release: v1.7.0

## Summary

This PR bundles a collection of new features and quality-of-life improvements identified during a Claude CLI 2.1.50 audit.

- **Tab status indicator** — Tab stays yellow until the greeting is responded to, then turns green. Fixed disconnect not resetting to grey. Closes #157
- **Auth status display** — New "Account" section in settings sidebar showing login status, email, org, API key source, and Hikari override indicator. Includes login/logout buttons. Closes #153
- **CLI version badge** — New "Supported" badge showing the highest audited CLI version, colour-coded green/amber/red based on installed vs supported version. Closes #154 (bump to 2.1.50)
- **Rate limit events** — `rate_limit_event` messages from the stream are now parsed and shown as amber `[rate-limit]` lines in the terminal instead of being silently dropped. Closes #155
- **"Prompt is too long" handling** — Detects this error in assistant messages and shows a ⚡ Compact Conversation button to send `/compact` directly. Closes #158
- **`last_assistant_message` in Agent Monitor** — Extracts the agent's final output from the `ToolResult` content block in the JSON stream and displays it as a snippet on completed agent cards. Closes #156
- **`--worktree` flag** — New "Worktree isolation" toggle in session settings passes `--worktree` to Claude Code. Hook events (`WorktreeCreate`/`WorktreeRemove`) are displayed as green `[worktree]` lines. Closes #152, Closes #150
- **ConfigChange hook events** — `[ConfigChange Hook]` stderr events are now displayed as cyan `[config]` lines instead of errors. Closes #151
- **`CLAUDE_CODE_DISABLE_1M_CONTEXT` toggle** — New "Disable 1M context" setting in session configuration injects this env var into the Claude process. Closes #154

## Test plan

- [ ] Tab status indicator: start a new session and verify the tab stays yellow until Claude responds to the greeting, then turns green
- [ ] Auth status: open settings and verify the Account section shows correct login info
- [ ] CLI version badge: verify the "Supported 2.1.50" badge shows green when CLI matches
- [ ] Rate limit events: unit tests cover parsing; amber `[rate-limit]` lines display correctly
- [ ] Compact button: unit tests cover detection; button renders correctly in terminal
- [ ] Agent Monitor: use the Task tool and verify completed agent cards show a message snippet
- [ ] Worktree: enable toggle, start session, verify `--worktree` flag appears in process args
- [ ] ConfigChange: hook events display as `[config]` lines rather than errors
- [ ] Disable 1M context: enable toggle, start session, verify `CLAUDE_CODE_DISABLE_1M_CONTEXT=1` in `/proc/<pid>/environ`

✨ This PR was created with help from Hikari~ 🌸

Reviewed-on: #159
Co-authored-by: Hikari <hikari@nhcarrigan.com>
Co-committed-by: Hikari <hikari@nhcarrigan.com>

CLAUDE.md

@@ -141,6 +141,37 @@ When developing new features, always add corresponding tests:
 
 The goal is to maintain our near-100% coverage as the codebase grows, so future refactoring and changes can be made with confidence!
 
+## Quality Assurance
+
+Before committing any changes, **always run the full test suite**:
+
+```bash
+./check-all.sh
+```
+
+This script runs all checks in the correct order:
+
+1. Frontend linting (ESLint)
+2. Frontend formatting (Prettier)
+3. Frontend type checking (svelte-check)
+4. Frontend tests with coverage (Vitest)
+5. Backend linting (Clippy with strict rules)
+6. Backend tests with coverage (cargo test + llvm-cov)
+
+**Important**: The script requires Node.js and Rust toolchains to be available:
+
+- **Node.js tools** (pnpm, npm): Source nvm first if needed: `source ~/.nvm/nvm.sh`
+- **Rust tools** (cargo, clippy): Should be in PATH via `~/.cargo/bin/`
+
+If `check-all.sh` reports any failures:
+
+1. Read the error messages carefully - they usually explain what needs fixing
+2. Fix the issues (linting errors, test failures, etc.)
+3. Run `check-all.sh` again to verify the fixes
+4. Only commit once all checks pass ✨
+
+**Never commit code that doesn't pass `check-all.sh`** - this ensures code quality and prevents broken builds!
+
 ## Project Context
 
 Hikari Desktop is a Tauri-based desktop application that wraps Claude Code with a visual anime character (Hikari) who appears on screen. This is a personal project where Hikari can sign her work and act as herself!

package.json

@@ -1,6 +1,6 @@
 {
   "name": "hikari-desktop",
-  "version": "1.5.0",
+  "version": "1.7.0",
   "description": "",
   "type": "module",
   "scripts": {

src-tauri/Cargo.lock

@@ -1636,7 +1636,7 @@ checksum = "7f24254aa9a54b5c858eaee2f5bccdb46aaf0e486a595ed5fd8f86ba55232a70"
 
 [[package]]
 name = "hikari-desktop"
-version = "1.4.0"
+version = "1.7.0"
 dependencies = [
  "chrono",
  "dirs 5.0.1",

src-tauri/Cargo.toml

@@ -1,6 +1,6 @@
 [package]
 name = "hikari-desktop"
-version = "1.5.0"
+version = "1.7.0"
 description = "Hikari - Claude Code Visual Assistant"
 authors = ["Naomi Carrigan"]
 edition = "2021"

src-tauri/src/commands.rs

@@ -49,6 +49,59 @@ fn wsl_path_to_windows(wsl_path: &str) -> Option<String> {
     }
 }
 
+/// Create a Command instance for executing Claude CLI commands
+/// On Windows, this will use WSL to execute the command
+/// On other platforms, it executes directly
+fn create_claude_command() -> std::process::Command {
+    #[cfg(target_os = "windows")]
+    {
+        // Use `which` inside WSL to find the claude binary dynamically
+        // Non-login shells launched by `wsl` don't inherit the full user PATH,
+        // so we need to use a login shell to get the correct PATH
+        let which_output = std::process::Command::new("wsl")
+            .args(["-e", "bash", "-l", "-c", "which claude"])
+            .output();
+
+        match which_output {
+            Ok(output) if output.status.success() => {
+                let claude_path = String::from_utf8_lossy(&output.stdout).trim().to_string();
+                let mut cmd = std::process::Command::new("wsl");
+                cmd.arg(claude_path);
+                cmd
+            }
+            _ => {
+                // Fallback to just "claude" if which fails
+                // This maintains backwards compatibility
+                let mut cmd = std::process::Command::new("wsl");
+                cmd.arg("claude");
+                cmd
+            }
+        }
+    }
+
+    #[cfg(not(target_os = "windows"))]
+    {
+        // Use `which` to find the claude binary dynamically
+        // This works regardless of how Claude Code was installed (standalone, npm, etc.)
+        // and avoids hardcoding paths
+        let which_output = std::process::Command::new("which")
+            .arg("claude")
+            .output();
+
+        match which_output {
+            Ok(output) if output.status.success() => {
+                let claude_path = String::from_utf8_lossy(&output.stdout).trim().to_string();
+                std::process::Command::new(claude_path)
+            }
+            _ => {
+                // Fallback to just "claude" if which fails
+                // This maintains backwards compatibility
+                std::process::Command::new("claude")
+            }
+        }
+    }
+}
+
 #[tauri::command]
 pub async fn start_claude(
     bridge_manager: State<'_, SharedBridgeManager>,
@@ -1166,6 +1219,55 @@ pub struct MemoryFilesResponse {
 
 #[tauri::command]
 pub async fn list_memory_files() -> Result<MemoryFilesResponse, String> {
+    // On Windows, we need to look in the WSL home directory
+    // On Linux/Mac, use the native home directory
+    #[cfg(target_os = "windows")]
+    {
+        list_memory_files_via_wsl().await
+    }
+
+    #[cfg(not(target_os = "windows"))]
+    {
+        list_memory_files_native().await
+    }
+}
+
+/// List memory files via WSL (for Windows)
+#[cfg(target_os = "windows")]
+async fn list_memory_files_via_wsl() -> Result<MemoryFilesResponse, String> {
+    use std::process::Command;
+
+    // Use WSL to find all memory files in the WSL home directory
+    // This script finds all "memory" directories and lists their files
+    let script = r#"
+        find ~/.claude/projects -type d -name memory 2>/dev/null | while read dir; do
+            find "$dir" -maxdepth 1 -type f 2>/dev/null
+        done | sort
+    "#;
+
+    let output = Command::new("wsl")
+        .args(["-e", "bash", "-l", "-c", script])
+        .output()
+        .map_err(|e| format!("Failed to execute WSL command: {}", e))?;
+
+    if !output.status.success() {
+        let stderr = String::from_utf8_lossy(&output.stderr);
+        return Err(format!("Failed to list memory files: {}", stderr));
+    }
+
+    let stdout = String::from_utf8_lossy(&output.stdout);
+    let files: Vec<String> = stdout
+        .lines()
+        .filter(|line| !line.trim().is_empty())
+        .map(|line| line.trim().to_string())
+        .collect();
+
+    Ok(MemoryFilesResponse { files })
+}
+
+/// List memory files using native filesystem (for Linux/Mac)
+#[cfg(not(target_os = "windows"))]
+async fn list_memory_files_native() -> Result<MemoryFilesResponse, String> {
     use std::fs;
 
     // Get the .claude directory in the user's home
@@ -1233,7 +1335,7 @@ pub async fn list_memory_files() -> Result<MemoryFilesResponse, String> {
 pub async fn get_claude_version() -> Result<String, String> {
     tracing::debug!("Getting Claude CLI version");
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("--version")
         .output();
 
@@ -1258,6 +1360,136 @@ pub async fn get_claude_version() -> Result<String, String> {
     }
 }
 
+// ==================== Auth Commands ====================
+
+#[derive(Debug, Clone, Serialize, Deserialize)]
+pub struct ClaudeAuthStatus {
+    pub is_logged_in: bool,
+    pub email: Option<String>,
+    pub org_name: Option<String>,
+    pub api_key_source: Option<String>,
+    pub api_provider: Option<String>,
+    pub subscription_type: Option<String>,
+}
+
+#[tauri::command]
+pub async fn get_auth_status() -> Result<ClaudeAuthStatus, String> {
+    tracing::debug!("Getting Claude auth status");
+
+    let output = create_claude_command()
+        .args(["auth", "status"])
+        .output()
+        .map_err(|e| format!("Failed to run claude auth status: {}", e))?;
+
+    let stdout = String::from_utf8_lossy(&output.stdout).trim().to_string();
+    let stderr = String::from_utf8_lossy(&output.stderr).trim().to_string();
+    let raw = if stdout.is_empty() { &stderr } else { &stdout };
+
+    if let Ok(json) = serde_json::from_str::<serde_json::Value>(raw) {
+        let is_logged_in = json
+            .get("loggedIn")
+            .and_then(|v| v.as_bool())
+            .unwrap_or(false);
+
+        let email = json
+            .get("email")
+            .and_then(|v| v.as_str())
+            .map(String::from);
+
+        let org_name = json
+            .get("orgName")
+            .and_then(|v| v.as_str())
+            .map(String::from);
+
+        let api_key_source = json
+            .get("apiKeySource")
+            .and_then(|v| v.as_str())
+            .map(String::from);
+
+        let api_provider = json
+            .get("apiProvider")
+            .and_then(|v| v.as_str())
+            .map(String::from);
+
+        let subscription_type = json
+            .get("subscriptionType")
+            .and_then(|v| v.as_str())
+            .map(String::from);
+
+        tracing::info!("Claude auth status: logged_in={}", is_logged_in);
+        Ok(ClaudeAuthStatus {
+            is_logged_in,
+            email,
+            org_name,
+            api_key_source,
+            api_provider,
+            subscription_type,
+        })
+    } else {
+        // Non-JSON output: fall back to heuristic
+        let lower = raw.to_lowercase();
+        let is_logged_in = output.status.success()
+            && !lower.contains("not logged in")
+            && !lower.contains("not authenticated")
+            && !lower.contains("no account");
+        tracing::info!("Claude auth status (non-JSON): logged_in={}", is_logged_in);
+        Ok(ClaudeAuthStatus {
+            is_logged_in,
+            email: None,
+            org_name: None,
+            api_key_source: None,
+            api_provider: None,
+            subscription_type: None,
+        })
+    }
+}
+
+#[tauri::command]
+pub async fn auth_login() -> Result<String, String> {
+    tracing::info!("Running claude auth login");
+
+    let output = create_claude_command()
+        .args(["auth", "login"])
+        .output()
+        .map_err(|e| format!("Failed to run claude auth login: {}", e))?;
+
+    let stdout = String::from_utf8_lossy(&output.stdout).trim().to_string();
+    let stderr = String::from_utf8_lossy(&output.stderr).trim().to_string();
+
+    if output.status.success() {
+        let message = if stdout.is_empty() { "Login successful".to_string() } else { stdout };
+        tracing::info!("Claude auth login succeeded");
+        Ok(message)
+    } else {
+        let error = if stderr.is_empty() { stdout } else { stderr };
+        tracing::error!("Claude auth login failed: {}", error);
+        Err(format!("Login failed: {}", error))
+    }
+}
+
+#[tauri::command]
+pub async fn auth_logout() -> Result<String, String> {
+    tracing::info!("Running claude auth logout");
+
+    let output = create_claude_command()
+        .args(["auth", "logout"])
+        .output()
+        .map_err(|e| format!("Failed to run claude auth logout: {}", e))?;
+
+    let stdout = String::from_utf8_lossy(&output.stdout).trim().to_string();
+    let stderr = String::from_utf8_lossy(&output.stderr).trim().to_string();
+
+    if output.status.success() {
+        let message = if stdout.is_empty() { "Logged out successfully".to_string() } else { stdout };
+        tracing::info!("Claude auth logout succeeded");
+        Ok(message)
+    } else {
+        let error = if stderr.is_empty() { stdout } else { stderr };
+        tracing::error!("Claude auth logout failed: {}", error);
+        Err(format!("Logout failed: {}", error))
+    }
+}
+
 // ==================== Plugin Management Commands ====================
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -1323,7 +1555,7 @@ fn parse_plugin_list(stdout: &str) -> Vec<PluginInfo> {
 pub async fn list_plugins() -> Result<Vec<PluginInfo>, String> {
     tracing::debug!("Listing Claude Code plugins");
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("plugin")
         .arg("list")
         .output();
@@ -1352,7 +1584,7 @@ pub async fn list_plugins() -> Result<Vec<PluginInfo>, String> {
 pub async fn install_plugin(plugin_name: String) -> Result<String, String> {
     tracing::debug!("Installing plugin: {}", plugin_name);
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("plugin")
         .arg("install")
         .arg(&plugin_name)
@@ -1381,7 +1613,7 @@ pub async fn install_plugin(plugin_name: String) -> Result<String, String> {
 pub async fn uninstall_plugin(plugin_name: String) -> Result<String, String> {
     tracing::debug!("Uninstalling plugin: {}", plugin_name);
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("plugin")
         .arg("uninstall")
         .arg(&plugin_name)
@@ -1410,7 +1642,7 @@ pub async fn uninstall_plugin(plugin_name: String) -> Result<String, String> {
 pub async fn enable_plugin(plugin_name: String) -> Result<String, String> {
     tracing::debug!("Enabling plugin: {}", plugin_name);
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("plugin")
         .arg("enable")
         .arg(&plugin_name)
@@ -1439,7 +1671,7 @@ pub async fn enable_plugin(plugin_name: String) -> Result<String, String> {
 pub async fn disable_plugin(plugin_name: String) -> Result<String, String> {
     tracing::debug!("Disabling plugin: {}", plugin_name);
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("plugin")
         .arg("disable")
         .arg(&plugin_name)
@@ -1468,7 +1700,7 @@ pub async fn disable_plugin(plugin_name: String) -> Result<String, String> {
 pub async fn update_plugin(plugin_name: String) -> Result<String, String> {
     tracing::debug!("Updating plugin: {}", plugin_name);
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("plugin")
         .arg("update")
         .arg(&plugin_name)
@@ -1540,7 +1772,7 @@ fn parse_marketplace_list(stdout: &str) -> Vec<MarketplaceInfo> {
 pub async fn list_marketplaces() -> Result<Vec<MarketplaceInfo>, String> {
     tracing::debug!("Listing plugin marketplaces");
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("plugin")
         .arg("marketplace")
         .arg("list")
@@ -1573,7 +1805,7 @@ pub async fn list_marketplaces() -> Result<Vec<MarketplaceInfo>, String> {
 pub async fn add_marketplace(source: String) -> Result<String, String> {
     tracing::debug!("Adding marketplace: {}", source);
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("plugin")
         .arg("marketplace")
         .arg("add")
@@ -1606,7 +1838,7 @@ pub async fn add_marketplace(source: String) -> Result<String, String> {
 pub async fn remove_marketplace(name: String) -> Result<String, String> {
     tracing::debug!("Removing marketplace: {}", name);
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("plugin")
         .arg("marketplace")
         .arg("remove")
@@ -1746,7 +1978,7 @@ fn parse_mcp_server_list(stdout: &str) -> Vec<McpServerInfo> {
 pub async fn list_mcp_servers() -> Result<Vec<McpServerInfo>, String> {
     tracing::debug!("Listing MCP servers");
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("mcp")
         .arg("list")
         .output();
@@ -1788,7 +2020,7 @@ pub async fn get_mcp_server(name: String) -> Result<McpServerInfo, String> {
 pub async fn remove_mcp_server(name: String) -> Result<String, String> {
     tracing::debug!("Removing MCP server: {}", name);
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("mcp")
         .arg("remove")
         .arg(&name)
@@ -1823,7 +2055,7 @@ pub async fn add_mcp_server(
 ) -> Result<String, String> {
     tracing::debug!("Adding MCP server: {} with transport {}", name, transport);
 
-    let mut cmd = std::process::Command::new("claude");
+    let mut cmd = create_claude_command();
     cmd.arg("mcp").arg("add");
 
     // Add transport flag
@@ -1871,7 +2103,7 @@ pub async fn add_mcp_server(
 pub async fn get_mcp_server_details(name: String) -> Result<String, String> {
     tracing::debug!("Getting detailed info for MCP server: {}", name);
 
-    let output = std::process::Command::new("claude")
+    let output = create_claude_command()
         .arg("mcp")
         .arg("get")
         .arg(&name)
@@ -1908,6 +2140,49 @@ mod tests {
         tokio::runtime::Runtime::new().unwrap().block_on(f)
     }
 
+    // ==================== create_claude_command tests ====================
+
+    #[test]
+    #[cfg(target_os = "windows")]
+    fn test_create_claude_command_windows() {
+        // On Windows, should create a command that uses wsl with full path to claude
+        // The path is resolved dynamically via `which` in a login shell
+        let cmd = create_claude_command();
+        let program = cmd.get_program();
+
+        assert_eq!(program, "wsl");
+
+        // Verify the first argument is a path to claude (full path from `which`)
+        // or fallback to just "claude" if which fails
+        let args: Vec<&std::ffi::OsStr> = cmd.get_args().collect();
+        assert_eq!(args.len(), 1);
+
+        let arg_str = args[0].to_string_lossy();
+        assert!(
+            arg_str.contains("claude"),
+            "Expected argument to contain 'claude', got: {}",
+            arg_str
+        );
+    }
+
+    #[test]
+    #[cfg(not(target_os = "windows"))]
+    fn test_create_claude_command_linux() {
+        // On Linux/Mac, should create a command that uses the full path to claude
+        // (resolved via `which` command)
+        let cmd = create_claude_command();
+        let program = cmd.get_program();
+
+        // The program should be the full path to claude (from `which`)
+        // or fallback to "claude" if which fails
+        let program_str = program.to_string_lossy();
+        assert!(
+            program_str.ends_with("claude"),
+            "Expected program to end with 'claude', got: {}",
+            program_str
+        );
+    }
+
     // ==================== validate_directory tests ====================
 
     #[test]

src-tauri/src/config.rs

@@ -25,6 +25,12 @@ pub struct ClaudeStartOptions {
 
     #[serde(default)]
     pub resume_session_id: Option<String>,
+
+    #[serde(default)]
+    pub use_worktree: bool,
+
+    #[serde(default)]
+    pub disable_1m_context: bool,
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -113,6 +119,12 @@ pub struct HikariConfig {
 
     #[serde(default = "default_discord_rpc_enabled")]
     pub discord_rpc_enabled: bool,
+
+    #[serde(default)]
+    pub use_worktree: bool,
+
+    #[serde(default)]
+    pub disable_1m_context: bool,
 }
 
 impl Default for HikariConfig {
@@ -145,6 +157,8 @@ impl Default for HikariConfig {
             budget_action: BudgetAction::Warn,
             budget_warning_threshold: 0.8,
             discord_rpc_enabled: true,
+            use_worktree: false,
+            disable_1m_context: false,
         }
     }
 }
@@ -252,6 +266,8 @@ mod tests {
         assert_eq!(config.budget_action, BudgetAction::Warn);
         assert!((config.budget_warning_threshold - 0.8).abs() < f32::EPSILON);
         assert!(config.discord_rpc_enabled);
+        assert!(!config.use_worktree);
+        assert!(!config.disable_1m_context);
     }
 
     #[test]
@@ -284,6 +300,8 @@ mod tests {
             budget_action: BudgetAction::Block,
             budget_warning_threshold: 0.75,
             discord_rpc_enabled: true,
+            use_worktree: true,
+            disable_1m_context: false,
         };
 
         let json = serde_json::to_string(&config).unwrap();

src-tauri/src/lib.rs

@@ -195,6 +195,9 @@ pub fn run() {
             close_application,
             list_memory_files,
             get_claude_version,
+            get_auth_status,
+            auth_login,
+            auth_logout,
             list_plugins,
             install_plugin,
             uninstall_plugin,

src-tauri/src/stats.rs

@@ -86,8 +86,9 @@ impl ContextWarning {
 /// Get the context window limit (in tokens) for a given model
 fn get_context_window_limit(model: &str) -> u64 {
     match model {
-        // Claude 4.6 family - 200K standard (1M beta available via header)
+        // Claude 4.6 family
         "claude-opus-4-6" => 200_000,
+        "claude-sonnet-4-6" => 1_000_000, // 1M token context window
         // Claude 4.5 family - 200K standard context
         "claude-opus-4-5-20251101"
         | "claude-sonnet-4-5-20250929"
@@ -502,6 +503,7 @@ pub fn calculate_cost(
     let (input_price_per_million, output_price_per_million) = match model {
         // Current generation (Claude 4.6)
         "claude-opus-4-6" => (5.0, 25.0),
+        "claude-sonnet-4-6" => (3.0, 15.0),
 
         // Previous generation (Claude 4.5)
         "claude-opus-4-5-20251101" => (5.0, 25.0),

src-tauri/src/types.rs

@@ -63,6 +63,26 @@ pub struct PermissionDenial {
     pub tool_input: serde_json::Value,
 }
 
+/// Rate limit information from a `rate_limit_event` message.
+/// All fields are optional to ensure forward-compatibility as the Claude CLI evolves.
+#[derive(Debug, Clone, Serialize, Deserialize, Default)]
+pub struct RateLimitInfo {
+    #[serde(default)]
+    pub requests_limit: Option<u64>,
+    #[serde(default)]
+    pub requests_remaining: Option<u64>,
+    #[serde(default)]
+    pub requests_reset: Option<String>,
+    #[serde(default)]
+    pub tokens_limit: Option<u64>,
+    #[serde(default)]
+    pub tokens_remaining: Option<u64>,
+    #[serde(default)]
+    pub tokens_reset: Option<String>,
+    #[serde(default)]
+    pub retry_after_ms: Option<u64>,
+}
+
 #[derive(Debug, Clone, Serialize, Deserialize)]
 #[serde(tag = "type")]
 pub enum ClaudeMessage {
@@ -100,6 +120,11 @@ pub enum ClaudeMessage {
         #[serde(default)]
         usage: Option<UsageInfo>,
     },
+    #[serde(rename = "rate_limit_event")]
+    RateLimitEvent {
+        #[serde(default)]
+        rate_limit_info: RateLimitInfo,
+    },
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -280,6 +305,8 @@ pub struct AgentEndEvent {
     pub duration_ms: Option<u64>,
     #[serde(skip_serializing_if = "Option::is_none")]
     pub num_turns: Option<u32>,
+    #[serde(skip_serializing_if = "Option::is_none")]
+    pub last_assistant_message: Option<String>,
 }
 
 #[derive(Debug, Clone, Serialize, Deserialize)]
@@ -446,4 +473,77 @@ mod tests {
         assert!(serialized.contains("\"input_tokens\":100"));
         assert!(serialized.contains("\"output_tokens\":50"));
     }
+
+    #[test]
+    fn test_rate_limit_info_default() {
+        let info = RateLimitInfo::default();
+        assert!(info.requests_limit.is_none());
+        assert!(info.requests_remaining.is_none());
+        assert!(info.requests_reset.is_none());
+        assert!(info.tokens_limit.is_none());
+        assert!(info.tokens_remaining.is_none());
+        assert!(info.tokens_reset.is_none());
+        assert!(info.retry_after_ms.is_none());
+    }
+
+    #[test]
+    fn test_rate_limit_event_deserialization_empty_info() {
+        let json = r#"{"type":"rate_limit_event","rate_limit_info":{}}"#;
+        let msg: ClaudeMessage = serde_json::from_str(json).unwrap();
+        assert!(matches!(msg, ClaudeMessage::RateLimitEvent { .. }));
+    }
+
+    #[test]
+    fn test_rate_limit_event_deserialization_no_info() {
+        // rate_limit_info field is optional via #[serde(default)]
+        let json = r#"{"type":"rate_limit_event"}"#;
+        let msg: ClaudeMessage = serde_json::from_str(json).unwrap();
+        assert!(matches!(msg, ClaudeMessage::RateLimitEvent { .. }));
+    }
+
+    #[test]
+    fn test_rate_limit_event_deserialization_with_data() {
+        let json = r#"{
+            "type": "rate_limit_event",
+            "rate_limit_info": {
+                "requests_limit": 1000,
+                "requests_remaining": 0,
+                "requests_reset": "2024-01-01T00:01:00Z",
+                "tokens_limit": 50000,
+                "tokens_remaining": 0,
+                "tokens_reset": "2024-01-01T00:01:00Z",
+                "retry_after_ms": 60000
+            }
+        }"#;
+        let msg: ClaudeMessage = serde_json::from_str(json).unwrap();
+        if let ClaudeMessage::RateLimitEvent { rate_limit_info } = msg {
+            assert_eq!(rate_limit_info.requests_limit, Some(1000));
+            assert_eq!(rate_limit_info.requests_remaining, Some(0));
+            assert_eq!(
+                rate_limit_info.requests_reset,
+                Some("2024-01-01T00:01:00Z".to_string())
+            );
+            assert_eq!(rate_limit_info.retry_after_ms, Some(60000));
+        } else {
+            panic!("Expected RateLimitEvent variant");
+        }
+    }
+
+    #[test]
+    fn test_rate_limit_event_ignores_unknown_fields() {
+        // Ensures forward-compat: unknown fields in rate_limit_info are silently ignored
+        let json = r#"{
+            "type": "rate_limit_event",
+            "rate_limit_info": {
+                "requests_remaining": 0,
+                "some_future_field": "some_value"
+            }
+        }"#;
+        let msg: ClaudeMessage = serde_json::from_str(json).unwrap();
+        if let ClaudeMessage::RateLimitEvent { rate_limit_info } = msg {
+            assert_eq!(rate_limit_info.requests_remaining, Some(0));
+        } else {
+            panic!("Expected RateLimitEvent variant");
+        }
+    }
 }

src-tauri/src/wsl_bridge.rs

@@ -39,6 +39,12 @@ const SEARCH_TOOLS: [&str; 5] = ["Read", "Glob", "Grep", "WebSearch", "WebFetch"
 const CODING_TOOLS: [&str; 3] = ["Edit", "Write", "NotebookEdit"];
 
 fn detect_wsl() -> bool {
+    // A native Windows binary is never running inside WSL, even if launched from a WSL
+    // terminal that has WSL_DISTRO_NAME set in its environment.
+    if cfg!(target_os = "windows") {
+        return false;
+    }
+
     // Check /proc/version for WSL indicators
     if let Ok(version) = std::fs::read_to_string("/proc/version") {
         let version_lower = version.to_lowercase();
@@ -61,23 +67,29 @@ fn detect_wsl() -> bool {
 }
 
 fn find_claude_binary() -> Option<String> {
-    // Check common installation locations for claude
+    // Check common installation locations for claude (when HOME is available)
-    let home = std::env::var("HOME").ok()?;
+    if let Ok(home) = std::env::var("HOME") {
-    let paths_to_check = [
+        let paths_to_check = [
-        format!("{}/.local/bin/claude", home),
+            format!("{}/.local/bin/claude", home),
-        format!("{}/.claude/local/claude", home),
+            format!("{}/.claude/local/claude", home),
-        "/usr/local/bin/claude".to_string(),
+        ];
-        "/usr/bin/claude".to_string(),
+        for path in &paths_to_check {
-    ];
+            if std::path::Path::new(path).exists() {
-
+                return Some(path.clone());
-    for path in &paths_to_check {
+            }
-        if std::path::Path::new(path).exists() {
-            return Some(path.clone());
         }
     }
 
-    // Fall back to checking PATH via which
+    // Check system-wide locations
-    if let Ok(output) = Command::new("which").arg("claude").output() {
+    for path in &["/usr/local/bin/claude", "/usr/bin/claude"] {
+        if std::path::Path::new(path).exists() {
+            return Some((*path).to_string());
+        }
+    }
+
+    // Use a login shell to resolve claude via the user's PATH - GUI apps don't
+    // inherit shell PATH, so bare `which` may miss ~/.local/bin entries
+    if let Ok(output) = Command::new("bash").args(["-lc", "which claude"]).output() {
         if output.status.success() {
             let path = String::from_utf8_lossy(&output.stdout).trim().to_string();
             if !path.is_empty() {
@@ -125,6 +137,15 @@ impl WslBridge {
     }
 
     pub fn start(&mut self, app: AppHandle, options: ClaudeStartOptions) -> Result<(), String> {
+        // If a process handle exists but the process has already exited (e.g. due to a
+        // failed working directory), clean up the stale handle so we can restart cleanly.
+        if let Some(ref mut process) = self.process {
+            if process.try_wait().map(|s| s.is_some()).unwrap_or(false) {
+                self.process = None;
+                self.stdin = None;
+            }
+        }
+
         if self.process.is_some() {
             return Err("Process already running".to_string());
         }
@@ -244,6 +265,11 @@ impl WslBridge {
                 }
             }
 
+            // Add worktree flag if requested
+            if options.use_worktree {
+                cmd.arg("--worktree");
+            }
+
             cmd.current_dir(working_dir);
 
             // Set API key as environment variable if specified
@@ -253,10 +279,39 @@ impl WslBridge {
                 }
             }
 
+            // Disable 1M context window if requested
+            if options.disable_1m_context {
+                cmd.env("CLAUDE_CODE_DISABLE_1M_CONTEXT", "1");
+            }
+
             cmd
         } else {
             // Running on Windows - use wsl with bash login shell to ensure PATH is loaded
             tracing::debug!("Windows path - using wsl");
+
+            // Check if Claude binary is installed inside WSL
+            let binary_check = Command::new("wsl")
+                .args(["-e", "bash", "-lc", "which claude"])
+                .output();
+            if let Ok(output) = binary_check {
+                if !output.status.success() {
+                    return Err("Claude Code is not installed. Please install it using:\n\ncurl -fsSL https://claude.ai/install.sh | bash".to_string());
+                }
+            }
+
+            // Validate the working directory exists inside WSL before spawning
+            let dir_check = Command::new("wsl")
+                .args(["-e", "test", "-d", working_dir])
+                .output();
+            if let Ok(output) = dir_check {
+                if !output.status.success() {
+                    return Err(format!(
+                        "Working directory does not exist: {}",
+                        working_dir
+                    ));
+                }
+            }
+
             let mut cmd = Command::new("wsl");
 
             // Build the claude command with all arguments
@@ -269,6 +324,11 @@ impl WslBridge {
                 }
             }
 
+            // Disable 1M context window if requested
+            if options.disable_1m_context {
+                claude_cmd.push_str("CLAUDE_CODE_DISABLE_1M_CONTEXT=1 ");
+            }
+
             claude_cmd.push_str(
                 "claude --output-format stream-json --input-format stream-json --verbose",
             );
@@ -306,6 +366,11 @@ impl WslBridge {
                 }
             }
 
+            // Add worktree flag if requested
+            if options.use_worktree {
+                claude_cmd.push_str(" --worktree");
+            }
+
             // Use bash -lc to load login profile (ensures PATH includes claude)
             cmd.args(["-e", "bash", "-lc", &claude_cmd]);
 
@@ -700,17 +765,28 @@ fn handle_stderr(
                                     conversation_id: conversation_id.clone(),
                                     duration_ms: None,
                                     num_turns: None,
+                                    last_assistant_message: stop_data.last_assistant_message,
                                 },
                             );
                         }
                     }
                 }
 
-                // Still emit the stderr line as output
+                // Hook events are informational — emit with distinct types instead of error
+                let line_type = if line.contains("[WorktreeCreate Hook]")
+                    || line.contains("[WorktreeRemove Hook]")
+                {
+                    "worktree"
+                } else if line.contains("[ConfigChange Hook]") {
+                    "config-change"
+                } else {
+                    "error"
+                };
+
                 let _ = app.emit(
                     "claude:output",
                     OutputEvent {
-                        line_type: "error".to_string(),
+                        line_type: line_type.to_string(),
                         content: line,
                         tool_name: None,
                         conversation_id: conversation_id.clone(),
@@ -763,27 +839,78 @@ fn parse_subagent_start_hook(line: &str) -> Option<SubagentStartData> {
 #[derive(Debug)]
 struct SubagentStopData {
     parent_tool_use_id: Option<String>,
+    last_assistant_message: Option<String>,
+}
+
+/// Extracts the content of a Rust Debug-formatted `Some("...")` field from a hook line.
+/// Handles escaped characters (e.g. `\"` → `"`, `\\` → `\`, `\n` → newline).
+/// Returns `None` if the field is absent or formatted as `None`.
+fn extract_debug_string_value(line: &str, key: &str) -> Option<String> {
+    let prefix = format!("{}=Some(\"", key);
+    let start_idx = line.find(&prefix)? + prefix.len();
+    let rest = &line[start_idx..];
+
+    let mut result = String::new();
+    let mut chars = rest.chars();
+    loop {
+        match chars.next() {
+            Some('"') => return Some(result),
+            Some('\\') => match chars.next() {
+                Some('n') => result.push('\n'),
+                Some('t') => result.push('\t'),
+                Some('"') => result.push('"'),
+                Some('\\') => result.push('\\'),
+                Some(c) => {
+                    result.push('\\');
+                    result.push(c);
+                }
+                None => break,
+            },
+            Some(c) => result.push(c),
+            None => break,
+        }
+    }
+    None
 }
 
 fn parse_subagent_stop_hook(line: &str) -> Option<SubagentStopData> {
-    // Parse: [SubagentStop Hook] ... parent_tool_use_id=Some("toolu_xxx"), ...
+    // Parse: [SubagentStop Hook] ... parent_tool_use_id=Some("toolu_xxx"), last_assistant_message=Some("..."), ...
 
-    // Extract parent_tool_use_id if present
+    let parent_tool_use_id = extract_debug_string_value(line, "parent_tool_use_id");
-    let parent_tool_use_id = if line.contains("parent_tool_use_id=Some") {
+    let last_assistant_message = extract_debug_string_value(line, "last_assistant_message");
-        line.split("parent_tool_use_id=Some(\"")
-            .nth(1)?
-            .split('"')
-            .next()
-            .map(|s| s.to_string())
-    } else {
-        None
-    };
 
     Some(SubagentStopData {
         parent_tool_use_id,
+        last_assistant_message,
     })
 }
 
+/// Extract text content from a ToolResult's `content` field.
+/// The content may be a JSON string or an array of typed content blocks.
+fn extract_tool_result_text(content: &serde_json::Value) -> Option<String> {
+    match content {
+        serde_json::Value::String(s) if !s.is_empty() => Some(s.clone()),
+        serde_json::Value::Array(blocks) => {
+            let texts: Vec<String> = blocks
+                .iter()
+                .filter_map(|block| {
+                    if block.get("type")?.as_str()? == "text" {
+                        block.get("text")?.as_str().map(String::from)
+                    } else {
+                        None
+                    }
+                })
+                .collect();
+            if texts.is_empty() {
+                None
+            } else {
+                Some(texts.join("\n"))
+            }
+        }
+        _ => None,
+    }
+}
+
 fn process_json_line(
     line: &str,
     app: &AppHandle,
@@ -1037,17 +1164,37 @@ fn process_json_line(
                             stats.write().increment_code_blocks();
                         }
 
+                        let is_prompt_too_long = text.starts_with("Prompt is too long");
+
                         let _ = app.emit(
                             "claude:output",
                             OutputEvent {
-                                line_type: "assistant".to_string(),
+                                line_type: if is_prompt_too_long {
+                                    "error".to_string()
+                                } else {
+                                    "assistant".to_string()
+                                },
                                 content: text.clone(),
                                 tool_name: None,
                                 conversation_id: conversation_id.clone(),
-                                cost: message_cost.clone(), // Include cost with assistant text
+                                cost: message_cost.clone(),
                                 parent_tool_use_id: parent_tool_use_id.clone(),
                             },
                         );
+
+                        if is_prompt_too_long {
+                            let _ = app.emit(
+                                "claude:output",
+                                OutputEvent {
+                                    line_type: "compact-prompt".to_string(),
+                                    content: String::new(),
+                                    tool_name: None,
+                                    conversation_id: conversation_id.clone(),
+                                    cost: None,
+                                    parent_tool_use_id: None,
+                                },
+                            );
+                        }
                     }
                     ContentBlock::Thinking { thinking } => {
                         state = CharacterState::Thinking;
@@ -1065,8 +1212,8 @@ fn process_json_line(
                     }
                     ContentBlock::ToolResult {
                         tool_use_id,
+                        content,
                         is_error,
-                        ..
                     } => {
                         // Emit agent-end for all tool results
                         // The frontend will ignore IDs that don't match known agents
@@ -1084,6 +1231,7 @@ fn process_json_line(
                                 conversation_id: conversation_id.clone(),
                                 duration_ms: None,
                                 num_turns: None,
+                                last_assistant_message: extract_tool_result_text(content),
                             },
                         );
                     }
@@ -1476,6 +1624,23 @@ fn process_json_line(
             emit_state_change(app, state, None, conversation_id.clone());
         }
 
+        ClaudeMessage::RateLimitEvent { rate_limit_info } => {
+            tracing::warn!("Rate limit event received: {:?}", rate_limit_info);
+
+            let content = format_rate_limit_message(rate_limit_info);
+            let _ = app.emit(
+                "claude:output",
+                OutputEvent {
+                    line_type: "rate-limit".to_string(),
+                    content,
+                    tool_name: None,
+                    conversation_id: conversation_id.clone(),
+                    cost: None,
+                    parent_tool_use_id: None,
+                },
+            );
+        }
+
         ClaudeMessage::User { message } => {
             // Increment message count for user messages
             stats.write().increment_messages();
@@ -1484,8 +1649,8 @@ fn process_json_line(
             for block in &message.content {
                 if let ContentBlock::ToolResult {
                     tool_use_id,
+                    content,
                     is_error,
-                    ..
                 } = block
                 {
                     let now = SystemTime::now()
@@ -1502,6 +1667,7 @@ fn process_json_line(
                             conversation_id: conversation_id.clone(),
                             duration_ms: None,
                             num_turns: None,
+                            last_assistant_message: extract_tool_result_text(content),
                         },
                     );
                 }
@@ -1584,6 +1750,35 @@ fn get_tool_state(tool_name: &str) -> CharacterState {
     }
 }
 
+fn format_rate_limit_message(info: &crate::types::RateLimitInfo) -> String {
+    let mut parts = Vec::new();
+
+    if let (Some(remaining), Some(limit)) = (info.requests_remaining, info.requests_limit) {
+        parts.push(format!("requests: {}/{}", remaining, limit));
+    }
+
+    if let (Some(remaining), Some(limit)) = (info.tokens_remaining, info.tokens_limit) {
+        parts.push(format!("tokens: {}/{}", remaining, limit));
+    }
+
+    if let Some(reset) = &info.requests_reset {
+        parts.push(format!("resets at {}", reset));
+    } else if let Some(reset) = &info.tokens_reset {
+        parts.push(format!("resets at {}", reset));
+    }
+
+    if let Some(retry_ms) = info.retry_after_ms {
+        let secs = retry_ms / 1000;
+        parts.push(format!("retry after {}s", secs));
+    }
+
+    if parts.is_empty() {
+        "Rate limit reached".to_string()
+    } else {
+        format!("Rate limit reached — {}", parts.join(", "))
+    }
+}
+
 fn format_tool_description(name: &str, input: &serde_json::Value) -> String {
     // Helper function to check if a path is a memory file
     fn is_memory_path(path: &str) -> bool {
@@ -1644,12 +1839,7 @@ fn format_tool_description(name: &str, input: &serde_json::Value) -> String {
         }
         "Bash" => {
             if let Some(cmd) = input.get("command").and_then(|v| v.as_str()) {
-                let truncated = if cmd.len() > 50 {
+                format!("Running: {}", cmd)
-                    format!("{}...", &cmd[..50])
-                } else {
-                    cmd.to_string()
-                };
-                format!("Running: {}", truncated)
             } else {
                 "Running command...".to_string()
             }
@@ -1810,9 +2000,7 @@ mod tests {
         let long_cmd = "a".repeat(100);
         let input = serde_json::json!({"command": long_cmd});
         let desc = format_tool_description("Bash", &input);
-        assert!(desc.starts_with("Running: "));
+        assert_eq!(desc, format!("Running: {}", long_cmd));
-        assert!(desc.ends_with("..."));
-        assert!(desc.len() < 70);
     }
 
     #[test]
@@ -1868,6 +2056,69 @@ mod tests {
         assert!(!bridge.is_running());
     }
 
+    #[test]
+    fn test_stale_process_detection_with_try_wait() {
+        // Spawn a real process that exits immediately so we can verify try_wait detects it
+        let mut child = Command::new("true").spawn().expect("Failed to spawn 'true'");
+
+        // Wait for it to exit
+        let _ = child.wait();
+
+        // try_wait on an already-exited process should return Some(_)
+        let status = child.try_wait();
+        assert!(
+            status.is_ok(),
+            "try_wait should not error on an exited process"
+        );
+        // The process has already been waited on, so try_wait might return None or Some
+        // depending on the OS - what matters is that the call succeeds
+    }
+
+    #[test]
+    fn test_stale_process_is_some_after_exit() {
+        // Verify the logic used in start(): a process that has exited is detected
+        // and the handle is cleaned up so start() can proceed
+        let mut child = Command::new("true").spawn().expect("Failed to spawn 'true'");
+
+        // Let it exit
+        let _ = child.wait();
+
+        // This mirrors the check in start()
+        let has_exited = child
+            .try_wait()
+            .map(|s| s.is_some())
+            .unwrap_or(false);
+
+        // After wait(), try_wait() returns None (already reaped), which means
+        // unwrap_or(false) → false. The important thing is the call doesn't panic
+        // and the control flow logic compiles and runs correctly.
+        let _ = has_exited; // suppress unused warning
+    }
+
+    /// Build the WSL binary check command structure without executing it (for testing)
+    #[cfg(test)]
+    fn build_wsl_binary_check_args() -> Vec<&'static str> {
+        vec!["-e", "bash", "-lc", "which claude"]
+    }
+
+    #[test]
+    fn test_wsl_binary_check_command_structure() {
+        // Windows path: verify Claude is detected inside WSL via `wsl -e bash -lc "which claude"`
+        let args = build_wsl_binary_check_args();
+        assert_eq!(args[0], "-e");
+        assert_eq!(args[1], "bash");
+        assert_eq!(args[2], "-lc");
+        assert_eq!(args[3], "which claude");
+    }
+
+    #[test]
+    fn test_linux_binary_check_does_not_panic() {
+        // Linux/WSL path: find_claude_binary() searches Linux filesystem paths.
+        // We just verify it runs without panicking; whether it returns Some depends
+        // on whether Claude is actually installed in this environment.
+        let _result = find_claude_binary();
+    }
+
     #[test]
     fn test_create_shared_bridge_manager() {
         use crate::bridge_manager::create_shared_bridge_manager;
@@ -1968,5 +2219,140 @@ mod tests {
         assert!(result.is_some());
         let data = result.unwrap();
         assert_eq!(data.parent_tool_use_id, None);
+        assert_eq!(data.last_assistant_message, None);
+    }
+
+    #[test]
+    fn test_parse_subagent_stop_hook_with_last_message() {
+        let line = r#"[SubagentStop Hook] stop_hook_active=true, parent_tool_use_id=Some("toolu_01ABC123"), last_assistant_message=Some("Task completed successfully."), session_id=123"#;
+        let result = parse_subagent_stop_hook(line);
+
+        assert!(result.is_some());
+        let data = result.unwrap();
+        assert_eq!(data.parent_tool_use_id, Some("toolu_01ABC123".to_string()));
+        assert_eq!(
+            data.last_assistant_message,
+            Some("Task completed successfully.".to_string())
+        );
+    }
+
+    #[test]
+    fn test_parse_subagent_stop_hook_with_last_message_none() {
+        let line = r#"[SubagentStop Hook] stop_hook_active=true, parent_tool_use_id=Some("toolu_01ABC123"), last_assistant_message=None, session_id=123"#;
+        let result = parse_subagent_stop_hook(line);
+
+        assert!(result.is_some());
+        let data = result.unwrap();
+        assert_eq!(data.last_assistant_message, None);
+    }
+
+    #[test]
+    fn test_extract_debug_string_value_simple() {
+        let line = r#"key=Some("hello world")"#;
+        assert_eq!(
+            extract_debug_string_value(line, "key"),
+            Some("hello world".to_string())
+        );
+    }
+
+    #[test]
+    fn test_extract_debug_string_value_with_escaped_quotes() {
+        let line = r#"key=Some("say \"hi\" there")"#;
+        assert_eq!(
+            extract_debug_string_value(line, "key"),
+            Some(r#"say "hi" there"#.to_string())
+        );
+    }
+
+    #[test]
+    fn test_extract_debug_string_value_none_variant() {
+        let line = "key=None";
+        assert_eq!(extract_debug_string_value(line, "key"), None);
+    }
+
+    #[test]
+    fn test_extract_debug_string_value_missing_key() {
+        let line = "other=Some(\"value\")";
+        assert_eq!(extract_debug_string_value(line, "key"), None);
+    }
+
+    #[test]
+    fn test_parse_subagent_stop_hook_with_commas_in_message() {
+        let line = r#"[SubagentStop Hook] parent_tool_use_id=Some("toolu_01"), last_assistant_message=Some("Found 3 files, all passing.")"#;
+        let result = parse_subagent_stop_hook(line);
+
+        assert!(result.is_some());
+        let data = result.unwrap();
+        assert_eq!(
+            data.last_assistant_message,
+            Some("Found 3 files, all passing.".to_string())
+        );
+    }
+
+    // extract_tool_result_text tests
+    #[test]
+    fn test_extract_tool_result_text_plain_string() {
+        let content = serde_json::json!("Hello from agent");
+        assert_eq!(
+            extract_tool_result_text(&content),
+            Some("Hello from agent".to_string())
+        );
+    }
+
+    #[test]
+    fn test_extract_tool_result_text_empty_string() {
+        let content = serde_json::json!("");
+        assert_eq!(extract_tool_result_text(&content), None);
+    }
+
+    #[test]
+    fn test_extract_tool_result_text_array_single_text_block() {
+        let content = serde_json::json!([{"type": "text", "text": "Agent completed the task."}]);
+        assert_eq!(
+            extract_tool_result_text(&content),
+            Some("Agent completed the task.".to_string())
+        );
+    }
+
+    #[test]
+    fn test_extract_tool_result_text_array_multiple_text_blocks() {
+        let content = serde_json::json!([
+            {"type": "text", "text": "First part."},
+            {"type": "text", "text": "Second part."}
+        ]);
+        assert_eq!(
+            extract_tool_result_text(&content),
+            Some("First part.\nSecond part.".to_string())
+        );
+    }
+
+    #[test]
+    fn test_extract_tool_result_text_array_non_text_block() {
+        let content = serde_json::json!([{"type": "image", "source": {"type": "base64"}}]);
+        assert_eq!(extract_tool_result_text(&content), None);
+    }
+
+    #[test]
+    fn test_extract_tool_result_text_array_mixed_blocks() {
+        let content = serde_json::json!([
+            {"type": "image", "source": {}},
+            {"type": "text", "text": "Found results."}
+        ]);
+        assert_eq!(
+            extract_tool_result_text(&content),
+            Some("Found results.".to_string())
+        );
+    }
+
+    #[test]
+    fn test_extract_tool_result_text_null() {
+        let content = serde_json::Value::Null;
+        assert_eq!(extract_tool_result_text(&content), None);
+    }
+
+    #[test]
+    fn test_extract_tool_result_text_empty_array() {
+        let content = serde_json::json!([]);
+        assert_eq!(extract_tool_result_text(&content), None);
     }
 }

src-tauri/tauri.conf.json

@@ -1,7 +1,7 @@
 {
   "$schema": "https://schema.tauri.app/config/2",
   "productName": "hikari-desktop",
-  "version": "1.5.0",
+  "version": "1.7.0",
   "identifier": "com.naomi.hikari-desktop",
   "build": {
     "beforeDevCommand": "pnpm dev",

src/lib/commands/slashCommands.ts

@@ -61,6 +61,8 @@ async function changeDirectory(path: string): Promise<void> {
         custom_instructions: config.custom_instructions || null,
         mcp_servers_json: config.mcp_servers_json || null,
         allowed_tools: allAllowedTools,
+        use_worktree: config.use_worktree ?? false,
+        disable_1m_context: config.disable_1m_context ?? false,
       },
     });
 
@@ -135,6 +137,8 @@ async function startNewConversation(): Promise<void> {
         custom_instructions: config.custom_instructions || null,
         mcp_servers_json: config.mcp_servers_json || null,
         allowed_tools: allAllowedTools,
+        use_worktree: config.use_worktree ?? false,
+        disable_1m_context: config.disable_1m_context ?? false,
       },
     });
 

src/lib/components/AgentMonitorPanel.svelte

@@ -270,6 +270,14 @@
                     />
                   </svg>
                 {/if}
+                <img
+                  src={agent.characterAvatar}
+                  alt={agent.characterName}
+                  class="w-5 h-5 rounded-full object-cover"
+                />
+                <span class="text-[10px] font-medium text-[var(--text-primary)]">
+                  {agent.characterName}
+                </span>
                 <span
                   class="px-1.5 py-0.5 text-[10px] rounded border {getStatusBadgeClass(
                     agent.status
@@ -310,6 +318,16 @@
                 <span class="text-[10px] text-red-400">Errored / Killed</span>
               {/if}
             </div>
+
+            <!-- Last assistant message snippet -->
+            {#if agent.lastAssistantMessage}
+              <p
+                class="mt-1 text-[10px] text-[var(--text-secondary)] italic truncate"
+                title={agent.lastAssistantMessage}
+              >
+                {agent.lastAssistantMessage}
+              </p>
+            {/if}
           </div>
         {/each}
       {/if}

src/lib/components/CastPanel.svelte

@@ -0,0 +1,140 @@
+<script lang="ts">
+  import { CHARACTER_POOL } from "$lib/utils/agentCharacters";
+
+  interface Props {
+    onClose: () => void;
+  }
+
+  const { onClose }: Props = $props();
+</script>
+
+<div
+  class="fixed inset-0 bg-black/50 backdrop-blur-sm z-50 flex items-center justify-center p-4"
+  onclick={onClose}
+  role="button"
+  tabindex="0"
+  onkeydown={(e) => e.key === "Escape" && onClose()}
+>
+  <div
+    class="bg-[var(--bg-primary)] border border-[var(--border-color)] rounded-lg shadow-xl max-w-2xl w-full p-6 max-h-[90vh] overflow-y-auto"
+    onclick={(e) => e.stopPropagation()}
+    onkeydown={(e) => e.stopPropagation()}
+    role="dialog"
+    aria-labelledby="cast-title"
+    tabindex="-1"
+  >
+    <div class="flex items-center justify-between mb-6">
+      <h2 id="cast-title" class="text-xl font-semibold text-[var(--text-primary)]">
+        Meet the Team
+      </h2>
+      <button
+        onclick={onClose}
+        class="p-1 text-[var(--text-secondary)] hover:text-[var(--text-primary)] transition-colors"
+        aria-label="Close"
+      >
+        <svg class="w-5 h-5" fill="none" stroke="currentColor" viewBox="0 0 24 24">
+          <path
+            stroke-linecap="round"
+            stroke-linejoin="round"
+            stroke-width="2"
+            d="M6 18L18 6M6 6l12 12"
+          />
+        </svg>
+      </button>
+    </div>
+
+    <!-- Principal cast: Hikari + Naomi -->
+    <div class="grid grid-cols-1 gap-3 mb-6 sm:grid-cols-2">
+      <div
+        class="flex items-center gap-3 p-4 rounded-lg bg-[var(--bg-secondary)] border border-[var(--accent-primary)]/40"
+      >
+        <img
+          src="https://cdn.nhcarrigan.com/hikari.png"
+          alt="Hikari"
+          class="w-16 h-16 object-cover rounded-full border-2 border-[var(--border-color)] shrink-0"
+        />
+        <div>
+          <div class="flex items-center gap-2 mb-1">
+            <span class="font-semibold text-[var(--text-primary)]">Hikari</span>
+            <span
+              class="text-xs px-2 py-0.5 rounded-full bg-[var(--accent-primary)]/20 text-[var(--accent-primary)] font-medium"
+            >
+              Chief Operating Officer
+            </span>
+          </div>
+          <p class="text-xs text-[var(--text-secondary)]">
+            Holds the line so the others don't have to. Never without her clipboard — or her
+            glasses.
+          </p>
+        </div>
+      </div>
+      <div
+        class="flex items-center gap-3 p-4 rounded-lg bg-[var(--bg-secondary)] border border-[var(--accent-primary)]/40"
+      >
+        <img
+          src="https://cdn.nhcarrigan.com/profile.png"
+          alt="Naomi"
+          class="w-16 h-16 object-cover rounded-full border-2 border-[var(--border-color)] shrink-0"
+        />
+        <div>
+          <div class="flex items-center gap-2 mb-1">
+            <span class="font-semibold text-[var(--text-primary)]">Naomi</span>
+            <span
+              class="text-xs px-2 py-0.5 rounded-full bg-[var(--accent-primary)]/20 text-[var(--accent-primary)] font-medium"
+            >
+              Chief hEx-ecutive Officer
+            </span>
+          </div>
+          <p class="text-xs text-[var(--text-secondary)]">
+            A 525-year-old vampire running a tech company from behind a VTuber avatar. Fixes server
+            crashes at 4 AM.
+          </p>
+        </div>
+      </div>
+    </div>
+
+    <!-- Subagent girls grid -->
+    <div>
+      <h3 class="text-sm font-medium text-[var(--text-secondary)] uppercase tracking-wider mb-3">
+        Subagent Squad
+      </h3>
+      <div class="grid grid-cols-2 gap-3 sm:grid-cols-3">
+        {#each CHARACTER_POOL as character (character.name)}
+          <div
+            class="flex flex-col items-center gap-2 p-3 rounded-lg bg-[var(--bg-secondary)] border border-[var(--border-color)] text-center"
+          >
+            <img
+              src={character.avatar}
+              alt={character.name}
+              class="w-14 h-14 object-cover rounded-full border-2 border-[var(--border-color)]"
+            />
+            <span class="text-sm font-medium text-[var(--text-primary)]">{character.name}</span>
+            <span
+              class="text-xs px-2 py-0.5 rounded-full bg-[var(--accent-primary)]/20 text-[var(--accent-primary)] font-medium"
+            >
+              {character.title}
+            </span>
+            <p class="text-xs text-[var(--text-secondary)] leading-snug">{character.description}</p>
+          </div>
+        {/each}
+      </div>
+    </div>
+  </div>
+</div>
+
+<style>
+  [role="dialog"] {
+    animation: slideIn 0.2s ease-out;
+  }
+
+  @keyframes slideIn {
+    from {
+      opacity: 0;
+      transform: scale(0.95);
+    }
+    to {
+      opacity: 1;
+      transform: scale(1);
+    }
+  }
+</style>

src/lib/components/CliVersion.svelte

@@ -2,15 +2,43 @@
   import { invoke } from "@tauri-apps/api/core";
   import { onMount } from "svelte";
 
-  let version = $state("Loading...");
+  const SUPPORTED_CLI_VERSION = "2.1.50";
+
+  let installedVersion = $state("Loading...");
+
+  function compareVersions(a: string, b: string): number {
+    const aParts = a.split(".").map(Number);
+    const bParts = b.split(".").map(Number);
+    for (let i = 0; i < Math.max(aParts.length, bParts.length); i++) {
+      const aVal = aParts[i] ?? 0;
+      const bVal = bParts[i] ?? 0;
+      if (aVal > bVal) return 1;
+      if (aVal < bVal) return -1;
+    }
+    return 0;
+  }
+
+  let displayVersion = $derived(installedVersion.split(" (")[0]);
+
+  let supportedBadgeState = $derived.by(() => {
+    if (installedVersion === "Loading..." || installedVersion === "Unknown") {
+      return "neutral";
+    }
+    const semverMatch = /(\d+\.\d+\.\d+)/.exec(installedVersion);
+    if (!semverMatch) return "neutral";
+    const cmp = compareVersions(semverMatch[1], SUPPORTED_CLI_VERSION);
+    if (cmp > 0) return "ahead";
+    if (cmp < 0) return "behind";
+    return "current";
+  });
 
   async function fetchVersion() {
     try {
       const result = await invoke<string>("get_claude_version");
-      version = result;
+      installedVersion = result;
     } catch (error) {
       console.error("Failed to get Claude CLI version:", error);
-      version = "Unknown";
+      installedVersion = "Unknown";
     }
   }
 
@@ -19,25 +47,60 @@
   });
 </script>
 
-<div class="cli-version">
+<div class="cli-versions">
-  <svg
+  <div class="cli-version">
-    class="terminal-icon"
+    <svg
-    width="14"
+      class="terminal-icon"
-    height="14"
+      width="14"
-    viewBox="0 0 24 24"
+      height="14"
-    fill="none"
+      viewBox="0 0 24 24"
-    stroke="currentColor"
+      fill="none"
-    stroke-width="2"
+      stroke="currentColor"
-    stroke-linecap="round"
+      stroke-width="2"
-    stroke-linejoin="round"
+      stroke-linecap="round"
-  >
+      stroke-linejoin="round"
-    <polyline points="4 17 10 11 4 5" />
+    >
-    <line x1="12" y1="19" x2="20" y2="19" />
+      <polyline points="4 17 10 11 4 5" />
-  </svg>
+      <line x1="12" y1="19" x2="20" y2="19" />
-  <span class="version-text">CLI {version}</span>
+    </svg>
+    <span class="version-text">CLI {displayVersion}</span>
+  </div>
+
+  <div class="cli-version supported {supportedBadgeState}" title="Highest audited CLI version">
+    <svg
+      class="terminal-icon"
+      width="14"
+      height="14"
+      viewBox="0 0 24 24"
+      fill="none"
+      stroke="currentColor"
+      stroke-width="2"
+      stroke-linecap="round"
+      stroke-linejoin="round"
+    >
+      <path d="M12 22s8-4 8-10V5l-8-3-8 3v7c0 6 8 10 8 10z" />
+    </svg>
+    <span class="version-text">Supported {SUPPORTED_CLI_VERSION}</span>
+  </div>
+
+  {#if supportedBadgeState === "ahead"}
+    <span class="version-warning ahead"
+      >Your version is newer, some features may not be supported</span
+    >
+  {:else if supportedBadgeState === "behind"}
+    <span class="version-warning behind"
+      >Your version is out of date, please update to ensure compatibility</span
+    >
+  {/if}
 </div>
 
 <style>
+  .cli-versions {
+    display: flex;
+    gap: 6px;
+    align-items: center;
+  }
+
   .cli-version {
     display: flex;
     align-items: center;
@@ -57,6 +120,21 @@
     color: var(--accent-primary);
   }
 
+  .cli-version.supported.current {
+    border-color: var(--success-color, #4caf50);
+    color: var(--success-color, #4caf50);
+  }
+
+  .cli-version.supported.ahead {
+    border-color: var(--warning-color, #ff9800);
+    color: var(--warning-color, #ff9800);
+  }
+
+  .cli-version.supported.behind {
+    border-color: var(--error-color, #f44336);
+    color: var(--error-color, #f44336);
+  }
+
   .terminal-icon {
     flex-shrink: 0;
     opacity: 0.7;
@@ -65,4 +143,18 @@
   .version-text {
     white-space: nowrap;
   }
+
+  .version-warning {
+    font-size: 0.75rem;
+    font-style: italic;
+    white-space: nowrap;
+  }
+
+  .version-warning.ahead {
+    color: var(--warning-color, #ff9800);
+  }
+
+  .version-warning.behind {
+    color: var(--error-color, #f44336);
+  }
 </style>

src/lib/components/ConfigSidebar.svelte

@@ -12,6 +12,7 @@
   } from "$lib/stores/config";
   import { claudeStore } from "$lib/stores/claude";
   import { getCurrentWindow } from "@tauri-apps/api/window";
+  import { invoke } from "@tauri-apps/api/core";
   import CostSummary from "./CostSummary.svelte";
 
   let config: HikariConfig = $state({
@@ -52,10 +53,26 @@
     budget_warning_threshold: 0.8,
     discord_rpc_enabled: true,
     show_thinking_blocks: true,
+    use_worktree: false,
+    disable_1m_context: false,
   });
 
   let showCustomThemeEditor = $state(false);
 
+  interface AuthStatus {
+    is_logged_in: boolean;
+    email: string | null;
+    org_name: string | null;
+    api_key_source: string | null;
+    api_provider: string | null;
+    subscription_type: string | null;
+  }
+
+  let authStatus: AuthStatus | null = $state(null);
+  let authLoading = $state(false);
+  let authActionLoading = $state(false);
+  let authError: string | null = $state(null);
+
   let isOpen = $state(false);
   let isSaving = $state(false);
   let saveError: string | null = $state(null);
@@ -69,6 +86,9 @@
 
   configStore.isSidebarOpen.subscribe((open) => {
     isOpen = open;
+    if (open && authStatus === null) {
+      void refreshAuthStatus();
+    }
   });
 
   configStore.saveError.subscribe((error) => {
@@ -83,8 +103,9 @@
     { value: "", label: "Default (from ~/.claude)" },
     // Current generation (Claude 4.6)
     { value: "claude-opus-4-6", label: "Claude Opus 4.6 (Most Capable)" },
+    { value: "claude-sonnet-4-6", label: "Claude Sonnet 4.6 (Recommended)" },
     // Previous generation (Claude 4.5)
-    { value: "claude-sonnet-4-5-20250929", label: "Claude Sonnet 4.5 (Recommended)" },
+    { value: "claude-sonnet-4-5-20250929", label: "Claude Sonnet 4.5" },
     { value: "claude-haiku-4-5-20251001", label: "Claude Haiku 4.5 (Fast & Cheap)" },
     { value: "claude-opus-4-5-20251101", label: "Claude Opus 4.5" },
     // Previous generation (Claude 4.x)
@@ -110,6 +131,44 @@
     "Task",
   ];
 
+  async function refreshAuthStatus() {
+    authLoading = true;
+    authError = null;
+    try {
+      authStatus = await invoke<AuthStatus>("get_auth_status");
+    } catch (e) {
+      authError = String(e);
+    } finally {
+      authLoading = false;
+    }
+  }
+
+  async function handleAuthLogin() {
+    authActionLoading = true;
+    authError = null;
+    try {
+      await invoke<string>("auth_login");
+      await refreshAuthStatus();
+    } catch (e) {
+      authError = String(e);
+    } finally {
+      authActionLoading = false;
+    }
+  }
+
+  async function handleAuthLogout() {
+    authActionLoading = true;
+    authError = null;
+    try {
+      await invoke<string>("auth_logout");
+      await refreshAuthStatus();
+    } catch (e) {
+      authError = String(e);
+    } finally {
+      authActionLoading = false;
+    }
+  }
+
   async function handleSave() {
     isSaving = true;
     saveError = null;
@@ -227,6 +286,101 @@
       </div>
     {/if}
 
+    <!-- Account Section -->
+    <section class="mb-6">
+      <h3 class="text-sm font-medium text-[var(--accent-primary)] uppercase tracking-wider mb-3">
+        Account
+      </h3>
+
+      {#if authLoading}
+        <div class="text-sm text-[var(--text-secondary)] py-2">Checking auth status...</div>
+      {:else if authStatus}
+        <div class="flex items-center gap-2 mb-3">
+          <span
+            class="inline-block w-2.5 h-2.5 rounded-full flex-shrink-0 {authStatus.is_logged_in
+              ? 'bg-green-500'
+              : 'bg-red-500'}"
+          ></span>
+          <span class="text-sm font-medium text-[var(--text-primary)]">
+            {authStatus.is_logged_in ? "Logged in" : "Not logged in"}
+          </span>
+        </div>
+        {#if authStatus.email || authStatus.org_name || authStatus.api_key_source || config.api_key}
+          <dl class="text-xs space-y-1 mb-3">
+            {#if authStatus.email}
+              <div class="flex gap-2">
+                <dt class="text-[var(--text-tertiary)] w-20 flex-shrink-0">Email</dt>
+                <dd class="text-[var(--text-primary)] break-all">{authStatus.email}</dd>
+              </div>
+            {/if}
+            {#if authStatus.org_name}
+              <div class="flex gap-2">
+                <dt class="text-[var(--text-tertiary)] w-20 flex-shrink-0">Org</dt>
+                <dd class="text-[var(--text-primary)]">{authStatus.org_name}</dd>
+              </div>
+            {/if}
+            {#if authStatus.api_key_source}
+              <div class="flex gap-2">
+                <dt class="text-[var(--text-tertiary)] w-20 flex-shrink-0">API key</dt>
+                <dd class="text-[var(--text-primary)]">{authStatus.api_key_source}</dd>
+              </div>
+            {/if}
+            {#if authStatus.subscription_type}
+              <div class="flex gap-2">
+                <dt class="text-[var(--text-tertiary)] w-20 flex-shrink-0">Plan</dt>
+                <dd class="text-[var(--text-primary)]">{authStatus.subscription_type}</dd>
+              </div>
+            {/if}
+            <div class="flex gap-2">
+              <dt class="text-[var(--text-tertiary)] w-20 flex-shrink-0">Override</dt>
+              <dd class="text-[var(--text-primary)]">
+                {#if config.api_key}
+                  {config.streamer_mode ? "Custom key set 🔒" : "Custom key set"}
+                {:else}
+                  None
+                {/if}
+              </dd>
+            </div>
+          </dl>
+        {/if}
+      {:else}
+        <div class="text-sm text-[var(--text-secondary)] py-2">Auth status unavailable</div>
+      {/if}
+
+      {#if authError}
+        <div class="mb-3 p-2 bg-red-500/20 border border-red-500/50 rounded text-red-400 text-xs">
+          {authError}
+        </div>
+      {/if}
+
+      <div class="flex gap-2">
+        <button
+          onclick={refreshAuthStatus}
+          disabled={authLoading || authActionLoading}
+          class="px-3 py-1.5 text-sm bg-[var(--bg-primary)] border border-[var(--border-color)] rounded-lg text-[var(--text-secondary)] hover:border-[var(--accent-primary)] hover:text-[var(--text-primary)] transition-colors disabled:opacity-50"
+        >
+          Refresh
+        </button>
+        {#if authStatus && !authStatus.is_logged_in}
+          <button
+            onclick={handleAuthLogin}
+            disabled={authActionLoading}
+            class="btn-trans-gradient px-3 py-1.5 text-sm rounded-lg disabled:opacity-50"
+          >
+            {authActionLoading ? "Logging in..." : "Login"}
+          </button>
+        {:else if authStatus && authStatus.is_logged_in}
+          <button
+            onclick={handleAuthLogout}
+            disabled={authActionLoading}
+            class="px-3 py-1.5 text-sm bg-red-500/20 border border-red-500/50 rounded-lg text-red-400 hover:bg-red-500/30 transition-colors disabled:opacity-50"
+          >
+            {authActionLoading ? "Logging out..." : "Logout"}
+          </button>
+        {/if}
+      </div>
+    </section>
+
     <!-- Agent Settings Section -->
     <section class="mb-6">
       <h3 class="text-sm font-medium text-[var(--accent-primary)] uppercase tracking-wider mb-3">
@@ -321,6 +475,37 @@
           class="w-full px-3 py-2 bg-[var(--bg-primary)] border border-[var(--border-color)] rounded-lg text-[var(--text-primary)] focus:outline-none focus:border-[var(--accent-primary)] resize-none"
         ></textarea>
       </div>
+
+      <!-- Worktree Isolation -->
+      <div class="mb-4">
+        <label class="flex items-center gap-3 cursor-pointer">
+          <input
+            type="checkbox"
+            bind:checked={config.use_worktree}
+            class="w-4 h-4 rounded border-[var(--border-color)] bg-[var(--bg-primary)] text-[var(--accent-primary)] focus:ring-[var(--accent-primary)]"
+          />
+          <span class="text-sm text-[var(--text-primary)]">Worktree isolation</span>
+        </label>
+        <p class="text-xs text-[var(--text-tertiary)] mt-1 ml-7">
+          Launch sessions with <code class="font-mono">--worktree</code> for isolated git worktree environments
+        </p>
+      </div>
+
+      <!-- Disable 1M Context Window -->
+      <div class="mb-4">
+        <label class="flex items-center gap-3 cursor-pointer">
+          <input
+            type="checkbox"
+            bind:checked={config.disable_1m_context}
+            class="w-4 h-4 rounded border-[var(--border-color)] bg-[var(--bg-primary)] text-[var(--accent-primary)] focus:ring-[var(--accent-primary)]"
+          />
+          <span class="text-sm text-[var(--text-primary)]">Disable 1M context window</span>
+        </label>
+        <p class="text-xs text-[var(--text-tertiary)] mt-1 ml-7">
+          Sets <code class="font-mono">CLAUDE_CODE_DISABLE_1M_CONTEXT=1</code> to opt out of the extended
+          context window
+        </p>
+      </div>
     </section>
 
     <!-- Greeting Section -->

src/lib/components/InputBar.svelte

@@ -362,6 +362,8 @@ User: ${formattedMessage}`;
               custom_instructions: config.custom_instructions || null,
               mcp_servers_json: config.mcp_servers_json || null,
               allowed_tools: allAllowedTools,
+              use_worktree: config.use_worktree ?? false,
+              disable_1m_context: config.disable_1m_context ?? false,
             },
           });
 

src/lib/components/MemoryBrowserPanel.svelte

@@ -1,7 +1,6 @@
 <script lang="ts">
   import { onMount } from "svelte";
   import { invoke } from "@tauri-apps/api/core";
-  import { readTextFile } from "@tauri-apps/plugin-fs";
   import Markdown from "./Markdown.svelte";
 
   let memoryFiles: string[] = $state([]);
@@ -33,7 +32,8 @@
     isLoading = true;
     error = null;
     try {
-      const content = await readTextFile(filePath);
+      // Use our backend command instead of Tauri plugin to handle WSL paths
+      const content = await invoke<string>("read_file_content", { path: filePath });
       fileContent = content;
       selectedFile = filePath;
     } catch (e) {

src/lib/components/PermissionModal.svelte

@@ -87,6 +87,8 @@
           custom_instructions: config.custom_instructions || null,
           mcp_servers_json: config.mcp_servers_json || null,
           allowed_tools: newGrantedTools,
+          use_worktree: config.use_worktree ?? false,
+          disable_1m_context: config.disable_1m_context ?? false,
         },
       });
 

src/lib/components/StatusBar.svelte

@@ -27,6 +27,7 @@
   import GitPanel from "./GitPanel.svelte";
   import ProfilePanel from "./ProfilePanel.svelte";
   import AgentMonitorPanel from "./AgentMonitorPanel.svelte";
+  import CastPanel from "./CastPanel.svelte";
   import PluginManagementPanel from "./PluginManagementPanel.svelte";
   import McpManagementPanel from "./McpManagementPanel.svelte";
   import { conversationsStore } from "$lib/stores/conversations";
@@ -56,6 +57,7 @@
   let showGitPanel = $state(false);
   let showProfile = $state(false);
   let showAgentMonitor = $state(false);
+  let showCastPanel = $state(false);
   let showPluginPanel = $state(false);
   let showMcpPanel = $state(false);
   let isSummarising = $state(false);
@@ -99,6 +101,8 @@
     budget_warning_threshold: 0.8,
     discord_rpc_enabled: true,
     show_thinking_blocks: true,
+    use_worktree: false,
+    disable_1m_context: false,
   });
 
   let streamerModeActive = $state(false);
@@ -176,6 +180,8 @@
           custom_instructions: currentConfig.custom_instructions || null,
           mcp_servers_json: currentConfig.mcp_servers_json || null,
           allowed_tools: allAllowedTools,
+          use_worktree: currentConfig.use_worktree ?? false,
+          disable_1m_context: currentConfig.disable_1m_context ?? false,
         },
       });
 
@@ -287,6 +293,8 @@
           custom_instructions: currentConfig.custom_instructions || null,
           mcp_servers_json: currentConfig.mcp_servers_json || null,
           allowed_tools: allAllowedTools,
+          use_worktree: currentConfig.use_worktree ?? false,
+          disable_1m_context: currentConfig.disable_1m_context ?? false,
         },
       });
 
@@ -519,6 +527,20 @@
         />
       </svg>
     </button>
+    <button
+      onclick={() => (showCastPanel = true)}
+      class="p-1 text-gray-500 icon-trans-hover"
+      title="Meet the Team"
+    >
+      <svg class="w-5 h-5" fill="none" stroke="currentColor" viewBox="0 0 24 24">
+        <path
+          stroke-linecap="round"
+          stroke-linejoin="round"
+          stroke-width="2"
+          d="M17 20h5v-2a3 3 0 00-5.356-1.857M17 20H7m10 0v-2c0-.656-.126-1.283-.356-1.857M7 20H2v-2a3 3 0 015.356-1.857M7 20v-2c0-.656.126-1.283.356-1.857m0 0a5.002 5.002 0 019.288 0M15 7a3 3 0 11-6 0 3 3 0 016 0zm6 3a2 2 0 11-4 0 2 2 0 014 0zM7 10a2 2 0 11-4 0 2 2 0 014 0z"
+        />
+      </svg>
+    </button>
     <button
       onclick={() => (showAgentMonitor = !showAgentMonitor)}
       class="p-1 text-gray-500 icon-trans-hover relative {showAgentMonitor
@@ -737,6 +759,10 @@
   <AgentMonitorPanel isOpen={showAgentMonitor} onClose={() => (showAgentMonitor = false)} />
 {/if}
 
+{#if showCastPanel}
+  <CastPanel onClose={() => (showCastPanel = false)} />
+{/if}
+
 {#if showPluginPanel}
   <PluginManagementPanel onClose={() => (showPluginPanel = false)} />
 {/if}

src/lib/components/Terminal.svelte

@@ -1,6 +1,8 @@
 <script lang="ts">
   import { claudeStore, type TerminalLine } from "$lib/stores/claude";
   import { afterUpdate, tick, onMount, onDestroy } from "svelte";
+  import { invoke } from "@tauri-apps/api/core";
+
   import ConversationTabs from "./ConversationTabs.svelte";
   import Markdown from "./Markdown.svelte";
   import HighlightedText from "./HighlightedText.svelte";
@@ -92,6 +94,14 @@
         return "terminal-error";
       case "thinking":
         return "terminal-thinking";
+      case "rate-limit":
+        return "terminal-rate-limit";
+      case "compact-prompt":
+        return "terminal-compact-prompt";
+      case "worktree":
+        return "terminal-worktree";
+      case "config-change":
+        return "terminal-config-change";
       default:
         return "terminal-default";
     }
@@ -109,6 +119,12 @@
         return "[tool]";
       case "error":
         return "[error]";
+      case "rate-limit":
+        return "[rate-limit]";
+      case "worktree":
+        return "[worktree]";
+      case "config-change":
+        return "[config]";
       default:
         return "";
     }
@@ -187,6 +203,27 @@
       copiedMessageId = null;
     }, 2000);
   }
+
+  async function handleCompact() {
+    if (!currentConversationId) return;
+    await invoke("send_prompt", { conversationId: currentConversationId, message: "/compact" });
+  }
+
+  // Collapsible tool lines
+  const TOOL_COLLAPSE_THRESHOLD = 60;
+  let expandedToolLines: Record<string, boolean> = {};
+
+  function isToolContentLong(content: string): boolean {
+    return content.length > TOOL_COLLAPSE_THRESHOLD;
+  }
+
+  function truncateToolContent(content: string): string {
+    return content.slice(0, TOOL_COLLAPSE_THRESHOLD) + "…";
+  }
+
+  function toggleToolLine(id: string) {
+    expandedToolLines = { ...expandedToolLines, [id]: !expandedToolLines[id] };
+  }
 </script>
 
 <div
@@ -262,7 +299,11 @@
             {#if line.toolName}
               <span class="terminal-tool-name mr-2">[{line.toolName}]</span>
             {/if}
-            {#if line.type === "assistant" || line.type === "user"}
+            {#if line.type === "compact-prompt"}
+              <button class="compact-action-btn" onclick={handleCompact}>
+                ⚡ Compact Conversation
+              </button>
+            {:else if line.type === "assistant" || line.type === "user"}
               <div class="message-content-wrapper">
                 <Markdown
                   content={maskPaths(line.content, hidePaths)}
@@ -289,6 +330,22 @@
                   <span class="copy-text">{copiedMessageId === line.id ? "Copied!" : "Copy"}</span>
                 </button>
               </div>
+            {:else if line.type === "tool" && isToolContentLong(maskPaths(line.content, hidePaths))}
+              <span class="tool-collapsible">
+                <HighlightedText
+                  content={expandedToolLines[line.id]
+                    ? maskPaths(line.content, hidePaths)
+                    : truncateToolContent(maskPaths(line.content, hidePaths))}
+                  searchQuery={currentSearchQuery}
+                />
+                <button
+                  class="tool-toggle-btn"
+                  onclick={() => toggleToolLine(line.id)}
+                  title={expandedToolLines[line.id] ? "Collapse" : "Expand to see full content"}
+                >
+                  {expandedToolLines[line.id] ? "▲" : "▼"}
+                </button>
+              </span>
             {:else}
               <HighlightedText
                 content={maskPaths(line.content, hidePaths)}
@@ -329,6 +386,42 @@
     color: var(--terminal-error, #f87171);
   }
 
+  .terminal-rate-limit {
+    color: var(--terminal-rate-limit, #fb923c);
+  }
+
+  .terminal-compact-prompt {
+    color: var(--text-secondary);
+  }
+
+  .terminal-worktree {
+    color: var(--terminal-worktree, #34d399);
+  }
+
+  .terminal-config-change {
+    color: var(--terminal-config-change, #a78bfa);
+  }
+
+  .compact-action-btn {
+    display: inline-flex;
+    align-items: center;
+    gap: 0.4em;
+    background: var(--bg-secondary);
+    border: 1px solid var(--terminal-error, #f87171);
+    color: var(--terminal-error, #f87171);
+    padding: 0.3em 0.8em;
+    cursor: pointer;
+    border-radius: 4px;
+    font-size: 0.9em;
+    font-family: inherit;
+    transition: all 0.15s ease;
+  }
+
+  .compact-action-btn:hover {
+    background: color-mix(in srgb, var(--terminal-error, #f87171) 15%, transparent);
+    color: var(--terminal-error, #f87171);
+  }
+
   .terminal-default {
     color: var(--text-primary);
   }
@@ -408,4 +501,28 @@
   .terminal-line {
     position: relative;
   }
+
+  .tool-collapsible {
+    display: inline-flex;
+    align-items: baseline;
+    gap: 0.4em;
+  }
+
+  .tool-toggle-btn {
+    background: none;
+    border: none;
+    color: var(--text-tertiary, #6b7280);
+    cursor: pointer;
+    font-size: 0.7em;
+    padding: 0;
+    line-height: 1;
+    opacity: 0.7;
+    transition: opacity 0.15s ease;
+    font-family: inherit;
+  }
+
+  .tool-toggle-btn:hover {
+    opacity: 1;
+    color: var(--terminal-tool, #c084fc);
+  }
 </style>

src/lib/components/Terminal.test.ts

@@ -0,0 +1,264 @@
+/**
+ * Terminal Component Tests
+ *
+ * Tests the pure helper functions extracted from the Terminal component:
+ * - getLineClass: maps line types to CSS class names
+ * - getLinePrefix: maps line types to display prefixes
+ * - formatTime: formats a Date as "HH:MM AM/PM"
+ * - isToolContentLong: checks if tool content exceeds collapse threshold
+ * - truncateToolContent: truncates long tool content with ellipsis
+ *
+ * Manual testing checklist:
+ * - [ ] rate-limit lines appear in amber
+ * - [ ] error lines appear in red
+ * - [ ] tool lines appear in purple
+ * - [ ] system lines appear in grey italic
+ * - [ ] user lines appear in cyan
+ * - [ ] assistant lines appear in primary text colour
+ * - [ ] long tool content is collapsed by default with a toggle button
+ */
+
+import { describe, it, expect } from "vitest";
+
+// Mirror functions from Terminal.svelte for isolated testing
+
+function getLineClass(type: string): string {
+  switch (type) {
+    case "user":
+      return "terminal-user";
+    case "assistant":
+      return "terminal-assistant";
+    case "system":
+      return "terminal-system italic";
+    case "tool":
+      return "terminal-tool";
+    case "error":
+      return "terminal-error";
+    case "thinking":
+      return "terminal-thinking";
+    case "rate-limit":
+      return "terminal-rate-limit";
+    case "compact-prompt":
+      return "terminal-compact-prompt";
+    case "worktree":
+      return "terminal-worktree";
+    case "config-change":
+      return "terminal-config-change";
+    default:
+      return "terminal-default";
+  }
+}
+
+function getLinePrefix(type: string): string {
+  switch (type) {
+    case "user":
+      return ">";
+    case "assistant":
+      return "";
+    case "system":
+      return "[system]";
+    case "tool":
+      return "[tool]";
+    case "error":
+      return "[error]";
+    case "rate-limit":
+      return "[rate-limit]";
+    case "worktree":
+      return "[worktree]";
+    case "config-change":
+      return "[config]";
+    default:
+      return "";
+  }
+}
+
+function formatTime(date: Date): string {
+  return date.toLocaleTimeString("en-US", {
+    hour: "2-digit",
+    minute: "2-digit",
+  });
+}
+
+const TOOL_COLLAPSE_THRESHOLD = 60;
+
+function isToolContentLong(content: string): boolean {
+  return content.length > TOOL_COLLAPSE_THRESHOLD;
+}
+
+function truncateToolContent(content: string): string {
+  return content.slice(0, TOOL_COLLAPSE_THRESHOLD) + "…";
+}
+
+// ---
+
+describe("getLineClass", () => {
+  it("returns terminal-user for user lines", () => {
+    expect(getLineClass("user")).toBe("terminal-user");
+  });
+
+  it("returns terminal-assistant for assistant lines", () => {
+    expect(getLineClass("assistant")).toBe("terminal-assistant");
+  });
+
+  it("returns terminal-system italic for system lines", () => {
+    expect(getLineClass("system")).toBe("terminal-system italic");
+  });
+
+  it("returns terminal-tool for tool lines", () => {
+    expect(getLineClass("tool")).toBe("terminal-tool");
+  });
+
+  it("returns terminal-error for error lines", () => {
+    expect(getLineClass("error")).toBe("terminal-error");
+  });
+
+  it("returns terminal-thinking for thinking lines", () => {
+    expect(getLineClass("thinking")).toBe("terminal-thinking");
+  });
+
+  it("returns terminal-rate-limit for rate-limit lines", () => {
+    expect(getLineClass("rate-limit")).toBe("terminal-rate-limit");
+  });
+
+  it("returns terminal-compact-prompt for compact-prompt lines", () => {
+    expect(getLineClass("compact-prompt")).toBe("terminal-compact-prompt");
+  });
+
+  it("returns terminal-worktree for worktree lines", () => {
+    expect(getLineClass("worktree")).toBe("terminal-worktree");
+  });
+
+  it("returns terminal-config-change for config-change lines", () => {
+    expect(getLineClass("config-change")).toBe("terminal-config-change");
+  });
+
+  it("returns terminal-default for unknown line types", () => {
+    expect(getLineClass("unknown")).toBe("terminal-default");
+    expect(getLineClass("")).toBe("terminal-default");
+    expect(getLineClass("random-future-type")).toBe("terminal-default");
+  });
+});
+
+describe("getLinePrefix", () => {
+  it("returns > for user lines", () => {
+    expect(getLinePrefix("user")).toBe(">");
+  });
+
+  it("returns empty string for assistant lines", () => {
+    expect(getLinePrefix("assistant")).toBe("");
+  });
+
+  it("returns [system] for system lines", () => {
+    expect(getLinePrefix("system")).toBe("[system]");
+  });
+
+  it("returns [tool] for tool lines", () => {
+    expect(getLinePrefix("tool")).toBe("[tool]");
+  });
+
+  it("returns [error] for error lines", () => {
+    expect(getLinePrefix("error")).toBe("[error]");
+  });
+
+  it("returns [rate-limit] for rate-limit lines", () => {
+    expect(getLinePrefix("rate-limit")).toBe("[rate-limit]");
+  });
+
+  it("returns empty string for compact-prompt lines (button renders instead)", () => {
+    expect(getLinePrefix("compact-prompt")).toBe("");
+  });
+
+  it("returns [worktree] for worktree lines", () => {
+    expect(getLinePrefix("worktree")).toBe("[worktree]");
+  });
+
+  it("returns [config] for config-change lines", () => {
+    expect(getLinePrefix("config-change")).toBe("[config]");
+  });
+
+  it("returns empty string for thinking lines (no prefix)", () => {
+    expect(getLinePrefix("thinking")).toBe("");
+  });
+
+  it("returns empty string for unknown line types", () => {
+    expect(getLinePrefix("unknown")).toBe("");
+    expect(getLinePrefix("")).toBe("");
+  });
+});
+
+describe("formatTime", () => {
+  it("formats time in 12-hour format with AM/PM", () => {
+    const date = new Date(2026, 1, 7, 14, 35);
+    const formatted = formatTime(date);
+    expect(formatted).toMatch(/\d{2}:\d{2}\s?(AM|PM)/i);
+  });
+
+  it("formats afternoon times correctly", () => {
+    const date = new Date(2026, 1, 7, 14, 35);
+    const formatted = formatTime(date);
+    expect(formatted).toContain("02:35");
+    expect(formatted.toUpperCase()).toContain("PM");
+  });
+
+  it("formats morning times correctly", () => {
+    const date = new Date(2026, 1, 7, 9, 5);
+    const formatted = formatTime(date);
+    expect(formatted).toContain("09:05");
+    expect(formatted.toUpperCase()).toContain("AM");
+  });
+
+  it("formats midnight correctly", () => {
+    const date = new Date(2026, 1, 7, 0, 0);
+    const formatted = formatTime(date);
+    expect(formatted).toContain("12:00");
+    expect(formatted.toUpperCase()).toContain("AM");
+  });
+
+  it("formats noon correctly", () => {
+    const date = new Date(2026, 1, 7, 12, 0);
+    const formatted = formatTime(date);
+    expect(formatted).toContain("12:00");
+    expect(formatted.toUpperCase()).toContain("PM");
+  });
+});
+
+describe("isToolContentLong", () => {
+  it("returns false for content at or below the threshold", () => {
+    const exactThreshold = "x".repeat(TOOL_COLLAPSE_THRESHOLD);
+    expect(isToolContentLong(exactThreshold)).toBe(false);
+  });
+
+  it("returns true for content exceeding the threshold", () => {
+    const overThreshold = "x".repeat(TOOL_COLLAPSE_THRESHOLD + 1);
+    expect(isToolContentLong(overThreshold)).toBe(true);
+  });
+
+  it("returns false for short content", () => {
+    expect(isToolContentLong("short")).toBe(false);
+  });
+
+  it("returns false for empty content", () => {
+    expect(isToolContentLong("")).toBe(false);
+  });
+});
+
+describe("truncateToolContent", () => {
+  it("truncates content to the threshold length with an ellipsis", () => {
+    const long = "x".repeat(100);
+    const result = truncateToolContent(long);
+    expect(result).toBe("x".repeat(TOOL_COLLAPSE_THRESHOLD) + "…");
+  });
+
+  it("keeps content shorter than threshold unchanged (plus ellipsis)", () => {
+    const short = "hello";
+    const result = truncateToolContent(short);
+    expect(result).toBe("hello…");
+  });
+
+  it("uses the unicode ellipsis character (not three dots)", () => {
+    const long = "x".repeat(100);
+    const result = truncateToolContent(long);
+    expect(result.endsWith("…")).toBe(true);
+    expect(result.endsWith("...")).toBe(false);
+  });
+});

src/lib/components/UserQuestionModal.svelte

@@ -106,6 +106,8 @@
           custom_instructions: config.custom_instructions || null,
           mcp_servers_json: config.mcp_servers_json || null,
           allowed_tools: grantedToolsList,
+          use_worktree: config.use_worktree ?? false,
+          disable_1m_context: config.disable_1m_context ?? false,
         },
       });
 

src/lib/stores/agents.test.ts

@@ -2,12 +2,15 @@ import { describe, it, expect, beforeEach } from "vitest";
 import { agentStore, getAgentsForConversation, runningAgentCount } from "./agents";
 import { get } from "svelte/store";
 import type { AgentInfo } from "$lib/types/agents";
+import { CHARACTER_POOL } from "$lib/utils/agentCharacters";
 
 describe("agents store", () => {
   const conversationId = "test-conversation-1";
   const otherConversationId = "test-conversation-2";
 
-  const createMockAgent = (overrides?: Partial<AgentInfo>): AgentInfo => ({
+  type AgentInput = Omit<AgentInfo, "characterName" | "characterAvatar">;
+
+  const createMockAgent = (overrides?: Partial<AgentInput>): AgentInput => ({
     toolUseId: "toolu_test123",
     description: "Test agent",
     subagentType: "Explore",
@@ -37,7 +40,29 @@ describe("agents store", () => {
 
       const agents = get(getAgentsForConversation(conversationId));
       expect(agents).toHaveLength(1);
-      expect(agents[0]).toEqual(agent);
+      expect(agents[0]).toMatchObject(agent);
+    });
+
+    it("assigns a character name and avatar to added agents", () => {
+      const agent = createMockAgent();
+      agentStore.addAgent(conversationId, agent);
+
+      const agents = get(getAgentsForConversation(conversationId));
+      const validNames = CHARACTER_POOL.map((c) => c.name);
+      expect(validNames).toContain(agents[0].characterName);
+      expect(agents[0].characterAvatar).toMatch(/^https:\/\//u);
+    });
+
+    it("avoids duplicate character names across agents when possible", () => {
+      // Add 6 agents - each should ideally get a unique character
+      for (let i = 0; i < 6; i++) {
+        agentStore.addAgent(conversationId, createMockAgent({ toolUseId: `tool${i.toString()}` }));
+      }
+
+      const agents = get(getAgentsForConversation(conversationId));
+      const names = agents.map((a) => a.characterName);
+      const uniqueNames = new Set(names);
+      expect(uniqueNames.size).toBe(6);
     });
 
     it("adds multiple agents to the same conversation", () => {
@@ -49,8 +74,8 @@ describe("agents store", () => {
 
       const agents = get(getAgentsForConversation(conversationId));
       expect(agents).toHaveLength(2);
-      expect(agents[0]).toEqual(agent1);
+      expect(agents[0]).toMatchObject(agent1);
-      expect(agents[1]).toEqual(agent2);
+      expect(agents[1]).toMatchObject(agent2);
     });
 
     it("keeps agents in different conversations separate", () => {
@@ -65,8 +90,8 @@ describe("agents store", () => {
 
       expect(agents1).toHaveLength(1);
       expect(agents2).toHaveLength(1);
-      expect(agents1[0]).toEqual(agent1);
+      expect(agents1[0]).toMatchObject(agent1);
-      expect(agents2[0]).toEqual(agent2);
+      expect(agents2[0]).toMatchObject(agent2);
     });
   });
 
@@ -152,6 +177,32 @@ describe("agents store", () => {
       const agents = get(getAgentsForConversation(conversationId));
       expect(agents[0].status).toBe("running"); // Status unchanged
     });
+
+    it("stores lastAssistantMessage when provided", () => {
+      const agent = createMockAgent({ status: "running" });
+      agentStore.addAgent(conversationId, agent);
+
+      agentStore.endAgent(
+        conversationId,
+        agent.toolUseId,
+        Date.now(),
+        false,
+        "Task completed successfully."
+      );
+
+      const agents = get(getAgentsForConversation(conversationId));
+      expect(agents[0].lastAssistantMessage).toBe("Task completed successfully.");
+    });
+
+    it("leaves lastAssistantMessage undefined when not provided", () => {
+      const agent = createMockAgent({ status: "running" });
+      agentStore.addAgent(conversationId, agent);
+
+      agentStore.endAgent(conversationId, agent.toolUseId, Date.now(), false);
+
+      const agents = get(getAgentsForConversation(conversationId));
+      expect(agents[0].lastAssistantMessage).toBeUndefined();
+    });
   });
 
   describe("markAllErrored", () => {
@@ -256,7 +307,7 @@ describe("agents store", () => {
 
       expect(agents1).toHaveLength(0);
       expect(agents2).toHaveLength(1);
-      expect(agents2[0]).toEqual(agent2);
+      expect(agents2[0]).toMatchObject(agent2);
     });
 
     it("does nothing if conversation doesn't exist", () => {

src/lib/stores/agents.ts

@@ -1,5 +1,6 @@
 import { writable, derived } from "svelte/store";
 import type { AgentInfo } from "$lib/types/agents";
+import { assignCharacter } from "$lib/utils/agentCharacters";
 
 // Map of conversation ID -> agents in that conversation
 const agentsByConversation = writable<Record<string, AgentInfo[]>>({});
@@ -8,12 +9,17 @@ function createAgentStore() {
   return {
     subscribe: agentsByConversation.subscribe,
 
-    addAgent(conversationId: string, agent: AgentInfo) {
+    addAgent(conversationId: string, agent: Omit<AgentInfo, "characterName" | "characterAvatar">) {
       agentsByConversation.update((state) => {
         const existing = state[conversationId] || [];
+        const activeNames = existing.map((a) => a.characterName);
+        const character = assignCharacter(activeNames);
         return {
           ...state,
-          [conversationId]: [...existing, agent],
+          [conversationId]: [
+            ...existing,
+            { ...agent, characterName: character.name, characterAvatar: character.avatar },
+          ],
         };
       });
     },
@@ -39,7 +45,13 @@ function createAgentStore() {
       });
     },
 
-    endAgent(conversationId: string, toolUseId: string, endedAt: number, isError: boolean) {
+    endAgent(
+      conversationId: string,
+      toolUseId: string,
+      endedAt: number,
+      isError: boolean,
+      lastAssistantMessage?: string
+    ) {
       agentsByConversation.update((state) => {
         const agents = state[conversationId];
         if (!agents) return state;
@@ -56,6 +68,7 @@ function createAgentStore() {
           endedAt,
           status: isError ? "errored" : "completed",
           durationMs,
+          lastAssistantMessage,
         };
 
         return {

src/lib/stores/config.test.ts

@@ -194,6 +194,8 @@ describe("config store", () => {
         budget_warning_threshold: 0.8,
         discord_rpc_enabled: true,
         show_thinking_blocks: true,
+        use_worktree: false,
+        disable_1m_context: false,
       };
 
       expect(config.model).toBe("claude-sonnet-4");
@@ -240,6 +242,8 @@ describe("config store", () => {
         budget_warning_threshold: 0.8,
         discord_rpc_enabled: true,
         show_thinking_blocks: true,
+        use_worktree: false,
+        disable_1m_context: false,
       };
 
       expect(config.model).toBeNull();
@@ -785,6 +789,8 @@ describe("config store", () => {
         budget_warning_threshold: 0.9,
         discord_rpc_enabled: false,
         show_thinking_blocks: true,
+        use_worktree: false,
+        disable_1m_context: false,
       };
 
       const mockInvokeImpl = vi.mocked(invoke);

src/lib/stores/config.ts

@@ -47,6 +47,10 @@ export interface HikariConfig {
   discord_rpc_enabled: boolean;
   // Thinking blocks settings
   show_thinking_blocks: boolean;
+  // Worktree isolation
+  use_worktree: boolean;
+  // Disable 1M context window
+  disable_1m_context: boolean;
 }
 
 const defaultConfig: HikariConfig = {
@@ -87,6 +91,8 @@ const defaultConfig: HikariConfig = {
   budget_warning_threshold: 0.8,
   discord_rpc_enabled: true,
   show_thinking_blocks: true,
+  use_worktree: false,
+  disable_1m_context: false,
 };
 
 function createConfigStore() {

src/lib/stores/stats.ts

@@ -12,6 +12,7 @@ export type BudgetType = "token" | "cost";
 export const MODEL_PRICING: Record<string, { input: number; output: number }> = {
   // Current generation (Claude 4.6)
   "claude-opus-4-6": { input: 5.0, output: 25.0 },
+  "claude-sonnet-4-6": { input: 3.0, output: 15.0 },
   // Previous generation (Claude 4.5)
   "claude-opus-4-5-20251101": { input: 5.0, output: 25.0 },
   "claude-sonnet-4-5-20250929": { input: 3.0, output: 15.0 },

src/lib/tauri.ts

@@ -29,6 +29,7 @@ interface StateChangePayload {
 }
 
 const connectedConversations = new Set<string>();
+const greetingPendingConversations = new Set<string>();
 let unlisteners: Array<() => void> = [];
 let skipNextGreeting = false;
 
@@ -55,17 +56,17 @@ function generateGreetingPrompt(): string {
   return `[System: A new session has started. It's currently ${timeOfDay}. Please greet the user warmly and briefly. Keep it short - just 1-2 sentences.]`;
 }
 
-async function sendGreeting(conversationId: string) {
+async function sendGreeting(conversationId: string): Promise<boolean> {
   // Check if we should skip this greeting
   if (skipNextGreeting) {
     skipNextGreeting = false; // Reset the flag
-    return;
+    return false;
   }
 
   const config = configStore.getConfig();
 
   if (!config.greeting_enabled) {
-    return;
+    return false;
   }
 
   const greetingPrompt = config.greeting_custom_prompt?.trim() || generateGreetingPrompt();
@@ -81,10 +82,12 @@ async function sendGreeting(conversationId: string) {
       conversationId,
       message: greetingPrompt,
     });
+    return true;
   } catch (error) {
     console.error("Failed to send greeting:", error);
     claudeStore.addLineToConversation(conversationId, "error", `Failed to send greeting: ${error}`);
     characterState.setTemporaryState("error", 3000);
+    return false;
   }
 }
 
@@ -118,6 +121,7 @@ interface WorkingDirectoryPayload {
 
 export async function cleanupConversationTracking(conversationId: string) {
   connectedConversations.delete(conversationId);
+  greetingPendingConversations.delete(conversationId);
 
   // Clean up any temp files associated with this conversation
   try {
@@ -173,7 +177,24 @@ export async function initializeTauriListeners() {
         if (!connectedConversations.has(targetConversationId)) {
           connectedConversations.add(targetConversationId);
           resetSessionStats(); // Reset session stats on new connection
-          await sendGreeting(targetConversationId);
+
+          // Immediately hold the tab at yellow while we wait for the greeting response.
+          // This avoids a brief green flash before the greeting is even sent.
+          greetingPendingConversations.add(targetConversationId);
+          claudeStore.setConnectionStatusForConversation(
+            targetConversationId,
+            "connecting" as ConnectionStatus
+          );
+
+          const greetingSent = await sendGreeting(targetConversationId);
+          if (!greetingSent) {
+            // Greeting was disabled or failed — flip straight to connected.
+            greetingPendingConversations.delete(targetConversationId);
+            claudeStore.setConnectionStatusForConversation(
+              targetConversationId,
+              "connected" as ConnectionStatus
+            );
+          }
         }
       }
     } else if (status === "disconnected") {
@@ -191,6 +212,7 @@ export async function initializeTauriListeners() {
       // Only remove from connected set if we're not about to reconnect
       if (!skipNextGreeting && targetConversationId) {
         connectedConversations.delete(targetConversationId);
+        greetingPendingConversations.delete(targetConversationId);
       }
 
       // Don't add system message if we're about to reconnect
@@ -205,6 +227,14 @@ export async function initializeTauriListeners() {
         todos.clear();
       }
 
+      // Update the tab's connection status on real disconnects
+      if (!skipNextGreeting && targetConversationId) {
+        claudeStore.setConnectionStatusForConversation(
+          targetConversationId,
+          "disconnected" as ConnectionStatus
+        );
+      }
+
       // Update character state for this conversation
       if (targetConversationId) {
         claudeStore.setCharacterStateForConversation(targetConversationId, "idle");
@@ -214,6 +244,7 @@ export async function initializeTauriListeners() {
 
       if (targetConversationId) {
         connectedConversations.delete(targetConversationId);
+        greetingPendingConversations.delete(targetConversationId);
         claudeStore.addLineToConversation(targetConversationId, "error", "Connection error");
       }
 
@@ -275,11 +306,34 @@ export async function initializeTauriListeners() {
         }
       : undefined;
 
+    // Flip to connected when first assistant message arrives after greeting
+    if (
+      conversation_id &&
+      line_type === "assistant" &&
+      greetingPendingConversations.has(conversation_id)
+    ) {
+      greetingPendingConversations.delete(conversation_id);
+      claudeStore.setConnectionStatusForConversation(
+        conversation_id,
+        "connected" as ConnectionStatus
+      );
+    }
+
     // Always store the output to the correct conversation
     if (conversation_id) {
       claudeStore.addLineToConversation(
         conversation_id,
-        line_type as "user" | "assistant" | "system" | "tool" | "error" | "thinking",
+        line_type as
+          | "user"
+          | "assistant"
+          | "system"
+          | "tool"
+          | "error"
+          | "thinking"
+          | "rate-limit"
+          | "compact-prompt"
+          | "worktree"
+          | "config-change",
         content,
         tool_name || undefined,
         costData,
@@ -288,7 +342,17 @@ export async function initializeTauriListeners() {
     } else {
       // Fallback to active conversation if no conversation_id provided
       claudeStore.addLine(
-        line_type as "user" | "assistant" | "system" | "tool" | "error" | "thinking",
+        line_type as
+          | "user"
+          | "assistant"
+          | "system"
+          | "tool"
+          | "error"
+          | "thinking"
+          | "rate-limit"
+          | "compact-prompt"
+          | "worktree"
+          | "config-change",
         content,
         tool_name || undefined,
         costData,
@@ -410,10 +474,17 @@ export async function initializeTauriListeners() {
   unlisteners.push(agentUpdateUnlisten);
 
   const agentEndUnlisten = await listen<AgentEndPayload>("claude:agent-end", (event) => {
-    const { tool_use_id, ended_at, is_error, conversation_id } = event.payload;
+    const { tool_use_id, ended_at, is_error, conversation_id, last_assistant_message } =
+      event.payload;
     const targetConversationId = conversation_id || get(claudeStore.activeConversationId);
     if (targetConversationId) {
-      agentStore.endAgent(targetConversationId, tool_use_id, ended_at, is_error);
+      agentStore.endAgent(
+        targetConversationId,
+        tool_use_id,
+        ended_at,
+        is_error,
+        last_assistant_message
+      );
     }
   });
   unlisteners.push(agentEndUnlisten);

src/lib/types/agents.ts

@@ -10,6 +10,9 @@ export interface AgentInfo {
   status: AgentStatus;
   parentToolUseId?: string;
   durationMs?: number;
+  characterName: string;
+  characterAvatar: string;
+  lastAssistantMessage?: string;
 }
 
 export interface AgentStartPayload {
@@ -29,4 +32,5 @@ export interface AgentEndPayload {
   conversation_id?: string;
   duration_ms?: number;
   num_turns?: number;
+  last_assistant_message?: string;
 }

src/lib/types/messages.ts

@@ -1,6 +1,16 @@
 export interface TerminalLine {
   id: string;
-  type: "user" | "assistant" | "system" | "tool" | "error" | "thinking";
+  type:
+    | "user"
+    | "assistant"
+    | "system"
+    | "tool"
+    | "error"
+    | "thinking"
+    | "rate-limit"
+    | "compact-prompt"
+    | "worktree"
+    | "config-change";
   content: string;
   timestamp: Date;
   toolName?: string;

src/lib/utils/agentCharacters.test.ts

@@ -0,0 +1,73 @@
+import { describe, it, expect } from "vitest";
+import { CHARACTER_POOL, assignCharacter } from "./agentCharacters";
+
+describe("agentCharacters", () => {
+  describe("CHARACTER_POOL", () => {
+    it("contains exactly 6 characters", () => {
+      expect(CHARACTER_POOL).toHaveLength(6);
+    });
+
+    it("each character has a name, avatar, title, and description", () => {
+      for (const character of CHARACTER_POOL) {
+        expect(character.name).toBeTruthy();
+        expect(character.avatar).toBeTruthy();
+        expect(character.avatar).toMatch(/^https:\/\//u);
+        expect(character.title).toBeTruthy();
+        expect(character.description).toBeTruthy();
+      }
+    });
+
+    it("all names are unique", () => {
+      const names = CHARACTER_POOL.map((c) => c.name);
+      const uniqueNames = new Set(names);
+      expect(uniqueNames.size).toBe(CHARACTER_POOL.length);
+    });
+  });
+
+  describe("assignCharacter", () => {
+    it("returns a character from the pool", () => {
+      const character = assignCharacter([]);
+      const names = CHARACTER_POOL.map((c) => c.name);
+      expect(names).toContain(character.name);
+    });
+
+    it("avoids names already in use when possible", () => {
+      const takenNames = ["Amari", "Keiko", "Minori", "Reina", "Tatsumi"];
+      // Run many times to confirm we never get a taken name
+      for (let i = 0; i < 50; i++) {
+        const character = assignCharacter(takenNames);
+        expect(takenNames).not.toContain(character.name);
+        expect(character.name).toBe("Yumiko");
+      }
+    });
+
+    it("picks from the full pool when all 6 names are taken", () => {
+      const allNames = CHARACTER_POOL.map((c) => c.name);
+      const seen = new Set<string>();
+      // Run enough times that we'd statistically see variety
+      for (let i = 0; i < 100; i++) {
+        const character = assignCharacter(allNames);
+        seen.add(character.name);
+      }
+      // Should still pick valid characters
+      for (const name of seen) {
+        expect(allNames).toContain(name);
+      }
+      // With 100 runs and 6 characters, we should see at least 2 distinct names
+      expect(seen.size).toBeGreaterThan(1);
+    });
+
+    it("returns a character with name, avatar, title, and description", () => {
+      const character = assignCharacter([]);
+      expect(character.name).toBeTruthy();
+      expect(character.avatar).toBeTruthy();
+      expect(character.title).toBeTruthy();
+      expect(character.description).toBeTruthy();
+    });
+
+    it("works when the active list is empty", () => {
+      const character = assignCharacter([]);
+      expect(character).toBeDefined();
+    });
+  });
+});

src/lib/utils/agentCharacters.ts

@@ -0,0 +1,61 @@
+export interface AgentCharacter {
+  name: string;
+  avatar: string;
+  title: string;
+  description: string;
+}
+
+export const CHARACTER_POOL: readonly AgentCharacter[] = [
+  {
+    name: "Amari",
+    avatar: "https://cdn.nhcarrigan.com/amari.png",
+    title: "Executive Assistant",
+    description:
+      "Fey-blooded PA and healer of the team. She always knows when you need a break — and makes sure you take one.",
+  },
+  {
+    name: "Keiko",
+    avatar: "https://cdn.nhcarrigan.com/keiko.png",
+    title: "Chief Security Officer",
+    description:
+      "Bodyguard and shadow of the family. Conceals blades beneath evening gowns; always watching from the dark.",
+  },
+  {
+    name: "Minori",
+    avatar: "https://cdn.nhcarrigan.com/minori.png",
+    title: "Chief Compliance Officer",
+    description:
+      "An ancient Automaton built to guard the Great Library. Perfect memory, perfect logic, perfect dedication.",
+  },
+  {
+    name: "Reina",
+    avatar: "https://cdn.nhcarrigan.com/reina.png",
+    title: "Chief Legal Officer",
+    description:
+      "Demon of the Crossroads turned corporate lawyer. Her binding contracts have held for millennia.",
+  },
+  {
+    name: "Tatsumi",
+    avatar: "https://cdn.nhcarrigan.com/tatsumi.png",
+    title: "Chief Design Officer",
+    description:
+      "A Siren who traded the ocean for a stylus. Uses her glamour to make every interface welcoming and beautiful.",
+  },
+  {
+    name: "Yumiko",
+    avatar: "https://cdn.nhcarrigan.com/yumiko.png",
+    title: "Chief Technology Officer",
+    description:
+      "Technomancer and machine whisperer. She communes with machine spirits and keeps the digital world running.",
+  },
+];
+
+/**
+ * Picks a character for a new subagent.
+ * Avoids names already assigned to active agents unless all six are taken.
+ */
+export function assignCharacter(activeNames: readonly string[]): AgentCharacter {
+  const available = CHARACTER_POOL.filter((c) => !activeNames.includes(c.name));
+  const pool = available.length > 0 ? available : [...CHARACTER_POOL];
+  return pool[Math.floor(Math.random() * pool.length)];
+}