litellm/litellm/litellm_core_utils
Mateo Wang d0dd3ce2d8
Merge pull request #38869 from BerriAI/litellm_fix_guardrail_route_call_types
fix(guardrails): resolve generateContent routes and async-first passthrough call types
2026-09-07 15:15:51 -07:00
..
audio_utils fix(audio_utils): validate MPEG frame headers before labeling sniffed audio 2026-08-29 14:20:40 -07:00
llm_cost_calc fix(spend): price caching savings on the billed request basis (#40160) 2026-09-07 21:41:05 +00:00
llm_response_utils refactor(typing): replace Any with proven types in 65 backend files 2026-09-02 09:11:36 +00:00
prompt_templates Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_async_remote_image_fetch 2026-09-05 00:37:19 -07:00
specialty_caches feat(newrelic): per-team cost and usage metrics via team callbacks (#37610) 2026-08-26 23:42:02 -07:00
tokenizers Code Quality Improvement - remove tokenizers/ from /llms (#7163) 2024-12-10 23:50:15 -08:00
agentic_loop_settings.py fix: keep accepting a loop ceiling that spells a whole number 2026-08-22 11:24:22 -07:00
api_route_to_call_types.py fix(guardrails): resolve generateContent routes and async-first passthrough call types 2026-08-29 21:35:19 -07:00
app_crypto.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
asyncify.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
aws_partition.py fix(aws): build every AWS endpoint and ARN from the region partition 2026-08-29 01:21:59 -07:00
cached_imports.py refactor(lint): apply every safe ruff autofix and zero 28 strict-rule budgets 2026-08-01 15:43:29 -07:00
chat_completion_agentic_loop.py refactor(agentic-loop): narrow logging_obj before building the fake stream wrapper 2026-08-27 23:19:17 +00:00
cli_keyring.py fix(cli): stop asking a keychain that already stopped answering 2026-08-20 04:12:23 -07:00
cli_token_utils.py fix(cli): keep the refresh token in the OS keychain, not in token.json 2026-08-20 11:43:53 -07:00
cloud_storage_security.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
completion_timeout.py chore(lint): strip inert type: ignore comments and zero LIT009, LIT010, LIT011 headroom 2026-08-05 02:37:24 -07:00
core_helpers.py refactor(typing): replace Any with proven types in 65 backend files 2026-09-02 09:11:36 +00:00
coroutine_checker.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
credential_accessor.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
custom_logger_registry.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
dd_tracing.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
default_encoding.py chore(lint): strip inert type: ignore comments and zero LIT009, LIT010, LIT011 headroom 2026-08-05 02:37:24 -07:00
dot_notation_indexing.py refactor(typing): replace Any with proven types in 89 more backend files 2026-09-02 23:08:42 +00:00
duration_parser.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
env_utils.py fix(token_counter): stop large token counts from blocking the proxy event loop (#37697) 2026-08-20 16:09:07 -07:00
exception_mapping_utils.py fix(exceptions): keep a refused connection an APIConnectionError 2026-08-27 21:00:24 -07:00
fallback_generalizations.py chore(lint): clear grandfathered over-limit lint drift and ratchet budgets down 2026-08-05 12:18:13 -07:00
fallback_utils.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
get_blog_posts.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
get_litellm_params.py refactor(rust): remove per-request enablement arguments (#39928) 2026-09-07 10:43:45 -07:00
get_llm_provider_logic.py fix(router): guard the declared-provider check for requests without a model 2026-09-01 14:06:14 -07:00
get_model_cost_map.py fix(responses): floor reasoning support on the bundled cost map and resolve fine-tuned ids 2026-09-05 16:24:36 -07:00
get_provider_specific_headers.py fix(proxy): stop forwarding a client Anthropic OAuth token to Bedrock and Vertex 2026-08-21 18:02:40 -07:00
get_supported_openai_params.py fix(router): drop a tier param the routed target cannot take (#38622) 2026-08-28 14:17:49 -07:00
health_check_helpers.py fix(ocr): send each provider a health-check document it accepts 2026-09-04 22:52:12 -07:00
health_check_utils.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
initialize_dynamic_callback_params.py feat(langfuse): support langfuse_environment as a per-key dynamic callback param (#38264) 2026-08-26 16:56:55 -07:00
internal_call_metadata.py fix(auto_router): bill the routing embedding to the caller's key and team (#39532) 2026-09-03 13:53:30 -07:00
json_fragment_accumulator.py perf(streaming): add shared JSONFragmentAccumulator for Vertex and Anthropic (#36610) 2026-08-25 16:15:47 -07:00
json_validation_rule.py refactor(typing): replace Any with proven types in 89 more backend files 2026-09-02 23:08:42 +00:00
litellm_logging.py fix: capture provider request id in failure logging payloads (#40045) 2026-09-07 11:12:34 -07:00
llm_judge.py fix(shadow_eval): refuse a judge model that also serves one of the arms it grades (#38589) 2026-08-27 18:44:44 -07:00
llm_request_utils.py fix(hosted_vllm): forward Omni media URLs instead of downloading them 2026-08-24 17:59:52 -04:00
logging_callback_manager.py chore(lint): strip inert type: ignore comments and zero LIT009, LIT010, LIT011 headroom 2026-08-05 02:37:24 -07:00
logging_utils.py perf(logging): scan large base64 payloads for log truncation off the event loop (#39890) 2026-09-05 11:51:15 -07:00
logging_worker.py fix(logging_worker): swallow cancellation in exit flush and revive dequeued tasks on loop change 2026-08-26 13:30:40 -07:00
mock_functions.py refactor(lint): apply every safe ruff autofix and zero 28 strict-rule budgets 2026-08-01 15:43:29 -07:00
model_param_helper.py merge litellm_internal_staging into litellm_anthropic_messages_response_cache 2026-08-11 20:48:41 +00:00
model_response_utils.py chore(techdebt): clear fresh debt from the 2026-08-29 window 2026-08-30 07:57:16 +00:00
private_json.py fix(cli): finish a refused token file rewrite in place 2026-08-20 02:58:53 -07:00
ptu_pricing.py fix(ptu): zero the Maps grounding rate on PTU deployments 2026-08-26 15:50:36 -07:00
README.md Guardrails API - add streaming support (#17400) 2025-12-02 22:52:09 -08:00
realtime_errors.py fix(realtime): relay the upstream websocket close to the client instead of hanging 2026-09-04 19:25:12 -07:00
realtime_streaming.py fix(realtime): settle the budget reservation only for sessions the success log does not own 2026-09-05 01:11:24 -07:00
reasoning_effort_utils.py fix(bedrock): normalize Messages system role and adaptive-thinking for Claude Invoke (#31364) 2026-06-27 11:35:36 -07:00
redact_messages.py chore(typing): clear fresh tech debt from the Aug 25 window 2026-08-26 07:55:16 +00:00
request_timeout_resolver.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
response_header_helpers.py fix(utils.py): guarantee openai-compatible headers always exist in response 2024-09-28 21:08:15 -07:00
rules.py chore(lint): strip inert type: ignore comments and zero LIT009, LIT010, LIT011 headroom 2026-08-05 02:37:24 -07:00
safe_json_dumps.py refactor(typing): replace Any with proven types in 89 more backend files 2026-09-02 23:08:42 +00:00
safe_json_loads.py refactor(lint): apply every safe ruff autofix and zero 28 strict-rule budgets 2026-08-01 15:43:29 -07:00
secret_redaction.py fix(utils): redact credential kwargs from the set_verbose request line 2026-09-03 01:55:56 -07:00
sensitive_data_masker.py Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_/mongodb-vector-store-e4ff63 2026-09-04 14:00:10 -07:00
service_tier_utils.py feat(lint): enforce Final on locals and freeze function parameters (LIT010, LIT011) 2026-08-04 12:54:39 -07:00
streaming_chunk_builder_utils.py Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_stream_usage_cost_default 2026-09-01 13:03:18 -07:00
streaming_handler.py Merge pull request #38808 from BerriAI/litellm_headroom_ccr_streaming_responses 2026-09-03 13:13:18 -07:00
thread_pool_executor.py fix(logging): bound the shared logging executor backlog (#37694) 2026-08-20 16:04:43 -07:00
token_counter.py Merge branch 'litellm_internal_staging' of https://github.com/BerriAI/litellm into litellm_decrease_anys_opus5_r2 2026-08-31 15:05:34 -07:00
url_utils.py fix(image_handling): answer every SSRF rejection with one message so error text cannot probe internal hostnames 2026-09-05 00:16:14 -07:00

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])