Commit graph

29793 commits

Author SHA1 Message Date
Yuneng Jiang
0a0b29f721
chore: fixes 2026-04-04 22:48:01 -07:00
Cursor Agent
d44e3403ac Refactor: Simplify Claude model load balancing tutorial
Co-authored-by: krrishdholakia <krrishdholakia@gmail.com>
2026-01-08 18:21:02 +00:00
Cursor Agent
a956c971a9 Add tutorial for load balancing Claude models
Co-authored-by: krrishdholakia <krrishdholakia@gmail.com>
2026-01-08 11:20:51 +00:00
Sameer Kankute
c023c69eae
Merge pull request #18739 from BerriAI/litellm_fix_deepinfra_tool_call
[Fix]: Tool content should be string for Deepinfra
2026-01-08 15:41:56 +05:30
Sameer Kankute
f52cc32a4c fix mypy error 2026-01-08 15:38:28 +05:30
Sameer Kankute
c13bc21520
Merge pull request #18754 from BerriAI/litellm_add_annotations_responses_bridge
Add annotations to completions responses API bridge
2026-01-08 15:30:16 +05:30
Sameer Kankute
0eb20ad500
Merge pull request #18745 from BerriAI/litellm_fix_gemini_audio_file_upload
Fix: Gemini generate content request with audio file id
2026-01-08 15:30:09 +05:30
Sameer Kankute
df7337fd38
Merge pull request #18800 from BerriAI/litellm_add_model_id_support_bedrock
Add support for model id in bedrock passthrough
2026-01-08 15:29:47 +05:30
Sameer Kankute
e0662d53a2
Merge pull request #18799 from BerriAI/litellm_fix_claude_usage_object
Fix: Incomplete usage in response object passed
2026-01-08 15:29:26 +05:30
Sameer Kankute
4abc94119f
Merge pull request #18797 from BerriAI/litellm_bedrock_kimi2_model
[Feat]Add bedrock kimi2 model support
2026-01-08 15:29:12 +05:30
Sameer Kankute
c05e148488
Merge pull request #18809 from BerriAI/main
merge main
2026-01-08 15:28:13 +05:30
Sameer Kankute
c95544959b
Merge pull request #18808 from BerriAI/main
merge main
2026-01-08 15:25:50 +05:30
Sameer Kankute
6941a29ad3
Merge pull request #18807 from BerriAI/main
merge main
2026-01-08 15:25:13 +05:30
Emerson Gomes
6c00f6f342
Add support to zai glm-4.7 model in Vertex (#18782)
* Add support to zai glm-4.7 model in Vertex

* Avoid failed on missing 'created' streaming chunk key
2026-01-08 13:20:02 +05:30
Sameer Kankute
c78bf8cfcd Add support for model id in bedrock passthrough 2026-01-08 13:03:58 +05:30
Sameer Kankute
7e98843d97 Fix: Incomplete usage in response object passed 2026-01-08 10:57:07 +05:30
Sameer Kankute
e5c3fcbb52 fix mypy tests 2026-01-08 10:48:14 +05:30
Sameer Kankute
c4bab70306 Fix: Add moonshot in get_bedrock_model_id 2026-01-08 10:21:38 +05:30
Sameer Kankute
2a4dc8e041 Fix: aws creds getting passed in req 2026-01-08 10:18:15 +05:30
Sameer Kankute
af6883712e Add tests for kimi 2 bedrock model 2026-01-08 10:07:33 +05:30
Sameer Kankute
ddd52e0e2f Add support for kimi2 model on bedrock 2026-01-08 09:51:34 +05:30
Alexsander Hamir
2f803171d6
refactor(prometheus): skip metrics for invalid API key requests (#18788) 2026-01-07 17:14:14 -08:00
yuneng-jiang
e285e2b91d
Merge pull request #18675 from BerriAI/litellm_key_team_routing_config
[Feature] Allow Add and Update for router_settings on Keys and Teams
2026-01-07 16:24:04 -08:00
yuneng-jiang
33ac5dae2b linting 2026-01-07 15:24:49 -08:00
Alexsander Hamir
98d7a428b6
Fix: Clarify database_connection_pool_limit applies per worker, not per instance (#18780) 2026-01-07 13:57:03 -08:00
yuneng-jiang
797ab1d7f3 Adding docs for team 2026-01-07 12:43:27 -08:00
yuneng-jiang
611b85bfd8 Fixing mypy linting 2026-01-07 12:36:34 -08:00
Alexsander Hamir
1544e8f971
feat: Add line_profiler support for performance analysis and fix Windows CRLF issues in Docker builds (#18773) 2026-01-07 11:36:57 -08:00
LouisShark
ea8a94988f
fix(bedrock): ensure toolUse.input is always a dict when converting from OpenAI format (#18414)
When some providers (like OpenRouter) return tool call arguments as '""'
(a JSON-encoded empty string), json.loads returns an empty string instead
of a dict. Since Bedrock requires toolUse.input to be a JSON object, this
causes a BedrockException.

This fix adds a type check after json.loads() to ensure the result is
always a dictionary.

Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
2026-01-08 00:54:46 +05:30
yuneng-jiang
a57f7bc9bf Fixing documentation 2026-01-07 11:24:15 -08:00
Danial Khan
f126f75995
feat: pass server_tool_use and tool_search_tool_result blocks to anthropic (#18770)
* feat: Allow message types of server_tool_use and tool_search_tool_result to reach anthropic

* test: anthropic server tool use pass through testing
2026-01-08 00:47:28 +05:30
yuneng-jiang
eb9f5267b6 Adding builds 2026-01-07 11:11:46 -08:00
yuneng-jiang
b2ebb5e1f1 adding migration 2026-01-07 11:10:59 -08:00
yuneng-jiang
b6f5ba6205 bump: version 0.4.19 → 0.4.20 2026-01-07 11:10:26 -08:00
yuneng-jiang
140ce5fce2 Merge remote-tracking branch 'origin' into litellm_key_team_routing_config 2026-01-07 11:08:01 -08:00
yuneng-jiang
19f323d7c9
Merge pull request #18729 from BerriAI/litellm_endpoint_usage_breakdown
[Feature] Add endpoint to Daily Activity Tables
2026-01-07 11:07:46 -08:00
Krish Dholakia
c89a4115eb
Update production proxy resource recommendations (#18771)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-01-08 00:37:12 +05:30
yuneng-jiang
943445dd0f Adding test 2026-01-07 11:00:07 -08:00
yuneng-jiang
9a49bb293f Merge remote-tracking branch 'origin' into litellm_key_team_routing_config 2026-01-07 10:55:38 -08:00
yuneng-jiang
bc812672a1 Addressing comments, pending tests 2026-01-07 10:55:25 -08:00
yuneng-jiang
6523c8f233 Adding builds 2026-01-07 10:27:50 -08:00
yuneng-jiang
ec6510c61b bump: version 0.4.18 → 0.4.19 2026-01-07 10:27:07 -08:00
yuneng-jiang
7da8d5fcd5 Merge remote-tracking branch 'origin' into litellm_endpoint_usage_breakdown 2026-01-07 10:25:43 -08:00
Ishaan Jaff
929af510fa
[Feat] New provider - Add Azure BFL FLux for image edits (#18766)
* add azure_ai/flux.2-pro

* get_flux2_image_generation_url

* azure_client_params

* docs

* add Image Editing

* add azure ai image edits

* AzureFoundryFlux2ImageEditConfig

* TestAzureAIFlux2ImageEdit
2026-01-07 23:28:39 +05:30
Ishaan Jaff
3430325919
[Feat] Add Azure BFL - Flux 2 models (#18764)
* add azure_ai/flux.2-pro

* get_flux2_image_generation_url

* azure_client_params

* docs
2026-01-07 23:28:28 +05:30
vasilisazayka
b4a39a9ea2
fix(sap): correct filtering of optional_params (#18716) 2026-01-07 21:48:29 +05:30
Ishaan Jaffer
bbabc1089c litellm_mapped_tests_litellm_core_utils 2026-01-07 21:35:12 +05:30
Ishaan Jaffer
6c2408f957 litellm_mapped_tests_integrations 2026-01-07 21:22:10 +05:30
Ishaan Jaffer
6122ff9fce TestEncryptResponseId 2026-01-07 21:03:22 +05:30
Cesar Garcia
e34e8b4650
Fix component label automation to prevent false positives (#18765)
* Fix component label automation to prevent false positives

The GitHub Actions workflow was applying component labels (SDK, Proxy, UI Dashboard, Docs) too broadly by only checking if the component name appeared anywhere in the issue body. This caused issues to be mislabeled when users mentioned these terms in their descriptions.

Changes:
- Add more specific condition that checks for both the dropdown field header "What part of LiteLLM is this about?" AND the component name
- Applied to all 4 component labels: SDK, Proxy, UI Dashboard, and Docs
- Labels will now only be applied when users actually select the option from the dropdown

Fixes issues being incorrectly labeled with 'docs' and other component labels.

* Use more specific pattern to match dropdown selection exactly

Updated the label conditions to use a more precise pattern that matches
the dropdown header immediately followed by the selected value. This
prevents false positives when users mention component names in their
descriptions but select a different component.

Before: Checked for header AND component name anywhere in body
After: Checks for exact pattern "header\n\ncomponent"

This ensures labels are only applied when the component is actually
selected from the dropdown, not just mentioned in the issue text.

* Fix component label automation and require explicit user selection

This PR fixes two issues with component labeling:

1. **Improved label accuracy**: Updated the workflow to use exact pattern
   matching ("### What part of LiteLLM is this about?\n\nDocs") instead of
   broad substring matching. This prevents false positives where issues were
   mislabeled when users mentioned component names in their descriptions.

2. **Require explicit component selection**: Added empty string ('') as the
   first dropdown option to prevent GitHub from auto-selecting "SDK" as the
   default. Users must now consciously select which component their issue
   relates to.

Changes:
- Updated all component label conditions in label-component.yml workflow
- Added empty string as first option in bug_report.yml dropdown
- Added empty string as first option in feature_request.yml dropdown
- Labels only apply when users actually select a component from the dropdown

This ensures accurate labeling and prevents the default SDK label from
being applied to all new issues.
2026-01-07 20:01:14 +05:30