📝 Expand README with complete feature documentation

Document previously undocumented Studio features: - Real-time streaming and token usage tracking - Full mouse support (click, scroll, navigate) - Clipboard integration with visual feedback - File search modal (Ctrl+F) - Explore mode with semantic blame feature - In-app modals table (Settings, File Search, Preset/Emoji selectors) - New --raw flag for markdown output commands Also adds Explore mode controls and expands Commit mode keyboard shortcuts with preset (p) and emoji (m) selector keys.

Author: hyperb1iss

CLAUDE.md

@@ -117,31 +117,34 @@ Studio is built on a **pure reducer pattern** for predictable state management:
 ### Key Components
 
 **Events (`events.rs`):**
+
 - `StudioEvent` enum captures all possible state transitions
 - Events are dispatched from handlers and async tasks
 - Clear, traceable data flow
 
 **Reducer (`reducer.rs`):**
+
 - Pure function: `(state, event) → (state, effects)`
 - No I/O inside reducer—side effects returned as data
 - Enables testing, replay, debugging
 
 **Side Effects:**
+
 - `SpawnAgent { task }` — Start async agent execution
 - `LoadData { data_type, from_ref, to_ref }` — Load git data
 - `UpdateContent { content, update_type }` — Update displayed content
 - `StreamUpdate { tool_name, message }` — Show progress updates
 
 ### Studio Modes
 
-| Mode | Description | State Struct |
-|------|-------------|--------------|
-| **Explore** | Navigate codebase with AI insights | `ExploreMode` |
-| **Commit** | Generate/edit commit messages | `CommitMode` |
-| **Review** | AI-powered code reviews | `ReviewMode` |
-| **PR** | Pull request descriptions | `PRMode` |
-| **Changelog** | Structured changelog generation | `ChangelogMode` |
-| **Release Notes** | Release documentation | `ReleaseNotesMode` |
+| Mode  | Description  | State Struct  |
+| ----------------- | ---------------------------------- | ------------------ |
+| **Explore**  | Navigate codebase with AI insights | `ExploreMode`  |
+| **Commit**  | Generate/edit commit messages  | `CommitMode`  |
+| **Review**  | AI-powered code reviews  | `ReviewMode`  |
+| **PR**  | Pull request descriptions  | `PRMode`  |
+| **Changelog**  | Structured changelog generation  | `ChangelogMode`  |
+| **Release Notes** | Release documentation  | `ReleaseNotesMode` |
 
 ### Chat Integration
 
@@ -159,6 +162,7 @@ pub struct ChatState {
 ```
 
 Iris can update content directly through tools:
+
 - `update_commit` — Modify commit message
 - `update_pr` — Modify PR description
 - `update_review` — Modify review content
@@ -169,41 +173,41 @@ Iris can update content directly through tools:
 
 Each capability is defined in `src/agents/capabilities/*.toml`:
 
-| Capability | Output Type | Description |
-|------------|-------------|-------------|
-| `commit` | `GeneratedMessage` | Commit messages with emoji/title/body |
-| `review` | `MarkdownReview` | Multi-dimensional code analysis |
-| `pr` | `MarkdownPullRequest` | Pull request descriptions |
-| `changelog` | `MarkdownChangelog` | Keep a Changelog format |
-| `release_notes` | `MarkdownReleaseNotes` | Release documentation |
-| `chat` | Varies | Interactive conversation |
+| Capability  | Output Type  | Description  |
+| --------------- | ---------------------- | ------------------------------------- |
+| `commit`  | `GeneratedMessage`  | Commit messages with emoji/title/body |
+| `review`  | `MarkdownReview`  | Multi-dimensional code analysis  |
+| `pr`  | `MarkdownPullRequest`  | Pull request descriptions  |
+| `changelog`  | `MarkdownChangelog`  | Keep a Changelog format  |
+| `release_notes` | `MarkdownReleaseNotes` | Release documentation  |
+| `chat`  | Varies  | Interactive conversation  |
 
 ### Tools Available to Iris
 
-| Tool | Purpose |
-|------|---------|
-| `git_diff(detail, from, to)` | Get changes with relevance scores |
-| `git_log(count)` | Recent commit history for style reference |
-| `git_status()` | Repository status |
-| `git_changed_files()` | List of changed files |
-| `file_analyzer()` | Deep file analysis (content, metadata) |
-| `code_search()` | Search for patterns, functions, classes |
-| `workspace()` | Iris's notes and task tracking |
-| `project_docs(doc_type)` | Read README, AGENTS.md, CLAUDE.md |
-| `parallel_analyze()` | Concurrent subagent processing |
-| `update_commit()` | Chat: update commit message |
-| `update_pr()` | Chat: update PR description |
-| `update_review()` | Chat: update review |
+| Tool  | Purpose  |
+| ---------------------------- | ----------------------------------------- |
+| `git_diff(detail, from, to)` | Get changes with relevance scores  |
+| `git_log(count)`  | Recent commit history for style reference |
+| `git_status()`  | Repository status  |
+| `git_changed_files()`  | List of changed files  |
+| `file_analyzer()`  | Deep file analysis (content, metadata)  |
+| `code_search()`  | Search for patterns, functions, classes  |
+| `workspace()`  | Iris's notes and task tracking  |
+| `project_docs(doc_type)`  | Read README, AGENTS.md, CLAUDE.md  |
+| `parallel_analyze()`  | Concurrent subagent processing  |
+| `update_commit()`  | Chat: update commit message  |
+| `update_pr()`  | Chat: update PR description  |
+| `update_review()`  | Chat: update review  |
 
 ### Context Strategy
 
 Iris adapts her approach based on changeset size:
 
-| Scenario | Strategy |
-|----------|----------|
-| Small (<10 files, <100 lines each) | Full context for all files |
-| Medium (10-20 files) | Relevance scoring to prioritize |
-| Large (20+ files) | Parallel subagent analysis |
+| Scenario  | Strategy  |
+| ---------------------------------- | ------------------------------- |
+| Small (<10 files, <100 lines each) | Full context for all files  |
+| Medium (10-20 files)  | Relevance scoring to prioritize |
+| Large (20+ files)  | Parallel subagent analysis  |
 
 ### Adding a New Capability
 
@@ -227,13 +231,13 @@ Instructions for Iris...
 
 Iris produces structured responses (all in `src/types/`):
 
-| Type | Format | Description |
-|------|--------|-------------|
-| `GeneratedMessage` | JSON | `{ emoji, title, message }` |
-| `MarkdownPullRequest` | Markdown | `{ content: String }` |
-| `MarkdownReview` | Markdown | `{ content: String }` |
-| `MarkdownChangelog` | Markdown | `{ content: String }` |
-| `MarkdownReleaseNotes` | Markdown | `{ content: String }` |
+| Type  | Format  | Description  |
+| ---------------------- | -------- | --------------------------- |
+| `GeneratedMessage`  | JSON  | `{ emoji, title, message }` |
+| `MarkdownPullRequest`  | Markdown | `{ content: String }`  |
+| `MarkdownReview`  | Markdown | `{ content: String }`  |
+| `MarkdownChangelog`  | Markdown | `{ content: String }`  |
+| `MarkdownReleaseNotes` | Markdown | `{ content: String }`  |
 
 The `Markdown*` types use a simple wrapper, letting the LLM drive format while capability TOMLs provide guidelines.
 
@@ -243,23 +247,23 @@ Git-Iris follows the **SilkCircuit Neon** color palette for a cohesive, electric
 
 ### Color Palette
 
-| Color | Hex | RGB | Usage |
-|-------|-----|-----|-------|
-| Electric Purple | `#e135ff` | `(225, 53, 255)` | Active modes, markers, emphasis |
-| Neon Cyan | `#80ffea` | `(128, 255, 234)` | Paths, interactions, focus |
-| Coral | `#ff6ac1` | `(255, 106, 193)` | Hashes, numbers, constants |
-| Electric Yellow | `#f1fa8c` | `(241, 250, 140)` | Warnings, timestamps |
-| Success Green | `#50fa7b` | `(80, 250, 123)` | Success, confirmations |
-| Error Red | `#ff6363` | `(255, 99, 99)` | Errors, danger |
+| Color  | Hex  | RGB  | Usage  |
+| --------------- | --------- | ----------------- | ------------------------------- |
+| Electric Purple | `#e135ff` | `(225, 53, 255)`  | Active modes, markers, emphasis |
+| Neon Cyan  | `#80ffea` | `(128, 255, 234)` | Paths, interactions, focus  |
+| Coral  | `#ff6ac1` | `(255, 106, 193)` | Hashes, numbers, constants  |
+| Electric Yellow | `#f1fa8c` | `(241, 250, 140)` | Warnings, timestamps  |
+| Success Green  | `#50fa7b` | `(80, 250, 123)`  | Success, confirmations  |
+| Error Red  | `#ff6363` | `(255, 99, 99)`  | Errors, danger  |
 
 ### Backgrounds
 
-| Surface | Hex | Usage |
-|---------|-----|-------|
-| Base | `#121218` | Main background |
-| Panel | `#181820` | Individual panels |
-| Highlight | `#2d283c` | Selections |
-| Code | `#1e1e28` | Code blocks |
+| Surface  | Hex  | Usage  |
+| --------- | --------- | ----------------- |
+| Base  | `#121218` | Main background  |
+| Panel  | `#181820` | Individual panels |
+| Highlight | `#2d283c` | Selections  |
+| Code  | `#1e1e28` | Code blocks  |
 
 ### Implementation
 
@@ -325,11 +329,11 @@ git-iris config --provider anthropic --model claude-sonnet-4-5-20250929
 
 ### Provider Details
 
-| Provider | Default Model | Fast Model | Context |
-|----------|---------------|------------|---------|
-| openai | gpt-5.1 | gpt-5.1-mini | 128K |
-| anthropic | claude-sonnet-4-5-20250929 | claude-haiku-4-5-20251001 | 200K |
-| google | gemini-3-pro-preview | gemini-2.5-flash | 1M |
+| Provider  | Default Model  | Fast Model  | Context |
+| --------- | -------------------------- | ------------------------- | ------- |
+| openai  | gpt-5.1  | gpt-5.1-mini  | 128K  |
+| anthropic | claude-sonnet-4-5-20250929 | claude-haiku-4-5-20251001 | 200K  |
+| google  | gemini-3-pro-preview  | gemini-2.5-flash  | 1M  |
 
 ## Key Design Decisions
 

CONFIG.md

@@ -14,11 +14,11 @@ The configuration file is organized into these main sections:
 
 ### Global Settings
 
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
-| `use_gitmoji` | Boolean | `false` | Enable Gitmoji in commit messages |
-| `custom_instructions` | String | `""` | Custom instructions included in all LLM prompts |
-| `instruction_preset` | String | `"default"` | Default preset for AI instructions |
+| Option  | Type  | Default  | Description  |
+| --------------------- | ------- | ----------- | ----------------------------------------------- |
+| `use_gitmoji`  | Boolean | `false`  | Enable Gitmoji in commit messages  |
+| `custom_instructions` | String  | `""`  | Custom instructions included in all LLM prompts |
+| `instruction_preset`  | String  | `"default"` | Default preset for AI instructions  |
 
 **Examples:**
 
@@ -33,8 +33,8 @@ instruction_preset = "conventional"
 
 ### Default Provider
 
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
+| Option  | Type  | Default  | Description  |
+| ------------------ | ------ | ---------- | ------------------------------- |
 | `default_provider` | String | `"openai"` | The default LLM provider to use |
 
 **Example:**
@@ -47,23 +47,23 @@ default_provider = "anthropic"
 
 Each provider has its own subtable under `[providers]` with these fields:
 
-| Field | Type | Required | Description |
-|-------|------|----------|-------------|
-| `api_key` | String | Yes | The provider's API key |
-| `model` | String | No | Primary model for complex analysis tasks |
-| `fast_model` | String | No | Fast model for simple tasks (status updates, parsing) |
-| `additional_params` | Table | No | Additional provider-specific parameters |
-| `custom_token_limit` | Integer | No | Custom token limit override |
+| Field  | Type  | Required | Description  |
+| -------------------- | ------- | -------- | ----------------------------------------------------- |
+| `api_key`  | String  | Yes  | The provider's API key  |
+| `model`  | String  | No  | Primary model for complex analysis tasks  |
+| `fast_model`  | String  | No  | Fast model for simple tasks (status updates, parsing) |
+| `additional_params`  | Table  | No  | Additional provider-specific parameters  |
+| `custom_token_limit` | Integer | No  | Custom token limit override  |
 
 ## 🤖 Supported Providers
 
 Git-Iris supports three LLM providers:
 
-| Provider | Default Model | Fast Model | Context Window | API Key Env |
-|----------|---------------|------------|----------------|-------------|
-| **openai** | gpt-5.1 | gpt-5.1-mini | 128,000 | `OPENAI_API_KEY` |
-| **anthropic** | claude-sonnet-4-5-20250929 | claude-haiku-4-5-20251001 | 200,000 | `ANTHROPIC_API_KEY` |
-| **google** | gemini-3-pro-preview | gemini-2.5-flash | 1,000,000 | `GOOGLE_API_KEY` |
+| Provider  | Default Model  | Fast Model  | Context Window | API Key Env  |
+| ------------- | -------------------------- | ------------------------- | -------------- | ------------------- |
+| **openai**  | gpt-5.1  | gpt-5.1-mini  | 128,000  | `OPENAI_API_KEY`  |
+| **anthropic** | claude-sonnet-4-5-20250929 | claude-haiku-4-5-20251001 | 200,000  | `ANTHROPIC_API_KEY` |
+| **google**  | gemini-3-pro-preview  | gemini-2.5-flash  | 1,000,000  | `GOOGLE_API_KEY`  |
 
 > **Note:** The `claude` provider name is still supported as a legacy alias for `anthropic`.
 
@@ -157,13 +157,13 @@ git-iris project-config --print
 
 You can also configure Git-Iris using environment variables:
 
-| Variable | Description |
-|----------|-------------|
-| `OPENAI_API_KEY` | OpenAI API key |
-| `ANTHROPIC_API_KEY` | Anthropic API key |
-| `GOOGLE_API_KEY` | Google API key |
-| `GITIRIS_PROVIDER` | Default provider (for Docker/CI) |
-| `GITIRIS_API_KEY` | API key (for Docker/CI) |
+| Variable  | Description  |
+| ------------------- | -------------------------------- |
+| `OPENAI_API_KEY`  | OpenAI API key  |
+| `ANTHROPIC_API_KEY` | Anthropic API key  |
+| `GOOGLE_API_KEY`  | Google API key  |
+| `GITIRIS_PROVIDER`  | Default provider (for Docker/CI) |
+| `GITIRIS_API_KEY`  | API key (for Docker/CI)  |
 
 **Example (Docker/CI):**
 
@@ -179,13 +179,15 @@ docker run --rm -v "$(pwd):/git-repo" \
 Git-Iris includes built-in instruction presets for different styles:
 
 **General Presets:**
+
 - `default` — Standard professional style
 - `conventional` — Conventional Commits specification
 - `detailed` — More context and explanation
 - `concise` — Short and to-the-point
 - `cosmic` — Mystical, space-themed language ✨
 
 **Review-Specific Presets:**
+
 - `security` — Focus on security vulnerabilities
 - `performance` — Analyze performance optimizations
 - `architecture` — Evaluate design patterns
@@ -221,13 +223,13 @@ git-iris config --provider openai --token-limit 4000
 
 ## 🐛 Troubleshooting
 
-| Issue | Solution |
-|-------|----------|
-| **Authentication failed** | Verify API key is correct and has required permissions |
-| **Model not found** | Check you're using a supported model for your provider |
-| **Token limit exceeded** | Reduce `custom_token_limit` or use a smaller changeset |
-| **Slow responses** | Try a faster model with `--fast-model` |
-| **Debug issues** | Enable logging with `-l` or use `--debug` for agent details |
+| Issue  | Solution  |
+| ------------------------- | ----------------------------------------------------------- |
+| **Authentication failed** | Verify API key is correct and has required permissions  |
+| **Model not found**  | Check you're using a supported model for your provider  |
+| **Token limit exceeded**  | Reduce `custom_token_limit` or use a smaller changeset  |
+| **Slow responses**  | Try a faster model with `--fast-model`  |
+| **Debug issues**  | Enable logging with `-l` or use `--debug` for agent details |
 
 **Enable debug logging:**