Ishaan Jaffer
6a9041e67d
Revert "aws fix base"
...
This reverts commit 225f411abc
2026-01-10 14:08:11 -08:00
Ishaan Jaffer
6b7f114847
test_lists_with_sensitive_keys_are_masked
2026-01-10 13:55:11 -08:00
Ishaan Jaffer
ff8e9aeb5c
Revert "Add support for Vertex AI API keys"
...
This reverts commit ad501048f3
2026-01-10 13:39:49 -08:00
Ishaan Jaff
c0cf8bc27d
[Feat] Manus FILES API - Add File upload, get, delete, list ( #18904 )
...
* add MANUS get response
* init TwoStepFileUploadRequest
* init TwoStepFileUploadConfig
* add async_create_file to handle 2 step uploads
* init ManusFilesConfig
* add add get_provider_files_config MANUS
* fix validate_environment
* test_manus_files_api_e2e_all_methods
* aws fix base
* init files API MANUS
* test_manus_responses_api_with_file_upload
* mypy lint fixes
* fix BedrockFilesConfig
* manus docs
* docs manus
* mypy lint
* add add fix resposne api utils MANUS
2026-01-10 13:27:54 -08:00
Ishaan Jaffer
3c3ed3bcfb
fix resposne api utils
2026-01-10 13:25:31 -08:00
Ishaan Jaff
ab50fea663
[Fix] turn_off_message_logging Does Not Redact Request Messages in proxy_server_request Field When Stored to Database ( #18897 )
...
* update _get_proxy_server_request_for_spend_logs_payload
* test_spend_logs_redacts_request_and_response_when_turn_off_message_logging_enabled
2026-01-10 11:28:21 -08:00
Sameer Kankute
cb03e5a6dd
Merge pull request #18852 from BerriAI/litellm_add_ssl_verify_bedrock
...
[Bug]: Add Custom CA certificates to boto3 clients
2026-01-10 11:41:32 +05:30
yuneng-jiang
dfb298792c
New endpoint for router fields + react query
2026-01-09 16:49:22 -08:00
YutaSaito
07db8fe656
Merge pull request #18855 from BerriAI/litellm_fix_mcp-error-in-multiple-server
...
[fix] mcp error in multiple servers
2026-01-10 07:26:16 +09:00
yuneng-jiang
c29d042df4
Case insensitive email login
2026-01-09 12:51:00 -08:00
Sameer Kankute
0c7db97ad5
Merge pull request #18871 from BerriAI/litellm_fix_test_count_tokens_caching
...
Fix :test_count_tokens_caching
2026-01-10 01:20:55 +05:30
Harshit Jain
8a683d9a6a
Add fix for bedrock_cache, metadata and max_model_budget ( #18872 )
2026-01-10 01:09:00 +05:30
Sameer Kankute
777ae4f530
Fix :test_count_tokens_caching
2026-01-10 00:57:11 +05:30
Shivam Rawat
43dd0e6ef5
remove model before casting it in the transformation ( #18810 )
2026-01-10 00:43:38 +05:30
Cesar Garcia
c19c97591e
fix: align max_tokens with max_output_tokens for consistency ( #18820 )
...
* fix: align max_tokens with max_output_tokens for consistency
Fixed inconsistent max_tokens definitions in model_prices_and_context_window.json.
According to LiteLLM convention, max_tokens should equal max_output_tokens when available.
Models fixed:
- deepseek-chat: 131072 → 8192 (now equals max_output_tokens)
- dashscope/qwen-flash: 1000000 → 32768 (now equals max_output_tokens)
- databricks/databricks-gemma-3-12b: 128000 → 32000 (now equals max_output_tokens)
This ensures consistency across all providers where max_tokens represents
the maximum number of tokens that can be generated in the output.
* fix: align max_tokens with max_output_tokens for 244 models
- Fix 244 models where max_tokens != max_output_tokens
- Add test to validate max_tokens consistency and prevent regressions
According to model_prices_and_context_window.json spec:
- max_tokens is a LEGACY parameter
- Should always equal max_output_tokens when both are present
This ensures consistency across all model definitions.
2026-01-10 00:37:45 +05:30
Sameer Kankute
8dac83e093
Merge pull request #18859 from BerriAI/litellm_azure_image_gen_fix
...
Fix: response_format leaking into extra_body
2026-01-09 23:09:27 +05:30
Andrés
9768eca33e
fix(azure): add logprobs support for Azure OpenAI GPT-5.2 model ( #18856 )
...
* fix(azure): add logprobs support for Azure OpenAI GPT-5 models
Azure OpenAI GPT-5 models (including gpt-5.2) support logprobs
parameters, unlike OpenAI's GPT-5 reasoning models. This fix
overrides the parent class restriction to enable logprobs for Azure.
Changes:
- Override get_supported_openai_params() in AzureOpenAIGPT5Config
- Add "logprobs" and "top_logprobs" to supported params
- Add comprehensive tests for logprobs functionality
Testing:
- Verified with direct Azure API calls to gpt-5.2
- API version: 2025-01-01-preview
- Successfully returns logprobs data
Related: #7974 , #4022
* refactor: restrict logprobs support to gpt-5.2 only
Only gpt-5.2 has been verified to support logprobs on Azure.
Other gpt-5 variants (gpt-5, gpt-5.1) have not been tested.
Changes:
- Add conditional check for is_model_gpt_5_2_model()
- Update tests to be specific to gpt-5.2
- Add negative tests for gpt-5 and gpt-5.1
- Update documentation to reflect gpt-5.2 specificity
2026-01-09 22:57:50 +05:30
Harshit Jain
819468554f
fix(security): prevent expired key plaintext leak in error response ( #18860 )
2026-01-09 22:27:39 +05:30
Sameer Kankute
e7efd51bd7
Merge branch 'main' into litellm_staging_01_06_2026
2026-01-09 17:06:17 +05:30
Sameer Kankute
bb9347207b
Merge pull request #18833 from BerriAI/litellm_staging_01_08_2026
...
Litellm staging 01 08 2026
2026-01-09 17:04:29 +05:30
Sameer Kankute
844c766c65
Merge pull request #18763 from BerriAI/litellm_staging_01_07_2026
...
Staging - 01/07/2026
2026-01-09 17:01:58 +05:30
Sameer Kankute
ffa0d6706c
Fix: response_format leaking into extra_body
2026-01-09 16:53:35 +05:30
Yuta Saito
5927a557fb
tests: add test
2026-01-09 17:25:21 +09:00
Justas Brazauskas
c0ee5da444
Fix: Add thought_signatures to VertexGeminiConfig and test
2026-01-09 10:03:45 +02:00
Sameer Kankute
c6101ef977
[Bug]: Add Custom CA certificates to boto3 clients
2026-01-09 12:30:36 +05:30
Yuta Saito
022db6c9ed
feat: add mcp registry
2026-01-09 15:07:39 +09:00
Sameer Kankute
d9b275e62a
Merge pull request #18806 from BerriAI/litellm_vertex_ai_api_key_support
...
[FEAT]: Add support for Vertex AI API keys
2026-01-09 09:44:36 +05:30
Yuta Saito
48bc5ccb4f
fix: test
2026-01-09 11:23:47 +09:00
Yuta Saito
f129f598a0
fix: how to execute cloudzero sql
2026-01-09 10:52:48 +09:00
YutaSaito
661f03058c
Merge pull request #18802 from BerriAI/litellm_feat_focus_backend
...
[feat] Focus export support
2026-01-09 07:21:04 +09:00
yuneng-jiang
1b9c7deec6
Merge remote-tracking branch 'origin' into litellm_key_team_routing_3
2026-01-08 10:39:12 -08:00
yuneng-jiang
864e8c6543
Merge pull request #18775 from BerriAI/litellm_fs_callback_fix
...
[Fix] Normalize Proxy Config Callback
2026-01-08 10:37:21 -08:00
Harshit Jain
516e4f8b96
fix: proactive RDS IAM token refresh to prevent 15-min connection failed ( #18795 )
...
* fix: proactive RDS IAM token refresh to prevent 15-min connection failures (#16220 )
* fix: add noqa for PLR0915 in proxy_startup_event
2026-01-08 23:53:36 +05:30
Cesar Garcia
2ef8bbdf6a
fix: add xiaomi_mimo to LlmProviders enum to fix router support ( #18819 )
...
Added XIAOMI_MIMO to the LlmProviders enum in types/utils.py.
The provider was already configured in providers.json but was
missing from the enum, causing "Unsupported provider" errors
when using it in Router/Proxy configurations.
Also added comprehensive unit tests to prevent regression.
2026-01-08 23:45:57 +05:30
Cesar Garcia
1c1ee8de46
Mask extra header secrets in model info ( #18822 )
2026-01-08 23:42:05 +05:30
Chongshun
60edf13a21
feat(tag-routing): support toggling tag matching between ANY and ALL ( #18776 )
2026-01-08 23:39:03 +05:30
Constantine
3ebec39b74
fix(proxy): use async anthropic client to prevent event loop blocking ( #18435 )
...
Fixes #16716 .
Previously, synchronous Anthropic client was used for token counting, which blocked the event loop.
This change switches to AsyncAnthropic and caches the client instance.
2026-01-08 23:26:46 +05:30
Ishaan Jaff
b482d336b3
[Feat] New provider - Manus API on /responses, GET /responses ( #18804 )
...
* init ManusResponsesAPIConfig
* init MANUS ApI
* init MANUS create responses
* init MANUS
* test_extract_agent_profile
* transform_get_response_api_request
* test fix
* fixes non stream
* fix streaming
* add MANUSConfig
* test_multiturn_responses_api
* code QA check
* add manus
* Potential fix for code scanning alert no. 3961: Clear-text logging of sensitive information
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
2026-01-08 18:37:42 +05:30
Sameer Kankute
5241b27bea
fix: test_video_status_basic
2026-01-08 17:30:58 +05:30
Sameer Kankute
f5b5073649
fix: test_video_status_async
2026-01-08 17:20:38 +05:30
Sameer Kankute
62d860ea7d
fix: litellm/tests/test_litellm/test_responses_id_security.py
2026-01-08 17:01:44 +05:30
Sameer Kankute
0a9861c3ec
Fix: test_token_counter_lazy_imports
2026-01-08 16:44:35 +05:30
Sameer Kankute
9d5eb60ff1
Fix: test_text_format_to_text_conversion - properly mock handler to avoid API calls
2026-01-08 16:37:12 +05:30
Sameer Kankute
b6e011309a
Fix: test_spend_logs_payload_success_log_with_router
2026-01-08 16:07:00 +05:30
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
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
c05e148488
Merge pull request #18809 from BerriAI/main
...
merge main
2026-01-08 15:28:13 +05:30
