Diego Rodrigues de Sa e Souza 0ecc380928 feat(sse): add nvidia NIM local RPM budget + concurrency cap (#6846) (#7726) ...

Phase 1 of client-side quota tracking for NVIDIA NIM (no rate-limit
headers, no usage API):

- Register nvidia in PROVIDER_DEFAULT_RATE_LIMITS (40 RPM sliding
  window, matching the documented free-tier note), operator-overridable
  via a new ResilienceSettings.providerQuotaOverrides map.
- Per-connection concurrency cap (default 6) via a new
  nvidiaConcurrencyGate leaf module wrapping rateLimitSemaphore,
  wired into DefaultExecutor.execute().
- Per-model 429 lockout: confirmed already satisfied by #6773's
  passthroughModels flag on the nvidia registry entry (no new code
  needed) — added as a regression-guard test instead.

Phase 2 (AIMD adaptive ceiling learning) and Phase 3 (dashboard quota
card + combo-routing headroom preference) are explicitly deferred to
follow-up issues, per the plan's own scope note.

2026-07-19 14:37:18 -03:00

..

_setup

fix(test): skip real DNS writes in MITM dynamic-import test (#7398)

2026-07-18 21:18:49 -03:00

benchmarks

Release v3.8.2 (#2503)

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

boundary

Release v3.8.47 (#6569)

2026-07-13 09:12:40 -03:00

e2e

Release v3.8.43 (#5609)

2026-07-02 10:47:13 -03:00

fixtures

fix(router-eval): retained-optimization gate cleanup (#7318)

2026-07-18 15:13:39 -03:00

golden-set

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

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

helpers

Fase 8 · Bloco B — suíte de correção (property + golden + SSE-correctness) (#3808)

2026-06-14 18:02:51 -03:00

homolog

feat(homolog): real-environment E2E homologation suite (npm run homolog) (#7133)

2026-07-14 16:24:11 -03:00

integration

Add reasoning-based model and effort routing (#7607)

2026-07-18 22:09:47 -03:00

live

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

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

llm-security

Fase 8 · Bloco D — injection-guard em todas as rotas LLM + red-team (#3857)

2026-06-14 18:02:18 -03:00

load

Release v3.8.45 (#6202)

2026-07-06 02:25:17 -03:00

manual

Release v3.8.47 (#6569)

2026-07-13 09:12:40 -03:00

security

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

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

snapshots

fix(providers): correct Chutes registry baseUrl (#7621) (#7708)

2026-07-19 02:31:12 -03:00

translator

chore: apply PR 1495 and update changelog

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

unit

feat(sse): add nvidia NIM local RPM budget + concurrency cap (#6846) (#7726)

2026-07-19 14:37:18 -03:00

_cp_mock_hook.mts

fix(test): skip real DNS writes in MITM dynamic-import test (#7398)

2026-07-18 21:18:49 -03:00

_cp_mock_module.mts

fix(test): skip real DNS writes in MITM dynamic-import test (#7398)

2026-07-18 21:18:49 -03:00

_run_dns_guard_test.sh

fix(test): skip real DNS writes in MITM dynamic-import test (#7398)

2026-07-18 21:18:49 -03:00

e2e-tool-calls.sh

Release v3.8.24 (#3747)

2026-06-13 17:27:40 -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

theoldllm-stress.test.ts

Honor provider proxies for The Old LLM Vercel blocks (#7380)

2026-07-18 15:13:13 -03:00