feat(mcp): 聊天工具默认使用实时数据源

- MCP 聊天、移动端上下文和搜索工具默认传递 source=auto
- 工具 schema 公开 source 枚举与默认值
- 搜索结果区分实时索引与旧快照索引的新鲜度说明
- 账号信息返回 direct/decrypted 模式、db_storage、密钥和 realtime 状态
- 支持从 PyInstaller _MEIPASS 或环境变量定位 Copilot Skill
- 更新 Copilot Skill 文档中的实时数据源说明
- 补充 MCP source 默认值、schema 和打包 Skill 读取测试

Author: 2977094657

skills/wechat-mcp-copilot/references/chats.md

@@ -5,8 +5,8 @@ Use this for chat sessions, message search, and message context.
 ## Flow
 
 1. Resolve fuzzy target with `wechat.chat.resolve_session`.
-2. For recent messages, call `wechat.chat.get_messages` with a small `limit`.
-3. For keywords, call `wechat.chat.search_messages`.
+2. For recent/latest messages, call `wechat.chat.get_messages` with a small `limit`; the default `source=auto` reads live WeChat WCDB directly.
+3. For keywords, call `wechat.chat.search_messages`; the default `source=auto` uses the WCDB-derived realtime FTS index. If it is still building, retry after the index status becomes ready.
 4. Use `wechat.chat.list_search_senders` when the user needs sender facets for a broad search.
 5. For a hit that needs context, call `wechat.chat.get_message_around`.
 6. For merged-forward chat history or AppMsg cards that only expose `server_id`, call `wechat.chat.resolve_chat_history` or `wechat.chat.resolve_app_message`.
@@ -26,3 +26,11 @@ Use this for chat sessions, message search, and message context.
 - `wechat.chat.resolve_app_message`
 
 Do not scan full histories by pagination when an aggregate or search tool can answer.
+
+## Freshness
+
+- `list_sessions`, `resolve_session`, `get_messages`, `get_message_around`, `get_message_anchor`, `get_daily_message_counts`, and `search_messages` default to `source=auto`.
+- Use `source=realtime` only when you explicitly require live WeChat WCDB and want failure instead of fallback.
+- Use `source=decrypted` only for explicit legacy snapshot analysis against output databases.
+- `search_messages source=auto` and `list_search_senders source=auto` use the same realtime WCDB-derived index, so single-character Chinese searches should not fall back to slow bounded scans once the index is ready.
+- `get_message_raw` intentionally remains an output-snapshot debugging tool for raw decrypted fields.

skills/wechat-mcp-copilot/references/mobile.md

@@ -22,9 +22,10 @@ Use this for phone, ScreenMemo, and external MCP clients unless the user needs a
 - Do not fetch binary media through MCP. Use returned URLs in the app.
 - Use low-level tools only for debugging, raw fields, or unusual media URL construction.
 - Data preparation, index/cache build, export, realtime sync, local editing, system settings, and data deletion tools are not exposed through MCP.
+- Chat/session/context/calendar tools default to `source=auto` (direct live WeChat WCDB). Mobile chat search also defaults to `source=auto` and uses the WCDB-derived realtime FTS index; `source=decrypted` is only for explicit legacy output snapshots.
 
 ## Recovery
 
 - If `ready=false`, stop content tools and direct the user to the desktop/web app for data preparation or backend diagnostics.
 - If target resolution is ambiguous, ask for one clarifying clue or show top candidates.
-- If search returns nothing, try `resolve_target` and then `get_chat_context` before declaring no data.
+- If search returns nothing, try `resolve_target` and then `get_chat_context` before declaring no data; `source=auto` search is backed by the realtime WCDB-derived FTS index and may need the index build to finish first.

src/wechat_decrypt_tool/mcp/registry.py

@@ -131,10 +131,12 @@ def object_schema(
     return schema
 
 
-def string_schema(description: str, *, enum: list[str] | None = None) -> dict[str, Any]:
+def string_schema(description: str, *, enum: list[str] | None = None, default: str | None = None) -> dict[str, Any]:
     out: dict[str, Any] = {"type": "string", "description": description}
     if enum:
         out["enum"] = enum
+    if default is not None:
+        out["default"] = default
     return out