scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-06 08:16:43 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 178
31415 commits 4106 branches 1402 tags 4.2 GiB
Commit graph

693 commits

Author SHA1 Message Date
Ishaan Jaffer
8b575f4656 test_bedrock_nova_grounding_web_search_options_non_streaming 2026-01-31 11:23:48 -08:00
Ishaan Jaff
5345a763c2
[Feat] v2 - Logs view with side panel and improved UX (#20091) 
* init: azure_ai/azure-model-router

* show additional_costs in CostBreakdown

* UI show cost breakdown fields

* feat: dedicated cost calc for azure ai

* test_azure_ai_model_router

* docs azure model router

* test azure model router

* fix transfrom

* Add transform file

* fix:feat: route to config

* v0 - looks decen view

* refactored code

* fix ui

* fixes ui

* complete v2 viewer

* address feedback

* address feedback
 2026-01-30 18:34:13 -08:00
Sameer Kankute
11c2160379 Add web search tests 2026-01-30 14:56:11 +05:30
Sameer Kankute
42a0d576f3
Merge pull request #19910 from BerriAI/main 
merge 01 27
 2026-01-28 08:30:47 +05:30
Sameer Kankute
29fc4f8f61
Merge pull request #19850 from BerriAI/litellm_grok_reasonnig_support 
Add grok reasoning content
 2026-01-27 17:46:07 +05:30
Sameer Kankute
c834d7d1fe
Merge branch 'main' into litellm_oss_staging_01_27_2026 2026-01-27 17:11:15 +05:30
Sameer Kankute
9a2750f8ec
Merge pull request #19617 from BerriAI/litellm_oss_staging_01_23_2026 
Litellm oss staging 01 23 2026
 2026-01-27 16:55:32 +05:30
Sameer Kankute
e695cb5367 Add grok reasoning content 2026-01-27 16:34:57 +05:30
Sameer Kankute
13313ac2be
Merge pull request #19232 from natimofeev/fix-gigachat-function-output-format 
Fix: ensure function content is valid JSON for GigaChat
 2026-01-27 13:02:38 +05:30
Ishaan Jaffer
6710abd1fa test_web_search 2026-01-24 11:06:23 -08:00
Nikita Timofeev
e63537c6c1 Fix: ensure function content is valid JSON for GigaChat 2026-01-23 15:27:46 +00:00
Sameer Kankute
9894721285
Merge pull request #19548 from BerriAI/litellm_staging_01_22_2026 
Litellm staging 01 22 2026
 2026-01-23 20:03:11 +05:30
Sameer Kankute
a4bf14f6e7 Fix: test_nova_invoke_streaming_chunk_parsing 2026-01-23 19:49:42 +05:30
Sameer Kankute
acf5ad1155 Add tool choice mapping for giga chat 2026-01-23 16:29:19 +05:30
jquinter
0622ce3f2c
Fix/nova grounding (#19598) 
* added support for nova grounding for amazon nova model

* added citations support

* added integration tests

* removing test file

* refactor: Use web_search_options for Nova grounding instead of system_tool

---------

Co-authored-by: Juhie <juhiechandra@gmail.com>
Co-authored-by: Juhie <75068056+juhiechandra@users.noreply.github.com>
 2026-01-22 19:34:29 -08:00
Sameer Kankute
ddaf127b4a
Merge pull request #19562 from BerriAI/litellm_stop_setting 
feat: Limit stop sequence as per openai spec
 2026-01-22 19:44:56 +05:30
Sameer Kankute
110e2c69d4 Fix : test_anthropic_via_responses_api 2026-01-22 18:28:56 +05:30
Sameer Kankute
4d20c8fbc0 feat: Limit stop sequence as per openai spec 2026-01-22 17:52:13 +05:30
Sameer Kankute
9e1275b76c
Merge branch 'main' into litellm_staging_01_19_2026 2026-01-20 19:19:36 +05:30
이명현
0dfc3fad5a
Fix: bedrock invoke claude 4 optional params #19318 (#19381) 2026-01-19 19:14:58 -08:00
Jón Levy
5db0e3289a
fix(agentcore): simplify agentcore streaming (#17141) 
* fix(agentcore): simplify agentcore streaming

* fix(agentcore): move CustomStreamWrapper import to module level

The deferred imports inside streaming methods caused initialization delays
during health check requests, leading to timeouts in ECS deployments.

- Move CustomStreamWrapper import to module-level (line 19)
- Remove deferred imports from get_sync_custom_stream_wrapper (line 588)
- Remove deferred import from get_async_custom_stream_wrapper (line 747)
- Remove from TYPE_CHECKING block to use actual import

This ensures the import happens at module load time rather than during
first request processing, preventing health check endpoint blocking.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* test(agentcore): ensure sync response

* chore: upgrade boto3 to 1.40.76 in pyproject.toml

* chore: added taplo.toml

* fix(types): correct annotation type hint for MyPy compatibility

Update _convert_annotations_to_chat_format return type from
Dict[str, Any] to ChatCompletionAnnotation TypedDict to match
the Message class's expected type signature.

Co-Authored-By: Claude <noreply@anthropic.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Benedikt Óskarsson <bensi94@hotmail.com>
 2026-01-19 05:20:24 -08:00
Ishaan Jaffer
60dd04ac95 test_aiohttp_openai 2026-01-17 17:05:00 -08:00
Ishaan Jaffer
db7de13818 test_deepseek_mock_completion 2026-01-17 16:36:42 -08:00
Ishaan Jaff
d2a40c8456
[Fix] - Reliability fix OOMs with image url handling (#19257) 
* fix MAX_IMAGE_URL_DOWNLOAD_SIZE_MB

* test_image_exceeds_size_limit_with_content_length

* fix: _process_image_response

* add constants 50MB

* fix convert_to_anthropic_image_obj image handling

* test_gemini_image_size_limit_exceeded

* MAX_IMAGE_URL_DOWNLOAD_SIZE_MB fix

* MAX_IMAGE_URL_DOWNLOAD_SIZE_MB

* test_image_size_limit_disabled

* async_convert_url_to_base64

* docs fix

* code QA check

* fix Exception
 2026-01-16 16:41:44 -08:00
Yuta Saito
34e8e97222 fix: ci test 
gemini 2.5 depricated
 2026-01-17 09:17:31 +09:00
YutaSaito
ca2019776e
Revert "Fix: malformed tool call transformation in bedrock" 2026-01-17 06:04:24 +09:00
Sameer Kankute
bf99cea82f Fix malformed tool call tranform 2026-01-16 14:33:25 +05:30
John Greek
07b1f84ec6
fix(bedrock): strip throughput tier suffixes from model names (#19147) 
Co-authored-by: Greek, John <jgreek@users.noreply.github.com>
 2026-01-15 18:43:10 -08:00
Sameer Kankute
e9a2999f61 Fix: handling of model name in query param 2026-01-15 15:06:37 +05:30
Sameer Kankute
7dbf09cb12 Fix all 130126 tests 2026-01-14 17:47:03 +05:30
Sameer Kankute
ff467c797d
Merge pull request #19079 from BerriAI/main 
merge main
 2026-01-14 16:44:31 +05:30
Ishaan Jaff
1b00576711
[Feat] New Model - Azure Model Router on LiteLLM AI Gateway (#19054) 
* fix - azure model router integration

* fix:_check_provider_match

* fix:_get_response_model

* tests azure model router

* test_azure_ai_model_router_streaming_model_in_chunk

* fix LlmProviders.AZURE.value

* test_azure_ai_model_router_streaming_cost_with_stream_options

* def test_get_model_from_chunks_azure_model_router():

* _get_model_from_chunks

* docs azure model router

* azure model router
 2026-01-13 18:31:43 -08:00
Mateusz Szewczyk
72dc65fbb4
chore: allow passing scope id for watsonx inferencing (#18959) 
* chore: allow inference with space

* make lint and make format
 2026-01-14 03:47:20 +05:30
Sameer Kankute
ebf61998e0
Merge pull request #18954 from BerriAI/litellm_replicate_support 
[Feat] Add all chat replicate models support
 2026-01-12 18:15:46 +05:30
Harshit Jain
5ce3a56ac3
add better err handling for antropic (#18955) 2026-01-12 17:03:03 +05:30
Sameer Kankute
3d38ec4756 Add all replicate models in model cost map 2026-01-12 15:19:49 +05:30
Sameer Kankute
c0b05fc47a
Merge pull request #18250 from sjmatta/claude/fix-issue-17910-QBgDq 
[Fix] Nova model detection for Bedrock provider (#17910)
 2026-01-09 17:30:51 +05:30
Sameer Kankute
be28fcd463
Merge pull request #18858 from raghav-stripe/raghav-add-bedrock-tokencounter 
feat: add Bedrock as a backend API for token counting
 2026-01-09 17:10:52 +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
Raghav Jhavar
ba78194ff1 add support for bedrock in token counting api 2026-01-09 17:08:07 +07:00
Sameer Kankute
af6883712e Add tests for kimi 2 bedrock model 2026-01-08 10:07:33 +05:30
Elkhan Eminov
bae625bdc6
OpenRouter embeddings API support (#18391) 
* support for OpenRouter embeddings

* add bearer

* add content header
 2026-01-08 00:57:31 +05:30
Ishaan Jaffer
407575efb3 test_completion_bedrock_claude_aws_session_token 2026-01-07 18:09:07 +05:30
Stephen Matta
b40a6a0f6c
[Fix] Nova model detection for Bedrock provider (#17910) 
Resolves issue #17910 where Amazon Nova models (like amazon.nova-pro-v1:0)
were incorrectly identified as Amazon Titan models, causing requests to
use textGenerationConfig instead of inferenceConfig.

The fix moves the "nova" check before the initial provider check on the
split model name. This ensures that models containing "nova" (like
amazon.nova-pro-v1:0 or amazon.nova-2-lite-v1:0) are correctly identified
as Nova models, rather than matching "amazon" first.
 2026-01-06 21:12:30 -05:00
Sameer Kankute
0d050dc0ea fix:test_anthropic_beta_header 2026-01-06 14:28:30 +05:30
Sameer Kankute
8aff258a93 fix: test_databricks_embeddings[True] 2026-01-06 14:20:30 +05:30
0717376
12f02f6c54
feat: Add GigaChat provider support (#18564) 
* feat: Add GigaChat provider support

Add native support for GigaChat API (Sber AI, Russia's leading LLM).

Supported features:
- Chat completions (sync/async)
- Streaming (sync/async)
- Function calling / Tools
- Structured output via JSON schema (emulated through function calls)
- Image input (base64 and URL)
- Embeddings

Closes #18515

* fix: resolve mypy type errors in GigaChat handler

- Fix _prepare_file_data return type (use 3-tuple for cleaner type flow)
- Add type annotations for lists in _process_content_parts methods
- Add type annotations in _collapse_user_messages
- Use ChatCompletionToolCallChunk for proper tool_use typing
- Add type: ignore[override] for astreaming async generator

* refactor(gigachat): migrate to BaseConfig pattern

* fix: remove unused imports

* fix: resolve mypy type errors

* fix: mypy type errors

* refactor: address review feedback for GigaChat provider

- Remove singleton pattern, reuse litellm HTTPHandler
- Move constants/errors to transformation files, delete common_utils.py
- Add models to model_prices_and_context_window.json
- Fix ssl_verify not passed to HTTP client for embeddings

* docs: update GigaChat documentation with ssl_verify requirement
 2026-01-06 10:10:02 +05:30
ゆり
dc62cdb300
fix: handle empty error objects in response conversion (#18493) 
Some OpenAI-compatible providers (e.g., Apertis) return empty error
objects even on successful responses. The previous check only verified
that error was not None, causing spurious APIErrors.

Now the code checks if the error object contains meaningful data:
- For dict errors: non-empty message OR non-null code
- For string errors: non-empty string
- Other truthy values are still treated as errors

Fixes #18407

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: yurekami <yurekami@users.noreply.github.com>
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
 2026-01-04 00:37:52 +05:30
Sameer Kankute
c7e0366925 Add support for minmax tts 2025-12-23 21:53:53 +05:30
Alexsander Hamir
5534038e93
Fix CI: Revert security scan changes and add GitGuardian ignore rules (#18358) 2025-12-22 17:03:53 -08:00