diff --git a/basedpyright-code-budget.json b/basedpyright-code-budget.json index 3f0011c80d2..5ec49f48dc7 100644 --- a/basedpyright-code-budget.json +++ b/basedpyright-code-budget.json @@ -1,6 +1,6 @@ { "reportAny": { - "limit": 19945 + "limit": 19936 }, "reportArgumentType": { "limit": 2566 @@ -24,7 +24,7 @@ "limit": 19 }, "reportExplicitAny": { - "limit": 6048 + "limit": 6047 }, "reportFunctionMemberAccess": { "limit": 7 @@ -57,7 +57,7 @@ "limit": 5663 }, "reportMissingTypeArgument": { - "limit": 15545 + "limit": 15536 }, "reportMissingTypeStubs": { "limit": 40 @@ -105,13 +105,13 @@ "limit": 109 }, "reportUnknownMemberType": { - "limit": 38998 + "limit": 38990 }, "reportUnknownParameterType": { - "limit": 19876 + "limit": 19868 }, "reportUnknownVariableType": { - "limit": 30554 + "limit": 30540 }, "reportUnnecessaryCast": { "limit": 117 diff --git a/litellm/litellm_core_utils/llm_cost_calc/usage_object_transformation.py b/litellm/litellm_core_utils/llm_cost_calc/usage_object_transformation.py index df436ef7611..f11f6d46fb2 100644 --- a/litellm/litellm_core_utils/llm_cost_calc/usage_object_transformation.py +++ b/litellm/litellm_core_utils/llm_cost_calc/usage_object_transformation.py @@ -1,6 +1,6 @@ from collections.abc import Mapping, Sequence from types import MappingProxyType -from typing import Any +from typing import Any, Final from litellm.types.utils import ( CompletionTokensDetailsWrapper, @@ -39,7 +39,7 @@ class TranscriptionUsageObjectTransformation: return None -_INTERACTIONS_MODALITY_FIELDS: Mapping[str, str] = MappingProxyType( +_INTERACTIONS_MODALITY_FIELDS: Final[Mapping[str, str]] = MappingProxyType( { "text": "text_tokens", "audio": "audio_tokens", @@ -59,7 +59,7 @@ def _token_count(value: object) -> int: def _modality_token_sums(entries: Sequence[Mapping[str, Any]]) -> Mapping[str, int]: - fields = frozenset(field for entry in entries if (field := _modality_field(entry)) is not None) + fields: Final = frozenset(field for entry in entries if (field := _modality_field(entry)) is not None) return MappingProxyType( { field: sum(_token_count(entry.get("tokens")) for entry in entries if _modality_field(entry) == field) @@ -69,10 +69,13 @@ def _modality_token_sums(entries: Sequence[Mapping[str, Any]]) -> Mapping[str, i def _google_search_query_count(usage_object: Mapping[str, Any]) -> int: + entries: Final = usage_object.get("grounding_tool_count") + if not isinstance(entries, Sequence): + return 0 return sum( _token_count(entry.get("count")) - for entry in tuple(usage_object.get("grounding_tool_count") or ()) - if isinstance(entry, Mapping) and entry.get("type") == "google_search" # pyright: ignore[reportUnnecessaryIsInstance] # provider JSON, not the empty tuple inferred from `or ()` + for entry in entries + if isinstance(entry, Mapping) and entry.get("type") == "google_search" ) @@ -112,30 +115,30 @@ class InteractionsUsageObjectTransformation: @staticmethod def transform_interactions_usage_object(usage_object: Mapping[str, Any]) -> Usage: - input_entries = tuple(usage_object.get("input_tokens_by_modality") or ()) + tuple( + input_entries: Final = tuple(usage_object.get("input_tokens_by_modality") or ()) + tuple( usage_object.get("tool_use_tokens_by_modality") or () ) - cached_sums = _modality_token_sums(tuple(usage_object.get("cached_tokens_by_modality") or ())) - output_sums = _modality_token_sums(tuple(usage_object.get("output_tokens_by_modality") or ())) + cached_sums: Final = _modality_token_sums(tuple(usage_object.get("cached_tokens_by_modality") or ())) + output_sums: Final = _modality_token_sums(tuple(usage_object.get("output_tokens_by_modality") or ())) - total_cached_tokens = _token_count(usage_object.get("total_cached_tokens")) - input_sums = _subtract_cached_from_input( + total_cached_tokens: Final = _token_count(usage_object.get("total_cached_tokens")) + input_sums: Final = _subtract_cached_from_input( input_sums=_modality_token_sums(input_entries), cached_sums=cached_sums, total_cached_tokens=total_cached_tokens, ) - reasoning_tokens = _token_count(usage_object.get("total_reasoning_tokens")) or _token_count( + reasoning_tokens: Final = _token_count(usage_object.get("total_reasoning_tokens")) or _token_count( usage_object.get("total_thought_tokens") ) - prompt_tokens = _token_count(usage_object.get("total_input_tokens")) + _token_count( + prompt_tokens: Final = _token_count(usage_object.get("total_input_tokens")) + _token_count( usage_object.get("total_tool_use_tokens") ) - completion_tokens = _token_count(usage_object.get("total_output_tokens")) + reasoning_tokens - total_tokens = _token_count(usage_object.get("total_tokens")) or (prompt_tokens + completion_tokens) + completion_tokens: Final = _token_count(usage_object.get("total_output_tokens")) + reasoning_tokens + total_tokens: Final = _token_count(usage_object.get("total_tokens")) or (prompt_tokens + completion_tokens) - web_search_requests = _google_search_query_count(usage_object) - prompt_tokens_details = ( + web_search_requests: Final = _google_search_query_count(usage_object) + prompt_tokens_details: Final = ( PromptTokensDetailsWrapper( cached_tokens=total_cached_tokens or None, web_search_requests=web_search_requests or None, @@ -144,7 +147,7 @@ class InteractionsUsageObjectTransformation: if input_sums or total_cached_tokens or web_search_requests else None ) - completion_tokens_details = ( + completion_tokens_details: Final = ( CompletionTokensDetailsWrapper( reasoning_tokens=reasoning_tokens or None, **output_sums, diff --git a/litellm/litellm_core_utils/prompt_templates/common_utils.py b/litellm/litellm_core_utils/prompt_templates/common_utils.py index 72ea85dfa33..748347fe938 100644 --- a/litellm/litellm_core_utils/prompt_templates/common_utils.py +++ b/litellm/litellm_core_utils/prompt_templates/common_utils.py @@ -511,9 +511,6 @@ def update_messages_with_model_file_ids( if "llm_output_file_id," in unified_file_id: provider_file_id = unified_file_id.split("llm_output_file_id,")[1].split(";")[0] if not provider_file_id and is_model_embedded_id(file_id): - # `litellm:;model,` encoding from the - # x-litellm-model upload path. Strip the wrapper - # so the provider sees its own ID. provider_file_id = get_original_file_id(file_id) file_object_file_field["file_id"] = provider_file_id or file_id if format: @@ -588,9 +585,6 @@ def update_responses_input_with_model_file_ids( updated_content_item["file_id"] = provider_file_id updated_content.append(updated_content_item) elif is_model_embedded_id(file_id): - # `litellm:;model,` encoding from the - # x-litellm-model upload path. Strip the wrapper - # so the provider sees its own ID. updated_content_item = content_item.copy() updated_content_item["file_id"] = get_original_file_id(file_id) updated_content.append(updated_content_item) diff --git a/litellm/proxy/health_check.py b/litellm/proxy/health_check.py index d8fde8ca5dc..4e12974189f 100644 --- a/litellm/proxy/health_check.py +++ b/litellm/proxy/health_check.py @@ -183,7 +183,7 @@ async def run_with_timeout(task, timeout): return {"error": "Timeout exceeded", "exception": timeout_exception} -def _is_strategy_router_deployment(litellm_params: dict) -> bool: +def _is_strategy_router_deployment(litellm_params: Mapping[str, object]) -> bool: """True for strategy-router deployments.""" model: Final[object] = litellm_params.get("model", "") return isinstance(model, str) and classify_strategy_router_model(model) is not None diff --git a/ruff-strict-budget.json b/ruff-strict-budget.json index 69902ecfbbb..1cf302a98c9 100644 --- a/ruff-strict-budget.json +++ b/ruff-strict-budget.json @@ -12,10 +12,10 @@ "limit": 2016 }, "ANN202": { - "limit": 850 + "limit": 849 }, "ANN204": { - "limit": 709 + "limit": 708 }, "ANN205": { "limit": 112 @@ -24,7 +24,7 @@ "limit": 133 }, "ANN401": { - "limit": 1185 + "limit": 1183 }, "ASYNC230": { "limit": 11 @@ -231,7 +231,7 @@ "limit": 5 }, "TID251": { - "limit": 1210 + "limit": 1209 }, "TRY002": { "limit": 524 diff --git a/type-discipline-budget.json b/type-discipline-budget.json index 4f2314b2a0a..4054af17d1e 100644 --- a/type-discipline-budget.json +++ b/type-discipline-budget.json @@ -1,9 +1,9 @@ { "LIT001": { - "limit": 22795 + "limit": 22788 }, "LIT002": { - "limit": 26872 + "limit": 26871 }, "LIT003": { "limit": 269 @@ -27,7 +27,7 @@ "limit": 0 }, "LIT010": { - "limit": 16672 + "limit": 16657 }, "LIT011": { "limit": 5588