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-ai-review.yml

@@ -7,14 +7,11 @@
 #       secrets: inherit
 #
 # Voraussetzungen: globaler Runner `eulernest`, anon-Clone für public Repos.
-# Ohne ANTHROPIC_API_KEY überspringt das Skript den KI-Schritt sauber (Job grün).
+# KI-Backend = Jetson-Ollama (self-hosted, LAN-direkt). Kein Secret nötig.
 name: ci-ai · review (reusable)
 
 on:
-  workflow_call:
-    secrets:
-      ANTHROPIC_API_KEY:
-        required: false
+  workflow_call: {}
 
 jobs:
   review:
@@ -31,9 +28,9 @@ jobs:
 
       - name: KI-Review (überspringt sauber ohne Key)
         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
         run: python /opt/ci-ai/scripts/ai_review.py