scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103

refactor(types): move SpanAttributes, SpecialHeaders and AllowedModelRegion out of proxy._types (#44717)

Browse source 
Co-authored-by: nate <nate@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
devin-ai-integration[bot] 2026-10-05 21:40:13 -07:00 • committed by GitHub
parent c3e0156979
commit b72c737fc8
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
19 changed files with 139 additions and 125 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
litellm/anthropic_beta_headers_manager.py
View file

@ -29,7 +29,7 @@ from typing import Final
import httpx
from litellm.litellm_core_utils.litellm_logging import verbose_logger
from litellm._logging import verbose_logger
# Cache for the loaded configuration
_BETA_HEADERS_CONFIG: dict | None = None

2
litellm/integrations/SlackAlerting/slack_alerting.py
View file

@ -39,7 +39,6 @@ from litellm.llms.custom_httpx.http_handler import (
httpxSpecialProvider,
)
from litellm.proxy._types import (
AlertType,
CallInfo,
InvitationModel,
InvitationNew,
@ -52,6 +51,7 @@ from litellm.repositories.table_repositories import InvitationLinkRepository
from litellm.repositories.team_repository import TeamRepository
from litellm.repositories.user_repository import UserRepository
from litellm.types.integrations.slack_alerting import *
from litellm.types.integrations.slack_alerting import AlertType
from litellm.types.proxy.model_deprecation import (
DEFAULT_DEPRECATION_CHECK_INTERVAL_SECONDS,
DEPRECATION_IDLE_POLL_SECONDS,

2
litellm/integrations/SlackAlerting/utils.py
View file

@ -8,8 +8,8 @@ from typing import TYPE_CHECKING, Any, Final
import litellm
from litellm.integrations.custom_logger import CustomLogger
from litellm.proxy._types import AlertType
from litellm.secret_managers.main import get_secret
from litellm.types.integrations.slack_alerting import AlertType
if TYPE_CHECKING:
from litellm.litellm_core_utils.litellm_logging import Logging as _Logging

2
litellm/integrations/langtrace.py
View file

@ -1,7 +1,7 @@
import json
from typing import TYPE_CHECKING, Any, Final
from litellm.proxy._types import SpanAttributes
from litellm.types.integrations.otel_span_attributes import SpanAttributes
if TYPE_CHECKING:
from opentelemetry.trace import Span as _Span

13
litellm/integrations/opentelemetry.py
View file

@ -14,7 +14,9 @@ import litellm
from litellm._logging import verbose_logger
from litellm.integrations._types.open_inference import (
OpenInferenceSpanKindValues,
SpanAttributes,
)
from litellm.integrations._types.open_inference import (
SpanAttributes as OpenInferenceSpanAttributes,
)
from litellm.integrations.custom_logger import CustomLogger
from litellm.integrations.langtrace import LANGTRACE_TRACE_PATH
@ -38,6 +40,7 @@ from litellm.litellm_core_utils.service_tier_utils import (
get_served_service_tier,
)
from litellm.secret_managers.main import get_secret_bool, str_to_bool
from litellm.types.integrations.otel_span_attributes import SpanAttributes
from litellm.types.services import ServiceLoggerPayload
from litellm.types.utils import (
ChatCompletionMessageToolCall,
@ -2055,7 +2058,7 @@ class OpenTelemetry(OTELGenAISemconvMixin, CustomLogger):
self.safe_set_attribute(
span=guardrail_span,
key=SpanAttributes.OPENINFERENCE_SPAN_KIND,
key=OpenInferenceSpanAttributes.OPENINFERENCE_SPAN_KIND,
value=OpenInferenceSpanKindValues.GUARDRAIL.value,
)
@ -2306,8 +2309,6 @@ class OpenTelemetry(OTELGenAISemconvMixin, CustomLogger):
def set_tools_attributes(self, span: Span, tools):
import json
from litellm.proxy._types import SpanAttributes
if not tools:
return
@ -2357,8 +2358,6 @@ class OpenTelemetry(OTELGenAISemconvMixin, CustomLogger):
def _tool_calls_kv_pair(
tool_calls: list[ChatCompletionMessageToolCall],
) -> dict[str, object]:
from litellm.proxy._types import SpanAttributes
kv_pairs: Final[dict[str, object]] = {}
for idx, tool_call in enumerate(tool_calls):
_function = tool_call.get("function")
@ -2394,8 +2393,6 @@ class OpenTelemetry(OTELGenAISemconvMixin, CustomLogger):
set_weave_otel_attributes(span, kwargs, response_obj)
return
from litellm.proxy._types import SpanAttributes
optional_params: Final = kwargs.get("optional_params", {})
litellm_params: Final = kwargs.get("litellm_params", {}) or {}
standard_logging_payload: Final[StandardLoggingPayload | None] = kwargs.get("standard_logging_object")

2
litellm/llms/anthropic/common_utils.py
View file

@ -39,7 +39,6 @@ from litellm.llms.anthropic.wif import (
)
from litellm.llms.base_llm.base_utils import BaseLLMModelInfo, BaseTokenCounter
from litellm.llms.base_llm.chat.transformation import BaseLLMException
from litellm.proxy._types import SpecialHeaders
from litellm.types.llms.anthropic import (
ANTHROPIC_HOSTED_TOOLS,
ANTHROPIC_MID_CONVERSATION_OUTPUT_CONFIG_BETA_HEADER,
@ -53,6 +52,7 @@ from litellm.types.llms.anthropic import (
AnthropicThinkingParam,
)
from litellm.types.llms.openai import AllMessageValues
from litellm.types.proxy.auth.special_headers import SpecialHeaders
from litellm.types.proxy.model_listing import ModelInfoResponse
from litellm.types.utils import LlmProviders

2
litellm/llms/anthropic/pass_through/messages/transformation.py
View file

@ -3,9 +3,9 @@ from typing import Any, ClassVar, Final
import httpx
from litellm._logging import verbose_logger
from litellm.exceptions import AuthenticationError
from litellm.litellm_core_utils.litellm_logging import Logging as LiteLLMLoggingObj
from litellm.litellm_core_utils.litellm_logging import verbose_logger
from litellm.llms.base_llm.anthropic_messages.transformation import (
BaseAnthropicMessagesConfig,
)

2
litellm/llms/bedrock/messages/invoke_transformations/anthropic_claude3_transformation.py
View file

@ -5,6 +5,7 @@ from typing import TYPE_CHECKING, Any, Final, cast
import httpx
import litellm
from litellm._logging import verbose_logger
from litellm.anthropic_beta_headers_manager import filter_and_transform_beta_headers
from litellm.constants import (
BEDROCK_MIN_THINKING_BUDGET_TOKENS,
@ -12,7 +13,6 @@ from litellm.constants import (
DEFAULT_REASONING_EFFORT_MEDIUM_THINKING_BUDGET,
DEFAULT_REASONING_EFFORT_XHIGH_THINKING_BUDGET,
)
from litellm.litellm_core_utils.litellm_logging import verbose_logger
from litellm.llms.anthropic.chat.transformation import (
DROP_UNSUPPORTED_OUTPUT_CONFIG_WARNING,
AnthropicConfig,

107
litellm/proxy/_types.py
View file

@ -34,6 +34,9 @@ from litellm.types.agents import AgentCaller, AgentResponse
from litellm.types.integrations.compression_interception import (
CompressionSavingsMetadata,
)
from litellm.types.integrations.otel_span_attributes import (
SpanAttributes as SpanAttributes, # noqa: PLC0414 # public re-export
)
from litellm.types.integrations.slack_alerting import AlertType
from litellm.types.llms.openai import (
AllMessageValues,
@ -52,6 +55,9 @@ from litellm.types.mcp import (
)
from litellm.types.mcp_server.mcp_server_manager import MCPInfo
from litellm.types.proxy.agent_identity import ManagedAgentContext
from litellm.types.proxy.auth.special_headers import (
SpecialHeaders as SpecialHeaders, # noqa: PLC0414 # public re-export
)
from litellm.types.proxy.carried_budget_state import (
OrgBudgetSnapshot,
TeamBudgetSnapshot,
@ -59,7 +65,7 @@ from litellm.types.proxy.carried_budget_state import (
)
from litellm.types.proxy.control_plane_endpoints import WorkerRegistryEntry
from litellm.types.proxy.spend_capture_rate import SpendCaptureRateCheckSettings
from litellm.types.router import RouterErrors, UpdateRouterConfig
from litellm.types.router import AllowedModelRegion, RouterErrors, UpdateRouterConfig
from litellm.types.router_weights import validate_router_settings_dict
from litellm.types.secret_managers.main import KeyManagementSystem
from litellm.types.utils import (
@ -2064,9 +2070,6 @@ class DeleteUserRequest(LiteLLMPydanticObjectBase):
user_ids: list[str] # required
AllowedModelRegion = Literal["eu", "us"]
class BudgetNewRequest(LiteLLMPydanticObjectBase):
budget_id: str | None = Field(default=None, description="The unique budget id.")
max_budget: float | None = Field(
@ -4299,66 +4302,6 @@ class SpendLogsPayload(TypedDict):
litellm_call_id: ReadOnly[str | None]
class SpanAttributes(str, enum.Enum):
# Note: We've taken this from opentelemetry-semantic-conventions-ai
# I chose to not add a new dependency to litellm for this
# Semantic Conventions for LLM requests, this needs to be removed after
# OpenTelemetry Semantic Conventions support Gen AI.
# Issue at https://github.com/open-telemetry/opentelemetry-python/issues/3868
# Refer to https://github.com/open-telemetry/semantic-conventions/blob/main/docs/gen-ai/llm-spans.md
LLM_SYSTEM = "gen_ai.system"
LLM_REQUEST_MODEL = "gen_ai.request.model"
LLM_REQUEST_MAX_TOKENS = "gen_ai.request.max_tokens"
LLM_REQUEST_TEMPERATURE = "gen_ai.request.temperature"
LLM_REQUEST_TOP_P = "gen_ai.request.top_p"
LLM_PROMPTS = "gen_ai.prompt"
LLM_COMPLETIONS = "gen_ai.completion"
LLM_RESPONSE_MODEL = "gen_ai.response.model"
LLM_USAGE_COMPLETION_TOKENS = "gen_ai.usage.completion_tokens"
LLM_USAGE_PROMPT_TOKENS = "gen_ai.usage.prompt_tokens"
# OTEL 1.38 attributes
GEN_AI_INPUT_MESSAGES = "gen_ai.input.messages"
GEN_AI_OUTPUT_MESSAGES = "gen_ai.output.messages"
GEN_AI_USAGE_INPUT_TOKENS = "gen_ai.usage.input_tokens"
GEN_AI_USAGE_OUTPUT_TOKENS = "gen_ai.usage.output_tokens"
GEN_AI_USAGE_TOTAL_TOKENS = "gen_ai.usage.total_tokens"
GEN_AI_OPERATION_NAME = "gen_ai.operation.name"
GEN_AI_REQUEST_ID = "gen_ai.request.id"
GEN_AI_SYSTEM_INSTRUCTIONS = "gen_ai.system_instructions"
GEN_AI_RESPONSE_FINISH_REASONS = "gen_ai.response.finish_reasons"
LLM_TOKEN_TYPE = "gen_ai.token.type"
# To be added
# LLM_RESPONSE_FINISH_REASON = "gen_ai.response.finish_reasons"
# LLM_RESPONSE_ID = "gen_ai.response.id"
# LLM
LLM_REQUEST_TYPE = "llm.request.type"
LLM_USAGE_TOTAL_TOKENS = "llm.usage.total_tokens"
LLM_USAGE_TOKEN_TYPE = "llm.usage.token_type"
LLM_USER = "llm.user"
LLM_HEADERS = "llm.headers"
LLM_TOP_K = "llm.top_k"
LLM_IS_STREAMING = "llm.is_streaming"
LLM_FREQUENCY_PENALTY = "llm.frequency_penalty"
LLM_PRESENCE_PENALTY = "llm.presence_penalty"
LLM_CHAT_STOP_SEQUENCES = "llm.chat.stop_sequences"
LLM_REQUEST_FUNCTIONS = "llm.request.functions"
LLM_REQUEST_REPETITION_PENALTY = "llm.request.repetition_penalty"
LLM_RESPONSE_FINISH_REASON = "llm.response.finish_reason"
LLM_RESPONSE_STOP_REASON = "llm.response.stop_reason"
LLM_CONTENT_COMPLETION_CHUNK = "llm.content.completion.chunk"
# OpenAI
LLM_OPENAI_RESPONSE_SYSTEM_FINGERPRINT = "gen_ai.openai.system_fingerprint"
LLM_OPENAI_API_BASE = "gen_ai.openai.api_base"
LLM_OPENAI_API_VERSION = "gen_ai.openai.api_version"
LLM_OPENAI_API_TYPE = "gen_ai.openai.api_type"
class ManagementEndpointLoggingPayload(LiteLLMPydanticObjectBase):
route: str
request_data: dict
@ -4993,42 +4936,6 @@ class JWTKeyMappingResponse(LiteLLMPydanticObjectBase):
updated_by: str | None = None
class SpecialHeaders(enum.Enum):
"""Used by user_api_key_auth.py to get litellm key"""
openai_authorization = "Authorization"
azure_authorization = "API-Key"
anthropic_authorization = "x-api-key"
google_ai_studio_authorization = "x-goog-api-key"
azure_apim_authorization = "Ocp-Apim-Subscription-Key"
custom_litellm_api_key = "x-litellm-api-key"
mcp_auth = "x-mcp-auth"
mcp_servers = "x-mcp-servers"
mcp_access_groups = "x-mcp-access-groups"
@classmethod
def litellm_credential_header_names(cls) -> "frozenset[str]":
"""Lowercased header names user_api_key_auth accepts as a litellm key.
Every header here authenticates the caller, so any code that forwards a
request onward (e.g. the plugin reverse proxy) must strip all of them to
avoid leaking the caller's litellm credential downstream. The static
custom-key header (general_settings.litellm_key_header_name) is runtime
config and must be added on top of this set by the caller.
"""
return frozenset(
header.value.lower()
for header in (
cls.openai_authorization,
cls.azure_authorization,
cls.anthropic_authorization,
cls.google_ai_studio_authorization,
cls.azure_apim_authorization,
cls.custom_litellm_api_key,
)
)
class LitellmDataForBackendLLMCall(TypedDict, total=False):
headers: dict
organization: str

2
litellm/secret_managers/aws_secret_manager.py
View file

@ -17,7 +17,7 @@ from typing import Any, Final
from pydantic import TypeAdapter
import litellm
from litellm.proxy._types import KeyManagementSystem
from litellm.types.secret_managers.main import KeyManagementSystem
_PARSED_LITERAL: Final = TypeAdapter(object)

3
litellm/secret_managers/aws_secret_manager_v2.py
View file

@ -30,11 +30,10 @@ from litellm.llms.custom_httpx.http_handler import (
_get_httpx_client,
get_async_httpx_client,
)
from litellm.proxy._types import KeyManagementSystem
from litellm.rust_bridge.secret_manager import resolve_native_provider_reader
from litellm.secret_managers.main import get_secret_str
from litellm.types.llms.custom_http import httpxSpecialProvider
from litellm.types.secret_managers.main import KeyManagementSettings
from litellm.types.secret_managers.main import KeyManagementSettings, KeyManagementSystem
from .base_secret_manager import BaseSecretManager

2
litellm/secret_managers/cyberark_secret_manager.py
View file

@ -16,8 +16,8 @@ from litellm.llms.custom_httpx.http_handler import (
get_async_httpx_client,
httpxSpecialProvider,
)
from litellm.proxy._types import KeyManagementSystem
from litellm.rust_bridge.secret_manager import resolve_native_provider_reader, resolve_native_provider_writer
from litellm.types.secret_managers.main import KeyManagementSystem
from .base_secret_manager import BaseSecretManager, raise_if_unsafe_secret_name
from .main import str_to_bool

2
litellm/secret_managers/google_kms.py
View file

@ -12,7 +12,7 @@ import os
from typing import Final
import litellm
from litellm.proxy._types import KeyManagementSystem
from litellm.types.secret_managers.main import KeyManagementSystem
def validate_environment():

3
litellm/secret_managers/google_secret_manager.py
View file

@ -8,8 +8,9 @@ from litellm.caching.caching import InMemoryCache
from litellm.constants import SECRET_MANAGER_REFRESH_INTERVAL
from litellm.integrations.gcs_bucket.gcs_bucket_base import GCSBucketBase
from litellm.llms.custom_httpx.http_handler import _get_httpx_client
from litellm.proxy._types import CommonProxyErrors, KeyManagementSystem
from litellm.proxy._types import CommonProxyErrors
from litellm.rust_bridge.secret_manager import resolve_native_provider_reader
from litellm.types.secret_managers.main import KeyManagementSystem
class GoogleSecretManager(GCSBucketBase):

2
litellm/secret_managers/hashicorp_secret_manager.py
View file

@ -15,8 +15,8 @@ from litellm.llms.custom_httpx.http_handler import (
get_async_httpx_client,
httpxSpecialProvider,
)
from litellm.proxy._types import KeyManagementSystem
from litellm.rust_bridge.secret_manager import resolve_native_provider_reader, resolve_native_provider_writer
from litellm.types.secret_managers.main import KeyManagementSystem
from .base_secret_manager import BaseSecretManager, raise_if_unsafe_secret_name

61
litellm/types/integrations/otel_span_attributes.py Normal file
View file

@ -0,0 +1,61 @@
import enum
class SpanAttributes(str, enum.Enum):
# Note: We've taken this from opentelemetry-semantic-conventions-ai
# I chose to not add a new dependency to litellm for this
# Semantic Conventions for LLM requests, this needs to be removed after
# OpenTelemetry Semantic Conventions support Gen AI.
# Issue at https://github.com/open-telemetry/opentelemetry-python/issues/3868
# Refer to https://github.com/open-telemetry/semantic-conventions/blob/main/docs/gen-ai/llm-spans.md
LLM_SYSTEM = "gen_ai.system"
LLM_REQUEST_MODEL = "gen_ai.request.model"
LLM_REQUEST_MAX_TOKENS = "gen_ai.request.max_tokens"
LLM_REQUEST_TEMPERATURE = "gen_ai.request.temperature"
LLM_REQUEST_TOP_P = "gen_ai.request.top_p"
LLM_PROMPTS = "gen_ai.prompt"
LLM_COMPLETIONS = "gen_ai.completion"
LLM_RESPONSE_MODEL = "gen_ai.response.model"
LLM_USAGE_COMPLETION_TOKENS = "gen_ai.usage.completion_tokens"
LLM_USAGE_PROMPT_TOKENS = "gen_ai.usage.prompt_tokens"
# OTEL 1.38 attributes
GEN_AI_INPUT_MESSAGES = "gen_ai.input.messages"
GEN_AI_OUTPUT_MESSAGES = "gen_ai.output.messages"
GEN_AI_USAGE_INPUT_TOKENS = "gen_ai.usage.input_tokens"
GEN_AI_USAGE_OUTPUT_TOKENS = "gen_ai.usage.output_tokens"
GEN_AI_USAGE_TOTAL_TOKENS = "gen_ai.usage.total_tokens"
GEN_AI_OPERATION_NAME = "gen_ai.operation.name"
GEN_AI_REQUEST_ID = "gen_ai.request.id"
GEN_AI_SYSTEM_INSTRUCTIONS = "gen_ai.system_instructions"
GEN_AI_RESPONSE_FINISH_REASONS = "gen_ai.response.finish_reasons"
LLM_TOKEN_TYPE = "gen_ai.token.type"
# To be added
# LLM_RESPONSE_FINISH_REASON = "gen_ai.response.finish_reasons"
# LLM_RESPONSE_ID = "gen_ai.response.id"
# LLM
LLM_REQUEST_TYPE = "llm.request.type"
LLM_USAGE_TOTAL_TOKENS = "llm.usage.total_tokens"
LLM_USAGE_TOKEN_TYPE = "llm.usage.token_type"
LLM_USER = "llm.user"
LLM_HEADERS = "llm.headers"
LLM_TOP_K = "llm.top_k"
LLM_IS_STREAMING = "llm.is_streaming"
LLM_FREQUENCY_PENALTY = "llm.frequency_penalty"
LLM_PRESENCE_PENALTY = "llm.presence_penalty"
LLM_CHAT_STOP_SEQUENCES = "llm.chat.stop_sequences"
LLM_REQUEST_FUNCTIONS = "llm.request.functions"
LLM_REQUEST_REPETITION_PENALTY = "llm.request.repetition_penalty"
LLM_RESPONSE_FINISH_REASON = "llm.response.finish_reason"
LLM_RESPONSE_STOP_REASON = "llm.response.stop_reason"
LLM_CONTENT_COMPLETION_CHUNK = "llm.content.completion.chunk"
# OpenAI
LLM_OPENAI_RESPONSE_SYSTEM_FINGERPRINT = "gen_ai.openai.system_fingerprint"
LLM_OPENAI_API_BASE = "gen_ai.openai.api_base"
LLM_OPENAI_API_VERSION = "gen_ai.openai.api_version"
LLM_OPENAI_API_TYPE = "gen_ai.openai.api_type"

37
litellm/types/proxy/auth/special_headers.py Normal file
View file

@ -0,0 +1,37 @@
import enum
class SpecialHeaders(enum.Enum):
"""Used by user_api_key_auth.py to get litellm key"""
openai_authorization = "Authorization"
azure_authorization = "API-Key"
anthropic_authorization = "x-api-key"
google_ai_studio_authorization = "x-goog-api-key"
azure_apim_authorization = "Ocp-Apim-Subscription-Key"
custom_litellm_api_key = "x-litellm-api-key"
mcp_auth = "x-mcp-auth"
mcp_servers = "x-mcp-servers"
mcp_access_groups = "x-mcp-access-groups"
@classmethod
def litellm_credential_header_names(cls) -> "frozenset[str]":
"""Lowercased header names user_api_key_auth accepts as a litellm key.
Every header here authenticates the caller, so any code that forwards a
request onward (e.g. the plugin reverse proxy) must strip all of them to
avoid leaking the caller's litellm credential downstream. The static
custom-key header (general_settings.litellm_key_header_name) is runtime
config and must be added on top of this set by the caller.
"""
return frozenset(
header.value.lower()
for header in (
cls.openai_authorization,
cls.azure_authorization,
cls.anthropic_authorization,
cls.google_ai_studio_authorization,
cls.azure_apim_authorization,
cls.custom_litellm_api_key,
)
)

15
litellm/types/router.py
View file

@ -6,7 +6,18 @@ import datetime
import enum
from collections.abc import Container, Mapping, Sequence
from dataclasses import dataclass
from typing import TYPE_CHECKING, Annotated, Any, ClassVar, Final, Generic, Literal, TypeVar, get_type_hints
from typing import (
TYPE_CHECKING,
Annotated,
Any,
ClassVar,
Final,
Generic,
Literal,
TypeAlias,
TypeVar,
get_type_hints,
)
from zoneinfo import ZoneInfo, ZoneInfoNotFoundError
import httpx
@ -39,6 +50,8 @@ from .utils import (
server_owned_wif_litellm_params as _server_owned_wif_litellm_params,
)
AllowedModelRegion: TypeAlias = Literal["eu", "us"]
class ConfigurableClientsideParamsCustomAuth(TypedDict):
api_base: str

3
litellm/utils.py
View file

@ -432,7 +432,6 @@ if TYPE_CHECKING:
)
from litellm.llms.cohere.common_utils import CohereModelInfo
from litellm.llms.custom_httpx.http_handler import AsyncHTTPHandler, HTTPHandler
from litellm.proxy._types import AllowedModelRegion
from litellm.router_utils.get_retry_from_policy import (
get_num_retries_from_retry_policy,
reset_retry_policy,
@ -447,7 +446,7 @@ if TYPE_CHECKING:
ChatCompletionToolCallFunctionChunk,
)
from litellm.types.rerank import RerankResponse
from litellm.types.router import LiteLLM_Params
from litellm.types.router import AllowedModelRegion, LiteLLM_Params
from litellm.llms.base_llm.chat.transformation import BaseConfig
from litellm.llms.base_llm.completion.transformation import BaseTextCompletionConfig