Fabian Reinold
c173a4a275
Helm Chart: add ingress-only labels ( #17348 )
...
* feat(helm): add ingress-only labels
* feat(helm): add ingress configuration tests
* chore(helm): bump chart version
2025-12-02 22:30:54 -08:00
Cesar Garcia
86350fe6d7
docs: add Google ADK and Harbor to projects ( #17352 )
...
Both frameworks integrate with LiteLLM:
- Google ADK uses LiteLLM for model-agnostic agent building
- Harbor uses LiteLLM for agent evaluation across providers
2025-12-02 22:27:04 -08:00
Cesar Garcia
4c6604b0da
Cleanup: Remove orphan docs pages and Docusaurus template files ( #17356 )
...
* docs: update getting started page
- Add Core Functions table with link to full list
- Add Responses API section
- Add Async section with acompletion() example
- Add "Switch Providers with One Line" example
- Clarify Basic Usage supports multiple endpoints
- Update models to current versions (openai/gpt-4o, anthropic/claude-sonnet-4)
- Use provider/model format throughout
- Fix deprecated import: from openai.error -> from openai
- Keep original structure: community key, More details links, observability env vars
* Cleanup: Remove orphan docs pages and Docusaurus template files
- Remove orphan getting_started.md (not linked in sidebar)
- Remove Docusaurus template intro.md
- Remove tutorial-basics/ directory (Docusaurus template)
- Remove tutorial-extras/ directory (Docusaurus template)
2025-12-02 22:25:26 -08:00
Deepak Tammali
e289f5e454
feat: make streaming chunk size configurable in bedrock converse and invoke handlers ( #17357 )
2025-12-02 22:14:48 -08:00
Jonathan Yang
43dd9e4a90
fix: replace deprecated .dict() with .model_dump() in streaming_handler ( #17359 )
...
Replace Pydantic v1 `.dict()` method with v2 `.model_dump()` to fix
PydanticDeprecatedSince20 warnings. The `.dict()` method is deprecated
in Pydantic v2 and will be removed in v3.
Fixes #5987
2025-12-02 22:12:55 -08:00
Jonathan Yang
17faea96bb
fix: conditionally pass enable_cleanup_closed to aiohttp TCPConnector ( #17367 )
...
* fix: conditionally pass enable_cleanup_closed to aiohttp TCPConnector
Fixes deprecation warning on Python 3.12.7+ and 3.13.1+ where
enable_cleanup_closed is no longer needed since the underlying
CPython SSL connection leak bug was fixed.
See: https://github.com/python/cpython/pull/118960
* chore: add aiohttp source reference to AIOHTTP_NEEDS_CLEANUP_CLOSED
2025-12-02 22:09:57 -08:00
Mariano Hielpos
566adebdec
update model_prices_and_context_window.json ( #17376 )
...
* update model_prices_and_context_window.json
* update
* update
2025-12-02 22:06:51 -08:00
Ali Saleh
6b5ad5d5a6
docs: Update Instructions For Phoenix Integration ( #17373 )
2025-12-02 22:03:54 -08:00
mossbanay
ae633184f7
Add model price & details for Bedrock model global.anthropic.claude-opus-4-5-20251101-v1:0 ( #17380 )
2025-12-02 22:02:57 -08:00
Matt Greathouse
f22bc0aab2
Support Deepseek 3.2 with Reasoning ( #17384 )
...
* Add openrouter/deepseek/deepseek-v3.2
* Added deepseek-provided v3.2
* Allow reasoning effort param for openrouter models that support it
* Added tests
2025-12-02 22:00:19 -08:00
Richard Song
099ccf56a7
Refactor add_schema_to_components to move definitions to components/schemas and add corresponding unit test ( #17389 )
2025-12-02 21:57:07 -08:00
Sameer Kankute
40c203e32b
Make thought sign in tool call id as a beta feat
2025-12-03 11:04:53 +05:30
Sameer Kankute
209e9e05aa
Fix gemini 3 last chunk thinking block
2025-12-03 10:13:59 +05:30
Sameer Kankute
a0819d6df0
Merge branch 'main' into litellm_vertex-bge-cherrypick
2025-12-03 08:37:04 +05:30
yuneng-jiang
7fea97a0c0
Add is_sso_configured to UI Config
2025-12-02 17:53:16 -08:00
yuneng-jiang
afedc9aac3
Fixing test
2025-12-02 17:34:53 -08:00
yuneng-jiang
8f565a811c
Merge with main
2025-12-02 17:31:03 -08:00
yuneng-jiang
4006987f0e
Merge remote-tracking branch 'origin' into litellm_ui_cred_refresh
2025-12-02 17:29:22 -08:00
Ishaan Jaff
427074ac6e
Fix: Datadog callback regression when ddtrace is installed ( #17393 )
...
* fix DD agent host logging
* docs fix
* test_datadog_agent_configuration
* test_datadog_ignores_ddtrace_agent_host
2025-12-02 17:27:50 -08:00
yuneng-jiang
b000851be8
Merge remote-tracking branch 'origin' into litellm_ui_cred_refresh
2025-12-02 17:27:10 -08:00
yuneng-jiang
451690bf11
Merge pull request #17321 from BerriAI/litellm_ui_user_alias_table
...
[Feature] Add User Alias Column to Internal User Table
2025-12-02 17:26:49 -08:00
yuneng-jiang
cfedc371d6
Merge pull request #17325 from BerriAI/litellm_ui_key_terminology
...
[Refactor] Standardize API Key vs Virtual Key in UI
2025-12-02 17:26:31 -08:00
yuneng-jiang
6e3a44b82c
Merge pull request #17397 from BerriAI/litellm_ui_cred_fix
...
[Fix] Show all credential values on Edit Credential Modal
2025-12-02 17:12:36 -08:00
yuneng-jiang
4063501d69
Show all credential values on Edit Credential Modal
2025-12-02 17:08:17 -08:00
flozonn
31cad8e6e6
feat: Add Nova lite 2 reasoning support with reasoningConfig ( #17371 )
2025-12-02 16:33:07 -08:00
Ishaan Jaff
10d56e7c46
add new deepseek-v3p2 ( #17395 )
2025-12-02 16:19:34 -08:00
yuneng-jiang
12d3c4a1d4
Merge pull request #17394 from BerriAI/litellm_ui_org_models_fix
...
[Fix] UI - Change Edit Team Models Shown to Match Create Team
2025-12-02 16:06:36 -08:00
Krrish Dholakia
8ee298f9c9
fix: remove python3 headers
2025-12-02 16:06:06 -08:00
yuneng-jiang
9867cc6cf9
Change edit team models to match create team models
2025-12-02 15:58:27 -08:00
Krrish Dholakia
7fb2f4730b
build: remove duplicate packages
2025-12-02 15:53:10 -08:00
Ishaan Jaff
6c188c5ae2
[Feat] New model/provider - Adds support for Google Cloud Chirp3 HD on /speech ( #17391 )
...
* docs vertex tts
* place vertex ai types in file
* use VertexAITextToSpeechConfig
* use vertex_voice_dict
* refactor docs
* docs vertex ai chirp
* TestVertexAITextToSpeechConfig
* new provider vertex ai chirp3
* test_litellm_speech_vertex_ai_chirp
* add vertex_ai/chirp cost trackign
2025-12-02 15:36:23 -08:00
yuneng-jiang
5a8154335f
Changed default provider and made optional status of Vertex API Base more obvious
2025-12-02 15:00:52 -08:00
Leslie Cheng
de4ff120eb
🐛 Fix proxy caching between requests in aiohttp transport ( #17122 )
...
* write a regression test
* impl fix
* add test for host case
* use the host as cache key
2025-12-02 14:37:45 -08:00
Ishaan Jaff
db6c6eea89
[Docs] Add guide on how to debug gateway error vs provider error ( #17387 )
...
* add error diagnosis
* docs error diagnosis
2025-12-02 14:10:00 -08:00
yuneng-jiang
102b8401b3
Change labeling around Vertex Fields
2025-12-02 12:32:51 -08:00
yuneng-jiang
7d4f3f9290
Merge pull request #17382 from BerriAI/litellm_vertex_api_base
...
[Infra] Add Google Private API Endpoint to Vertex AI fields
2025-12-02 12:26:28 -08:00
yuneng-jiang
8b8f93d508
Add Google Private API Endpoint to Vertex AI fields
2025-12-02 12:24:00 -08:00
yuneng-jiang
61b0dbd726
Merge pull request #17378 from BerriAI/litellm_indent_import_fix
...
[Fix] Bedrock Guardrail Indent and Import fix
2025-12-02 11:28:12 -08:00
yuneng-jiang
8c1290dcd2
Indent and import fix
2025-12-02 11:26:29 -08:00
yuneng-jiang
6ee9d9c344
/login route refactor
2025-12-02 11:19:27 -08:00
kothamah
12530b375f
Litellm bedrock OpenAI model support ( #17368 )
...
* Update constants.py
added constants
* Update base_aws_llm.py
added steps
* Update invoke_handler.py
added openai support
* Update base_invoke_transformation.py
added
* Update test_bedrock_completion.py
added
2025-12-02 09:19:53 -08:00
Cesar Garcia
81f4d863ca
docs: add Azure AI Foundry documentation for Claude models ( #17104 )
...
* docs: add Azure AI Foundry documentation for Claude models
Add documentation explaining how to use Claude models (Sonnet 4.5,
Haiku 4.5, Opus 4.1) deployed on Azure AI Foundry with LiteLLM.
Azure exposes Claude using Anthropic's native API, so users can use
the existing anthropic/ provider with their Azure endpoint.
Closes #17066
* docs: Add alternative method for Azure AI Foundry using anthropic/ provider
Document that users can use anthropic/ provider with Azure endpoint
as an alternative to the dedicated azure_ai/ provider.
2025-12-02 09:08:10 -08:00
Sameer Kankute
4ac9e4c81c
Merge pull request #17345 from BerriAI/litellm_fix_jwt_auth_route_issue
...
Add other routes in jwt auth
2025-12-02 22:21:04 +05:30
Sameer Kankute
397aceced8
Merge pull request #17342 from BerriAI/litellm_fix_mcp_auth_header_forwarding
...
Fix: litellm user auth not passing issue
2025-12-02 22:20:33 +05:30
Sameer Kankute
18a9af3488
Merge pull request #17291 from BerriAI/litellm_fix_correct_attribute_error_code_raise
...
Fix 500 error for malformed request
2025-12-02 22:17:48 +05:30
Ishaan Jaff
1bb9e1bde8
[Feat] Add vllm batch+files API support ( #15823 )
...
* add OPENAI_COMPATIBLE_BATCH_AND_FILES_PROVIDERS
* fix use OPENAI_COMPATIBLE_BATCH_AND_FILES_PROVIDERS
* add _get_batch_job_total_usage_from_file_content
* fixes for vLLM + 12 labs async invoke
* fix: vLLM Batch APIs
* afile_retrieve
* test_hosted_vllm_full_workflow
* fix SERVER_URL for test
2025-12-02 08:41:50 -08:00
Sameer Kankute
2201e12acc
Fix import error
2025-12-02 22:08:23 +05:30
Ishaan Jaffer
fe03833d3b
test_vertex_ai_bge_psc_endpoint_url_construction
2025-12-02 21:59:53 +05:30
Ishaan Jaffer
bfa7f12d4c
fix get_vertex_base_model_name
2025-12-02 21:59:53 +05:30
Ishaan Jaffer
87b75afe12
fix VertexAIGemmaModels
2025-12-02 21:59:53 +05:30
