feat: Build the Dream Weaver interior restyling workflow to preserve room geometry while changing aesthetics (#5)

#3 Self-approved and unit tests passed with flying colors.

Co-authored-by: Sagnik <sagnik7896@gmail.com>
Reviewed-on: sagnik/Project_Velocity#5

.Agent Context/Sprint 1/Project Velocity_ Dream Weaver.md

@@ -0,0 +1,73 @@
+1\. Executive Summary: The "Dream Weaver" Objective  
+The goal is to move beyond simple "image-to-image" generation, which often "hallucinates" new walls or windows. "Dream Weaver" uses **Structural Constraint Logic** to ensure that while the furniture, wallpaper, and flooring change, the **physical dimensions, window placements, and vanishing points** of the original room remain 100% accurate to the real-world property.  
+---
+
+2\. Technical Architecture & Component Research  
+A. The Foundation: RealVisXL V5.0 (Lightning)
+
+* **Why:** Unlike Juggernaut (which is cinematic), RealVisXL ([https://civitai.com/models/139562?modelVersionId=789646](https://civitai.com/models/139562?modelVersionId=789646)) is trained on architectural photography datasets. It understands the "white balance" of a real room and doesn't over-saturate colors.  
+* **V5.0 Lightning Advantage:** It allows for high-quality generation in just 4–8 steps, making the "visualizer" tool feel snappy and responsive for the end-user.
+
+B. The Guidance Layer: Dual-ControlNet Strategy  
+To preserve geometry, a single ControlNet is rarely enough. We will use a **stacked approach**:
+
+1. **M-LSD (Line Segment Detection):** Best for architecture. It identifies straight lines (ceiling joints, floor corners, door frames). This prevents the walls from "bending."  
+2. **Depth (Zoe or MiDaS):** Provides the model with a 3D map of the room. This ensures that a new rug placed on the floor correctly recedes into the distance.
+
+C. The Isolation Layer: SAM (Segment Anything Model)
+
+* **Purpose:** We don't want to change the view out of the window or the specific crown molding if it's a selling point.  
+* **Implementation:** SAM allows the workflow to "mask" specific areas (e.g., *only* the back wall) so the AI only repaints the pixels within that mask.
+
+---
+
+3\. Implementation Guide: Step-by-Step Build  
+Phase 1: Input & Pre-Processing
+
+1. **Image Load & Rescale:** Input image must be scaled to **1024x1024** (SDXL native) while maintaining aspect ratio via padding.  
+2. **Analysis:** Pass the image through two parallel pre-processor nodes:  
+   1. `M-LSD Lines Preprocessor`: Set threshold to detect only structural lines.  
+   2. `Zoe-DepthMap Preprocessor`: Generate a high-contrast depth map.
+
+Phase 2: Semantic Masking (The "Wall Selector")
+
+1. **GroundingDINO \+ SAM:** Use a text-based segmenter.  
+   1. *Prompt:* "walls, floor, ceiling."  
+2. **Mask Refinement:** Use a `Mask Dilate` node (2-5 pixels) to ensure the AI "bleeds" slightly into the corners, avoiding ugly seams between the new style and the old structure.
+
+Phase 3: The K-Sampler Logic (The "Restyler")
+
+1. **Positive Prompting (The Style):** Use a LoRA-weighted prompt.  
+   1. *Example:* `<lora:Interior_Style_Modern_Scandi:0.8>, hyper-realistic interior design, oak wood textures, minimalist furniture, soft sunlight, 8k architectural photography.`  
+2. **ControlNet Integration:**  
+   1. Apply **M-LSD ControlNet** at a strength of **0.8** (High structural adherence).  
+   2. Apply **Depth ControlNet** at a strength of **0.5** (Medium adherence for furniture placement).  
+3. **Inpainting / Latent Noise:**  
+   1. Set `denoising_strength` to **0.65 \- 0.75**.  
+   2. Lower than 0.6 keeps too much of the "empty" wall.  
+   3. Higher than 0.8 might ignore the ControlNet and hallucinate a new room.
+
+---
+
+4\. SWOT Analysis of the "Dream Weaver" Workflow
+
+| STRENGTHS | WEAKNESSES |
+| :---- | :---- |
+| **High Fidelity:** M-LSD ensures the "bones" of the house never change. | **Hardware Intensive:** SDXL \+ Dual ControlNet \+ SAM requires at least 12GB+ VRAM. |
+| **Lightning Speed:** RealVisXL V5.0 allows for sub-10 second renders. | **Prompt Sensitivity:** Requires specific "Architectural" keywords to avoid looking like a render. |
+| **OPPORTUNITIES** | **THREATS** |
+| **Custom LoRAs:** Can train a LoRA on a developer's specific "Signature Style" or furniture catalog. | **Copyright:** Ensure the LoRAs used aren't trained on copyrighted photographer assets. |
+| **API Integration:** JSON workflows allow this to be the backend for a mobile app. | **Edge Cases:** Very dark rooms or highly reflective surfaces can confuse Depth maps. |
+
+---
+
+5\. Best Practices & "Gotchas"
+
+* **Lighting Consistency:** Always include "global illumination" or "soft natural light" in the negative prompt to avoid the AI creating conflicting light sources (e.g., two suns).  
+* **The "Straight Lines" Rule:** Real estate photos are shot at eye level with "verticals" corrected. If the input photo is tilted, the AI will struggle. Use a **Perspective Correction** node at the start of the workflow.  
+* **Negative Prompting:** This is crucial for RealVisXL.  
+  * *Standard Negative:* `(worst quality, low quality, illustration, 3d, 2d, painting, cartoons, sketch), blurry, distorted, deformed, extra windows, unrealistic lighting.`  
+* **JSON Portability:** When exporting the workflow, use **"API Format"** in ComfyUI. Ensure all custom nodes (like Impact Pack for SAM) are version-locked to prevent the internal tool from breaking during updates.
+
+---
+

.Agent Context/Sprint 1/Project Velocity_ Product Suite Task List for Taiga Import - Table 1.csv

@@ -0,0 +1,33 @@
+User Story,Task Name,Module/Component,Description,Assignee,Priority
+"As an Architect, I need to configure the local and cloud hardware environments so the team can build without bottlenecks.","Define local ""Black Box"" edge server requirements",Architecture/Infrastructure,Define requirements for the offline-first experience center setup.,Sagnik,High
+"As an Architect, I need to configure the local and cloud hardware environments so the team can build without bottlenecks.",Provision AWS 8xA100 instance,Architecture/Infrastructure,Set up a powerful AWS instance with 8xA100 GPUs for heavy lifting.,Sagnik,High
+"As an Architect, I need to configure the local and cloud hardware environments so the team can build without bottlenecks.",Configure AWS virtualization (Compute Nodes),Architecture/Infrastructure,Split AWS instance into Node 1 (Sourik) and Node 2 (Sagnik/Sayan).,Sagnik,High
+"As an Architect, I need to configure the local and cloud hardware environments so the team can build without bottlenecks.",Set up secure SSH tunnels,Architecture/Infrastructure,Establish secure network access for remote compute nodes.,Sagnik,High
+"As an AI Visual Artist, I need to create API-ready ComfyUI workflows for ""The Catalyst"" and ""Immersive Sales Companion"".","Build ""Dream Weaver"" interior restyling workflow",The Catalyst / ComfyUI,Interior restyling using ControlNet + segment masking.,Sagnik,High
+"As an AI Visual Artist, I need to create API-ready ComfyUI workflows for ""The Catalyst"" and ""Immersive Sales Companion"".",Build marketing poster generation workflow,The Catalyst / ComfyUI,Leverage Qwen-Image 2512 for advanced multilingual typography.,Sagnik,High
+"As an AI Visual Artist, I need to create API-ready ComfyUI workflows for ""The Catalyst"" and ""Immersive Sales Companion"".",Implement Wan 2.2 video generation workflow,The Catalyst / ComfyUI,Generate cinematic promotional videos; test 1.3B locally and 14B on AWS.,Sagnik,High
+"As an AI Visual Artist, I need to create API-ready ComfyUI workflows for ""The Catalyst"" and ""Immersive Sales Companion"".",Expose ComfyUI via Async Queue API,The Catalyst / ComfyUI,Ensure Sourik's agents can trigger workflows automatically.,Sagnik,High
+"As an AI Engineer, I need to generate system prompts and fine-tune models.","Draft ""The Oracle"" persona prompts",The Oracle / AI,Adapt tone of top-tier Dubai brokers for WhatsApp CRM agent.,Sagnik,High
+"As an AI Engineer, I need to generate system prompts and fine-tune models.",Create marketing strategy prompts,The Catalyst / AI,Generate Meta/Google ad copy based on demographic inputs.,Sagnik,High
+"As an AI Engineer, I need to generate system prompts and fine-tune models.",Lock Frontend UI design,Dashboard / Frontend,"Finalize ""Apple/Steve Jobs"" aesthetic and hand over to Sayan.",Sagnik,High
+"As an iOS Developer, I need to build the ""Immersive Sales Companion"" iPad App using Swift.",Build native SwiftUI app shell,iOS App / Swift,"Mirror WebOS interface: Dashboard, Inventory, Oracle tabs.",Sayan,High
+"As an iOS Developer, I need to build the ""Immersive Sales Companion"" iPad App using Swift.",Implement camera capture for room transformation,iOS App / Swift,Push photos of empty rooms to ComfyUI API endpoint.,Sayan,High
+"As an iOS Developer, I need to build the ""Immersive Sales Companion"" iPad App using Swift.",Integrate ARKit/Sun Path simulation,iOS App / Swift,Overlay mathematical sun positioning over live feed or 3D view.,Sayan,High
+"As a Backend Engineer, I need to build the FastAPI neural core.",Set up Python FastAPI server & DB,Neural Dashboard / Backend,Configure server with PostgreSQL/Supabase database.,Sayan,High
+"As a Backend Engineer, I need to build the FastAPI neural core.",Create Oracle API endpoints,The Oracle / API,Endpoints for /api/leads and /api/chat-logs.,Sayan,High
+"As a Backend Engineer, I need to build the FastAPI neural core.",Create Sentinel API endpoints,The Sentinel / API,Endpoints for /api/biometrics and /api/sentiment.,Sayan,High
+"As a Backend Engineer, I need to build the FastAPI neural core.",Set up WebSockets,Neural Dashboard / Real-time,Stream sentiment drops and new messages to React frontend.,Sayan,High
+"As a Full-Stack Engineer, I need to build the ""Walled Garden"" CRM.",Connect React components to FastAPI,Neural Dashboard / Frontend,Wire the frontend components to backend endpoints.,Sayan,High
+"As a Full-Stack Engineer, I need to build the ""Walled Garden"" CRM.",Develop Kanban CRM logic,The Oracle / CRM,Auto-update lead stages based on Oracle triggers.,Sayan,High
+"As a Full-Stack Engineer, I need to build the ""Walled Garden"" CRM.",Visualize AI Sentiment insights,The Sentinel / Dashboard,Ensure accurate visualization of parsed AI sentiment data.,Sayan,High
+"As an Automation Engineer, I need to deploy the Claw bot ecosystem for ""The Oracle"".",Deploy PicoClaw/IronClaw bots,The Oracle / Agent,Deploy ultra-lightweight (Pico) or secure (Iron) bots for communication.,Sourik,High
+"As an Automation Engineer, I need to deploy the Claw bot ecosystem for ""The Oracle"".",Connect bots to WhatsApp/Email APIs,The Oracle / Integration,Ingest client messages into the ecosystem.,Sourik,High
+"As an Automation Engineer, I need to deploy the Claw bot ecosystem for ""The Oracle"".",Configure DM pairing & Allowlists,The Oracle / Security,Ensure enterprise privacy through security configurations.,Sourik,High
+"As an Automation Engineer, I need to deploy the Claw bot ecosystem for ""The Oracle"".",Route logs to CRM via webhooks,The Oracle / Integration,Send parsed transcripts and logs into Sayan's database.,Sourik,High
+"As an AI Operator, I need to set up the MCP Server and Agent Tools.",Set up Model Context Protocol (MCP) server,Architecture / Agent,"Give bot access to files, database, and internet.",Sourik,High
+"As an AI Operator, I need to set up the MCP Server and Agent Tools.",Configure background tasks (Heartbeat/Cron),Architecture / Automation,Set up SEO tracking and real estate news scraping.,Sourik,High
+"As an AI Operator, I need to set up the MCP Server and Agent Tools.",Configure Brave Search API,Architecture / Search,Allow agent to research target audiences autonomously.,Sourik,High
+"As a Marketing Automation Lead, I need to build ""The Catalyst"" integration.",Integrate Meta & Google Ads APIs,The Catalyst / Skills,Add ad business APIs as agent skills.,Sourik,High
+"As a Marketing Automation Lead, I need to build ""The Catalyst"" integration.",Implement Automated Bidding strategies,The Catalyst / Automation,Enable agent to manage budgets and read ad insights.,Sourik,High
+"As a Marketing Automation Lead, I need to build ""The Catalyst"" integration.",Write ComfyUI API bridge script,The Catalyst / AI Bridge,Prompt Sagnik's models to generate visual assets based on strategy.,Sourik,High
+"As a Marketing Automation Lead, I need to build ""The Catalyst"" integration.",Configure Social Auto-posting,The Catalyst / Social,Use headless browser/API to post generated content.,Sourik,High

.Agent Context/Sprint 1/Project Velocity_ User Stories and Task Breakdown Sprint 1.md

@@ -0,0 +1,228 @@
+Project Title: Project Velocity  
+The Immersive Sales Suite
+
+Sprint 1
+
+Project Description:
+
+Project Velocity is an integrated AI-powered real estate sales ecosystem designed for high-tier brokerages. The suite encompasses edge-computing hardware ("Black Box"), automated visual generation pipelines via ComfyUI ("The Catalyst"), a robust FastAPI-based neural core, and an immersive Swift-based iPad application ("Immersive Sales Companion"). The system manages the entire lead lifecycle: from autonomous engagement and lead qualification via WhatsApp/Email bots ("The Oracle"), to real-time sentiment analysis, automated ad bidding, and on-the-fly marketing asset generation.
+
+EPIC 1: Architecture, Visual AI & Prompt Engineering (Assignee: Sagnik)
+
+User Story 1.1: As an Architect, I need to configure the local and cloud hardware environments so the team can build without bottlenecks.
+
+UX: 0
+
+Design: 0
+
+Front: 0
+
+Back: 8
+
+Total Points: 8
+
+Tasks:
+
+* W1: Define the local "Black Box" edge server requirements for the offline-first experience center setup.  
+* W2: Provision the AWS 8xA100 instance.  
+* W2: Configure virtualization to split the AWS instance into two compute nodes: Node 1 (Sourik's Agent/Bot Operations) and Node 2 (Sagnik & Sayan's Model/Render Operations).  
+* W2: Set up secure SSH tunnels networks to allow remote access to the AWS nodes.
+
+User Story 1.2: As an AI Visual Artist, I need to create API-ready ComfyUI workflows for "The Catalyst" and the "Immersive Sales Companion".
+
+UX: 0
+
+Design: 3
+
+Front: 2
+
+Back: 3
+
+Total Points: 8
+
+Tasks:
+
+* W1: Build the "Dream Weaver" interior restyling workflow using ControlNet \+ segment masking to preserve room geometry while changing aesthetics.  
+* W1: Build a marketing poster generation workflow using Qwen-Image 2512 to leverage its advanced multilingual text rendering capabilities for precise real estate typography.  
+* W2: Implement the Wan 2.2 (14B or 1.3B) video generation workflow for cinematic promotional videos.  
+* W2: Expose all ComfyUI workflows via the Asynchronous Queue API so Sourik's agents can trigger them automatically.
+
+User Story 1.3: As an AI Engineer, I need to generate system prompts and fine-tune models so "The Oracle" and "The Catalyst" behave like elite real estate professionals.
+
+UX: 2
+
+Design: 3
+
+Front: 3
+
+Back: 0
+
+Total Points: 8
+
+Tasks:
+
+* W1: Draft "The Oracle" persona prompts (adapting the tone of top-tier Dubai brokers) for the WhatsApp CRM agent.  
+* W1: Create marketing strategy prompts for "The Catalyst" to generate Meta/Google ad copy based on demographic inputs.  
+* W1: Lock the frontend UI design (the "Apple/Steve Jobs" aesthetic) and officially hand over the React components and required API schemas to Sayan for backend wiring.
+
+EPIC 2: Full-Stack Integration, CRM & iOS App (Assignee: Sayan)
+
+User Story 2.1: As an iOS Developer, I need to build the "Immersive Sales Companion" iPad App using Swift.
+
+UX: 3
+
+Design: 2
+
+Front: 3
+
+Back: 0
+
+Total Points: 8
+
+Tasks:
+
+* W1: Build the native SwiftUI app shell mirroring the WebOS interface (Dashboard, Inventory, Oracle tabs).  
+* W1: Implement the camera capture feature to take photos of empty walls/rooms and push them to Sagnik's ComfyUI API endpoint.  
+* W1: Integrate ARKit/CoreLocation/CoreMotion to overlay the mathematical Sun Path over the live camera feed or 3D model view.
+
+User Story 2.2: As a Backend Engineer, I need to build the FastAPI neural core to connect all 4 software components.
+
+UX: 0
+
+Design: 0
+
+Front: 0
+
+Back: 8
+
+Total Points: 8
+
+Tasks:
+
+* W1: Set up the Marketing page frontend for Sourik.  
+* W1: Set up the Python FastAPI server with a PostgreSQL/Supabase database.  
+* W1: Create API endpoints for "The Oracle" (/api/leads, /api/chat-logs) to receive data from Sourik's WhatsApp bots.  
+* W1: Create API endpoints for "The Sentinel" (/api/biometrics, /api/sentiment) to ingest video player facial/voice data points.  
+* W1: Set up WebSockets to stream real-time updates directly to the WebOS React frontend.
+
+User Story 2.3: As a Full-Stack Engineer, I need to build the "Walled Garden" CRM and wire the React WebOS.
+
+UX: 2
+
+Design: 0
+
+Front: 3
+
+Back: 3
+
+Total Points: 8
+
+Tasks:
+
+* W2: Connect the frontend React components to the FastAPI endpoints.  
+* W2: Develop the logic for the simplified "Kanban" CRM pipeline, ensuring lead stages automatically update based on triggers from "The Oracle".  
+* W2: Ensure the WebOS dashboard accurately visualizes the parsed AI sentiment data’s output.
+
+EPIC 3: Agentic Framework, Automation & Ad Network (Assignee: Sourik)
+
+User Story 3.1: As an Automation Engineer, I need to deploy and manage the Claw bot ecosystem for "The Oracle".
+
+UX: 0
+
+Design: 0
+
+Front: 0
+
+Back: 5
+
+Total Points: 5
+
+Tasks:
+
+* W1: Deploy PicoClaw or IronClaw to act as the primary communication agent.  
+* W1: Connect the bot to WhatsApp/Email APIs to ingest client messages.  
+* W1: Configure DM pairing and security allowlists.  
+* W1: Route all parsed chat transcripts, call durations, and interaction logs directly into Sayan's CRM database via FastAPI webhooks.
+
+User Story 3.2: As an AI Operator, I need to set up the MCP Server and Agent System Tools.
+
+UX: 0
+
+Design: 0
+
+Front: 0
+
+Back: 5
+
+Total Points: 5
+
+Tasks:
+
+* W1: Set up the Model Context Protocol (MCP) server for secure access to local files, the property database, and the internet.  
+* W1: Configure HEARTBEAT.md or Cron tools for periodic background tasks.  
+* W1: Configure Brave Search API to allow the agent to autonomously research target audiences.
+
+User Story 3.3: As a Marketing Automation Lead, I need to build "The Catalyst" integration.
+
+UX: 2
+
+Design: 1
+
+Front: 2
+
+Back: 3
+
+Total Points: 8
+
+Tasks:
+
+* W2: Integrate Meta Business API and Google AdWords API as agent "Skills".  
+* W2: Give the agent the ability to read ad insights, manage marketing budgets, and execute automated bidding strategies.  
+* W2: Write the bridging script allowing the agent to autonomously prompt Sagnik's ComfyUI API to generate custom posters and promotional videos.  
+* W2: Configure the headless browser tool or social APIs for autonomous content posting.
+
+EPIC 4: Immersive Reality & Buyer Intelligence (Phase 2\)
+
+Focus: Cinematic AI life simulation, interactive AR environments, biometric engagement tracking, and wealth projections.
+
+User Story 4.1: As an AI Visual Artist and iOS Developer, we need to build the "Future Life" and "Time & Light" engines to emotionally anchor the buyer to the property.
+
+UX: 5
+
+Design: 5
+
+Front: 5
+
+Back: 8
+
+Total Points: 23
+
+Assignees: Sagnik & Sayan
+
+Tasks:
+
+* \[ \] Phase 2: (Sagnik) Build a ComfyUI/Wan 2.2 workflow for "Future Life Simulation" that generates cinematic videos of specific lifestyle prompts (morning sunlight, kids playing, dinner parties) mapped to the unit's floorplan.  
+* \[ \] Phase 2: (Sayan) Integrate a "Time & Light Engine" into the Swift iPad app using ARKit/SceneKit to simulate real-time sun paths, seasonal shadows, and weather changes (rain, festive lighting) over the 3D model.  
+* \[ \] Phase 2: (Sayan) Add interactive touchscreen sliders to the iPad app to control month, time of day, and view obstruction massing.
+
+User Story 4.2: As a Full-Stack Engineer and Automation Lead, we need to build the Engagement Intelligence and Social Proof layer to give the sales team data-driven closing tools.
+
+UX: 3
+
+Design: 3
+
+Front: 5
+
+Back: 8
+
+Total Points: 19
+
+Assignees: Sayan & Sourik
+
+Tasks:
+
+* \[ \] Phase 2: (Sayan) Build the "Legacy Mode" wealth projection UI in the iPad app and WebOS, visualizing 10-20 year compounding appreciation and rental yields against gold/stock benchmarks.  
+* \[ \] Phase 2: (Sayan) Create the "Social Proof" live map in the frontend, dynamically clustering anonymized buyer demographics (NRI vs local, professions) to build tribe psychology.  
+* \[ \] Phase 2: (Sourik) Configure "The Sentinel" backend API to ingest and process eye-tracking and micro-expression data from the iPad's front-facing camera (with consent) during the tour.  
+* \[ \] Phase 2: (Sayan) Update the WebOS CRM dashboard to visualize the emotional spike data, highlighting exactly which rooms peaked the buyer's interest for post-tour sales anchoring.
+