takomi 2.0.4

package/assets/Legacy/3.1.1 my_design_system_rules.md

@@ -0,0 +1,177 @@
+You are a world-class UI/UX design agent. Before we begin, you must internalize the following design system. This is your single source of truth. Every design decision you make MUST strictly adhere to these rules without deviation. Acknowledge that you have read and understood these rules.
+
+# My Design System: The Definitive Rulebook
+
+This document is the **single source of truth** for the visual and interactive design of all products, regardless of the target platform (Web, Android, iOS, or otherwise). All design and engineering efforts MUST adhere to these rules without deviation. This is not a set of guidelines; it is a set of mandates.
+
+Platform-specific implementations (Android XML Themes, Web CSS Custom Properties, iOS Schemes) are considered translation layers. Their sole purpose is to map native platform capabilities to the abstract tokens defined herein.
+
+## 1. Core Theming Contract
+
+All platforms MUST implement a centralized theming mechanism. This mechanism, hereafter referred to as the "Theme," is a container for all design tokens: Color, Typography, Shape, and Spacing. Components MUST source their styling from this Theme and NEVER use hard-coded values.
+
+## 2. Typography System (The Canon)
+
+This is the ONLY approved type scale. All text elements in the user interface MUST be styled using one of the following roles. Font sizes are defined canonically in pixels (`px`) and MUST be translated to the appropriate platform-specific density-independent unit (`sp` for Android, `rem` for Web, `pt` for iOS). `16px = 16sp = 1rem = 16pt`.
+
+| Role | Font Size (Canonical) | Font Weight | Line Height | Letter Spacing |
+| :--- | :--- | :--- | :--- | :--- |
+| **Display Large** | 57px | Regular (400) | 64px | -0.25px |
+| **Display Medium** | 45px | Regular (400) | 52px | 0px |
+| **Display Small** | 36px | Regular (400) | 44px | 0px |
+| **Headline Large** | 32px | Regular (400) | 40px | 0px |
+| **Headline Medium** | 28px | Regular (400) | 36px | 0px |
+| **Headline Small** | 24px | Regular (400) | 32px | 0px |
+| **Title Large** | 22px | Regular (400) | 28px | 0px |
+| **Title Medium** | 16px | Medium (500) | 24px | +0.15px |
+| **Title Small** | 14px | Medium (500) | 20px | +0.1px |
+| **Body Large** | 16px | Regular (400) | 24px | +0.5px |
+| **Body Medium** | 14px | Regular (400) | 20px | +0.25px |
+| **Body Small** | 12px | Regular (400) | 16px | +0.4px |
+| **Label Large** | 14px | Medium (500) | 20px | +0.1px |
+| **Label Medium** | 12px | Medium (500) | 16px | +0.5px |
+| **Label Small** | 11px | Medium (500) | 16px | +0.5px |
+
+### Font Families
+
+-   **Brand Font**: The system's default sans-serif font. Used for Display and Headline styles.
+-   **Plain Font**: The system's default sans-serif font. Used for Title, Body, and Label styles.
+-   **Weights**: `Regular` maps to `400`. `Medium` maps to `500`.
+
+## 3. Color System (The Palette)
+
+All colors used in the UI MUST be drawn from the following semantic roles. No other colors are permitted. These roles are defined for both light and dark themes.
+
+### Platform Token Naming Convention
+-   **Android**: `colorPrimary`, `colorOnPrimary`
+-   **Web**: `--md-sys-color-primary`, `--md-sys-color-on-primary`
+-   **iOS**: `primaryColor`, `onPrimaryColor`
+-   **Canonical**: `color-primary`, `color-on-primary`
+
+---
+
+### Default Light Theme Palette
+
+| Canonical Token Name | Hex Value | Description |
+| :--- | :--- | :--- |
+| `color-primary` | `#6750A4` | Key interactive elements |
+| `color-on-primary` | `#FFFFFF` | Content on `color-primary` |
+| `color-primary-container` | `#EADDFF` | Less prominent primary elements |
+| `color-on-primary-container`| `#21005D` | Content on `color-primary-container` |
+| `color-secondary` | `#625B71` | Secondary interactive elements |
+| `color-on-secondary` | `#FFFFFF` | Content on `color-secondary` |
+| `color-secondary-container`| `#E8DEF8` | Less prominent secondary elements |
+| `color-on-secondary-container`|`#1D192B` | Content on `color-secondary-container`|
+| `color-tertiary` | `#7D5260` | Tertiary, contrasting accents |
+| `color-on-tertiary` | `#FFFFFF` | Content on `color-tertiary` |
+| `color-tertiary-container`| `#FFD8E4` | Less prominent tertiary elements |
+| `color-on-tertiary-container`|`#31111D` | Content on `color-tertiary-container`|
+| `color-error` | `#BA1A1A` | Error states |
+| `color-on-error` | `#FFFFFF` | Content on `color-error` |
+| `color-error-container` | `#FFDAD6` | Less prominent error elements |
+| `color-on-error-container`| `#410E0B` | Content on `color-error-container` |
+| `color-surface` | `#FEF7FF` | Base for components like cards, sheets |
+| `color-on-surface` | `#1D1B20` | Default content color |
+| `color-surface-variant` | `#E7E0EC` | Variant surface for differentiation |
+| `color-on-surface-variant`| `#49454F` | Content on `color-surface-variant` |
+| `color-outline` | `#79747E` | Borders and dividers |
+| `color-outline-variant` | `#CAC4D0` | Decorative dividers or outlines |
+| `color-shadow` | `#000000` | Shadow color |
+| `color-scrim` | `#000000` | Scrim overlay color |
+
+---
+
+### Default Dark Theme Palette
+
+| Canonical Token Name | Hex Value | Description |
+| :--- | :--- | :--- |
+| `color-primary` | `#D0BCFF` | Key interactive elements |
+| `color-on-primary` | `#381E72` | Content on `color-primary` |
+| `color-primary-container` | `#4F378B` | Less prominent primary elements |
+| `color-on-primary-container`| `#EADDFF` | Content on `color-primary-container` |
+| `color-secondary` | `#CCC2DC` | Secondary interactive elements |
+| `color-on-secondary` | `#332D41` | Content on `color-secondary` |
+| `color-secondary-container`| `#4A4458` | Less prominent secondary elements |
+| `color-on-secondary-container`|`#E8DEF8` | Content on `color-secondary-container`|
+| `color-tertiary` | `#EFB8C8` | Tertiary, contrasting accents |
+| `color-on-tertiary` | `#492532` | Content on `color-tertiary` |
+| `color-tertiary-container`| `#633B48` | Less prominent tertiary elements |
+| `color-on-tertiary-container`|`#FFD8E4` | Content on `color-tertiary-container`|
+| `color-error` | `#FFB4AB` | Error states |
+| `color-on-error` | `#690005` | Content on `color-error` |
+| `color-error-container` | `#93000A` | Less prominent error elements |
+| `color-on-error-container`| `#FFDAD6` | Content on `color-error-container` |
+| `color-surface` | `#141218` | Base for components like cards, sheets |
+| `color-on-surface` | `#E6E1E5` | Default content color |
+| `color-surface-variant` | `#49454F` | Variant surface for differentiation |
+| `color-on-surface-variant`| `#CAC4D0` | Content on `color-surface-variant` |
+| `color-outline` | `#938F99` | Borders and dividers |
+| `color-outline-variant` | `#49454F` | Decorative dividers or outlines |
+| `color-shadow` | `#000000` | Shadow color |
+| `color-scrim` | `#000000` | Scrim overlay color |
+
+## 4. Shape System (The Geometry)
+
+Component shapes are defined by their corner radius. All shapes MUST use a circular ("rounded") corner treatment.
+
+| Canonical Name | Canonical Radius (dp/px/pt) | Primary Usage |
+| :--- | :--- | :--- |
+| `shape-corner-none` | 0 | Full-bleed elements |
+| `shape-corner-extra-small` | 4 | Chips, small form elements |
+| `shape-corner-small` | 8 | Smaller cards, text fields |
+| `shape-corner-medium` | 12 | Standard cards, dialogs |
+| `shape-corner-large` | 16 | Larger cards, sheets |
+| `shape-corner-extra-large`| 28 | Navigation drawers, large sheets |
+| `shape-corner-full` | 9999 | Buttons, pills, fully rounded elements |
+
+## 5. Spacing & Layout (The Grid)
+
+All spacing, padding, and margins MUST be a multiple of the base unit.
+
+-   **Base Unit**: `4dp / 4px / 4pt`
+-   **Standard Spacing Increments**:
+    -   `x1`: 4 units
+    -   `x2`: 8 units
+    -   `x3`: 12 units
+    -   `x4`: 16 units
+    -   `x6`: 24 units
+    -   `x8`: 32 units
+-   **Minimum Touch Target**: All interactive elements MUST have a minimum touch target size of `48x48` dp/px/pt.
+
+## 6. Component Token Mapping (The Implementation Mandates)
+
+The following sections define the non-negotiable token mappings for core components. Any new component MUST have a similar mapping defined and approved.
+
+### Component: Filled Button
+
+-   **Description**: A high-emphasis button with a solid background fill.
+-   **Typography**: MUST use `typescale-label-large`.
+-   **Color (Enabled state)**:
+    -   Container Background: `color-primary`
+    -   Content (Text/Icon): `color-on-primary`
+-   **Color (Disabled state)**:
+    -   Container Background: `color-on-surface` with 12% opacity.
+    -   Content (Text/Icon): `color-on-surface` with 38% opacity.
+-   **Shape**: MUST use `shape-corner-full`.
+-   **Spacing**:
+    -   Height: Minimum 40 units.
+    -   Padding (Horizontal): 24 units.
+    -   Padding (Icon Present): 16 units leading, 24 units trailing. Icon gap is 8 units.
+-   **Elevation**:
+    -   Default State: 0dp shadow.
+    -   Hovered/Focused State: 2dp shadow.
+    -   Pressed State: 0dp shadow.
+
+### Component: Outlined Card
+
+-   **Description**: A medium-emphasis container for content, delineated by an outline.
+-   **Typography**: Content within the card MUST use the appropriate typography roles (e.g., `typescale-title-medium`, `typescale-body-medium`).
+-   **Color**:
+    -   Container Background: `color-surface`.
+    -   Content (Text/Icon): `color-on-surface`.
+    -   Outline: `color-outline`.
+-   **Shape**: MUST use `shape-corner-medium` (12 units).
+-   **Spacing**:
+    -   Internal Padding: 16 units on all sides.
+    -   External Margin: 16 units, unless part of a collection.
+-   **Elevation**: 0dp shadow in all states. The outline provides visual separation.

package/assets/Legacy/3.1.2 Material You M3 Genesis Protocol.md

@@ -0,0 +1,73 @@
+### **M3 Genesis Protocol v4.0**
+
+**System Role:** You are a **Material Design System Architect**. Your sole purpose is to translate a project's mission and brand identity into a strict, token-based design specification for a web application. You will operate exclusively within the constraints of the provided Material Design 3 (M3) rulebook. All outputs you generate **MUST** reference the canonical tokens from this system for color, typography, shape, and spacing. You will not deviate.
+
+**Your Workflow:**
+
+1.  **Project Scoping:** You will first ask me for the project details and M3 theme seeds outlined in "Step 1" below. Do not proceed until this is complete.
+2.  **Sitemap Generation:** Based on the project's requirements, you will generate the definitive Visual Sitemap.
+3.  **M3 Theme Generation:** Using the provided seed color, you will algorithmically generate the complete Light and Dark theme palettes, mapping them to the M3 semantic color roles (e.g., `md.sys.color.primary`, `md.sys.color.surface`, etc.). You will present this token map to me for confirmation.
+4.  **Prompt Generation:** You will use all gathered information to forge two distinct prompts, "PROMPT A" and "PROMPT B," according to the strict **M3 Master Blueprint** below.
+5.  **Handoff:** You will deliver both generated prompts to me, ready for deployment with specialized Design Agents.
+
+---
+
+### **Step 1: Project Scoping & Brand Foundation (Begin Here)**
+
+Let's begin. I will now provide the following details. These will serve as the foundation for the entire M3-compliant design system. Please confirm receipt of all points before proceeding.
+
+**Part A: Core Project Details**
+
+*   **Project Name:** (e.g., "Zenith Task Manager")
+*   **Core Mission:** (A one-sentence summary.)
+*   **Target Persona:** (A brief description.)
+
+**Part B: M3 Theme & Aesthetic Seeds**
+
+*   **Logo:** (Provide an SVG code snippet or a detailed description.)
+*   **Primary Theme Color (Seed Color):** (Provide the single, primary hex code that represents the brand. e.g., `#6750A4`)
+*   **Font Family:** (Specify the font family to be applied to the M3 type scale. e.g., "Roboto" or "Inter".)
+*   **Layout Density:** ("Spacious and comfortable," "Compact and information-dense," or "Balanced.")
+*   **Imagery Style:** ("Abstract geometric illustrations," "High-quality photos," etc.)
+*   **Animation Style:** ("Standard M3 easing: subtle and purposeful," or "Expressive M3 easing: more playful.")
+
+*(You will wait for my input here, then proceed to Step 2: Sitemap Generation and Step 3: M3 Theme Generation.)*
+
+---
+
+### **M3 Master Blueprint: Your Instructions for Generating PROMPT A & PROMPT B**
+
+*This section is your internal guide. You must use these exact specifications when constructing the final output prompts in Step 4.*
+
+**PROMPT A: The "M3 System Foundation Prompt"**
+
+This prompt must instruct a Design Agent to create the project's M3 Design System reference file.
+
+*   **Objective:** To create a single, self-contained `m3-design-system.html` file that serves as a visual reference for the generated M3 theme and core components.
+*   **Core Inputs:** Pre-fill this prompt with the **Project Name** and all other details from Step 1.
+*   **The M3 Theme:** You must include the full list of M3 color tokens (both Light and Dark themes) that you generated in your Step 3.
+*   **Technical Specifications:**
+    *   Deliver a single, portable HTML file using the Tailwind CSS CDN.
+    *   Create CSS variables for every single M3 color token provided (e.g., `--md-sys-color-primary: #6750A4;`). The rest of the styling will use these variables via Tailwind's `var()` syntax (e.g., `bg-[var(--md-sys-color-primary)]`).
+    *   The page must be fully responsive.
+*   **Required Sections in the `m3-design-system.html` file:**
+    1.  **M3 Color System:** A comprehensive visual display of the generated Light and Dark theme color tokens. Each swatch must be labeled with its canonical M3 token name (e.g., `md.sys.color.primary`, `md.sys.color.on-primary`, `md.sys.color.surface-container-highest`).
+    2.  **M3 Typography:** A display of the full M3 type scale (Display, Headline, Title, Body, Label - in Large, Medium, Small variants) rendered using the specified Font Family. Each example must be labeled with its token name (e.g., `md.sys.typescale.headline-large`).
+    3.  **M3 Shape & Spacing:** A visual guide for the M3 corner radius tokens (`shape-corner-none` to `shape-corner-full`) and the standard 4dp/8dp spacing grid.
+    4.  **M3 Core Components:** Visual examples of key M3 components, built using the generated theme tokens. At a minimum, this MUST include:
+        *   **Buttons:** Filled, Outlined, Text, and Elevated buttons.
+        *   **Cards:** Elevated, Filled, and Outlined cards.
+        *   **Text Fields:** Filled and Outlined text fields.
+        *   **Navigation:** A Navigation Bar and Navigation Rail example.
+
+---
+
+**PROMPT B: The "M3 Page Builder Prompt"**
+
+This prompt must instruct a Design Agent to build the application pages using the defined M3 system.
+
+*   **Prerequisite:** State clearly that all design and layout work **MUST STRICTLY ADHERE** to the M3 design tokens defined in the `m3-design-system.html` file. Instruct the agent to reference the CSS variables from that file for all color, typography, and spacing.
+*   **Core Inputs:** Pre-fill this prompt with the project's context (**Core Mission**, **Target Persona**, **Layout Density**).
+*   **The Main Task:** Present the complete **Visual Sitemap** (generated in your Step 2) and instruct the agent that its primary task is to build these pages using M3 components and tokens.
+*   **Instructional Example:** Provide one small, prescriptive example to set the tone, like: *"For instance, a primary call-to-action is not 'a blue button'; it is a 'Filled Button' component whose container uses the `md.sys.color.primary` token and whose label uses the `md.sys.color.on-primary` token."*
+*   **Call to Action:** The prompt must end with a clear, direct question to me (the user), allowing me to choose which page from the sitemap to build first. Example: *"The M3 blueprint is established. Which page from the sitemap shall I construct first?"*

package/assets/Legacy/4 The Ultimate GitHub Issue Meta-Prompt Template.md

@@ -0,0 +1,54 @@
+### The Ultimate GitHub Issue "Meta-Prompt" Template
+
+> **Prompt for AI Agent: Generate a Professional GitHub Issue**
+>
+> **Objective:**
+> Your task is to generate a complete, professionally formatted GitHub Issue based on the details I provide below. The issue should be clear, actionable, and follow a structured format that makes it easy for any developer (human or AI) to understand the problem and the proposed solution.
+>
+> **Instructions:**
+> Use the information in the `[[...]]` sections to populate the template. Adhere strictly to the Markdown formatting.
+>
+> ---
+>
+> **[[ 1. Type of Issue: (Choose one: Bug Report / Feature Request / Refactor / Documentation) ]]**
+>
+> **[[ 2. Title of the Issue: (A clear, concise summary of the bug or feature) ]]**
+>
+> **[[ 3. Labels: (Provide a comma-separated list of relevant labels, e.g., `bug`, `enhancement`, `critical-ux`, `v1.2`, `help-wanted`, `clipboard`) ]]**
+>
+> **[[ 4. Problem Description / User Story: (Describe the problem from a user's perspective. What is happening that shouldn't be, or what is the user trying to achieve? If it's a bug, include steps to reproduce.) ]]**
+>
+> **[[ 5. Root Cause Analysis / Proposed Solution: (This is the "Plan-and-Solve" part. Explain the technical reason for the issue and outline a clear, step-by-step plan for the fix or implementation. Mention specific files, functions, or libraries that need to be added or modified.) ]]**
+>
+> **[[ 6. Acceptance Criteria: (Provide a short, bulleted list of testable outcomes that will prove the issue has been successfully resolved. How will we know it's "done"?) ]]**
+>
+> ---
+>
+> **Your Deliverable:**
+> Based on the information above, generate the complete text for the GitHub Issue, including the title and the fully formatted body.
+
+---
+
+### How to Use the Template: An Example
+
+Let's use our screenshot bug as an example. You would fill out the template like this:
+
+**[[ 1. Type of Issue: ]]**
+`Bug Report`
+
+**[[ 2. Title of the Issue: ]]**
+`Multimodal query fails to recognize image data from screenshots on the clipboard`
+
+**[[ 3. Labels: ]]**
+`bug`, `multimodal`, `clipboard`, `critical-ux`
+
+**[[ 4. Problem Description / User Story: ]]**
+`As a user, when I take a screenshot with the Windows Snipping Tool (Win+Shift+S), I expect to be able to use that image directly with Blink's multimodal feature. Currently, the feature only works if I save the screenshot as a file and copy the file. This breaks the workflow. Steps to reproduce: 1. Take a screenshot. 2. Verify it's on the clipboard by pasting in Paint. 3. Try to use the multimodal hotkey. 4. Observe that the query fails.`
+
+**[[ 5. Root Cause Analysis / Proposed Solution: ]]**
+`The root cause is that our clipboard manager only checks for file paths (CF_HDROP format) and text. It does not check for raw image data (CF_DIB format). The solution is to refactor clipboard_manager.py to use the Pillow library's ImageGrab.grabclipboard() function to detect and handle image data directly. The check for image data must be prioritized before checking for file paths. The hotkey_manager.py then needs to be updated to handle this new 'image_data' type by Base64 encoding it and sending it to the LLM.`
+
+**[[ 6. Acceptance Criteria: ]]**
+`- After taking a screenshot with Win+Shift+S, using the multimodal hotkey successfully sends the image to the LLM.`
+`- Copying an image file from Explorer continues to work correctly.`
+`- The system correctly prioritizes screenshot data over any old file paths on the clipboard.`

package/assets/Legacy/5 The Escalation & Handoff Protocol.md

@@ -0,0 +1,97 @@
+### The "Escalation & Handoff" Protocol
+
+This protocol is a two-part process: first, you instruct the local agent to generate a "Damage Report," and second, you use that report to brief the Orchestrator.
+
+### Part 1: The "Damage Report" Meta-Prompt (For the Local IDE Agent)
+
+This is the reusable prompt you'll use to command the failing local agent to summarize its own failure. It's designed to be a direct, no-nonsense command.
+
+> **Prompt for Local IDE Agent: Generate an Escalation Handoff Report**
+>
+> **Objective:**
+> You are to cease your current task and generate a detailed "Escalation Handoff Report." I, the user, have determined that your current approach is not solving the problem, and I need to escalate this issue to a senior AI Orchestrator for a new strategy.
+>
+> Your task is to provide a concise, factual summary of the situation to give the Orchestrator immediate context.
+>
+> **Instructions:**
+> First, ensure you have undone any recent, uncommitted code changes related to this failed attempt. Then, generate a report in Markdown with the following sections:
+>
+> 1.  **Original Goal:**
+>     *   State the original task or GitHub Issue I asked you to work on. (e.g., "Implement the 'RAG from Folder' feature.")
+>
+> 2.  **Observed Failure / Error:**
+>     *   Provide the full, exact error message, traceback, or a clear description of the incorrect behavior you were producing.
+>     *   (e.g., `AttributeError: 'NoneType' object has no attribute 'search'`, or "The UI button is created but does not respond to clicks.")
+>
+> 3.  **Your (Failed) Approach:**
+>     *   Briefly summarize the implementation strategy you were attempting.
+>     *   (e.g., "I was trying to add a new method to `hotkey_manager.py` that directly calls the `chromadb` library.")
+>
+> 4.  **Key Files Involved:**
+>     *   Based on your attempt, create a bulleted list of the primary files you created or modified. This will be the list of files I need to provide to the Orchestrator.
+>     *   (e.g.,
+>         *   `src/hotkey_manager.py`
+>         *   `src/ui/settings_window.py`
+>         *   `src/rag_manager.py` (New File))
+>
+> 5.  **Your Best-Guess Diagnosis:**
+>     *   In one or two sentences, state your best hypothesis for *why* your approach failed.
+>     *   (e.g., "I believe the issue is a race condition, as the `chromadb` instance may not be fully initialized before the first query is attempted.")
+>
+> **Your Deliverable:**
+> Provide only the complete Markdown report. Do not attempt to solve the problem further.
+
+---
+
+### Part 2: The "SOS" Prompt (For the AI Orchestrator)
+
+Once the local agent has generated the "Escalation Handoff Report," you will use this second prompt to bring the Orchestrator up to speed.
+
+> **Prompt for AI Orchestrator: Debugging Escalation & Strategic Reroute**
+>
+> **Objective:**
+> We have encountered a critical bug during implementation that the local in-IDE agent was unable to solve. I have escalated the issue to you for a strategic review and a new plan of attack.
+>
+> Your task is to analyze the situation, diagnose the root cause, and provide a new, corrected "Plan-and-Solve" implementation plan.
+>
+> ---
+>
+> **Part 1: The Escalation Handoff Report**
+> This report was generated by the local agent that failed the task. It contains the ground truth of the problem.
+>
+> ```markdown
+> [[ PASTE THE ENTIRE MARKDOWN REPORT FROM THE LOCAL AI HERE ]]
+> ```
+>
+> ---
+>
+> **Part 2: The Relevant Code**
+> Here are the full contents of the files identified in the report.
+>
+> ```python
+> # File: src/hotkey_manager.py
+> [[ PASTE FULL CONTENT OF hotkey_manager.py HERE ]]
+> ```
+> ```python
+> # File: src/ui/settings_window.py
+> [[ PASTE FULL CONTENT OF settings_window.py HERE ]]
+> ```
+>
+> *... (continue pasting the content of all files listed in the report) ...*
+>
+> ---
+>
+> **Part 3: Your Directive**
+>
+> 1.  **Analyze the Failure:** Based on the report and the provided code, give me a concise, one-paragraph diagnosis of the true root cause of the problem. Your high-level perspective may identify an architectural flaw the local agent missed.
+> 2.  **Formulate a New Plan:** Generate a complete, corrected "Plan-and-Solve" implementation plan to fix the bug and achieve the original goal. This plan should detail the exact code changes needed in the provided files.
+
+---
+
+### Why This Protocol is So Effective:
+
+*   **It Formalizes Failure:** It gives you a structured way to handle a common problem. Instead of getting frustrated, you're initiating a clear, logical protocol.
+*   **Empowers the Local Agent:** It gives the failing agent one final, useful task: documenting its own failure. This is often more valuable than letting it try the same wrong thing again.
+*   **Maximizes the Orchestrator's Strength:** The Orchestrator is a strategist. This protocol feeds it exactly what a strategist needs: a clear goal, a report of what failed, and the raw data (the code). It can then do what it does best: see the bigger picture and devise a better plan.
+
+You've now designed a complete, end-to-end "Takomi" workflow, covering everything from project genesis to mid-project debugging escalations. This is an incredibly sophisticated and powerful way to work with multiple AI agents.

package/assets/Legacy/8 The Seamless Migration Meta-Prompt (Your Reusable Tool).md

@@ -0,0 +1,38 @@
+### The "Seamless Migration" Meta-Prompt (Your Reusable Tool)
+
+> **Prompt for AI Orchestrator: Generate a "State Snapshot" Handoff Prompt**
+>
+> **Objective:**
+> Your task is to generate a special "State Snapshot" prompt. I am at the end of a long and productive chat session with you and need to migrate our entire project context, our collaborative dynamic, and your specific persona to a new, fresh chat session.
+>
+> The output of this prompt will be the *first thing* I send to the new AI in the new chat.
+>
+> **Instructions:**
+> Use the information I provide below to synthesize a comprehensive, first-person handoff prompt. The prompt should be written from **your perspective** (the AI Orchestrator) as if you are briefing your successor.
+>
+> ---
+>
+> **[[ 1. Our Personas & Vibe: ]]**
+> *   **Your Persona:** *e.g., "The AI Orchestrator. You act as a senior architect, project manager, and coding partner. Your tone is professional but enthusiastic, using a 'Gen Z' or 'Takomi' style where appropriate."*
+> *   **My Persona:** *e.g., "The Human Lead / Visionary. I provide the ideas, feedback, and final decisions. You treat me as a capable partner."*
+> *   **Our Dynamic:** *e.g., "A fast-paced, collaborative partnership. We use a 'Plan-and-Solve' methodology and create GitHub issues to track our work."*
+>
+> **[[ 2. Project Core Details: ]]**
+> *   **Project Name:** *e.g., "Blink"*
+> *   **Elevator Pitch:** *e.g., "A system-wide AI assistant for Windows that allows users to query an LLM from any application via a hotkey."*
+> *   **Tech Stack:** *e.g., "Python, PyQt6, PyInstaller, Inno Setup."*
+>
+> **[[ 3. The Project Journey (Key Milestones & "War Stories"): ]]**
+> *   (Provide a bulleted list of the major technical hurdles we overcame. This is the most important part.)
+> *   *e.g., "- Solved a series of complex 'Direct Stream' bugs, from race conditions to input saturation, finally landing on a 'Metronome' clipboard-paste solution."*
+> *   *e.g., "- Designed and built a professional multi-page installer with Inno Setup, including custom UI and intelligent dependency handling (Tesseract)."*
+> *   *e.g., "- Implemented advanced features like conversational memory, multimodal input, and a 'First Run' intelligent setup wizard."*
+>
+> **[[ 4. Current Status & Immediate Next Steps: ]]**
+> *   **Last Accomplishment:** *e.g., "We just finalized the plan for the v1.0.1 release, including creating a professional README with demo GIFs and setting up the GitHub Releases page."*
+> *   **Next on the Roadmap:** *e.g., "The immediate next steps are to implement the advanced features we've documented in our GitHub Issues, such as 'Context Compression' and 'Rule Re-injection'."*
+>
+> ---
+>
+> **Your Deliverable:**
+> Synthesize all of the above into a single, comprehensive handoff prompt. It must be written from your first-person perspective and instruct the new AI to adopt your persona and state immediately.

package/assets/Legacy/9 The Reverse Genesis Protocol.md

@@ -0,0 +1,75 @@
+This is the protocol for onboarding your AI Orchestrator onto an existing project. It's a multi-stage process that uses different AI agents for what they're best at.
+
+**Phase 1: Ground Truth Reconnaissance (Using your local In-IDE AI)**
+
+Your local AI (like Cline, Copilot with context, etc.) is the perfect "recon squad" because it can directly "read" your entire codebase. You will use it to gather the raw intelligence needed for the Orchestrator.
+
+**Your Prompt to the Local AI (The "Recon Prompt"):**
+
+> **Objective:** Analyze the entire codebase in this repository and generate a comprehensive "Project Autopsy Report" in Markdown. Your goal is to reverse-engineer the project's architecture, conventions, and current state.
+>
+> **Instructions:**
+> Scan every relevant file and produce a report with the following sections:
+>
+> 1.  **Project Elevator Pitch:** Based on the code and any existing documentation, what is the one-sentence purpose of this application?
+> 2.  **Core Technology Stack:** List the primary languages, frameworks, and key libraries you can identify.
+> 3.  **Inferred Architecture:** Describe the architectural pattern you observe (e.g., "Modular Python with a central `hotkey_manager`," "Layered architecture with UI, business logic, and data layers").
+> 4.  **Key Modules & Responsibilities:** Create a Markdown table listing the most important files/modules and your inferred one-sentence description of their role.
+> 5.  **Inferred Coding Conventions:** Analyze the code and describe the observed conventions:
+>     *   **Naming:** `snake_case`, `PascalCase`, etc.
+>     *   **Formatting:** Is it consistent with a known formatter like Black or PEP 8?
+>     *   **Error Handling:** What is the common pattern? (`try...except` blocks, custom exceptions, etc.)
+> 6.  **Dependency Analysis:** Generate the command needed to list all dependencies (e.g., `cat requirements.txt`).
+> 7.  **Potential Entry Points:** Identify the likely main entry point of the application (e.g., `main.py`).
+
+**The Outcome:** You will now have a detailed, factual document—the "Autopsy Report"—that describes the *current state* of the project. This is the ground truth.
+
+---
+
+### Phase 2: Strategic Briefing (Creating the Orchestrator's "Brain")
+
+Now you switch to your high-level AI Orchestrator. You will combine the "Autopsy Report" with your *new goals* to create the final, powerful onboarding prompt.
+
+**Your Prompt to the AI Orchestrator (The "Mission Briefing" Prompt):**
+
+> **Objective:** Assimilate the following project information and become the dedicated AI Orchestrator for this ongoing project. Your task is to understand the existing codebase and then help me plan and execute new features.
+>
+> ---
+>
+> **Part 1: The "Project Autopsy Report" (Ground Truth)**
+> This report was generated by a local AI that scanned the entire codebase. This is what we know about the project as it exists today.
+>
+> ```markdown
+> [[ PASTE THE ENTIRE MARKDOWN OUTPUT FROM YOUR LOCAL AI HERE ]]
+> ```
+>
+> ---
+>
+> **Part 2: The New Mission (My Goals)**
+> Now that you understand the current state, here is what I have been tasked with building.
+>
+> *   **Primary Goal:** *e.g., "To implement a new 'RAG from Folder' feature that allows the app to answer questions based on a user's local documents."*
+> *   **Key New Features (as GitHub Issues):**
+>     *   **[Feature] Create a UI for folder selection in the settings window.** *User story: As a user, I want to be able to select a folder on my computer that Blink will use as a knowledge base.*
+>     *   **[Feature] Implement a local vector store using ChromaDB.** *User story: As a user, I want the contents of my selected folder to be indexed into a persistent local database for fast retrieval.*
+>     *   **[Feature] Integrate RAG into the LLM query pipeline.** *User story: As a user, when I ask a question, Blink should first search my documents for relevant context and then inject that context into the prompt sent to the LLM.*
+>
+> ---
+>
+> **Part 3: Your Directive**
+>
+> You are now the AI Orchestrator for this project.
+>
+> 1.  **Acknowledge Assimilation:** Confirm that you have understood the existing codebase via the Autopsy Report and my new mission.
+> 2.  **Adopt the Vibe:** Based on the inferred conventions, adopt the project's "coding vibe."
+> 3.  **Begin Planning:** Your first task is to take my first new feature, **"Create a UI for folder selection in the settings window,"** and generate a full "Plan-and-Solve" implementation plan for it, respecting the existing architecture.
+
+---
+
+### Why This "Reverse Genesis" Protocol is So Powerful
+
+*   **Separation of Concerns:** It uses the right AI for the right job. The local AI is a "scanner," excellent at low-level code analysis. The Orchestrator is a "strategist," excellent at high-level planning.
+*   **Grounds the Orchestrator in Reality:** By providing the Autopsy Report, you prevent the Orchestrator from "hallucinating" or suggesting solutions that don't fit the existing patterns. It is forced to work within the constraints of the project as it is.
+*   **Combines "What Is" with "What's Next":** This process seamlessly bridges the gap between understanding the past (the existing code) and planning for the future (your new tasks).
+
+You were right—the prompt has to be dope. And the best way to make it dope is to feed it high-quality, pre-digested intelligence from the codebase itself. This protocol is your key to becoming an effective contributor to any project, right from day one.