yuneng-jiang
ac8f3807db
Merge pull request #20462 from BerriAI/litellm_model_info_cost
...
[Fix] UI - Model Info Page: Fix Input and Output Labels
2026-02-06 12:34:34 -08:00
yuneng-jiang
4de0ed7a9e
Merge pull request #20444 from BerriAI/litellm_ui_config_req_auth_mh
...
[Feature] UI - Admin Settings: Add option for Authentication for public AI Hub
2026-02-06 12:34:27 -08:00
yuneng-jiang
49eab29335
Merge pull request #20596 from BerriAI/litellm_ui_yj_cov_01
...
[Infra] UI - Testing: Adding Unit Testing Coverage
2026-02-06 12:33:40 -08:00
yuneng-jiang
8df6cfe9d8
fix model page col resize
2026-02-06 12:27:03 -08:00
Murali
52c9cf6058
fix(proxy): skip premium check for empty metadata fields on team/key update
...
Fixes #20534
The UI sends the full form on every team update, including premium
metadata fields like `policies: []` and `team_member_key_duration: ""`.
The backend's `_update_metadata_fields` treated any non-None value as
premium feature usage and returned 403 for non-enterprise users — even
when the fields were empty and the user was just updating basic settings
like team name or budget.
Added `_has_non_empty_value` helper and use it in the premium field gate
in `_update_metadata_fields` so empty lists, blank strings, and None
values skip the premium check entirely. Non-empty values still enforce
the enterprise requirement as before.
2026-02-06 14:50:24 -05:00
Alexsander Hamir
5733f6213b
Add INFO-level session reuse logging per request ( #20597 )
...
- Log when shared aiohttp session is attached to each request
- Log when no shared session is available
- Visible at INFO level (production-safe)
2026-02-06 11:36:33 -08:00
yuneng-jiang
ee70010ef1
Adding testing coverage
2026-02-06 11:32:35 -08:00
Ryan Crabbe
fc130376d9
test: add test for get_router_model_info with Deployment object
...
Verifies that get_router_model_info accepts a Deployment object directly
and properly handles the LiteLLM_Params isinstance check.
2026-02-06 10:13:54 -08:00
Ryan Crabbe
6500503ea5
perf: reuse LiteLLM_Params in get_router_model_info to avoid redundant construction
...
Pass Deployment object directly instead of converting to dict with .model_dump(),
then reuse the existing LiteLLM_Params instance via isinstance check. This
eliminates redundant Pydantic model construction in the deployment callback path.
~8% improvement in deployment_callback_on_success total time.
2026-02-06 10:03:36 -08:00
yuneng-jiang
b859d76cc2
Merge pull request #20553 from BerriAI/litellm_team_soft_budget_email
...
[Feature] Team Soft Budget Email Alerts
2026-02-06 09:36:16 -08:00
Alexsander Hamir
09fb6d0087
Warn when budget lookup fails; cache won't populate ( #20545 )
...
* Warn when budget lookup fails; cache won't populate
- Add _log_budget_lookup_failure helper in auth_checks.py
- Log at WARNING in get_user_object, get_team_object, get_key_object
when DB lookups fail (schema mismatch, etc.)
- Add schema migration hint for prisma/db errors
- Add dry-run test for _log_budget_lookup_failure
* fix: skip budget lookup failure log for expected user-not-found case
Avoid logging 'cache will not be populated' when the user simply doesn't
exist - not caching is correct behavior in that case. Only log for
unexpected errors (schema, DB, etc.) where the message is meaningful.
2026-02-06 09:24:44 -08:00
Kelvin Tran
789d9708b7
restore poetry lock
2026-02-06 09:23:40 -08:00
Kelvin Tran
82ba49690e
generate poetry lock with 2.3.2 poetry
2026-02-06 09:22:23 -08:00
Alexsander Hamir
53a1f2d21c
perf(prometheus): parallelize budget metrics, fix caching bug, reduce CPU by ~40% ( #20544 )
2026-02-06 09:18:24 -08:00
Sameer Kankute
ad1282de82
Merge pull request #20551 from BerriAI/litellm_opus_4.6_thinking
...
Add full support for Opus 4.6 (Anthropic, Azure AI, Bedrock, Vertex AI)
2026-02-06 19:30:47 +05:30
Sameer Kankute
eab7a99800
Merge pull request #20578 from BerriAI/litellm_claude_code_beta_headers
...
Add unsupported claude code beta headers in json
2026-02-06 19:10:13 +05:30
Sameer Kankute
285b2d2a12
add context_management header for compact_20260112 for messages
2026-02-06 19:06:49 +05:30
Sameer Kankute
db8423b799
Fix: test_json_response_nested_json_schema
2026-02-06 18:52:04 +05:30
Sameer Kankute
2e0715bd61
Fix mypy issue
2026-02-06 18:45:54 +05:30
Sameer Kankute
05ce4c68e5
Fix: test_vertex_ai_partner_models_anthropic_remove_prompt_caching_scope_beta_header
2026-02-06 18:34:57 +05:30
Sameer Kankute
fa26c6eeec
fix mypy issue
2026-02-06 18:29:28 +05:30
Sameer Kankute
40ff79655c
Add not_available in inference_geo
2026-02-06 18:29:28 +05:30
Sameer Kankute
786bd6ebc0
Fix merge conflicts
2026-02-06 18:29:14 +05:30
Sameer Kankute
c1a43914ee
Add documentation related to new beta header json
2026-02-06 17:54:56 +05:30
Sameer Kankute
3f9a7b1956
Add update_headers_with_filtered_beta in all messages API providers
2026-02-06 17:45:45 +05:30
Sameer Kankute
25a19b2091
Add update_headers_with_filtered_beta in anthropic
2026-02-06 17:45:05 +05:30
Sameer Kankute
920fea9520
feat: Add Unsupported Anthropic beta headers for each provider json
2026-02-06 17:44:09 +05:30
Swayambhu
a48a8ec945
refactor: Directly use Ant Design's notification hook instead of App.useApp for notification management.
2026-02-06 15:35:11 +05:30
Sameer Kankute
bfd21b5e00
Merge branch 'main' into litellm_opus_4.6_thinking
2026-02-06 14:17:40 +05:30
Sameer Kankute
d07c87860d
Merge pull request #20514 from PeterDaveHelloKitchen/feat/add-claude-opus-4-6-model
...
Align Claude Opus 4.6 metadata and limits
2026-02-06 14:14:52 +05:30
Sameer Kankute
a2b29d6328
Add complete documentation for claude_opus_4_6
2026-02-06 14:04:39 +05:30
Sameer Kankute
1ec89b8a04
Feat: add inference_geo based pricing
2026-02-06 13:58:47 +05:30
Sameer Kankute
0934a4ab68
Correct litellm/litellm/llms/anthropic/chat/transformation.py
2026-02-06 13:08:43 +05:30
Sameer Kankute
358a081f63
Add compaction support for vertex ai
2026-02-06 12:52:28 +05:30
Sameer Kankute
1396813d74
The compact beta feature is not currently supported on the Converse and ConverseStream APIs
2026-02-06 12:52:28 +05:30
Sameer Kankute
d0444f402c
Add test for compaction in anthropic
2026-02-06 12:52:28 +05:30
Sameer Kankute
7a473f2954
Apply suggestion from @greptile-apps[bot]
...
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-02-06 12:07:13 +05:30
Sameer Kankute
ea518a7684
Apply suggestion from @greptile-apps[bot]
...
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-02-06 12:06:50 +05:30
Sameer Kankute
887a977ab4
Add doc on how to enable compaction via chat completion
2026-02-06 12:05:36 +05:30
Sameer Kankute
24dda99bd7
Handle compaction block in the input request
2026-02-06 11:55:12 +05:30
Sameer Kankute
c03ba8394e
Add compaction block in provider spcific fields streaming+ non streaming
2026-02-06 11:54:47 +05:30
Sameer Kankute
039b37fac1
Add compaction type block in the output
2026-02-06 11:31:35 +05:30
yuneng-jiang
0cb79ace97
Fixing tests
2026-02-05 21:44:00 -08:00
yuneng-jiang
b3f0dccf56
enterprise build
2026-02-05 21:31:20 -08:00
yuneng-jiang
e39530d0e6
bump: version 0.1.30 → 0.1.31
2026-02-05 21:28:13 -08:00
yuneng-jiang
b60d94d655
addressing comments
2026-02-05 21:27:42 -08:00
yuneng-jiang
de70a1c273
Merge pull request #20554 from BerriAI/ui_build_yj_03
...
[Refactor] Rename admins to AdminPanel
2026-02-05 21:12:48 -08:00
yuneng-jiang
968b953f84
rename admins to AdminPanel
2026-02-05 21:11:26 -08:00
yuneng-jiang
3504f05a5c
Adding tests + update pyproject
2026-02-05 21:00:05 -08:00
yuneng-jiang
704fac56fe
reverting .29 deletion
2026-02-05 20:51:55 -08:00
