chore: prepare release v0.8.8

Author: Tim Sinaeve

docs/FUNCTIONAL_MANUAL.md

@@ -29,7 +29,7 @@ The resizable left panel is your main navigation and organization area.
 - **Search:** A search bar at the top lets you filter your documents and folders. It instantly checks titles while also running a background full-text search across document bodies, returning contextual snippets with the matched terms highlighted so you can quickly confirm relevance.
 - **Documents List:** A hierarchical tree view of all your documents and folders.
     - **Action Toolbar:** A toolbar at the top of the list provides icon buttons to quickly create a new document, create a new root folder, create a new document from a template, expand/collapse all folders, and toggle the active document's lock state.
-    - **Row Quick Actions:** Hover or focus any row to reveal a compact strip of icons for frequent tasks—duplicate, export, rename, lock/unlock (for editable repositories), and more. The controls float on the right edge so the row height stays consistent and labels retain their full width.
+    - **Row Quick Actions:** Hover or focus any row to reveal a compact strip of icons for the most common tasks—duplicate, export, rename, lock/unlock (for editable repositories), and more. The quick actions float over the right edge so the row keeps its full height and the title stays readable.
     - **Folders:** Can be expanded or collapsed.
 - **Documents:** Individual document files. Selecting a document opens it in the Main Content Area.
 - **Emoji Titles:** Document rows display emoji prefixes when present, and the rename input includes an emoji picker you can open from the context menu.
@@ -136,8 +136,37 @@ The document editor is powered by Monaco, the same editor core used in VS Code,
 Import PDFs by dragging `.pdf` files from your operating system into the sidebar, using the "Import" options in context menus, or converting clipboard data through **New from Clipboard** when it contains PDF bytes or data URLs. Opening a PDF switches the editor to **Preview Only** mode automatically so you can focus on the embedded viewer. The preview displays the document in an inline reader with Chromium's native toolbar (page navigation, zoom, and print controls) and honors keyboard shortcuts exposed by the viewer. DocForge synchronizes the viewer with the global preview zoom so the zoom buttons, scroll wheel shortcuts, and reset commands behave consistently across file types. Because PDFs are stored as binary data, editing is disabled by default; switching to the editor view will show the raw payload, and changing it can corrupt the file.
 
 #### Image Documents
-
-PNG, JPEG, GIF, BMP, WEBP, and SVG assets are detected when you import them from disk, drop them into the sidebar, or pipe image data through **New from Clipboard**. Image documents also open directly in **Preview Only** mode. The preview uses DocForge's zoom and pan surface so you can scroll, drag to reposition, double-click to zoom, or press the on-screen controls to reset the view. Image metadata—such as pixel dimensions and MIME type—appears in the status bar while the preview is active, and the renderer clamps the image inside the workspace with padding so large assets remain manageable. Editing the underlying binary/text data is optional but discouraged unless you are intentionally replacing the encoded image contents.
+ 
+ PNG, JPEG, GIF, BMP, WEBP, and SVG assets are detected when you import them from disk, drop them into the sidebar, or pipe image data through **New from Clipboard**. Image documents also open directly in **Preview Only** mode. The preview uses DocForge's zoom and pan surface so you can scroll, drag to reposition, double-click to zoom, or press the on-screen controls to reset the view. Image metadata—such as pixel dimensions and MIME type—appears in the status bar while the preview is active.
+ 
+ **Interacting with Images**:
+ - **Pasting**: When an image document is open and unlocked, you can paste an image directly from your clipboard (**Ctrl+V**) to replace its content.
+ - **Drag-and-Drop**: Drop any image file from your computer onto the open image editor to update the document.
+ - **Manual Creation**: Create a new document, change its language to **Image**, and then paste or drop your content.
+ 
+ Editing the underlying binary/text data is optional but discouraged unless you are intentionally replacing the encoded image contents.
+
+#### RAG (Chat with Workspace)
+
+The "Chat with Workspace" feature allows you to query your entire collection of documents using a local AI model.
+
+- **Indexing**: Before you can chat, DocForge needs to index your workspace. This process creates a semantic representation of your documents, allowing the AI to find relevant context even if the exact keywords don't match.
+- **Configurable Retrieval**: In Settings, you can adjust the **RAG Similarity Threshold**. A lower value (e.g., 0.8) makes the search more restrictive, returning only highly relevant matches, while a higher value (e.g., 1.5) returns more context.
+- **Context Limit**: You can configure the chat to analyze up to **500 documents** at once for deep workspace insights.
+- **Source Attribution**: When the AI answers a question, it lists the specific documents it used as context. These sources are streamed immediately as soon as the search completes.
+- **Smart Privacy**: If the AI determines that none of the retrieved documents contain the answer to your question, the source list is automatically hidden to keep the chat interface clean.
+
+#### Agentic Chat & Workspace Orchestration
+
+Agent Mode transforms the chat assistant from a passive information retriever into an active workspace participant.
+
+- **Tool Calling**: When Agent Mode is enabled, the AI can proactively use tools to interact with your workspace. This includes:
+    - **Document Management**: Creating new documents or folders, renaming existing ones, and moving files between directories.
+    - **Content Refactoring**: Reading document contents and performing bulk edits or restructurings based on your instructions.
+    - **Script Execution**: Running Python, Shell, or PowerShell scripts to process data, generate files, or automate complex workflows.
+- **Action Approval Gate**: For security, all sensitive actions (like deleting documents or running scripts) can be configured to require your manual approval. A glassmorphic modal will appear showing exactly what the AI intends to do, including any script code or move parameters, allowing you to approve or deny the request before it executes.
+- **Thoughtful Execution**: The agent can perform multi-step tasks—for example, it can list all documents in a folder, search for specific patterns, and then create a summary document based on its findings—all in a single conversation turn.
+- **Deep Integration**: The agent has direct access to the same document hooks as the GUI, ensuring that its actions are consistent with the application's state and history.
 
 #### Python Execution Panel
 

docs/README.md

@@ -35,6 +35,9 @@ DocForge is a desktop application designed to streamline the process of creating
 - **Comprehensive Action Logging**: Every user action is logged, and the logger panel now supports range selections, modifier-aware drag selection, and configurable copy-to-clipboard exports with or without timestamps and levels.
 - **Offline First:** All your data is stored locally on your machine.
 - **Auto-Update:** Control automatic startup checks, opt into pre-release builds, and trigger manual "Check for Updates" scans that report success or errors inline.
+- **RAG-Powered "Chat with Workspace":** Semantic search across your entire workspace. Adjust the similarity threshold to tune the relevance of retrieved context and analyze up to 500 documents at once.
+- **Smart Source Attribution:** Chat responses include streamed sources that automatically hide if no relevant information is found, keeping your context clean and focused.
+- **Enhanced Image Clipboard & Drag-Drop:** Create image documents directly from the clipboard, or update existing image nodes by simply pasting (**Ctrl+V**) or dropping an image file onto the editor.
 - **Resizable Layout:** The sidebar, templates panel, and logger panel are all fully resizable to customize your workspace.
 
 ## Getting Started

docs/TECHNICAL_MANUAL.md

@@ -172,6 +172,6 @@ DocForge integrates GitHub Spec Kit to manage feature planning artifacts alongsi
 
 -   **CLI tooling:** Install the Specify CLI with `uv tool install specify-cli --from git+https://github.com/github/spec-kit.git` and run `specify check` to validate prerequisites.
 -   **Project scripts:** Helper scripts live under `.specify/scripts/` for creating feature folders, updating agent context, and enforcing executable permissions.
--   **Spec storage:** Feature specifications, plans, and task lists reside in numbered folders under `specs/`. See [`specs/README.md`](../specs/README.md) for the canonical workflow.
+-   **Spec storage:** Feature specifications, plans, and task lists reside in numbered folders under `specs/`. See [`specs/README.md`](./specs/README.md) for the canonical workflow.
 -   **Agent prompts:** Slash-command prompt files for AI assistants are stored in `.github/prompts/`, enabling `/speckit.*` commands inside supported tools.
 -   **Governance:** The living constitution at `.specify/memory/constitution.md` defines development principles, quality gates, and review expectations for the project.

docs/VERSION_LOG.md

@@ -1,4 +1,24 @@
-# Version Log
+## v0.8.8 - The Agentic Workspace Update
+
+### ✨ Features
+
+-   **Agentic Chat & Workspace Orchestrator**:
+    *   Transformed the chat panel from a passive RAG assistant into an active **Workspace Agent**.
+    *   **Autonomous Operations**: The AI can now create, rename, move, and edit documents and folders directly through natural language commands.
+    *   **Script Orchestration**: The agent can write and execute **Python**, **Shell**, and **PowerShell** scripts to automate complex data processing or system tasks.
+    *   **Multi-Step Reasoning**: Capable of performing complex workflows (e.g., "Find all documents mentioning X, then move them to a new folder called Y") in a single conversation.
+-   **Security & Action Approval**:
+    *   Implemented a high-fidelity **Action Approval Modal** with a glassmorphic design.
+    *   Configurable safety gates: Users can choose to require manual approval for all agent actions, especially destructive operations or script executions.
+-   **UI/UX Polish**:
+    *   **Tool Execution Visibility**: Added specialized status indicators and animated icons to show when the AI is "thinking" or "using a tool."
+    *   **Syntax-Highlighted Tool Results**: Results from scripts and workspace operations are now rendered in a dedicated terminal-style card within the chat history.
+    *   **Enhanced Settings**: Added a new "AI Chat" settings section to toggle Agent Mode and Approval requirements.
+
+### 🐛 Fixes
+
+-   **Chat Stability**: Fixed several syntax and state synchronization errors in the chat panel that could cause crashes during long-running tool executions.
+-   **Tag Balance**: Resolved various build-breaking JSX tag mismatches in the Chat UI.
 
 ## v0.8.7 - The RAG & Clipboard Image Update
 

docs/releases/v0.8.8.md

@@ -0,0 +1,26 @@
+# Release Notes - v0.8.8
+
+## The Agentic Workspace Update
+
+This release transforms the chat panel into an active **Workspace Agent** capable of autonomous operations, script orchestration, and multi-step reasoning.
+
+### ✨ Features
+
+#### Agentic Chat & Workspace Orchestrator
+- **Autonomous Operations**: The AI can now create, rename, move, and edit documents and folders directly through natural language commands.
+- **Script Orchestration**: The agent can write and execute **Python**, **Shell**, and **PowerShell** scripts to automate complex data processing or system tasks.
+- **Multi-Step Reasoning**: Capable of performing complex workflows (e.g., "Find all documents mentioning X, then move them to a new folder called Y") in a single conversation.
+
+#### Security & Action Approval
+- **Action Approval Modal**: Implemented a high-fidelity glassmorphic modal for reviewing and approving agent actions.
+- **Safety Gates**: Configurable settings allow users to require manual approval for all agent actions, especially destructive operations or script executions.
+
+#### UI/UX Polish
+- **Tool Execution Visibility**: Added specialized status indicators and animated icons to show when the AI is "thinking" or "using a tool."
+- **Syntax-Highlighted Tool Results**: Results from scripts and workspace operations are rendered in dedicated terminal-style cards within the chat history.
+- **Enhanced Settings**: A new "AI Chat" settings section allows toggling Agent Mode and Approval requirements.
+
+### 🐛 Fixes
+
+- **Chat Stability**: Fixed several syntax and state synchronization errors in the chat panel that could cause crashes during long-running tool executions.
+- **Tag Balance**: Resolved various build-breaking JSX tag mismatches in the Chat UI.