From b273f3a304f0abe662781df32f987cfd32fc16c8 Mon Sep 17 00:00:00 2001 From: Luxferre Date: Mon, 23 Mar 2026 08:52:04 +0200 Subject: [PATCH] upd readme --- README.md | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/README.md b/README.md index 4408ff7..555729a 100644 --- a/README.md +++ b/README.md @@ -243,6 +243,10 @@ Speed, robustness, platform support. Writing the same in C would involve a lot m Yes, but don't think much in terms of user-facing features. Think of it as a Lego: Sidekick gives you a good set of building blocks to orchestrate the flow, it's totally up to you what to do with these blocks. That's why it also exposes itself as an MCP server: to be called by other agents. You can even configure a Sidekick subagent to call another running instance of itself if you really need to. However, because of the subagentic architecture, you most probably won't need this. +### Why does the `shell_exec` tool have a separate safety toggle but `write_file`/`edit_file` don't? + +In production environments, the agent is supposed to run within a container without external mounts. As such, inadvertent writes to the container's ephemeral filesystem should not harm anything. On the other hand, these built-in tools allow the LLMs to optimize some processes by caching the data to reduce the amount of iterations and outside calls. + ### Is Sidekick going to include a more beautiful TUI application, tailored for coder's needs (like OpenCode, Claude Code, Gemini CLI, Qwen Code etc)? Yes, there are plans to implement something like that once the core agentic functionality is polished. It may be a totally separate application or a `sidekick-tui` evolution. The current `sidekick-tui` is more tailored for testing your agent configurations (`config.toml` and `prompt.toml`) without having to spin up the MCP server.