Diego Rodrigues de Sa e Souza e0c6fb9f8c fix(providers): use a reliable NVIDIA validation probe model (#3116) (#3223) ...

The NVIDIA key-validation chat probe used models[0] (z-ai/glm-5.1), which
requires the 'Public API Endpoints' account permission and has DEGRADED
windows. Accounts lacking that permission see the probe hang until the
validation timeout, surfacing as a misleading 'Upstream Error' on a valid key.
Probe the universally-available meta/llama-3.1-8b-instruct instead, still
overridable via providerSpecificData.validationModelId. + unit test.

2026-06-05 10:17:40 -03:00

..

benchmarks

Release v3.8.2 (#2503)

2026-05-23 01:46:59 -03:00

e2e

test: stabilize quota syncQuotaCombos shards + fix 2 e2e specs

2026-06-02 22:39:13 -03:00

fixtures

feat(plugins): plugin hook wiring + comprehensive test suite + welcome-banner example (#3045)

2026-06-01 16:20:11 -03:00

golden-set

feat(compression): expand caveman parity and MCP metadata compression

2026-05-03 09:14:20 -03:00

helpers

feat(auth): enforce dashboard sessions for management routes

2026-04-17 16:45:27 -03:00

integration

Release v3.8.10 (#3140)

2026-06-04 20:05:38 -03:00

live

fix(security): resolve CodeQL ReDoS + URL sanitization alerts

2026-05-17 07:43:32 -03:00

load

chore(release): v3.6.6 — Stabilization (#1241)

2026-04-16 05:26:17 -03:00

manual

Release v3.8.0 (#2073)

2026-05-10 00:55:06 -03:00

security

feat: OmniRoute v1.0.0 — Intelligent AI Gateway & Universal LLM Proxy

2026-02-18 00:02:15 -03:00

translator

chore: apply PR 1495 and update changelog

2026-04-21 21:12:29 -03:00

unit

fix(providers): use a reliable NVIDIA validation probe model (#3116) (#3223)

2026-06-05 10:17:40 -03:00

scratch_test.mjs

refactor: implement path utilities, add custom date formatting, improve type safety, and unify database imports

2026-04-21 21:10:48 -03:00