scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-09 22:31:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 133
litellm/litellm
History
Tin Chi Lo 8ca809d426 fix(mcp): scope semantic filter matching and indexing errors to the requesting call 
Match candidates are restricted to the request's own tool names via
route_filter, so routes learned from other principals' listings cannot
displace the caller's tools from top_k. Lazy indexing now uses the
async aadd flow exclusively; an embedding failure, including a
context-window overflow on an oversized description, raises for the
requesting call only and never writes the shared context_window_error,
so one request cannot poison the filter for every user on the worker.
The router is also sized to the configured top_k, which the
semantic-router index layer otherwise silently caps at its default
of 5.
2026-07-14 19:34:17 -07:00
..
a2a_protocol fix(responses): stop scheduling sync success_handler concurrently with async_success_handler (#32239) 2026-07-07 09:13:50 -07:00
anthropic_interface style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
assistants style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
batch_completion style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
batches feat(batches): track cost for unmanaged Bedrock batches, generalize the flag (#32315) 2026-07-13 10:33:13 +05:30
caching fix(caching): pass only metadata to valkey semantic async embedding (#32295) 2026-07-07 08:52:03 +03:00
completion_extras style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
compression style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
containers style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
endpoints/speech/speech_to_completion_bridge style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
evals style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
experimental_mcp_client feat(mcp): relay upstream 401 on client-forwarded pass-through tool calls 2026-07-10 10:09:31 -07:00
files style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
fine_tuning chore(lint): zero out crash-class pyright rules and ban new type: ignore comments (#32152) 2026-07-04 16:56:12 -07:00
google_genai style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
images style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
integrations fix(s3): sanitize slashes in response-id-derived object key file name (#33271) 2026-07-14 17:26:00 -07:00
interactions fix(responses): stop scheduling sync success_handler concurrently with async_success_handler (#32239) 2026-07-07 09:13:50 -07:00
litellm_core_utils feat(pricing): add gemini-omni-flash-preview with video output token pricing 2026-07-14 14:04:51 -07:00
llms feat(guardrails): streaming text transformation in generic_guardrail_api (#33110) 2026-07-14 17:38:11 -07:00
models fix(keys): persist key_type so the UI shows correct key scope instead of "All Proxy Models" (#33115) 2026-07-13 18:08:43 -07:00
ocr test: litellm fix failing tests (#32577) 2026-07-09 13:54:45 -07:00
passthrough fix(logging): classify allm_passthrough_route as async to prevent duplicate success callbacks (#32265) 2026-07-06 15:04:05 -07:00
proxy fix(mcp): scope semantic filter matching and indexing errors to the requesting call 2026-07-14 19:34:17 -07:00
proxy_auth style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
rag style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
realtime_api fix(vertex): forward realtime health check params (#32550) 2026-07-08 17:30:46 -07:00
repositories fix(proxy): count only active users toward license seat limit (#31227) 2026-06-29 18:01:02 -07:00
rerank_api fix(rerank): log optional_rerank_params at debug to stop leaking request content (#32533) 2026-07-08 18:48:03 -07:00
responses fix(responses): continue MCP gateway tool turns from the final response and surface failures 2026-07-13 11:33:02 +10:00
router_strategy feat(router): opt-in session affinity for complexity router (#33126) 2026-07-13 18:28:13 -07:00
router_utils feat(router): add separate ITPM/OTPM deployment rate limits (#31952) 2026-07-05 21:58:35 +05:30
rust_bridge feat(ocr): thin Rust OCR Python bridge (#31368) 2026-06-25 18:42:59 -07:00
sandbox style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
search style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
secret_managers fix(proxy): harden secret name validation for external secret manager integrations (LIT-4201) (#32092) 2026-07-08 10:36:00 -07:00
skills style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
types feat(guardrails): streaming text transformation in generic_guardrail_api (#33110) 2026-07-14 17:38:11 -07:00
vector_store_files style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
vector_stores style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
videos style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
__init__.py feat(budget): throttle keys after spend limit instead of revoking access (#31300) 2026-07-07 09:41:01 -07:00
_internal_context.py fix(proxy): harden request parameter handling 2026-04-16 01:38:12 +00:00
_lazy_imports.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
_lazy_imports_registry.py feat(tencent): add Tencent TokenHub as a provider (#31903) 2026-07-02 18:31:59 -07:00
_logging.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
_redis.py fix(redis): only use SSLConnection when ssl is truthy in connection pool kwargs (#32825) 2026-07-10 17:16:10 -07:00
_redis_credential_provider.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
_service_logger.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
_uuid.py build(deps-dev): bump black to 26.3.1 and apply formatting (#28525) 2026-05-21 17:24:18 -07:00
_version.py
anthropic_beta_headers_config.json fix(bedrock-invoke): retain clear_tool_uses_20250919 context_management edits and emit context-management-2025-06-27 beta (LIT-3393) (#32658) 2026-07-09 14:31:27 -07:00
anthropic_beta_headers_manager.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
blog_posts.json docs(blog): add WebRTC blog post link 2026-03-13 17:54:33 +05:30
budget_manager.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
constants.py feat: add Meta Model API provider and muse-spark-1.1 (day-0) (#32701) 2026-07-09 20:45:27 -07:00
cost.json
cost_calculator.py fix(proxy): bill tier-only deployments instead of $0 2026-07-11 13:47:56 -07:00
exceptions.py fix(guardrails/bedrock): honor disable_exception_on_block by raising ModifyResponseException (#32289) 2026-07-09 13:18:51 -07:00
main.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
model_prices_and_context_window_backup.json Merge pull request #33274 from BerriAI/litellm_gemini_omni_flash_preview_pricing 2026-07-14 16:58:04 -07:00
policy_templates_backup.json feat(add-new-block_code_execution-guardrail): prevent agent from executing code (#22154) 2026-02-25 22:02:14 -08:00
provider_endpoints_support_backup.json chore: litellm oss staging (#30968) 2026-06-23 07:31:44 -07:00
py.typed
router.py fix(auto-router): correct Responses API tool_choice shape and propagate alias litellm_params (#32974) 2026-07-13 15:11:48 -07:00
scheduler.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
setup_wizard.py feat(anthropic): add Claude Sonnet 5 2026-06-30 18:47:08 +00:00
timeout.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
utils.py feat(pricing): add gemini-omni-flash-preview with video output token pricing 2026-07-14 14:04:51 -07:00