feat: add LiteLLM provider and Code-Inc image target

README.md

@@ -4,8 +4,8 @@
 
 **Self-hosted intelligence dashboard. 27 open sources. Docker-first. No telemetry.**
 
-[![Gitea Repository](https://img.shields.io/badge/source-Gitea-609926?style=for-the-badge&logo=gitea&logoColor=white)](https://git.wilkensxl.de/MrSphay/intelligence-terminal)
-[![Docker Image](https://img.shields.io/badge/image-Gitea%20Registry-0b1220?style=for-the-badge&logo=docker&logoColor=white)](https://git.wilkensxl.de/MrSphay/-/packages/container/intelligence-terminal/latest)
+[![Gitea Repository](https://img.shields.io/badge/source-Gitea-609926?style=for-the-badge&logo=gitea&logoColor=white)](https://git.wilkensxl.de/Code-Inc/intelligence-terminal)
+[![Docker Image](https://img.shields.io/badge/image-Gitea%20Registry-0b1220?style=for-the-badge&logo=docker&logoColor=white)](https://git.wilkensxl.de/Code-Inc/-/packages/container/intelligence-terminal/latest)
 
 [![Node.js 22+](https://img.shields.io/badge/node-22%2B-brightgreen)](#quick-start)
 [![License: AGPL v3](https://img.shields.io/badge/license-AGPLv3-blue.svg)](LICENSE)
@@ -32,7 +32,7 @@
 
 > **Supported deployment:** private home-server or lab deployment through Docker, Dockge, Pangolin, or local Node.js.
 > Runtime data stays in your configured `runs/` volume and API keys are operator-owned.
-> **Source:** [git.wilkensxl.de/MrSphay/intelligence-terminal](https://git.wilkensxl.de/MrSphay/intelligence-terminal)
+> **Source:** [git.wilkensxl.de/Code-Inc/intelligence-terminal](https://git.wilkensxl.de/Code-Inc/intelligence-terminal)
 > Pull the image or clone the repository to run Intelligence Terminal on your own infrastructure.
 
 Intelligence Terminal pulls satellite fire detection, flight tracking, radiation monitoring, satellite constellation tracking, economic indicators, live market prices, conflict data, sanctions lists, and social sentiment from 27 open-source intelligence feeds in parallel, every 15 minutes, and renders everything on a single self-contained dashboard.
@@ -66,7 +66,7 @@ It was built for anyone who wants to understand what's actually happening in the
 
 ```bash
 # 1. Clone the repo
-git clone https://git.wilkensxl.de/MrSphay/intelligence-terminal.git
+git clone https://git.wilkensxl.de/Code-Inc/intelligence-terminal.git
 cd intelligence-terminal
 
 # 2. Install dependencies (just Express)
@@ -92,7 +92,7 @@ The dashboard opens automatically at `http://localhost:3117` and immediately beg
 ### Docker
 
 ```bash
-docker pull git.wilkensxl.de/mrsphay/intelligence-terminal:latest
+docker pull git.wilkensxl.de/code-inc/intelligence-terminal:latest
 ```
 
 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.
@@ -102,7 +102,7 @@ Dashboard at `http://localhost:3117`. Sweep data persists in `./runs/` via volum
 ```yaml
 services:
   intelligence-terminal:
-    image: git.wilkensxl.de/mrsphay/intelligence-terminal:latest
+    image: git.wilkensxl.de/code-inc/intelligence-terminal:latest
     container_name: intelligence-terminal
     env_file:
       - path: .env
@@ -146,7 +146,7 @@ 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_SITE_URL=https://git.wilkensxl.de/Code-Inc/intelligence-terminal
 OPENROUTER_APP_NAME=Intelligence Terminal
 
 FRED_API_KEY=
@@ -169,6 +169,12 @@ DISCORD_WEBHOOK_URL=
 Local LLM examples:
 
 ```env
+# LiteLLM proxy (the URL must include the OpenAI-compatible /v1 path)
+LLM_PROVIDER=litellm
+LLM_BASE_URL=https://llm.example.com/v1
+LLM_API_KEY=your-litellm-api-key
+LLM_MODEL=your-model-alias
+
 # LM Studio
 LLM_PROVIDER=lmstudio
 LLM_BASE_URL=http://host.docker.internal:1234/v1
@@ -288,10 +294,10 @@ Scenario states are `dormant`, `watching`, `building`, and `confirmed`. The dash
 
 ```bash
 docker login git.wilkensxl.de -u MrSphay
-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
+docker build -t git.wilkensxl.de/code-inc/intelligence-terminal:latest .
+docker tag git.wilkensxl.de/code-inc/intelligence-terminal:latest git.wilkensxl.de/code-inc/intelligence-terminal:YYYYMMDD
+docker push git.wilkensxl.de/code-inc/intelligence-terminal:latest
+docker push git.wilkensxl.de/code-inc/intelligence-terminal:YYYYMMDD
 ```
 
 Gitea Actions publishes the same image automatically when the repository secret `REGISTRY_TOKEN` is set with package read/write permissions. The workflow tags images as `latest`, the commit SHA, and a UTC `YYYYMMDD` release tag.
@@ -380,7 +386,7 @@ Alerts are delivered as rich embeds with color-coded sidebars: red for FLASH, ye
 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: OpenRouter, OpenAI-compatible APIs, LM Studio, Ollama, OpenAI, Anthropic Claude, Google Gemini, OpenAI Codex, MiniMax, Mistral, Grok
+- Providers: LiteLLM, 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:
@@ -625,7 +631,7 @@ All settings are in `.env` with sensible defaults:
 | `STALE_DATA_MAX_AGE_MINUTES` | `60` | Data age threshold for stale health state |
 | `STALE_ALERT_COOLDOWN_MINUTES` | `60` | Minimum time between repeated operator stale-data alerts |
 | `DASHBOARD_URL` | local URL | Dashboard URL included in operator alerts |
-| `LLM_PROVIDER` | disabled | `anthropic`, `openai`, `gemini`, `codex`, `openrouter`, `minimax`, `mistral`, or `grok` |
+| `LLM_PROVIDER` | disabled | `litellm`, `openrouter`, `openai-compatible`, `lmstudio`, `ollama`, `anthropic`, `openai`, `gemini`, `codex`, `minimax`, `mistral`, or `grok` |
 | `LLM_API_KEY` | — | API key (not needed for codex) |
 | `LLM_MODEL` | per-provider default | Override model selection |
 | `TELEGRAM_BOT_TOKEN` | disabled | For Telegram alerts + bot commands |
@@ -751,7 +757,7 @@ For contribution guidelines, review expectations, and source-add rules, see `CON
 
 For bugs, feature requests, and integration ideas, use the Gitea issue tracker so discussion stays visible and actionable:
 
-https://git.wilkensxl.de/MrSphay/intelligence-terminal/issues
+https://git.wilkensxl.de/Code-Inc/intelligence-terminal/issues
 
 ## Upstream And License