32324 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
Aarish Alam	3e04e20205	🐛 Bug Fix #19642 : bug in Vertex AI context caching (#19657) ... * add vertex tests * add uperbound * add pagination tests	2026-02-02 18:13:34 +05:30
Chesars	b3f1696946	refactor(vertex_ai): reuse get_vertex_base_url for URL construction ... Use existing get_vertex_base_url from common_utils instead of duplicating the global vs regional URL logic in create_vertex_url and get_api_base.	2026-02-02 18:13:18 +05:30
Chesars	3215dc4d4e	feat(vertex_ai): add global endpoint support for Qwen MaaS models ... Fixes #19788 - Add `supported_regions: ["global"]` to Qwen MaaS models in model_prices_and_context_window.json - Update `get_supported_regions()` to read directly from `model_cost` dict - Update `get_complete_vertex_url()` to use `get_vertex_region()` for global-only models - Update `create_vertex_url()` to generate correct URL for global location (without region prefix) - Add tests for Qwen global endpoint support	2026-02-02 18:13:10 +05:30
Emerson Gomes	bb5397d9b2	fix: enforce scheme for Azure AI rerank api_base	2026-02-02 18:13:04 +05:30
Emerson Gomes	92763a14a9	Update litellm/llms/azure_ai/rerank/transformation.py ... Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>	2026-02-02 18:12:59 +05:30
Emerson Gomes	c4dd22c079	fix: broaden Azure AI rerank URL handling	2026-02-02 18:12:52 +05:30
Chesars	11fd92c21b	refactor(image-gen): move thought_signature to provider_specific_fields ... Per review feedback, thought_signature should not be a root-level param on ImageObject as it's not OpenAI compatible. Moved to provider_specific_fields dict to match the pattern used in chat completions (Message, Delta, Choices, etc).	2026-02-02 18:12:41 +05:30
Chesars	b2463291c7	fix(image-gen): add thought_signature to ImageObject for Gemini 3 Pro ... Fixes #17184 - Gemini 3 Pro image preview model returns a thoughtSignature field required for interactive image editing. This change: - Adds thought_signature field to ImageObject class - Updates Gemini and Vertex AI transformations to extract thoughtSignature - Adds test for thought_signature in response transformation	2026-02-02 18:12:28 +05:30
Sameer Kankute	27b4052231	Merge pull request #20244 from BerriAI/litellm_nova_sonic_imp_2_feb ... [Feat]Add support for nova sonic Speech to speech model	2026-02-02 18:04:02 +05:30
Sameer Kankute	8e2f7e5757	Fix mypy issues	2026-02-02 17:58:01 +05:30
Sameer Kankute	686aafe03a	Merge pull request #20262 from BerriAI/litellm_test_bedrock_optional_params_embeddings_dimension ... Litellm test bedrock optional params embeddings dimension	2026-02-02 17:49:47 +05:30
Sameer Kankute	bb363f0307	Fix: test_bedrock_optional_params_embeddings_dimension	2026-02-02 17:49:18 +05:30
Sameer Kankute	01cdc272ec	Fix: test_bedrock_optional_params_embeddings_dimension	2026-02-02 17:47:20 +05:30
Sameer Kankute	be0bb975c0	Fix test_aaamodel_prices_and_context_window_json_is_valid	2026-02-02 17:46:37 +05:30
Sameer Kankute	dafa26baa6	Merge pull request #20247 from BerriAI/litellm_smoketest_suite ... Add Anthropic caching and context tests	2026-02-02 17:45:25 +05:30
Sameer Kankute	19f6640309	Merge pull request #20249 from BerriAI/litellm_add_0_budget_model_bypass2 ... [Feat] Add support for 0 cost models	2026-02-02 17:45:05 +05:30
Sameer Kankute	fe7c7dadba	Merge pull request #20253 from BerriAI/litellm_SAP-model-routing-to-OpenAI ... Fix open_ai_embedding_models to have custom_llm_provider None	2026-02-02 17:44:14 +05:30
Sameer Kankute	8d65ac62f7	Merge pull request #20254 from BerriAI/litellm_anthropic_reasoning_content ... fix: Map reasoning content to anthropic thinking block(streaming+non-streaming)	2026-02-02 17:43:50 +05:30
Sameer Kankute	fff35ee032	Merge pull request #20257 from BerriAI/litellm_slack_alert_fix_jfeb_02 ... Fix: Slack alert issue	2026-02-02 17:43:05 +05:30
Sameer Kankute	7773a92069	Merge pull request #20258 from BerriAI/litellm_cerebras_reasoning ... fix: add reasoning param support for GPT OSS cerebras	2026-02-02 17:42:28 +05:30
Sameer Kankute	415c26f281	fix: add reasoning param support for GPT OSS cerebras	2026-02-02 17:20:04 +05:30
Sameer Kankute	72482c0cb5	Fix: Slack alert issue	2026-02-02 16:49:10 +05:30
Sameer Kankute	15cec5a4a0	Merge pull request #20255 from BerriAI/litellm_tts_doc ... Update Vertex AI Text to Speech doc to show use of audio	2026-02-02 16:16:28 +05:30
Sameer Kankute	c6f178eeae	Update Vertex AI Text to Speech doc to show use of audio	2026-02-02 16:15:48 +05:30
Sameer Kankute	eee737520f	fix: Map reasoning content to anthropic thinking block(streaming+non-streaming)	2026-02-02 16:04:13 +05:30
Sameer Kankute	c2298c2417	Fix open_ai_embedding_models to have custom_llm_provider None	2026-02-02 15:18:56 +05:30
Sameer Kankute	6f2dc19ea0	Merge pull request #20214 from cscguochang/feat/bedrock-1hr-tiered-caching-cost ... feat(bedrock): add 1hr tiered caching costs for long-context models (#18988)	2026-02-02 15:05:22 +05:30
Sameer Kankute	1a7fcfb713	Merge pull request #19881 from jayy-77/feat/user-agent-customization-issue-19017 ... feat: add User-Agent customization support	2026-02-02 15:01:39 +05:30
Sameer Kankute	f1df5ea9a9	Merge pull request #20252 from BerriAI/main ... merge main	2026-02-02 14:54:50 +05:30
Sameer Kankute	14c2932387	Add docs on Zero-Cost Models	2026-02-02 13:29:37 +05:30
Sameer Kankute	1f4222e6b2	Add support for 0 cost models	2026-02-02 13:29:37 +05:30
Sameer Kankute	88cb101d88	Add Anthropic caching and context tests	2026-02-02 13:25:47 +05:30
Sameer Kankute	c13cb4cf51	Merge pull request #20235 from amirzaushnizer/litellm-support-cohere-embed-v4 ... feat: Support dimensions param for Cohere embed v4	2026-02-02 12:52:16 +05:30
Sameer Kankute	5e17dea24d	Add tutorial to use bedrock nova	2026-02-02 12:19:17 +05:30
Sameer Kankute	ea6c31a02a	Add documentation on nova sonic	2026-02-02 12:19:04 +05:30
Sameer Kankute	cdeefe85ea	Add nova sonic tests	2026-02-02 12:18:43 +05:30
Sameer Kankute	eb0f019359	Add nova sonic realtime	2026-02-02 12:18:32 +05:30
Sameer Kankute	037c10d7cb	Add bedrock route in realtim main.py	2026-02-02 12:16:05 +05:30
amirzaushnizer	f0853b2564	feat: enhance Cohere embedding support with additional parameters and model version	2026-02-01 18:04:08 +02:00
yuneng-jiang	b8876838a6	revert react 18	2026-01-31 20:09:39 -08:00
yuneng-jiang	33343bc1ef	remove node_modules	2026-01-31 19:57:54 -08:00
shin-bot-litellm	df387c39f6	docs: Update v1.81.6 release notes - focus on Logs v2 with Tool Call Tracing (#20225) ... - Updated title to highlight Logs v2 feature - Simplified Key Highlights to focus on Logs v2 / tool call tracing - Rewrote Logs v2 description with improved language style - Removed Claude Agents SDK and RAG API from key highlights section - TODO: Add image (logs_v2_tool_tracing.png) Co-authored-by: shin-bot-litellm <shin-bot-litellm@users.noreply.github.com>	2026-01-31 19:29:06 -08:00
yuneng-jiang	9926a576e7	clean install for build ui	2026-01-31 19:14:27 -08:00
Ishaan Jaffer	b7e48f1d9e	test fix	2026-01-31 19:08:07 -08:00
Ishaan Jaffer	466e6bdcf1	fix(test): make test_proxy_failure_metrics resilient to missing proxy-level metrics ... - Check for both litellm_proxy_failed_requests_metric_total and the deprecated litellm_llm_api_failed_requests_metric_total - The proxy-level failure hook may not always be called depending on where the exception occurs - Simplify total_requests check to only verify key fields Co-authored-by: Cursor <cursoragent@cursor.com>	2026-01-31 18:46:27 -08:00
Ishaan Jaffer	92c8e00520	test_proxy_success_metrics	2026-01-31 18:36:22 -08:00
yuneng-jiang	dc5c8c8918	react 19	2026-01-31 18:33:03 -08:00
yuneng-jiang	c68baa3943	upgrade react version	2026-01-31 18:13:44 -08:00
Ishaan Jaffer	faff9d1dc5	test_proxy_failure_metrics	2026-01-31 18:10:17 -08:00
Ishaan Jaffer	35e29c2bcd	Revert "Merge pull request #18790 from BerriAI/litellm_key_team_routing_3" ... This reverts commit ae26d8e68a, reversing changes made to 864e8c6543.	2026-01-31 17:58:46 -08:00