Error with neovim: expected struct FileStore with 1 element

[thnguyen996]

Hello, I'm having this error when setting up the server with neovim: ERROR lsp_ai: invalid length 0, expected struct FileStore with 1 element\n

I'm using the native nvim lsp to configure the server. Using nvim-lspconfig resulted in the same error. Here is my configuration in the init.lua file:

vim.lsp.start({
  name = 'lsp-ai',
 cmd = 'path to lsp-ai binary',
  root_dir = 'hard coded root dir just for testing',
  init_options = {
  memory = {
  file_store = {},
      },
  model = {
  model1 = {
       type = "ollama", 
       model = "starcoder2-15b", 
      generate_endpoint = "http://.../generate", 
}
},
    completion = {
       model = "model1",
      parameters = {max_content = 300},
        } 
   } 
})

I believe it has something to do with the empty file_store option but I don't really know how to fix that.

[SilasMarvin]

I actually ran into this error the other day. This is caused by how lua converts tables into JSON. Lua converts the {} into a JSON [] which is incorrect as the LSP-AI server expects file_store to be an object.

Here is an example of some init options that will work copied directly from my init.lua file:

-- Set leader
vim.g.mapleader = " "
vim.g.maplocalleader = "\\"

-- The init_options
local lsp_ai_init_options_json = [[
{
  "memory": {
    "file_store": {}
  },
  "models": {
    "model1": {
      "type": "anthropic",
      "chat_endpoint": "https://api.anthropic.com/v1/messages",
      "model": "claude-3-5-sonnet-20240620",
      "auth_token_env_var_name": "ANTHROPIC_API_KEY"
    }
  },
  "actions": [
    {
      "trigger": "!C",
      "action_display_name": "Chat",
      "model": "model1",
      "parameters": {
        "max_context": 4096,
        "max_tokens": 4096,
        "system": "You are an AI coding assistant. Your task is to complete code snippets. The user's cursor position is marked by \"<CURSOR>\". Follow these steps:\n\n1. Analyze the code context and the cursor position.\n2. Provide your chain of thought reasoning, wrapped in <reasoning> tags. Include thoughts about the cursor position, what needs to be completed, and any necessary formatting.\n3. Determine the appropriate code to complete the current thought, including finishing partial words or lines.\n4. Replace \"<CURSOR>\" with the necessary code, ensuring proper formatting and line breaks.\n5. Wrap your code solution in <answer> tags.\n\nYour response should always include both the reasoning and the answer. Pay special attention to completing partial words or lines before adding new lines of code.\n\n<examples>\n<example>\nUser input:\n--main.py--\n# A function that reads in user inpu<CURSOR>\n\nResponse:\n<reasoning>\n1. The cursor is positioned after \"inpu\" in a comment describing a function that reads user input.\n2. We need to complete the word \"input\" in the comment first.\n3. After completing the comment, we should add a new line before defining the function.\n4. The function should use Python's built-in `input()` function to read user input.\n5. We'll name the function descriptively and include a return statement.\n</reasoning>\n\n<answer>t\ndef read_user_input():\n    user_input = input(\"Enter your input: \")\n    return user_input\n</answer>\n</example>\n\n<example>\nUser input:\n--main.py--\ndef fibonacci(n):\n    if n <= 1:\n        return n\n    else:\n        re<CURSOR>\n\n\nResponse:\n<reasoning>\n1. The cursor is positioned after \"re\" in the 'else' clause of a recursive Fibonacci function.\n2. We need to complete the return statement for the recursive case.\n3. The \"re\" already present likely stands for \"return\", so we'll continue from there.\n4. The Fibonacci sequence is the sum of the two preceding numbers.\n5. We should return the sum of fibonacci(n-1) and fibonacci(n-2).\n</reasoning>\n\n<answer>turn fibonacci(n-1) + fibonacci(n-2)</answer>\n</example>\n</examples>\n",
        "messages": [
          {
            "role": "user",
            "content": "{CODE}"
          }
        ]
      },
      "post_process": {
        "extractor": "(?s)<answer>(.*?)</answer>"
      }
    }
  ]
}
]]

-- The configuration
local lsp_ai_config = {
  cmd = { 'lsp-ai' },
  root_dir = vim.loop.cwd(),
  init_options = vim.fn.json_decode(lsp_ai_init_options_json),
}

-- Start lsp-ai when opening a buffer
vim.api.nvim_create_autocmd("BufEnter", {
  callback = function(args)
    local bufnr = args.buf
    local client = vim.lsp.get_active_clients({bufnr = bufnr, name = "lsp-ai"})
    if #client == 0 then
      vim.lsp.start(lsp_ai_config, {bufnr = bufnr})
    end
  end,
})

-- Key mapping for code actions
vim.api.nvim_set_keymap('n', '<leader>c', '<cmd>lua vim.lsp.buf.code_action()<CR>', {noremap = true, silent = true})

Basically use the vim.fn.json_decode function and it will fix it.

Let me know if you have any other issues or suggestions. Thanks for checking it out!