tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-15 10:24:33 +00:00
Code Issues Packages Projects Releases Wiki Activity
29,008 Commits 2,072 Branches 1,425 Tags
d7647f5b868f5cc6dd2600a8cdc7eaa53d8d49ac
Commit Graph
1888 Commits
Author SHA1 Message Date
Lucas SugiandGitHub 9f88d61d10 fix: Change extra_headers to additional_headers (#17950) 2025-12-18 08:57:20 +05:30
yuneng-jiangandGitHub 7b2f33b9b4 Merge pull request #17559 from BerriAI/litellm_new_user_collision_handling 
[Fix] New user route user_id collision handling
 2025-12-17 19:19:41 -08:00
yuneng-jiangandGitHub 1db7492639 Merge pull request #18159 from BerriAI/litellm_login_500_fix 
[Fix] Login Page Failed To Parse JSON Error
 2025-12-17 19:19:27 -08:00
yuneng-jiangandGitHub 866d1eded5 Merge pull request #17995 from BerriAI/litellm_email_budget_alerts_2 
[Feature] Email Budget Alerts
 2025-12-17 19:16:17 -08:00
yuneng-jiang dd182a2ed0 Adding tests 2025-12-17 16:28:15 -08:00
yuneng-jiang f4017a1986 Tests 2025-12-17 16:07:01 -08:00
YutaSaitoandGitHub 6595619906 Merge pull request #18150 from BerriAI/litellm_feat_vault-per-team-config 
Litellm feat vault per team config
 2025-12-18 06:57:24 +09:00
Yuta Saito b7b22d559e feat: allow per-team Vault overrides when storing keys 2025-12-18 06:21:53 +09:00
Dmitri TikhonovGitHubClaude
 		844d0d47b7 Fix tag management to preserve encrypted fields in litellm_params (#17484) 
The _add_tag_to_deployment function was directly modifying the
deployment's litellm_params in memory and writing it back to the
database, which caused encrypted API keys and other sensitive fields
to be lost. This fix retrieves the model from the database first,
preserves all existing fields including encrypted ones, adds only the
new tag to the tags array, and updates the database with the modified
params while keeping encrypted fields intact.

Added comprehensive unit tests covering preservation of encrypted
fields, handling of both string and dict litellm_params formats,
duplicate tag prevention, and error handling for missing models.

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

Co-authored-by: Claude <noreply@anthropic.com>
 2025-12-18 02:28:39 +05:30
Ishaan JaffandGitHub 539f629eff [Feat] New Logging Integration - Azure Sentinel Logger (#18146) 
* add AzureSentinelLogger

* logging: AzureSentinelLogger

* test_azure_sentinel_signature_and_send_batch

* docs azure sentinel

* fix AzureSentinelLogger

* test fix

* docs fix

* fix: AzureSentinelLogger

* docs sentintel

* feat: add example SLP

* docs sentinel

* docs fix

* docs fix

* docs fix

* fix code qa

* QA fix

* fix test

* TestInitializeInteractionsEndpoints
 2025-12-18 02:04:49 +05:30
yuneng-jiang 087dfbf648 Merge remote-tracking branch 'origin' into litellm_email_budget_alerts_2 2025-12-17 11:37:49 -08:00
yuneng-jiang 8cdb481832 Merge remote-tracking branch 'origin' into litellm_new_user_collision_handling 2025-12-17 11:34:46 -08:00
yuneng-jiangandGitHub 49a1e50672 Merge pull request #17912 from BerriAI/litellm_dd_callback_fix 
[Fix] Callback Environment Variables Casing
 2025-12-17 11:33:41 -08:00
yuneng-jiangandGitHub 202f71c13a Merge pull request #17752 from BerriAI/litellm_ui_model_test_connection_fix 
[Fix] /health/test_connection to resolve env variables like /chat/completions
 2025-12-17 11:06:57 -08:00
yuneng-jiang 70f7c8b771 Merge remote-tracking branch 'origin' into litellm_dd_callback_fix 2025-12-17 11:05:46 -08:00
yuneng-jiangandGitHub 358ee482e2 Merge pull request #18078 from BerriAI/litellm_sso_readiness_route 
[Feature] SSO Readiness Health Check
 2025-12-17 11:03:53 -08:00
Sameer KankuteandGitHub a13611dcdb Merge branch 'main' into litellm_image_edit_vertex_cred_fix 2025-12-17 22:38:07 +05:30
Sameer KankuteandGitHub 230db7e161 Merge pull request #18100 from BerriAI/litellm_bedrock_qwen_arn_fix 
fix: Add qwen 2 and qwen 3 in get_bedrock_model_id
 2025-12-17 22:34:05 +05:30
Sameer KankuteandGitHub 25f2213262 Merge pull request #18135 from BerriAI/litellm_gemini_flash_day_0 
feat: gemini-3-flash-preview day 0 support
 2025-12-17 22:30:10 +05:30
Sameer KankuteandGitHub 95b2e72dfc Merge pull request #18105 from BerriAI/litellm_staging_12_17_2025 
Staging - 12/17/2025
 2025-12-17 22:23:21 +05:30
Sameer Kankute e3cf0110bb Rename: gemini-3-flash-preview 2025-12-17 21:48:15 +05:30
Alexsander HamirandGitHub e96b301642 Fix: Prevent LiteLLM API key leakage on /health endpoint failures (#18133) 2025-12-17 08:08:05 -08:00
Sameer Kankute ba90985300 Add reasoning effort mapping 2025-12-17 18:03:48 +05:30
Sameer Kankute ed6c66c20c Add support for structured output thinkingConfig param 2025-12-17 18:02:15 +05:30
Sameer Kankute 969ed1efb8 fix: Vertex AI image edit credential source 2025-12-17 15:56:10 +05:30
CurtisandGitHub d1c6eb3a7c fix(image_edit): add drop_params support and fix Vertex AI config (#18077) 2025-12-17 11:28:34 +05:30
yuneng-jiangandGitHub 9faee8bba6 Merge pull request #17989 from Jetemple/non-root-ui-path-fix 
fix: update UI path handling for non-root Docker and restructure HTML…
 2025-12-16 21:57:31 -08:00
jk-f5andGitHub 576580244f fix(azure_ai): return AzureAnthropicConfig for Claude models in get_provider_chat_config (#18086) 
Claude models on Azure AI were incorrectly using AzureAIStudioConfig,
causing tool calls to fail with invalid_request_error because tools
remained in OpenAI format instead of being transformed to Anthropic format.
 2025-12-17 11:24:04 +05:30
Sameer Kankute f83b821f3d fix: Add qwen 2 and qwen 3 in get_bedrock_model_id 2025-12-17 09:22:55 +05:30
yuneng-jiangandGitHub f316caa088 Merge pull request #18033 from BerriAI/litellm_ui_logs_overhead 
[Feature] Add LiteLLM Overhead to Logs
 2025-12-16 14:51:50 -08:00
Ishaan JaffandGitHub c727c8216f [Feat] New Endpoint - Google Interactions API - added on litellm SDK (#18079) 
* init BaseInteractionsAPIConfig

* updated types for interactions API

* fix SDK level interactions API

* InteractionsAPIRequestUtils

* init base

* init interactions API

* init Interactions API Types

* init interactins API

* GoogleAIStudioInteractionsConfig

* init http handler

* remove file no longer needed

* test OPENAPI_SPEC_URL

* TestGoogleInteractionsCreate
 2025-12-17 02:18:51 +04:00
yuneng-jiang 2d8f5111af add /sso/readiness route 2025-12-16 13:16:13 -08:00
yuneng-jiang 0e5b56eddf Fixing tests 2025-12-16 12:51:44 -08:00
Alexsander HamirandGitHub 80d445a96f feat: lazy load GuardrailItem following existing patterns (#18072) 
- Add TYPES_NAMES tuple and _lazy_import_types function in _lazy_imports.py
- Remove direct import of GuardrailItem from __init__.py
- Add lazy loading handler in __getattr__ to dispatch type imports
- Add type stub for GuardrailItem in TYPE_CHECKING block
- Add test_types_lazy_imports test to verify lazy loading works
- Use from __future__ import annotations for forward reference support
- Follows same pattern as DOTPROMPT_NAMES and LLM_CONFIG_NAMES for consistency
 2025-12-16 11:48:36 -08:00
Alexsander HamirandGitHub 014c74fd06 [Refactor] litellm/init.py: lazy-load AmazonConverseConfig (#18069) 
- Add LLM_CONFIG_NAMES tuple and _lazy_import_llm_configs function in _lazy_imports.py
- Remove direct import of AmazonConverseConfig from __init__.py
- Add lazy loading handler in __getattr__ to dispatch LLM config imports
- Add type stub for AmazonConverseConfig in TYPE_CHECKING block
- Add test_llm_config_lazy_imports test to verify lazy loading works
- Follows same pattern as DOTPROMPT_NAMES for consistency
 2025-12-16 10:48:11 -08:00
Sameer KankuteandGitHub 2b495f84ab Merge pull request #18025 from BerriAI/litellm_staging_12_16_2025 
Litellm staging 12 16 2025
 2025-12-16 22:31:39 +05:30
Sameer KankuteandGitHub 3661f8010f Revert "fix(proxy): extract model from vertex ai passthrough url pattern (#17…" 
This reverts commit ae7c994526.
 2025-12-16 21:44:10 +05:30
Sameer KankuteandGitHub 8864c6937c Merge pull request #18031 from BerriAI/litellm_anthropic_claude_skills_int 
Add support for agent skills in chat completion
 2025-12-16 21:39:11 +05:30
Sameer KankuteandGitHub 215857cce3 Merge branch 'main' into litellm_staging_12_16_2025 2025-12-16 21:38:14 +05:30
Sameer KankuteandGitHub abfa869030 Merge pull request #18049 from BerriAI/litellm_bedrock_ttl_issue 
Remove ttl field when routing to bedrock
 2025-12-16 21:34:57 +05:30
Sameer KankuteandGitHub 616417eaaa Merge pull request #18037 from BerriAI/litellm_fix_vertex_ai_headers 
fix: skip adding beta headers for vertex ai as it is not suppported
 2025-12-16 21:33:35 +05:30
Alexsander HamirandGitHub f8168f5063 [Refactor] litellm/init.py: lazy load dotprompt integration (#18056) 2025-12-16 07:18:11 -08:00
Alexsander HamirandGitHub feb6924efe [Refactor] litellm/init.py: lazy load .types.utils (#18054) 2025-12-16 06:42:17 -08:00
Alexsander HamirandGitHub ea06fb70fb refactor: lazy load bedrock types (#18053) 2025-12-16 06:05:01 -08:00
Alexsander HamirandGitHub 6ca812130b [Refactor] litellm/init.py: lazy load LLMClientCache (#18008) 2025-12-16 05:44:06 -08:00
Sameer Kankute 6ccfb8b45e Remove ttl fiedl when routing to bedrock 2025-12-16 16:20:19 +05:30
Nicolai van der SmagtandGitHub 09ba89d4fe fix: add headers to metadata for guardrails on pass-through endpoints (#17992) 
Fixes #17477

Guardrails couldn't access request headers (like User-Agent) on Bedrock
pass-through endpoints because headers were only stored in
data["proxy_server_request"]["headers"] but not in data["metadata"]["headers"]
where guardrails typically look for them.

This fix adds headers to metadata in add_litellm_data_to_request() so
guardrails can access User-Agent, API keys, and other header-based checks
on all endpoints including Bedrock pass-through.

Test added to verify headers are available in metadata for guardrails.
 2025-12-16 13:41:34 +05:30
Sameer Kankute 7a5e49a328 fix: skip adding beta headers for vertex ai as it is not suppported 2025-12-16 11:56:46 +05:30
yuneng-jiang c5e25a1728 Merge remote-tracking branch 'origin' into litellm_ui_model_test_connection_fix 2025-12-15 21:07:32 -08:00
yuneng-jiang 66306f21b1 Add litellm overhead to spend logs metadata 2025-12-15 20:56:55 -08:00