Ishaan Jaff
142567e143
[Fix] Containers API - Allow using LIST, Create Containers using custom-llm-provider ( #17740 )
...
* test_router_acreate_container_without_model
* _init_containers_api_endpoints
* test_init_containers_api_endpoints
2025-12-09 17:00:35 -08:00
yuneng-jiang
d99cf81386
Fixing test
2025-12-09 16:11:17 -08:00
yuneng-jiang
9a7831dd33
Merge pull request #17697 from BerriAI/litellm_ui_settings_ui
...
[Feature] UI - UI Settings
2025-12-09 15:58:08 -08:00
ephrimstanley
a91dda1194
Return 403 instead of 503 for unauthorized routes ( #17723 )
2025-12-09 15:16:11 -08:00
Krrish Dholakia
cc8a46b6b2
bump: version 1.80.9 → 1.80.10
2025-12-09 14:55:43 -08:00
yuneng-jiang
bdfc3308b1
Merge pull request #17741 from BerriAI/litellm_ui_cred_fix_2
...
[Fix] Change credential encryption to only affect db credentials
2025-12-09 14:04:20 -08:00
Alexsander Hamir
9a0432d013
[Fix] Perf - Reduce memory accumulation of spend_logs ( #17742 )
...
Replaces time-based spend log processing with a queue-size-based approach to improve performance and reduce memory usage. The new implementation:
- Adds background task that monitors spend_log_transactions queue size
- Triggers processing when queue reaches configurable threshold (default: 100)
- Implements exponential backoff when queue is idle to reduce CPU usage
- Increases batch processing limits (BATCH_SIZE: 100→1000, MAX_LOGS_PER_INTERVAL: 1000→10000)
- Adds configurable environment variables: SPEND_LOG_QUEUE_SIZE_THRESHOLD, SPEND_LOG_QUEUE_POLL_INTERVAL
This approach prevents unbounded queue growth while reducing unnecessary polling overhead.
2025-12-09 14:00:34 -08:00
yuneng-jiang
879ae45421
Change credential encryption to only affect db credentials
2025-12-09 13:36:40 -08:00
YutaSaito
80a18f989a
feat: propagate Langfuse trace_id ( #17669 )
2025-12-09 12:25:52 -08:00
yuneng-jiang
68419cfe4e
Merge remote-tracking branch 'origin' into litellm_tag_spend_dedupe
2025-12-09 11:59:47 -08:00
yuneng-jiang
39bf7a9f7c
Merge remote-tracking branch 'origin' into litellm_allow_custom_mount_paths
2025-12-09 11:58:05 -08:00
yuneng-jiang
4bffbe0bff
Merge remote-tracking branch 'origin' into litellm_sso_config_2
2025-12-09 11:56:30 -08:00
yuneng-jiang
9253a9c365
Merge pull request #17689 from BerriAI/litellm_ui_settings_backend
...
[Feature] Get and Update Backend Routes for UI Settings
2025-12-09 11:55:28 -08:00
Shivam Rawat
43a7bbeeaf
added note for using Azure Active Directory Tokens with all the other endpoints ( #17733 )
2025-12-09 11:51:28 -08:00
yuneng-jiang
aa450e7ebe
Merge pull request #17738 from BerriAI/litellm_doc_update_1805
...
[Docs] Adding known issues to 1.80.5-stable docs
2025-12-09 11:46:08 -08:00
yuneng-jiang
431884f591
Adding known issues to 1.80.5-stable docs
2025-12-09 11:45:16 -08:00
yuneng-jiang
1b86269584
Bump version to include new schema
2025-12-09 11:25:24 -08:00
yuneng-jiang
7957244367
bump: version 0.4.11 → 0.4.12
2025-12-09 11:24:18 -08:00
yuneng-jiang
36183c3a9b
Adding migration
2025-12-09 11:23:26 -08:00
yuneng-jiang
e4442c2946
Change UI Settings to a dedicated table
2025-12-09 11:19:53 -08:00
Derek Duenas
3322523e07
Passthrough in response ( #17102 )
...
* attempt to implement the passthrough feature
* Formatting and small change
* Fix formatting
* feat: grayswan guardrail overwrite ModelResponse in passthrough mode
* fix missing exception error catching on certain
endpoints
* fix wrong call site
* fix: patch anthropic endpoint internal error on streaming obj
* fix grayswan testcase
* feat: update the violation response to more natural
* Formatting
* move passthrough exception definition to custom_guardrail.
* Enhancement: show whether the blocked at input or output
* update exception name
* fix a typo in testing unit.
---------
Co-authored-by: Xiaohan Fu <xiaohan@grayswan.ai>
2025-12-09 10:45:45 -08:00
yuneng-jiang
305a7c6bd5
Merge remote-tracking branch 'origin' into litellm_ui_settings_backend
2025-12-09 10:21:52 -08:00
yuneng-jiang
486bcbe4e8
Revert "UI Settings Frontend"
...
This reverts commit 51275e7014
2025-12-09 10:21:30 -08:00
Sameer Kankute
baed9fcea2
Merge branch 'main' into litellm_videos_bugs_2
2025-12-09 23:30:13 +05:30
Sameer Kankute
878c86e632
Add tests for handling video with litellm param
2025-12-09 23:27:20 +05:30
Sameer Kankute
237f6b991f
Merge pull request #17708 from BerriAI/litellm_videos_bug_fixes
...
Fix error about encoding video id for azure
2025-12-09 23:11:17 +05:30
Sameer Kankute
320f861916
Fix : use litellm params for other video apis
2025-12-09 23:03:29 +05:30
Krish Dholakia
81f0bbad73
Add Azure AI Search to supported vector stores ( #17726 )
...
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2025-12-09 09:04:04 -08:00
Raghav Jhavar
face8173b0
fix failing test
2025-12-09 19:42:26 +07:00
Sameer Kankute
b39c21d90c
fix: Add _delete_nested_value_custom to recursive function ignore list
...
The _delete_nested_value_custom function is recursive but has bounded depth
(limited by the number of path segments), preventing infinite recursion.
This is necessary for nested field removal in additional_drop_params.
2025-12-09 17:56:13 +05:30
Sameer Kankute
920fe3bf01
chore: Revert poetry.lock to match origin/main
...
The nested field removal feature uses a custom implementation with zero
external dependencies, so poetry.lock should match origin/main. The
previous changes were from the intermediate commit that added jsonpath-ng,
which was later removed.
2025-12-09 17:52:03 +05:30
Sameer Kankute
4ff992a073
fix: Improve type safety in dot_notation_indexing for nested field removal
...
- Change _delete_nested_value_custom parameter type from Dict[str, Any] to Union[Dict[str, Any], List[Any]] to accurately reflect that it handles both dicts and lists
- Add explicit isinstance checks before recursing into list items to ensure type safety
- Prevents potential runtime errors when encountering primitive types in nested structures
2025-12-09 17:44:24 +05:30
mzagar
9bb0e7dd75
feat: Replace jsonpath-ng with custom minimal parser for additional_drop_params
2025-12-09 17:30:30 +05:30
mzagar
761798e5c7
fix: Use .get() method to access additional_drop_params for MyPy compatibility
...
Changes litellm_params.additional_drop_params to litellm_params.get("additional_drop_params")
to avoid MyPy error since additional_drop_params is not a defined Pydantic field.
This matches the existing pattern used throughout llm_http_handler.py for accessing
optional fields (e.g., ssl_verify, timeout, etc.).
2025-12-09 17:30:00 +05:30
mzagar
da2aa2ba8d
feat: Add nested field removal support to additional_drop_params using JSONPath
2025-12-09 17:29:56 +05:30
Raghav Jhavar
7bdf52c491
fix linting error
2025-12-09 18:28:17 +07:00
Raghav Jhavar
9e85dcbd60
read responses api usage
2025-12-09 18:14:00 +07:00
Sameer Kankute
a7e5be8e03
Fix error about encoding video id for azure
2025-12-09 16:36:11 +05:30
Sameer Kankute
385f4e8eee
Add anthropic retrieve batches and retreive file content support
2025-12-09 13:58:56 +05:30
yuneng-jiang
dab4c9d8ab
Merge remote-tracking branch 'origin' into litellm_sso_config_2
2025-12-08 21:19:50 -08:00
yuneng-jiang
8039c5052f
Merge pull request #17681 from BerriAI/litellm_ui_fallback_login_alert
...
[Fix] Change deprecation banner to only show on /sso/key/generate
2025-12-08 21:18:38 -08:00
yuneng-jiang
0a6038d4c5
UI Settings Frontend
2025-12-08 21:12:43 -08:00
yuneng-jiang
51275e7014
UI Settings Frontend
2025-12-08 21:12:06 -08:00
YutaSaito
5b926ae2c6
fix: resolve UI session MCP permissions across real teams ( #17620 )
...
* fix: resolve UI session MCP permissions across real teams
* fix: remove user from logs
2025-12-08 19:03:01 -08:00
chenzhaofei01
458032b083
fix dashscope default api_base error ( #17584 )
2025-12-08 19:02:55 -08:00
Earl St Sauver
ad9c69860e
Fix Cerebras context window errors not recognized ( #17587 )
...
Add detection for Cerebras's context window exceeded error format:
"Current length is X while limit is Y"
This ensures LiteLLM raises ContextWindowExceededError instead of
generic BadRequestError when Cerebras API calls exceed the model's
context limit, enabling downstream libraries like DSPy to properly
catch and handle these errors for automatic context management.
2025-12-08 19:02:06 -08:00
Cesar Garcia
a7ad8a36a4
chore: cleanup unused scripts and fix misplaced test file ( #17611 )
...
Remove scripts/ directory containing unused development/debug scripts:
- mock_ibm_guardrails_server.py
- test_groq_streaming_issue.py (debug for #12660 )
- test_mock_ibm_guardrails.py
- update_readme_providers_table.py
Move misplaced test file to correct location:
- test_litellm/ -> tests/test_litellm/ (from PR #17221 )
2025-12-08 19:00:55 -08:00
Ishaan Jaff
b673177b22
Add 227 new Fireworks AI models ( #17692 )
2025-12-08 18:57:43 -08:00
Sergei Silnov
f5dc8b7c38
fix: Use python instead of wget for healthcheck in docker-compose.yml ( #17646 )
...
Fixes #17645
2025-12-08 18:54:54 -08:00
Chetan Choudhary
38eda3409a
docs: Add SumoLogic integration documentation ( #17647 )
...
* docs: Add SumoLogic integration documentation
* minor update
2025-12-08 18:54:07 -08:00
