feat: add ollama as supported provider (#1543)

* feat: add ollama as supported provider

*This implementation is only working with `stream = true`*
- Uses the actual ollama api and allows for passing additional options
- Properly passes the system prompt to api

Use ollama as provider in opts like this:
opts = {
        debug = true,
        provider = "ollama",
        ollama = {
                api_key_name = "",
                endpoint = "http://127.0.0.1:11434",
                model = "qwen2.5-coder:latest",
                options = {
                        num_ctx = 32768,
                        temperature = 0,
                },
                stream = true,
        },

* fix: ollama types

---------

Co-authored-by: jtabke <25010496+jtabke@users.noreply.github.com>

lua/avante/config.lua

@@ -20,7 +20,7 @@ local M = {}
 ---@field custom_tools AvanteLLMToolPublic[]
 M._defaults = {
   debug = false,
-  ---@alias ProviderName "claude" | "openai" | "azure" | "gemini" | "vertex" | "cohere" | "copilot" | "bedrock" | string
+  ---@alias ProviderName "claude" | "openai" | "azure" | "gemini" | "vertex" | "cohere" | "copilot" | "bedrock" | "ollama" | string
   provider = "claude",
   -- WARNING: Since auto-suggestions are a high-frequency operation and therefore expensive,
   -- currently designating it as `copilot` provider is dangerous because: https://github.com/yetone/avante.nvim/issues/1048
@@ -255,6 +255,15 @@ M._defaults = {
     temperature = 0,
     max_tokens = 4096,
   },
+  ---@type AvanteSupportedProvider
+  ollama = {
+    endpoint = "http://127.0.0.1:11434",
+    timeout = 30000, -- Timeout in milliseconds
+    options = {
+      temperature = 0,
+      num_ctx = 4096,
+    },
+  },
   ---To add support for custom provider, follow the format below
   ---See https://github.com/yetone/avante.nvim/wiki#custom-providers for more details
   ---@type {[string]: AvanteProvider}