feat(v2): complete multi-LLM providers, TUI redesign, and advanced agent features

Multi-LLM Provider Support:
- Add llm-core crate with LlmProvider trait abstraction
- Implement Anthropic Claude API client with streaming
- Implement OpenAI API client with streaming
- Add token counting with SimpleTokenCounter and ClaudeTokenCounter
- Add retry logic with exponential backoff and jitter

Borderless TUI Redesign:
- Rewrite theme system with terminal capability detection (Full/Unicode256/Basic)
- Add provider tabs component with keybind switching [1]/[2]/[3]
- Implement vim-modal input (Normal/Insert/Visual/Command modes)
- Redesign chat panel with timestamps and streaming indicators
- Add multi-provider status bar with cost tracking
- Add Nerd Font icons with graceful ASCII fallbacks
- Add syntax highlighting (syntect) and markdown rendering (pulldown-cmark)

Advanced Agent Features:
- Add system prompt builder with configurable components
- Enhance subagent orchestration with parallel execution
- Add git integration module for safe command detection
- Add streaming tool results via channels
- Expand tool set: AskUserQuestion, TodoWrite, LS, MultiEdit, BashOutput, KillShell
- Add WebSearch with provider abstraction

Plugin System Enhancement:
- Add full agent definition parsing from YAML frontmatter
- Add skill system with progressive disclosure
- Wire plugin hooks into HookManager

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

crates/platform/permissions/src/lib.rs

@@ -16,6 +16,12 @@ pub enum Tool {
     Task,
     TodoWrite,
     Mcp,
+    // New tools
+    MultiEdit,
+    LS,
+    AskUserQuestion,
+    BashOutput,
+    KillShell,
 }
 
 #[derive(Debug, Clone, Copy, PartialEq, Eq, Serialize, Deserialize)]
@@ -123,23 +129,27 @@ impl PermissionManager {
         match self.mode {
             Mode::Plan => match tool {
                 // Read-only tools are allowed in plan mode
-                Tool::Read | Tool::Grep | Tool::Glob | Tool::NotebookRead => {
+                Tool::Read | Tool::Grep | Tool::Glob | Tool::NotebookRead | Tool::LS => {
                     PermissionDecision::Allow
                 }
+                // User interaction and session state tools allowed
+                Tool::AskUserQuestion | Tool::TodoWrite => PermissionDecision::Allow,
                 // Everything else requires asking
                 _ => PermissionDecision::Ask,
             },
             Mode::AcceptEdits => match tool {
                 // Read operations allowed
-                Tool::Read | Tool::Grep | Tool::Glob | Tool::NotebookRead => {
+                Tool::Read | Tool::Grep | Tool::Glob | Tool::NotebookRead | Tool::LS => {
                     PermissionDecision::Allow
                 }
                 // Edit/Write operations allowed
-                Tool::Edit | Tool::Write | Tool::NotebookEdit => PermissionDecision::Allow,
+                Tool::Edit | Tool::Write | Tool::NotebookEdit | Tool::MultiEdit => PermissionDecision::Allow,
                 // Bash and other dangerous operations still require asking
                 Tool::Bash | Tool::WebFetch | Tool::WebSearch | Tool::Mcp => PermissionDecision::Ask,
+                // Background shell operations same as Bash
+                Tool::BashOutput | Tool::KillShell => PermissionDecision::Ask,
                 // Utility tools allowed
-                Tool::TodoWrite | Tool::SlashCommand | Tool::Task => PermissionDecision::Allow,
+                Tool::TodoWrite | Tool::SlashCommand | Tool::Task | Tool::AskUserQuestion => PermissionDecision::Allow,
             },
             Mode::Code => {
                 // Everything allowed in code mode