Generated client files (AGENTS.md block, SKILL.md) teach a call syntax no harness can execute
维护者通常 1 天内回复
还没有人认领这个 Issue。
评估
- 难度
- 2/5
- 预计耗时
- 1-3 小时
- 新手友好度
- 75/100
- Issue 类型
- 缺陷
- 描述清晰度
- 描述清楚
- 活跃度
- 活跃
- 技术栈
- markdown
调研方向
首先定位安装程序代码,找到生成 codebase-memory SKILL.md 和 agent 指令文件中 codebase-memory-mcp 区块的部分。阅读现有的工具调用示例,并根据 CLI 或 MCP 工具定义确认支持的调用形式。更新生成的指南,为原生 JSON 参数和代码执行调用添加可执行示例;当新生成的文件解释简写形式并展示这两种形式时,工作即告完成。
由索引模型根据 Issue 内容生成。
描述
Version
0.12.1
Platform
Linux (x64)
Install channel
GitHub release archive / install.sh / install.ps1
Binary variant
standard
What happened, and what did you expect?
The client instruction files generated by the installer (the codebase-memory-mcp block written into agent instruction files such as AGENTS.md/CLAUDE.md, and the generated codebase-memory SKILL.md) teach tool calls with a syntax that no harness can execute:
search_graph(name_pattern=".*OrderHandler.*")trace_path(function_name="OrderHandler", direction="inbound")get_code_snippet(qualified_name="pkg/orders.OrderHandler")
The tool(param="...") keyword-args-in-parens form matches no actual invocation path. MCP tools are invoked either as native tool calls (a JSON object of arguments), or — in harnesses that route MCP tools through a code-execution tool — as code like tools["codebase-memory-mcp"].search_graph({ name_pattern: "..." }). An agent that tries to follow the example literally cannot produce a valid call and tends to fall back to grep, which quietly defeats the "ALWAYS prefer MCP graph tools over grep/glob" instruction in the same block.
Expected: the generated guidance should be executable. Concretely:
- keep the
tool(param=...)notation as shorthand in tables/workflows, but state explicitly that it is tool + params shorthand, not literal syntax; - add one concrete example per real invocation form (native tool call with JSON args, and the code-execution form);
- optionally note that only a couple of the 17 tools appear in a code-execution tool catalog by default, so agents should list the server's tools before assuming one is missing.
Related but distinct: #3029 fixes the installed skill's query guidance content (its tool inventory also omits compare_graphs and get_file_outline — the generated SKILL.md still says "15 MCP Tools" on 0.12.1). This report is about the invocation syntax, which #3029 does not cover.
Reproduction
- Install 0.12.1 via the release archive / install.sh path.
- Open the generated
codebase-memoryskill's SKILL.md, and thecodebase-memory-mcpblock in the generated agent instructions file (AGENTS.md/CLAUDE.md). - Observe the examples use
tool(param="...")syntax, and the section heading "15 MCP Tools". - Compare with any real invocation: e.g.
codebase-memory-mcp cli search_graph '{"project":"...","name_pattern":"..."}'takes a JSON object of arguments; an MCP-native tool call likewise takes a JSON object. Neither matches the documented parenthesised keyword-arg form. - In a harness that routes MCP tools through a code-execution tool, ask an agent to "find who calls X using the graph tools": it cannot map the examples to a real call and typically falls back to grep.
No indexed code is involved — the defect is in the generated files themselves.
Logs
Diagnostics trajectory (memory / performance / leak issues)
Project scale (if relevant)
No response
Confirmations
- I searched existing issues and this is not a duplicate.
- My reproduction uses shareable code (a dummy snippet or a public OSS repository), not proprietary code.
- 主要语言
- C
- 星标
- 45.8k
- 派生
- 3.8k
- 平均合并
- 1 天 23 小时
- 30 天内合并 PR
- 83
环境准备
这个项目没有提供开发容器、Dockerfile 或贡献指南,环境需要你自己搭建:先看它的 README,通用步骤见我们的新手贡献指南。
从这里开始
- 先读完整个 Issue,再读项目的贡献指南。
- 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
- Fork 仓库,在一个分支上完成修改。
- 提交 Pull Request,并在描述里引用这个 Issue 编号。
DeusData/codebase-memory-mcp 的其他 Issue
-
parsing/quality
难度 2/5 1-3 小时 新手友好度 75/100
DeusData/codebase-memory-mcp#3062 · 1 条评论 ·
维护者通常 1 天内回复
-
editor/integration parsing/quality
难度 2/5 1-3 小时 新手友好度 68/100
DeusData/codebase-memory-mcp#2286 ·
维护者通常 1 天内回复
-
install writes an unsupported `args` key into the Claude Code SubagentStart hook, so it never runs未关闭bug editor/integration priority/high stability/performance ux/behavior
难度 2/5 1-3 小时 新手友好度 72/100
DeusData/codebase-memory-mcp#2239 · 1 条评论 ·
维护者通常 1 天内回复
-
bug priority/high ux/behavior
难度 2/5 1-3 小时 新手友好度 72/100
DeusData/codebase-memory-mcp#2232 · 2 条评论 ·
维护者通常 1 天内回复
-
documentation editor/integration parsing/quality priority/normal
难度 2/5 1-3 小时 新手友好度 85/100
DeusData/codebase-memory-mcp#2169 ·
维护者通常 1 天内回复
查看 DeusData/codebase-memory-mcp 的全部 Issue
相似的 Issue
-
难度 2/5 1-3 小时 新手友好度 62/100
维护者通常 1 天内回复
-
area:gates kind:gate-defect
难度 2/5 1-3 小时 新手友好度 83/100
InauguralSystems/EigenScript#2476 ·
维护者通常 1 天内回复
-
难度 1/5 1 小时以内 新手友好度 92/100
flipperdevices/flipperzero-firmware#4520 ·
维护者通常 1 天内回复
-
area/build-framework kind/enhancement priority/low
难度 2/5 1-3 小时 新手友好度 77/100
yugabyte/yugabyte-db#38826 ·
维护者通常 1 天内回复
-
难度 2/5 1-3 小时 新手友好度 68/100
the-miint/duckdb-miint#497 ·
维护者通常 1 天内回复