docs: add registry dockge and dashboard operations

README.md

@@ -97,13 +97,105 @@ The dashboard opens automatically at `http://localhost:3117` and immediately beg
 ### Docker
 
 ```bash
-git clone https://github.com/calesthio/Crucix.git
-cd Crucix
-cp .env.example .env    # add your API keys
-docker compose up -d
+docker pull git.wilkensxl.de/mrsphay/intelligence-terminal:latest
 ```
 
-Dashboard at `http://localhost:3117`. Sweep data persists in `./runs/` via volume mount. Includes a health check endpoint.
+Dashboard at `http://localhost:3117`. Sweep data persists in `./runs/` via volume mount. The container disables browser auto-open by default, exposes `/api/health` and `/api/metrics`, and is suitable for Dockge/Pangolin.
+
+#### Dockge / Pangolin Compose
+
+```yaml
+services:
+  intelligence-terminal:
+    image: git.wilkensxl.de/mrsphay/intelligence-terminal:latest
+    container_name: intelligence-terminal
+    env_file:
+      - path: .env
+        required: false
+    environment:
+      PORT: ${PORT:-3117}
+      AUTO_OPEN_BROWSER: "false"
+    ports:
+      - "${PORT:-3117}:${PORT:-3117}"
+    volumes:
+      - ./runs:/app/runs
+    restart: unless-stopped
+    healthcheck:
+      test: ["CMD", "node", "-e", "fetch('http://127.0.0.1:'+(process.env.PORT||3117)+'/api/health').then(r=>{if(![200,503].includes(r.status))process.exit(1);return r.json()}).then(j=>{if(j.status==='error')process.exit(1)}).catch(()=>process.exit(1))"]
+      interval: 60s
+      timeout: 10s
+      start_period: 45s
+      retries: 3
+```
+
+#### Required `.env` Example
+
+```env
+PORT=3117
+REFRESH_INTERVAL_MINUTES=15
+AUTO_OPEN_BROWSER=false
+STALE_DATA_MAX_AGE_MINUTES=60
+SWEEP_TOKEN=
+BRIEF_VERBOSITY=standard
+
+LLM_PROVIDER=openrouter
+LLM_BASE_URL=https://openrouter.ai/api/v1
+LLM_API_KEY=
+LLM_MODEL=openrouter/free
+LLM_TEMPERATURE=0.2
+LLM_MAX_TOKENS=2000
+LLM_TIMEOUT_MS=90000
+OPENROUTER_SITE_URL=https://git.wilkensxl.de/MrSphay/intelligence-terminal
+OPENROUTER_APP_NAME=Intelligence Terminal
+
+FRED_API_KEY=
+FIRMS_MAP_KEY=
+EIA_API_KEY=
+AISSTREAM_API_KEY=
+ACLED_EMAIL=
+ACLED_PASSWORD=
+CLOUDFLARE_API_TOKEN=
+BLS_API_KEY=
+
+TELEGRAM_BOT_TOKEN=
+TELEGRAM_CHAT_ID=
+DISCORD_BOT_TOKEN=
+DISCORD_CHANNEL_ID=
+DISCORD_GUILD_ID=
+DISCORD_WEBHOOK_URL=
+```
+
+Local LLM examples:
+
+```env
+# LM Studio
+LLM_PROVIDER=lmstudio
+LLM_BASE_URL=http://host.docker.internal:1234/v1
+LLM_MODEL=local-model
+
+# Ollama
+LLM_PROVIDER=ollama
+LLM_BASE_URL=http://host.docker.internal:11434
+LLM_MODEL=llama3.1:8b
+
+# Generic OpenAI-compatible endpoint
+LLM_PROVIDER=openai-compatible
+LLM_BASE_URL=http://host.docker.internal:8000/v1
+LLM_API_KEY=
+LLM_MODEL=your-model
+```
+
+For Pangolin or another reverse proxy, forward HTTP traffic to `intelligence-terminal:3117` (or the `PORT` you set). Missing API keys do not crash sweeps; affected sources are reported as degraded in `/api/health`.
+
+#### Build And Publish Your Gitea Image
+
+```bash
+docker login git.wilkensxl.de
+docker build -t git.wilkensxl.de/mrsphay/intelligence-terminal:latest .
+docker tag git.wilkensxl.de/mrsphay/intelligence-terminal:latest git.wilkensxl.de/mrsphay/intelligence-terminal:20260516
+docker push git.wilkensxl.de/mrsphay/intelligence-terminal:latest
+docker push git.wilkensxl.de/mrsphay/intelligence-terminal:20260516
+```
 
 ---
 
@@ -186,12 +278,26 @@ Alerts are delivered as rich embeds with color-coded sidebars: red for FLASH, ye
 **Optional dependency:** The full bot requires `discord.js`. Install it with `npm install discord.js`. If it's not installed, Crucix automatically falls back to webhook-only mode.
 
 ### Optional LLM Layer
-Connect any of 8 LLM providers for enhanced analysis:
+Connect cloud or local OpenAI-compatible LLM providers for enhanced analysis:
 - **AI trade ideas** — quantitative analyst producing 5-8 actionable ideas citing specific data
 - **Smarter alert evaluation** — LLM classifies signals into FLASH/PRIORITY/ROUTINE tiers with cross-domain correlation and confidence scoring
-- Providers: Anthropic Claude, OpenAI, Google Gemini, OpenRouter (Unified API), OpenAI Codex (ChatGPT subscription), MiniMax, Mistral, Grok
+- Providers: OpenRouter, OpenAI-compatible APIs, LM Studio, Ollama, OpenAI, Anthropic Claude, Google Gemini, OpenAI Codex, MiniMax, Mistral, Grok
 - Graceful fallback — when LLM is unavailable, a rule-based engine takes over alert evaluation. LLM failures never crash the sweep cycle.
 
+Primary env keys:
+
+```env
+LLM_PROVIDER=openrouter
+LLM_BASE_URL=https://openrouter.ai/api/v1
+LLM_API_KEY=
+LLM_MODEL=openrouter/free
+LLM_TEMPERATURE=0.2
+LLM_MAX_TOKENS=2000
+LLM_TIMEOUT_MS=90000
+```
+
+OpenRouter also supports model ids ending in `:free`; use the model id shown in your OpenRouter account when you want a specific free model.
+
 ---
 
 ## API Keys Setup