Commit graph

6 commits

Author SHA1 Message Date
mateo
fcbb02231b chore(backport): merge rc/1.105.0 and move supported_decisions_providers to litellm.decisions.call
The decision model guardrail backport (#45894) landed on the line after this branch
forked and imports supported_decisions_providers from litellm.decisions.main, which
#45846 replaces here. Match main by exposing it from litellm.decisions.call and point
the guardrail endpoint and its test at that module. schema.d.ts and the lazy OpenAPI
snapshot are regenerated on the merged tree

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-11 01:17:04 +00:00
yucheng-berri
495288a074
feat(guardrails): backport the decision model guardrail to rc/1.105.0 (#45663) (#45894)
Some checks are pending
LiteLLM Rust / rust-lint (push) Waiting to run
LiteLLM Rust / rust-test (push) Waiting to run
LiteLLM Rust / rust-wheel (push) Waiting to run
Cherry-pick of #45663 adapted to rc/1.105.0, which predates
litellm/decisions/call.py, GuardrailReadOnlyDetails.tsx, LiteLLMBaseModel,
@/lib/decisionModels and the TypeSafe Add Model provider.

- supported_decisions_providers() lists rc's DECISIONS_ENDPOINTS in
  litellm/decisions/main.py
- The read-only decision model section moves to
  decision_model/DecisionModelDetails.tsx, rendered by guardrail_info.tsx
- DecisionModelCheck extends LiteLLMPydanticObjectBase
- isDecisionMode is inlined and the TypeSafe garden card bundles typesafe.png
- The OpenAPI snapshot and schema.d.ts were regenerated on this branch
- Masked guardrail params are built with BaseLitellmParams.model_validate,
  which keeps rc's type-check budget with the two new typed fields

(cherry picked from commit 5f9dd38867)
2026-10-10 17:38:28 -07:00
devin-ai-integration[bot]
d131c43782
fix(guardrails): restore Azure guardrail get_user_prompt dispatch and allow logging (#44067)
* fix(guardrails): restore Azure guardrail get_user_prompt dispatch and allow logging

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): use transport-level doubles in Azure dispatch regression tests

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): add Azure dispatch audit matrix integration cells

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): restore global callback lists after Router reset in SDK cells

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(guardrails): make proxy restart cell independent of shutdown timing

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: yucheng <yucheng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-01 23:30:32 -07:00
PhimmStraiker
826b21aab6
fix(guardrails): straiker v3 routes sk_agt_ keys to v3 and fails closed on a missing verdict (#44011)
* fix(guardrails): straiker v3 routes sk_agt_ keys to v3 and stops reading a missing verdict as allow

An sk_agt_ key always calls /api/v3/detect, even when the guardrail was saved with
api_version 'v1' by the old shared default: the v1 webhook rejects that key with 401.
A 200 with no decision, or permissionDecision 'ask', now takes the failure policy
instead of allowing the request. A detect-mode action is still not a block.
A response-phase block is no longer remembered under the request, so asking the same
question again is scored instead of refused from memory. The replay memory is scoped
by principal and session together, so two principals on one session id never share a
block. A text-only /guardrails/apply_guardrail call relays the text as a user turn.
The agent_ref description now matches the code: the configured value wins.

* fix(guardrails): straiker v3 relays text beside an empty messages list and keys the memory on the key

/guardrails/apply_guardrail sends `messages: []` beside `text`; an empty list is no
conversation, so the text is relayed as the user turn. A verdict whose blocked_by is not
a list states no decision and takes the failure policy, the same way a missing decision
does. A key that names no user is still the caller, so the replay memory is keyed on the
key when no user is known.

* test(guardrails): build the straiker replay-scope request data without mutating it

---------

Co-authored-by: PhimmStraiker <PhimmStraiker@users.noreply.github.com>
2026-10-01 22:38:04 -07:00
devin-ai-integration[bot]
73072b8643
test(proxy): move management_endpoints, management_helpers and guardrails tests into tests/unit/proxy (#44003)
* test(proxy): move auth, hooks, policy_engine and client tests into tests/unit/proxy

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): stub HIBP through respx by disabling the aiohttp transport

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): share the httpx transport fixture across proxy unit tests

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): restore proxy globals without a missing-value sentinel

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): package moved dirs and stub the login breach check at the HTTP boundary

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): isolate the mcp server manager per test

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): move management_endpoints, management_helpers and guardrails tests into tests/unit/proxy

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): reuse the shared httpx transport fixture in moved proxy tests

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): stub outbound HTTP and package moved test dirs

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): restore the config server hostname in the mcp resolution test

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(proxy): pin the completion tokenizer model in the straiker screening test

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

---------

Co-authored-by: yuneng <yuneng@berri.ai>
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-01 10:52:03 -07:00
Itai Modiano
0c553f0398
feat(guardrails): send a configured gateway_name from noma_v2 to Noma (#43678)
* feat(guardrails): send a configured gateway_name from noma_v2 to Noma

The noma_v2 guardrail accepts a gateway_name param, falling back to the
NOMA_GATEWAY_NAME env var. The value is stripped, and when it is non-empty
it goes out as a top-level gateway_name field on /litellm/guardrail. The
param works for both guardrail: noma_v2 and guardrail: noma with use_v2,
and it is appended after the existing constructor params so positional
callers keep their meaning

* chore(ui): regenerate OpenAPI snapshot and dashboard types for gateway_name

The new noma_v2 gateway_name param shows up in the proxy OpenAPI spec, so
the lazy snapshot and the generated dashboard types need regenerating

* Update litellm/proxy/guardrails/guardrail_hooks/noma/noma_v2.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

---------

Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-09-29 10:20:40 -07:00