| .. |
|
audio_utils
|
feat(vertex_ai): add Google Cloud Speech-to-Text Chirp 3 transcription support (#32274)
|
2026-07-06 18:25:22 -07:00 |
|
llm_cost_calc
|
feat(pricing): add gemini-omni-flash-preview with video output token pricing
|
2026-07-14 14:04:51 -07:00 |
|
llm_response_utils
|
chore(lint): zero out crash-class pyright rules and ban new type: ignore comments (#32152)
|
2026-07-04 16:56:12 -07:00 |
|
prompt_templates
|
feat(router): add Router(plugins=[...]) routing-plugin pipeline (#32972)
|
2026-07-11 21:38:18 -07:00 |
|
specialty_caches
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
tokenizers
|
Code Quality Improvement - remove tokenizers/ from /llms (#7163)
|
2024-12-10 23:50:15 -08:00 |
|
api_route_to_call_types.py
|
Agent Guardrails - on streaming output (#21206)
|
2026-02-14 11:36:52 -08:00 |
|
app_crypto.py
|
style: run black formatter on entire codebase
|
2026-03-11 17:07:57 -03:00 |
|
asyncify.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
cached_imports.py
|
style: run black formatter on entire codebase
|
2026-03-11 17:07:57 -03:00 |
|
chat_completion_agentic_loop.py
|
fix(websearch): websearch_interception agentic loop fixes for chat completions and anthropic messages (#31669)
|
2026-07-01 09:36:40 +08:00 |
|
cli_token_utils.py
|
feat: add lite auth print-token for Claude Code apiKeyHelper support (#32846)
|
2026-07-11 13:31:41 -07:00 |
|
cloud_storage_security.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
completion_timeout.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
core_helpers.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
coroutine_checker.py
|
style: run black formatter on entire codebase
|
2026-03-11 17:07:57 -03:00 |
|
credential_accessor.py
|
fix(router.py): support reusable credentials via passthrough router (#9758)
|
2025-04-04 18:40:14 -07:00 |
|
custom_logger_registry.py
|
feat: litellm oss 110626 (#30202)
|
2026-06-11 22:30:26 -07:00 |
|
dd_tracing.py
|
_add_dd_apm_tags_for_litellm_call_id (#22219)
|
2026-02-26 16:42:23 -08:00 |
|
default_encoding.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
dot_notation_indexing.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
duration_parser.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
env_utils.py
|
fix(callbacks): allow MAX_CALLBACKS override via env var (#20781)
|
2026-02-09 12:11:32 -08:00 |
|
exception_mapping_utils.py
|
fix(mcp): fail closed and surface semantic filter context window errors
|
2026-07-10 00:41:54 -07:00 |
|
fallback_generalizations.py
|
fix(fallback-generalizations): tolerate legacy remote rule schema and keep register_model cache-pricing inheritance
|
2026-07-11 00:27:45 -07:00 |
|
fallback_utils.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
get_blog_posts.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
get_litellm_params.py
|
fix(completion): forward aws credential kwargs into litellm_params so the responses bridge keeps WIF auth
|
2026-07-11 16:10:39 -07:00 |
|
get_llm_provider_logic.py
|
refactor(fallback-generalizations): split rules into routing and provider-neutral capability kinds
|
2026-07-11 00:27:45 -07:00 |
|
get_model_cost_map.py
|
feat: declarative fallback generalizations for unknown models (#29718)
|
2026-06-27 21:01:19 -07:00 |
|
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
|
feat(tencent): add Tencent TokenHub as a provider (#31903)
|
2026-07-02 18:31:59 -07:00 |
|
health_check_helpers.py
|
fix(vertex): forward realtime health check params (#32550)
|
2026-07-08 17:30:46 -07:00 |
|
health_check_utils.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
initialize_dynamic_callback_params.py
|
fix(proxy): restore admin key/team callback_vars.turn_off_message_logging override (LIT-3587) (#31905)
|
2026-07-02 15:01:58 -07:00 |
|
json_validation_rule.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
litellm_logging.py
|
feat(prometheus): expose video duration and image count consumption metrics (#33138)
|
2026-07-13 18:51:13 -07:00 |
|
llm_request_utils.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
logging_callback_manager.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
logging_utils.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
logging_worker.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
mock_functions.py
|
Support returning virtual key in custom auth + Handle provider-specific optional params for embedding calls (#11346)
|
2025-06-03 07:24:13 -07:00 |
|
model_param_helper.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
model_response_utils.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
README.md
|
Guardrails API - add streaming support (#17400)
|
2025-12-02 22:52:09 -08:00 |
|
realtime_streaming.py
|
fix(responses): stop scheduling sync success_handler concurrently with async_success_handler (#32239)
|
2026-07-07 09:13:50 -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
|
fix: redact async complete streaming response for custom callbacks (#33106)
|
2026-07-13 13:35:14 -07:00 |
|
request_timeout_resolver.py
|
fix(router): honor litellm_settings.request_timeout as an independent per-attempt timeout (#31119)
|
2026-06-23 14:22:54 -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
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
|
safe_json_dumps.py
|
perf(spend-logs): only strip NUL bytes in safe_dumps when present (#31424)
|
2026-06-26 09:37:19 -07:00 |
|
safe_json_loads.py
|
style: run black formatter on files from main merge
|
2026-04-17 13:02:59 -07:00 |
|
secret_redaction.py
|
Litellm oss staging (#29492)
|
2026-06-02 08:48:10 -07:00 |
|
sensitive_data_masker.py
|
fix(guardrails): mask credentials embedded in guardrail_response before persist (LIT-4314) (#32687)
|
2026-07-09 20:26:22 -07:00 |
|
streaming_chunk_builder_utils.py
|
fix(anthropic): bill streaming 1h prompt-cache writes at the 1h rate (#32073)
|
2026-07-03 17:34:16 -07:00 |
|
streaming_handler.py
|
chore(lint): zero out crash-class pyright rules and ban new type: ignore comments (#32152)
|
2026-07-04 16:56:12 -07:00 |
|
thread_pool_executor.py
|
(Fixes) OpenAI Streaming Token Counting + Fixes usage track when litellm.turn_off_message_logging=True (#8156)
|
2025-01-31 15:06:37 -08:00 |
|
token_counter.py
|
fix(token_counter): count legacy function_call.arguments (VERIA-492) (#31741)
|
2026-06-30 14:23:09 -07:00 |
|
url_utils.py
|
style: unify ruff format width on 120 (#31518)
|
2026-06-27 12:39:29 -07:00 |
