tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-13 12:22:57 +00:00
Code Issues Packages Projects Releases Wiki Activity
27,803 Commits 2,072 Branches 1,425 Tags
v1.80.5.dev2
Commit Graph
4310 Commits
Author SHA1 Message Date
Ishaan Jaffer 529c56423c test_opentelemetry_integration 2025-11-26 12:28:47 -08:00
Ishaan Jaffer 44e3133827 test_imagen_get_complete_url 2025-11-26 12:26:49 -08:00
Ishaan Jaffer 4bf5830106 test fix 2025-11-26 12:07:58 -08:00
Ishaan Jaffer 983ada20c3 mock test fixes 2025-11-26 12:02:35 -08:00
Ishaan Jaffer 2d70aee0c2 test_edit_mcp_server_redacts_credentials 2025-11-26 11:54:11 -08:00
Ishaan Jaffer 50328d15d4 test_process_chunk_with_response_completed_event 2025-11-26 11:52:05 -08:00
Ishaan Jaffer 6530749c89 test fixes 2025-11-26 11:42:12 -08:00
Ishaan Jaffer 85d4000af6 test_vertex_ai_partner_models_token_counting_endpoint 2025-11-26 11:37:55 -08:00
Ishaan Jaffer 19a6693dfc test_create_mcp_server_direct 2025-11-26 11:35:23 -08:00
Sameer KankuteandGitHub d4e80c6132 Merge pull request #17124 from BerriAI/litellm_gemini_file_search 
Add gemini file search support
 2025-11-26 22:07:11 +05:30
Sameer KankuteandGitHub 79c1203377 Merge pull request #17129 from BerriAI/litellm_fix_mcp_responses_anthropic 
Fix Thinking may not be enabled when tool_choice forces tool use
 2025-11-26 22:06:59 +05:30
Sameer Kankute 86a9b74fc8 Fix Thinking may not be enabled when tool_choice forces tool use 2025-11-26 13:32:13 +05:30
Sameer Kankute 241ad27843 Add gemini file search support 2025-11-26 11:17:30 +05:30
ripepersimmonandGitHub be970735de feat: Add gemini-3-pro-image-preview model support for imageSize parameters (#17019) 
- Add model identifier to FLASH_IMAGE_PREVIEW_MODEL_IDENTIFIERS
- Add imageSize parameter support (1K, 2K, 4K) with GeminiImageSize type
- Add tests for imageSize parameter transformation
- Update documentation with new model
 2025-11-25 19:38:29 -08:00
Igal BoxermanandGitHub e6e1e8fca4 feat(pillar): add automatic LiteLLM context headers (#17076) 
- Automatically pass LiteLLM virtual key context as X-LiteLLM-* headers
- Includes key_alias, user_id, team_id, org_id, and user_email
- No configuration required - always enabled for application/user tracking
- Excludes sensitive data (metadata, API tokens) for security
- Add comprehensive tests (30 tests, all passing)
- Update documentation with header details
 2025-11-25 19:35:39 -08:00
Carlo Alberto FerrarisandGitHub b50fcc4b56 vertex ai: use the correct domain for the global location when counting tokens (#17116) 2025-11-25 19:22:20 -08:00
Sameer KankuteandGitHub cd65a84abd Merge pull request #16844 from Chesars/fix/response-format-to-text-format-bridge-conversion 
fix: Support response_format parameter in completion -> responses bridge
 2025-11-26 08:51:09 +05:30
Ishaan JaffandGitHub 5c192a23c3 [Feat] Add new RAG API on LiteLLM AI Gateway (#17109) 
* init RAG api types

* add RAG endpoints

* init main.py for RAG ingest API

* init RecursiveCharacterTextSplitter

* add BaseRAGIngestion

* fix OpenAIRAGIngestion

* fix img handler

* init OpenAIRAGIngestion

* init BedrockRAGIngestion

* init BedrockRAGIngestion

* init rag tests

* init BedrockVectorStoreOptions

* implement BedrockRAGIngestion

* add BaseRAGAPI

* add endpoint for RAG ingest

* add ingest RAG endpoints

* add test doc

* add parse_rag_ingest_request

* update endpoints

* docs add docs for new RAG API

* fix qa check

* fix linting

* docs ficx

* docs

* add max depth checks

* docs anthropic
 2025-11-25 17:54:29 -08:00
Kerem TurgutluandGitHub 8637d74e17 include server_tool_use in streaming usage (#16826) 
* include server_tool_use in streaming usage

* add test
 2025-11-25 14:50:17 -08:00
Ishaan JaffandGitHub be712908a3 [Feat] Add OpenAI compatible bedrock imported models. - qwen etc (#17097) 
* test_bedrock_openai_imported_model

* AmazonBedrockOpenAIConfig

* add openai route for bedrock

* docs fix

* fix code qa check
 2025-11-25 12:20:39 -08:00
Sameer KankuteandGitHub 67622fb040 Add day 0 support for anthropic new feat (#17091) 
* Added tool search support for anthropic

* Add programtic tool calling support

* Add tool use input examples support

* Add anthropic effort param support

* Add anthropic effort param support

* Add blog for new features

* fix mypy and lint errors

* fix mypy and lint errors

* fix mypy and lint errors

* fix mypy and lint errors

* Add better handling

* Add better handling
 2025-11-25 11:28:47 -08:00
Sameer KankuteandGitHub 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 KankuteandGitHub 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 KankuteandGitHub 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 KankuteandGitHub 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 DholakiaGitHubCursor Agent
 		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 KankuteandGitHub 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 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 883cfaeeaf Add tests 2025-11-25 13:32:13 +05:30
wcyatandGitHub 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
Dmitrii KomarovandGitHub 046b7efbbe Make Bedrock image generation more consistent (#17021) 2025-11-24 20:58:01 -08:00
Saar wintrovandGitHub 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 GarciaandGitHub 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-jiangandGitHub d2b3ef0667 Add aws_bedrock_runtime_endpoint into Credential Types (#17053) 2025-11-24 20:48:51 -08:00
yuneng-jiangandGitHub 3f5a34d72c Deleting a user from team deletes key user created for team (#17057) 2025-11-24 20:47:43 -08:00
yuya_matsubaandGitHub 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 JhavarandGitHub 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
Sameer KankuteandGitHub 282ac87617 Add temperature support for 5.1 models (#17011) 2025-11-24 18:54:22 -08:00
Sameer KankuteandGitHub 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 KankuteandGitHub 35bfcac3bc Add header forwarding in embedding (#16869) 2025-11-24 18:48:10 -08:00
Sameer KankuteandGitHub c6fbdc7dc5 fix bedrock passthrough auth issue (#16879) 2025-11-24 18:44:59 -08:00
Sameer KankuteandGitHub 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
Sameer KankuteandGitHub 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
Ishaan JaffGitHubCopilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
 		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
Lior DrihemGitHubOri TabacVitaly Neyman
 		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
John LathouwersandGitHub 61fed95f8c OCI Provider: Fix pydantic validation errors during tool call with streaming. (#16899) 
* logic to handle missing required fields in OCI streaming tool calls

* Fix test mocks
 2025-11-23 22:03:44 -08:00
yuneng-jiangGitHubKrish Dholakia
 		adfdcf1d61 [Fix] UI - Hide Default Team Settings From Proxy Admin Viewers (#16900) 
* Add fallback in sort to prevent NoneType and str comparison

* Hide Default Team Settings from Proxy Admin Viewers

---------

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
 2025-11-23 22:01:38 -08:00