tiennm99/litellm
1
0
Fork 0
mirror of https://github.com/tiennm99/litellm.git synced 2026-08-09 00:26:01 +00:00
Code Issues Packages Projects Releases Wiki Activity
28,463 Commits 2,072 Branches 1,425 Tags
3a43042fad0164c8fcddcfca6c2e8d5a2fa2c626
Commit Graph
28463 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Ishaan JaffandGitHub 3a43042fad docs - add sap gen ai provider on LiteLLM (#17667) 2025-12-08 12:43:42 -08:00
_juliettechandGitHub ee0812a297 Add Helicone as a provider and update observability documentation (#17663) 
* Add Helicone as a provider to liteLLM

* Add Helicone provider integration
 2025-12-08 12:34:11 -08:00
vasilisazaykaGitHubMathis BoernerkarimmohrazKarim
 		c87874c29e [New provider] Sap gen ai hub (#16053) 
* add sap gen ai hub

* add async tests

* add async and streaming support

* add embedding model support

* add embedding support

* remove unused import

* fix structured output

* clean-up

* remove timeout and add tool support

* remove unused code

* fix(sap): improve streaming robustness; restore embed URL builder compatibility
- sap/embed/transformation: add api_key and litellm_params to get_complete_url to align with core flow and prevent failures
- sap/chat/handler: wrap async/sync streaming iterators to safely handle Stop(Async)Iteration and errors
- sap/chat/transformation: remove unused imports and dead code

* fix(sap): linter fix

* fix(sap): made gen_ai_hub optional: import check + OptionalDependencyError with install hint if missing.

* test(sap): add chat/stream/async tests and OptionalDependencyError check

* Fix tool call handling in SAP GenAI Hub transformation
Add sap models to model_prices_and_context_window.json and model_prices_and_context_window_backup.json

* fix(sap): delete unnecessary code, linter fix

* fix(sap): - refactor chat transformation
- add support of list and dict content

* fix(sap): - fix tests

* fix(sap): - fix lint

* Update transformation.py

* fix(sap): fix model description and fix after rebase

* change(sap): - http calls in chat handler, response transformation and auth handling without sap sdk.

* change(sap): switching to v2 (chat handler, chat transformation), code clean up

* add deployment discovery and improved crendentials handling

* add deployment discovery and improved crendentials handling

* change(sap): - fix sync stream

* change(sap): - fix sync stream

* fix(sap): - fix response format

* fix(sap): - switch embedding to v2 and http request
- reimplement stream creator
- improve request transformation

* fix async streaming

* fix(sap): linters, transformation models, remove sap dependency test

* fix(sap): code clean up

* add unit test for sap chat completion

* linters fix

* move token, rg and base_url to properties

* (sap): add embedding unit test

Signed-off-by: Vasilisa Parshikova <vasilisa.parshikova@sap.com>

* fix(sap): bypass response format for some models

Signed-off-by: Vasilisa Parshikova <vasilisa.parshikova@sap.com>

* fix(sap): fix chat transformation and list of supported params

Signed-off-by: Vasilisa Parshikova <vasilisa.parshikova@sap.com>

* fix(sap): fix lint

* add sap service key module parameter

* fix(sap): remove unused code

* fix(sap): remove prices

* add service key support

* fix(sap): - add message content validations
- change get_supported_openai_params in chat transformation

* typo in mock

* fix(sap): - fix in supported params map

* fix(sap): - fix in message content validation

* fix(sap): - fix in message content validation

* fix(sap): - use litellm client for credentials

* fix(sap): - linter fix

* fix(sap): - use build in custom_http_client
- move credentials handling to transformation

* fix(sap): - handle stream_options

* fix(sap): - fix tests

* fix(sap): - code clean up, linter fix

* skip other authentication options when creds are provided

* fix local variable

---------

Signed-off-by: Vasilisa Parshikova <vasilisa.parshikova@sap.com>
Co-authored-by: Mathis Boerner <mathis.boerner@sap.com>
Co-authored-by: karimmohraz <37623804+karimmohraz@users.noreply.github.com>
Co-authored-by: Karim <karim.mohraz@sap.com>
v1.80.9-nightly 		2025-12-08 12:31:06 -08:00
Alexsander HamirandGitHub 958c190134 Fix flanky tests (#17665) 
* Fix test_delete_polling_removes_from_cache mock setup

- Mock async_delete_cache to properly execute the real implementation path
- Ensures init_async_client() is called and delete() is invoked on the returned client
- Fixes AssertionError: Expected 'delete' to be called once. Called 0 times.

* fix: resolve timeout in add_model_tab test by mocking useProviderFields hook

- Mock useProviderFields hook to prevent network calls and React Query delays
- Use waitFor to properly handle async operations
- Test now passes reliably without 10s timeout

* fix: add test timeout to prevent CI timeout failure

- Add 15 second timeout to 'should display Test Connect and Add Model buttons' test
- Test takes ~6 seconds locally, but CI was timing out at default 5 second limit
- Ensures test has sufficient time to complete in CI environment

* test: quarantine flaky test_oidc_circleci_with_azure

Quarantine test that fails with 401 Unauthorized from Azure OAuth.
The test is flaky and blocks CI builds. Marked with @pytest.mark.skip
until Azure authentication can be fixed or migrated to our own account.
 2025-12-08 12:21:26 -08:00
Eric84626andGitHub 2d5a50804b fix: Return 403 exception when calling GET responses api (#17629) 2025-12-08 11:27:52 -08:00
Sameer KankuteandGitHub 05f800fe7d Merge pull request #17653 from BerriAI/litellm_fireworks_rerank_model 
(Feat) Add fireworks rerank support
 2025-12-08 21:33:08 +05:30
Sameer KankuteandGitHub 7aaab32313 Merge pull request #17651 from BerriAI/litellm_audio_caching_fix 
Use audio content for caching
 2025-12-08 20:57:09 +05:30
Sameer KankuteandGitHub 83b803743f Merge pull request #17654 from BerriAI/litellm_fix_responses_polling_lint 
Fix error for response api polling
 2025-12-08 20:56:15 +05:30
Sameer KankuteandGitHub b4eb3dc6a6 Merge branch 'main' into litellm_fix_responses_polling_lint 2025-12-08 20:43:45 +05:30
Sameer Kankute 0766bfd005 Fix lint and mypy error for response api polling 2025-12-08 20:42:23 +05:30
Sameer KankuteandGitHub 76469182bc Merge pull request #17641 from BerriAI/litellm_responses_api_usage_populated 
Add usage details in responses usage object
 2025-12-08 20:38:31 +05:30
Sameer Kankute 498b4e4513 Remove unused import: litellm.secret_managers.main.get_secret_str 2025-12-08 20:32:51 +05:30
Sameer Kankute 87cf6f3ffe Add fireworks rerank support 2025-12-08 20:29:50 +05:30
Sameer Kankute f486fb2283 Use audio content for caching 2025-12-08 19:31:22 +05:30
Alexsander HamirandGitHub 60a325e403 Document missing environment variables and fix incorrect types (#17649) 
* fix: correct type annotations for anthropic streaming handlers

- Fix return type of _handle_accumulated_json_chunk from Optional[GenericStreamingChunk] to Optional[ModelResponseStream]
- Fix return type of _parse_sse_data from Optional[GenericStreamingChunk] to Optional[ModelResponseStream]
- Add type annotation for output_items in background_streaming.py

These changes align type annotations with actual return values from chunk_parser() which returns ModelResponseStream.

* docs: add missing ONYX_API_KEY and ONYX_API_BASE to environment variables reference

- Add ONYX_API_BASE documentation entry
- Add ONYX_API_KEY documentation entry
- Fixes test_env_keys.py test failure
 2025-12-08 05:38:21 -08:00
Krrish Dholakia 6ec7e95f28 bump: version 1.80.8 → 1.80.9 2025-12-07 23:49:51 -08:00
Cesar GarciaandGitHub b6b155d67b fix(anthropic): handle partial JSON chunks in streaming responses (#17493) 
Fixes #17473 - Anthropic streaming fails with JSONDecodeError when
network fragmentation causes SSE data to arrive in partial chunks.

Changes:
- Add accumulated_json buffer and chunk_type to ModelResponseIterator
- Add _handle_accumulated_json_chunk() to accumulate partial JSON
- Add _parse_sse_data() to handle both complete and partial chunks
- Modify __next__ and __anext__ to use accumulation logic
- Add unit tests for partial chunk handling
 2025-12-07 23:34:42 -08:00
Tamir KivitiandGitHub 0f5694c8eb add onyx guardrail hooks integration (#16591) 
* add onyx guardrail hooks integration

* fix lint issue

* fix lint issue

* update PR to use the new custom guardrail interface

* lint fix
 2025-12-07 23:33:28 -08:00
Raney CainandGitHub eb689a1f07 fix(proxy): async_post_call_streaming_iterator_hook now properly iterates async generators (#17626) 
The async_post_call_streaming_iterator_hook function was broken:
1. Was a sync function (def) not async generator
2. Returned AsyncGenerator without iterating it
3. Callback generators were chained but never consumed

This fix:
1. Makes the function an async generator (async def + yield)
2. Actually iterates through the chained callbacks with 'async for'
3. Properly yields chunks to the caller

Fixes #9639
 2025-12-07 23:29:42 -08:00
exprucandGitHub 2d112fc8b2 add option to include additional resources to chart (#17627) 2025-12-07 23:25:57 -08:00
Kevin MarxandGitHub 0650b5e80d fix(anthropic): prevent duplicate tool_result blocks with same (#17632) 
tool_use_id
 2025-12-07 23:24:58 -08:00
Chetan ChoudharyandGitHub d8ac213c6a Native Webhook Integration Sumologic (#17630) 
* Fix: Support generic_api_compatible_callbacks.json in callback initialization

- Added check in _add_custom_callback_generic_api_str to load callbacks from generic_api_compatible_callbacks.json
- Added SumoLogic webhook integration to generic_api_compatible_callbacks.json
- Fixes bug where callbacks in JSON file were not being loaded

* Added 3 unit tests for JSON callback loading
 2025-12-07 23:23:39 -08:00
Emerson GomesandGitHub b10cd13fd2 correct model type (#17635) 2025-12-07 23:18:54 -08:00
Kris XiaandGitHub 3f17c8d4ff docs(contributing): update clone instructions to recommend forking first (#17637) 
Update the setup instructions to guide contributors to fork the repository
on GitHub before cloning, which is the standard GitHub workflow for
open source contributions.
 2025-12-07 23:15:40 -08:00
Marty SullivanandGitHub d37f0b13f0 Add New Bedrock OSS Models to Model List (#17638) 
* try adding new bedrock models to backup file

* add new models to main model list

* fix amazon.nova-2-lite pricing
 2025-12-07 23:14:57 -08:00
Sameer Kankute 41f0cf8523 Add usage details in responses usage object 2025-12-08 11:51:47 +05:30
Sameer KankuteandGitHub b83bc10562 Merge pull request #16862 from xianzongxie-stripe/add_polling_via_cache_feature 
Add polling via cache feature
 2025-12-08 08:41:25 +05:30
yuneng-jiangandGitHub 321ffd7258 Merge pull request #17180 from BerriAI/litellm_non_root_docker_logo_fix 
[Fix] Add User Writable Directory to Non Root Docker for Logo
 2025-12-06 22:22:27 -08:00
yuneng-jiangandGitHub e2e35c3f87 Merge pull request #17522 from BerriAI/litellm_custom_webhook_fix 
[Fix] Custom Callback on UI
v1.80.8.dev.1 		2025-12-06 22:22:02 -08:00
yuneng-jiang d3d005f9bf fixing tests 2025-12-06 21:23:49 -08:00
yuneng-jiangandGitHub f9a4ba3359 Merge pull request #16795 from BerriAI/litellm_add_model_fix_team_admin 
[Fix] Make /litellm_model_cost_map public
 2025-12-06 21:06:39 -08:00
yuneng-jiangandGitHub d75f24e1ea Merge pull request #17513 from BerriAI/litellm_scim_v2_fix 
[Fix] Race Condition Handling in SCIM v2
 2025-12-06 21:06:30 -08:00
yuneng-jiang a560db56d5 Merge remote-tracking branch 'origin' into litellm_scim_v2_fix 2025-12-06 20:01:05 -08:00
yuneng-jiang 1d95595522 Merge remote-tracking branch 'origin' into litellm_non_root_docker_logo_fix 2025-12-06 20:00:33 -08:00
yuneng-jiang 539e3721f2 Merge remote-tracking branch 'origin' into litellm_add_model_fix_team_admin 2025-12-06 20:00:01 -08:00
yuneng-jiang 96f39484f1 Merge remote-tracking branch 'origin' into litellm_custom_webhook_fix 2025-12-06 19:59:15 -08:00
yuneng-jiangandGitHub a2688c7017 Merge pull request #17567 from BerriAI/litellm_ui_chat_endpoint_search 
[Fix] Filtering for Chat UI Endpoint Selector
 2025-12-06 19:57:32 -08:00
yuneng-jiangandGitHub 38ae12e124 Merge pull request #17573 from BerriAI/litellm_ui_reusable_table_action_button 
[Refactor] Reusable Table Icon Button
 2025-12-06 19:57:05 -08:00
yuneng-jiangandGitHub 816854e426 Merge pull request #17623 from BerriAI/litellm_usage_page_ui_improvements 
[Feature] Logs Spend Enhancements
 2025-12-06 19:56:49 -08:00
yuneng-jiangandGitHub ec06b31e64 Merge pull request #17624 from BerriAI/litellm_old_ui_deprecation_message 
[Fix] Fix links + old login page deprecation message
 2025-12-06 19:56:32 -08:00
yuneng-jiangandGitHub 37da2f90c2 Merge pull request #17625 from BerriAI/litellm_user_info_delete_modal 
[Feature] User Info Delete Modal
 2025-12-06 19:56:10 -08:00
yuneng-jiang b9fe2cb2fb Fix links + old login page deprecation message 2025-12-06 17:17:47 -08:00
yuneng-jiang 76e9b69cad Fixing tests 2025-12-06 17:03:37 -08:00
yuneng-jiang 99d95457b6 Fixing tests 2025-12-06 17:00:58 -08:00
yuneng-jiang 71cf7b9dd8 Delete User Modal on Info Page 2025-12-06 16:59:05 -08:00
Ishaan Jaffer cc2386601d ci/cd new release v1.80.8-nightly v1.80.8.rc.1 2025-12-06 16:22:00 -08:00
Ishaan Jaffer 2b069a343b test_init_custom_logger_compatible_class_as_callback 2025-12-06 16:21:50 -08:00
yuneng-jiangandGitHub 6fb1cf3ae5 Merge pull request #17621 from BerriAI/litellm_ui_edit_team_member_modal 
[Feature] Loading states for Edit Membership modal
 2025-12-06 16:16:20 -08:00
Ishaan Jaffer c78c2cf3e9 test_async_no_duplicate_spend_logs 2025-12-06 16:14:56 -08:00
yuneng-jiang 4e4a2e7ca2 Spend logs spend column enhancement 2025-12-06 16:14:33 -08:00