scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-07 02:59:05 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 103
31292 commits 3222 branches 1436 tags 4.7 GiB
Commit graph

31292 commits

This branch
This branch
All branches
Author SHA1 Message Date
yuneng-jiang
cccda30a9e
Merge pull request #19960 from BerriAI/litellm_ui_spend_logs_error_message 
[Feature] Add error_message Search in Spend Logs Endpoint
 2026-01-28 16:04:29 -08:00
yuneng-jiang
0cdfa8e5fa Adding Error message search to ui spend logs 2026-01-28 15:39:32 -08:00
yuneng-jiang
cb8ead6013 Add error_message search in spend logs endpoint 2026-01-28 15:06:31 -08:00
Ishaan Jaff
3ef475b70e
[Fix] A2a Gateway - Allow supporting old A2a card formats (#19949) 
* fix: LiteLLMA2ACardResolver

* fix: LiteLLMA2ACardResolver

* feat: .well-known/agent.json

* test_card_resolver_fallback_from_new_to_old_path
 2026-01-28 15:02:08 -08:00
yuneng-jiang
054918e7a3
Merge pull request #19918 from BerriAI/litellm_ui_spend_logs_store 
[Feature] UI - Spend Logs: Settings Modal
 2026-01-28 15:00:31 -08:00
Ishaan Jaffer
5135efb60e fix pypdf: >=6.6.2 2026-01-28 14:54:58 -08:00
yuneng-jiang
dbd1ff306d Fixing build 2026-01-28 13:42:58 -08:00
yuneng-jiang
077cfa8c15 Adding test 2026-01-28 13:36:19 -08:00
yuneng-jiang
8a54fff5cf Merge remote-tracking branch 'origin' into litellm_key_alias_spend_usage_report 2026-01-28 13:30:49 -08:00
yuneng-jiang
905e9cd6c9 breakdown by team and keys 2026-01-28 13:30:27 -08:00
Ishaan Jaffer
e444199d95 UI: New build 2026-01-28 12:05:36 -08:00
Alexsander Hamir
4c1b24eed9
Fix thread leak in OpenTelemetry dynamic header path (#19946) 2026-01-28 10:35:37 -08:00
michelligabriele
ea3853e977
fix(vertex_ai): support model names with slashes in passthrough URLs (#19944) 
The regex in get_vertex_model_id_from_url() was using [^/:]+
which stopped at the first slash, truncating model names like
'gcp/google/gemini-2.5-flash' to just 'gcp'. This caused
access_groups checks to fail for custom model names.

Changed the pattern to [^:]+ to allow slashes in model names,
only stopping at the colon before the action (e.g., :generateContent).
 2026-01-28 09:33:53 -08:00
boarder7395
8e4f06583a
Fix team cli auth flow (#19666) 
* Cleanup code for user cli auth, and make sure not to prompt user for team multiple times while polling

* Adding tests

* Cleanup normalize teams some more
 2026-01-28 08:52:52 -08:00
Sameer Kankute
3ab1b9f543 Fix gemini-robotics-er-1.5-preview name 2026-01-28 21:13:37 +05:30
Sameer Kankute
1cdda28b6c Fix gemini-robotics-er-1.5-preview name 2026-01-28 21:10:44 +05:30
Sameer Kankute
169c9dae79
Merge pull request #19914 from BerriAI/litellm_responses_api_bridge_usage 
Fix: output_tokens_details.reasoning_tokens None
 2026-01-28 18:35:30 +05:30
Sameer Kankute
9fe8b12f44
Merge pull request #19924 from BerriAI/litellm_minimax_reasoning_caching_1 
Add Prompt caching and reasoning support for MiniMax, GLM, Xiaomi
 2026-01-28 18:04:13 +05:30
Sameer Kankute
b6c769880e
Merge pull request #19842 from BerriAI/litellm_fix_timeout_test_fix 
Fixes Timeouts during chat completion calls no longer reported as timeout in failure callback
 2026-01-28 18:03:21 +05:30
Sameer Kankute
f5e5569e40
Merge pull request #19636 from BerriAI/litellm_langfuse_callback 
Add litellm_callback_logging_failures_metric for Langfuse, Langfuse Otel and other Otel providers
 2026-01-28 18:02:17 +05:30
Sameer Kankute
c5c1fbc5a2 Fix test_calculate_usage_completion_tokens_details_always_populated and logging object test 2026-01-28 18:00:42 +05:30
Sameer Kankute
0fadcbb21f
Merge pull request #19915 from BerriAI/litellm_x_ai_responses_web 
Add xai websearch params support fo Responses API
 2026-01-28 17:34:28 +05:30
Sameer Kankute
7386621d04
Merge pull request #19839 from BerriAI/litellm_oss_staging_01_27_2026 
Litellm oss staging 01 27 2026
 2026-01-28 17:33:27 +05:30
Sameer Kankute
f6ead49afe Add Prompt caching and reasoning support for MiniMax, GLM, Xiaomi 2026-01-28 17:25:26 +05:30
Sameer Kankute
4f7425df0c
Merge pull request #19661 from Chesars/fix/oci-image-url-format 
fix(oci): serialize imageUrl as object for OCI GenAI API
 2026-01-28 15:26:50 +05:30
Sameer Kankute
f58305b747
Merge pull request #19882 from milan-berri/fix/tiktoken-offline-import-order 
initialize tiktoken environment at import time to support offline usage
 2026-01-28 15:13:47 +05:30
Sameer Kankute
156751e8fc
Merge pull request #19919 from lizhen921/fix/anthropic-cache-control-null-issue 
fix(anthropic): remove explicit cache_control null in tool_result content
 2026-01-28 13:24:56 +05:30
yuneng-jiang
07c8618227 Fixing tests 2026-01-27 23:47:47 -08:00
lizhen
e4cb28aa07 fix(anthropic): remove explicit cache_control null in tool_result content 
Fixes issue where tool_result content blocks include explicit
'cache_control': null which breaks some Anthropic API channels.

Changes:
- Only include cache_control field when explicitly set and not None
- Prevents serialization of null values in tool_result text content
- Maintains backward compatibility with existing cache_control usage

Related issue: Anthropic tool_result conversion adds explicit null values
that cause compatibility issues with certain API implementations.

Co-Authored-By: Claude (claude-4.5-sonnet) <noreply@anthropic.com>
 2026-01-28 15:39:01 +08:00
yuneng-jiang
c4d3750601 adding tests 2026-01-27 23:38:23 -08:00
yuneng-jiang
58eca8fb28 Spend logs setting modal 2026-01-27 23:34:50 -08:00
Sameer Kankute
9b44984510
Merge pull request #19899 from xianzongxie-stripe/add_native_background_mode_override 
Add native_background_mode to override polling_via_cache for specific models
 2026-01-28 12:27:19 +05:30
Sameer Kankute
bd15ebba84 fix: Pydantic will fail to parse it because cached_tokens is required but not provided 2026-01-28 11:51:26 +05:30
yuneng-jiang
ab655ef296
Merge pull request #19913 from BerriAI/litellm_store_prompt_backend 
[Feature] Allow Dynamic Setting of store_prompts_in_spend_logs
 2026-01-27 22:07:57 -08:00
Sameer Kankute
6fb2a0d11f Fix: output_tokens_details.reasoning_tokens None 2026-01-28 11:35:18 +05:30
yuneng-jiang
28ca991296 Allow dynamic setting of store_prompts_in_spend_logs 2026-01-27 20:52:07 -08:00
Sameer Kankute
d76fb5932a Add xai websearch params support 2026-01-28 09:54:43 +05:30
Ishaan Jaff
3080e04180
[Feat] UI: Allow Admins to control what pages are visible on LeftNav (#19907) 
* feat: enabled_ui_pages_internal_users

* init ui for internal user controsl

* fix ui settings

* fix build

* fix leftnav

* fix leftnav

* test fixes

* fix leftnav

* isPageAccessibleToInternalUsers

* docs fix

* docs ui viz
 2026-01-27 19:31:24 -08:00
Sameer Kankute
74b308bc2d
Merge pull request #19911 from BerriAI/litellm_merge_timeout_issue 
merge main in timeout
 2026-01-28 08:56:49 +05:30
Sameer Kankute
5276085f3c
Merge branch 'litellm_fix_timeout_test_fix' into litellm_merge_timeout_issue 2026-01-28 08:56:29 +05:30
mubashir1osmani
9a245031bd
feat(hosted_vllm): support thinking parameter in anthropic_messages() and .completion() 
feat(hosted_vllm): support `thinking` parameter in `anthropic_messages()` and `.completion()`
 2026-01-27 22:13:53 -05:00
yuneng-jiang
b76286e11c
Merge pull request #19908 from BerriAI/litellm_ui_model_table_server_sort 
[Feature] UI - Model Page: Server Sort
 2026-01-27 19:02:54 -08:00
Sameer Kankute
42a0d576f3
Merge pull request #19910 from BerriAI/main 
merge 01 27
 2026-01-28 08:30:47 +05:30
Cesar Garcia
64c102e3c2
fix(gemini): subtract implicit cached tokens from text_tokens for correct cost calculation (#19775) 
When Gemini uses implicit caching, it returns cachedContentTokenCount but
NOT cacheTokensDetails. Previously, text_tokens was not adjusted in this case,
causing costs to be calculated as if all tokens were non-cached.

This fix subtracts cachedContentTokenCount from text_tokens when no
cacheTokensDetails is present (implicit caching), ensuring correct cost
calculation with the reduced cache_read pricing.
 2026-01-27 18:18:47 -08:00
Cesar Garcia
807ba011eb
fix(main): use local tiktoken cache in lazy loading (#19774) 
The lazy loading implementation for encoding in __getattr__ was calling
tiktoken.get_encoding() directly without first setting TIKTOKEN_CACHE_DIR.
This caused tiktoken to attempt downloading the encoding file from the
internet instead of using the local copy bundled with litellm.

This fix uses _get_default_encoding() from _lazy_imports which properly
sets TIKTOKEN_CACHE_DIR before loading tiktoken, ensuring the local cache
is used.
 2026-01-27 18:16:58 -08:00
Brian Caswell
920ef665a3
inspect BadRequestError after all other policy types (#19878) 
As indicated by https://docs.litellm.ai/docs/exception_mapping,
BadRequestError is used as the base type for multiple exceptions.  As
such, it should be tested last in handling retry policies.

This updates the integration test that validates retry policies work as
expected.

Fixes #19876
 2026-01-27 18:15:04 -08:00
yuneng-jiang
29c841d7f9 Fixing build and tests 2026-01-27 18:14:30 -08:00
Ryan Wilson
70eb732b41
docs: fix guardrail logging docs (#19833) 2026-01-27 18:13:04 -08:00
Pragya Sardana
b4a27712a1
Add Init Containers in the community helm chart (#19816) 2026-01-27 18:10:47 -08:00
yuneng-jiang
37bfab929d All Models Page server side sorting 2026-01-27 18:08:17 -08:00