feat: add top-level mistral provider (#2932)

* feat: add top-level mistral provider

Mistral is a big provider so it makes sense to have a default for it.
Even more so since it wont work out of the box and need a bit of
tweaking see #1570

* [pre-commit.ci lite] apply automatic fixes

---------

Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>

Author: teto

lua/avante/config.lua

@@ -31,7 +31,7 @@ M._defaults = {
   ---@alias avante.Mode "agentic" | "legacy"
   ---@type avante.Mode
   mode = "agentic",
-  ---@alias avante.ProviderName "claude" | "openai" | "azure" | "gemini" | "vertex" | "cohere" | "copilot" | "bedrock" | "ollama" | "watsonx_code_assistant" | string
+  ---@alias avante.ProviderName "claude" | "openai" | "azure" | "gemini" | "vertex" | "cohere" | "copilot" | "bedrock" | "ollama" | "watsonx_code_assistant" | "mistral" | string
   ---@type avante.ProviderName
   provider = "claude",
   -- WARNING: Since auto-suggestions are a high-frequency operation and therefore expensive,
@@ -503,6 +503,15 @@ M._defaults = {
       model = "qwen3-coder-plus",
       api_key_name = "DASHSCOPE_API_KEY",
     },
+    mistral = {
+      __inherited_from = "openai",
+      endpoint = "https://api.mistral.ai/v1",
+      model = "mistral-large-latest",
+      api_key_name = "MISTRAL_API_KEY",
+      extra_request_body = {
+        max_tokens = 4096, -- to avoid using the unsupported max_completion_tokens
+      },
+    },
   },
   ---Specify the special dual_boost mode
   ---1. enabled: Whether to enable dual_boost mode. Default to false.

lua/avante/providers/init.lua

@@ -10,6 +10,7 @@ local Utils = require("avante.utils")
 ---@field cohere AvanteProviderFunctor
 ---@field copilot AvanteProviderFunctor
 ---@field gemini AvanteProviderFunctor
+---@field mistral AvanteProviderFunctor
 ---@field ollama AvanteProviderFunctor
 ---@field openai AvanteProviderFunctor
 ---@field vertex_claude AvanteProviderFunctor