ai-workspace-services/litellm
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
26,690 Commits 9 Branches 7 Tags 935 MiB
e1cb92862e
Commit Graph

26690 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Ishaan Jaff
e1cb92862e
[Feat] Add def search() APIs for Web Search - Perplexity API (#15769) 
* add BaseSearchConfig

* add BaseSearchConfig

* validate_environment

* fix handlers

* add PerplexitySearchConfig

* add PerplexitySearchConfig

* add LiteLLM Search API module.

* add BaseSearchConfig

* add _build_search_optional_params

* add search_testing

* add BaseSearchTest

* add TestPerplexitySearch

* fix BASE

* fix handler

* add search API

* add to init

* fix: working perplexity search API

* add _hidden_params to search
 2025-10-21 16:58:51 -07:00
Ishaan Jaff
9135e748a0
[Feat ] /ocr - Add mode + Health check support for OCR models (#15767) 
* get_mode_handlers

* use get_mode_handlers

* test_ahealth_check_ocr

* Add OCR mode to test models

* docs OCR Health Checks

* fix connection endpoint
 2025-10-21 16:58:37 -07:00
Javier Garcia
b0a3a7c4fb
Add details in docs (#15721) 
* Add details in docs

* add logic to set span attributes and unit tests

* Restore html files

* Remove html files

* Remove html files
 2025-10-21 16:57:51 -07:00
Thomas Mildner
1cfc4624c3
[Feat] Add SENTRY_ENVIRONMENT configuration for Sentry integration (#15760) 
* [Feat] Add SENTRY_ENVIRONMENT configuration for Sentry integration and corresponding tests

* [Refactor] Enhance test_sentry_environment by mocking sentry_sdk and improving environment handling

* [Fix] Update default SENTRY_ENVIRONMENT to 'production' and enhance test for Sentry integration

* [Fix] Update test_sentry_environment to verify correct handling of SENTRY_ENVIRONMENT values

* [Fix] Update test_sentry_environment to assert correct handling of production environment
 2025-10-21 16:40:55 -07:00
Kowyo
1fcadd6c05
feat(ollama): set 'think' to False when reasoning effort is not high/medium/low (#15763) 2025-10-21 16:39:08 -07:00
Krrish Dholakia
2a1dbb5b9e docs(creating_adapters.md): document how to write an adapter 2025-10-21 16:20:31 -07:00
nuernber
353dfb1238
Add AWS us-gov-west-1 Claude 3.7 Sonnet costs (#15775) 
* add us-gov-west-1 claude 3.7 sonnet to prices

* add to _backup file as well
 2025-10-21 16:17:07 -07:00
YutaSaito
39641e7e68
chore: rename GraySwan to Gray Swan (#15771) 2025-10-21 15:18:55 -07:00
Vinod Singh
d4aadda692
Auth Header Fix for MCP Tool Call (#15736) 
* fixed the Auth header for MCP Tool Call

* Final fix for Auth header

* testcase for mcp_auth_header_extraction, insensitive_alias_matching, insensitive_servername_matching added
 2025-10-21 13:58:03 -07:00
Krrish Dholakia
1e0368521e refactor: cleanup 2025-10-21 13:46:19 -07:00
Ishaan Jaffer
3741c43396 docs fix 2025-10-21 13:21:59 -07:00
Ishaan Jaff
8ad9bbbd02
[Docs] Add Azure AI - OCR to docs (#15768) 
* add Azure OCR to docs

* docs fix

* docs fix

* docs fix

* docs OCR
 2025-10-21 13:10:45 -07:00
Ishaan Jaffer
185182bebc Revert "add Azure OCR to docs" 
This reverts commit a3699e28a4.
 2025-10-21 13:02:31 -07:00
Ishaan Jaffer
a3699e28a4 add Azure OCR to docs 2025-10-21 13:02:21 -07:00
Ishaan Jaffer
6605aba307 docs grayswan 2025-10-21 11:16:25 -07:00
YutaSaito
d79bdd491f
feat: add GraySwan Guardrails support (#15756) 2025-10-21 11:13:50 -07:00
Talal
46d55bd92a
fix: Add response_type + PKCE parameters to OAuth authorization endpoint (#15720) 
* fix: Add response_type parameter to OAuth authorization endpoint

Fixes #15684

OAuth providers like Google require the response_type parameter during
the authorization flow. This commit adds response_type=code to the
authorization redirect parameters, which is required by the OAuth 2.0
specification (RFC 6749 Section 4.1.1).

Changes:
- Added response_type=code to authorization params in discoverable_endpoints.py
- Added test coverage for the response_type parameter

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

* fix oauth flow by forwarding code_challenge and forwarding code_verifier

---------

Co-authored-by: Claude <noreply@anthropic.com>
 2025-10-21 09:43:19 -07:00
Tom Haynes
98f1d63508
use correct otel logger, and normalise otel paths (#15645) 2025-10-21 09:16:03 -07:00
Ishaan Jaffer
8b522d88a2 is_llm_api_route 2025-10-20 18:05:35 -07:00
Ishaan Jaff
92335d991c
[Feat] Add Azure AVA (Speech AI) Cost Tracking (#15754) 
* add azure/speech/ cost tracking

* test_azure_ava_tts_async

* add azure/speech to model cost map

* docs cost tracking

* docs tts AVA

* add azure/speech/azure-tts
 2025-10-20 18:01:51 -07:00
Ishaan Jaffer
60fab591db rename test files 2025-10-20 18:00:17 -07:00
Ishaan Jaff
157739da01
[Bug]: Fix Incorrect status value in responses api with gemini (#15753) 
* _map_chat_completion_finish_reason_to_responses_status

* test_transform_chat_completion_response_with_reasoning_content

* test_transform_chat_completion_response_output_item_status
 2025-10-20 17:58:56 -07:00
Ishaan Jaffer
5ce2be732e get_provider_text_to_speech_config 2025-10-20 17:10:09 -07:00
Ishaan Jaffer
9a25eeccb2 docs fix 2025-10-20 17:02:38 -07:00
Ishaan Jaffer
c9152003bd bump V 2025-10-20 16:55:03 -07:00
Ishaan Jaff
73a23a6c78
[Feat] Add Azure AVA TTS integration (#15749) 
* add AzureBaseIssueTokenHandler

* add BaseTextToSpeechConfig

* async_text_to_speech_handler

* add AzureAVATextToSpeechConfig

* add get_provider_text_to_speech_config

* add AzureAVATextToSpeechConfig

* fixes for base_llm_http_handler

* fix transform_text_to_speech_request

* test_azure_ava_tts_async

* test_azure_ava_tts_async

* fix TextToSpeechRequestData

* fix transform_text_to_speech_request

* add text_to_speech_handler in LLMHttpHandler

* remove old file

* fix transform_text_to_speech_request

* fix dispatch_text_to_speech

* fix azure TTS

* fix AVA TTS

* fix transform

* fix linting

* ci/cd - use one job for audio testing

* fix tests

* fix llm http handler debugging

* unit tests azure tts

* docs Azure speech

* docs fix

* docs azure AVA

* docs azure AVA

* fix handlers

* test_async_realtime_uses_max_size_parameter
 2025-10-20 16:52:23 -07:00
akraines
41a6ecd5b6
Change max_tokens value to match max_output_tokens for claude sonnet 4.5: 64000 (#15715) 
See https://github.com/RooCodeInc/Roo-Code/issues/8454
 2025-10-20 16:11:36 -07:00
Ishaan Jaff
0c25b1a256
[Fix] OpenAI Realtime API integration fails due to websockets.exceptions.PayloadTooBig error (#15751) 
* fix REALTIME_WEBSOCKET_MAX_MESSAGE_SIZE_BYTES

* edit max_size for websockets

* fix AzureOpenAIRealtime
 2025-10-20 15:54:14 -07:00
Sameer Kankute
1fb798f81d
(Bug) Fix JSON serialization error in Helicone logging by removing OpenTelemetry span from metadata (#15728) 
* remove span object from helicon metadata

* Add test
 2025-10-20 08:53:22 -07:00
Sameer Kankute
3955a3de5d
fix the wrong request body in json mode doc (#15729) 2025-10-20 08:44:14 -07:00
Timothée Lecomte
3ef9b2015a
feat: read from custom-llm-provider header (#15528) 2025-10-18 22:04:53 -07:00
jlan-nl
4a74190c12
Fix: Add gpt 4.1 pricing for response endpoint (#15593) 
* Add gpt41, gpt-41-mini, and gpt-41-nano to pricing and context window json

* Add gpt-41s to azure_llms dict

* Undo json changes

---------

Co-authored-by: IQHL (Hans Jacob Landelius) <iqhl@novnordisk.com>
 2025-10-18 22:04:14 -07:00
Lucas Sugi
ae86862e74
fix: Add function responsible to call precall (#15636) 
* fix: Add function responsible to call precall

* fix: Set correct route_type
 2025-10-18 22:01:14 -07:00
Lucas Sugi
ce9e22688d
fix: Add pre and post call for list batches (#15673) 2025-10-18 21:52:35 -07:00
Ishaan Jaff
f55745fc5e
[Fix] Forward anthropic-beta headers to Bedrock, VertexAI (#15700) 
* [Fix] Forward anthropic-beta headers to Bedrock and other cross-provider scenarios (#15623)

* add_provider_specific_headers_to_request

* fix add_provider_specific_headers_to_request

* test_provider_specific_header_multi_provider

* test_provider_specific_header_in_request

---------

Co-authored-by: Jack Venberg <jack.venberg@rover.com>
 2025-10-18 16:26:32 -07:00
Alexsander Hamir
441aed2c87
fix: update worker recommendation (#15702) 2025-10-18 16:24:32 -07:00
Ishaan Jaffer
3fc49a029f docs fix 2025-10-18 15:28:49 -07:00
Ishaan Jaffer
eed1ddba49 docs v1.78.5-stable 2025-10-18 15:28:07 -07:00
Ishaan Jaff
6ab9b0af9f
[Fix] Anthropic cache_control incorrectly applied to all content items instead of last item only (#15699) 
* fix: _safe_insert_cache_control_in_message

* test_anthropic_cache_control_hook_system_message

* docs prompt cache injection

* docs fix
 2025-10-18 15:18:08 -07:00
Jason Roberts
c471bf1f16
feat(guardrails): Add content masking and streaming support to PANW Prisma AIRS guardrail (#15666) 
* feat(guardrails): Add content masking and streaming support to PANW Prisma AIRS

- Add mask_request_content and mask_response_content parameters
- Implement content masking for prompts and responses
- Add streaming support with real-time masking
- Add comprehensive test coverage (28 tests)
- Update documentation with masking examples and security notes

* fix(guardrails): Fix PANW Prisma AIRS env var fallback and text completion support
 2025-10-18 13:57:51 -07:00
YutaSaito
645f84c02e
fix: add imagePullSecrets to migrations-job (#15681) 2025-10-18 13:56:31 -07:00
katsuhiro muto
d5e686b3e8
[Fix] Support service_tier in chat completion (#15693) 
* Support service_tier

* fix test
 2025-10-18 13:55:54 -07:00
Krish Dholakia
c1355e92dc
fix(proxy_server.py): re-encrypt env var on config save + use original value on decrypt error (#15671) 
* fix(proxy_server.py): re-encrypt env var on config save + use original value on decrypt error

Closes https://github.com/BerriAI/litellm/issues/14854

Fixes https://github.com/BerriAI/litellm/issues/13406

* docs: email.md

document PROXY_BASE_URL param

* fix(proxy_server.py): pop model list before writing to db
 2025-10-18 13:39:25 -07:00
Ishaan Jaffer
a91e3f1873 docs fix 2025-10-18 13:36:48 -07:00
Ishaan Jaff
2ec7ed2990
[Docs] v1.78.5 notes (#15698) 
* stash changes

* docs fix

* docs fix
 2025-10-18 13:35:42 -07:00
Ishaan Jaffer
c9875bfd52 bump: version 1.78.4 → 1.78.5 2025-10-18 13:31:39 -07:00
Ishaan Jaffer
f35a286f64 fix update_team 2025-10-18 13:23:51 -07:00
Ishaan Jaff
f92ddb1c05
fix: Successfully added rout (#15697) 2025-10-18 13:20:04 -07:00
Krish Dholakia
4e141df03a
(feat) Team level model-specific tpm/rpm limits + working key-level validation of tpm/rpm limit when assigned to team (#15513) 
* fix(support-model-specific-tpm/rpm-limits): Allows setting rate limits by tpm/rpm for models by team

* fix(key_management_endpoints.py): enforce guaranteed throughput with key-level model tpm/rpm limits, when team-level tpm/rpm limits are set

* test: add unit testing

* fix: fix minor linting errors

* fix: refactor
 2025-10-18 13:14:04 -07:00
Ishaan Jaffer
46d754a0f9 fix workflow 2025-10-18 11:14:18 -07:00