yuneng-jiang
4bcbd8b0a9
Fix callback env variables
2025-12-12 18:03:08 -08:00
Ishaan Jaffer
802a343fdb
ui new build
2025-12-12 17:15:40 -08:00
Ishaan Jaffer
17ce970d99
ui fix
2025-12-12 17:10:36 -08:00
Ishaan Jaffer
2027ee7f85
UI new build
2025-12-12 17:04:48 -08:00
Ishaan Jaffer
c57f0665db
ui buld fix
2025-12-12 16:58:47 -08:00
Ishaan Jaff
3054b6ea60
[Feat] A2A Gateway - allow adding Azure Foundry Agents on UI ( #17909 )
...
* add CostConfigFields
* add CostConfigFields
* add output_cost_per_token
* refactor table
* add agent cost view
* add azure foundry fields
* add foundry logo
* fix: clean error
* fix utils
* fix agent edi
* add easter egg
* fix order
* test_handle_streaming_forwards_api_key
* fix forward api key down
* fix a2a send msg
* add A2a comparison on compare playground
* fix chat ui
* fix bedrock agentcore stream
2025-12-12 16:38:04 -08:00
Ishaan Jaff
bede40a90d
[A2a gateway] Add agent cost tracking on UI ( #17899 )
...
* add CostConfigFields
* add CostConfigFields
* add output_cost_per_token
* refactor table
* add agent cost view
2025-12-12 16:37:31 -08:00
YutaSaito
b93a5f0ca6
Merge pull request #17908 from BerriAI/litellm_fix-mcp-tool-name-prefix
...
Litellm fix mcp tool name prefix
2025-12-13 08:23:47 +09:00
Yuta Saito
bcb26cc55a
fix: format
2025-12-13 07:56:05 +09:00
Yuta Saito
864b61b433
fix: support ResponseFunctionToolCall in follow-up input
2025-12-13 07:55:13 +09:00
yuneng-jiang
11926ea2d4
Merge pull request #17901 from BerriAI/litellm_usage_date_pick_fix
...
[Fix] UI - Agent Usage Page Minor Issues
2025-12-12 14:34:15 -08:00
yuneng-jiang
64aaba6c58
Merge pull request #17902 from BerriAI/litellm_ui_default_user
...
[Fix] Add All Proxy Models To Default User Settings
2025-12-12 14:33:42 -08:00
Yuta Saito
48579eafe3
fix: strip mcp server prefixes in responses
2025-12-13 07:17:50 +09:00
yuneng-jiang
d090b4ad3e
Add All Proxy Models To Default User Settings
2025-12-12 13:15:25 -08:00
yuneng-jiang
94a0ff08b7
Merge remote-tracking branch 'origin' into litellm_usage_date_pick_fix
2025-12-12 13:00:59 -08:00
Cesar Garcia
ed28818f76
feat(bedrock): add EU Claude Opus 4.5 model ( #17897 )
...
Add eu.anthropic.claude-opus-4-5-20251101-v1:0 to support
AWS Bedrock cross-region inference in EU regions.
Fixes #17867
2025-12-12 12:56:17 -08:00
yuneng-jiang
5d01f14f94
Fixing build
2025-12-12 12:55:15 -08:00
yuneng-jiang
b2695379d1
Merge pull request #17896 from BerriAI/litellm_agent_usage_2
...
[Feature] Usage Entity labels
2025-12-12 12:53:16 -08:00
yuneng-jiang
19504adb9d
Agent Usage small issues
2025-12-12 12:52:51 -08:00
yuneng-jiang
1037dc18b9
Adding test
2025-12-12 12:23:11 -08:00
yuneng-jiang
5b0bf86ee5
Usage Entity labels
2025-12-12 12:13:51 -08:00
Ishaan Jaff
92d71a3ed4
[UI] - Re organize leftnav to have correct categories + get agents on root ( #17890 )
...
* left nav
* fix order
* fix
* fix bad new usage
* fix new
2025-12-12 12:10:13 -08:00
YutaSaito
8899b63fa4
Merge pull request #17747 from BerriAI/litellm_feat_mcp-chat-completions
...
feat: add support for using MCPs on /chat/completions
2025-12-13 05:05:21 +09:00
Ishaan Jaff
b651012fdc
[fix] UI playground - allow custom model name as option[0] ( #17892 )
...
* fix: move custom model to top
* fix test
2025-12-12 12:00:23 -08:00
Cesar Garcia
1531b58493
feat(openai): add reasoning_effort='xhigh' support for gpt-5.2 models ( #17875 )
...
Add support for the 'xhigh' reasoning effort level on all gpt-5.2 model
variants, not just gpt-5.2-pro. This enables deeper reasoning capabilities
for the base gpt-5.2 model.
Changes:
- Add is_model_gpt_5_2_model() method to detect gpt-5.2 variants
- Update xhigh validation to allow gpt-5.2 models
- Update documentation with gpt-5.2 reasoning_effort support
- Update tests to reflect new behavior
2025-12-12 11:40:35 -08:00
Ishaan Jaff
700a1bb574
[Feat] UI - show UI version on top left near logo ( #17891 )
...
* left nav
* fix order
* fix
* add ui version on ui
* fix link
2025-12-12 11:39:02 -08:00
Alexsander Hamir
b635f92d90
Add benchmark_proxy_vs_provider.py script to scripts directory with usage examples ( #17889 )
2025-12-12 11:26:34 -08:00
Alexsander Hamir
f4db4b6f0e
feat(otel): add latency metrics (TTFT, TPOT, Total Generation Time) to OTEL logging ( #17888 )
...
- Add time_to_first_token_histogram using api_call_start_time for accurate measurement
- Add time_per_output_token_histogram for average time per output token
- Add response_duration_histogram for total LLM API generation time
- Extract latency metric recording into dedicated helper methods
- Fix parent span double-ending bug when reused as primary span
- Use api_call_start_time for TTFT to exclude LiteLLM overhead (matches Prometheus)
- Support both streaming and non-streaming requests
- Handle both datetime and float timestamp formats
2025-12-12 11:19:17 -08:00
Ishaan Jaff
d38f241032
[Feat] JWT Auth - auth allow selecting team_id from request header ( #17884 )
...
* feat: add get_team_id_from_header for JWT Auth
* fix Auth builder JWT Auth
* test_get_team_id_from_header
* test_auth_builder_uses_team_from_header_e2e
* Select Team via Request Header
2025-12-12 10:18:20 -08:00
yuneng-jiang
25a38b0f27
Merge pull request #17883 from BerriAI/litellm_ui_new_badge
...
[Feature] New Badge for Agent Usage
2025-12-12 10:02:31 -08:00
yuneng-jiang
1829e58d25
New Badge for Agent Usage
2025-12-12 09:47:08 -08:00
Sameer Kankute
d5fcb6fce6
Merge pull request #17882 from BerriAI/litellm_target_storage_documentation
...
Add documentation for target storage
2025-12-12 22:46:04 +05:30
Sameer Kankute
6f0efff28b
Add documentation for target storage
2025-12-12 22:44:53 +05:30
Sameer Kankute
da81ab6d97
Merge pull request #17758 from BerriAI/litellm_managed_files_target_storage
...
Add v0 support for target storage
2025-12-12 22:26:34 +05:30
Sameer Kankute
afda51d476
Merge pull request #17873 from BerriAI/litellm_rerank_foraward_headers
...
Add support for forwarding client headers in /rerank endpoint
2025-12-12 22:25:57 +05:30
Sameer Kankute
d98ee8a448
Merge pull request #17872 from BerriAI/litellm_embedding_header_forwarding
...
fix: bedrock header forwarding with cutom api
2025-12-12 22:25:45 +05:30
Sameer Kankute
abbf8be07b
Merge pull request #17864 from BerriAI/litellm_fix_x-litellm-key-spend
...
Fix x-litellm-key-spend header update
2025-12-12 22:23:42 +05:30
Sameer Kankute
e0428388a7
Merge pull request #17860 from BerriAI/litellm_openai_files_expire_after_support
...
Add support for expires after param in Files endpoint
2025-12-12 22:23:11 +05:30
Alexsander Hamir
d196e0b9c8
refactor(router): replace time.perf_counter() with time.time() for timing measurements ( #17881 )
2025-12-12 08:51:18 -08:00
AlexsanderHamir
1ad6763500
fix: add PROMETHEUS_MULTIPROC_DIR to docs
2025-12-12 08:33:38 -08:00
Alexsander Hamir
d9cf53b555
fix: remove dependency on database and redis from health test ( #17880 )
2025-12-12 08:21:48 -08:00
Alexsander Hamir
9c39539d78
revert CI changes ( #17879 )
2025-12-12 08:13:18 -08:00
Alexsander Hamir
5f2f823d44
fix: use docker executor ( #17878 )
2025-12-12 07:56:03 -08:00
Alexsander Hamir
c9063d13b1
Add health endpoint tests to CI with database and Redis support ( #17877 )
...
- Add database and Redis setup to litellm_mapped_tests_proxy job in CircleCI
- Create shared test helpers in tests/test_litellm/proxy/conftest.py for proxy test setup
- Refactor health endpoint tests to use shared helpers from conftest
- Support automatic Redis cache configuration when REDIS_HOST is set
- Ensure minimal config is created when Redis/database is needed
2025-12-12 07:35:50 -08:00
Alexsander Hamir
762b429d6c
enhance: create_litellm_branch tool to be more robust ( #17874 )
2025-12-12 05:35:50 -08:00
Krish Dholakia
eab5bca583
Add Milvus REST client and update examples ( #17736 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2025-12-12 04:38:28 -08:00
Devaj Mody
f25344484f
fix(router): add minimum request threshold for error rate cooldown ( #17464 )
...
Fixes #17418
- Add DEFAULT_FAILURE_THRESHOLD_MINIMUM_REQUESTS constant (default: 5)
- Require minimum requests before applying error rate cooldown
- Prevents cooldown from triggering on first failure
2025-12-12 04:36:10 -08:00
razvan_butnaru
f6251efab9
Update proxy_server.py ( #17468 )
...
Co-authored-by: razvan9991 <57962056+razvan9991@users.noreply.github.com>
2025-12-12 04:34:43 -08:00
Sameer Kankute
d28160b2b2
Add tests for header forwarding
2025-12-12 17:54:17 +05:30
Ariel
5df701d15c
[feat]: Add opt-in evidence results for Pillar Security guardrail during monitoring ( #17812 )
...
* add evidence headers to litellm
* ensure that evidence is surface-able, even in opt-in mode
* update the docs
2025-12-12 04:09:13 -08:00
