scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-09 03:18:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 108
29695 commits 3347 branches 1448 tags 5 GiB
Commit graph

29695 commits

This branch
This branch
All branches
Author SHA1 Message Date
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
yuneng-jiang
6078f4687e
Merge pull request #18732 from BerriAI/litellm_ui_build_fix_3 
[Infra] Fixing UI Build
 2026-01-06 17:22:34 -08:00
yuneng-jiang
ae7df51e69 Fixing e2e 2026-01-06 17:06:48 -08:00
yuneng-jiang
8878b43466 Adding timeout for flaky test 2026-01-06 16:56:54 -08:00
YutaSaito
c6b1e0512f
Merge pull request #18726 from gkarthi-signoz/main 
[Docs]: Adding SigNoz integration to observability docs
 2026-01-07 09:47:18 +09:00
yuneng-jiang
874e8d1a6e Fixing build 2026-01-06 16:33:08 -08:00
Goutham Karthi
2865b17988 adding signoz integration to observability docs 2026-01-06 15:29:44 -08:00
Alexsander Hamir
bb4c01ffa0
Add LITELLM_DISABLE_LAZY_LOADING env var to fix VCR cassette creation issue (#18725) 2026-01-06 14:49:11 -08:00
Otavio Brito
18ca6b2add
Handle not supported region for vertex ai count tokens - v1/messages/count_tokens (#18665) 
* Handle not supported region for vertex ai count tokens

* add unit test
 2026-01-07 00:05:00 +05:30
Lundin Matthews
762345172c
Add LlamaGate as a new provider (#18673) 
Adds LlamaGate (https://llamagate.dev) as an OpenAI-compatible provider with:
- Provider configuration in providers.json
- Documentation page with usage examples
- Model pricing for 17 models across categories:
  - General purpose (Llama 3.1/3.2, Mistral, Qwen, Dolphin)
  - Reasoning (DeepSeek R1, OpenThinker)
  - Code (Qwen Coder, DeepSeek Coder, CodeLlama)
  - Vision (Qwen VL, LLaVA, Gemma 3)
  - Embeddings (Nomic, Qwen3 Embedding)

Provider details:
- Base URL: https://api.llamagate.dev/v1
- Auth: Bearer token via LLAMAGATE_API_KEY
- Pricing: $0.02-$0.55 per 1M tokens
- All models are open-weights
 2026-01-07 00:00:30 +05:30
Lize Cai
fe9b05e23e
Add header for SAP AI Core Tracking (#18714) 
Signed-off-by: Lize Cai <lize.cai@sap.com>
 2026-01-06 23:59:02 +05:30
Rohit Ravikant Rane
a7c39ccc12
fix(router): correct num_retries tracking in retry logic (#18712) 
* fix(router): correct num_retries tracking in retry logic

- Fix off-by-one error in num_retries attribute when retries exhausted
- Correct remaining_retries calculation
- Add comprehensive tests for retry tracking edge cases

Fixes incorrect retry count in error messages and logging

* chore: trigger CI re-run

* chore: trigger CI tests again
 2026-01-06 23:58:41 +05:30
Kazuki Matsumaru
26bdf7b7a8
Remove redundant comments about setting litellm.callbacks (#18711) 
- Removed duplicate comment in test_router_endpoints.py
- Removed duplicate comment in logging.md
- Kept clearer comment: 'Set litellm.callbacks = [proxy_handler_instance] on the proxy'
 2026-01-06 23:58:01 +05:30
Isaac Reis
a17757159c
add amazon.nova-2-multimodal-embeddings-v1:0 to model_prices_and_context_window.json (#18710) 2026-01-06 23:57:35 +05:30
Pascal Bro
cac2a8d158
Fix/gcs cache docs missing for proxy mode (#13328) 
* fixed issues with gcs cache to verify functionality

* restore changes

* Fix capitalization of 'S3 Bucket Cache'

---------

Co-authored-by: Nelson Alfonso <45660392+Dashing-Nelson@users.noreply.github.com>
 2026-01-06 23:49:08 +05:30
Kris Xia
5e00a49e7f
fix(streaming): normalize status code extraction to prevent 4xx errors from triggering mid-stream fallback (#18698) 
在流式处理错误时，添加状态码标准化逻辑，确保 4xx 客户端错误直接抛出而不是被包装成 MidStreamFallbackError。

- 新增 _normalize_status_code 函数用于从异常对象提取状态码
- 优先从异常的 status_code 属性获取，其次从 response.status_code 获取
- 当映射异常或原始异常的状态码在 400-499 范围内时，直接抛出映射异常
- 添加单元测试验证 Vertex AI 400 错误正确抛出为 BadRequestError
- 确保流式处理中的客户端错误能够正确传播，而不会触发回退机制
 2026-01-06 23:41:23 +05:30
Ishaan Jaff
69aa111fdd
[UI] - Feat add request provider form on UI (#18704) 
* add request provider form

* fix link to github

* add button

* fix link
 2026-01-06 18:54:57 +05:30
Sameer Kankute
ce0f71fbe9
Merge pull request #18706 from BerriAI/litellm_fix_reasoning_summary_default 
[Bug] fix model map
 2026-01-06 18:31:33 +05:30
Sameer Kankute
0cd92e895f fix model map 2026-01-06 18:14:00 +05:30
Sameer Kankute
e3cbd5ff56
Merge pull request #18705 from BerriAI/litellm_fix_reasoning_summary_default 
Add the LITELLM_REASONING_AUTO_SUMMARY in doc
 2026-01-06 18:05:55 +05:30
Sameer Kankute
1c177a576b Add the LITELLM_REASONING_AUTO_SUMMARY in doc 2026-01-06 18:04:09 +05:30
Sameer Kankute
353769d2ac
Merge pull request #18688 from BerriAI/litellm_fix_reasoning_summary_default 
[Fix] Put automatic reasoning summary inclusion behind feat flag
 2026-01-06 17:56:40 +05:30
Sameer Kankute
aca656f036
Merge pull request #18702 from BerriAI/litellm_fix_mapped_test_3 
fix: remove display name
 2026-01-06 16:35:24 +05:30
Sameer Kankute
ffc462465d fix: remove display name 2026-01-06 16:31:07 +05:30
Ishaan Jaff
76eda472be
[Feat] New API Endpoint - Responses API (v1/responses/compact) (#18697) 
* init transform_compact_response_api_request

* init acompact_responses

* init async_compact_response_api_handler in llm http handler

* init transform_compact_response_api_request for openai

* init acompact_responses

* fix acompact_responses

* add OAI Compact API

* docs responses API Compact

* code qa checks

* test_openai_compact_responses_api

* fix mypy linting
 2026-01-06 16:24:04 +05:30
Sameer Kankute
2e668d1dfe
Merge pull request #18701 from BerriAI/revert-17330-add-model-metadata 
Revert "feat(model_cost): add display_name, model_vendor, and model_version metadata to model entries"
 2026-01-06 15:30:19 +05:30
Sameer Kankute
2baec27657
Revert "feat(model_cost): add display_name, model_vendor, and model_version metadata to model entries" 2026-01-06 15:29:42 +05:30
Sameer Kankute
eb0193a8a5
Merge pull request #18695 from BerriAI/litellm_fix_mapped_test_060126 
Fix mapped test 060126
 2026-01-06 15:05:19 +05:30
Sameer Kankute
84b24ad030 fix:mypy mcp management 2026-01-06 14:48:31 +05:30
Sameer Kankute
15a28c7fe2 fix:test_api_error_handling 2026-01-06 14:44:34 +05:30
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
Sameer Kankute
386ea1354a fix: async def test_bedrock_apply_guardrail_blocked() 2026-01-06 14:15:06 +05:30
Sameer Kankute
9c795a2baa fix: test_all_models_have_display_name 2026-01-06 14:09:43 +05:30
Sameer Kankute
a087df365e fix: test_aaamodel_prices_and_context_window_json_is_valid 2026-01-06 14:04:09 +05:30
Sameer Kankute
865c7a2215 fix: test_update_ui_settings_allowlisted_value 2026-01-06 13:58:37 +05:30
Sameer Kankute
9d59d3eef6 fix: test_secret_manager_failure_does_not_block_email 2026-01-06 13:58:15 +05:30
Sameer Kankute
9f65f82c56 Fix: ImportError: qualifire package is required for QualifireGuardrail. Install it with: pip install qualifire 2026-01-06 13:52:26 +05:30
YutaSaito
facc4b0b79
Merge pull request #18693 from BerriAI/litellm_fix_main_test 
fix main test
 2026-01-06 17:17:33 +09:00
Yuta Saito
ca14160375 Revert "fix: model eol" 
This reverts commit 5aa1665d79.
 2026-01-06 16:49:30 +09:00
Yuta Saito
23713d1811 fix: anthropic claude-3-opus-20240229 EOL 2026-01-06 16:06:21 +09:00
Yuta Saito
5aa1665d79 fix: model eol 2026-01-06 15:47:37 +09:00
YutaSaito
abb4df9dc7
Merge pull request #18687 from BerriAI/revert-18177-litellm_fix_redisvl_dependency 
Revert "Add redisvl in requirements.txt"
 2026-01-06 15:12:39 +09:00
Sameer Kankute
bb00a53786 Put reasoning summary behind feat flag 2026-01-06 11:36:20 +05:30
YutaSaito
1897a1f894
Revert "Add redisvl in requirements.txt" 2026-01-06 15:04:56 +09:00
Sameer Kankute
694e44551f
Merge pull request #17330 from nmgarza5/add-model-metadata 
feat(model_cost): add display_name, model_vendor, and model_version metadata to model entries
 2026-01-06 10:56:49 +05:30
Sameer Kankute
0f55c2b216
Merge pull request #18513 from talesofai/feat/responses-api-hooks-parity 
feat (proxy) : Responses API Support More Streaming Callback Hooks
 2026-01-06 10:51:48 +05:30
Sameer Kankute
3c0248edb9
Merge pull request #18663 from BerriAI/litellm_staging_01_05_2026 
Staging 01/05/2026
 2026-01-06 10:46:04 +05:30
Sameer Kankute
4ebd9b266b
Merge pull request #18177 from BerriAI/litellm_fix_redisvl_dependency 
Add redisvl in requirements.txt
 2026-01-06 10:43:25 +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