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
46359 commits 3222 branches 1436 tags 4.7 GiB
Commit graph

14525 commits

Author SHA1 Message Date
yuneng-jiang
bd4a893daf fixing tests 2026-01-16 12:42:35 -08:00
Dushyant
2a0f87bde0
Fix audio cost per second override (#19158) 2026-01-17 01:00:16 +05:30
Anand Kamble
2c75194b49
fix(vertex_ai): Vertex AI 400 Error: Model used by GenerateContent request (models/gemini-3-*) and CachedContent (models/gemini-3-*) has to be the same (#19193) 
* fix(vertex_ai): include model in context cache key generation

* test(vertex_ai): update context caching tests to verify model in cache key
 2026-01-17 00:56:15 +05:30
yuneng-jiang
33ff58b70a Merge remote-tracking branch 'origin' into litellm_deleted_keys_team 2026-01-16 09:55:52 -08:00
yuneng-jiang
e3d1e0345c only show own internal user usage 2026-01-16 09:38:34 -08:00
Sameer Kankute
6fecfe4911
Merge pull request #19198 from BerriAI/litellm_handle_malformed_tool_bedrock 
Fix: malformed tool call transformation in bedrock
 2026-01-16 18:05:10 +05:30
Sameer Kankute
9388dd842a
Merge pull request #19159 from BerriAI/litellm_staging_01_15_2026 
Litellm staging 01 15 2026
 2026-01-16 18:04:25 +05:30
Sameer Kankute
fb3b4e6b33
Merge pull request #19196 from BerriAI/litellm_sanitise_anthropic_mesages 
Add sanititzation for anthropic messages
 2026-01-16 17:48:55 +05:30
Sameer Kankute
4ad695e6f0
Merge pull request #19140 from BerriAI/litellm_bedrock_passthroguh_user_logging 
Add user auth in standard logging object for bedrock passthrough
 2026-01-16 17:47:55 +05:30
Sameer Kankute
43893cb81a
Merge pull request #19191 from BerriAI/litellm_fix_stream_timeout 
Fix: [Bug]: stream_timeout：The function of this parameter has been changed
 2026-01-16 17:43:43 +05:30
Sameer Kankute
cca6632dae
Merge pull request #19185 from BerriAI/litellm_fallback_endpoints_support 
[Feat] Add fallback endpoints support
 2026-01-16 17:39:35 +05:30
Sameer Kankute
ca06bb4e3a
Merge pull request #19201 from BerriAI/litellm_fix_vertex_ai_structured_output2 
Fix: vertex ai doesn't support structured output
 2026-01-16 17:09:03 +05:30
Sameer Kankute
e315f6bed2
Merge pull request #19214 from BerriAI/main 
merge main in malformed tool call PR
 2026-01-16 17:04:44 +05:30
Sameer Kankute
101230e538
Merge pull request #19213 from BerriAI/main 
merge main in sanitisation
 2026-01-16 17:04:01 +05:30
Sameer Kankute
f562186c75
Merge pull request #19212 from BerriAI/main 
merge main in timeout PR
 2026-01-16 17:02:22 +05:30
Sameer Kankute
e54af42774
Merge pull request #19211 from BerriAI/main 
merge main in fallback PR
 2026-01-16 17:01:10 +05:30
Sameer Kankute
b6aa05df16
Merge pull request #19210 from BerriAI/main 
merge main in bedrock passthrough
 2026-01-16 17:00:11 +05:30
Sameer Kankute
84974d5745 Fix boto3 conflicting dependency 2026-01-16 16:55:12 +05:30
Sameer Kankute
09fb1581cb Fix:add async_get_available_deployment_for_pass_through in code tests 2026-01-16 16:37:44 +05:30
Sameer Kankute
f3ca05112e
Merge pull request #19206 from BerriAI/main 
merge main
 2026-01-16 15:22:16 +05:30
Sameer Kankute
dcd66db4a8
Revert "fix: models loadbalancing billing issue by filter (#18891)" 
This reverts commit 41d8f79929.
 2026-01-16 15:21:10 +05:30
Sameer Kankute
b0c6a1b308
Merge pull request #19203 from BerriAI/main 
merge main
 2026-01-16 15:16:29 +05:30
Sameer Kankute
ac5a4df724 Fix: vertex ai doesn't support structured output 2026-01-16 14:54:31 +05:30
Sameer Kankute
bf99cea82f Fix malformed tool call tranform 2026-01-16 14:33:25 +05:30
Sameer Kankute
f1bde3c549 Add sanititzation for anthropic messages 2026-01-16 12:47:56 +05:30
Sameer Kankute
c0e5637eae Fix: [Bug]: stream_timeout：The function of this parameter has been changed 2026-01-16 11:40:49 +05:30
YutaSaito
45d38bea5b
Merge pull request #19188 from BerriAI/litellm_fix_ci_security_tests 
[chore] add jaraco liccheck
 2026-01-16 14:55:51 +09:00
Yuta Saito
9e1235c0aa chore: add jaraco liccheck 2026-01-16 14:55:14 +09:00
Sameer Kankute
9ac490de62
Merge pull request #19179 from BerriAI/litellm_fix_streaming_chunk 
Fix : test_stream_chunk_builder_litellm_mixed_calls
 2026-01-16 10:52:25 +05:30
Sameer Kankute
d585b760c9 Add fallback endpoints support 2026-01-16 10:51:33 +05:30
Sameer Kankute
aec1990dc2 Fix : test_streaming_multiple_partial_tool_calls 2026-01-16 09:29:54 +05:30
Yuta Saito
3a55f68ea4 test: handle wildcard routes in route validation test 2026-01-16 12:53:27 +09:00
YutaSaito
f123e08b16
Merge pull request #19178 from BerriAI/litellm_fix_ci_litellm_mapped_tests_llms 
[tests] skip Azure SDK init check for acreate_skill
 2026-01-16 12:17:55 +09:00
Yuta Saito
1c38847b17 tests: skip Azure SDK init check for acreate_skill 2026-01-16 12:03:38 +09:00
YutaSaito
3d80432675
Merge pull request #19175 from BerriAI/revert-19053-litellm_intern_user_usage 
Revert "[Fix] /team/daily/activity Show Internal Users Their Spend Only"
 2026-01-16 11:50:36 +09:00
John Greek
07b1f84ec6
fix(bedrock): strip throughput tier suffixes from model names (#19147) 
Co-authored-by: Greek, John <jgreek@users.noreply.github.com>
 2026-01-15 18:43:10 -08:00
YutaSaito
bbf9a9e6e6
Revert "[Fix] /team/daily/activity Show Internal Users Their Spend Only" 2026-01-16 11:27:59 +09:00
Ishaan Jaff
117c7dd158
[Feat] Claude Code - Add End-user tracking with Claude Code (#19171) 
* add claude code customer usage tracking

* fix get end user trackign claude code

* TestGetCustomerIdFromStandardHeaders
 2026-01-15 17:57:10 -08:00
YutaSaito
9de97b9724
Merge pull request #19170 from BerriAI/litellm_fix_ci_check_code_and_doc_quality 
Litellm fix ci check code and doc quality
 2026-01-16 10:41:51 +09:00
Yuta Saito
c03630d95e test: fix missing test 2026-01-16 10:33:53 +09:00
YutaSaito
05a1d15c65
Merge pull request #19168 from BerriAI/revert-19027-litellm_add_0_budget_model_bypass 
Revert "[Feat] Add support for 0 cost models"
 2026-01-16 10:21:51 +09:00
Yuta Saito
993742166d test: fix router_code_coverage test fail 2026-01-16 10:16:01 +09:00
Ishaan Jaff
362b1a1577
[Feat] Add support for Tool Search on /messages API - Azure, Bedrock, Anthropic API (#19165) 
* fix _update_headers_with_anthropic_beta

* init ANTHROPIC_BETA_HEADER_VALUES

* fix ANTHROPIC_BETA_HEADER_VALUES

* fix: _update_headers_with_anthropic_beta - anthropic API

* init _update_headers_with_anthropic_beta - azure AI support

* init VertexAIPartnerModelsAnthropicMessagesConfig

* fix _get_total_tokens_from_usage

* working TestBedrockInvokeToolSearch

* fix get_extra_headers

* TestBedrockInvokeToolSearch

* _get_tool_search_beta_header_for_bedrock

* fix mypy linting
 2026-01-15 16:35:00 -08:00
YutaSaito
960bdbbd8e
Revert "[Feat] Add support for 0 cost models" 2026-01-16 09:33:38 +09:00
yuneng-jiang
5ff768e5e0 Merge remote-tracking branch 'origin' into litellm_deleted_keys_team 2026-01-15 15:55:18 -08:00
yuneng-jiang
6a7edd8f2b
Merge pull request #18785 from BerriAI/litellm_user_promethus_metrics 
[Feature] User Metrics for Promethus
 2026-01-15 15:51:02 -08:00
yuneng-jiang
e07106244e
Merge pull request #19116 from BerriAI/litellm_org_admin_escalte 
[Fix] /user/new Privilege Escalation
 2026-01-15 15:50:43 -08:00
Emerson Gomes
f7726c8950 Fix wrong keys being used for model sticky entry 2026-01-15 17:42:29 -06:00
Emerson Gomes
059e75ad88 fix(router): scope deployment affinity by model_map_key 
- Key affinity by (user_api_key_hash, model_map_key) -> model_id
- Ignore OpenAI 'user' param for affinity
- Avoid double hashing user_api_key_hash
- Add unit tests + docs clarifications
 2026-01-15 16:28:36 -06:00
choigawoon
d76f3acb80
fix: video status/content credential injection for wildcard models (#18854) 
* fix: video status/content credential injection for wildcard models

When using wildcard model patterns like `vertex_ai/*`, the video status
and content endpoints failed to resolve the model_name correctly,
causing credential injection to be skipped.

Changes:
- router.py: Added `custom_llm_provider` parameter to
  `resolve_model_name_from_model_id` method
- router.py: Added Strategy 2 (provider prefix matching) and
  Strategy 4 (wildcard pattern matching)
- endpoints.py: Pass `provider_from_id` to resolver in video_status,
  video_content, and video_remix endpoints

This allows video_id like `vertex_ai:veo-3.0-generate-preview:...` to
correctly match `vertex_ai/*` wildcard pattern and inject credentials
from the model config.

Fixes: Video status returns "Your default credentials were not found"
when using Vertex AI video generation with wildcard model patterns.

* pr18845-video기능버그픽스 (vibe-kanban e43e2d2d)

pr코멘트 대응

litellm fork해서 branch만들고 작업후 pull request를 올렸는데 피드백을줬어.

이 내용 파악해서 내가 올린 pr 브랜치에 해당 작업 이어서 해야할거같아.

https://github.com/BerriAI/litellm/pull/18854#discussion\_r2677026995

여기 내용 읽고 현황 파악해서 작업하자.

테스트코드 작성해달라는데 테스트코드작성후 로컬에서 테스트명령어 한번 돌리고 커밋 푸시하려고.

litellm에서 pull request를 위한 문서가 있어.

https://docs.litellm.ai/docs/extras/contributing\_code

CRA서명은 했어. 그다음거부터 양식에 맞게 해야할듯. 지금 버그만 바로 고쳐서 pr했거든.

* fix: resolve mypy type error in resolve_model_name_from_model_id

Rename loop variable to avoid type conflict between DeploymentTypedDict
and Dict[Any, Any] from pattern_router.route() return type.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

---------

Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-16 03:45:25 +05:30