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

..

antigravity

fix(antigravity): streaming passthrough for non-streaming clients (#7408)

2026-07-18 21:19:20 -03:00

base

feat(kimi): sync Code, Web, and Moonshot providers (#7531)

2026-07-18 21:19:42 -03:00

chatgpt-web

Release v3.8.47 (#6569)

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

claude-web

Release v3.8.47 (#6569)

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

codex

fix(codex): strip regex lookaround from tool schema patterns (#7100)

2026-07-16 14:13:03 -03:00

cursor

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

deepseek-web

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

default

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

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

duckduckgo-web

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

grok-web

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

huggingchat

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

kiro

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

lmarena

Release v3.8.47 (#6569)

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

muse-spark-web

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

perplexity-web

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

adapta-web.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00

antigravity.ts

fix(antigravity): streaming passthrough for non-streaming clients (#7408)

2026-07-18 21:19:20 -03:00

antigravityUpstreamError.ts

fix(antigravity): alias agy gemini-3.1-pro -high/-low + stop masking upstream 4xx (#3229) (#3245)

2026-06-05 14:20:05 -03:00

auggie.ts

fix(auggie): update model registry to match v0.32.0 CLI model IDs (#7032)

2026-07-18 11:33:57 -03:00

awsPollyTts.ts

feat: add EdgeTTS audio-tts provider (#6668) (#7605)

2026-07-17 11:32:25 -03:00

azure-openai.ts

Release v3.8.38 (#5078)

2026-06-27 09:07:12 -03:00

base.ts

feat(resilience): guard OmniRoute peer routing loops (#7555)

2026-07-18 21:19:50 -03:00

bedrock.ts

Release v3.8.27 (#3968)

2026-06-17 02:43:21 -03:00

blackbox-web.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00

chatgpt-web.ts

fix(chatgpt-web): recognize update_content.messages[] celsius WS frames (#7357) (#7578)

2026-07-17 06:12:15 -03:00

chatgptWebErrors.ts

Release v3.8.28 (#4053)

2026-06-17 19:26:32 -03:00

chatgptWebTools.ts

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

chipotle.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00

claude-web-with-auto-refresh.ts

feat(claude-web): implement session-based executor with auto-refresh (#2283)

2026-05-15 12:51:07 -03:00

claude-web.ts

fix(claude-web): unify Turnstile/executor/fast-path User-Agents behind one fingerprint (#7548) (#7711)

2026-07-19 02:31:26 -03:00

claudeIdentity.ts

Release v3.8.47 (#6569)

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

cliproxyapi.ts

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

cloudflare-ai.ts

Release v3.8.47 (#6569)

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

codebuddy-cn.ts

Release v3.8.38 (#5078)

2026-06-27 09:07:12 -03:00

codex.ts

fix(executors): disable parallel tools for Codex Responses Lite (#7171)

2026-07-18 21:18:06 -03:00

commandCode.ts

Release v3.8.47 (#6569)

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

copilot-m365-connection.ts

Release v3.8.46

2026-07-07 13:14:06 -03:00

copilot-m365-frames.ts

Release v3.8.45 (#6202)

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

copilot-m365-web.ts

Release v3.8.46

2026-07-07 13:14:06 -03:00

copilot-web.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00

cursor.ts

Release v3.8.47 (#6569)

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

deepseek-web-done-terminator.ts

Release v3.8.47 (#6569)

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

deepseek-web-with-auto-refresh.ts

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

deepseek-web.ts

Release v3.8.47 (#6569)

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

default.ts

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

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

devin-cli.ts

feat(oauth): complete Windsurf / Devin CLI OAuth + API-token flows (#2168)

2026-05-11 21:49:32 -03:00

doubao-web.ts

Release v3.8.46

2026-07-07 13:14:06 -03:00

duckduckgo-web.ts

fix: DDG circuit breaker (#6999) + null content validation (#7000) (#7001)

2026-07-18 15:17:57 -03:00

edgeTts.ts

feat: add EdgeTTS audio-tts provider (#6668) (#7605)

2026-07-17 11:32:25 -03:00

felo-web.ts

feat(providers): add Felo chat-aggregator provider (#6666) (#7599)

2026-07-17 11:31:54 -03:00

firecrawl-fetch.ts

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

forceResponsesUpstream.ts

Release v3.8.43 (#5609)

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

gemini-business.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00

gemini-web.ts

fix(sse): persist rotated Gemini web-session cookies via onCredentialsRefreshed (#7676) (#7751)

2026-07-19 09:39:02 -03:00

github.ts

feat(sse): route GitHub Copilot Claude models through native /v1/messages (#7223)

2026-07-17 10:40:09 -03:00

gitlab.ts

Release v3.8.46

2026-07-07 13:14:06 -03:00

gitlabResponses.ts

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

glm.ts

fix(sse): clamp glm-4.6v max_tokens to the 32768 ceiling (#7364) (#7585)

2026-07-17 06:55:41 -03:00

grok-cli.ts

fix(sse): proactively refresh Grok Build OAuth token before dispatch (#7610) (#7715)

2026-07-19 02:34:49 -03:00

grok-web.ts

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

gtts.ts

feat(providers): Speechmatics STT, gTTS, VibeProxy preset (#6659, #6667, #6874) (#7655)

2026-07-18 03:16:58 -03:00

huggingchat.ts

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

index.ts

feat(kimi): sync Code, Web, and Moonshot providers (#7531)

2026-07-18 21:19:42 -03:00

inner-ai.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00

jina-reader-fetch.ts

Release v3.8.3 (#2617)

2026-05-24 18:05:58 -03:00

kie.ts

fix: address kie provider review feedback

2026-05-07 00:01:54 +07:00

kimi-web.ts

feat(kimi): sync Code, Web, and Moonshot providers (#7531)

2026-07-18 21:19:42 -03:00

kimi.ts

feat(kimi): sync Code, Web, and Moonshot providers (#7531)

2026-07-18 21:19:42 -03:00

kiro.ts

Release v3.8.47 (#6569)

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

kiroThinking.ts

Release v3.8.38 (#5078)

2026-06-27 09:07:12 -03:00

lmarena.ts

Release v3.8.47 (#6569)

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

microsoft-designer-web.ts

feat: add Microsoft Designer as image provider (#6672) (#7609)

2026-07-17 12:09:12 -03:00

mimocode.ts

fix: preserve relayAuth for pool-referenced relay proxies (#5716) (#7182)

2026-07-14 21:13:45 -03:00

moonshot.ts

feat(kimi): sync Code, Web, and Moonshot providers (#7531)

2026-07-18 21:19:42 -03:00

muse-spark-web.ts

Release v3.8.47 (#6569)

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

ninerouter.ts

Release v3.8.4 (#2678)

2026-05-26 23:51:47 -03:00

nlpcloud.ts

feat(providers): add GitLab Duo, NLP Cloud, and enterprise gateways

2026-04-24 07:00:21 -03:00

notion-web.ts

feat(providers): notion-web live model discovery via getAvailableModels (#7696)

2026-07-19 04:26:26 -03:00

opencode.ts

feat(6922): effort-tier aliases for glm-5.2 & mimo-v2.5 on opencode-go (#6987)

2026-07-18 15:14:37 -03:00

perplexity-web.ts

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

poe-web.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00

pollinations.ts

Release v3.8.36 (#4854)

2026-06-25 13:17:40 -03:00

puter.ts

feat(providers): adicionar provedor Puter AI com 500+ modelos

2026-03-22 20:29:06 -03:00

qoder.ts

Release v3.8.44 (#5925)

2026-07-04 13:00:30 -03:00

qwen-web.ts

Release v3.8.47 (#6569)

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

t3-chat-web.ts

Release v3.8.43 (#5609)

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

tavily-fetch.ts

Release v3.8.3 (#2617)

2026-05-24 18:05:58 -03:00

theoldllm.ts

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

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

tinyfish-fetch.ts

Release v3.8.46

2026-07-07 13:14:06 -03:00

trae.ts

Release v3.8.47 (#6569)

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

v0-vercel-web.ts

Release v3.8.47 (#6569)

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

venice-web.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00

veoaifree-web.ts

Release v3.8.40

2026-06-29 08:40:06 -03:00

vertex.ts

Release v3.8.26 (#3875)

2026-06-16 01:00:40 -03:00

vertexMedia.ts

Release v3.8.26 (#3875)

2026-06-16 01:00:40 -03:00

windsurf.ts

Release v3.8.4 (#2678)

2026-05-26 23:51:47 -03:00

xai.ts

feat(providers): add xAI OAuth PKCE provider (#7399)

2026-07-18 21:18:53 -03:00

yuanbao-web.ts

fix(tests+providers): env-dependent tests exposed by GH-hosted runners (#6634 selfref shallow checkout + yuanbao live-network 401) (#7174)

2026-07-14 15:40:09 -03:00

zai-web.ts

Release v3.8.47 (#6569)

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

zed-hosted.ts

Release v3.8.46

2026-07-07 13:14:06 -03:00

zenmux-free.ts

Release v3.8.38 (#5078)

2026-06-27 09:07:12 -03:00