feat: Enhance LLM model support with an updated roster, documentation, and flutter_markdown_plus integration.

Author: princepspolycap

docs/MODELS.md

@@ -14,84 +14,83 @@ Wingman supports a tiered model strategy to balance speed, intelligence, and pri
 
 ---
 
-## Model Roster (Verified Specs)
+## Model Roster (Verified Official List)
 
-All models are optimized for **LiteRT (MediaPipe)** and verified for on-device performance.
+All models are official LiteRT builds from the **`litert-community`** organization on HuggingFace.
 
 | Model | Class | Size | RAM | Context | Category |
 |-------|-------|------|-----|---------|----------|
-| **FunctionGemma** ⭐ | 270M | 150MB | 2GB | 8K | Agent (Tools) |
-| **Gemma 3 1B** 💎 | 1B | 555MB | 4GB | 32K | General Chat |
-| **DeepSeek R1** | 1.5B | 1.2GB | 4GB | 32K | Reasoning |
+| **DeepSeek R1** | 1.5B | 1.2GB | 4GB | 32K | Reasoning/Agent |
 | **Phi-4 Mini** | 3.8B | 2.8GB | 6GB | 128K | Logic/Reasoning |
-| **Hammer 2.1** | 0.5B | 480MB | 2GB | 8K | Actions |
-| **Qwen 2.5** | 1.5B | 1.1GB | 4GB | 32K | Multilingual |
-| **Gemma 3n E4B** | 4B | 3.1GB | 3GB* | 32K | Multimodal |
-| **Gemma 3n E2B** | 2B | 1.6GB | 2GB* | 32K | Multimodal |
-
-*\*Note: Gemma 3n models use effective parameter counting for lower VRAM footprints.*
+| **Gemma 3 1B** 💎 | 1B | 689MB | 4GB | 32K | General Chat |
+| **Gemma 3 270M** | 270M | 276MB | 2GB | 32K | Fast Chat |
+| **Qwen 2.5 1.5B** | 1.5B | 1.1GB | 4GB | 32K | Multilingual |
+| **Qwen 2.5 0.5B** | 0.5B | 400MB | 2GB | 32K | Fast Actions |
+| **Gemma 2 2B IT** | 2B | 1.6GB | 4GB | 8K | High Quality Text |
+| **FunctionGemma** ⭐ | 270M | 150MB | 2GB | 8K | Specialized Agent |
+| **TinyLlama 1.1B** | 1.1B | 650MB | 2GB | 2K | Legacy Support |
+| **SmolLM 135M** | 135M | 270MB | 1GB | 2K | Ultra-Lightweight |
 
 ---
 
-## Tier 1: Agent & Tools (The "Brain")
+## Model Tiers
+
+### Tier 1: Agent & Tools (The "Brain")
+*   **DeepSeek R1 1.5B**: Best for complex reasoning and tool chaining.
+*   **Phi-4 Mini**: Advanced logic for deeper strategy analysis.
+*   **FunctionGemma 270M**: The core model for simple on-device actions.
+*   **Qwen 2.5 (1.5B/0.5B)**: Exceptional for multilingual tool requests.
 
-### FunctionGemma 270M ⭐
-**Recommended for Wingman's tool-calling features.**
-- **Capabilities**: Clipboard, Reminders, Dossier Updates.
-- **Vibe**: Fast, structured, reliable.
+### Tier 2: General Chat (The "Vibe")
+*   **Gemma 3 1B** 💎: **Recommended.** Best balance of wit, speed, and persona.
+*   **Gemma 2 2B IT**: High-precision text for nuanced advice.
+*   **Gemma 3 270M**: Whisper-fast chat for quick check-ins.
 
-### Hammer 2.1 0.5B
-- **Capabilities**: Multi-turn tool use, action planning.
-- **Vibe**: High-speed task execution.
+### Tier 3: Support Models (The "Safety Net")
+*   **TinyLlama 1.1B**: Reliable chat for older hardware.
+*   **SmolLM 135M**: Runs on almost anything; perfect for emergency advice.
 
 ---
 
-## Tier 2: General Chat (The "Vibe")
+## Technical Setup
 
-### Gemma 3 1B 💎
-**The gold standard for natural "WINGMAN" persona.**
-- **Capabilities**: High-quality chat, cultural nuance, humor.
-- **Vibe**: Authentic, witty, helpful.
+### RAM Recommendations
+- **Old Devices (2GB)**: Use FunctionGemma 270M.
+- **Standard (4GB)**: Gemma 3 1B or DeepSeek R1.
+- **Pro Devices (6GB+)**: Phi-4 Mini or Gemma 3n E4B.
 
-### Qwen 2.5 1.5B
-- **Capabilities**: Superior multilingual support (Spanish/Latino slang).
-- **Vibe**: Culturally sophisticated, versatile.
+### Context Management
+Wingman uses a dynamic sliding-window context. Older messages are summarized once they exceed the model's `contextWindowK` (listed above), ensuring you nunca pierdas el hilo de la conversacion.
 
 ---
 
-## Tier 3: Reasoning & Logic (The "Strategist")
-
-### Phi-4 Mini 3.8B 🔬
-- **Capabilities**: Complex pattern matching, relationship strategy.
-- **Vibe**: Analytical, deep-thinking, logical.
+## Official Sources & Repositories
 
-### DeepSeek R1 1.5B
-- **Capabilities**: Logical chain-of-thought, problem solving.
-- **Vibe**: Methodical, clarifying, reasoning.
+Wingman uses strictly verified `.task` models to ensure compatibility with MediaPipe/LiteRT.
 
----
-
-## Tier 4: Multimodal (The "Eyes")
+### Primary Source: LiteRT Community
+Most models are sourced from the [LiteRT Community HuggingFace Organization](https://huggingface.co/litert-community).
+- **DeepSeek R1 1.5B**: [Link](https://huggingface.co/litert-community/DeepSeek-R1-Distill-Qwen-1.5B)
+- **Phi-4 Mini**: [Link](https://huggingface.co/litert-community/Phi-4-mini-instruct)
+- **Gemma 3 Family**: [Link](https://huggingface.co/litert-community/Gemma3-1B-IT)
+- **Qwen 2.5 Family**: [Link](https://huggingface.co/litert-community/Qwen2.5-1.5B-Instruct)
 
-### Gemma 3n E4B / E2B
-- **Capabilities**: Screenshot transcriptions, photo analysis.
-- **Vibe**: Visual, observant.
+### Specialized Agent Models
+- **FunctionGemma 270M**: Sourced from [sasha-denisov/function-gemma-270M-it](https://huggingface.co/sasha-denisov/function-gemma-270M-it). This model is specifically fine-tuned for on-device tool calling and low-latency interaction.
 
 ---
 
-## Technical Setup
-
-### RAM Recommendations
-- **Old Devices (2GB)**: Use FunctionGemma 270M.
-- **Standard (4GB)**: Gemma 3 1B or DeepSeek R1.
-- **Pro Devices (6GB+)**: Phi-4 Mini or Gemma 3n E4B.
+## Technical Specifications (Summary)
 
-### Context Management
-Wingman uses a dynamic sliding-window context. Older messages are summarized once they exceed the model's `contextWindowK` (listed above), ensuring you nunca pierdas el hilo de la conversacion.
+| Metric | Minimum | Recommended |
+|--------|---------|-------------|
+| **Device RAM** | 2GB | 4GB - 6GB |
+| **Storage** | 1GB | 5GB+ (for multiple models) |
+| **OS** | iOS 16.0+ / Android 11+ | Latest |
 
 ---
 
-## Sources & Credits
-- **Google AI**: Native Gemma family support.
-- **LiteRT Community**: For optimized `.task` conversions of DeepSeek, Qwen, and Phi models.
-- **MediaPipe**: The underlying inference engine.
+## Credits
+- **Google AI**: For the Gemma architecture and MediaPipe SDK.
+- **DeepSeek / Microsoft / Alibaba**: For the weights used in distilled LiteRT models.
+- **Sasha Denisov**: For the FunctionGemma fine-tune optimized for mobile agents.

lib/main.dart

@@ -64,7 +64,7 @@ final _router = GoRouter(
   routes: [
     // Home screen (profiles list) - accessible via drawer/button
     GoRoute(
-      path: '/profiles',
+      path: '/radar',
       builder: (context, state) => const HomeScreen(),
     ),
     // Main chat route