feat: sub-agent streaming progress — TaskTool emits real-time status events

- Rust: LoopEvent::SubtaskStatus variant added to loop_runner.rs
- Rust: ToolContext.event_sender field for streaming tool progress
- Rust: TaskTool emits started/running/completed/failed via event_sender
- Rust: StreamChatEvent::SubtaskStatus mapped in Tauri chat command
- TS: StreamEventSubtaskStatus type + onSubtaskStatus callback added
- TS: kernel-chat.ts handles subtaskStatus event from Tauri
- TS: streamStore.ts wires callback, maps backend→frontend status,
  updates assistant message subtasks array in real-time

crates/zclaw-runtime/src/tool/builtin/task.rs

@@ -10,7 +10,7 @@ use zclaw_types::{AgentId, Result, ZclawError};
 use zclaw_memory::MemoryStore;
 
 use crate::driver::LlmDriver;
-use crate::loop_runner::AgentLoop;
+use crate::loop_runner::{AgentLoop, LoopEvent};
 use crate::tool::{Tool, ToolContext, ToolRegistry};
 use crate::tool::builtin::register_builtin_tools;
 use std::sync::Arc;
@@ -106,6 +106,15 @@ impl Tool for TaskTool {
             description, max_iterations
         );
 
+        // Emit subtask_started event
+        if let Some(ref tx) = context.event_sender {
+            let _ = tx.send(LoopEvent::SubtaskStatus {
+                description: description.to_string(),
+                status: "started".to_string(),
+                detail: None,
+            }).await;
+        }
+
         // Create a sub-agent with its own ID
         let sub_agent_id = AgentId::new();
 
@@ -148,6 +157,15 @@ impl Tool for TaskTool {
             sub_loop = sub_loop.with_path_validator(validator.clone());
         }
 
+        // Emit subtask_running event
+        if let Some(ref tx) = context.event_sender {
+            let _ = tx.send(LoopEvent::SubtaskStatus {
+                description: description.to_string(),
+                status: "running".to_string(),
+                detail: Some("子Agent正在执行中...".to_string()),
+            }).await;
+        }
+
         // Execute the sub-agent loop (non-streaming — collect full result)
         let result = match sub_loop.run(session_id.clone(), prompt.to_string()).await {
             Ok(loop_result) => {
@@ -155,6 +173,19 @@ impl Tool for TaskTool {
                     "[TaskTool] Sub-agent completed: {} iterations, {} input tokens, {} output tokens",
                     loop_result.iterations, loop_result.input_tokens, loop_result.output_tokens
                 );
+
+                // Emit subtask_completed event
+                if let Some(ref tx) = context.event_sender {
+                    let _ = tx.send(LoopEvent::SubtaskStatus {
+                        description: description.to_string(),
+                        status: "completed".to_string(),
+                        detail: Some(format!(
+                            "完成 ({}次迭代, {}输入token)",
+                            loop_result.iterations, loop_result.input_tokens
+                        )),
+                    }).await;
+                }
+
                 json!({
                     "status": "completed",
                     "description": description,
@@ -166,6 +197,16 @@ impl Tool for TaskTool {
             }
             Err(e) => {
                 tracing::warn!("[TaskTool] Sub-agent failed: {}", e);
+
+                // Emit subtask_failed event
+                if let Some(ref tx) = context.event_sender {
+                    let _ = tx.send(LoopEvent::SubtaskStatus {
+                        description: description.to_string(),
+                        status: "failed".to_string(),
+                        detail: Some(e.to_string()),
+                    }).await;
+                }
+
                 json!({
                     "status": "failed",
                     "description": description,