Commit Graph
25087 Commits
Author SHA1 Message Date
Krrish Dholakia d96e397de5 fix(_health_endpoints.py): protect /health/test_connection - only allow users who are allowed to create models, to call this endpoint
Closes LIT-989
2025-09-17 15:28:35 -07:00
Krrish Dholakia 530662d735 test: add unit testing 2025-09-17 14:54:44 -07:00
Krrish Dholakia 1ada663959 fix(bedrock_guardrails.py): respect bedrock runtime endpoint when using guardrails
Closes LIT-983
2025-09-17 14:41:40 -07:00
Ishaan JaffandGitHub 06f3991ed0 bump aiohttp==3.12.14 (#14638) 2025-09-17 09:44:39 -07:00
Carlos MarchalandGitHub e168161e64 Feat/add posthog observability (#14610)
* feat: add posthog observability

* docs: add posthog logging docs

* docs: posthog integration in proxy mode
2025-09-17 08:24:04 -07:00
Krish DholakiaandGitHub a74fda1159 Merge pull request #14625 from timelfrink/fix/mdx-compilation-error-compactifai
Fix: MDX compilation error in CompactifAI documentation
2025-09-16 23:06:50 -07:00
Krish DholakiaandGitHub bf0dd4a284 Merge pull request #14418 from iabhi4/deep-copy-issue
fix: avoid deepcopy crash with non-pickleables in Gemini/Vertex
2025-09-16 22:55:31 -07:00
Tim Elfrink 79d1992de0 Fix: MDX compilation error in CompactifAI documentation
- Replace (<5%) with (under 5%) in two locations to fix JSX parsing
- Resolves webpack build failure in Docusaurus documentation
- Maintains same meaning while avoiding MDX syntax conflicts

Fixes #14624
2025-09-17 07:50:38 +02:00
Krish DholakiaandGitHub ef14270dec Merge pull request #14448 from vvidovic/propagate_metadata_to_vertexai_labels_docs
Describing the `labels` field use in the Vertex AI
2025-09-16 22:46:28 -07:00
Krish DholakiaandGitHub 2563c0ab2d Merge pull request #14534 from hula-la/fix/response-api-bugfixes
fix: improve response api handling and cold storage configuration
2025-09-16 22:46:03 -07:00
Krish DholakiaandGitHub fcf84027e8 Merge pull request #14555 from mubashir1osmani/dd_spend_metric
DataDog shows spend metrics
2025-09-16 22:44:47 -07:00
Krish DholakiaandGitHub 635dc72211 Merge pull request #14604 from Sameerlite/litellm_gemini_api_base_update
Litellm gemini api base update
2025-09-16 22:38:44 -07:00
Krish DholakiaandGitHub 701b4fffee Merge pull request #14600 from mubashir1osmani/fix_all_docs
docs: helicone integration and mcp
2025-09-16 22:37:38 -07:00
Krish DholakiaandGitHub 92c82a682e Merge pull request #14613 from ronaldpereira/patch-1
Fix error message for missing OCI parameters
2025-09-16 22:36:00 -07:00
Krish DholakiaandGitHub 6bccdcd530 Merge pull request #14620 from BerriAI/litellm_dev_09_16_2025_p2
(feat) Anthropic - document pricing for cache creation tokens above 1hr
2025-09-16 22:33:11 -07:00
Krish DholakiaandGitHub cd53f25427 Merge pull request #14622 from ARajan1084/guardrail-key-configuration-fix
Fix: 14473: Guardrail view, edit, and delete behavior
2025-09-16 22:32:12 -07:00
Mubashir OsmaniandGitHub 0fde408e35 added langfuse logging for responses api (#14597)
* added langfuse logging for responses api

* tests added
2025-09-16 21:43:19 -07:00
Oleksandr TereshchenkoandGitHub f507bf8881 Fix AttributeError: NoneType object has no attribute 'get' (#14609) 2025-09-16 21:38:01 -07:00
mubashir1osmani 439577fd35 fixed lint errors 2025-09-17 00:31:29 -04:00
mubashir1osmani e56b11cb54 added tests 2025-09-17 00:19:03 -04:00
mubashir1osmani fc7de7a1c5 added user_api_key_spend 2025-09-17 00:10:02 -04:00
= 626c48b783 removed problematic tooltips; used generic GuardrailSelector component 2025-09-16 19:42:53 -07:00
Ishaan JaffandGitHub 93524cf19b [Feat] Batches - Add bedrock retrieve endpoint support (#14618)
* feat: add bedrock retrieve endpoint

* feat: feat: add bedrock retrieve endpoint

* test: batches mocked transform

* ruff fix

* refactor

* fix transform

* fix: parse_timestamp
2025-09-16 19:19:02 -07:00
Krrish Dholakia 22d3e492f9 fix(test_utils.py): fix test 2025-09-16 19:17:44 -07:00
Krrish Dholakia c1a33dcc5f fix(types/utils.py): add cache_creation_input_token_cost_above_1hr to modelinfobase 2025-09-16 19:15:26 -07:00
Krrish Dholakia e735808614 test(test_utils.py): fix cache creation tokens 2025-09-16 19:03:16 -07:00
Krrish Dholakia 97cc5f55d6 build(model_prices_and_context_window.json): add claude-3-5 haiku, claude-3-5 sonnet, claude-opus 3, claude-haiku 3 "cache_creation_input_token_cost_above_1hr" pricing 2025-09-16 18:58:49 -07:00
Krrish Dholakia 3188ae9281 build(model_prices_and_context_window.json): add claude-opus-4, claude-3-7-sonnet, claude-sonnet-4 "cache_creation_input_token_cost_above_1hr" pricing 2025-09-16 18:56:24 -07:00
Krrish Dholakia a2bfd3e476 build(model_prices_and_context_window.json): add claude-opus-4-1 "cache_creation_input_token_cost_above_1hr" pricing 2025-09-16 18:53:56 -07:00
Krrish Dholakia 0fa11c3c25 build(model_prices_and_context_window.json): add "cache_creation_input_token_cost_above_1hr" to all claude-3-5-sonnet models 2025-09-16 18:52:37 -07:00
Krrish Dholakia 1c855385c9 build(model_cost): add cache_creation_input_token_cost_above_1hr pricing 2025-09-16 18:43:57 -07:00
Sameer KankuteandGitHub ab1fb2b2e7 Add Support for Bedrock Guardrails to supportive selective Guarding (#14575)
* Add Support for Bedrock Guardrails to supportive selective Guarding

* Add method for better handling

* Add guarded_text content type

* Add guarded_text content type

* Update Dockerfile

* Update Dockerfile
2025-09-16 16:43:34 -07:00
Ishaan Jaffer 7de8811c4c test 2025-09-16 16:33:10 -07:00
Alexsander HamirandGitHub 02db2e8ae8 [Performance] RPS Improvement +500 RPS when sending the user field (#14616)
* perf tool

* fix: cache type issue

* fix: exception hanging & cache setting

1. Removed unhandled exceptions
2. Set cache value to dict
2025-09-16 16:18:23 -07:00
Ishaan Jaffer 68105ce1a7 fix type 2025-09-16 15:41:52 -07:00
Ronald PereiraandGitHub 0f5ab261df Fix error message for missing OCI parameters 2025-09-16 16:37:22 -03:00
Sameerlite 5b896d2757 make model param optional 2025-09-16 15:47:23 +05:30
Sameerlite 573230348d fix lint error 2025-09-16 15:21:48 +05:30
Sameerlite f08fc45a0f add base url support for gemini 2025-09-16 15:15:24 +05:30
mubashir1osmani a2d5bde837 changed docs 2025-09-16 00:58:08 -04:00
Krish DholakiaandGitHub f34bbd1f35 Merge pull request #14569 from talesofai/volcengine-fix-thinking-parameters-missing-if-not-set
fix volcengine thinking parameters missing when it set disable
2025-09-15 21:33:31 -07:00
Krish DholakiaandGitHub 3f90fe938d Merge pull request #14514 from iabhi4/fix-13581
feat(proxy): Assign default budget to auto-generated JWT teams
2025-09-15 21:22:25 -07:00
Krish DholakiaandGitHub f4e2870490 Merge pull request #14532 from timelfrink/feat/issue-14476-compactifai-provider
Add CompactifAI provider support
2025-09-15 21:15:00 -07:00
mubashir1osmani f5f00043ce fixed tests 2025-09-16 00:14:48 -04:00
Krish DholakiaandGitHub e368a0895f Merge pull request #14542 from uc4w6c/fix/mcp-server-delete-refresh
fix: recompute filters after deleting an MCP Server
2025-09-15 21:12:55 -07:00
LingXuanYin f8c9009fe5 add more test 2025-09-16 12:11:10 +08:00
Krish DholakiaandGitHub 784eb18366 Merge pull request #14558 from iabhi4/fix-14536
fix(proxy): Correctly parse multi-part MCP server aliases from URL paths
2025-09-15 21:05:22 -07:00
Krish DholakiaandGitHub 9d2cce43ba Merge pull request #14583 from pazevedo-hyland/fix/bedrock_convert_layer
Fix: handle empty arguments in Bedrock tool call invocation
2025-09-15 20:57:45 -07:00
Ishaan JaffandGitHub 8e22cf5d65 [Fix] /responses API - add cancel endpoint + allow non-admins to use this as an llm api endpoint (#14594)
* fix: ensure /responses/cancel works for non admins

* test: cancel endpoint

* fix responses API  cancel endpoint

* test fix

* TestGoogleAIStudioResponsesAPITest
2025-09-15 18:49:54 -07:00
Krish DholakiaandGitHub e1a6b9f858 Merge pull request #14582 from timelfrink/fix/issue-14573-aws-external-id-support
Add AWS external ID parameter support for Bedrock authentication
2025-09-15 17:32:00 -07:00