Really Cool Tool. Wish it was more like Aider though!

[roshaans]

I really love all the customizability and editabilty of this plugin. I just come from having significantly used Aider and it makes editing your codebase a breeze.

Some things that would make me switch over:

1. Seems like no matter what model I use, it only seems to make 1 change at a time. I have to currently fight it to make more general changes. Where as, Aider reads my mind and knows exactly what I am trying to do.

What I would like to see here is that it keeps prompting itself naturally (Aider style). I think by default the chat should assume that a user is trying to make a project wide change using the @editor, @files included. At the moment it seems like editing files is secondary and primary function is simply chatting with your files.

I have not tried to make good use of workflows yet, but if that would solve any of my problems do let me know!

2. Buffer management, Aider makes it very easy to do buffer management where as I am always confused what is in context and what is not. I have tried to use VectorCode and it may work, but still its extra things to setup. If VectorCode could be plugged in by default that'd be nice. Still though, even with VectorCode, It's still very hard to know what CodeCompanion is using as context.

Besides this, the entire expereince of having the entire chat history be a whole buffer is super neat and I have not seen that done before. Also MCP server integration with MCPHub was a breeze! Great work!

[roshaans]

I tried to use the Aider-mcp-server integrated into MCPHub.nvim and these are the results :/. It did not end up changing anything.

---

model: gpt-4o
reasoning_effort: medium
temperature: 0
max_tokens: 15000
top_p: 1
n: 1

Me

Context:

• access_mcp_resource
• use_mcp_tool

@mcp use aider to create a new controller called users

CodeCompanion (Copilot)

Tool Output

use_mcp_tool Tool: Returned the following:

success

Me

Context:

• access_mcp_resource
• use_mcp_tool
• src/api/controllers/leaderboard.ts
• cmd_runner
• editor
• files

@full_stack_dev use aider to create a new controller called users

CodeCompanion (Copilot)

Tool Output

use_mcp_tool Tool: Returned the following:

success

Me

Great. Now let's consider your code. I'd like you to check it carefully for correctness, style, and efficiency, and give constructive criticism for how to improve it.

CodeCompanion (Copilot)

Please provide the code you'd like me to review, or let me know where I can access it. If it's already in a Neovim buffer, I can analyze it directly.

Me

Thanks. Now let's revise the code based on the feedback, without additional explanations.

CodeCompanion (Copilot)

Please share the code or specify the buffer where it resides so I can revise it based on the feedback.

Me

I wnat you to add new new files...use the AIder tool it knows what to do!

CodeCompanion (Copilot)

Understood. I'll directly use the Aider tool to create the new files as per your request. Let me proceed.

Me

[cjoke]

Why build a second Aider?

[ravitemer]

@roshaans Can you link the Aider MCP Server so that I can test it

[roshaans]

https://glama.ai/mcp/servers/@sengokudaikon/aider-mcp-server

Maybe there is a better mcp server. But I think something closer to a native experience would be better. I often find that CodeCompanion also masks important MCP server errors sometimes.

There does not seem to be any concept of retries. I think that would help a ton!

[ravitemer]

Maybe there is a better mcp server. But I think something closer to a native experience would be better. I often find that CodeCompanion also masks important MCP server errors sometimes.

I think this is not the case anymore. Please update both the plugins. The mcphub extension responds with the error. Can you give me an example if it's still the case?

[olimorris]

Seems like no matter what model I use, it only seems to make 1 change at a time

This seems to be very LLM dependent. It's quite the frustration. I'm not sure if we're missing a parameter in the request object which tells the LLM to call multiple function calls or if it's a system prompt fix. But it's annoying having to do that with certain LLMs.

It's still very hard to know what CodeCompanion is using as context.

You should see a big context block in the chat buffer which indicates what's been shared with the LLM. VectorCode is the exception.