --- a/litellm/main.py +++ b/litellm/main.py @@ -2199,6 +2199,38 @@ def completion( # type: ignore # noqa: PLR0915 logging_obj=logging, # model call logging done inside the class as we make need to modify I/O to fit aleph alpha's requirements client=client, ) + elif custom_llm_provider == "a2a": + # A2A (Agent-to-Agent) Protocol + api_base = ( + api_base + or litellm.api_base + or get_secret_str("A2A_API_BASE") + ) + + if api_base is None: + raise Exception("api_base is required for A2A provider") + + headers = headers or litellm.headers + + response = base_llm_http_handler.completion( + model=model, + stream=stream, + messages=messages, + acompletion=acompletion, + api_base=api_base, + model_response=model_response, + optional_params=optional_params, + litellm_params=litellm_params, + shared_session=shared_session, + custom_llm_provider=custom_llm_provider, + timeout=timeout, + headers=headers, + encoding=_get_encoding(), + api_key=api_key, + logging_obj=logging, + client=client, + provider_config=provider_config, + ) elif custom_llm_provider == "gigachat": # GigaChat - Sber AI's LLM (Russia) api_key = ( @@ -3113,8 +3145,8 @@ def completion( # type: ignore # noqa: PLR0915 api_key or litellm.api_key or litellm.openrouter_key - or get_secret("OPENROUTER_API_KEY") - or get_secret("OR_API_KEY") + or get_secret_str("OPENROUTER_API_KEY") + or get_secret_str("OR_API_KEY") ) openrouter_site_url = get_secret("OR_SITE_URL") or "https://litellm.ai" @@ -4884,8 +4916,8 @@ def embedding( # noqa: PLR0915 api_key or litellm.api_key or litellm.openrouter_key - or get_secret("OPENROUTER_API_KEY") - or get_secret("OR_API_KEY") + or get_secret_str("OPENROUTER_API_KEY") + or get_secret_str("OR_API_KEY") ) openrouter_site_url = get_secret("OR_SITE_URL") or "https://litellm.ai" diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 485bee4f191..b9e48fd7e11 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -27113,6 +27113,34 @@ "supports_reasoning": true, "supports_tool_choice": true }, + "together_ai/zai-org/GLM-4.7": { + "input_cost_per_token": 4.5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 200000, + "max_output_tokens": 200000, + "max_tokens": 200000, + "mode": "chat", + "output_cost_per_token": 2e-06, + "source": "https://www.together.ai/models/glm-4-7", + "supports_function_calling": true, + "supports_parallel_function_calling": true, + "supports_reasoning": true, + "supports_tool_choice": true + }, + "together_ai/moonshotai/Kimi-K2.5": { + "input_cost_per_token": 5e-07, + "litellm_provider": "together_ai", + "max_input_tokens": 256000, + "max_output_tokens": 256000, + "max_tokens": 256000, + "mode": "chat", + "output_cost_per_token": 2.8e-06, + "source": "https://www.together.ai/models/kimi-k2-5", + "supports_function_calling": true, + "supports_tool_choice": true, + "supports_vision": true, + "supports_reasoning": true + }, "together_ai/moonshotai/Kimi-K2-Instruct-0905": { "input_cost_per_token": 1e-06, "litellm_provider": "together_ai", diff --git a/litellm/types/utils.py b/litellm/types/utils.py index 09c944e1fe8..e1f780ffcc3 100644 --- a/litellm/types/utils.py +++ b/litellm/types/utils.py @@ -3029,6 +3029,7 @@ class LlmProviders(str, Enum): MISTRAL = "mistral" MILVUS = "milvus" GROQ = "groq" + A2A = "a2a" GIGACHAT = "gigachat" NVIDIA_NIM = "nvidia_nim" CEREBRAS = "cerebras" diff --git a/litellm/utils.py b/litellm/utils.py index f3d14b455cd..7109f7aa881 100644 --- a/litellm/utils.py +++ b/litellm/utils.py @@ -1453,6 +1453,10 @@ def client(original_function): # noqa: PLR0915 logging_obj, kwargs = function_setup( original_function.__name__, rules_obj, start_time, *args, **kwargs ) + + # Type assertion: logging_obj is guaranteed to be non-None after function_setup + assert logging_obj is not None, "logging_obj should not be None after function_setup" + ## LOAD CREDENTIALS load_credentials_from_list(kwargs) kwargs["litellm_logging_obj"] = logging_obj @@ -1771,6 +1775,9 @@ def client(original_function): # noqa: PLR0915 logging_obj, kwargs = function_setup( original_function.__name__, rules_obj, start_time, *args, **kwargs ) + + # Type assertion: logging_obj is guaranteed to be non-None after function_setup + assert logging_obj is not None, "logging_obj should not be None after function_setup" modified_kwargs = await async_pre_call_deployment_hook(kwargs, call_type) if modified_kwargs is not None: @@ -7799,6 +7806,7 @@ class ProviderConfigManager: # Simple provider mappings (no model parameter needed) LlmProviders.DEEPSEEK: (lambda: litellm.DeepSeekChatConfig(), False), LlmProviders.GROQ: (lambda: litellm.GroqChatConfig(), False), + LlmProviders.A2A: (lambda: litellm.A2AConfig(), False), LlmProviders.BYTEZ: (lambda: litellm.BytezChatConfig(), False), LlmProviders.DATABRICKS: (lambda: litellm.DatabricksConfig(), False), LlmProviders.XAI: (lambda: litellm.XAIChatConfig(), False), diff --git a/poetry.lock b/poetry.lock index 3b2a8d20f20..537367c5aa0 100644 --- a/poetry.lock +++ b/poetry.lock @@ -1,4 +1,4 @@ -# This file is automatically @generated by Poetry 2.1.4 and should not be changed by hand. +# This file is automatically @generated by Poetry 2.2.0 and should not be changed by hand. [[package]] name = "a2a-sdk" @@ -5704,24 +5704,6 @@ pytest = ">=7.0.0" [package.extras] dev = ["black", "flake8", "isort", "mypy"] -[[package]] -name = "pytest-retry" -version = "1.7.0" -description = "Adds the ability to retry flaky tests in CI environments" -optional = false -python-versions = ">=3.9" -groups = ["dev"] -files = [ - {file = "pytest_retry-1.7.0-py3-none-any.whl", hash = "sha256:a2dac85b79a4e2375943f1429479c65beb6c69553e7dae6b8332be47a60954f4"}, - {file = "pytest_retry-1.7.0.tar.gz", hash = "sha256:f8d52339f01e949df47c11ba9ee8d5b362f5824dff580d3870ec9ae0057df80f"}, -] - -[package.dependencies] -pytest = ">=7.0.0" - -[package.extras] -dev = ["black", "flake8", "isort", "mypy"] - [[package]] name = "python-dateutil" version = "2.9.0.post0" diff --git a/provider_endpoints_support.json b/provider_endpoints_support.json index 0738c6e4e09..93e9e7beaaa 100644 --- a/provider_endpoints_support.json +++ b/provider_endpoints_support.json @@ -32,6 +32,23 @@ } }, "providers": { + "a2a": { + "display_name": "A2A (Agent-to-Agent) (`a2a`)", + "url": "https://docs.litellm.ai/docs/providers/a2a", + "endpoints": { + "chat_completions": true, + "messages": false, + "responses": false, + "embeddings": false, + "image_generations": false, + "audio_transcriptions": false, + "audio_speech": false, + "moderations": false, + "batches": false, + "rerank": false, + "a2a": false + } + }, "abliteration": { "display_name": "Abliteration (`abliteration`)", "url": "https://docs.litellm.ai/docs/providers/abliteration", diff --git a/requirements.txt b/requirements.txt index 0b7cf4992e8..69768b6c1f7 100644 --- a/requirements.txt +++ b/requirements.txt @@ -73,4 +73,4 @@ pypdf>=6.6.2 # for PDF text extraction in RAG ingestion ######################## # LITELLM ENTERPRISE DEPENDENCIES ######################## -litellm-enterprise==0.1.28 +litellm-enterprise==0.1.29 diff --git a/tests/code_coverage_tests/recursive_detector.py b/tests/code_coverage_tests/recursive_detector.py index d5640f4256c..ed7595bb023 100644 --- a/tests/code_coverage_tests/recursive_detector.py +++ b/tests/code_coverage_tests/recursive_detector.py @@ -40,6 +40,7 @@ IGNORE_FUNCTIONS = [ "filter_exceptions_from_params", # max depth set (default 20) to prevent infinite recursion. "__getattr__", # lazy loading pattern in litellm/__init__.py with proper caching to prevent infinite recursion. "_validate_inheritance_chain", # max depth set (default 100) to prevent infinite recursion in policy inheritance validation. + "extract_text_from_a2a_message", # max depth set (default 10) to prevent infinite recursion in A2A message parsing. ] diff --git a/tests/llm_translation/test_a2a.py b/tests/llm_translation/test_a2a.py new file mode 100644 index 00000000000..2cfd3110ae1 --- /dev/null +++ b/tests/llm_translation/test_a2a.py @@ -0,0 +1,132 @@ +""" +Minimal E2E tests for A2A (Agent-to-Agent) Protocol provider. + +Tests validate that the endpoint is reachable and can handle both +streaming and non-streaming requests. +""" +import os +import sys + +import pytest + +sys.path.insert(0, os.path.abspath("../..")) + +import litellm + + +@pytest.mark.asyncio +async def test_a2a_completion_async_non_streaming(): + """ + Test A2A provider with async non-streaming request. + + Minimal test to validate endpoint reachability. + + Note: Requires an A2A agent running at http://0.0.0.0:9999 + Set A2A_API_BASE environment variable to use a different endpoint. + """ + api_base = os.environ.get("A2A_API_BASE", "http://0.0.0.0:9999") + + try: + response = await litellm.acompletion( + model="a2a/test-agent", + messages=[{"role": "user", "content": "Hello"}], + api_base=api_base, + stream=False, + ) + + print(f"Response: {response}") + assert response is not None, "Expected non-None response" + print(f"✅ Async non-streaming test passed") + + except litellm.exceptions.APIConnectionError as e: + pytest.skip(f"A2A agent not reachable at {api_base}: {e}") + except Exception as e: + pytest.fail(f"Error occurred: {e}") + + +@pytest.mark.asyncio +async def test_a2a_completion_async_streaming(): + """ + Test A2A provider with async streaming request. + + Minimal test to validate streaming endpoint reachability. + """ + api_base = os.environ.get("A2A_API_BASE", "http://0.0.0.0:9999") + + try: + response = await litellm.acompletion( + model="a2a/test-agent", + messages=[{"role": "user", "content": "Hello"}], + api_base=api_base, + stream=True, + ) + + chunks = [] + async for chunk in response: # type: ignore + chunks.append(chunk) + print(f"Chunk: {chunk}") + + assert len(chunks) > 0, "Expected at least one chunk in streaming response" + print(f"✅ Async streaming test passed: received {len(chunks)} chunks") + + except litellm.exceptions.APIConnectionError as e: + pytest.skip(f"A2A agent not reachable at {api_base}: {e}") + except Exception as e: + pytest.fail(f"Error occurred: {e}") + + +def test_a2a_completion_sync(): + """ + Test A2A provider with synchronous non-streaming request. + + Minimal test to validate sync endpoint reachability. + """ + api_base = os.environ.get("A2A_API_BASE", "http://0.0.0.0:9999") + + try: + response = litellm.completion( + model="a2a/test-agent", + messages=[{"role": "user", "content": "Hello"}], + api_base=api_base, + stream=False, + ) + + print(f"Response: {response}") + assert response is not None, "Expected non-None response" + print(f"✅ Sync non-streaming test passed") + + except litellm.exceptions.APIConnectionError as e: + pytest.skip(f"A2A agent not reachable at {api_base}: {e}") + except Exception as e: + pytest.fail(f"Error occurred: {e}") + + +def test_a2a_completion_sync_streaming(): + """ + Test A2A provider with synchronous streaming request. + + Minimal test to validate sync streaming endpoint reachability. + """ + api_base = os.environ.get("A2A_API_BASE", "http://0.0.0.0:9999") + + try: + response = litellm.completion( + model="a2a/test-agent", + messages=[{"role": "user", "content": "Hello"}], + api_base=api_base, + stream=True, + ) + + chunks = [] + for chunk in response: # type: ignore + chunks.append(chunk) + print(f"Chunk: {chunk}") + + assert len(chunks) > 0, "Expected at least one chunk in streaming response" + print(f"✅ Sync streaming test passed: received {len(chunks)} chunks") + + except litellm.exceptions.APIConnectionError as e: + pytest.skip(f"A2A agent not reachable at {api_base}: {e}") + except Exception as e: + pytest.fail(f"Error occurred: {e}") + diff --git a/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.tsx b/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.tsx index 6a4882a92a2..8bfbaa8d3a6 100644 --- a/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.tsx +++ b/ui/litellm-dashboard/src/app/(dashboard)/models-and-endpoints/ModelsAndEndpointsView.tsx @@ -400,6 +400,7 @@ const ModelsAndEndpointsView: React.FC = ({ premiumUser, te all_models_on_proxy={allModelsOnProxy} getDisplayModelName={getDisplayModelName} setSelectedModelId={setSelectedModelId} + teams={teams} /> string; setSelectedModelId?: (modelId: string) => void; + teams?: Team[] | null; } const HealthCheckComponent: React.FC = ({ @@ -32,6 +34,7 @@ const HealthCheckComponent: React.FC = ({ all_models_on_proxy, getDisplayModelName, setSelectedModelId, + teams, }) => { const [modelHealthStatuses, setModelHealthStatuses] = useState<{ [key: string]: HealthStatus }>({}); const [selectedModelsForHealth, setSelectedModelsForHealth] = useState([]); @@ -574,6 +577,7 @@ const HealthCheckComponent: React.FC = ({ showErrorModal, showSuccessModal, setSelectedModelId, + teams, )} data={modelData.data.map((model: any) => { const modelName = model.model_name; diff --git a/ui/litellm-dashboard/src/components/model_dashboard/health_check_columns.tsx b/ui/litellm-dashboard/src/components/model_dashboard/health_check_columns.tsx index 077b9d1004f..3e8ae662ad4 100644 --- a/ui/litellm-dashboard/src/components/model_dashboard/health_check_columns.tsx +++ b/ui/litellm-dashboard/src/components/model_dashboard/health_check_columns.tsx @@ -2,6 +2,7 @@ import { ColumnDef } from "@tanstack/react-table"; import { Tooltip, Checkbox } from "antd"; import { Text } from "@tremor/react"; import { InformationCircleIcon, PlayIcon, RefreshIcon } from "@heroicons/react/outline"; +import { Team } from "@/components/key_team_helpers/key_list"; interface HealthCheckData { model_name: string; @@ -42,6 +43,7 @@ export const healthCheckColumns = ( showErrorModal?: (modelName: string, cleanedError: string, fullError: string) => void, showSuccessModal?: (modelName: string, response: any) => void, setSelectedModelId?: (modelId: string) => void, + teams?: Team[] | null, ): ColumnDef[] => [ { header: () => ( @@ -100,6 +102,31 @@ export const healthCheckColumns = ( ); }, }, + { + header: "Team Alias", + accessorKey: "model_info.team_id", + enableSorting: true, + sortingFn: "alphanumeric", + cell: ({ row }) => { + const model = row.original; + const teamId = model.model_info?.team_id; + + if (!teamId) { + return -; + } + + const team = teams?.find((t) => t.team_id === teamId); + const teamAlias = team?.team_alias || teamId; + + return ( +
+ +
{teamAlias}
+ +
+ ); + }, + }, { header: "Health Status", accessorKey: "health_status", diff --git a/ui/litellm-dashboard/src/components/templates/model_dashboard.tsx b/ui/litellm-dashboard/src/components/templates/model_dashboard.tsx index e4dc896f55d..6f3ce27567c 100644 --- a/ui/litellm-dashboard/src/components/templates/model_dashboard.tsx +++ b/ui/litellm-dashboard/src/components/templates/model_dashboard.tsx @@ -1368,6 +1368,7 @@ const OldModelDashboard: React.FC = ({ all_models_on_proxy={all_models_on_proxy} getDisplayModelName={getDisplayModelName} setSelectedModelId={setSelectedModelId} + teams={teams} />