Commit graph

42415 commits

Author SHA1 Message Date
Ryan Crabbe
1533f6896e
fix(ui): fix imports and update placeholder for team multi select 2026-04-03 14:36:46 -07:00
Ryan Crabbe
cd7b2620c7
fix(ui): add paginated team search to usage page filter
Replace the static team dropdown on the usage page with a new
TeamMultiSelect component that uses the paginated v2/team/list
endpoint with debounced server-side search and infinite scroll.
2026-04-03 13:59:46 -07:00
ishaan-berri
fc885af994
docs(blog): add security hardening April 2026 post (#25101) (#25102) 2026-04-03 13:06:14 -07:00
Ryan Crabbe
1bb726aa7a
fix(ui): only send organization_id when changed and use raw initial value 2026-04-03 12:15:45 -07:00
Ryan Crabbe
5a8f910fe3
add: making organizations a select instead of read only badges 2026-04-03 11:54:52 -07:00
joereyna
6cc56f58fd
Fix broken codeql-action SHA in scorecard workflow 2026-04-03 11:36:02 -07:00
Ryan Crabbe
a287154905
fix(ui): migrate guardrails tabs to antd and fix internal user view
- Replace Tremor TabGroup with antd Tabs (key-based matching) to fix
  blank content when conditional tabs are hidden for non-admins
- Skip /guardrails/submissions fetch for non-admin users via
  useAuthorized() hook (avoids 401 error)
- Move get_team_membership to inline import in register endpoint
- Non-admins default to Submitted Guardrails tab with Add Guardrail
  button visible
2026-04-03 09:34:29 -07:00
mubashir1osmani
d4a3a5e530
fix gpt-5.4 pricing (#24748) 2026-04-02 21:51:21 -07:00
yuneng-jiang
50f4fdea3e
bump: version 1.83.0 → 1.83.1 (#25054) 2026-04-02 21:43:42 -07:00
michelligabriele
a6dfd02610
fix(guardrails): return HTTP 400 instead of 500 for Model Armor streaming blocks (#24693)
When Model Armor blocks a streaming response, it correctly raises
HTTPException(status_code=400) but create_response() catches it with a
bare except Exception and hardcodes a 500 response, discarding the
original status code.

Fix create_response() to preserve status_code from HTTPException instead
of hardcoding 500. Also update Model Armor's streaming hook to yield an
SSE error event instead of raising (matching the Prisma Airs pattern),
and fix make_model_armor_request() to return 400 for upstream API
failures instead of passing through the upstream status code.
2026-04-02 21:28:52 -07:00
Marty Sullivan
52a596d2a4
Bedrock Model Updates 2026-03-26 (#24645)
* add new bedrock models & remove duplicate vertexai entry

* adding non-regional entry for minimax-2.5
2026-04-02 21:26:04 -07:00
ishaan-berri
1e5b79d887
[Bedrock] Fix Anthropic file_id support - async path + document URL→base64 + beta header filtering (#25047) (#25050)
Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
2026-04-02 21:13:56 -07:00
Joe Reyna
ee3e848ded
allow hashed token_id in /key/update endpoint (#24969) 2026-04-02 21:13:33 -07:00
Ryan Crabbe
adb7454f85
fix: address review feedback on guardrail registration
- Make team_id optional again, fall back to API key's team_id
  (preserves backwards compatibility)
- Add PROXY_ADMIN bypass for team membership check
  (admins can register guardrails for any team)
- Move get_team_membership import to module level
- Prevent extra_litellm_params spread from overwriting controlled
  fields (guardrail, mode, api_base) by spreading extras first
2026-04-02 18:08:22 -07:00
Ryan Crabbe
0d602857af
feat: wire guardrail submission to backend and allow internal user access
Backend:
- Add required team_id to RegisterGuardrailRequest body
- Validate team membership before allowing submission

Frontend:
- Add useRegisterGuardrail React Query mutation hook
- Wire form onFinish to mutation, pass team_id from dropdown
- Remove admin-only restriction on guardrails nav item
- Internal users see only Test Playground + Submitted Guardrails tabs
- Admins continue to see all 4 tabs
2026-04-02 18:00:58 -07:00
yuneng-jiang
4094801b3c
Merge pull request #25037 from BerriAI/litellm_fix_non_root_docker_build
[Fix] Dockerfile.non_root: install node-gyp for npm ci
2026-04-02 17:52:27 -07:00
Ryan Crabbe
fe8cc100de
feat: wire submit guardrail form to POST /guardrails/register
Backend:
- Add required team_id to RegisterGuardrailRequest body
- Validate team membership before allowing submission

Frontend:
- Add useRegisterGuardrail React Query mutation hook
- Wire form onFinish to mutation, pass team_id from dropdown
- Show notification and refresh submissions on success
2026-04-02 17:51:17 -07:00
Yuneng Jiang
d4813a2a0f
adding poetry lock 2026-04-02 17:31:16 -07:00
Yuneng Jiang
fa629c307c
[Fix] Dockerfile.non_root: install node-gyp for npm ci
The wolfi-base npm@11.12.1 package does not bundle node-gyp, causing
`npm ci` to fail with `Cannot find module 'node-gyp/bin/node-gyp.js'`
when building the Admin UI in the non-root Docker image.

Install node-gyp@12.2.0 globally and symlink it into npm's internal
node_modules where @npmcli/run-script expects to find it.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-02 17:29:47 -07:00
Ryan Crabbe
7a27434f89
feat(ui): add submit guardrail form to Submitted Guardrails tab
Wire the placeholder "Add Guardrail" button to open an antd Modal+Form
with team selector, guardrail name, mode, API base URL, optional extra
litellm_params JSON, and optional guardrail_info JSON. Backend call is
stubbed with a TODO for now.
2026-04-02 17:21:54 -07:00
yuneng-jiang
3604b600d3
[Infra] Merge internal dev branch with main (#25036)
* fix(proxy): enforce key-level model allowlist for custom auth

custom_auth_run_common_checks only runs common_checks (team/user/project model checks).
Custom auth now also enforces key-level model restrictions via can_key_call_model.

Move the custom-auth key-access regression tests to test_user_api_key_auth.py and keep test_custom_auth_end_user_budget.py focused on end-user budget behavior.

Made-with: Cursor

* fix(proxy): gate custom-auth key model checks behind opt-in

Keep key-level model allowlist enforcement in custom auth behind `custom_auth_run_common_checks` to preserve backwards compatibility, and update tests to verify default non-enforcement and opt-in enforcement behavior.

Made-with: Cursor

* test(proxy): isolate custom auth default check from shared settings state

Patch `proxy_server.general_settings` to an empty dict in the default custom-auth key-access test so it remains deterministic under shared module state.

Made-with: Cursor

* test(proxy): strengthen custom auth post-check assertions

Tighten custom auth regression tests by asserting exact can_key_call_model args and remove an unused common_checks mock from the default behavior path.

Made-with: Cursor

* fix(agentcore): parse A2A JSON-RPC responses in AgentCore provider

* fix(prompt-templates): ensure_alternating_roles handles tool-call chains

* feat(auth): add JWT claim routing overrides for OAuth2 validation

Made-with: Cursor

* docs(auth): document JWT-to-OAuth2 routing overrides

Add generic docs for running JWT and OAuth2 together, including routing_overrides YAML examples and list-based selector behavior for iss/client_id/aud.

Made-with: Cursor

---------

Co-authored-by: Milan <milan@berri.ai>
Co-authored-by: michelligabriele <gabriele.michelli@icloud.com>
2026-04-02 16:38:01 -07:00
shin-berri
f11cdf7934
Merge pull request #25034 from BerriAI/extras_apr2
[Infra] Bump extras version
2026-04-02 16:18:10 -07:00
Ryan Crabbe
f0bd33486e
fix: lazy import get_access_object to break cyclic import + short-circuit all-proxy-models display
- Remove get_access_object from module-level import in team_endpoints.py
  and use a lazy _get_access_object wrapper to avoid cyclic dependency
- Add _prisma_client is None early-exit guard in _resolve_access_group_resources
- Short-circuit UI to show "All Proxy Models" when team.models is empty
  or contains "all-proxy-models", skipping access group model resolution
2026-04-02 16:14:34 -07:00
Yuneng Jiang
3ad953e75c
bump: version 0.4.62 → 0.4.63 2026-04-02 16:10:32 -07:00
Ryan Crabbe
c19a63e2bf
docs: clarify that models sub-field only applies to SSO auto-created teams 2026-04-02 16:00:20 -07:00
David Chen
b7ccc5b691
[Test Fix] fix gov pricing tests (#25022)
* fix pricing tests

* fix mypy

* fix cost expectation since us based model is used now.

* fix test get model info
2026-04-02 15:55:55 -07:00
Ryan Crabbe
59b09102b9
docs: add default_team_params to config reference and update examples
- Add default_team_params to litellm_settings reference table in
  config_settings.md with all sub-fields documented
- Update self_serve.md and msft_sso.md examples to include
  team_member_permissions, tpm_limit, and rpm_limit
- Fix misleading comment that implied default_team_params only applies
  to SSO auto-created teams — it applies to all /team/new calls
2026-04-02 15:51:28 -07:00
Krrish Dholakia
06df8edf92
docs: cleanup (#25026) 2026-04-02 15:18:24 -07:00
Ryan Crabbe
bbe708b093
perf(teams): single-pass access group resolution + asyncio.gather in list endpoint
- Fetch each access group object once and extract all 3 resource fields
  in a single pass instead of 3 separate calls (3N → N lookups)
- Use asyncio.gather to resolve access groups across teams concurrently
  in list_team_v2 instead of sequential awaits
- Add 5 unit tests for _resolve_access_group_resources
2026-04-02 14:52:32 -07:00
yuneng-jiang
9c5fda435f
Merge pull request #25023 from BerriAI/litellm_/fervent-noether
[Infra] Harden supply chain: remove unused scripts, add pip binary-only install
2026-04-02 14:49:09 -07:00
Yuneng Jiang
51af6fedb3
[Infra] Harden supply chain: remove unused scripts, add pip binary-only install
Remove ci_cd/publish-proxy-extras.sh (dead, unreferenced PyPI publish script)
and .pre-commit-config.yaml (pulls external repos from GitHub on git commit).
Add --only-binary :all: to scripts/install.sh to prevent execution of
malicious setup.py during pip install.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-02 14:13:57 -07:00
Krrish Dholakia
cae8613660
Announce April Townhall (#25021)
* fix: replace hardcoded url

* docs: announce april townhall
2026-04-02 14:10:49 -07:00
yuneng-jiang
068e6e2a9e
Merge pull request #24951 from BerriAI/litellm_remove_neon_cli
[Fix] Remove Neon CLI and Pin All JS Dependencies
2026-04-02 12:47:46 -07:00
Ryan Crabbe
f62658795a
feat(teams): resolve access group models/MCPs/agents in team endpoints
Add access_group_models, access_group_mcp_server_ids, and
access_group_agent_ids to /team/info and /v2/team/list responses.
These fields contain resources inherited from access groups, kept
separate from direct assignments so the UI can distinguish the source.

Backend: _resolve_access_group_resources() helper resolves access
group resources via existing _get_*_from_access_groups() functions.

UI: Teams table and detail view show direct models as blue badges
and access-group-sourced models as green badges.
2026-04-02 12:25:48 -07:00
Sameer Kankute
ec004a54e9
feat(vertex_ai): propagate metadata labels to embedding, Imagen, rerank
- Add pop_vertex_request_labels / vertex_request_labels_from_litellm_params in common_utils
- Vertex embeddings: pass litellm_params, set predict body labels; Gemini uses shared helper
- Imagen: top-level labels from metadata; rerank: userLabels for Discovery Engine Rank API
- Thread litellm_params through rerank handler and all BaseRerankConfig implementations

Made-with: Cursor
2026-04-02 09:56:56 +05:30
David Chen
d1df4e838b
Litellm fix update bedrock models (#24947)
* update bedrock models in tests

* updated more tests and model_prices_and_context_window

* fix model id and pricing

* replace more sonnet models

* update tests

* git push

* update pricing

* flaky total cost

* monkey patch

* relax the cost change

* fix and revert some changes

* revert the pricing

* chore: move cost/pricing changes to bedrock-cost-fixes branch

* chore: split Bedrock file-api beta stripping to separate branch

Removes strip_unsupported_file_api_betas_for_bedrock_invoke from this branch;
see litellm_bedrock_invoke_strip_file_api_betas for that fix.

Made-with: Cursor
2026-04-01 19:22:54 -07:00
michelligabriele
adedae2cfa
fix(auth): enforce budget for models not in cost map (#24949)
* fix(auth): enforce budget for models not in cost map

* fix log injection in debug messages + isolate test global state
2026-04-01 19:10:30 -07:00
Yuneng Jiang
006d481025
[Fix] Remove neon CLI dependency and pin all JS dependencies
Remove @neondatabase/api-client and neonctl to address CVE-2026-25639
(axios supply chain vulnerability). Pin all JS dependencies to exact
versions across all package.json files to prevent future supply chain
attacks via semver range resolution.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 16:15:32 -07:00
yuneng-jiang
7250cba3db
Merge pull request #24905 from BerriAI/litellm_pin_pip_2
[Infra] Pin All Docker Build Dependencies
2026-04-01 15:05:25 -07:00
Yuneng Jiang
d038093562
add poetry lock 2026-04-01 14:28:15 -07:00
Yuneng Jiang
0fb5ab515d
[Fix] Revert cryptography to 43.0.3 in pyproject.toml for Python 3.9.0/3.9.1 compat
cryptography 46.0.5 excludes Python 3.9.0 and 3.9.1, which conflicts
with pyproject.toml's python = ">=3.9,<4.0" range. Docker still uses
46.0.5 via requirements.txt.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 14:27:51 -07:00
Yuneng Jiang
85f72c9d24
[Fix] Remove unused aioboto3 dependency and botocore conflict workarounds
aioboto3 was listed as a dependency for async sagemaker calls but is not
imported anywhere in the codebase — async calls use httpx + botocore SigV4
instead. Removing it eliminates the unresolvable botocore version conflict
between boto3 and aiobotocore, along with all grep -v / --no-deps workarounds
across Dockerfiles and CI.

Also addresses Greptile review feedback: collapse redundant grpcio
python-version markers, bump pyproject.toml cryptography to 46.0.5 to
match Docker (GHSA-r6ph-v2qm-q3c2), and fix misleading .npmrc comment.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 14:25:44 -07:00
Yuneng Jiang
9c6d5f2b60
[Fix] Add aioitertools and wrapt to authorized licenses
Both are transitive deps of aiobotocore, added to requirements.txt in
the previous commit. aioitertools is MIT, wrapt is BSD.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 13:01:10 -07:00
Yuneng Jiang
821a634d25
[Fix] Handle boto3/aioboto3 botocore conflict across CI and Docker builds
boto3==1.42.80 and aioboto3==15.5.0 have incompatible botocore version
ranges. No aioboto3 release supports botocore 1.42.x yet. Both uv and
pip 26.0.1 reject the resolution.

Fix: filter aioboto3 out of requirements.txt at install time, then
install aioboto3+aiobotocore with --no-deps to bypass resolution.
Added wrapt and aioitertools to requirements.txt as pinned transitive
deps of aiobotocore (skipped by --no-deps). Fixed pip stdin handling
(/dev/stdin). Applied to all 5 Dockerfiles and all CircleCI install
paths.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 12:27:21 -07:00
Yuneng Jiang
fc8eb81549
[Fix] Filter aioboto3 from resolver to fix boto3/aioboto3 conflict
boto3==1.42.80 and aioboto3==15.5.0 have incompatible botocore ranges.
Both uv and pip 26.0.1 reject the resolution. Fix: filter aioboto3 out
of requirements.txt at install time, then install aioboto3+aiobotocore
separately with --no-deps to bypass resolution. Removes uv-overrides.txt
which only partially addressed the conflict.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 11:57:07 -07:00
Yuneng Jiang
b7849bff56
[Fix] Add boto3 override alongside botocore in uv-overrides.txt
aiobotocore[boto3] pins both boto3<1.40.62 and botocore<1.40.62.
The previous commit only overrode botocore. Added boto3 override too.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 11:49:25 -07:00
Yuneng Jiang
467abd1909
[Fix] Add uv override for boto3/aioboto3 botocore conflict
boto3==1.42.80 requires botocore>=1.42.80 but aioboto3==15.5.0 (via
aiobotocore==2.25.1) requires botocore<1.40.62. No aioboto3 release
supports botocore 1.42.x yet. pip's lenient resolver handles this for
Docker builds, but uv's strict resolver rejects it in CI. Added
uv-overrides.txt to force botocore to match boto3 during uv installs.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 11:34:19 -07:00
Yuneng Jiang
43077af378
[Fix] Sync CircleCI dependency pins with requirements.txt
CircleCI had stale version pins (e.g. boto3==1.36.0, aioboto3==13.4.0) that
conflict with requirements.txt (boto3==1.42.80, aioboto3==15.5.0), causing
uv resolution failures. Updated all mismatched pins across config.yml and
.circleci/requirements.txt to match requirements.txt as the source of truth.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-01 11:27:44 -07:00
ishaan-berri
e4442a4d98
test fix us.anthropic.claude-haiku-4-5-20251001-v1:0 (#24931)
* test fix us.anthropic.claude-haiku-4-5-20251001-v1:0

* ignore mypy cache files

---------

Co-authored-by: Ishaan Jaffer <ishaanjaffer0324@gmail.com>
Co-authored-by: David Chen <clfhhc@gmail.com>
2026-04-01 11:01:03 -07:00
David Chen
c987bdba84
fix lint problem (#24932) 2026-04-01 10:24:37 -07:00