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。

docs/features/task-and-job/scheduled-task-prd.md

@@ -231,8 +231,10 @@ type TimeTrigger =
 
 同一 Conversation 的普通消息和 Scheduled Task occurrence 使用同一 FIFO 队列。Agent
 正在回复时，到期 occurrence 只显示为待执行，不中断当前输出；当前执行结束后才认领下一项。
-用户显式选择“立即中断并插入”时，系统取消当前 Conversation 的活动请求，并让所选项成为
-下一项。删除待执行 occurrence 只取消该次运行，不删除稳定 Task、Conversation 或历史结果。
+执行以失败、取消或中断结束时同样立即释放该 Conversation，下一项无需用户再次操作即会
+执行。用户显式选择“立即中断并插入”时，系统取消当前 Conversation 的活动请求，并让所选项
+成为下一项。删除待执行 occurrence 只取消该次运行，不删除稳定 Task、Conversation 或历史
+结果。
 
 ## 8. 一次触发的对象关系
 
@@ -365,6 +367,8 @@ Task Center 显示 Scheduled Task 的范围、关联 Conversation、状态、模
 - [x] 当前回复期间可以继续发送普通消息，并在 Composer 上沿查看、删除或提升待发送项。
 - [x] 应用重启恢复尚未执行的队列项和有界附件上下文；已写入 Conversation 的用户输入
   通过队列项身份完成恢复对账，不会再次进入待发送队列。
+- [x] 执行失败、取消或中断后立即释放会话，下一项和随后发送的新消息无需用户额外操作
+  即会执行。
 - [x] 文本结果只写入 Conversation，独立交付物才进入成果。
 - [ ] Task Center 和桌面通知可以打开正确 Conversation 并定位 Task。
 - [ ] 应用重启不自动重放结果未知的副作用。