feat: preview Agent HTML in conversations and unblock long replies

Agent replies that produced HTML could only be read as source, so users had
to copy the markup into an external file to see the result. Completed Agent
and Subagent output now renders complete HTML documents, single-root HTML
replies, and `html` / `htm` code blocks as an isolated static preview in
place. Each preview keeps a persistent notice that scripts and network are
disabled and offers the same icon actions as Mermaid diagrams: a source
toggle and a full-screen preview. The new "render HTML in conversations"
switch under Platform Features / General is on by default, applies to the
open conversation immediately, and falls back to HTML source when disabled.
Previews cannot run scripts, reach the network, submit forms, open windows,
or load remote media; author stylesheets and inline styles are preserved so
the intended layout survives, and remote resource loading is refused by the
preview CSP instead.

Direct-model replies no longer fail once they grow large. The byte caps on
streaming responses, single stream blocks, non-streaming replies, model tool
arguments, tool request context, aggregate tool results, and accumulated
answer text are removed, so users stop seeing "模型接口流式响应超过安全限制"
on long answers. Response length is now governed by the request timeout,
cancellation, and context compression. Image generation responses keep their
decodable-image validation.

A message sent after a failed or interrupted run stayed in the pending queue
instead of running. The conversation is now released whenever a run reaches
any terminal state, not only when the renderer reports readiness again, and a
dispatched queue item whose run never starts releases its reservation and
returns to pending. Later messages dispatch without extra user action.

Release note: Agent 回复中的 HTML 现在可直接在会话内预览，支持查看源码和全屏预览，默认开启并可在“平台功能 / 通用设置”关闭；直连模型的长回复不再因大小限制中断；上一次运行失败或被中断后，新发送的消息会立即执行而不再排队等待。

src/main/agent/model-runtime.test.ts

@@ -1788,19 +1788,41 @@ describe('ModelAgentRuntime', () => {
     }
   })
 
-  it('bounds the total ordinary streaming response size', async () => {
-    const chunk = new TextEncoder().encode(
-      `data: ${JSON.stringify({
-        type: 'content_block_delta',
-        delta: {
-          type: 'text_delta',
-          text: 'x'.repeat(65_000)
-        }
-      })}\n\n`
-    )
+  it('streams long ordinary responses without a size limit', async () => {
+    const encoder = new TextEncoder()
+    const deltaChunks = 48
+    const deltaText = 'x'.repeat(65_000)
     const body = new ReadableStream<Uint8Array>({
-      pull(controller) {
-        controller.enqueue(chunk)
+      start(controller) {
+        controller.enqueue(
+          encoder.encode(
+            `data: ${JSON.stringify({
+              type: 'message_start',
+              message: {
+                id: 'message-long',
+                model: 'sonnet-5',
+                usage: { input_tokens: 5 }
+              }
+            })}\n\n`
+          )
+        )
+        for (let index = 0; index < deltaChunks; index += 1) {
+          controller.enqueue(
+            encoder.encode(
+              `data: ${JSON.stringify({
+                type: 'content_block_delta',
+                delta: {
+                  type: 'text_delta',
+                  text: deltaText
+                }
+              })}\n\n`
+            )
+          )
+        }
+        controller.enqueue(
+          encoder.encode('data: {"type":"message_stop"}\n\n')
+        )
+        controller.close()
       }
     })
     const runtime = new ModelAgentRuntime({
@@ -1816,22 +1838,26 @@ describe('ModelAgentRuntime', () => {
         })
       )
     })
-    const consume = async (): Promise<void> => {
-      for await (const _event of runtime.run(
-        {
-          requestId: crypto.randomUUID(),
-          conversationId: crypto.randomUUID(),
-          prompt: 'test'
-        },
-        new AbortController().signal
-      )) {
-        void _event
+    let streamedText = ''
+    let done = false
+    for await (const event of runtime.run(
+      {
+        requestId: crypto.randomUUID(),
+        conversationId: crypto.randomUUID(),
+        prompt: 'test'
+      },
+      new AbortController().signal
+    )) {
+      if (event.type === 'text') {
+        streamedText += event.delta
+      }
+      if (event.type === 'done') {
+        done = true
       }
     }
 
-    await expect(consume()).rejects.toThrow(
-      '流式响应超过安全限制'
-    )
+    expect(done).toBe(true)
+    expect(streamedText.length).toBe(deltaChunks * deltaText.length)
   })
 
   it('preserves bounded provider error messages', async () => {
@@ -5192,29 +5218,44 @@ describe('ModelAgentRuntime', () => {
     await replacement.dispose()
   })
 
-  it('counts image base64 data against the aggregate tool context limit', async () => {
-    const response = {
-      choices: [
-        {
-          message: {
-            role: 'assistant',
-            content: null,
-            tool_calls: [
-              {
-                id: 'call-large-image',
-                type: 'function',
-                function: {
-                  name: 'workspace_read_text',
-                  arguments: '{}'
-                }
-              }
-            ]
-          }
-        }
-      ]
-    }
+  it('keeps an oversized image tool result in the model round', async () => {
     const imageData = Buffer.alloc(1024 * 1024 + 1).toString('base64')
-    const fetcher = vi.fn<typeof fetch>(async () => Response.json(response))
+    const fetcher = vi
+      .fn<typeof fetch>()
+      .mockResolvedValueOnce(
+        Response.json({
+          choices: [
+            {
+              message: {
+                role: 'assistant',
+                content: null,
+                tool_calls: [
+                  {
+                    id: 'call-large-image',
+                    type: 'function',
+                    function: {
+                      name: 'workspace_read_text',
+                      arguments: '{}'
+                    }
+                  }
+                ]
+              }
+            }
+          ]
+        })
+      )
+      .mockResolvedValueOnce(
+        Response.json({
+          choices: [
+            {
+              message: {
+                role: 'assistant',
+                content: '图片已读取。'
+              }
+            }
+          ]
+        })
+      )
     const runtime = new ModelAgentRuntime({
       baseUrl: 'http://127.0.0.1:11434/v1',
       model: 'qwen3',
@@ -5234,23 +5275,25 @@ describe('ModelAgentRuntime', () => {
         }))
       })
     })
-    const consume = async (): Promise<void> => {
-      for await (const _event of runtime.run(
-        {
-          requestId: crypto.randomUUID(),
-          conversationId: crypto.randomUUID(),
-          prompt: 'run',
-          workMode: 'execute'
-        },
-        new AbortController().signal,
-        async () => 'once'
-      )) {
-        void _event
-      }
+    const events = []
+    for await (const event of runtime.run(
+      {
+        requestId: crypto.randomUUID(),
+        conversationId: crypto.randomUUID(),
+        prompt: 'run',
+        workMode: 'execute'
+      },
+      new AbortController().signal,
+      async () => 'once'
+    )) {
+      events.push(event)
     }
 
-    await expect(consume()).rejects.toThrow('结果总量超过 1MB')
-    expect(fetcher).toHaveBeenCalledOnce()
+    expect(fetcher).toHaveBeenCalledTimes(2)
+    expect(events.at(-1)).toMatchObject({ type: 'done' })
+    expect(fetcher.mock.calls[1]?.[1]?.body as string).toContain(
+      imageData
+    )
   })
 
   it('performs and validates a real image generation when testing an image connection', async () => {