WilsonSunBritten
4ea92d96cb
lint fix
2025-08-28 17:11:50 -06:00
WilsonSunBritten
0721345703
Switch to string constant based truncation
2025-08-28 16:28:36 -06:00
Ishaan Jaff
f3338bef9f
[MCP] Bug fix - adding SSE MCP tools - fix connection test when adding MCPs ( #14048 )
...
* fix: _execute_with_mcp_client
* add warning for SSE MCP
* docs - MCP videos / guides
2025-08-28 15:16:34 -07:00
Ishaan Jaff
37a599932d
[Bug Fix] Virtual keys with llm_api type cause Internal Server Error when using /anthropic/* and other llm passthrough routes ( #14046 )
...
* fix route checks passthrough_routes_wildcard
* refactor check_route_access
* test_virtual_key_llm_api_route_includes_passthrough_prefix
2025-08-28 15:14:09 -07:00
WilsonSunBritten
026480358b
Revert "Allow configuration to on what threshold to try truncating request content in db"
...
This reverts commit 771052d67d
2025-08-28 16:12:42 -06:00
lmwang
6760a6aaa1
Fix LoggingWorker graceful shutdown to prevent CancelledError warnings
...
- Change exception logging to debug level during shutdown cancellation
- Add clear_queue() call to process remaining coroutines during shutdown
- Prevents 'RuntimeWarning: coroutine was never awaited' messages
- Add comprehensive tests for graceful shutdown behavior
Fixes #13970
2025-08-28 14:15:17 -07:00
Const-antine
f8d1e03450
rework tests
2025-08-28 13:39:09 -04:00
Const-antine
1350336515
fix tests
2025-08-28 13:30:11 -04:00
Const-antine
d3b526041f
better formatting
2025-08-28 13:18:36 -04:00
Const-antine
730e9c90a2
fix formatting
2025-08-28 13:18:33 -04:00
Const-antine
5d973ea06e
update readme
2025-08-28 13:18:26 -04:00
Const-antine
409429ddd6
add new tests
2025-08-28 13:18:23 -04:00
Const-antine
ff4040bbe1
add functionality to mount existing configmap if needed
2025-08-28 13:18:05 -04:00
Wilson Britten
771052d67d
Allow configuration to on what threshold to try truncating request content in db
2025-08-28 09:48:50 -06:00
Diogo Munaro Vieira
d2ffca24bb
fix: timedelta as cache serializable error
2025-08-28 11:42:25 -03:00
0x5751
323fe8aeac
docs: add documentation for LITELLM_ANTHROPIC_DISABLE_URL_SUFFIX environment variable
...
Added comprehensive documentation for the new LITELLM_ANTHROPIC_DISABLE_URL_SUFFIX configuration option that allows users to disable automatic URL suffix appending when using custom Anthropic API endpoints. This is useful for proxy servers or custom endpoints that don't follow Anthropic's standard URL structure.
Changes:
- Added environment variable to Anthropic provider docs with examples
- Created "Custom API Base" section explaining usage scenarios
- Added entry to environment variables reference table in config settings
2025-08-28 22:21:41 +08:00
gotsysdba
15f1d82536
Fix tests
2025-08-28 14:54:38 +01:00
gotsysdba
87abfc3c11
Adding oci_key_file support for oci provider
2025-08-28 14:37:53 +01:00
Mohse Morad
d217c400df
Remove redundent
2025-08-28 12:26:18 +03:00
Mohse Morad
8cce5e6307
Added tests
2025-08-28 12:21:35 +03:00
Tomu Hirata
11228e946b
add supported text field to anthropic citation response
2025-08-28 14:39:00 +09:00
Krish Dholakia
e638c5490d
Merge pull request #13945 from NoWall57/feature/force-anthropic-custom-api-base
...
feat: Add support for custom Anthropic-compatible API endpoints
2025-08-27 22:28:55 -07:00
Krish Dholakia
74c9663189
Merge pull request #12797 from ericgtkb/fix-vertex-ai-anyof
...
Fix additional anyOf corner cases for Vertex AI Gemini tool calls - issue #11164
2025-08-27 22:26:13 -07:00
Krish Dholakia
68f4847659
Merge pull request #12865 from aholmberg/holmberg/default-reasoning
...
fix: make gemini and openai responses return reasoning by default
2025-08-27 22:25:30 -07:00
Krish Dholakia
fc738c5822
Merge branch 'main' into holmberg/default-reasoning
2025-08-27 22:25:22 -07:00
Krish Dholakia
df39320889
Merge pull request #12885 from xywei/main
...
Remove vector store methods from global scope
2025-08-27 22:22:59 -07:00
Krish Dholakia
67d432a6d7
Merge pull request #13243 from nagyv-team/main
...
Ensure that `function_call_prompt` extends system messages following its current schema
2025-08-27 22:16:53 -07:00
Krish Dholakia
10816a44d4
Merge pull request #13160 from pangeacyber/aidr-update
...
Update Pangea Guardrail to support new AIDR endpoint
2025-08-27 22:15:32 -07:00
Krish Dholakia
cf491a7931
Merge pull request #13562 from qidu/main
...
refactor(router): choose weights by 'weight', 'rpm', 'tpm' in one loop for simple_shuffle
2025-08-27 22:13:42 -07:00
Krish Dholakia
c692f19346
Merge branch 'main' into main
2025-08-27 22:13:29 -07:00
Krish Dholakia
12bef8fbf4
Merge pull request #13691 from timelfrink/feat/github-copilot-thinking-reasoning-support
...
feat: Add thinking and reasoning_effort parameter support for GitHub Copilot provider
2025-08-27 22:09:22 -07:00
Krish Dholakia
a913ecf60b
Merge branch 'main' into feat/github-copilot-thinking-reasoning-support
2025-08-27 22:09:15 -07:00
Krish Dholakia
f01c7d13e7
Merge pull request #13991 from ikaadil/fix/gemini-imagen-model-name-validation
...
[Bug Fix] Resolve invalid model name error for Gemini Imagen models
2025-08-27 21:56:19 -07:00
Krish Dholakia
f764e415be
Merge pull request #14012 from KRRT7/in-memory-cache-optimization
...
⚡ ️ Speed up InMemoryCache.evict_cache by 21%
2025-08-27 21:55:34 -07:00
Ishaan Jaff
d5774d89cc
Update Docker image tag to v1.75.8-stable ( #14014 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: ishaan <ishaan@berri.ai>
2025-08-27 16:44:50 -07:00
Ishaan Jaff
04dc1a5351
[Feat] Add support for returning images with gemini/gemini-2.5-flash-image-preview with /chat/completions ( #13983 )
...
* add gemini-2.5-flash-image-preview
* add gemini-2.5-flash-image-preview
* add image in ChatCompletionResponseMessage
* test_gemini_image_generation_async
* Revert "Merge pull request #13394 from Deviad/feature/enhance_logging_for_containers"
This reverts commit 539b94ad4e71af7bcf9c
2025-08-27 16:16:19 -07:00
Xingyao Wang
9acf80b8ad
Fix issue #13995 : Handle None metadata in batch requests ( #13996 )
...
* Fix issue #13995 : Handle None metadata in batch requests
- Added null check in add_key_level_controls method to prevent NoneType error
- Updated type hint to Optional[dict] for better type safety
- Added comprehensive test suite to verify the fix works correctly
- All existing tests pass, confirming no regression
Fixes #13995
Co-authored-by: openhands <openhands@all-hands.dev>
* Move test file to tests/test_litellm/proxy/ directory
- Moved test_batch_metadata_none_fix.py from tests/ to tests/test_litellm/proxy/
- Updated import structure to match existing test patterns
- This ensures the test runs in GitHub Actions as requested by @krrishdholakia
Co-authored-by: openhands <openhands@all-hands.dev>
---------
Co-authored-by: openhands <openhands@all-hands.dev>
2025-08-27 14:51:09 -07:00
Ishaan Jaff
165242e31f
[Feat] langfuse_otel logger - allow using LANGFUSE_OTEL_HOST for configuring host ( #14013 )
...
* feat - add _get_langfuse_otel_host
* test_get_langfuse_otel_config_with_otel_host_priority
* docs: LANGFUSE_OTEL_HOST
2025-08-27 14:43:47 -07:00
Ifta Khairul Alam Adil
75aeca14b2
Merge branch 'main' into fix/gemini-imagen-model-name-validation
2025-08-27 21:52:47 +02:00
Sam Xie
ee13c65701
[Bug]: /responses endpoint proxy ignores extra_headers in GitHub Copilot ( #13775 )
...
* fix: pass extra_headers parameter through responses API transformation chain
Ensure extra_headers parameter is properly forwarded from the responses() function
through the transformation handler and config to maintain header propagation in
litellm_completion_request dict.
* Add tests
2025-08-27 12:35:09 -07:00
Ishaan Jaff
4fff05f1cc
[Feature]: Support Gemini requests with only system prompt ( #14010 )
...
* _default_user_message_when_system_message_passed
* test_system_prompt_only_adds_blank_user_message
* test_system_message_with_no_user_message
2025-08-27 12:12:47 -07:00
Kevin Turcios
8404fdea5b
Update in_memory_cache.py
2025-08-27 13:35:48 -05:00
Ishaan Jaff
f35ce02475
[Bug Fix] LLM Translation - Allow using dynamic api_key for image generation requests ( #14007 )
...
* fix - allow using dyanmic api key for img gen
* test_aiml_image_generation_with_dynamic_api_key
2025-08-27 10:51:24 -07:00
Ifta Khairul Alam Adil
d9f8eb27c9
fix: enable tool choice support for model prices and context window
...
- Updated the "supports_tool_choice" field to true in the model_prices_and_context_window.json file, allowing for tool choice functionality in the specified model.
Signed-off-by: Ifta Khairul Alam Adil <ikaadil007@gmail.com>
2025-08-27 19:46:53 +02:00
Ishaan Jaff
ed52b67fcf
test_image_edit_array_handling
2025-08-27 09:51:22 -07:00
Ishaan Jaff
d5440f9614
test_image_edit_array_handling
2025-08-27 08:27:57 -07:00
Ishaan Jaff
76f78f7b2a
fix: LITELLM_LOG_FILE test
2025-08-27 08:25:24 -07:00
Ifta Khairul Alam Adil
8808f78ba6
Merge branch 'main' into fix/gemini-imagen-model-name-validation
2025-08-27 15:45:59 +02:00
Mohse Morad
cb65c98389
Fix lint
2025-08-27 15:25:42 +03:00
Mohse Morad
369aa02c4b
Bedrock handle json mode check correctly
2025-08-27 14:51:43 +03:00
