Commit Graph
26032 Commits
Author SHA1 Message Date
Ishaan JaffandGitHub ec9cdf783a Revert "Add streamGenerateContent cost tracking in passthrough (#15199)" (#15202)
This reverts commit 8095de506a.
2025-10-04 14:37:02 -07:00
Krish DholakiaandGitHub 82fd182df2 Merge pull request #15196 from BerriAI/litellm_staging_10_04_2025
Litellm staging 10 04 2025
2025-10-04 14:19:45 -07:00
Krish DholakiaandGitHub f24a7a5191 Merge pull request #15200 from BerriAI/litellm_dev_10_04_2025_p1
fix: fix ui rerender
2025-10-04 14:18:10 -07:00
Krrish Dholakia 3300c16d74 fix: fix ui rerender 2025-10-04 14:17:36 -07:00
Krish DholakiaandGitHub b2ffeb8397 Merge pull request #15094 from BerriAI/litellm_dev_09_30_2025_p1
Guardrails - run all guardrails before calling other post_call_success_hook + Prometheus - support custom metadata labels on key/team
2025-10-04 14:16:04 -07:00
Krish DholakiaandGitHub bed6c79bed Merge branch 'main' into litellm_dev_09_30_2025_p1 2025-10-04 14:15:55 -07:00
Krish DholakiaandGitHub 7cd0944b1a Merge pull request #15197 from ARajan1084/release-1-77-7-test-key-model-selection-fix
fix: Test key view: state on model info update
2025-10-04 14:08:42 -07:00
Krish DholakiaandGitHub 7a410940bd Merge pull request #15195 from BerriAI/litellm_dev_10_04_2025_p1
Litellm dev 10 04 2025 p1
2025-10-04 14:06:50 -07:00
Krrish Dholakia 2de05b4fd8 test: add min test for filtering logic 2025-10-04 14:05:55 -07:00
Krrish Dholakia 1bdf8cf264 fix(log_filter_logic.tsx): fix searching for end user logs, globally
ensures filters work outside of initial loaded page
2025-10-04 13:56:51 -07:00
Ishaan Jaffer e1ee428573 docs fix 2025-10-04 13:20:39 -07:00
Ishaan Jaffer 685e027d94 docs Dynamic Rate Limiter v3 2025-10-04 13:19:17 -07:00
Ishaan Jaffer c947994239 docs fix notes 2025-10-04 13:16:15 -07:00
Ishaan Jaffer 22b6a82105 docs fix 2025-10-04 13:10:27 -07:00
Ishaan Jaffer 57c6f8dedc ci/cd new release 2025-10-04 12:49:52 -07:00
Ishaan Jaffer 699072d302 Revert "fix: model_group not always present in litellm_params, and metadata reference location (#15108)"
This reverts commit 7e56600896.
2025-10-04 12:48:07 -07:00
Ishaan Jaffer 07e1e0a7ca bump proxy extras migration 2025-10-04 12:38:21 -07:00
Ishaan Jaffer 51457541b0 fix add allowed tools 2025-10-04 12:37:12 -07:00
Teddy AmkieandGitHub 7a176804f3 Add sync models GitHub documentation with Loom video and cross-references (#15191)
- Add comprehensive sync_models_github.md with API endpoints and examples
- Include Loom video tutorial for Admin UI sync process
- Add cross-references from model_management.md, cost_tracking.md, and ui.md
- Provide both manual and automated sync options
- Include Python SDK usage examples
2025-10-04 12:32:01 -07:00
Sameer KankuteandGitHub 8095de506a Add streamGenerateContent cost tracking in passthrough (#15199)
* Add streamgenerate cost tracking for gemini provider

* add cost tracking test
2025-10-04 12:31:25 -07:00
Ishaan Jaffer 3d6342f852 test_twelvelabs_missing_input_type_error 2025-10-04 12:28:09 -07:00
Ishaan Jaffer 6c79e12367 fix schema 2025-10-04 12:26:36 -07:00
Ishaan Jaffer be7ab0b3e3 test_gemini_url_context 2025-10-04 12:23:43 -07:00
= 06d50b55d7 fixes surrounding selection state on model info update 2025-10-04 12:13:18 -07:00
Krrish Dholakia 6745e9f3f5 fix(model_dashboard.tsx): fix query 2025-10-04 12:08:13 -07:00
Krrish Dholakia c2eb4d7f4e fix(networking.tsx): use more efficient query for getting list of users 2025-10-04 12:07:21 -07:00
Ishaan Jaffer c38c5d20cc test dynamic rate limiter 3 2025-10-04 12:06:13 -07:00
Krish DholakiaandGitHub 79014a8522 Merge pull request #15184 from ARajan1084/edit-key-nonpremium-user-fix
fix: empty premium fields resulting in edit key blocking
2025-10-04 11:51:40 -07:00
Ishaan Jaffer 2dc11316f2 fix failing deepseek-ai/DeepSeek-V3.1 2025-10-04 11:50:30 -07:00
Ishaan Jaffer cdfb53dd81 fix linting error 2025-10-04 11:40:47 -07:00
Krrish Dholakia 509927eec9 test: add vitest for clipboard http scenario 2025-10-04 11:34:12 -07:00
Krrish Dholakia fff40e2ed6 fix(datautils.ts): fix clipboard copy issue on http endpoints 2025-10-04 11:29:15 -07:00
Ishaan Jaffer 7a41c09529 test bedrock embedding tests marengo 2025-10-04 11:27:29 -07:00
Ishaan Jaffer 44db58c8df test_e2e_bedrock_async_invoke_embedding_async_twelvelabs_marengo 2025-10-04 11:13:39 -07:00
Ishaan Jaffer e7b570000e fix: azure passthrough test 2025-10-04 11:06:36 -07:00
Ishaan Jaffer 53503828b2 test fix 2025-10-04 10:57:02 -07:00
Ishaan Jaffer 6f298cf5f0 test_azure_openai_assistants_e2e_operations_stream 2025-10-04 10:53:46 -07:00
Ishaan Jaffer 4ab571f684 fix test /generateContent route 2025-10-04 10:49:46 -07:00
Ishaan JaffandGitHub f78608082c [Feat] Dynamic Rate Limiter v3 - fixes for detecting saturation + fixes for post saturation behavior (#15192)
* fix: test case 1, model hits saturation

* fix: _check_rate_limits test case 2

* fix: _get_priority_allocation

* test_default_priority_shared_pool

* fix: No Rate Limiting when low saturatation

* fix: correctly use  model_saturation_check

* fixes priority_descriptors

* fix: tune default PriorityReservationSettings
2025-10-04 10:45:17 -07:00
Alexsander HamirandGitHub 29a31e17dd [Doc] Perf: Last week improvement (#15193)
* doc: perf update

* fix: mixed up changes

* fix: add gist
2025-10-04 10:43:13 -07:00
Ishaan Jaffer ee36c30217 fix LF tests 2025-10-04 10:39:17 -07:00
Ishaan Jaffer 00f44861ea fix: gooogle GenAI route tests 2025-10-04 10:18:25 -07:00
Ishaan Jaffer df9a19bc9d fix OPENAI_EMBEDDING_PARAMS 2025-10-04 10:11:21 -07:00
Ishaan Jaffer 1655a9aea8 fix lf tests 2025-10-04 10:02:56 -07:00
Ishaan Jaffer eb417ed774 fix lf logging 2025-10-04 10:00:10 -07:00
Ishaan Jaffer 27fbfbe259 fix: include_subpath 2025-10-04 09:47:16 -07:00
Ishaan Jaffer 212a2e13f3 OTEL fix spans 2025-10-04 09:22:57 -07:00
Ishaan Jaffer a040e0154a add openai 2025-10-04 09:19:00 -07:00
Ishaan Jaffer 4400a6c189 test bedrock guardrails 2025-10-04 09:18:26 -07:00
Alexsander HamirandGitHub 5d22229d35 [Fix] Cache - Avoiding expensive operations when cache isn't available (#15182)
* Optimize cache performance by avoiding expensive operations when caching is disabled

- Moved cache availability checks before expensive operations to improve performance for non-cached requests
- Updated client code to handle None responses from caching handler

* clean hot path

* Fix TypeError with isinstance check for CustomStreamWrapper in caching

Fixed `TypeError: typing.Any cannot be used with isinstance()` that was
occurring in the caching handler when checking cached streaming responses.

The issue was caused by CustomStreamWrapper being aliased to `typing.Any`
at runtime through the TYPE_CHECKING conditional import pattern. When the
code attempted to use isinstance(cached_result, CustomStreamWrapper) at
lines 222 and 338, it failed because Python's isinstance() cannot be used
with typing.Any.

Solution: Import CustomStreamWrapper at runtime separately from the
TYPE_CHECKING block, while keeping a type alias for static type checking.
This allows isinstance checks to work properly while maintaining type hints.

* fix: remove unnecessary type checking
2025-10-04 09:10:37 -07:00