fa2b0fb533
docs: Update header to be markdown bold by removing space ( #18846 )
2026-01-10 00:32:21 +05:30
844c766c65
Merge pull request #18763 from BerriAI/litellm_staging_01_07_2026
...
Staging - 01/07/2026
2026-01-09 17:01:58 +05:30
022db6c9ed
feat: add mcp registry
2026-01-09 15:07:39 +09:00
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
e678540843
Merge pull request #18836 from drorIvry/main
...
feat: added qualifire eval webhook
2026-01-09 11:06:45 +09:00
c38294dc16
docs: add focus
2026-01-09 07:55:55 +09:00
661f03058c
Merge pull request #18802 from BerriAI/litellm_feat_focus_backend
...
[feat] Focus export support
2026-01-09 07:21:04 +09:00
e6c41c8f47
docs
2026-01-09 00:08:47 +02:00
5793f8b866
docs
2026-01-09 00:08:03 +02:00
8ff4cb89e1
feat: added qualifire eval webhook
2026-01-09 00:03:26 +02:00
7743c739a3
docs: fix PDF documentation inconsistency in Anthropic page ( #18816 )
...
Updated description to match the code example which uses `file`
content type with `file_data` field, instead of incorrectly
mentioning `image_url`.
2026-01-08 23:46:17 +05:30
60edf13a21
feat(tag-routing): support toggling tag matching between ANY and ALL ( #18776 )
2026-01-08 23:39:03 +05:30
cbac70a4ec
MANUS docs ( #18817 )
2026-01-08 18:58:10 +05:30
ad501048f3
Add support for Vertex AI API keys
2026-01-08 15:22:14 +05:30
790c80070f
docs: add FOCUS env
2026-01-08 17:24:51 +09:00
af6883712e
Add tests for kimi 2 bedrock model
2026-01-08 10:07:33 +05:30
98d7a428b6
Fix: Clarify database_connection_pool_limit applies per worker, not per instance ( #18780 )
2026-01-07 13:57:03 -08:00
c89a4115eb
Update production proxy resource recommendations ( #18771 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com >
2026-01-08 00:37:12 +05:30
929af510fa
[Feat] New provider - Add Azure BFL FLux for image edits ( #18766 )
...
* add azure_ai/flux.2-pro
* get_flux2_image_generation_url
* azure_client_params
* docs
* add Image Editing
* add azure ai image edits
* AzureFoundryFlux2ImageEditConfig
* TestAzureAIFlux2ImageEdit
2026-01-07 23:28:39 +05:30
3430325919
[Feat] Add Azure BFL - Flux 2 models ( #18764 )
...
* add azure_ai/flux.2-pro
* get_flux2_image_generation_url
* azure_client_params
* docs
2026-01-07 23:28:28 +05:30
dc4ce7c5a2
feat: Add abliteration.ai provider ( #18678 )
...
* feat: Add abliteration.ai provider
* adding signoz integration to observability docs
* Fixing build
* Adding timeout for flaky test
* Fixing e2e
* add team member budget duration in team/update
* Reusable Duration Select and update team member budget UI
---------
Co-authored-by: Goutham Karthi <goutham@signoz.io >
Co-authored-by: yuneng-jiang <yuneng.jiang@gmail.com >
Co-authored-by: YutaSaito <36355491+uc4w6c@users.noreply.github.com >
2026-01-07 21:46:54 +05:30
1b8708fccc
Litellm embeddings calltype fix for guardrail precallhook ( #18740 )
...
* adding signoz integration to observability docs
* Fixing build
* Adding timeout for flaky test
* Fixing e2e
* add team member budget duration in team/update
* Reusable Duration Select and update team member budget UI
* feat: allow configuring project name for OpenTelemetry service name
* docs: sets ARIZE_PROJECT_NAME
* added valid callType for bedrock guardrail pre hook
This is to resolve the error when bedrock guardrails are enabled and invoke the embedding models. {"error":{"message":"'embeddings' is not a valid CallTypes","type":"None","param":"None","code":"500"}}*
* updated the test case to reflect valid callType
---------
Co-authored-by: Goutham Karthi <goutham@signoz.io >
Co-authored-by: yuneng-jiang <yuneng.jiang@gmail.com >
Co-authored-by: YutaSaito <36355491+uc4w6c@users.noreply.github.com >
Co-authored-by: Yuta Saito <uc4w6c@bma.biglobe.ne.jp >
2026-01-07 21:40:36 +05:30
91b5c66cf2
fix(proxy): return json error response instead of sse format for initial streaming errors ( #18757 )
...
* adding signoz integration to observability docs
* Fixing build
* Adding timeout for flaky test
* Fixing e2e
* fix(proxy): return json error response instead of sse format for initial streaming errors
when the first chunk of a streaming response contains an error,
return a standard json error response instead of sse format.
this ensures clients receive properly formatted error responses
before the stream actually begins.
- rename create_streaming_response to create_response
- add logic to detect error in first chunk and return JSONResponse
- add _extract_error_from_sse_chunk helper function
- update all call sites to use the new function name
- update tests to reflect the function rename
* test(proxy): add comprehensive tests for error extraction from sse chunks
- Add new test class TestExtractErrorFromSSEChunk with 10 test cases
- Update existing tests to verify JSONResponse returned for initial streaming errors
- Add tests for error code as string, bytes input, invalid JSON, and edge cases
- Verify correct error format extraction from SSE chunks
---------
Co-authored-by: Goutham Karthi <goutham@signoz.io >
Co-authored-by: yuneng-jiang <yuneng.jiang@gmail.com >
Co-authored-by: YutaSaito <36355491+uc4w6c@users.noreply.github.com >
2026-01-07 21:26:47 +05:30
80ead21c3a
Litellm improve endpoint discovery ( #18762 )
...
* docs: document all endpoints in .json and add consistency checks against docs + providers.json
* docs: add more tests + improve coverage
2026-01-07 17:35:01 +05:30
000913fa12
Hotfix - docs qualifire ( #18724 )
...
* Hotfix - docs qualifire
* Hotfix - docs qualifire
* Hotfix - docs qualifire
* Hotfix - docs qualifire
* Hotfix - docs qualifire
* Hotfix - docs qualifire
* Hotfix - docs qualifire
2026-01-07 17:23:12 +05:30
3530218930
fix aupload_container_file
2026-01-07 14:19:36 +05:30
1f141f0dbb
[Feat] Litellm new endpoint add container file upload ( #18743 )
...
* init upload_container_file
* init upload_container_file
* _prepare_multipart_file_upload
* fix upload_container_file
* aupload_container_file, upload_container_file
* register_container_file_endpoints
2026-01-07 13:36:55 +05:30
e5be160ae0
docs: sets ARIZE_PROJECT_NAME
2026-01-07 14:27:16 +09:00
2865b17988
adding signoz integration to observability docs
2026-01-06 15:29:44 -08:00
bb4c01ffa0
Add LITELLM_DISABLE_LAZY_LOADING env var to fix VCR cassette creation issue ( #18725 )
2026-01-06 14:49:11 -08:00
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
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
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
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
1c177a576b
Add the LITELLM_REASONING_AUTO_SUMMARY in doc
2026-01-06 18:04:09 +05:30
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
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
bb00a53786
Put reasoning summary behind feat flag
2026-01-06 11:36:20 +05:30
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
31470032ad
Merge pull request #18681 from BerriAI/litellm_feat_mcp-server-visibility-configurable
...
[feat] mcp server visibility configurable
2026-01-06 12:53:07 +09:00
29e658012a
docs: add user_mcp_management_mode
2026-01-06 11:43:58 +09:00
375f3ed439
fix: missing mcp_allow_all_ui.png
2026-01-06 11:23:22 +09:00
100f617a8f
Merge pull request #18668 from BerriAI/litellm_feat_noma_mcp_guardrail
...
[feat] add support MCP guardrail to noma
2026-01-06 07:01:57 +09:00
bdd95314a7
docs: mention MCP prompt/resources types in overview
2026-01-06 06:29:37 +09:00
4eecf59f86
feat: add support MCP guardrail to noma
2026-01-06 06:15:56 +09:00
b6a64ff99a
feature/ add qualifire guardrails ( #18594 )
...
* init guardrails
* init guardrails
* some fixes
* some fixes
* ruff
* some fixes
* some fixes
* some fixes
* some fixes
* some fixes
* some fixes
* docs
2026-01-06 01:34:43 +05:30
d8d10f5e25
lasso-guardrail-api docs ( #18652 )
2026-01-05 20:58:26 +05:30
f752ec3eaf
fix
2026-01-05 20:25:39 +05:30
bf1c5bef59
[UI] Add view for estimating costs across requests ( #18645 )
...
* add estimate_cost endpoint
* TestCostEstimateEndpoint
* fix estimate_cost
* add /cost/estimate to spend tracking routes
* fix code QA checks
* fixes endpoint
* v0 cost estimator
* v0 cost estimator
* formatNumberWithCommas
* fix admin view
* docs
* docs fix + export PDF/CSV
* fixes for export
2026-01-05 19:19:58 +05:30
fee9553c51
feat: add allow_all_keys doc
2026-01-05 16:56:19 +09:00
DominikHallab