fix(cron): the silence instruction names [SILENT] as an untranslatable ASCII token; docs + trim tests

Follow-up to the salvaged #110940 commit:

- `cron/scheduler_prompt.py::_CRON_HINT` tells the model the sentinel is a literal
  ASCII control token that must never be translated or rephrased — the prompt-side
  half of the fix, so a lane answering in any other language is steered to the
  canonical token instead of relying on the filter knowing that language.
- Docs: the supported-token list ('Intentional Silence Tokens') gains the zh-Hans
  forms in the English page and the zh-Hans mirror gets the section it lacked.
- Tests trimmed to two invariants (translated forms match in every shape the English
  ones do; prose that mentions the word is still delivered), proven red on origin/main.

cron/scheduler_prompt.py

@@ -197,6 +197,8 @@ _CRON_HINT = (
     "final response and the system handles the rest. "
     "SILENT: If there is genuinely nothing new to report, respond "
     "with exactly \"[SILENT]\" (nothing else) to suppress delivery. "
+    "[SILENT] is a literal ASCII control token — never translate or "
+    "rephrase it, whatever language the rest of your answer uses. "
     "Never combine [SILENT] with content — either report your "
     "findings normally, or say [SILENT] and nothing more. "
     "RECURSION: This is a run of an EXISTING scheduled job — execute "

tests/gateway/test_response_filters.py

@@ -19,24 +19,15 @@ def test_autonomous_silence_accepts_marker_with_own_line_note():
     assert is_autonomous_silence_response("[SILENT] No changes detected")
 
 
-def test_translated_sentinel_suppresses_delivery():
-    """Regression: a non-English lane answers the silence instruction in its own language.
-
-    2026-09-14 — a deepseek cron lane had nothing to report and answered the cron
-    instruction ("respond with exactly [SILENT]") with "[静默]". The control token
-    was not a known marker, so the whole token was delivered to the user's DM as
-    content.
-    """
+def test_translated_sentinel_is_silence_in_every_form_the_english_one_is():
+    """#110935: a lane that answers the cron instruction in its own language translates the
+    sentinel; ``[静默]`` must suppress delivery exactly like ``[SILENT]`` (exact, own-line note,
+    reordered lines, bracketless, edge punctuation)."""
     assert is_intentional_silence_response("[静默]")
-    assert is_autonomous_silence_response("[静默]")
-
-
-def test_translated_sentinel_takes_the_same_forms_as_the_english_one():
-    """Same loose rule: own-line note, reordered lines, bracketless; the exact rule strips punctuation."""
+    assert is_intentional_silence_response("**沉默**")
     assert is_autonomous_silence_response("[静默]\n\nNothing new this tick.")
     assert is_autonomous_silence_response("2 deals filtered\n\n[沉默]")
     assert is_autonomous_silence_response("静默")
-    assert is_intentional_silence_response("**沉默**")
 
 
 def test_prose_mentioning_the_translated_sentinel_is_delivered():

website/docs/user-guide/messaging/index.md

@@ -140,6 +140,7 @@ Supported tokens:
 - `SILENT`
 - `NO_REPLY`
 - `NO REPLY`
+- `[静默]` / `静默` and `[沉默]` / `沉默` — the Chinese renderings a model produces when it translates the sentinel instead of emitting it literally
 
 Whitespace and case are normalized, but the whole final response must be the token. A sentence like "Use `[SILENT]` when nothing changed" is delivered normally.
 

website/i18n/zh-Hans/docusaurus-plugin-content-docs/current/user-guide/messaging/index.md

@@ -102,6 +102,22 @@ flowchart TB
 
 每个平台适配器接收消息，通过每个聊天的会话存储进行路由，并将其分发给 AIAgent 处理。网关还运行 cron 调度器，每 60 秒触发一次以执行到期任务。
 
+## 有意静默令牌
+
+在群聊、hooks 和自动化流程中，Hermes 支持显式的静默令牌。若 agent 的最终回复恰好只是一个受支持的令牌，网关会抑制外发投递，不向聊天发送任何内容。
+
+支持的令牌：
+
+- `[SILENT]`
+- `SILENT`
+- `NO_REPLY`
+- `NO REPLY`
+- `[静默]` / `静默` 与 `[沉默]` / `沉默` —— 模型把哨兵翻译成中文而非原样输出时产生的形式
+
+空白与大小写会被规范化，但整条最终回复必须只是该令牌。像"没有变化时请用 `[SILENT]`"这样的句子会正常投递。
+
+静默只是投递层面的决定：Hermes 仍会把这条静默回复保存在会话记录中，因此对话依旧正常交替。失败的回合仍会以错误形式呈现；不会因为文本形似静默令牌而隐藏失败。
+
 ## 快速配置
 
 配置消息平台最简单的方式是使用交互式向导：