feat(tui): dynamic status indicator for Execute vs Streaming states (#122)

Add distinct status indicators for different streaming phases:
- 'Execute' when request is pending (waiting for first token)
- 'Streaming..' when actively receiving tokens from the LLM

This provides clearer feedback to users about the current state of
their request. Previously, both states showed 'Working' which didn't
distinguish between waiting for a response and actively streaming one.

Changes:
- Add is_actively_streaming field to StreamingState
- Update status_header() to show different text based on streaming phase
- Mark is_actively_streaming = true when first delta arrives

Author: echobt

src/cortex-tui/src/app/streaming.rs

@@ -4,6 +4,9 @@ use std::time::Instant;
 #[derive(Debug, Clone, Default)]
 pub struct StreamingState {
     pub is_streaming: bool,
+    /// Whether we are actively receiving tokens from the LLM.
+    /// False when waiting for first token (processing), true when streaming.
+    pub is_actively_streaming: bool,
     pub current_tool: Option<String>,
     pub tool_status: Option<String>,
     pub thinking: bool,
@@ -29,6 +32,7 @@ impl StreamingState {
     ///   If false, preserves existing timer (use for tool continuations).
     pub fn start(&mut self, tool: Option<String>, reset_timer: bool) {
         self.is_streaming = true;
+        self.is_actively_streaming = false; // Not yet receiving tokens
         self.thinking = true;
         self.current_tool = tool;
         self.task_started_at = Some(Instant::now());
@@ -39,6 +43,12 @@ impl StreamingState {
         }
     }
 
+    /// Mark that we started actively receiving tokens from the LLM.
+    /// This transitions from "Execute" (waiting) to "Streaming.." state.
+    pub fn start_active_streaming(&mut self) {
+        self.is_actively_streaming = true;
+    }
+
     /// Get the elapsed seconds since the task started
     pub fn elapsed_seconds(&self) -> u64 {
         self.task_started_at
@@ -57,6 +67,7 @@ impl StreamingState {
     /// Reset streaming state when task completes
     pub fn stop(&mut self) {
         self.is_streaming = false;
+        self.is_actively_streaming = false;
         self.thinking = false;
         self.current_tool = None;
         self.tool_status = None;

src/cortex-tui/src/runner/event_loop/streaming.rs

@@ -305,6 +305,8 @@ impl EventLoop {
         match event {
             StreamEvent::Delta(delta) => {
                 self.stream_controller.append_text(&delta);
+                // Mark that we are now actively receiving tokens (transition from Execute to Streaming..)
+                self.app_state.streaming.start_active_streaming();
                 // Track text for interleaved display
                 self.app_state.append_streaming_text(&delta);
                 // Keep scroll at bottom if pinned (user hasn't scrolled up)

src/cortex-tui/src/views/minimal_session/view.rs

@@ -402,7 +402,12 @@ impl<'a> MinimalSessionView<'a> {
         } else if self.app_state.streaming.thinking && self.app_state.thinking_budget.is_some() {
             "Thinking".to_string()
         } else if self.app_state.streaming.is_streaming {
-            "Working".to_string()
+            // Differentiate between waiting for first token and actively streaming
+            if self.app_state.streaming.is_actively_streaming {
+                "Streaming..".to_string()
+            } else {
+                "Execute".to_string()
+            }
         } else {
             "Idle".to_string()
         }