feat: self-hosted LLM backend — point all workflows at the Jetson (Ollama, model=coder)

The Jetson Orin Nano (JetPack 7.2, Ollama on GPU) is live, so ci-ai runs fully
self-hosted: no Anthropic key, no cloud, no per-PR cost. AI_PROVIDER=ollama,
AI_BASE_URL=http://192.168.178.103:11434/v1. The Pi runner reaches it LAN-direct
(SNAT to .48, allowed by the Jetson UFW). Removed the dead ANTHROPIC_API_KEY
secret declarations.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

.gitea/workflows/reusable-commands.yml

@@ -11,10 +11,7 @@
 name: ci-ai · commands (reusable)
 
 on:
-  workflow_call:
-    secrets:
-      ANTHROPIC_API_KEY:
-        required: false
+  workflow_call: {}
 
 jobs:
   command:
@@ -23,9 +20,9 @@ jobs:
       image: python:3.12-slim
       options: "--memory=512m --memory-swap=768m"
     env:
-      AI_PROVIDER: anthropic
-      AI_MODEL: claude-3-5-haiku-latest
-      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
+      AI_PROVIDER: ollama
+      AI_MODEL: coder
+      AI_BASE_URL: http://192.168.178.103:11434/v1
       GITEA_TOKEN: ${{ github.token }}
       GITEA_API: https://git.eulernest.eu/api/v1
     steps: