Plugin

Provider Google Gemini multi-account: sceglie l'account con la quota residua maggiore, esegue failover su 429 con cooldown esponenziale, verifica gli account disabilitati in background e fornisce una pagina impostazioni cinese/inglese.

Catene fallback dichiarative provider/model per il picker: catena root ordinata e pool nominati, cambio per codice errore, cooldown per model, preset per fascia oraria e routing per ruolo subagent. Fork di omdsh-dev/dsh-llm-fallbacks 0.6.5; non installarli insieme perché condividono il profile row id “llm-fallbacks”.

Merges your configured, runtime-registered and locally cached models into one panel, probes and minimal-request tests them, pulls each channel's upstream /v1/models catalog, and chains the keepers into named schemes. A virtual ModelPool provider fails over at request time with per-model cooldowns, exponential backoff, image-request avoidance for text-only models, and a 10-minute memory for rejected reasoning levels. Adds a token ledger by day and model with CSV export, and 21 regression probes. Not a fork of dsh-llm-fallbacks.