scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-09-07 08:26:10 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 36
33245 commits 4135 branches 1402 tags 2.1 GiB
Commit graph

33245 commits

This branch
This branch
All branches
Author SHA1 Message Date
Sameer Kankute
c123dc5c24 Fix vercel build 2026-02-19 22:19:34 +05:30
Sameer Kankute
9f66a4c122 Fix test_reasoning_effort_dict_format_gemini_3 2026-02-19 22:14:20 +05:30
Sameer Kankute
884c763fb1 Fix date in docs 2026-02-19 22:14:20 +05:30
Sameer Kankute
a951d6c681 Update docs/my-website/blog/gemin_3.1/index.md 
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
 2026-02-19 22:14:20 +05:30
Sameer Kankute
e27725a8b5 Update docs/my-website/blog/gemin_3.1/index.md 
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
 2026-02-19 22:14:20 +05:30
Sameer Kankute
468be6f5a8 Fix date in docs 2026-02-19 22:14:20 +05:30
Sameer Kankute
2133a97e97 Add gemini-3.1-pro-preview pricing data 2026-02-19 22:14:19 +05:30
Sameer Kankute
8305bbee21 Add mapping for medium thinking level for gemini-3.1-pro-preview 2026-02-19 22:14:19 +05:30
Milan
83c88d5ab1 fix(router): add warning log and cleanup for credential resolution 
- Add warning when credential name is not found in credential_list
- Remove litellm_credential_name from credentials dict after resolution

Addresses Greptile bot review comments on PR #21502
 2026-02-19 18:09:19 +02:00
Milan
d477ddf591 trigger PR update 2026-02-19 17:40:23 +02:00
Julio Quinteros Pro
f3003a9840 fix(types): fix mypy errors in pass-through endpoint query param types 
- passthrough/utils.py: change `request_query_params` from `Dict` to
  `Mapping` so callers passing `dict[str, str]` satisfy the type checker
  (dict is invariant; Mapping is covariant in its value type)
- pass_through_endpoints.py: cast `param_default_query_params` to
  `Optional[dict]` consistent with the existing cast pattern for other
  params extracted from the untyped `target_params` dict

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-19 12:24:14 -03:00
Milan
d80ae36e4a test(router): add test for credential name resolution 
Add test to verify that get_deployment_credentials_with_provider correctly
resolves litellm_credential_name to actual credential values and removes
the credential name from the returned dictionary.
 2026-02-19 17:21:01 +02:00
jquinter
ec28395054
Merge pull request #21564 from BerriAI/fix/competitor-constants-env-override 
fix(constants): add env var override support for COMPETITOR_LLM_TEMPERATURE and MAX_COMPETITOR_NAMES
 2026-02-19 11:51:57 -03:00
michelligabriele
053ee4826f
fix(websearch_interception): fix pre_call_deployment_hook not triggering via proxy router (#21433) 
* fix(websearch_interception): fix pre_call_deployment_hook not triggering via proxy router

Fix provider lookup (check top-level kwargs + fallback to get_llm_provider),
return full kwargs dict instead of partial, and use OpenAI-format tool definition.

* remove unnecessary inline import
 2026-02-19 06:38:45 -08:00
Julio Quinteros Pro
4227690025 fix(constants): add env var override support for COMPETITOR_LLM_TEMPERATURE and MAX_COMPETITOR_NAMES 
These constants were added as hardcoded values in #21533 without environment
variable support, causing test_all_numeric_constants_can_be_overridden to fail.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
 2026-02-19 11:28:49 -03:00
Sameer Kankute
ca34e9a3f9
Merge pull request #21543 from BerriAI/litellm_passthrough_endpoint_method 
Add method based routing for passthrough endpoints
 2026-02-19 19:34:04 +05:30
Sameer Kankute
ca91814b85 rrevert changes 2026-02-19 19:33:34 +05:30
Sameer Kankute
f2393fc9cb Merge main into litellm_passthrough_endpoint_method 
Resolved conflicts in pass_through_endpoints.py by:
- Accepting main's formatting and mypy fixes
- Preserving branch's method support feature
- Preserving branch's default_query_params feature

Combined changes include:
- Method filtering for passthrough endpoints
- Default query parameters support
- Updated route key format to include methods
- Code formatting improvements from main
- Fixed type annotations

Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-02-19 19:22:41 +05:30
Sameer Kankute
647e5237a7
Merge pull request #21555 from BerriAI/litellm_server_side_compaction_trans 
[Feat] Add server side compaction translation from openai to anthropic
 2026-02-19 19:14:37 +05:30
Sameer Kankute
8bcca905a7
Merge pull request #21539 from BerriAI/litellm_fix_azure_store_param 
Fix: add stop param as supported for openai and azure
 2026-02-19 19:12:43 +05:30
Sameer Kankute
36e21830db
Merge pull request #21550 from BerriAI/litellm_add_global_usage 
[Feat] Add Default usage data configuration
 2026-02-19 19:10:35 +05:30
Sameer Kankute
1ad9d26c6f
Merge pull request #21559 from BerriAI/fix_openai/bge-multilingual-gemma2 
Fix usage in xai
 2026-02-19 19:07:09 +05:30
Sameer Kankute
308cdb2720
Merge pull request #21557 from SherifWaly/sherif.waly/add-reasoning-multi-turn-hosted-vllm 
Convert thinking_blocks to content blocks for hosted_vllm multi-turn
 2026-02-19 18:56:09 +05:30
Sameer Kankute
fc7fa73b6f Fix usage in xai 2026-02-19 18:48:30 +05:30
Harshit Jain
5258007e22
fix: remove old test file 2026-02-19 18:47:45 +05:30
Harshit Jain
19c8f78c2f
fix: update docker test file to right path 2026-02-19 18:44:28 +05:30
Sameer Kankute
8432d3488e
Merge pull request #20841 from themavik/fix/license-check-debug-log-spam-17953 
fix(proxy): prevent is_premium() debug log spam on every request
 2026-02-19 18:33:41 +05:30
Sameer Kankute
0bea9c1dbc
Merge pull request #21497 from SolitudePy/fix/github-provider-match-openai-metadata 
fix: allow github aliases to reuse upstream model metadata
 2026-02-19 18:30:33 +05:30
Sameer Kankute
0617afef30
Merge pull request #17430 from richardmcsong/patch-1 
Uncomment response_model in user_info endpoint
 2026-02-19 18:28:49 +05:30
Sameer Kankute
ea8c8ebc05
Merge pull request #21547 from ZeroAurora/remove-dashscope-str-transformation 
fix: remove list-to-str transformation from dashscope
 2026-02-19 18:20:06 +05:30
sherif.waly
5774c845d8 Convert thinking_blocks to content blocks for hosted_vllm multi-turn 
For multi-turn conversations, convert thinking_blocks on assistant
messages into content blocks prepended before the rest of the content,
so reasoning context is passed back to the hosted_vllm API.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-02-19 12:25:18 +00:00
Sameer Kankute
f86b195f88 rrevert changes 2026-02-19 16:47:29 +05:30
Sameer Kankute
02e10c9a74
Merge branch 'main' into litellm_server_side_compaction_trans 2026-02-19 16:45:53 +05:30
Sameer Kankute
a52fc738af Add server side compaction translation from openai to anthropic 2026-02-19 16:44:35 +05:30
Harshit Jain
9a71ba3505
Merge pull request #21078 from Harshit28j/litellm_project_management_apis 
Litellm project management apis
 2026-02-19 14:26:11 +05:30
Sameer Kankute
0eb2a0c014 Add Default usage data configuration 2026-02-19 14:04:07 +05:30
Harshit Jain
bdf01fa283
fix mypy error 2026-02-19 14:04:00 +05:30
Sameer Kankute
0771ea8d42 fix log 2026-02-19 13:27:50 +05:30
ZeroAurora
64c916b37b fix: remove list-to-str transformation from dashscope 2026-02-19 07:30:13 +00:00
Sameer Kankute
1ceb7d8e29 Add default query param in UI 2026-02-19 12:48:27 +05:30
Sameer Kankute
4a50c55d84 Add allow defining default query params for a pass through 2026-02-19 12:48:03 +05:30
yuneng-jiang
7a4383dfd4 adding migration and builds 2026-02-18 23:16:25 -08:00
yuneng-jiang
90a11038f8 bump: version 0.4.40 → 0.4.41 2026-02-18 23:15:53 -08:00
yuneng-jiang
6097905e55 [Feature] Track key last active timestamp 
Virtual keys only track created_at and updated_at, which don't indicate
when a key was last used. This adds a last_active field that gets updated
during the async batch spend update, giving admins visibility into which
keys are actively being used.

Changes:
- Add last_active DateTime? to VerificationToken and
  DeletedVerificationToken in all 3 schema files and Python types
- Set last_active in the batch key spend update alongside spend increment
- Add Last Active column to virtual keys UI table with info popover
  and hover tooltip showing full date/time with timezone

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-02-18 23:11:58 -08:00
Sameer Kankute
26c3d7debc Update Ui for adding method to passthrough endpoints 2026-02-19 11:59:36 +05:30
Sameer Kankute
5bd7bf1b3e Add documentation for adding method 2026-02-19 11:59:09 +05:30
Sameer Kankute
4e111d4372 Add test got method speicifc routing 2026-02-19 11:58:48 +05:30
Sameer Kankute
32bfbbfbe1 Add method support for passthrough endpoints 2026-02-19 11:58:25 +05:30
yuneng-jiang
70d5281b52
Merge pull request #21537 from BerriAI/litellm_team_member_usage_permission 
[Feature] Allow team members to view entire team usage
 2026-02-18 22:01:13 -08:00
Sameer Kankute
44a68cf1c6 Fix: add stop param as supported for openai and azure 2026-02-19 11:26:38 +05:30