scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-08-28 05:25:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 8
27733 commits 3745 branches 1395 tags 3.9 GiB
Commit graph

27733 commits

This branch
This branch
All branches
Author SHA1 Message Date
abi_jey
aec0ab777b feat: add GA protocol as litellm_params for realtime api on azure provider 2025-11-25 19:18:41 +00:00
Sameer Kankute
3249f6dd2d
Merge pull request #17070 from BerriAI/litellm_add_vertex_ai_image_support 
Add vertex ai image gen support for both gemini and imagen models
 2025-11-26 00:04:03 +05:30
Sameer Kankute
83a9dcd2d2
Merge pull request #16886 from BerriAI/litellm_anthopic_azure_support 
Added support for azure anthopic models via chat completion
 2025-11-26 00:03:52 +05:30
Sameer Kankute
59b4b9a07c fix documentation of anthropic azure 2025-11-26 00:02:48 +05:30
Sameer Kankute
59bcf079fb
Merge pull request #17078 from BerriAI/litellm_add_search_logging 
Add search API logging and cost tracking in LiteLLM Proxy
 2025-11-25 23:59:41 +05:30
Sameer Kankute
2e50db81a5
Merge pull request #17071 from BerriAI/litellm_azure_gpt_5_reasoning 
Fix `reasoning_effort="none"` not working on Azure for GPT-5.1
 2025-11-25 23:59:25 +05:30
Krish Dholakia
00e17c81a1
Add enforce user param functionality (#17088) 
* feat: Add reject_metadata_tags to proxy config

Co-authored-by: krrishdholakia <krrishdholakia@gmail.com>

* Refactor: Rename reject_metadata_tags to reject_clientside_metadata_tags

Co-authored-by: krrishdholakia <krrishdholakia@gmail.com>

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2025-11-25 09:36:24 -08:00
Sameer Kankute
1c612288bc fix lint errors 2025-11-25 20:20:09 +05:30
Sameer Kankute
255d1bc239 fix lint errors 2025-11-25 20:20:09 +05:30
Sameer Kankute
e0396e5fa7
Merge pull request #17082 from BerriAI/main 
merge main
 2025-11-25 18:49:52 +05:30
Sameer Kankute
e2f2ccd913 Add tests related messages api 2025-11-25 18:45:51 +05:30
Sameer Kankute
dd4c8ecbef Add v1/messages support for azure anthropic models 2025-11-25 18:36:39 +05:30
Sameer Kankute
afe540e88d Fix auth issue 2025-11-25 18:26:25 +05:30
Sameer Kankute
67d69d12b0 Add cost tracking and logging support 2025-11-25 17:14:59 +05:30
Sameer Kankute
c149ade6a8 Add tests related to reasoning param none 2025-11-25 13:57:15 +05:30
Sameer Kankute
a50083a87b Remove none support from reasoning param 2025-11-25 13:56:30 +05:30
Sameer Kankute
b0d511143c remove unsused imports 2025-11-25 13:36:20 +05:30
Sameer Kankute
883cfaeeaf Add tests 2025-11-25 13:32:13 +05:30
Sameer Kankute
f52f05748d Update docs related to vertex ai image gen 2025-11-25 13:31:50 +05:30
Sameer Kankute
29ab291cf5 Add vertex ai image support 2025-11-25 13:31:16 +05:30
wcyat
6dcb5425a5
fix(vertex): fix CreateCachedContentRequest enum error (#16965) 
* feat: add _fix_enum_types function to remove enums from non-string fields in schema

* test: add test for _fix_enum_types function to validate enum removal from non-string fields
 2025-11-24 21:24:29 -08:00
yuneng-jiang
babee43dde
Merge pull request #17068 from BerriAI/litellm_additional_delete_resource_modal 
[Feature] Change Delete Modals to Common Component
 2025-11-24 20:58:46 -08:00
Dmitrii Komarov
046b7efbbe
Make Bedrock image generation more consistent (#17021) 2025-11-24 20:58:01 -08:00
Saar wintrov
cfd35d3b14
Metadata: fix 401 when audio/transcriptions (#17023) 
* Metadata: fix 401 when audio/transcriptions

* check if str, CR fixes
 2025-11-24 20:56:27 -08:00
Cesar Garcia
650b18974f
fix(gemini): skip thinking config for image models (#17027) 
* fix(gemini): exclude image models from automatic thinking_level parameter (#17013)

- gemini-3-pro-image-preview does not support thinking_level parameter
- Added check to skip adding thinkingConfig for models containing "image"
- Fixes BadRequestError: "Thinking level is not supported for this model"
- Only affects automatic default behavior, user can still pass reasoning_effort explicitly

Fixes #17013

* test: add tests for gemini-3 image models thinking_level exclusion

* update docs
 2025-11-24 20:54:12 -08:00
yuneng-jiang
3aba6d96fd
[Fix] UI - Add No Default Models for Team and User Settings (#17037) 
* Add No Default Models to Team and User settings

* Removing unused imports

* Adding to Create User and Team flow
 2025-11-24 20:53:17 -08:00
Saar wintrov
777ef628d2
Enhancement(helm): ServiceMonitor template rendering (#17038) 
* Metadata: fix 401 when audio/transcriptions

* check if str, CR fixes

* Added new helmchart functionality

* .

* .

* adding new tests
 2025-11-24 20:53:02 -08:00
Emerson Gomes
597fa4d35c
Fix image edit endpoint (#17046) 
* Fix image edit endpoint

* Update litellm/proxy/image_endpoints/endpoints.py

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
 2025-11-24 20:52:35 -08:00
yuneng-jiang
d2b3ef0667
Add aws_bedrock_runtime_endpoint into Credential Types (#17053) 2025-11-24 20:48:51 -08:00
Krish Dholakia
1ae80955e8
Docs: Add link to logging payload spec (#17049) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2025-11-24 20:48:10 -08:00
yuneng-jiang
3f5a34d72c
Deleting a user from team deletes key user created for team (#17057) 2025-11-24 20:47:43 -08:00
yuneng-jiang
e371ff454a
Non root docker build fix (#17060) 2025-11-24 20:45:56 -08:00
yuya_matsuba
262fb742d2
Fix: Distinguish permission errors from idempotent errors in Prisma migrations (#17064) 
* fix: distinguish permission errors from idempotent errors in Prisma migrations

* style: apply Black formatting and fix line length issues
 2025-11-24 20:41:44 -08:00
Raghav Jhavar
bd8196f982
(fix) propagate x-litellm-model-id in responses (#16986) 
* propagate model id on errors too

* make it work for messages and streaming

* fix

* cleanup

* cleanup

* final

* cleanup

* clean up method name and fix responses api streaming

* remove comment
 2025-11-24 20:40:43 -08:00
yuneng-jiang
d53bc7b9a0 Change modals to reusable component 2025-11-24 20:37:33 -08:00
Sameer Kankute
282ac87617
Add temperature support for 5.1 models (#17011) 2025-11-24 18:54:22 -08:00
Sameer Kankute
fc219c7db8
Integrate eleven labs text-to-speech (#16573) 
* Add elevenlaps tts support

* fix mypy error

* add simple usage in docs
 2025-11-24 18:49:30 -08:00
Sameer Kankute
35bfcac3bc
Add header forwarding in embedding (#16869) 2025-11-24 18:48:10 -08:00
Sameer Kankute
c6fbdc7dc5
fix bedrock passthrough auth issue (#16879) 2025-11-24 18:44:59 -08:00
Sameer Kankute
3b6c170739
Fix the azure auth format for videos (#17009) 
* fix the azure auth in correct format

* Add litellm param in validate_environment method

* fix lint errors
 2025-11-24 17:40:55 -08:00
Haiyi
84e8b9a7bf
fix: handle None or empty contents in Gemini token counter (#17020) 
Adds null/empty check before processing contents in GoogleAIStudioTokenCounter
to prevent errors when contents is None or empty.

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

Co-authored-by: Claude <noreply@anthropic.com>
 2025-11-24 17:40:00 -08:00
Sameer Kankute
629404a100
Add cost tracking for cohere embed passthrough endpoint (#17029) 
* Add cost tracking for cohere embed passthrough endpoint

* update passthrough code

* update passthrough code

* fixed lint and mypy errors
 2025-11-24 17:39:26 -08:00
Mubashir Osmani
aec6590486
add strands tutorial (#17039) 
* add strands tutorial

* configgg
 2025-11-24 17:31:59 -08:00
YutaSaito
f5a3349fef
feat: add UI support for configuring tool permission guardrails (#17050) 
* feat: add UI support for configuring tool permission guardrails

* chore: rename UI/Docs references to "LiteLLM Tool Permission Guardrail"
 2025-11-24 17:13:07 -08:00
Ishaan Jaff
d2b90e6644
[Docs] Claude Skills API (#17052) 
* add skillls api

* init doc

* docs fix

* skills API
 2025-11-24 15:32:03 -08:00
Ishaan Jaff
4e195d639e
[Feat] New API - Claude Skills API (Anthropic) (#17042) 
* init readme

* init BaseSkillsAPIConfig

* init types for Skills APIs

* add feat: add create, list, retrieve skills

* add base skills config

* add BaseSkillsAPIConfig

* add get_provider_skills_api_config

* init skills

* add ANTHROPIC_SKILLS_API_BETA_VERSION

* init skills APIs

* working list, get skills

* working e2e skills API anthropic API

* add _prepare_skill_multipart_request

* add skills routes to llm api routes

* router _initialize_skills_endpoints

* add fix skills endpoints

* add convert_upload_files_to_file_data

* fix routing skills endpoints

* fix route llm request

* Potential fix for code scanning alert no. 3806: Clear-text logging of sensitive information

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

* Potential fix for code scanning alert no. 3809: Clear-text logging of sensitive information

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>

* fix ruff checks

* test_initialize_skills_endpoints

* fix claude skills mypy linting errors

---------

Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
 2025-11-24 15:01:40 -08:00
Mubashir Osmani
a807fe4450
add claude opus 4.5 (#17043) 
* add claude opus 4.5

* Apply suggestion from @Chesars

Co-authored-by: Cesar Garcia <128240629+Chesars@users.noreply.github.com>

---------

Co-authored-by: Cesar Garcia <128240629+Chesars@users.noreply.github.com>
 2025-11-24 14:30:36 -08:00
Lior Drihem
62b84d6aad
Prompt security litellm (#16365) 
* add prompt security guardrails provider

* cosmetic

* small

* add file sanitization and update context window

* add pdf and OOXML files support

* add system prompt support

* add tests and documentation

* remove print

* fix PLR0915 Too many statements (96 > 50)

* cosmetic

* fix mypy error

* Fix failed tests due to naming conflict of responses directory with same-named pip package

* Fix mypy error: use 'aembedding' instead of 'embeddings' for async embedding call type

* Fix: Install enterprise package into Poetry virtualenv for tests

The GitHub Actions workflow was installing litellm-enterprise to system Python
using 'python -m pip install -e .', but tests run in Poetry's virtualenv using
'poetry run pytest'. This caused ImportError for enterprise package types.

Changed to 'poetry run pip install -e .' so the package is available in the
same virtualenv where pytest executes.

Fixes enterprise test collection errors in GitHub Actions CI.

* Move Prompt Security guardrail tests to tests/test_litellm/

Per reviewer feedback, move test_prompt_security_guardrails.py from
tests/guardrails_tests/ to tests/test_litellm/proxy/guardrails/ so
it will be executed by GitHub Actions workflow test-litellm.yml.

This ensures the Prompt Security integration tests run in CI.

---------

Co-authored-by: Ori Tabac <oritabac@prompt.security>
Co-authored-by: Vitaly Neyman <vitaly@prompt.security>
 2025-11-24 11:44:20 -08:00
Krish Dholakia
559142a738
Add table explaining different callback hooks (#17035) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2025-11-24 08:37:35 -08:00
Krish Dholakia
7c1dfd4462
docs: Clarify optional user_allowed_email_domain (#17034) 
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
 2025-11-24 08:34:35 -08:00