Sameer Kankute
c9de4776bc
Fix test_process_chunk_exception_calls_handle_failure_once
2026-01-19 19:39:12 +05:30
Sameer Kankute
d6baa9a4ba
Merge pull request #19234 from BerriAI/litellm_staging_01_16_2026
...
Litellm staging 01 16 2026
2026-01-19 19:34:53 +05:30
Harshit Jain
1dc2d2ddac
fix(utils.py): correctly extract messages from google genai contents ( #19156 )
...
* fix(utils.py): correctly extract messages from google genai contents
* refactor use shared utilities
2026-01-19 06:00:23 -08:00
Harshit Jain
98e87c3e67
feat: Add Redis-based migration lock with bug fixes ( #19261 )
2026-01-19 05:57:24 -08:00
Harshit Jain
fe92f4af9c
fix(langfuse_otel): ignore service logs and fix callback shadowing ( #19298 )
...
* fix(langfuse_otel): ignore service logs and fix callback shadowing
* add test cases for service logger
2026-01-19 05:53:47 -08:00
Cesar Garcia
b49f0a91e4
fix(responses): resolve deepcopy error with tool_choice ValidatorIterator ( #17192 ) ( #17205 )
...
Replace copy.deepcopy with model_dump + model_validate in streaming
iterator logging to handle Pydantic ValidatorIterator objects that
cannot be pickled when tool_choice uses allowed_tools mode.
Co-authored-by: Krish Dholakia <krrishdholakia@gmail.com>
2026-01-19 05:44:20 -08:00
Sameer Kankute
daf70f7221
Merge pull request #19329 from BerriAI/litellm_vector_store_sync
...
Fix: vector store sync issues
2026-01-19 19:11:48 +05:30
Manuel Schweigert
29adf34313
Add ChatGPT subscription support and responses bridge ( #19030 )
...
* Add ChatGPT subscription support and responses bridge
* Fix typing import for responses bridge
* Guard device code timestamp parsing
* add /v1/messages endpoint to chatgpt model
2026-01-19 05:37:45 -08:00
Sameer Kankute
574391c118
Revert "Fix audio cost per second override ( #19158 )"
...
This reverts commit 2a0f87bde0
2026-01-19 18:51:08 +05:30
Jón Levy
5db0e3289a
fix(agentcore): simplify agentcore streaming ( #17141 )
...
* fix(agentcore): simplify agentcore streaming
* fix(agentcore): move CustomStreamWrapper import to module level
The deferred imports inside streaming methods caused initialization delays
during health check requests, leading to timeouts in ECS deployments.
- Move CustomStreamWrapper import to module-level (line 19)
- Remove deferred imports from get_sync_custom_stream_wrapper (line 588)
- Remove deferred import from get_async_custom_stream_wrapper (line 747)
- Remove from TYPE_CHECKING block to use actual import
This ensures the import happens at module load time rather than during
first request processing, preventing health check endpoint blocking.
🤖 Generated with [Claude Code](https://claude.com/claude-code )
Co-Authored-By: Claude <noreply@anthropic.com>
* test(agentcore): ensure sync response
* chore: upgrade boto3 to 1.40.76 in pyproject.toml
* chore: added taplo.toml
* fix(types): correct annotation type hint for MyPy compatibility
Update _convert_annotations_to_chat_format return type from
Dict[str, Any] to ChatCompletionAnnotation TypedDict to match
the Message class's expected type signature.
Co-Authored-By: Claude <noreply@anthropic.com>
---------
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Benedikt Óskarsson <bensi94@hotmail.com>
2026-01-19 05:20:24 -08:00
Harshit Jain
6cd4b3603f
fix(router): prevent retrying 4xx client errors ( #19275 )
2026-01-19 05:18:35 -08:00
Benedikt Óskarsson
f09cae2107
Merge branch 'main' into fix/bedrock-thinking-tool-call-2
2026-01-19 13:08:17 +00:00
Sameer Kankute
480fa13b1d
Merge pull request #19343 from BerriAI/litellm_anthropic_header_fix_19_jan
...
Fix: anthropic-beta is getting overriden and set to anthropic-beta
2026-01-19 18:24:46 +05:30
Sameer Kankute
a9475be06d
Merge pull request #19338 from BerriAI/litellm_fix_managed_load_balancing_batches
...
Add managed files support when load_balancing is True
2026-01-19 18:24:21 +05:30
Sameer Kankute
a8883a45bf
Merge pull request #19327 from BerriAI/litellm_vertex_ai_file_upload
...
Fix: upload pdfs for file endpoint
2026-01-19 18:23:41 +05:30
Sameer Kankute
68294228c2
Merge pull request #19326 from BerriAI/litellm_handle_failer_2_times
...
Fix: _handle_failure method getting called 2 times
2026-01-19 18:22:44 +05:30
Sameer Kankute
896d1a7dad
Fix Error: Found packages that need verification:
2026-01-19 18:18:24 +05:30
Sameer Kankute
c5a8d4e34e
Merge branch 'main' into litellm_staging_01_16_2026
2026-01-19 18:11:21 +05:30
Chesars
45eb35938b
fix: drop_params not dropping prompt_cache_key for non-OpenAI providers
...
Fixes #19225
Add prompt_cache_key and other missing OpenAI Chat Completions params
to DEFAULT_CHAT_COMPLETION_PARAM_VALUES so drop_params: true works.
Also fix additional_drop_params to filter extra params for all providers,
not just OpenAI/Azure.
2026-01-19 08:49:03 -03:00
Sameer Kankute
d7b103158a
Fix: anthropic-beta is getting overriden and set to anthropic-beta': 'structured-outputs-2025-11-13',
2026-01-19 16:43:27 +05:30
Sameer Kankute
eea24978b9
Add managed files support when load_balancing is True
2026-01-19 15:54:04 +05:30
Sameer Kankute
514ebb0d96
Fix: vector store sync issues
2026-01-19 13:17:08 +05:30
Sameer Kankute
480cb9c0d8
Fix: upload pdfs for file endpoint
2026-01-19 11:58:32 +05:30
YutaSaito
bb7aad9de1
Merge pull request #19319 from BerriAI/litellm_test_mcp_integration
...
[test] mcp integration test
2026-01-19 14:38:02 +09:00
Yuta Saito
44a166a792
fix: ci mcp version up
2026-01-19 14:27:00 +09:00
Yuta Saito
a141aa6026
test: temporary skip
2026-01-19 13:57:40 +09:00
Sameer Kankute
fbf2d83375
Fix: _handle_failure method getting called 2 times
2026-01-19 10:19:31 +05:30
Yuta Saito
1fbbe0a983
test: restore global MCP server manager after access-group test
2026-01-19 12:29:37 +09:00
Yuta Saito
30c4a38179
test: const
2026-01-19 12:03:26 +09:00
YutaSaito
14679cff3f
Merge pull request #19317 from BerriAI/litellm_fix-responses-api-non-openai-models
...
[fix] responses api non OpenAI models
2026-01-19 11:21:39 +09:00
Yuta Saito
20b6468222
test: refactor
2026-01-19 11:17:44 +09:00
Yuta Saito
c2b5e9c669
test: MCP E2E streamable_http
2026-01-19 11:12:36 +09:00
Yuta Saito
737fec600f
test: add mcp e2e test
2026-01-19 10:49:39 +09:00
Yuta Saito
d31c609600
test: Let MCP tool-execution mock accept new kwargs for streaming tests
2026-01-19 07:00:14 +09:00
Yuta Saito
4ad78236ab
test: Fail MCP streaming test when LiteLLM logs errors during follow-up calls
2026-01-19 06:46:39 +09:00
Yuta Saito
cd19039e39
test: Parametrize MCP streaming test to cover OpenAI and Anthropic models
2026-01-19 06:22:05 +09:00
Ishaan Jaffer
60dd04ac95
test_aiohttp_openai
2026-01-17 17:05:00 -08:00
yuneng-jiang
0c90c4c38e
Merge remote-tracking branch 'origin' into litellm_esca_reissue
2026-01-17 16:45:10 -08:00
Ishaan Jaffer
db7de13818
test_deepseek_mock_completion
2026-01-17 16:36:42 -08:00
Ishaan Jaffer
5812654bdd
test_router_fallbacks_with_custom_model_costs
2026-01-17 16:34:46 -08:00
yuneng-jiang
aad92c0b25
Merge pull request #19116 from BerriAI/litellm_org_admin_escalte
...
[Fix] /user/new Privilege Escalation
2026-01-17 16:32:04 -08:00
Ishaan Jaff
1417b002a3
[Feat] Claude Code x LiteLLM WebSearch - QA Fixes to work with Claude Code ( #19294 )
...
* fix websearch_interception_converted_stream
* test_websearch_interception_no_tool_call_streaming
* FakeAnthropicMessagesStreamIterator
* LITELLM_WEB_SEARCH_TOOL_NAME
* fixes tools def for litellm web search
* fixes FakeAnthropicMessagesStreamIterator
* test_litellm_standard_websearch_tool
* use new hook for modfying before any transfroms from litellm
* init WebSearchInterceptionLogger + ARCHITECTURE
* fix config.yaml
* init doc for claude code web search
* docs fix
* doc fix
* fix mypy linting
2026-01-17 16:30:31 -08:00
Chesars
cc39c71ac6
test: move helicone gemini test to tests/litellm/
...
Move test to correct directory per PR template requirements.
2026-01-17 18:07:40 -03:00
Chesars
542abc0429
fix(helicone): add Gemini/Vertex AI support to HeliconeLogger
...
- Add "gemini" to helicone_model_list so Gemini models are recognized
- Use /custom/v1/log endpoint for Gemini models instead of /oai/v1/log
- Set correct provider_url for Google's generativelanguage API
- Add unit test for Gemini model recognition
Previously, Gemini models were logged as "gpt-3.5-turbo" with OpenAI
as the provider, corrupting analytics. Now they log correctly with
their actual model name and CUSTOM provider.
2026-01-17 18:00:00 -03:00
Ishaan Jaff
104283ae8f
[Feat] Claude Code - Add Websearch support using LiteLLM /search (using web search interception hook) ( #19263 )
...
* init WebSearchInterceptionLogger
* test_websearch_interception_real_call
* init async_should_run_agentic_completion
* async_should_run_agentic_loop
* async_run_agentic_loop
* refactor folder
* fix organization
* WebSearchTransformation
* WebSearchInterceptionLogger
* _call_agentic_completion_hooks
* WebSearch Interception Architecture
* test_websearch_interception_real_call
* add streaming
* add transform_request for streaming
* get_llm_provider
* test fix
* fix info
* init from config.yaml
* fixes
* test handler
* fix _is_streaming_response
* async_run_agentic_loop
* mypy fix
2026-01-16 21:10:05 -08:00
Vedant Madane
11a622aa5a
Fix extract_cacheable_prefix to handle string content with message-level cache_control ( fixes #19228 )
2026-01-17 10:35:40 +05:30
yuneng-jiang
90dc0e9120
Merge remote-tracking branch 'origin' into litellm_deleted_keys_endpoint
2026-01-16 19:25:03 -08:00
yuneng-jiang
de84b2edce
Fixing tests and adding proper returns
2026-01-16 19:24:51 -08:00
yuneng-jiang
6e8dd06d18
fixing test
2026-01-16 19:06:23 -08:00
yuneng-jiang
bb4b791746
Merge remote-tracking branch 'origin' into litellm_deleted_keys_endpoint
2026-01-16 18:15:37 -08:00
