Commit graph

36177 commits

Author SHA1 Message Date
yuneng-jiang
10a3304e6a refactor: simplify onboarding page to use OnboardingForm component 2026-02-23 20:18:39 -08:00
Sameer Kankute
1696c094bc
Merge pull request #21975 from BerriAI/litellm_cicd_24_02
Fix content filter tests
2026-02-24 09:40:27 +05:30
Sameer Kankute
842d1cddf9 Fix content filter tests 2026-02-24 09:39:49 +05:30
Sameer Kankute
e486f8a408
Merge pull request #21972 from BerriAI/litellm_cicd_24_02
Litellm CICD fixes 02 24
2026-02-24 09:28:40 +05:30
Sameer Kankute
370dfdc514 bump: version 1.81.14 → 1.81.15 2026-02-24 09:26:18 +05:30
Sameer Kankute
3b2ff5b06a Fix cicd code quality 2026-02-24 09:22:40 +05:30
Sameer Kankute
8288e351ef Fix: test_sentence[dt_8] 2026-02-24 09:14:10 +05:30
Harshit28j
e5c907dc93 fix test case and req changes 2026-02-24 09:13:27 +05:30
Sameer Kankute
0beada96c1 Fix code qa 2026-02-24 09:09:23 +05:30
Sameer Kankute
d599c77311 Update poetry 2026-02-24 09:04:55 +05:30
Sameer Kankute
7df02e968a add package files 2026-02-24 09:01:57 +05:30
Sameer Kankute
8714b9ee8f bump: version 0.4.46 → 0.4.47 2026-02-24 08:53:50 +05:30
yuneng-jiang
32045217a6 refactor: simplify onboarding page to use OnboardingForm component
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-23 18:18:42 -08:00
yuneng-jiang
1f8d23ec5b fix: set cookie path and add error feedback on claim failure 2026-02-23 18:16:38 -08:00
yuneng-jiang
2bc6dc5cad fix: sync email field value into AntD Form after credentials load 2026-02-23 18:12:17 -08:00
yuneng-jiang
884904c6d1 feat: add OnboardingForm component with variant prop
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-23 18:08:31 -08:00
yuneng-jiang
ba0ed492c4 fix: improve type safety and defensive guard in useOnboarding hook
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-23 18:05:23 -08:00
yuneng-jiang
f4303f5e22 feat: add useOnboarding hook with query and mutation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-02-23 18:01:10 -08:00
yuneng-jiang
8f46a6917b
Merge pull request #21968 from BerriAI/litellm_ui_testing_coverage_00
[Infra] UI - Unit Testing Coverage: MCP Semantic Filter
2026-02-23 17:34:23 -08:00
yuneng-jiang
715e134a66 adding testing coverage + fixing flaky tests 2026-02-23 17:23:10 -08:00
yuneng-jiang
a8456a2a30
Merge pull request #21963 from BerriAI/litellm_queue_presets
[Fix] Spend Update Queue Aggregation Never Triggers with Default Presets
2026-02-23 17:21:33 -08:00
Lei Nie
eed2e4ee5f
fix(videos): pass api_key from litellm_params to video remix handlers (#21965)
video_remix_handler and async_video_remix_handler were not falling back
to litellm_params.api_key when the api_key parameter was None, causing
Authorization: Bearer None to be sent to the provider. This matches the
pattern already used by async_video_generation_handler.
2026-02-23 17:15:24 -08:00
yuneng-jiang
a749598693
Merge pull request #21859 from BerriAI/litellm_blog_dropdown
[Feature] UI - Blog Dropdown in Navbar
2026-02-23 16:22:22 -08:00
yuneng-jiang
a9c44d8530 adjust default aggregation threshold 2026-02-23 16:20:15 -08:00
yuneng-jiang
9f3fc492c2 adding tests 2026-02-23 16:02:36 -08:00
Alejandro Tapia
a1f5450b40 manualSorting fix. Filtering fetching fix 2026-02-23 16:01:04 -08:00
yuneng-jiang
09cc3b8bbc ui changes 2026-02-23 15:54:07 -08:00
Alejandro Tapia
bc99e38e55 Fix: accessToken not included in queryKey 2026-02-23 15:44:51 -08:00
Alejandro Tapia
f44c36f980 Fix Unbounded pagination 2026-02-23 15:43:04 -08:00
ryan-crabbe
3faf5e5912
Merge pull request #21961 from BerriAI/litellm_revert_duplicate_workflows
Revert duplicate issue checker to text-based matching
2026-02-23 15:30:02 -08:00
Ryan Crabbe
079ff24d78 Revert duplicate issue checker to text-based matching, remove duplicate PR workflow
Remove the Claude Code-powered duplicate PR detection workflow and revert
the duplicate issue checker back to wow-actions/potential-duplicates with
text similarity matching.
2026-02-23 15:28:13 -08:00
Alejandro Tapia
6d98622923 filters working properly for team virtual keys 2026-02-23 15:21:49 -08:00
yuneng-jiang
54b7e1af99 adjust blog post path 2026-02-23 15:12:05 -08:00
yuneng-jiang
08f4a27e32 Merge remote-tracking branch 'origin' into litellm_blog_dropdown 2026-02-23 15:02:07 -08:00
yuneng-jiang
94425dff1e fixing path 2026-02-23 15:01:49 -08:00
Alejandro Tapia
34d09a314c virtual-keys-team-table 2026-02-23 14:47:07 -08:00
Lei Nie
4ff2cfd8d6
feat(videos): add variant parameter to video content download (#21955)
openai videos models support the features to download variants.
See more details here: https://developers.openai.com/api/docs/guides/video-generation#use-image-references.
Plumb variant (e.g. "thumbnail", "spritesheet") through the full
video content download chain: avideo_content → video_content →
video_content_handler → transform_video_content_request. OpenAI
appends ?variant=<value> to the GET URL; other providers accept
the parameter in their signature but ignore it.
2026-02-23 14:45:19 -08:00
yuneng-jiang
1ecfbad46e adjust blog posts to fetch from github first 2026-02-23 14:45:05 -08:00
Julio Quinteros Pro
75d9f4d84f fix: use atomic increment-first pattern for model RPM rate limiting
Replace racy check-then-increment RPM logic with atomic increment-first
pattern to prevent concurrent requests from bypassing the rate limit.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-23 19:11:52 -03:00
ryan-crabbe
0ca9869b99
Merge pull request #21950 from ryan-crabbe/docs/v1-81-14-perf-section
docs: add performance & reliability section to v1.81.14 release notes
2026-02-23 13:13:21 -08:00
Julio Quinteros Pro
6574d8d395
Merge pull request #21937 from jquinter/fix/flaky-rpm-limit-test
fix(tests): make RPM limit test sequential to fix race condition
2026-02-23 17:27:58 -03:00
Arindam Majumder
71b4bd12a7
Add OpenAI Agents SDK tutorial with LiteLLM Proxy to docs (#21221)
* Add OpenAI Agents SDK tutorial to docs

* Update OpenAI Agents SDK tutorial to use LiteLLM environment variables

* Enhance OpenAI Agents SDK tutorial with built-in LiteLLM extension details and updated configuration steps. Adjust section headings for clarity and improve the flow of information regarding model setup and usage.
2026-02-23 12:10:01 -08:00
Ron Zhong
73fd5a41e4
feat: Singapore guardrail policies (PDPA + MAS AI Risk Management) (#21948)
* feat: Singapore PDPA PII protection guardrail policy template

Add Singapore Personal Data Protection Act (PDPA) guardrail support:

Regex patterns (patterns.json):
- sg_nric: NRIC/FIN detection ([STFGM] + 7 digits + checksum letter)
- sg_phone: Singapore phone numbers (+65/0065/65 prefix)
- sg_postal_code: 6-digit postal codes (contextual)
- passport_singapore: Passport numbers (E/K + 7 digits, contextual)
- sg_uen: Unique Entity Numbers (3 formats)
- sg_bank_account: Bank account numbers (dash format, contextual)

YAML policy templates (5 sub-guardrails):
- sg_pdpa_personal_identifiers: s.13 Consent
- sg_pdpa_sensitive_data: Advisory Guidelines
- sg_pdpa_do_not_call: Part IX DNC Registry
- sg_pdpa_data_transfer: s.26 overseas transfers
- sg_pdpa_profiling_automated_decisions: Model AI Governance Framework

Policy template entry in policy_templates.json with 9 guardrail definitions
(4 regex-based + 5 YAML conditional keyword matching).

Tests:
- test_sg_patterns.py: regex pattern unit tests
- test_sg_pdpa_guardrails.py: conditional keyword matching tests (100+ cases)

* feat: MAS AI Risk Management Guidelines guardrail policy template

Add Monetary Authority of Singapore (MAS) AI Risk Management Guidelines
guardrail support for financial institutions:

YAML policy templates (5 sub-guardrails):
- sg_mas_fairness_bias: Blocks discriminatory financial AI (credit/loans/insurance by protected attributes)
- sg_mas_transparency_explainability: Blocks opaque/unexplainable AI for consequential financial decisions
- sg_mas_human_oversight: Blocks fully automated financial decisions without human-in-the-loop
- sg_mas_data_governance: Blocks unauthorized sharing/mishandling of financial customer data
- sg_mas_model_security: Blocks adversarial attacks, model poisoning, inversion on financial AI

Policy template entry in policy_templates.json with 5 guardrail definitions.
Aligned with MAS FEAT Principles, Project MindForge, and NIST AI RMF.

Tests:
- test_sg_mas_ai_guardrails.py: conditional keyword matching tests (100+ cases)

* fix: address SG pattern review feedback

- Update NRIC lowercase test for IGNORECASE runtime behavior
- Add keyword context guard to sg_uen pattern to reduce false positives

* docs: clarify MAS AIRM timeline references

- Explicitly mark MAS AIRM as Nov 2025 consultation draft
- Add 2018 qualifier for FEAT principles in MAS policy descriptions
- Update MAS guardrail wording to avoid release-year ambiguity

* chore: commit resolved MAS policy conflicts

* test:

* chore:
2026-02-23 12:08:22 -08:00
Julio Quinteros Pro
bb63de2f82 fix(tests): make RPM limit test sequential to avoid race condition
Concurrent requests via run_in_executor + asyncio.gather caused a race
condition where more requests slipped through the rate limiter than
expected, leading to flaky test failures (e.g. 3 successes instead of 2
with rpm_limit=2).

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-23 16:34:52 -03:00
Julio Quinteros Pro
36813199b6
Merge pull request #21943 from jquinter/fix/interactions-incomplete-status
fix(tests): add INCOMPLETE to interactions status enum expected values
2026-02-23 16:31:41 -03:00
Ryan Crabbe
67ceade162 docs: add performance & reliability section to v1.81.14 release notes 2026-02-23 11:23:29 -08:00
Harshit28j
af9ad68a43 fix: presidio streaming, false positives 2026-02-24 00:42:29 +05:30
Krish Dholakia
4dfec4661b
Guardrail Monitor - measure guardrail reliability in prod (#21944)
* fix: fix log viewer for guardrail monitoring

* feat(ui/): fix rendering logs per guardrail

* fix: fix viewing logs on overview tab of guardrail

* fix: log viewer

* fix: fix naming to align with metric
2026-02-23 10:23:14 -08:00
Julio Quinteros Pro
f94d0fe0b6 fix: add INCOMPLETE status to Interactions API enum and test
Google added INCOMPLETE to the Interactions API OpenAPI spec status enum.
Update both the Status3 enum in the SDK types and the test's expected
values to match.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-23 15:07:41 -03:00
ryan-crabbe
c4c48fe977
Merge pull request #21942 from BerriAI/litellm_network_mock
feat: Litellm network mock
2026-02-23 10:07:11 -08:00