Commit Graph

31325 Commits

Author SHA1 Message Date
shin-bot-litellm 395ad9bdc1 litellm_fix(test): add acancel_batch to Azure SDK client initialization test (#20143) 2026-01-31 07:34:54 -08:00
shin-bot-litellm 1c757dee14 litellm_docs: add missing environment variable documentation (#20138) 2026-01-31 07:33:24 -08:00
shin-bot-litellm 7db4594200 litellm_fix(test): allow comment field in schema and exclude robotics models from tpm check (#20139) 2026-01-31 07:32:33 -08:00
shin-bot-litellm 14a5706131 litellm_fix(test): fix Bedrock tool search header test regression (#20135) 2026-01-31 00:44:47 -08:00
shin-bot-litellm 013b4701f4 litellm_fix(test): fix Azure AI cost calculator test - use Logging class (#20134) 2026-01-31 00:43:53 -08:00
shin-bot-litellm ecd0202f70 litellm_fix(e2e): disable bedrock-converse-claude-sonnet-4.5 model in tests (#20131) 2026-01-31 00:32:42 -08:00
shin-bot-litellm 8e69c2ef24 litellm_fix(ui): remove unused ToolOutlined import (#20129) 2026-01-31 00:25:06 -08:00
shin-bot-litellm 4029f61430 fix(proxy): reduce PLR0915 complexity in base_process_llm_request (#20127) 2026-01-31 00:20:12 -08:00
shin-bot-litellm 08e4d06f0c litellm_fix: add missing timezone import to proxy_server.py (#20121) 2026-01-30 23:59:52 -08:00
Shivam Rawat 3f1bda57e2 Merge pull request #20101 from BerriAI/ui-mcp-list-tools-instructions-fix
fixed mcp tools instructions on ui to show comma seprated str instead…
2026-01-30 19:40:37 -08:00
Krrish Dholakia 0edd50fe3c docs: cleanup docs 2026-01-30 19:39:17 -08:00
shivam d01267707e fixed mcp tools instructions on ui to show comma seprated str instead of list 2026-01-30 19:25:30 -08:00
Ishaan Jaffer 87c1e6fd68 remove md 2026-01-30 18:57:06 -08:00
Ishaan Jaff 4abae44006 [Feat] UI - Add Pretty print view of request/response (#20096)
* v1 - tool viewer in logs page

* add preview for tool sections

* ui fixes

* new tool view

* v1 - new pretty view

* clean ui

* polish fixes

* nice view input/output

* working i/o cards

* fixes for log view

---------

Co-authored-by: Warp <agent@warp.dev>
2026-01-30 18:56:34 -08:00
Ishaan Jaff 1cd83e9022 [Feat] UI - New View to render "Tools" on Logs View (#20093)
* v1 - tool viewer in logs page

* add preview for tool sections

* ui fixes

* new tool view

* Refactor: Address code review feedback - use Antd components

Changes:
- Use Antd Space component instead of manual flex layouts
- Use Antd Text.copyable prop instead of custom clipboard utilities
- Extract helper functions to utils.ts for testability
- Remove clipboardUtils.ts (replaced with Antd built-in)
- Update DrawerHeader, LogDetailsDrawer, and constants

Benefits:
- Cleaner code using standard Antd patterns
- Better testability with separated utils
- Consistent UX with Antd's copy tooltips
- Reduced custom code maintenance

Co-authored-by: Cursor <cursoragent@cursor.com>

---------

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-01-30 18:48:52 -08:00
Ishaan Jaff 5345a763c2 [Feat] v2 - Logs view with side panel and improved UX (#20091)
* init: azure_ai/azure-model-router

* show additional_costs in CostBreakdown

* UI show cost breakdown fields

* feat: dedicated cost calc for azure ai

* test_azure_ai_model_router

* docs azure model router

* test azure model router

* fix transfrom

* Add transform file

* fix:feat: route to config

* v0 - looks decen view

* refactored code

* fix ui

* fixes ui

* complete v2 viewer

* address feedback

* address feedback
2026-01-30 18:34:13 -08:00
Ishaan Jaffer e2f7b10c8d address feedback 2026-01-30 18:20:50 -08:00
Ishaan Jaffer 2ce87a3d62 new utils 2026-01-30 18:17:45 -08:00
yuneng-jiang 267993b388 Merge pull request #20095 from BerriAI/litellm_user_dropdown_v2
[Refactor] UI - Navbar: User Dropdown
2026-01-30 18:12:25 -08:00
yuneng-jiang 0942f98b4d refactoring user dropdown 2026-01-30 17:18:06 -08:00
yuneng-jiang b64cd318d8 Merge pull request #20092 from BerriAI/litellm_user_dropdown
[Fix] UI - Navbar: Fixed Default Logo + Bound Logo Box
2026-01-30 16:47:24 -08:00
yuneng-jiang 3e8e1ded54 update image and bounded logo in navbar 2026-01-30 16:35:24 -08:00
Ishaan Jaff ad1b48a008 Revert logs view commits to recreate with clean history (#20090)
This reverts commits:
- 437e9e23bd fix drawer
- 61bb51dc3d complete v2 viewer
- 2014bcf9d8 fixes ui
- 5f07635310 fix ui
- f07ef8af00 refactored code
- 8b7a9250ce v0 - looks decen view

Will create a new clean PR with the original changes.
2026-01-30 16:02:58 -08:00
Ishaan Jaffer 437e9e23bd fix drawer 2026-01-30 15:53:37 -08:00
Ishaan Jaffer 61bb51dc3d complete v2 viewer 2026-01-30 15:53:05 -08:00
Ishaan Jaffer 2014bcf9d8 fixes ui 2026-01-30 15:53:05 -08:00
Ishaan Jaffer 5f07635310 fix ui 2026-01-30 15:53:05 -08:00
Ishaan Jaffer f07ef8af00 refactored code 2026-01-30 15:53:05 -08:00
Ishaan Jaffer 8b7a9250ce v0 - looks decen view 2026-01-30 15:53:05 -08:00
Alexsander Hamir a11b043f33 fix(proxy): resolve high CPU when router_settings in DB by avoiding REGISTRY.collect() in PrometheusServicesLogger (#20087) 2026-01-30 14:01:45 -08:00
Ishaan Jaff 6897d5f59e [Feat] Add async_post_call_response_headers_hook to CustomLogger (#20083)
* Add async_post_call_response_headers_hook to CustomLogger (#20070)

Allow CustomLogger callbacks to inject custom HTTP response headers
into streaming, non-streaming, and failure responses via a new
async_post_call_response_headers_hook method.

* async_post_call_response_headers_hook

---------

Co-authored-by: michelligabriele <gabriele.michelli@icloud.com>
2026-01-30 12:44:44 -08:00
Ishaan Jaff 974837c4e1 fix: working claude code with agent SDKs (#20081) 2026-01-30 11:58:05 -08:00
Harshit Jain 481bb4b6ce fixes: ci pipeline router coverage failure (#20065) 2026-01-30 11:55:49 -08:00
Ishaan Jaff 3910161a02 Realtime API benchmarks (#20074)
* Add /realtime API benchmarks to Benchmarks documentation

- Added new section showing performance improvements for /realtime endpoint
- Included before/after metrics showing 182× faster p99 latency
- Added test setup specifications and key optimizations
- Referenced from v1.80.5-stable release notes

Co-authored-by: ishaan <ishaan@berri.ai>

* Update /realtime benchmarks to show current performance only

- Removed before/after comparison, showing only current metrics
- Clarified that benchmarks are e2e latency against fake realtime endpoint
- Simplified table format for better readability

Co-authored-by: ishaan <ishaan@berri.ai>

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: ishaan <ishaan@berri.ai>
2026-01-30 11:55:29 -08:00
Alexsander Hamir 0acfcb494b Add mock client factory pattern and mock support for PostHog, Helicone, and Braintrust integrations (#19707)
* Add LangSmith mock client support

- Create langsmith_mock_client.py following GCS and Langfuse patterns
- Add mock mode detection via LANGSMITH_MOCK environment variable
- Intercept LangSmith API calls via AsyncHTTPHandler.post patching
- Add verbose logging throughout mock implementation
- Update LangsmithLogger to initialize mock client when mock mode enabled
- Supports configurable mock latency via LANGSMITH_MOCK_LATENCY_MS

* Add Datadog mock client support

- Create datadog_mock_client.py following GCS, Langfuse, and LangSmith patterns
- Add mock mode detection via DATADOG_MOCK environment variable
- Intercept Datadog API calls via AsyncHTTPHandler.post and httpx.Client.post patching
- Add verbose logging throughout mock implementation
- Update DataDogLogger and DataDogLLMObsLogger to initialize mock client when mock mode enabled
- Supports both async and sync logging paths
- Supports configurable mock latency via DATADOG_MOCK_LATENCY_MS

* refactor: consolidate mock client logic into factory pattern

- Create mock_client_factory.py to centralize common mock HTTP client logic
- Refactor GCS, Langfuse, LangSmith, and Datadog mock clients to use factory
- Improve GET/DELETE mock accuracy for GCS (return valid StandardLoggingPayload)
- Fix DELETE mock to return empty body (204 No Content) instead of JSON
- Reduce code duplication across integration mock clients

* feat: add PostHog mock client support

- Create posthog_mock_client.py using factory pattern
- Integrate mock client into PostHogLogger with mock mode detection
- Add verbose logging for mock mode initialization and batch operations
- Enable mock mode via POSTHOG_MOCK environment variable

* Add Helicone mock client support

- Created helicone_mock_client.py using factory pattern (similar to GCS)
- Integrated mock mode detection and initialization in HeliconeLogger
- Mock client patches HTTPHandler.post to intercept Helicone API calls
- Uses factory pattern for should_use_mock and MockResponse utilities
- Custom HTTPHandler.post patching required since HTTPHandler uses self.client.send()

* Add mock support for Braintrust integration and extend mock client factory

- Add braintrust_mock_client.py with mock HTTP client for Braintrust integration testing
- Integrate mock client into BraintrustLogger with mock mode detection
- Refactor Helicone mock client to fully utilize factory's HTTPHandler.post patching
- Extend mock_client_factory to support patching HTTPHandler.post for sync calls
- Enable endpoint-specific mock responses for Braintrust (/project vs /project_logs)
- All mock clients now properly handle both async (AsyncHTTPHandler) and sync (HTTPHandler) calls

* Fix linter errors: remove unused imports and suppress complexity warning

- Remove unused imports from gcs_bucket_mock_client.py (httpx, json, timedelta, Dict, Optional)
- Remove unused Callable import from mock_client_factory.py
- Add noqa comment to suppress PLR0915 complexity warning for create_mock_client_factory function

* Document mock environment variables for PostHog, Helicone, Braintrust, Datadog, and Langsmith integrations

- Add POSTHOG_MOCK and POSTHOG_MOCK_LATENCY_MS documentation
- Add HELICONE_MOCK and HELICONE_MOCK_LATENCY_MS documentation
- Add BRAINTRUST_MOCK and BRAINTRUST_MOCK_LATENCY_MS documentation
- Add DATADOG_MOCK and DATADOG_MOCK_LATENCY_MS documentation
- Add LANGSMITH_MOCK and LANGSMITH_MOCK_LATENCY_MS documentation

All mock env vars follow the same pattern: enable mock mode for integration testing by intercepting API calls and returning mock responses without making actual network calls.

* Fix security issue
2026-01-30 09:52:53 -08:00
yuneng-jiang c301339412 Merge pull request #20039 from BerriAI/litellm_ui_key_model_bd
[Feature] UI - Usage: Model Breakdown Per Key
2026-01-30 09:16:23 -08:00
Sameer Kankute 6e9210381c Merge pull request #20058 from BerriAI/litellm_vertex_ai_prompt-caching-scope-2026-01-05,
Fix: remove unsupported prompt-caching-scope-2026-01-05 header for vertex ai
2026-01-30 20:32:00 +05:30
Sameer Kankute 8363a26d2e Fix: remove unsupported prompt-caching-scope-2026-01-05 header for vertex ai 2026-01-30 17:33:40 +05:30
Sameer Kankute 1877483deb Merge pull request #20056 from BerriAI/litellm_vllm_embedding
Fix: vllm embedding format
2026-01-30 17:01:57 +05:30
Sameer Kankute 5277a0cf82 Merge pull request #20053 from BerriAI/litellm_gemini_edit_jan_30
fix aspectRatio mapping in image edit
2026-01-30 17:01:46 +05:30
Sameer Kankute 8b9d5018b6 Merge pull request #20052 from BerriAI/litllm_disable_cache_jan_29
Add disable flag for anthropic gemini cache translation
2026-01-30 17:01:34 +05:30
Sameer Kankute 404c33eca6 Merge pull request #20051 from BerriAI/litellm_xai_web_search_routing
Add routing of xai chat completions to responses when web search options is present
2026-01-30 17:01:19 +05:30
Sameer Kankute 8d485f2403 Merge pull request #19986 from BerriAI/litellm_batch_cost_tracking_jan29
[Feat]Add cost tracking and usage object in aretrieve_batch call type
2026-01-30 17:00:42 +05:30
Sameer Kankute cfc9c77347 Merge pull request #19981 from BerriAI/litellm_fix_batches_permissions
Fix: Batch and File user level permissions
2026-01-30 17:00:10 +05:30
Sameer Kankute 51747ee534 Merge pull request #20055 from BerriAI/litellm_files_gemini_endpoints_support
feat: add /delete endpoint support for gemini
2026-01-30 16:58:59 +05:30
Sameer Kankute a8054264ae Merge pull request #19975 from BerriAI/litellm_oss_staging_01_29_2026
Litellm oss staging 01 29 2026
2026-01-30 16:58:28 +05:30
Sameer Kankute 55348dd9c5 Fix: vllm embedding format 2026-01-30 16:42:59 +05:30
Sameer Kankute fdb4b54add Merge pull request #20009 from genga6/fix/#20006-update-max-input-tokens-for-gpt-5.2-codex
Fix `max_input_tokens` for `gpt-5.2-codex`
2026-01-30 16:18:53 +05:30
Sameer Kankute ab8b459dfc Merge pull request #20046 from nht1206/bugfix/input-tokens-details-not-correctly-extracted
fix(ResponseAPILoggingUtils): extract input tokens details as dict
2026-01-30 16:13:35 +05:30
Sameer Kankute ed4c71ecf5 Merge pull request #20018 from varunsripad123/fix/google-files-retrieval
fix(gemini): support file retrieval in GoogleAIStudioFilesHandle
2026-01-30 16:09:19 +05:30