litellm/litellm/litellm_core_utils at b352d0d4fd76cc5ece5daadb6871a21cd2efe7b8 - litellm - Gitea: Git with a cup of tea

tiennm99/litellm

mirror of https://github.com/tiennm99/litellm.git synced 2026-07-15 20:20:28 +00:00

Files

T

History

Alexsander HamirandGitHub b352d0d4fd [Perf] Remove premature model.dump call on the hot path (#19109 )

2026-01-14 12:40:27 -08:00

..

Use audio content for caching

2025-12-08 19:31:22 +05:30

fix: include IMAGE token count in cost calculation for Gemini models (#18876 )

2026-01-12 17:03:42 +05:30

llm_response_utils

fix: handle empty error objects in response conversion (#18493 )

2026-01-04 00:37:52 +05:30

prompt_templates

fix(gemini): dereference $defs/$ref in tool response content (#19062 )

2026-01-14 22:28:28 +05:30

specialty_caches

…

…

api_route_to_call_types.py

fix: get_call_types_for_route should return None instead of empty list

2025-12-17 12:46:09 +05:30

app_crypto.py

[Fix] SQS Logger - Add Base64 handling (#16028 )

2025-10-28 16:41:32 -07:00

asyncify.py

…

cached_imports.py

…

cli_token_utils.py

…

core_helpers.py

fix: unify model names to provider-defined names

2026-01-02 08:36:58 +09:00

coroutine_checker.py

…

credential_accessor.py

…

custom_logger_registry.py

feat: add support focus export

2026-01-08 16:48:06 +09:00

dd_tracing.py

…

default_encoding.py

Remove double imports

2025-12-24 12:22:19 +05:30

dot_notation_indexing.py

Add Kubernetes ServiceAccount JWT authentication support (#18055 )

2026-01-02 14:02:31 +05:30

duration_parser.py

…

exception_mapping_utils.py

fix(exception_mapping): handle exceptions without response parameter (#18919 )

2026-01-14 04:03:05 +05:30

fallback_utils.py

fix: filter internal params in fallback code and fix test issues (#17941 )

2025-12-13 15:05:26 -08:00

get_litellm_params.py

[Feat] Agent Gateway - Add cost per query for agent invocations (#17774 )

2025-12-10 10:43:52 -08:00

get_llm_provider_logic.py

[Feat] New provider - Manus API on /responses, GET /responses (#18804 )

2026-01-08 18:37:42 +05:30

get_model_cost_map.py

[Fix] CI/CD - litellm_mapped_tests_llms | litellm_mapped_tests_core | caching_unit_tests (#18197 )

2025-12-18 08:49:23 -08:00

get_provider_specific_headers.py

[Fix] Forward anthropic-beta headers to Bedrock, VertexAI (#15700 )

2025-10-18 16:26:32 -07:00

get_supported_openai_params.py

[New provider] Sap gen ai hub (#16053 )

2025-12-08 12:31:06 -08:00

health_check_helpers.py

Add Vertex and Gemini Videos API with Cost Tracking + UI support (#16323 )

2025-11-08 16:03:51 -08:00

health_check_utils.py

…

initialize_dynamic_callback_params.py

…

json_validation_rule.py

…

litellm_logging.py

[Perf] Remove premature model.dump call on the hot path (#19109 )

2026-01-14 12:40:27 -08:00

llm_request_utils.py

…

logging_callback_manager.py

Add log_format parameter to GenericAPILogger (#18587 )

2026-01-02 23:28:30 +05:30

logging_utils.py

…

logging_worker.py

Add memory pattern detection test and fix bad memory patterns (#18589 )

2026-01-02 10:52:25 -08:00

mock_functions.py

…

model_param_helper.py

…

model_response_utils.py

fix: resolve memory leak caused by Pydantic 2.11+ deprecation warnings (#16110 )

2025-11-01 13:16:32 -07:00

README.md

Guardrails API - add streaming support (#17400 )

2025-12-02 22:52:09 -08:00

realtime_streaming.py

…

redact_messages.py

revert changes to redaction

2025-11-08 13:43:01 -08:00

response_header_helpers.py

…

rules.py

…

safe_json_dumps.py

add safe_dumps

2025-11-08 10:19:38 -08:00

safe_json_loads.py

…

sensitive_data_masker.py

Mask extra header secrets in model info (#18822 )

2026-01-08 23:42:05 +05:30

streaming_chunk_builder_utils.py

[Feat] New Model - Azure Model Router on LiteLLM AI Gateway (#19054 )

2026-01-13 18:31:43 -08:00

streaming_handler.py

[Feat] New Model - Azure Model Router on LiteLLM AI Gateway (#19054 )

2026-01-13 18:31:43 -08:00

thread_pool_executor.py

…

token_counter.py

Fix: anthropic token counter with thinking

2026-01-14 12:59:23 +05:30

README.md

Folder Contents

This folder contains general-purpose utilities that are used in multiple places in the codebase.

Core files:

streaming_handler.py: The core streaming logic + streaming related helper utils
core_helpers.py: code used in types/ - e.g. map_finish_reason.
exception_mapping_utils.py: utils for mapping exceptions to openai-compatible error types.
default_encoding.py: code for loading the default encoding (tiktoken)
get_llm_provider_logic.py: code for inferring the LLM provider from a given model name.
duration_parser.py: code for parsing durations - e.g. "1d", "1mo", "10s"
api_route_to_call_types.py: mapping of API routes to their corresponding CallTypes (e.g., /chat/completions -> [acompletion, completion])