tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-17 18:23:47 +00:00
Code Issues Packages Projects Releases Wiki Activity
28,376 Commits 2,072 Branches 1,425 Tags
14d331e9ea08c7bd67b878635f1794dfd94bd7aa
Commit Graph
28376 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Krish DholakiaandGitHub 14d331e9ea fix(vertex_llm_base.py): Add missing scopes to identity pool credentials (#17560) 
* fix(vertex_llm_base.py): Fixes https://github.com/BerriAI/litellm/issues/17377

* test: update tests
 2025-12-06 16:03:51 -08:00
Ishaan Jaffer 3090197861 fix docker 2025-12-06 16:02:02 -08:00
Ishaan Jaffer b6562b9d88 test_thought_true_with_empty_text_creates_block 2025-12-06 16:00:05 -08:00
Ishaan Jaffer 8539aac85a fix scans 2025-12-06 15:53:49 -08:00
Ishaan Jaffer 238affd332 fix code qa check 2025-12-06 15:51:44 -08:00
Sameer KankuteGitHubKrish Dholakia
 		5f27c70bb0 Add beta header in vertex request for claude websearch request (#16269) 
* Add beta header in vertex request for claude websearch request

* add condition if header present don't overide

---------

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
 2025-12-06 15:29:35 -08:00
yuneng-jiangandGitHub 69f65e20e0 Merge pull request #17618 from BerriAI/litellm_customer_usage_docs_path 
[Docs] Fixing path to image
 2025-12-06 14:47:18 -08:00
yuneng-jiang 7385801fba Fixing path to image 2025-12-06 14:45:50 -08:00
Anil KodaliandGitHub 1a50a89cd3 [New Model] Add Amazon Nova as first party provider for chat completions (#17351) 
* Add Amazon Nova as a first party provider

* Added new provider folder under llms/ to outline the openai supported params

* Updated supported endpoints on the documnetation
 2025-12-06 14:43:55 -08:00
yuneng-jiangandGitHub 324ce58003 Merge pull request #17617 from BerriAI/litellm_customer_usage_docs_sidebar 
[Docs] Update sidebar for customer usage
 2025-12-06 14:22:28 -08:00
yuneng-jiang bff3590dd0 Update sidebar for customer usage 2025-12-06 14:21:18 -08:00
Lukas de BoerandGitHub 3b8a6ec888 Helm Chart: Add possibility to override command, args and add deployment labels (#17535) 
* Helm Chart: Add possibility to override command, args and also add deployment labels

* Helm Chart: Fix helm lint issue

* Helm Chart: Fix helm unit tests
 2025-12-06 14:01:09 -08:00
Cesar GarciaandGitHub 8ccfaa21de docs: add Microsoft GraphRAG to projects using LiteLLM (#17616) 
* docs: add Microsoft GraphRAG to projects using LiteLLM

* docs: add arXiv paper link for GraphRAG

* docs: add GraphRAG to sidebar

* Update projects in sidebars.js

Reordered items in the projects list to include 'GraphRAG'.
 2025-12-06 13:47:46 -08:00
yuneng-jiangandGitHub b64be147d0 Merge pull request #17615 from BerriAI/litellm_customer_usage_docs 
[Docs] Customer Usage
 2025-12-06 13:44:23 -08:00
yuneng-jiang 3f7d51d53e Merge remote-tracking branch 'origin' into litellm_customer_usage_docs 2025-12-06 13:43:28 -08:00
yuneng-jiang da4b36fe9b Changed image 2025-12-06 13:23:49 -08:00
yuneng-jiang 40ad0e2e96 Customer Usage Docs 2025-12-06 13:17:54 -08:00
Alexsander HamirandGitHub 3359daf621 refactor: extract helper methods from pre_call_hook to fix PLR0915 linting error (#17613) 
- Extract _process_prompt_template method for prompt template processing
- Extract _process_guardrail_metadata method for guardrail metadata processing
- Reduces statement count in pre_call_hook from 68 to under 50
 2025-12-06 13:13:59 -08:00
Alexsander HamirandGitHub a1d114a8ad Fix: test_guardrails_with_api_key_controls (#17612) 
* Fix: around for the callback issue

* Remove comment
 2025-12-06 13:05:52 -08:00
Ishaan Jaffer df6cb4244d docs a2a gateway 2025-12-06 12:32:30 -08:00
Ishaan Jaffer fdf28331a5 docs fix 2025-12-06 11:48:00 -08:00
Ishaan Jaffer b4c6b29149 docs fix 2025-12-06 11:41:51 -08:00
Ishaan Jaffer 2bf0b951f7 docs fix 2025-12-06 11:37:08 -08:00
yuneng-jiangandGitHub 29e7cd452a Merge pull request #17610 from BerriAI/litellm_ui_build_4 
[Infra] Building UI To Include Fix
 2025-12-06 11:35:49 -08:00
Ishaan Jaffer 86a0c14aca docs guardrails 2025-12-06 11:34:55 -08:00
yuneng-jiang 4ca3c042e0 Building UI for fix 2025-12-06 11:34:13 -08:00
yuneng-jiangandGitHub 6de0ffbf04 Merge pull request #17609 from BerriAI/litellm_ui_mcp_fix 
[Fix] UI - MCP Test Tool Fix
 2025-12-06 11:30:34 -08:00
yuneng-jiang 19cacaaed5 UI MCP Test Tool Fix 2025-12-06 11:18:48 -08:00
Ishaan Jaffer 6bb4087b22 docs fix 2025-12-06 11:09:46 -08:00
Alexsander HamirandGitHub c44e075b2d feat: add script to create branches with litellm_ prefix (#17606) 
Add utility scripts to create branches with litellm_ prefix from contributor branches.
This helps maintain consistent branch naming conventions for CI/CD.

- scripts/create_litellm_branch.sh (Bash for macOS/Linux)
- scripts/create_litellm_branch.ps1 (PowerShell for Windows)

Usage:
  ./scripts/create_litellm_branch.sh [source_branch] [new_branch_name]
  ./scripts/create_litellm_branch.ps1 [source_branch] [new_branch_name]

Features:
- Auto-prefixes branch names with litellm_
- Handles existing branches gracefully
- Validates branch names
- Supports local and remote source branches
 2025-12-06 10:41:39 -08:00
Ishaan JaffandGitHub a9b654224e 1.80.8 RC docs (#17605) 
* stash docs

* docs fix

* doc fix

* docs fix
 2025-12-06 10:40:00 -08:00
Ishaan Jaffer edcfc13ebb bump: version 1.80.7 → 1.80.8 2025-12-06 10:18:23 -08:00
Ishaan Jaffer bfdcfca8b0 fix test 2025-12-06 10:15:00 -08:00
Ishaan Jaffer 8f98725503 fix mypy linting 2025-12-06 10:09:30 -08:00
Ishaan Jaffer bcf601b8a6 bump proxy extras pip 2025-12-06 10:00:22 -08:00
Ishaan Jaffer 71ea926f9a test_no_duplicate_spend_logs 2025-12-06 09:56:05 -08:00
Sungjun.KimGitHubIshaan Jaff
 		ca7241188a feat: Add xhigh reasoning effort for gpt-5.1-codex-max (#17585) 
Co-authored-by: Ishaan Jaff <ishaanjaffer0324@gmail.com>
 2025-12-06 09:48:18 -08:00
Cesar GarciaandGitHub 0f1d6c37d2 docs: add gpt-5.1-codex-max to OpenAI provider documentation (#17602) 
Add gpt-5.1-codex-max model to:
- Model list table
- Reasoning effort table
- Verbosity note
 2025-12-06 09:46:48 -08:00
Ishaan Jaffer 6358be3d0b fix build from PIP 2025-12-06 09:44:09 -08:00
Alexsander HamirandGitHub 09dcd381d7 fix: mark test_caching_with_reasoning_content as flaky and handle InternalServerError (#17603) 
- Add @pytest.mark.flaky(retries=3, delay=1) decorator to handle intermittent Anthropic API failures
- Add error handling to skip test when Anthropic API returns InternalServerError
- Prevents false test failures due to external API 500 errors
 2025-12-06 09:41:09 -08:00
Krrish Dholakia 497856e1e3 docs: document multi tenant architecture 2025-12-06 09:27:30 -08:00
Alexsander HamirandGitHub 8172f6cdd6 Fix security vulnerability: update mdast-util-to-hast to 13.2.1 (CVE-2025-66400) (#17601) 2025-12-06 09:26:26 -08:00
yuneng-jiangandGitHub 03706e4841 Merge pull request #17600 from BerriAI/litellm_ui_build_3 
[Infra] Building UI for release
 2025-12-06 09:22:38 -08:00
Alexsander HamirandGitHub 1254a92e66 fix: make test_log_langfuse_v2_handles_null_usage_values more robust (#17599) 
- Reset mock call counts at start of test to ensure clean state
- Add span method to mock trace to handle log_provider_specific_information_as_span calls
- Re-establish mock chain before test call to ensure fresh state
- Add exception handling to catch and report errors during test execution
- Add verification that trace was called before checking generation

This should fix the flaky test that was failing intermittently with
'Expected generation to have been called once. Called 0 times.'
 2025-12-06 09:21:00 -08:00
yuneng-jiang 0917f72bbd Building UI for release 2025-12-06 09:18:20 -08:00
yuneng-jiangandGitHub fe23eee079 Merge pull request #17598 from BerriAI/litellm_ui_customer_usage_banner 
[Feature] UI - Add Info Banner for Customer Usage
 2025-12-06 09:04:39 -08:00
yuneng-jiang fa47861ca0 Add banner for customer usage 2025-12-06 08:57:15 -08:00
Alexsander HamirandGitHub 53e2516ace fix: make test_watsonx_gpt_oss_prompt_transformation deterministic (#17597) 
- Remove network dependency by mocking HuggingFace template fetch
- Use mock template that produces correct format for test validation
- Test now focuses on transformation logic, not network calls
- Fixes flaky test failures due to network timeouts/rate limits

The test verifies that prompt transformation occurs (not simple
concatenation), which doesn't require the actual HuggingFace template.
Mocking makes the test deterministic and faster while still validating
the core behavior.
 2025-12-06 08:48:39 -08:00
Alexsander HamirandGitHub db40a38999 Add retry logic to apk package installation in Dockerfile.non_root (#17596) 
- Add retry loop (3 attempts with 5s delay) to builder stage apk add command
- Add retry logic to runtime stage apk upgrade and apk add commands
- Improves resilience to transient network errors during package downloads
 2025-12-06 08:17:50 -08:00
Alexsander HamirandGitHub 73075c7d24 fix: add retry logic for flaky Azure image generation health check test (#17595) 
- Add missing @pytest.mark.asyncio decorator
- Implement retry logic with exponential backoff (3 retries)
- Only retry on transient Azure internal server errors
- Fail immediately on non-transient errors

This fixes the flaky test_azure_img_gen_health_check which was failing
due to transient Azure internal server errors that are outside our control.
 2025-12-06 08:11:52 -08:00