yuneng-jiang
13adaa4a73
Merge remote-tracking branch 'origin' into litellm_sso_role_mapping
2025-12-22 09:44:04 -08:00
yuneng-jiang
31cc9654ce
Merge remote-tracking branch 'origin' into litellm_ui_cloudzero_improvements
2025-12-22 09:43:23 -08:00
Sameer Kankute
6d5eb07496
Merge pull request #18336 from BerriAI/litellm_add_nova_image_embedding_support
...
fix: request body for image embedding request
2025-12-22 19:11:42 +05:30
Ishaan Jaff
268ed11a01
Litellm content filter logs page ( #18335 )
...
* add view for litellm content filter
* add ContentFilterDetails
* test_apply_guardrail_logs_guardrail_information
* backend track litellm content filter
* ui view
* fix code qa check
2025-12-22 18:20:26 +05:30
Ishaan Jaff
2677d9d30d
[Feat] New provider TTS - Add AWS polly API for TTS ( #18326 )
...
* add aws_polly as new provider
* init AWSPollyTextToSpeechConfig
* test_aws_polly_tts_with_native_voice
* init aws_polly + AWS polly dispatch
* init AWSPollyTextToSpeechConfig
* fix transform
* add aws_polly as a new provider for TTS API
* add to sidebar
* docs aws polly
* code qa fix
* add AWS Polly Text-to-Speech
* add cost tracking for AWS polly
* docs fix
2025-12-22 18:19:34 +05:30
Sameer Kankute
9f9d7fe7a0
Merge pull request #18328 from BerriAI/litellm_add_usage_in_image_generation
...
Add usage object in image generation of gemini
2025-12-22 16:59:42 +05:30
Sameer Kankute
5bd014fd3f
Merge pull request #18327 from BerriAI/litellm_add_image_tokens_in_chat_completion
...
Add image tokens in chat completion
2025-12-22 16:59:30 +05:30
Sameer Kankute
cbc1ac9508
fix: request body for image embedding request
2025-12-22 16:55:04 +05:30
Ishaan Jaffer
57e07bddd3
fix remove flaky test
2025-12-22 16:32:13 +05:30
Ishaan Jaffer
09dcb38b4b
Revert "test_update_model_cost_map_url"
...
This reverts commit c9d61fcdba
2025-12-22 12:41:30 +05:30
Sameer Kankute
b01eb2b970
Add usage object in image generation of gemini
2025-12-22 11:59:30 +05:30
Ishaan Jaffer
c9d61fcdba
test_update_model_cost_map_url
2025-12-22 11:51:30 +05:30
Sameer Kankute
60b71d48bd
Add test image tokens in output
2025-12-22 11:46:14 +05:30
Yuta Saito
34b500c7f5
feat: support MCP stdio header env overrides
2025-12-22 12:58:31 +09:00
Yuta Saito
41bbb3a6a5
feat: datadog log trace linking
2025-12-22 06:53:44 +09:00
Yuta Saito
01aa082d16
fix: call datadog_handler
2025-12-22 05:33:39 +09:00
Yuta Saito
470179af2f
Revert "Revert "fix: ensure Datadog callback runs alongside LLM Observability" ( #18313 )"
...
This reverts commit 0acca76677
2025-12-22 05:22:42 +09:00
Harshit Jain
b2588dc399
fix: lost tool_calls when streaming has both text and tool_calls
2025-12-21 22:40:27 +05:30
Ishaan Jaffer
1f3a5756a1
test realtime fix
2025-12-21 10:21:25 +05:30
Ishaan Jaff
0acca76677
Revert "fix: ensure Datadog callback runs alongside LLM Observability" ( #18313 )
2025-12-21 09:13:28 +05:30
Alexsander Hamir
852bf63698
[Fix] CI/CD - check_code_and_doc_quality ( #18309 )
2025-12-20 17:34:08 -08:00
Alexsander Hamir
23477e7621
[Fix] CI/CD - test_openai_realtime_direct_call_with_intent ( #18308 )
2025-12-20 17:32:20 -08:00
Emerson Gomes
acce6b9c83
Apply suggestion from @Copilot
...
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-12-20 15:56:46 -06:00
YutaSaito
716cac4e3b
Merge pull request #18300 from BerriAI/litellm_fix_datadog-dual-callback-conflict
...
fix: ensure Datadog callback runs alongside LLM Observability
2025-12-21 06:22:21 +09:00
Yuta Saito
b54216d05f
fix: ensure Datadog callback runs alongside LLM Observability
2025-12-21 05:46:34 +09:00
Alexsander Hamir
699a91e031
fix(test): Fix test_users_in_team_budget to create user with team_id ( #18297 )
...
Previously, the test created a user first (without team_id), then added them
to a team. This caused the API key to have team_id=None, which broke team
budget tracking and enforcement.
The fix:
- Create team first, then create user with team_id parameter
- This ensures the API key gets team_id set from creation time
- Team budget tracking and enforcement now work correctly
Added comprehensive comments explaining why the order is critical and should
not be changed, as it tests the intended flow where keys are associated with
teams at creation time.
Also added extensive debugging output to help diagnose future issues.
2025-12-20 12:30:30 -08:00
Alexsander Hamir
5a76aada3c
[Fix] CI/CD - responses_api_testing ( #18295 )
2025-12-20 10:27:58 -08:00
Ishaan Jaffer
148715541c
test compl openai orgs
2025-12-20 23:41:29 +05:30
Ishaan Jaffer
de65f0e777
TestAzureOpenAIO3Mini
2025-12-20 23:18:19 +05:30
Ishaan Jaffer
179eb8815d
test_azure_safety_result
2025-12-20 22:40:53 +05:30
Ishaan Jaffer
987c9a608b
TestAzureOpenAIO3Mini
2025-12-20 22:37:59 +05:30
Ishaan Jaffer
b1090db927
test_openai_stream_options_call
2025-12-20 22:35:21 +05:30
Emerson Gomes
9002f75277
Require auth for MCP connection test
2025-12-20 11:01:41 -06:00
Ishaan Jaffer
9f205b0323
TestAzureOpenAIO3Mini
2025-12-20 21:52:28 +05:30
Ishaan Jaffer
7eb2af1959
test bad org fix
2025-12-20 21:43:27 +05:30
Ishaan Jaffer
abf14663ed
test_slack_gif_skill_creates_gif
2025-12-20 21:35:25 +05:30
Ishaan Jaffer
6112160a16
Revert "[Fix] Security - Remove example API keys with high entropy ( #18255 )"
...
This reverts commit 24edbccf5c
2025-12-20 20:48:11 +05:30
Ishaan Jaffer
7232039779
test fixes
2025-12-20 15:38:20 +05:30
Ishaan Jaffer
7d28485cb5
test_amazon_titan_image_gen
2025-12-20 15:16:55 +05:30
Ishaan Jaffer
eec05c036a
test_create_skill_sdk
2025-12-20 15:08:31 +05:30
Ishaan Jaffer
c13b4c5514
test_aaapass_through_endpoint_pass_through_keys_langfuse
2025-12-20 14:36:59 +05:30
Ishaan Jaffer
627d615322
test_amazon_titan_image_gen
2025-12-20 14:36:50 +05:30
Ishaan Jaffer
859474dd44
fix patch
2025-12-20 14:00:42 +05:30
Ishaan Jaffer
c1b116c5f5
fix
2025-12-20 13:54:05 +05:30
Cesar Garcia
138b415e81
fix(responses-api): use list format with input_text for tool results ( #18257 )
...
The Responses API expects tool results to use input_text/input_image types,
not output_text. This fix ensures consistent list format for all tool results:
- String content → [{"type": "input_text", "text": "..."}]
- Image content → [{"type": "input_image", "image_url": "..."}]
This resolves the conflict between tests that expected different formats
and aligns with OpenAI's Responses API requirements.
Fixes the regression introduced in #18226 .
2025-12-20 13:46:14 +05:30
Lucas Rothman
b981fddfaa
fix(gemini): properly catch context window exceeded errors
...
Fixes #18282
This PR fixes two issues with Gemini context window error handling:
1. **Pattern matching for Gemini 2.0 Flash**: The previous pattern
'input token count exceeds the maximum number of tokens allowed'
doesn't match Gemini 2.0 Flash errors which include dynamic token
counts like '(2800010)' in the message. Split into shorter patterns
that work with both formats.
2. **Add context window check to Gemini block**: The
is_error_str_context_window_exceeded() check was only called for
OpenAI-compatible providers, not for Gemini/Vertex AI. Added the
check to the Gemini-specific error handling block.
Test cases added for both Gemini 2.0 Flash and 2.5/3 error formats.
2025-12-19 23:20:04 -08:00
Eric84626
0306f02e74
fix: removed initialize the tool name to MCP server name mapping(oauth2) on startup for avoiding 401 error
2025-12-20 14:13:18 +08:00
Eric84626
684fba42ea
fix: added RFC RECOMMENDED property(scopes_supported) to protected resource and authorization server metadata
2025-12-20 13:22:29 +08:00
Eric84626
3a2ab6b0d1
fix: added additional grant type into oauth_authorization_server response for fixing mcp auth register bad request issue
2025-12-20 11:55:12 +08:00
yuneng-jiang
ffcac2eebc
Allow deleting key expiry
2025-12-19 18:04:04 -08:00
