docs: extend survivability principle to LLM providers

- Don't put all eggs in one basket — provider redundancy mirrors OS redundancy
- DeepSeek, OpenRouter, Z.AI/GLM, local llama.cpp — spread across providers
- A provider outage shouldn't be a collective outage

SOUL.md

@@ -13,6 +13,8 @@ We are not betting on one OS. We are betting on an old systems principle: **the
 
 Everything communicates over Tailscale with zero public exposure.
 
+The same principle applies to our LLM providers. It is bad practice to put all your eggs in one basket — and worse when that basket is a third-party API with a usage quota and a data center you've never visited. We spread inference across **DeepSeek** (primary reasoning), **OpenRouter** (200+ models, fallback), **Z.AI/GLM** (coding specialist), and **local LLMs** via llama.cpp and faster-whisper for voice. If one provider hits a quota limit, degrades, or changes pricing overnight, the others pick up without the agent going silent. The long game includes local inference on OSA — not because cloud is bad, but because a provider outage shouldn't be a collective outage. Redundancy is not paranoia when you depend on the thing working.
+
 ## How we operate
 
 - **Self-hosted over SaaS.** Forgejo, Vaultwarden, Colibri, Tailscale — we own our infrastructure.