Commit Graph
28563 Commits
Author SHA1 Message Date
yuneng-jiang ca11264bbf Fixing sendgrid integration 2025-12-10 20:31:33 -08:00
yuneng-jiang 439d42ba67 bump: version 0.1.24 → 0.1.25 2025-12-10 18:26:07 -08:00
yuneng-jiang 3d7c6cb690 Merge remote-tracking branch 'origin' into litellm_sendgrid 2025-12-10 10:42:47 -08:00
saisurya237andGitHub f3ead2c153 add a new feature fix to expose the team alias when authenticating th… (#17725)
* CLI SSO: show team aliases in team selection

* temp poetry lock fix

* add poetry.lock to gitignore

* Revert proxy_server background job refactor

* Revert proxy_server background job refactor

* rever gitignore and poetry lock file
2025-12-10 10:10:28 -08:00
yuneng-jiangandGitHub ba554a86b9 Merge pull request #16843 from BerriAI/litellm_allow_custom_mount_paths
[Feature] Allow Root Path to Redirect when Docs not on Root Path
2025-12-10 09:52:30 -08:00
Sameer KankuteandGitHub dea62e3f60 Merge pull request #17769 from BerriAI/litellm_test_fix
Fix nvdia and geminin tests
2025-12-10 22:29:04 +05:30
Sameer KankuteandGitHub ad45fc7cce Merge pull request #17770 from BerriAI/litellm_deepseek_v3.2
Add DeepSeek-V3.2 model support
2025-12-10 22:28:50 +05:30
Sameer KankuteandGitHub 4c78c1afc8 Merge pull request #17756 from BerriAI/litellm_add_gemini_computer_use
Add support for computer use for gemini
2025-12-10 22:28:37 +05:30
Sameer Kankute 05a82ae570 Add support for deepseek v3.2 2025-12-10 22:21:04 +05:30
Sameer Kankute ec30032bc3 Fix nvdia and geminin tests 2025-12-10 22:05:11 +05:30
Sameer KankuteandGitHub 0d2f8ce931 Merge pull request #17711 from BerriAI/litellm_add_additional_drop_params_support
feat: Add nested field removal support to additional_drop_params
2025-12-10 15:37:39 +05:30
Lucas SugiandGitHub c7fd8fabdb fix: Avoid error when we have just the tool_calls in input (#17753)
* fix: Avoid error when we have just the tool_calls in input

* fix: Remove the tool call validation

* feat: Add unit test
2025-12-09 22:59:59 -08:00
Krish DholakiaandGitHub b0a5a4b81d Arize Phoenix OSS - Prompt Management Integration (#17750)
* docs(prompt_management.md): document how to onboard prompts to litellm

* feat(arize_phoenix_prompt_manager.py): support new prompt management integration

allows users to connect arize phoenix prompt manager to litellm

* fix(proxy/utils.py): remove prompt variables to avoid re-processing prompt

* docs(arize_phoenix_prompts.md): document new prompt management integration
2025-12-09 22:53:42 -08:00
Sameer Kankute bcac9e41f6 Add support for computer use for gemini 2025-12-10 10:34:08 +05:30
yuneng-jiang 0769a290da Sendgrid integration + bump enterprise package 2025-12-09 19:34:09 -08:00
yuneng-jiang b5763d27eb bump: version 0.1.23 → 0.1.24 2025-12-09 19:31:12 -08:00
Ishaan JaffandGitHub e546f0e021 [Fix] UI SSO - allow up-serting user role when SSO provider role changes (#17754)
* use _build_sso_user_update_data

* test_build_sso_user_update_data_with_valid_role
2025-12-09 19:16:10 -08:00
Peter ChanthamynavongandGitHub 539ce89d4e fix(guardrails): mask all regex pattern matches, not just first (#17727)
Before: search() + replace() only replaced first match
After: sub() replaces all matches of each pattern

Closes #17687
2025-12-09 18:51:28 -08:00
Cesar GarciaandGitHub b4e0dabb37 fix: use absolute URL for Supported Endpoints link to avoid Docusaurus slug conflict (#17710)
The relative link was causing Docusaurus to incorrectly associate the
/supported_endpoints page with SDK Functions category instead of the
actual Supported Endpoints generated-index.
2025-12-09 18:49:49 -08:00
82f0c3c887 Support model names with slashes on Gemini endpoints (#17743)
* Support model names with slashes on Gemini endpoints

* Fix test

* Update tests/proxy_unit_tests/test_google_endpoint_routing.py

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

* Update tests/proxy_unit_tests/test_google_endpoint_routing.py

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

* Update tests/proxy_unit_tests/test_google_endpoint_routing.py

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

* Update tests/proxy_unit_tests/test_google_endpoint_routing.py

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

* Update tests/proxy_unit_tests/test_google_endpoint_routing.py

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

* Update tests/proxy_unit_tests/test_google_endpoint_routing.py

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

---------

Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-12-09 18:40:51 -08:00
Krrish Dholakia 8b125ff74e test: remove test_helicone - integration test made live calls to api and broke ci/cd 2025-12-09 18:36:51 -08:00
254c1155a2 Remove streaming_logging.md documentation (#17739)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2025-12-09 18:26:08 -08:00
Cesar GarciaandGitHub 01dec55c2f fix(anthropic): preserve server_tool_use and web_search_tool_result in multi-turn conversations (#17746)
- Extract web_search_tool_result blocks in extract_response_content()
- Store web_search_results in provider_specific_fields for round-trip
- Detect srvtoolu_ prefix to reconstruct as server_tool_use (not tool_use)
- Add corresponding web_search_tool_result after server_tool_use blocks

This ensures multi-turn conversations with Anthropic web search + custom
tools work correctly without Anthropic expecting tool_result for server-
side tool executions.
2025-12-09 18:25:23 -08:00
9fa6c51678 Fix: Add Gemini context window exception mapping (#17751)
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2025-12-09 18:24:13 -08:00
Krrish Dholakia f23a78fddc test: remove expensive test 2025-12-09 18:23:03 -08:00
Krrish Dholakia c276a87ab0 fix(anthropic/chat/transformation.py): pass output_config + thinking to claude opus 4.5 2025-12-09 18:21:41 -08:00
Sameer KankuteandGitHub 8fafd81f9d Merge pull request #17732 from BerriAI/litellm_videos_bugs_2
Fix : use litellm params for all videos apis
2025-12-10 07:49:55 +05:30
Krrish Dholakia d3531be9a0 docs(community.md): add new integration partner doc 2025-12-09 18:17:14 -08:00
Ishaan JaffandGitHub 42f5770cfa [docs] add docs for containers files api + code interpreter on LiteLLM (#17749)
* add new container api on OpenAI

* add related

* docs fix

* docs code interpreter

* code interp

* docs code interptert

* docs code int

* docs code interp

* docs code interp
2025-12-09 18:11:28 -08:00
Shivam RawatandGitHub 4ada6bee49 fixed flex tier pricing (#17748) 2025-12-09 18:10:51 -08:00
8d5e6cc62d Add community doc link (#17734)
* Add community contribution guide for integration partners

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

* Update community docs to direct users to #integration-partners

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

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2025-12-09 18:10:00 -08:00
Cesar GarciaandGitHub 63a97db663 feat(voyage): add rerank API support (#17744)
* feat(voyage): add rerank API support

Add support for Voyage AI rerank models (rerank-2.5, rerank-2.5-lite,
rerank-2, rerank-2-lite) to the LiteLLM rerank API.

Changes:
- Add VoyageRerankConfig transformation class
- Register voyage provider in rerank_api/main.py
- Add voyage case in utils.py get_provider_rerank_config
- Add rerank-2.5 and rerank-2.5-lite models to pricing JSON
- Add unit tests for transformation logic
- Update documentation for voyage.md and rerank.md

Usage:
```python
from litellm import rerank

response = rerank(
    model="voyage/rerank-2.5",
    query="What is the capital of France?",
    documents=["Paris is...", "London is..."],
    top_n=3,
)
```

* refactor(voyage): simplify rerank transformation code

Remove verbose docstrings to align with other providers (jina_ai pattern).
No functional changes - 168 lines vs 169 for jina_ai.

* fix(voyage): remove incorrect input_cost_per_query from rerank models

Voyage AI charges per token, not per query. The input_cost_per_query
field was incorrectly set to the same value as input_cost_per_token
in the existing rerank-2 and rerank-2-lite models.

Removes input_cost_per_query from all Voyage rerank models:
- voyage/rerank-2
- voyage/rerank-2-lite
- voyage/rerank-2.5
- voyage/rerank-2.5-lite

Pricing source: https://docs.voyageai.com/docs/pricing
2025-12-09 17:34:09 -08:00
Ishaan JaffandGitHub 3631e8fa1d [Feat] Containers API - add new container API file management + UI Interface (#17745)
* test_router_acreate_container_without_model

* _init_containers_api_endpoints

* test_init_containers_api_endpoints

* init container files endpoints

* init files api

* init container files API

* add containers api file content

* add code interpreter output UI

* add code interpreter input ui

* refactor code interpreter ui

* fix: require model selection

* cleaner container provision

* fix ContainerFileObject

* def container_file_content_handler(
add

* add retrieve_container_file_content

* aretrieve_container_file_content

* UI fix model

* fix linting errors
2025-12-09 17:33:26 -08:00
Ishaan JaffandGitHub 142567e143 [Fix] Containers API - Allow using LIST, Create Containers using custom-llm-provider (#17740)
* test_router_acreate_container_without_model

* _init_containers_api_endpoints

* test_init_containers_api_endpoints
2025-12-09 17:00:35 -08:00
yuneng-jiang d99cf81386 Fixing test 2025-12-09 16:11:17 -08:00
yuneng-jiangandGitHub 9a7831dd33 Merge pull request #17697 from BerriAI/litellm_ui_settings_ui
[Feature] UI - UI Settings
2025-12-09 15:58:08 -08:00
ephrimstanleyandGitHub a91dda1194 Return 403 instead of 503 for unauthorized routes (#17723) 2025-12-09 15:16:11 -08:00
Krrish Dholakia cc8a46b6b2 bump: version 1.80.9 → 1.80.10 2025-12-09 14:55:43 -08:00
yuneng-jiangandGitHub bdfc3308b1 Merge pull request #17741 from BerriAI/litellm_ui_cred_fix_2
[Fix] Change credential encryption to only affect db credentials
2025-12-09 14:04:20 -08:00
Alexsander HamirandGitHub 9a0432d013 [Fix] Perf - Reduce memory accumulation of spend_logs (#17742)
Replaces time-based spend log processing with a queue-size-based approach to improve performance and reduce memory usage. The new implementation:

- Adds background task that monitors spend_log_transactions queue size
- Triggers processing when queue reaches configurable threshold (default: 100)
- Implements exponential backoff when queue is idle to reduce CPU usage
- Increases batch processing limits (BATCH_SIZE: 100→1000, MAX_LOGS_PER_INTERVAL: 1000→10000)
- Adds configurable environment variables: SPEND_LOG_QUEUE_SIZE_THRESHOLD, SPEND_LOG_QUEUE_POLL_INTERVAL

This approach prevents unbounded queue growth while reducing unnecessary polling overhead.
2025-12-09 14:00:34 -08:00
yuneng-jiang 879ae45421 Change credential encryption to only affect db credentials 2025-12-09 13:36:40 -08:00
YutaSaitoandGitHub 80a18f989a feat: propagate Langfuse trace_id (#17669) 2025-12-09 12:25:52 -08:00
yuneng-jiang 39bf7a9f7c Merge remote-tracking branch 'origin' into litellm_allow_custom_mount_paths 2025-12-09 11:58:05 -08:00
yuneng-jiangandGitHub 9253a9c365 Merge pull request #17689 from BerriAI/litellm_ui_settings_backend
[Feature] Get and Update Backend Routes for UI Settings
2025-12-09 11:55:28 -08:00
Shivam RawatandGitHub 43a7bbeeaf added note for using Azure Active Directory Tokens with all the other endpoints (#17733) 2025-12-09 11:51:28 -08:00
yuneng-jiangandGitHub aa450e7ebe Merge pull request #17738 from BerriAI/litellm_doc_update_1805
[Docs] Adding known issues to 1.80.5-stable docs
2025-12-09 11:46:08 -08:00
yuneng-jiang 431884f591 Adding known issues to 1.80.5-stable docs 2025-12-09 11:45:16 -08:00
yuneng-jiang 1b86269584 Bump version to include new schema 2025-12-09 11:25:24 -08:00
yuneng-jiang 7957244367 bump: version 0.4.11 → 0.4.12 2025-12-09 11:24:18 -08:00
yuneng-jiang 36183c3a9b Adding migration 2025-12-09 11:23:26 -08:00