feat(streaming): token-level delta events + interrupt for CLI/WebUI/GUI

Expose the LLM token-level streaming deltas (EventReasoningDelta /
EventContentDelta) to every client channel and add user-initiated
interrupt (cancel generation / send interrupt message) to all three
frontends, preserving the existing interrupt-injection semantics.

SDK/events:
  - EventReasoningDelta, EventContentDelta constants exported in the
    public/internal SDK event alias tables.

CLI plugin:
  - handleChat subscribes to both delta events and forwards
    reasoning_delta / content_delta JSON frames (channel-filtered);
    aggregated reasoning/tool_call/response frames still fire as before.
  - New /stop (alias /interrupt) builtin injects an interrupt via
    InjectInterrupt(cliSource, cliChannel) - matches interceptLoop
    semantics: cancels an active stream and re-injects the message as
    a [中断消息] for a restarted turn; with no active LLM it behaves
    as a plain input.

Waiter client (line mode + TUI):
  - streamRender accumulates delta chunks and redraws the current line;
    a reset frame (stream abandoned, e.g. user interrupt) flushes the
    partial buffer so the next turn does not concatenate onto stale
    content. Aggregated frames terminate the delta line and render the
    final text (old servers without deltas behave exactly as before).
  - TUI merges content_delta into the in-flight agent message and seals
    it (final flag) on response/tool_call/error so subsequent deltas
    never append to a finished message.

WebUI:
  - SSE handler subscribes to the two delta events but does NOT record
    them into the replay ring - reconnection replays only aggregated
    events (the final truth), avoiding duplicate delta accumulation.
  - POST /api/v1/chat/interrupt calls InjectInterrupt(webui, webui)
    with optional message; fronted by a Stop button shown only while
    a generation is in flight.

dashboard.html / GUI app.js:
  - Stop button next to Send (hidden until chatLoading); interruptChat
    POSTs /chat/interrupt. Delta listeners append incrementally;
    agent_output (aggregated) now replaces (not appends) the in-flight
    content and marks _final; reset frames finalize the partial message.

process.go:
  - chatStreamWithFallback preserves the context.Canceled/
    DeadlineExceeded contract: a user interrupt returns the canceled
    error (never a partial-content success) so the existing continue
    branch restarts the turn with the [中断消息]. A reset
    EventContentDelta is published so connected clients drop stale
    partial renderings before the new turn begins.

Verified: /stop 'msg' via waiter triggers 'interrupt from cli/cli' in
interceptLoop; unit TestChatStreamCancelPreservesInterrupt confirms the
canceled error propagates instead of being swallowed.

cmd/gui/renderer/app.js

@@ -1166,6 +1166,9 @@ function buildChatLayout() {
     '<input id="chat-input" placeholder="' +
     __("输入消息...", "Type a message...") +
     '" onkeydown="if(event.key==\'Enter\')sendChat()">' +
+    '<button class="btn" onclick="interruptChat()" id="chat-stop-btn" style="display:none;background:#d1383d;color:#fff">' +
+    __("停止", "Stop") +
+    "</button>" +
     '<button class="btn btn-primary" onclick="sendChat()" id="chat-send-btn">' +
     __("发送", "Send") +
     "</button>" +
@@ -2036,6 +2039,7 @@ function buildChatStarmapGraph() {
 async function sendChat() {
   var inp = document.getElementById("chat-input");
   var btn = document.getElementById("chat-send-btn");
+  var stopBtn = document.getElementById("chat-stop-btn");
   var text = inp.value.trim();
   if (!text || state.chatLoading) return;
   if (state.currentConn && state.currentConn.type === "cli") {
@@ -2057,6 +2061,7 @@ async function sendChat() {
   state.chatStage = __("等待AI回复...", "Waiting for AI...");
   btn.disabled = true;
   btn.textContent = "";
+  if (stopBtn) stopBtn.style.display = ""; // 生成期间可停止
   rerenderChat();
   try {
     // webui 连接：同步 POST 等完整回复（服务端 X-Trigger-Only 也返回 response；SSE 公网不稳时靠同步兜底）
@@ -2124,10 +2129,26 @@ async function sendChat() {
     state.chatStage = "";
     btn.disabled = false;
     btn.textContent = __("发送", "Send");
+    var sb2 = document.getElementById("chat-stop-btn");
+    if (sb2) sb2.style.display = "none"; // 回复完成/失败，隐藏停止按钮
     rerenderChat();
   }
 }
 
+// 停止生成 / 发送中断消息。核心拦截语义：有 LLM 在跑则取消当前请求并以
+// [中断消息] 重启轮次；无则在跑则作为普通消息处理。
+async function interruptChat() {
+  try {
+    await api("/chat/interrupt", {
+      method: "POST",
+      body: JSON.stringify({}),
+    });
+    toast(__("已发送中断信号", "Interrupt signal sent"));
+  } catch (e) {
+    toast(__("中断失败: ", "Interrupt failed: ") + e.message, true);
+  }
+}
+
 async function queryMemoryChat() {
   var q = document.getElementById("mem-query")?.value;
   var r = document.getElementById("mem-result-chat");