71a2fc5331
fix classnames
2026-01-20 14:16:03 -08:00
f434d1c847
Option to pre fill custom proxy base URL
2026-01-20 14:07:54 -08:00
7f81dea8b3
Add custom auth header support and increase default prompt size to 100k chars ( #19436 )
2026-01-20 13:25:12 -08:00
e142474e0b
Merge pull request #19431 from BerriAI/litellm_ui_fix_build_002
...
[Infra] UI - Fixing UI Build
2026-01-20 13:17:25 -08:00
3ae71bf49e
fixing ui build
2026-01-20 13:03:27 -08:00
bfb94f56b7
Merge pull request #19276 from stiyyagura0901/litellm_fix_ui_auth_header_override
...
fix: UI dashboard respects custom authentication header override
2026-01-20 12:24:14 -08:00
5a06868652
Fix in-flight request termination on SIGTERM when health-check runs in a separate process ( #19427 )
2026-01-20 12:17:06 -08:00
f95f5563ea
docs: document input/output/total tokens behaviour
...
Closes https://github.com/BerriAI/litellm/issues/17480
2026-01-20 10:45:47 -08:00
1377721715
Fix: Handle PostgreSQL cached plan errors during rolling deployments ( #19424 )
2026-01-20 10:44:31 -08:00
ce37729da4
remove count tokens optional param before request is sent to vertex ( #19359 )
2026-01-20 09:03:27 -08:00
f6d6455cbc
fix rc
2026-01-20 08:39:17 -08:00
11dbae85d1
Merge pull request #19390 from BerriAI/litellm_consistent_id_streaming_responses
...
Fix: ID mismatch between text-start and text-delta
2026-01-20 20:46:34 +05:30
961a424069
Merge pull request #19355 from BerriAI/litellm_staging_01_19_2026
...
Litellm staging 01 19 2026
2026-01-20 20:45:12 +05:30
9e1275b76c
Merge branch 'main' into litellm_staging_01_19_2026
2026-01-20 19:19:36 +05:30
a3c1f4758d
Merge branch 'main' into litellm_consistent_id_streaming_responses
2026-01-20 19:02:23 +05:30
e69c12b6db
Merge pull request #19396 from BerriAI/litellm_responses_route_fix
...
Fix for Prometheus Metric Cardinality Issue with /responses Endpoint
2026-01-20 19:01:18 +05:30
bd6f7bae21
Merge pull request #19397 from BerriAI/litellm_google_computer_use_cost_tracking
...
Add gemini-2.5-computer-use-preview-10-2025 model for vertex ai provider
2026-01-20 19:00:34 +05:30
172ad17fbc
Merge pull request #19398 from BerriAI/litellm_add_multimodal_cost_tracking
...
Add input_cost_per_video_per_second in ModelInfoBase
2026-01-20 19:00:05 +05:30
37ce6957ab
Merge pull request #19386 from BerriAI/litellm_staging_01_20_2026
...
Litellm staging 01 20 2026
2026-01-20 18:53:59 +05:30
12c556e485
Merge pull request #19409 from BerriAI/revert-19261-feat/redis-migration-lock-safe
...
Revert "feat: Add Redis-based migration lock with bug fixes"
2026-01-20 18:46:38 +05:30
3cc19c56ba
Revert "feat: Add Redis-based migration lock with bug fixes ( #19261 )"
...
This reverts commit 98e87c3e67
2026-01-20 18:46:26 +05:30
dc3ee63359
fix: test_env_keys
2026-01-20 18:37:56 +05:30
2153db5e64
fix: test_convert_to_bedrock_format_post_call_streaming_hook
2026-01-20 18:27:36 +05:30
8b24720638
fix: test_standard_logging_payload_includes_guardrail_information
2026-01-20 18:21:32 +05:30
219f650445
Merge pull request #19405 from BerriAI/revert-19315-fix-litellm-params
...
Revert "fix #19254 - [Bug]: litellm_params ignored by get_llm_provider function in completion() definition"
2026-01-20 17:51:44 +05:30
f6fcd0cb85
Revert "fixed litellm params ( #19315 )"
...
This reverts commit 16b8ed6786
2026-01-20 17:50:45 +05:30
df89e7262a
Merge pull request #19404 from BerriAI/litellm_staging_01_20_2026_fix
...
Litellm staging 01 20 2026 fix
2026-01-20 17:40:23 +05:30
cd96c8cbb0
Fix:test_aaaaazure_tenant_id_auth
2026-01-20 17:39:08 +05:30
f0785d5a51
Fix:test_supported_params_limited_to_docs
2026-01-20 17:26:40 +05:30
c8ad14dbab
Merge pull request #19402 from BerriAI/revert-19371-feat/configurable-retry-logic
...
Revert "feat: add retry_delay, exponential_backoff, and jitter to completion()"
2026-01-20 17:07:11 +05:30
ae414ed462
Revert "feat: add retry_delay, exponential_backoff, and jitter to completion(…"
...
This reverts commit 1678f621db
2026-01-20 17:07:00 +05:30
dd6b35e825
Merge pull request #19401 from BerriAI/main
...
Merge main 01 20 2026
2026-01-20 16:45:08 +05:30
deb9142117
Merge pull request #19400 from BerriAI/main
...
merge main iin 19/1 staging
2026-01-20 16:45:01 +05:30
be0f61854f
Add input_cost_per_video_per_second in ModelInfoBase
2026-01-20 16:23:47 +05:30
cebcad48d3
Add gemini-2.5-computer-use-preview-10-2025 model for vertex ai provider
2026-01-20 15:53:02 +05:30
5f80e8d5e8
Fix for Prometheus Metric Cardinality Issue with /responses Endpoint
2026-01-20 15:28:09 +05:30
f945fd9a84
Fix: ID mismatch between text-start and text-delta
2026-01-20 11:15:37 +05:30
3eb3594ab7
Merge pull request #19346 from Chesars/fix/drop-params-prompt-cache-key-19225
...
fix: drop_params not dropping prompt_cache_key for non-OpenAI providers
2026-01-20 10:15:45 +05:30
931998f170
Merge pull request #19266 from VedantMadane/fix-prompt-caching-string-content
...
Fix extract_cacheable_prefix to handle string content with message-level cache_control
2026-01-20 10:11:48 +05:30
7d6d419a67
fix: preserve tool output ordering for gemini in responses bridge ( #19360 )
...
* fix: preserve tool output ordering for gemini in responses bridge
- Keep function_call_output adjacent to its function_call when building chat messages
- Normalize function_call_output.output lists (input_* parts) into tool message content
* fix test
* small improvements
2026-01-19 20:37:59 -08:00
d7ac8de832
docs: Migrate Pillar Security to Generic Guardrail API ( #19364 )
...
Update Pillar Security integration to use the generic_guardrail_api
instead of the dedicated pillar guardrail type. This aligns with
the Generic Guardrail API specification introduced in previous PRs.
Changes:
- Rewrite pillar_security.md with new generic_guardrail_api config
- Add Pillar Security example to generic_guardrail_api.md
- Add Pillar Security to quick_start.md guardrails examples
Related PRs: #17175 , #18647 , #18932 , #19023
2026-01-19 20:35:56 -08:00
581d086c20
fix(responses): stream tool call events in completion bridge ( #19368 )
...
Emit Responses API streaming events for tool calls when the underlying chat stream contains tool_call deltas, and recover tool calls into the stream when they only appear in the final response.
2026-01-19 20:29:50 -08:00
2ae308028d
Merge pull request #18787 from aproorg/fix/bedrock-thinking-tool-call-2
...
fix(bedrock): handle thinking with tool calls for Claude 4 models
2026-01-20 09:43:07 +05:30
00814d4d90
Merge pull request #19379 from BerriAI/litellm_feat_mcp_version_up
...
[feat] mcp version up
2026-01-20 13:09:29 +09:00
ea2e360cb5
docs
2026-01-19 19:49:51 -08:00
f865f92bec
docs plugin marketplaces
2026-01-19 19:42:15 -08:00
ab11ceff32
tests: patch MCP client mocks via module alias to avoid real network calls
2026-01-20 12:31:27 +09:00
1645be3a2f
feat: implement SafeAttributeModel for safe attribute access in models ( #18321 )
2026-01-19 19:24:03 -08:00
2761077820
docs: fix vertex_region to vertex_location in Vertex AI pass-through docs ( #19380 )
...
The documentation incorrectly used `vertex_region` as the parameter name,
but the actual parameter expected by LiteLLM is `vertex_location` as defined
in VertexPassThroughCredentials and other type definitions.
Co-authored-by: Claude <noreply@anthropic.com >
2026-01-19 19:15:17 -08:00
0dfc3fad5a
Fix: bedrock invoke claude 4 optional params #19318 ( #19381 )
2026-01-19 19:14:58 -08:00
yuneng-jiang