1237be04a5
test_aaamodel_prices_and_context_window_json_is_valid
2025-09-04 07:58:20 -07:00
a8cce5fbf3
Merge pull request #14237 from yeahyung/fix/tpm_limit_bug
...
Fixes #14204 TPM Rate Limit Bug
2025-09-04 07:29:47 -07:00
25afa67616
fix: Key Budget not resets at expectable times
2025-09-04 09:04:01 +00:00
7829de2948
( #14204 ) add test code
2025-09-04 16:41:29 +09:00
23ae7170d1
[Feat] Allow using Veo Video Generation through LiteLLM Pass through routes ( #14228 )
...
* fix: add follow_redirects=True,
* test_pass_through_with_httpbin_redirect
* cook book veo video
* docs Veo Video Generation with Google AI Studio
* add veo-3.0-generate-preview cost tracking details
* track vertex_video_models
2025-09-03 18:25:43 -07:00
be7c762882
add video_generation
2025-09-03 18:25:27 -07:00
19e2bab8c8
[Feat] Add Initial support for Bedrock Batches API ( #14190 )
...
* fix acreate_file with bedrock
* fix routing to bedrock batches api
* fix create_file
* working batch file upload
* fix batches API for file upload
* test: bedrock files and batches API
* add BaseBatchesConfig
* fix get_provider_batches_config
* transform bedrock batches
* fix run create batch through llm http handler
* test_async_file_and_batch
* main.batches creation
* fix: CommonBatchFilesUtils
* fix async_create_batch
* test_async_file_and_batch
* BedrockBatchesConfig
* fix ruff check
* ruff check fix
* fix docs ref
2025-09-03 17:19:58 -07:00
beb300abae
[Fix] SCIM - Bug fixes for handling SCIM Group Memberships ( #14226 )
...
* Feat: add better SCIM debugging
* fix _get_scim_member_display
* fix patch_group
* test_update_group_e2e
* test_get_scim_member_value
2025-09-03 16:15:51 -07:00
8e9352fce7
test fix
2025-09-03 11:06:09 -07:00
ca43514db4
[Feat] Support reasoning_effort in Groq ( #14207 )
...
* Support reasoning_effort in groq
* add test
2025-09-03 10:43:47 -07:00
63c4a30564
TestVertexAIGPTOSSTransformation
2025-09-02 23:07:52 -07:00
35b501b8d5
Merge pull request #14176 from mjmendo/feat/alert_type_in_slack_message
...
feat: added alert type to alert messate to slack for easier handling
2025-09-02 23:05:41 -07:00
dc0d2a44a5
Merge pull request #14171 from kutsushitaneko/fix/14158_tool_call_id
...
fix(oci): Handle assistant messages with both content and tool_calls in OCI provider (#14158 )
2025-09-02 23:05:04 -07:00
c8b177963e
Merge pull request #14191 from kayoch1n/fix-h11-model-name
...
Remove "/" or ":" from model name when being used as h11 header name
2025-09-02 23:02:45 -07:00
76555cad81
Format code
2025-09-03 11:20:52 +08:00
ffbe5cd899
Add a testcase
2025-09-03 11:08:23 +08:00
46655544a4
Merge pull request #14179 from zhirafovod/otel_logs_metrics
2025-09-02 19:50:40 -07:00
128d9a3488
[Feature]: Add header support for spend_logs_metadata ( #14186 )
...
* fix: allow settings spend_logs_metadata
* fix add_litellm_data_for_backend_llm_call
* fix: add add_litellm_metadata_from_request_headers
* fix add_litellm_metadata_from_request_headers
* test_add_litellm_metadata_from_request_headers
* add_litellm_metadata_from_request_headers
* docs Tracking Spend with custom metadata
* add_litellm_metadata_from_request_headers
* add_litellm_metadata_from_request_headers
2025-09-02 15:13:15 -07:00
c821f1ddf1
[Feature]: Support GPT-OSS models on vertex ai ( #14184 )
...
* add VertexAIGPTOSSTransformation
* fix: optional_params
* fix: is_vertex_partner_model
* test_partner_models_httpx
* docs GPT oss docs
* test_vertex_ai_gpt_oss_reasoning_effort
* add vertex ai models
2025-09-02 14:15:26 -07:00
4adfd18bc6
[Feat]Add support for safety_identifier parameter in chat.completions.create ( #14174 )
...
* Add support for safety_identifier parameter in chat.completions.create
* make sure param is getting actually passed to the raw api
2025-09-02 09:37:08 -07:00
db1b418b15
fix: update alert type formatting to handle enum names in Slack messages
2025-09-02 17:54:54 +02:00
5dcdbb35da
add metrics and logs (events) with semconv attributes
2025-09-02 09:20:25 -06:00
92f631d57c
fix: correct formatting of alert messages in Slack notifications
2025-09-02 15:12:11 +00:00
61b2209827
test_proxy_function_calling_support_consistency
2025-09-02 07:22:52 -07:00
c7109609fd
renamed unit test code
2025-09-02 19:11:37 +09:00
ae3931f5f3
FIx https://github.com/BerriAI/litellm/issues/14158
2025-09-02 18:32:45 +09:00
82d6c4d5b1
Merge branch 'main' into litellm_dev_08_31_2025_p1
2025-09-01 22:42:53 -07:00
6d36219a4d
Merge pull request #14122 from BerriAI/litellm_dev_08_30_2025_p1
...
Braintrust - fix logging when OTEL is enabled + Gemini - add 'thoughtSignature' support via 'thinking_blocks'
2025-09-01 22:42:12 -07:00
d2c519f005
Merge pull request #14133 from retanoj/fix/gemini-token-count
...
Fix token count error for gemini cli
2025-09-01 22:39:51 -07:00
20811372d8
Revert "Merge pull request #14126 from TomeHirata/citation-supported-text-2"
...
This reverts commit 3f2881cd6d04f9ff16c4
2025-09-01 20:24:14 -07:00
d37be48a80
test: llama-3.3-70b-versatile
2025-09-01 20:14:12 -07:00
3f2881cd6d
Merge pull request #14126 from TomeHirata/citation-supported-text-2
...
Add supported text field to anthropic citation response
2025-09-01 19:22:52 -07:00
67450feb79
Merge pull request #14146 from ProjectAlita/gpt_5_unsupported_params
...
GPT-5: Drop unsupported params
2025-09-01 18:54:49 -07:00
8e72f991cc
test_model_alias_map
2025-09-01 17:59:40 -07:00
4a422ca897
fix: support logging dynamic metadata values to braintrust
2025-09-01 17:38:15 -07:00
4c7b3e10ed
[Bug Fix] Gemini Tool Calling - fix gemini empty enum property ( #14155 )
...
* fix: _convert_schema_types
* fix recursive detector
* test_convert_schema_types_type_array_conversion
* fix: DEFAULT_NUM_WORKERS_LITELLM_PROXY
* add _fix_enum_empty_strings
* test_tool_call_with_empty_enum_property
* test_fix_enum_empty_strings
* fix _fix_enum_empty_strings
2025-09-01 17:05:01 -07:00
7656cb3d6e
test fix
2025-09-01 17:04:47 -07:00
2331fb45d5
[Bug]: Gemini 2.5 Pro – schema validation fails with OpenAI-style type arrays in tools ( #14154 )
...
* fix: _convert_schema_types
* fix recursive detector
* test_convert_schema_types_type_array_conversion
* fix: DEFAULT_NUM_WORKERS_LITELLM_PROXY
2025-09-01 16:53:20 -07:00
98d57b5d27
[Feat] Allow using x-litellm-stream-timeout header for stream timeout in requests ( #14147 )
...
* fix: allow passing stream_timeout header
* fix: _get_stream_timeout_from_request
* test_add_litellm_data_to_request_with_stream_timeout_header
* docs: LiteLLM Headers
* test_add_litellm_data_to_request_with_stream_timeout_header
2025-09-01 15:59:14 -07:00
58b713d19d
[Bug fix] Misclassified 500 error on invalid image_url in /chat/completions request ( #14149 )
...
* add ImageFetchError
* docs ImageFetchError
* fix ImageFetchError
* test_completion_with_invalid_image_url
2025-09-01 15:26:27 -07:00
c51665ec9c
fix xai cost calculation ( #14127 )
2025-09-01 11:31:56 -07:00
76dd9d8110
GPT-5: Test for unsupported params
2025-09-01 20:30:43 +03:00
002c2f16dc
fix token count error when proxy gemini cli to openai like model
2025-09-01 20:02:53 +08:00
1ac7f875c9
fix test
2025-09-01 17:21:47 +09:00
e334f48699
Add supported text field to anthropic citation response
2025-09-01 16:46:54 +09:00
2ad77d9bf6
feat(ollama/completion): output parse thinking content on streaming + non-streaming for ollama completion calls
...
Completes 'thinking' param support for ollama
2025-08-31 21:17:10 -07:00
b6f6dc5c1c
feat(vertex_ai.py): support parsing thinking content into gemini format
...
allows function calls with thought signatures to be sent back to gemini
Closes https://github.com/BerriAI/litellm/pull/13842
2025-08-30 18:49:34 -07:00
51c73dc60b
fix(vertex_and_google_ai_studio_gemini.py): bubble up thoughtsignature back to client
2025-08-30 17:26:18 -07:00
34275ab273
Revert "Merge pull request #14005 from moshemorad/bedrock_fix_structure_output"
...
This reverts commit 75c327cb9eafa687182a
2025-08-30 13:37:10 -07:00
48d3aad68f
test_caching_with_models_v2
2025-08-30 13:21:14 -07:00
Ishaan Jaff