[Feature]: Add json abstract when saving context from mcp

[lshpeng]

Note

This issue was translated by Claude.

Issue Checklist

• I understand that issues are for reporting problems and requesting features, not for off-topic comments, and I will provide as much detail as possible to help resolve the issue.
• I have checked the pinned issues and searched through the existing open issues, closed issues, and discussions and did not find a similar suggestion.
• I have provided a short and descriptive title so that developers can quickly understand the issue when browsing the issue list, rather than vague titles like "A suggestion" or "Stuck."
• The latest version of Cherry Studio does not include the feature I am suggesting.

Platform

Windows

Version

v1.9.6

Is your feature request related to an existing issue?

When MCP returns too much data, read errors often occur.

Desired Solution

Suggestion for improving CherryStudio:

When large MCP results are saved to tool-results/, write a JSON summary metadata on the first line of the file to help the Agent precisely locate the required data:

{"_meta":{"total_rows":144,"columns":["trade_date","ts_code","close","pct_chg",...],"avg_bytes_per_row":430}}

This way, the Agent can use Read(offset=N, limit=1KB) to precisely locate the required rows, instead of having to read the entire file every time or repeatedly try queries. The workload is very small—just add one line json.dumps(meta) + "\n" before writing the file.

Alternative Solutions

No response

Additional Information

No response

---

Original Content

Issue Checklist

• I understand that issues are for reporting problems and requesting features, not for off-topic comments, and I will provide as much detail as possible to help resolve the issue.
• I have checked the pinned issues and searched through the existing open issues, closed issues, and discussions and did not find a similar suggestion.
• I have provided a short and descriptive title so that developers can quickly understand the issue when browsing the issue list, rather than vague titles like "A suggestion" or "Stuck."
• The latest version of Cherry Studio does not include the feature I am suggesting.

Platform

Windows

Version

v1.9.6

Is your feature request related to an existing issue?

当mcp返回过长时，经常读取错误

Desired Solution

给 CherryStudio 的改进建议：

大 MCP 结果落盘到 tool-results/ 时，在文件第一行写入一行 JSON 摘要元数据，帮助 Agent 精确定位所需数据：

Json
{"_meta":{"total_rows":144,"columns":["trade_date","ts_code","close","pct_chg",...],"avg_bytes_per_row":430}}这样 Agent 可以用 Read(offset=N, limit=1KB) 精确定位到需要的行，而不是每次都要读整个文件或反复试 query。工作量很小——在写文件前加一行 json.dumps(meta) + "\n" 即可。

Alternative Solutions

No response

Additional Information

No response