Tim Elfrink
b5fa2ee73f
Merge remote-tracking branch 'origin/main' into feat/github-copilot-thinking-reasoning-support
2025-08-19 10:11:59 +02:00
Tim Elfrink
9b0fda7b14
fix: resolve case sensitivity and test failures for extended thinking support
...
- Fix supports_reasoning() call to use lowercase model names for proper lookup
- Remove custom_llm_provider parameter as model registry entries are provider-agnostic
- Update tests to use full model names with date stamps (required for supports_reasoning)
- Add test coverage for models without extended thinking support
2025-08-19 08:40:10 +02:00
Tim Elfrink
9f82b89051
fix: remove redundant github_copilot check in get_supported_openai_params
...
The provider_config_manager already handles github_copilot provider
through LlmProviders.GITHUB_COPILOT mapping, making the explicit
check unnecessary.
2025-08-19 08:21:18 +02:00
Tim Elfrink
8b66b50c31
fix: restrict thinking/reasoning_effort parameters to models with extended thinking support
...
Only models in the 4 family and 3-7 family support extended thinking features.
Previously all models would incorrectly receive these parameters.
Now uses supports_reasoning() to check model registry for actual capability.
2025-08-19 08:15:50 +02:00
Krrish Dholakia
137a98a5af
bump: version 1.75.8 → 1.75.9
2025-08-18 23:11:08 -07:00
Krish Dholakia
435995ba5c
Merge pull request #13617 from moandersson/fix/migratejob-resources
...
Add possibility to configure resources for migrations-job in Helm chart
2025-08-18 23:03:35 -07:00
Krish Dholakia
88e52c55d0
Merge pull request #13675 from colesmcintosh/fix/groq-streaming-encoding
...
Fix Groq streaming ASCII encoding issue
2025-08-18 23:00:00 -07:00
Krish Dholakia
9dadd279a4
Merge pull request #13741 from BerriAI/litellm_dev_08_18_2025_p1
...
Refactor - forward model group headers - reuse same logic as global header forwarding
2025-08-18 22:58:39 -07:00
Krrish Dholakia
2c0520635d
test: cleanup old tests
2025-08-18 22:58:29 -07:00
Krish Dholakia
048f22b7ec
Merge pull request #13742 from BerriAI/litellm_dev_08_18_2025_p2
...
Fix - gemini prompt caching cost calculation
2025-08-18 22:54:28 -07:00
Krish Dholakia
b5f06e2bd3
Merge pull request #13685 from BerriAI/azure-deployment-name-preset
...
Add Azure Deployment Name Support in UI
2025-08-18 22:48:33 -07:00
Krish Dholakia
78fcf7afa9
Merge pull request #13687 from BerriAI/model-filter-on-models
...
Add Search Functionality for Public Model Names in Model Dashboard
2025-08-18 22:44:36 -07:00
Krish Dholakia
3713c926c0
Merge pull request #13704 from michal-otmianowski/use-namespace-as-prefix-for-s3-cache
...
Use namespace as prefix for s3 cache
2025-08-18 22:37:18 -07:00
Krrish Dholakia
f7f1a0d0b7
test: add unit test
2025-08-18 22:32:36 -07:00
Krrish Dholakia
241f32b2a3
fix(vertex_and_google_ai_studio_gemini.py): adjust 'text token' value to be the non-cached tokens - for accurate cost tracking
2025-08-18 22:09:07 -07:00
Krrish Dholakia
2e16f2cb13
test: add unit tests
2025-08-18 21:19:43 -07:00
Krrish Dholakia
36f93444b2
refactor: cleanup
2025-08-18 21:14:38 -07:00
Krrish Dholakia
06d05c691d
fix(litellm_pre_call_utils.py): forward headers by model group at litellm pre call utils level
...
do it at the proxy level instead of router - allows reusing same forwarding logic as global forwarding
2025-08-18 21:13:52 -07:00
Krish Dholakia
422447b7f1
Responses API - add default api version for openai responses api calls + Openrouter - fix claude-sonnet-4 on openrouter + Azure - Handle openai/v1/responses
...
Responses API - add default api version for openai responses api calls + Openrouter - fix claude-sonnet-4 on openrouter + Azure - Handle `openai/v1/responses`
2025-08-18 18:59:28 -07:00
Krrish Dholakia
0459604721
docs: document new param
2025-08-18 18:56:39 -07:00
Krish Dholakia
3b52545db3
Merge pull request #13529 from BerriAI/litellm_dev_08_11_2025_p1
...
[Fix] Cooldowns - don't return raw Azure Exceptions to client
2025-08-18 18:54:19 -07:00
Ishaan Jaff
0945483721
fix mypy linting errors
2025-08-18 18:51:14 -07:00
Ishaan Jaff
aac7cdf2c8
ruff check fix
2025-08-18 18:28:25 -07:00
Ishaan Jaff
ba0881d728
[Bug Fix] image_edit() function returns APIConnectionError with litellm_proxy - Support for both image edits and image generations ( #13735 )
...
* add image edits litellm proxy on SDK
* add image gen provider
* add IMG Gen support for litellm_proxy provider
2025-08-18 18:26:32 -07:00
Ishaan Jaff
76f1064229
[Bug Fix] litellm incompatible with newest release of openAI v1.100.0 ( #13728 )
...
* fix imports OpenAI SDK
* ResponseText fixes
* fixes ResponseText
* fix imports
* catch AttributeError
* fix import
* use openai==1.100.1
* fix build from PIP
* fix lint test
* Print OpenAI version
* fix Install dependencies
2025-08-18 18:26:17 -07:00
Ishaan Jaff
ba1d2e8749
[Feat] DD LLM Observability - Add time to first token, litellm overhead, guardrail overhead latency metrics ( #13734 )
...
* fixes for DDLLMObsLatencyMetrics
* use _get_latency_metrics
* DD LLM Obs - track latency metrics
* fixes for bedrock guardrails
* DD unit tests
* test DD
2025-08-18 17:38:04 -07:00
Ishaan Jaff
ef08e18c66
[Feat] Datadog LLM Observability - Add support for Failure Logging ( #13726 )
...
* add async_log_failure_event for DD LLM Obs
* update types
* DataDogLLMObsLogger add failure logging support
* test_async_log_failure_event
* dd test failure
2025-08-18 15:19:48 -07:00
Thiago Salvatore
169a17400f
fix(vertexai-batch): fix vertexai batch file format ( #13576 )
...
* fix(access group): allow access group on mcp tool retrieval
* fix(test): fix broken tests and add test case for access group
* fix(mypy): fix typing issues
* fix(memory file): add content type to in memory file
2025-08-18 10:19:23 -07:00
Ishaan Jaff
eee93e250a
docs v1.75.5-stable
2025-08-18 09:23:18 -07:00
superpoussin22
b42df63d17
does not support function ( #13612 )
2025-08-18 08:45:25 -07:00
Michal Otmianowski
405e74ec16
use namespace as prefix in s3
2025-08-18 13:43:51 +02:00
Krish Dholakia
c99277c517
Merge pull request #13694 from BerriAI/litellm_dev_08_16_2025_p3
...
Litellm dev 08 16 2025 p3
2025-08-17 13:02:17 -07:00
Tim Elfrink
0febdf8c1c
feat: add thinking and reasoning parameter support for GitHub Copilot provider
...
- Add dynamic parameter support for anthropic models through GitHub Copilot
- Include thinking parameter for anthropic model compatibility
- Support reasoning_effort parameter for both anthropic and reasoning models
- Update test coverage for parameter validation logic
- Ensure proper parameter filtering based on model type
2025-08-17 17:51:58 +02:00
Tim Elfrink
d92092f040
formatting
2025-08-17 17:26:59 +02:00
Tim Elfrink
1e81a1bd7c
feat: Add thinking and reasoning_effort parameter support for GitHub Copilot provider
...
- Add github_copilot case to get_supported_openai_params function
- Implement get_supported_openai_params method in GithubCopilotConfig
- Dynamically add thinking and reasoning_effort params for Anthropic models
- Add comprehensive tests for parameter support validation
- Ensure case-insensitive model detection for parameter inclusion
Fixes UnsupportedParamsError when using advanced reasoning parameters
with Anthropic models through GitHub Copilot proxy.
2025-08-17 17:13:29 +02:00
Ishaan Jaff
6c4ced275d
ui new build
2025-08-16 19:08:18 -07:00
Ishaan Jaff
5c4ba732a6
fix client side exception ( #13684 )
2025-08-16 19:04:06 -07:00
tanjiro
ecb0b0ff53
search by public model name
2025-08-17 10:38:21 +09:00
tanjiro
b8a70e41cc
preset azure provider
2025-08-17 10:06:58 +09:00
Krrish Dholakia
21549a3463
docs(index.md): write up on session management
2025-08-16 17:55:18 -07:00
Krrish Dholakia
cb95f2d5d7
docs(index.md): clarify risk of upgrade
2025-08-16 17:38:50 -07:00
Krrish Dholakia
788a1d03a1
docs(index.md): cleanup
2025-08-16 17:33:07 -07:00
Krrish Dholakia
235b6b040f
docs(index.md): add highlight note on redis latency improvements
2025-08-16 17:32:45 -07:00
Krrish Dholakia
8a75ab8388
docs(index.md): cleanup doc
2025-08-16 17:16:04 -07:00
Krish Dholakia
50dec7cdee
Merge pull request #13682 from BerriAI/litellm_stable_release_fixes
...
Litellm stable release fixes
2025-08-16 15:10:55 -07:00
Krrish Dholakia
e035efeec7
fix(public_model_hub.tsx): fix ui
2025-08-16 14:30:26 -07:00
Krrish Dholakia
6322aef0e3
fix(streaming_handler.py): fix streaming chunk calculation
2025-08-16 14:25:29 -07:00
Krrish Dholakia
eb66daeef7
test: update test
...
we now return correct token usage on clientside
2025-08-16 14:14:35 -07:00
Ishaan Jaff
d96df5e9be
Revert "test_stream_token_counting_anthropic_with_include_usage"
...
This reverts commit c3aee1194b
2025-08-16 13:07:00 -07:00
Ishaan Jaff
c3aee1194b
test_stream_token_counting_anthropic_with_include_usage
2025-08-16 13:06:31 -07:00
