52639 commits

This branch

This branch

All branches

Author	SHA1	Message	Date
yuneng-jiang	79c7136292	Merge pull request #41794 from BerriAI/litellm_wt_0918_138e ... test(e2e): cover chat and responses registry gaps	2026-09-21 17:27:09 -07:00
Mateo Wang	9fad216030	Merge pull request #42295 from BerriAI/litellm_fix_azure_cancellederror_cooldown ... fix(azure): propagate asyncio.CancelledError instead of raising a 500	2026-09-21 17:24:22 -07:00
yucheng-berri	12f79308cf	Merge pull request #42354 from BerriAI/litellm_fix_video_key_guardrails_lit_6685 ... * fix(guardrails): scan video prompts for key-attached guardrails on /v1/videos /v1/videos dispatches call_type avideo_generation, which CallTypes did not know and no guardrail translation handler covered, so the unified guardrail hook returned the request unscanned. Add the video call types and an OpenAI video guardrail translation package that scans the prompt for create, remix, edit and extension requests Resolves LIT-6685 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * chore(ui): regenerate api types for video call types Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test: skip avideo_generation in azure sdk client exhaustive check Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(e2e): retry a leaked video job until the guardrail sync deadline Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * refactor(guardrails): satisfy the type-discipline gate in the video handler Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> * test(guardrails): gate the video e2e on a chat probe so a miss starts at most one paid job Addresses Greptile review: typed RewritingGuardrail override, dropped routine docstrings, and the e2e waits for the key guardrail to sync via /chat/completions before its single /v1/videos call Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com> --------- Co-authored-by: yucheng <yucheng@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 17:23:56 -07:00
Yassin Kortam	9cc5b78c33	Merge pull request #41634 from BerriAI/litellm_agent_access_groups ... feat(agents): attach access groups to agents and enforce them for models, MCP servers and agent calls	2026-09-21 19:13:46 -05:00
kerry-berri	17e3d314f0	Merge pull request #42371 from BerriAI/litellm-providers/price-sync-openrouter ... chore(prices): sync OpenRouter prices: 4 models	2026-09-21 17:10:29 -07:00
tin-berri	24f616b637	Merge pull request #42356 from BerriAI/litellm_cli_footer_version_guard ... fix(cli): preserve newer installed status lines during setup	2026-09-21 17:09:38 -07:00
yujonglee	ef8103a5a8	Merge pull request #42319 from BerriAI/litellm_native_redis_semantic_cache ... feat(cache): serve Redis Semantic caches natively in Rust	2026-09-21 17:05:49 -07:00
Yuneng Jiang	d90da59ac7	Merge branch 'main' into litellm_wt_0918_138e ... Resolve conflicts in the e2e Responses suite: main replaced the bespoke EndpointsClient with provider SDK clients (76bf0cd579), so the four added Vertex and Azure OpenAI /v1/responses tests are ported onto the OpenAI SDK and tool_choice=required now comes from the SDK instead of a custom request model.	2026-09-21 17:05:35 -07:00
tin-berri	094a60bb9c	Merge pull request #41872 from BerriAI/litellm_context_escalation_opt_in ... fix(router): make context-window escalation opt-in	2026-09-21 17:03:33 -07:00
yucheng-berri	99e284106d	Merge pull request #41213 from BerriAI/litellm_spend_log_cleanup_cancel_outcome ... fix(proxy): record aborted outcome when spend-log cleanup is cancelled at shutdown	2026-09-21 17:03:25 -07:00
yuneng-jiang	1f4b595072	Merge pull request #41788 from BerriAI/litellm_config_read_source ... feat(proxy): report the source of alerting, UI and router settings on read	2026-09-21 17:02:18 -07:00
berriai-litellm-provider-info-sync[bot]	c8252a50f5	chore(prices): sync OpenRouter prices: 4 models ... openrouter/~deepseek/deepseek-pro-latest: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, off_peak_pricing openrouter/deepseek/deepseek-v4-flash: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost openrouter/deepseek/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost openrouter/deepseek/deepseek-v4-pro-0813: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost, off_peak_pricing	2026-09-22 00:01:01 +00:00
yuneng-jiang	8d4ef24496	Merge pull request #41795 from BerriAI/litellm_wt_0918_5836 ... test(router): cover legacy lowest TPM selection	2026-09-21 16:57:19 -07:00
Yujong Lee	69b7224aef	test(python-bridge): initialize the interpreter in the embedder seed test ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:56:40 +00:00
yuneng-jiang	a158aa878f	Merge pull request #41773 from BerriAI/litellm_dashboard-form-happy-paths ... test(ui): cover dashboard form journeys	2026-09-21 16:56:25 -07:00
Tin Chi Lo	9221109d18	chore(router): resolve merge conflict with main	2026-09-21 16:52:47 -07:00
Yujong Lee	c31fa2ae7a	Merge remote-tracking branch 'origin/main' into litellm_native_redis_semantic_cache ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:51:16 +00:00
Tin Chi Lo	0cfc4bc782	fix(cli): serialize footer installs and tolerate unknown versions	2026-09-21 16:48:08 -07:00
yuneng-jiang	c21ab96741	Merge pull request #42293 from BerriAI/litellm_complexity_router_advanced_fields ... feat(ui): expose remaining complexity router advanced settings	2026-09-21 16:43:50 -07:00
yuneng-jiang	6b254b6be2	Merge pull request #41769 from BerriAI/litellm_model-actor-edges ... test(model_management): cover actor edges and wildcard models	2026-09-21 16:43:24 -07:00
tin-berri	c1c1ec4f84	Merge pull request #42026 from BerriAI/litellm_user_jwt_savings ... feat(ui): add internal-user savings and auto-router usage	2026-09-21 16:41:16 -07:00
kerry-berri	707c7493cf	Merge pull request #42365 from BerriAI/litellm-providers/price-sync-openrouter ... chore(prices): sync OpenRouter prices: 2 models	2026-09-21 16:39:50 -07:00
yujonglee	e05ebbc749	Merge pull request #42364 from BerriAI/litellm_valkey_semantic_stub ... fix(rust): declare _CacheTestHandle.valkey_semantic in native stub	2026-09-21 16:38:08 -07:00
ryan-crabbe-berri	582c664168	Merge pull request #42346 from BerriAI/litellm_jwt_team_allowed_routes_passthrough_grant ... fix(auth): let jwt team_allowed_routes paths grant auth=true passthrough	2026-09-21 16:38:05 -07:00
Mateo Wang	8c8fb73eb8	Merge pull request #42355 from BerriAI/litellm_logging_worker_flush_loop_change ... fix(logging_worker): make flush() survive an event loop change	2026-09-21 16:33:01 -07:00
berriai-litellm-provider-info-sync[bot]	10ac81cfb5	chore(prices): sync OpenRouter prices: 2 models ... openrouter/deepseek/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost openrouter/meta-llama/llama-4-maverick: input_cost_per_token, output_cost_per_token	2026-09-21 23:30:58 +00:00
Yujong Lee	e350455a66	fix(rust): declare _CacheTestHandle.valkey_semantic in native stub ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:30:14 +00:00
yujonglee	0b8faae494	Merge pull request #42316 from BerriAI/litellm_valkey_semantic_native_cache	2026-09-21 16:28:12 -07:00
kerry-berri	7f550165df	Merge pull request #42363 from BerriAI/litellm_bedrock_kimi_k3_bare_key ... fix(bedrock): add bare moonshotai.kimi-k3 cost map entry	2026-09-21 16:28:06 -07:00
kerry-berri	cf098ceccf	Merge pull request #42362 from BerriAI/litellm_xiaomi_mimo_v26 ... feat(xiaomi_mimo): add mimo-v2.6-pro and mimo-v2.6-flash cost map rows with live e2e coverage	2026-09-21 16:25:15 -07:00
yucheng	2f0584cec6	test(guardrails): gate the video e2e on a chat probe so a miss starts at most one paid job ... Addresses Greptile review: typed RewritingGuardrail override, dropped routine docstrings, and the e2e waits for the key guardrail to sync via /chat/completions before its single /v1/videos call Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:20:29 +00:00
kerry	cbed8cd0d8	fix(bedrock): sync moonshotai.kimi-k3 entry into cost map backup file ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:20:26 +00:00
Tin Chi Lo	2915272f2f	chore: retain the CI-generated API snapshot	2026-09-21 16:20:16 -07:00
Yujong Lee	2eee880aba	Merge origin/main into litellm_valkey_semantic_native_cache ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:18:54 +00:00
kerry	9af3363c2f	fix(bedrock): add bare moonshotai.kimi-k3 cost map entry mirroring the global inference profile ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:18:18 +00:00
mateo-berri	9388602f46	test(logging_worker): track callback runs with AsyncMock instead of a mutated list	2026-09-21 16:13:09 -07:00
kerry	47a1053065	feat(xiaomi_mimo): add mimo-v2.6-pro and mimo-v2.6-flash cost map rows with live e2e coverage ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:12:57 +00:00
yujonglee	a5431244ef	Merge pull request #42313 from BerriAI/litellm_rust_cache_s3 ... feat(rust): add native S3 cache backend	2026-09-21 16:12:54 -07:00
kerry-berri	745ae7124b	Merge pull request #42357 from BerriAI/litellm-providers/price-sync-openrouter ... chore(prices): sync OpenRouter prices: 4 models, 3 deprecated	2026-09-21 16:12:19 -07:00
Yujong Lee	9fa1683ed9	chore(cache): keep main's UnsupportedOperation message ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:09:03 +00:00
Yujong Lee	615a226a30	Merge remote-tracking branch 'origin/main' into litellm_native_redis_semantic_cache ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:08:37 +00:00
Yujong Lee	4c9e45f5f1	Merge origin/main into litellm_valkey_semantic_native_cache ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:08:31 +00:00
joshua-berri	1baa26d36b	Merge pull request #41074 from BerriAI/litellm_mcp_server_list_stable_order ... fix(mcp): keep server lists stable across refreshes	2026-09-21 23:06:09 +00:00
Yujong Lee	7282494c30	fix(python-bridge): propagate cancellation from semantic embedding awaits ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:04:44 +00:00
Yujong Lee	0c5bbf8c37	Merge branch 'main' into litellm_rust_cache_s3 ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:04:42 +00:00
ryan-crabbe-berri	a0d1f0236e	Merge pull request #42122 from BerriAI/litellm_db_callback_redaction_settings ... fix(proxy): apply DB-stored callback redaction settings before logger init	2026-09-21 16:03:44 -07:00
yujonglee	ced2980529	Merge pull request #42308 from BerriAI/litellm_rust_secrets_hashicorp_vault ... feat(rust): add HashiCorp Vault secret manager crate	2026-09-21 16:03:33 -07:00
Yujong Lee	d38514dfc6	test(cache-redis-semantic): pin shared-index behavior across embedding dimensions ... Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>	2026-09-21 23:02:23 +00:00
mateo-berri	37f1670a1e	Merge remote-tracking branch 'origin/main' into litellm_logging_worker_flush_loop_change	2026-09-21 16:02:04 -07:00
berriai-litellm-provider-info-sync[bot]	c371617786	chore(prices): sync OpenRouter prices: 4 models, 3 deprecated ... openrouter/bytedance-seed/seed-1.6: deprecation_date openrouter/bytedance-seed/seed-1.6-flash: deprecation_date openrouter/bytedance-seed/seed-2.0-code: deprecation_date openrouter/deepseek/deepseek-v4-pro: input_cost_per_token, output_cost_per_token, cache_read_input_token_cost	2026-09-21 23:01:01 +00:00