Ishaan Jaffer
8439fde7c1
bump litellm-proxy-extras
2025-11-15 09:11:34 -08:00
Ishaan Jaffer
7ee8a41cef
ruff check fix
2025-11-15 09:10:21 -08:00
yuneng-jiang
9f45348bb2
Building UI for QA ( #16686 )
2025-11-15 09:03:29 -08:00
Ishaan Jaffer
0699430206
test logging tests + mcp server QA checks
2025-11-15 08:58:46 -08:00
yuneng-jiang
cff8a3115a
Merge with main
2025-11-14 20:02:35 -08:00
Jorge Yero Salazar
15a04681ff
Fix UI logos loading with SERVER_ROOT_PATH ( #16618 )
2025-11-14 19:38:50 -08:00
Cesar Garcia
cc72037cec
feat(openai): Add verbosity parameter support for GPT-5 family models ( #16660 )
...
OpenAI's GPT-5 model family supports a verbosity parameter to control
the length and detail of responses. This parameter accepts three values:
'low', 'medium', or 'high'.
Changes:
- Added verbosity parameter to completion() and acompletion() signatures
- Added verbosity to DEFAULT_CHAT_COMPLETION_PARAM_VALUES in constants.py
- Added verbosity to get_optional_params() in utils.py
- Added verbosity to GPT-5 supported params list
- Updated OpenAI docs with verbosity usage examples
- Added comprehensive test for verbosity parameter
Supported models: gpt-5, gpt-5.1, gpt-5-mini, gpt-5-nano, gpt-5-codex, gpt-5-pro
2025-11-14 19:38:27 -08:00
Rob Geada
d35d9008c9
Ensure detector-id is passed as header to IBM detector server ( #16649 )
2025-11-14 19:35:49 -08:00
Luka Pečnik
d84e97f211
fix: preserve $defs for Anthropic tools input schema ( #16648 )
...
* fix: preserve $defs for Anthropic tools input schema
* fix: preserve $defs for Anthropic tools input schema
* fix: preserve $defs for Anthropic tools input schema
2025-11-14 19:35:27 -08:00
yuneng-jiang
473886d35a
user_alias in read and update path ( #16669 )
2025-11-14 19:34:28 -08:00
pnookala-godaddy
f599a462c1
openai(video): use GET for /videos/{id}/content by returning empty params; add tests to assert GET ( #16672 )
2025-11-14 19:33:37 -08:00
Ishaan Jaffer
63994e302e
test_call_with_key_over_model_budget
2025-11-14 19:05:00 -08:00
Ishaan Jaffer
acad73018d
fix pkg lock
2025-11-14 18:59:49 -08:00
Ishaan Jaffer
39c1a970a1
fix
2025-11-14 18:56:30 -08:00
Krrish Dholakia
9ced18b695
perf: use reusable http client
2025-11-14 18:56:14 -08:00
Krrish Dholakia
938ec7c39a
fix: fix linting error
2025-11-14 18:54:24 -08:00
Ishaan Jaffer
11cf22e7b8
add "provider_specific_fields": null
2025-11-14 18:49:35 -08:00
Ishaan Jaffer
a69011883a
fix logging_testing
2025-11-14 18:48:20 -08:00
Ishaan Jaffer
efb80ffab7
fix pkg lock
2025-11-14 18:43:41 -08:00
Ishaan Jaffer
a1286fb609
security fix
2025-11-14 18:43:41 -08:00
yuneng-jiang
09e226b140
[Feature] UI - New Callbacks table ( #16512 )
...
* New Callbacks table
* Change Action Buttons to use Icons
* Changed to follow our existing pattern
* Removed unused import
2025-11-14 18:36:59 -08:00
Ishaan Jaffer
9e8653ad3c
fix prisma client
2025-11-14 18:25:27 -08:00
Krrish Dholakia
54e7792933
fix: remove dailytag request id migration from agents_table.sql
2025-11-14 18:24:01 -08:00
Krish Dholakia
8097fafc05
Agents - support agent registration + discovery (A2A spec) ( #16615 )
...
* fix: initial commit adding types
* refactor: refactor to include agent registry
* feat(agents/): endpoints.py
working endpoint for agent discovery
* feat(agent_endpoints/endpoints.py): add permission management logic to agents endpoint
* feat: public endpoint for showing publicly discoverable agents
* feat: make /public/agent_hub discoverable
* feat(agent_endpoints/endpoints.py): working create agent endpoint
adds dynamic agent registration to the proxy
* feat: working crud endpoints
* feat: working multi-instance create/delete agents
* feat(migration.sql): add migration for agents table
2025-11-14 18:23:30 -08:00
Ishaan Jaffer
65468353d1
provider_specific_fields
2025-11-14 18:17:50 -08:00
YutaSaito
f487f4e3a9
feat: add dynamic OAuth2 metadata discovery for MCP servers ( #16676 )
...
* feat: add dynamic OAuth2 metadata discovery for MCP servers
* fix: lint error
2025-11-14 18:14:43 -08:00
yuneng-jiang
24c23c62ba
Linting
2025-11-14 18:14:22 -08:00
yuneng-jiang
ae4dfb53dd
Add migration
2025-11-14 18:06:49 -08:00
yuneng-jiang
63dcd00b8b
Merge remote-tracking branch 'origin/main' into litellm_org_usage
2025-11-14 18:05:50 -08:00
yuneng-jiang
6063a75155
Remove Description Field from LLM Credentials ( #16608 )
2025-11-14 17:48:44 -08:00
Ishaan Jaffer
7faff1a7c0
pkg lock
2025-11-14 17:43:43 -08:00
Ishaan Jaffer
936bed056b
security fix
2025-11-14 17:43:00 -08:00
Ishaan Jaff
8a43fbe8f7
Revert "[Feat] VertexAI - Add BGE Embeddings support ( #16033 )" ( #16677 )
...
This reverts commit 7133488282
2025-11-14 17:41:06 -08:00
Ishaan Jaffer
f8c022c8f5
bump new schema
2025-11-14 17:39:54 -08:00
Ishaan Jaffer
6b532b31a6
bump: version 1.79.3 → 1.79.4
2025-11-14 17:38:46 -08:00
Ishaan Jaffer
87b7780182
fix LiteLLM_DailyTagSpend add request_id
2025-11-14 17:35:54 -08:00
Ishaan Jaffer
8fdb12a44b
fix bedrock agentocre
2025-11-14 17:31:34 -08:00
Ishaan Jaffer
c18f411a5e
test_encrypt_response_id_success
2025-11-14 17:28:15 -08:00
Ishaan Jaffer
74763f6cfc
fix _map_reasoning_effort
2025-11-14 17:27:32 -08:00
Ishaan Jaff
bffc36794f
docs fix spend tracking ( #16675 )
2025-11-14 17:22:21 -08:00
Ishaan Jaff
efa4ec9294
[Docs] Add docs on APIs for model access management ( #16673 )
...
* docs access groups
* docs ui for access groups
* fix code snippets
* docs model access
2025-11-14 17:07:54 -08:00
Cesar Garcia
0a0b5eee47
fix: Resolve pytest module name collision for test_transformation.py files ( #16661 )
...
Fixes #16613
The issue was caused by two test files having the same module name
(test_transformation.py) in different directories, which caused pytest
to fail with an import file mismatch error.
Changes:
- Renamed tests/test_litellm/llms/xai/responses/test_transformation.py
to test_xai_responses_transformation.py
- Renamed tests/test_litellm/llms/openai_like/chat/test_transformation.py
to test_openai_like_chat_transformation.py
Both files now have unique, descriptive names that reflect their
specific test purposes and prevent module name collisions.
2025-11-14 16:50:40 -08:00
Emerson Gomes
1dac777346
Add Vertex Kimi-K2-Thinking ( #16671 )
...
* Add Vertex Kimi-K2-Thinking
* Update model_prices_and_context_window.json
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
* Update litellm/model_prices_and_context_window_backup.json
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
2025-11-14 16:49:48 -08:00
Ishaan Jaffer
e240ccef63
check if DB model
2025-11-14 16:41:32 -08:00
Ishaan Jaffer
d9df1e4ffd
code qa fix
2025-11-14 16:41:28 -08:00
Ishaan Jaff
b360cc957e
[Feat] Model Management API - Add API Endpoint for creating model access group ( #16663 )
...
* add NewModelGroupRequest
* add endpoint for create_model_group
* fix model_access_group_management_router
* add UpdateModelGroupRequest, info and delete
* fix model management tag
* fix validate_models_exist
* fix get_all_access_groups_from_db
* test_create_duplicate_access_group_fails
* test fixes
* fix working create access groups
* fix access group management endpoints
* add is db model checks for model access groups
2025-11-14 16:40:43 -08:00
yuneng-jiang
f1ff195bd8
Add Model uses endpoint info ( #16664 )
2025-11-14 16:08:27 -08:00
Ishaan Jaff
2bd6d0d82b
[Feat] Bedrock Batches - Add support for custom KMS encryption keys in Bedrock Batch operations ( #16662 )
...
* add s3_encryption_key_id
* add s3EncryptionKeyId to BedrockS3OutputDataConfig
* use s3EncryptionKeyId in bedrock output
* docs s3_encryption_key_id
* test_bedrock_batch_with_encryption_key_in_post_request
2025-11-14 16:00:43 -08:00
yuneng-jiang
7e22f4abc6
Normalize table action columns ( #16657 )
2025-11-14 14:11:01 -08:00
fzowl
b1922e19f8
Voyageai pricing and doc update ( #16641 )
...
* Refresh VoyageAI models and prices and context
* Refresh VoyageAI models and prices and context
* Refresh VoyageAI models and prices and context
* Updating the available VoyageAI models in the docs
* Updating the available VoyageAI models in the docs
* Updating the model prices and the docs
2025-11-14 14:09:11 -08:00
