3ebec39b74
fix(proxy): use async anthropic client to prevent event loop blocking ( #18435 )
...
Fixes #16716 .
Previously, synchronous Anthropic client was used for token counting, which blocked the event loop.
This change switches to AsyncAnthropic and caches the client instance.
2026-01-08 23:26:46 +05:30
cfda03ebe1
fix(gemini): support snake_case for google_search tool parameters ( #18451 )
...
* fix(gemini): support snake_case for google_search tool parameters
Add snake_case aliases for Gemini tool names to match the pattern
already used by other tools (url_context, google_maps, code_execution):
- google_search -> googleSearch
- google_search_retrieval -> googleSearchRetrieval
- enterprise_web_search -> enterpriseWebSearch
* test(gemini): add tests for snake_case google_search tool aliases
* refactor(gemini): simplify get_tool_value calls formatting
2026-01-08 23:25:36 +05:30
e285e2b91d
Merge pull request #18675 from BerriAI/litellm_key_team_routing_config
...
[Feature] Allow Add and Update for router_settings on Keys and Teams
2026-01-07 16:24:04 -08:00
f126f75995
feat: pass server_tool_use and tool_search_tool_result blocks to anthropic ( #18770 )
...
* feat: Allow message types of server_tool_use and tool_search_tool_result to reach anthropic
* test: anthropic server tool use pass through testing
2026-01-08 00:47:28 +05:30
140ce5fce2
Merge remote-tracking branch 'origin' into litellm_key_team_routing_config
2026-01-07 11:08:01 -08:00
943445dd0f
Adding test
2026-01-07 11:00:07 -08:00
9a49bb293f
Merge remote-tracking branch 'origin' into litellm_key_team_routing_config
2026-01-07 10:55:38 -08:00
7da8d5fcd5
Merge remote-tracking branch 'origin' into litellm_endpoint_usage_breakdown
2026-01-07 10:25:43 -08:00
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
6122ff9fce
TestEncryptResponseId
2026-01-07 21:03:22 +05:30
b855ad5541
test_encode_decode_helpers_roundtrip_in_cache_context
2026-01-07 18:23:17 +05:30
dd67235d4d
TestLevoIntegration
2026-01-07 18:17:22 +05:30
407575efb3
test_completion_bedrock_claude_aws_session_token
2026-01-07 18:09:07 +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
45f840d274
test_azure_image_edit_cost_tracking
2026-01-07 15:12:51 +05:30
5873cd4a32
test_completion_bedrock_titan_null_response
2026-01-07 15:09:44 +05:30
d56054e747
test_anthropic_messages_to_wildcard_model
2026-01-07 15:03:06 +05:30
269771a7c9
test_bedrock_httpx_streaming
2026-01-07 15:02:10 +05:30
645ca64780
a121 fixes
2026-01-07 15:00:49 +05:30
a5332a6d51
fix code qa check
2026-01-07 14:54:00 +05:30
ee2b51b2d0
test_openai_image_edit_cost_tracking
2026-01-07 14:36:50 +05:30
bab43ee9dd
fix list keys
2026-01-07 14:34:37 +05:30
38ccfb4234
test_completion_claude_3_function_call_with_otel
2026-01-07 14:22:54 +05:30
fa1b387237
test_routing_strategy_init
2026-01-07 14:21:03 +05:30
3530218930
fix aupload_container_file
2026-01-07 14:19:36 +05:30
b7798b7f7c
fix metadata.cost_breakdown
2026-01-07 14:17:08 +05:30
b5d74722ba
Revert "Litellm fixes a2a sdk ( #18748 )" ( #18752 )
...
This reverts commit 1661707492
2026-01-07 14:04:10 +05:30
1661707492
Litellm fixes a2a sdk ( #18748 )
...
* add a2a SDK to req
* fix
2026-01-07 13:31:45 +05:30
1d16a8526e
feat: allow configuring project name for OpenTelemetry service name
2026-01-07 14:20:10 +09:00
2a6f2a3fb8
add team member budget duration in team/update
2026-01-06 17:43:17 -08:00
ccfffc5de9
Add endpoint to aggregate activity tables
2026-01-06 15:54:03 -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
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
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
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
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
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
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
eb0193a8a5
Merge pull request #18695 from BerriAI/litellm_fix_mapped_test_060126
...
Fix mapped test 060126
2026-01-06 15:05:19 +05:30
0d050dc0ea
fix:test_anthropic_beta_header
2026-01-06 14:28:30 +05:30
8aff258a93
fix: test_databricks_embeddings[True]
2026-01-06 14:20:30 +05:30
386ea1354a
fix: async def test_bedrock_apply_guardrail_blocked()
2026-01-06 14:15:06 +05:30
865c7a2215
fix: test_update_ui_settings_allowlisted_value
2026-01-06 13:58:37 +05:30
9d59d3eef6
fix: test_secret_manager_failure_does_not_block_email
2026-01-06 13:58:15 +05:30
9f65f82c56
Fix: ImportError: qualifire package is required for QualifireGuardrail. Install it with: pip install qualifire
2026-01-06 13:52:26 +05:30
ca14160375
Revert "fix: model eol"
...
This reverts commit 5aa1665d79
2026-01-06 16:49:30 +09:00
23713d1811
fix: anthropic claude-3-opus-20240229 EOL
2026-01-06 16:06:21 +09:00
5aa1665d79
fix: model eol
2026-01-06 15:47:37 +09:00
Constantine