fix(weixin): preserve native markdown rendering

- stop rewriting markdown tables, headings, and links before delivery
- keep markdown table blocks and headings together during chunking
- update Weixin tests and docs for native markdown rendering

Closes #10308

gateway/platforms/weixin.py

@@ -623,42 +623,31 @@ def _rewrite_table_block_for_weixin(lines: List[str]) -> str:
 def _normalize_markdown_blocks(content: str) -> str:
     lines = content.splitlines()
     result: List[str] = []
-    i = 0
     in_code_block = False
+    blank_run = 0
 
-    while i < len(lines):
-        line = lines[i].rstrip()
-        fence_match = _FENCE_RE.match(line.strip())
-        if fence_match:
+    for raw_line in lines:
+        line = raw_line.rstrip()
+        if _FENCE_RE.match(line.strip()):
             in_code_block = not in_code_block
             result.append(line)
-            i += 1
+            blank_run = 0
             continue
 
         if in_code_block:
             result.append(line)
-            i += 1
             continue
 
-        if (
-            i + 1 < len(lines)
-            and "|" in lines[i]
-            and _TABLE_RULE_RE.match(lines[i + 1].rstrip())
-        ):
-            table_lines = [lines[i].rstrip(), lines[i + 1].rstrip()]
-            i += 2
-            while i < len(lines) and "|" in lines[i]:
-                table_lines.append(lines[i].rstrip())
-                i += 1
-            result.append(_rewrite_table_block_for_weixin(table_lines))
+        if not line.strip():
+            blank_run += 1
+            if blank_run <= 1:
+                result.append("")
             continue
 
-        result.append(_MARKDOWN_LINK_RE.sub(r"\1 (\2)", _rewrite_headers_for_weixin(line)))
-        i += 1
+        blank_run = 0
+        result.append(line)
 
-    normalized = "\n".join(item.rstrip() for item in result)
-    normalized = re.sub(r"\n{3,}", "\n\n", normalized)
-    return normalized.strip()
+    return "\n".join(result).strip()
 
 
 def _split_markdown_blocks(content: str) -> List[str]:
@@ -704,8 +693,8 @@ def _split_delivery_units_for_weixin(content: str) -> List[str]:
 
     Weixin can render Markdown, but chat readability is better when top-level
     line breaks become separate messages. Keep fenced code blocks intact and
-    attach indented continuation lines to the previous top-level line so
-    transformed tables/lists do not get torn apart.
+    attach indented continuation lines to the previous top-level line so nested
+    list items do not get torn apart.
     """
     units: List[str] = []
 
@@ -747,7 +736,9 @@ def _looks_like_chatty_line_for_weixin(line: str) -> bool:
         return False
     if line.startswith((" ", "\t")):
         return False
-    if stripped.startswith((">", "-", "*", "【")):
+    if stripped.startswith((">", "-", "*", "【", "#", "|")):
+        return False
+    if _TABLE_RULE_RE.match(stripped):
         return False
     if re.match(r"^\*\*[^*]+\*\*$", stripped):
         return False
@@ -757,10 +748,12 @@ def _looks_like_chatty_line_for_weixin(line: str) -> bool:
 
 
 def _looks_like_heading_line_for_weixin(line: str) -> bool:
-    """Return True when a short line behaves like a plain-text heading."""
+    """Return True when a short line behaves like a heading."""
     stripped = line.strip()
     if not stripped:
         return False
+    if _HEADER_RE.match(stripped):
+        return True
     return len(stripped) <= 24 and stripped.endswith((":", "："))
 
 

tests/gateway/test_weixin.py

@@ -24,17 +24,14 @@ def _make_adapter() -> WeixinAdapter:
 
 
 class TestWeixinFormatting:
-    def test_format_message_preserves_markdown_and_rewrites_headers(self):
+    def test_format_message_preserves_markdown(self):
         adapter = _make_adapter()
 
         content = "# Title\n\n## Plan\n\nUse **bold** and [docs](https://example.com)."
 
-        assert (
-            adapter.format_message(content)
-            == "【Title】\n\n**Plan**\n\nUse **bold** and docs (https://example.com)."
-        )
+        assert adapter.format_message(content) == content
 
-    def test_format_message_rewrites_markdown_tables(self):
+    def test_format_message_preserves_markdown_tables(self):
         adapter = _make_adapter()
 
         content = (
@@ -44,19 +41,14 @@ class TestWeixinFormatting:
             "| Retries | 3 |\n"
         )
 
-        assert adapter.format_message(content) == (
-            "- Setting: Timeout\n"
-            "  Value: 30s\n"
-            "- Setting: Retries\n"
-            "  Value: 3"
-        )
+        assert adapter.format_message(content) == content.strip()
 
     def test_format_message_preserves_fenced_code_blocks(self):
         adapter = _make_adapter()
 
         content = "## Snippet\n\n```python\nprint('hi')\n```"
 
-        assert adapter.format_message(content) == "**Snippet**\n\n```python\nprint('hi')\n```"
+        assert adapter.format_message(content) == content
 
     def test_format_message_returns_empty_string_for_none(self):
         adapter = _make_adapter()
@@ -102,7 +94,7 @@ class TestWeixinChunking:
         content = adapter.format_message("## 结论\n这是正文")
         chunks = adapter._split_text(content)
 
-        assert chunks == ["**结论**\n这是正文"]
+        assert chunks == ["## 结论\n这是正文"]
 
     def test_split_text_keeps_short_reformatted_table_in_single_chunk(self):
         adapter = _make_adapter()
@@ -378,16 +370,13 @@ class TestWeixinRemoteMediaSafety:
 
 
 class TestWeixinMarkdownLinks:
-    """Markdown links should be converted to plaintext since WeChat can't render them."""
+    """Markdown links should be preserved so WeChat can render them natively."""
 
-    def test_format_message_converts_markdown_links_to_plain_text(self):
+    def test_format_message_preserves_markdown_links(self):
         adapter = _make_adapter()
 
         content = "Check [the docs](https://example.com) and [GitHub](https://github.com) for details"
-        assert (
-            adapter.format_message(content)
-            == "Check the docs (https://example.com) and GitHub (https://github.com) for details"
-        )
+        assert adapter.format_message(content) == content
 
     def test_format_message_preserves_links_inside_code_blocks(self):
         adapter = _make_adapter()

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

@@ -90,7 +90,7 @@ The adapter will restore saved credentials, connect to the iLink API, and begin
 - **Media support** — images, video, files, and voice messages
 - **AES-128-ECB encrypted CDN** — automatic encryption/decryption for all media transfers
 - **Context token persistence** — disk-backed reply continuity across restarts
-- **Markdown formatting** — headers, tables, and code blocks are reformatted for WeChat readability
+- **Markdown formatting** — preserves Markdown, including headers, tables, and code blocks, so WeChat clients that support Markdown can render it natively
 - **Smart message chunking** — messages stay as a single bubble when under the limit; only oversized payloads split at logical boundaries
 - **Typing indicators** — shows "typing…" status in the WeChat client while the agent processes
 - **SSRF protection** — outbound media URLs are validated before download
@@ -206,12 +206,12 @@ This ensures reply continuity even after gateway restarts.
 
 ## Markdown Formatting
 
-WeChat's personal chat does not natively render full Markdown. The adapter reformats content for better readability:
+WeChat clients connected through the iLink Bot API can render Markdown directly, so the adapter preserves Markdown instead of rewriting it:
 
-- **Headers** (`# Title`) → converted to `【Title】` (level 1) or `**Title**` (level 2+)
-- **Tables** → reformatted as labeled key-value lists (e.g., `- Column: Value`)
-- **Code fences** → preserved as-is (WeChat renders these adequately)
-- **Excessive blank lines** → collapsed to double newlines
+- **Headers** stay as Markdown headings (`#`, `##`, ...)
+- **Tables** stay as Markdown tables
+- **Code fences** stay as fenced code blocks
+- **Excessive blank lines** are collapsed to double newlines outside fenced code blocks
 
 ## Message Chunking