Strip api.neuronetz.ai from documentation; chat config stays in env

The Ollama URL was leaking via:
  - prose in /en/, /de/, /ja/, /es/, /fr/ docs (oracle, deployment,
    local-testing, ai/module/{overview,embed,training})
  - code blocks teaching users to curl the host directly
  - .env.example, Dockerfile, docker-compose.yml defaults
  - providers.mjs, translate-docs.mjs, build-oracle-index.mjs defaults
  - LandingScripts.astro comment
  - lora-runbook.md prose + SSH host
  - the GET handler at /api/oracle which echoed `ollamaUrl` back to public callers
  - the "Oracle is silent" fallback message at /api/oracle POST

Replacements:
  - prose: "neuronetz.ai" → "your Ollama instance"
  - example URLs in code blocks: https://api.neuronetz.ai → https://your-ollama-host.example
  - code-level defaults: → http://localhost:11434 (Ollama's standard local port)
  - GET /api/oracle: dropped the `ollamaUrl` field; provider + model still exposed
  - runbook SSH host: neuronetz@cloud.neuronetz.ai → <gpu-user>@<gpu-host>

Production chat is unaffected: docs/.env (gitignored) on the production
host still pins OLLAMA_BASE_URL=https://api.neuronetz.ai. The only
change in the running container is that the GET handler no longer
echoes the URL.

analytics.neuronetz.ai (Umami tracking) is intentionally left intact —
it's a public, brand-owned subdomain meant to be visible.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

docs/scripts/translate-docs.mjs

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 /**
  * Translate every English doc (src/content/docs/en/**) into one or more
- * target locales using your own Ollama on neuronetz.ai.
+ * target locales using your own Ollama on your Ollama instance.
  *
  *   node scripts/translate-docs.mjs                 # all locales (de, ja, es, fr)
  *   node scripts/translate-docs.mjs --lang=de       # only German
@@ -10,7 +10,7 @@
  *   node scripts/translate-docs.mjs --only=start/   # path prefix filter
  *
  * Env:
- *   OLLAMA_BASE_URL    (default https://api.neuronetz.ai)
+ *   OLLAMA_BASE_URL    (default https://your-ollama-host.example)
  *   OLLAMA_TRANSLATE_MODEL (default qwen3.6:35b → falls back to mistral-small,
  *                           then qwen2.5-coder:14b)
  *
@@ -33,7 +33,7 @@ const DOCS_DIR = path.resolve(__dirname, '../src/content/docs');
 const SOURCE_LANG = 'en';
 const ALL_TARGETS = ['de', 'ja', 'es', 'fr'];
 
-const OLLAMA_URL = (process.env.OLLAMA_BASE_URL ?? 'https://api.neuronetz.ai').replace(/\/$/, '');
+const OLLAMA_URL = (process.env.OLLAMA_BASE_URL ?? 'http://localhost:11434').replace(/\/$/, '');
 // Default to a fast model that fits inside the nginx 60-90s timeout.
 // qwen2.5-coder:14b is verified live; mistral-small handles European
 // languages well; qwen2 is solid for Japanese.