fix: revert max_completion_tokens to max_tokens (#1741)

lua/avante/config.lua

@@ -196,7 +196,7 @@ M._defaults = {
     model = "gpt-4o",
     timeout = 30000, -- Timeout in milliseconds, increase this for reasoning models
     temperature = 0,
-    max_completion_tokens = 16384, -- Increase this to include reasoning tokens (for reasoning models)
+    max_tokens = 16384, -- Increase this to include reasoning tokens (for reasoning models)
     reasoning_effort = "medium", -- low|medium|high, only used for reasoning models
   },
   ---@type AvanteSupportedProvider
@@ -216,7 +216,7 @@ M._defaults = {
     api_version = "2024-12-01-preview",
     timeout = 30000, -- Timeout in milliseconds, increase this for reasoning models
     temperature = 0,
-    max_completion_tokens = 20480, -- Increase this to include reasoning tokens (for reasoning models)
+    max_tokens = 20480, -- Increase this to include reasoning tokens (for reasoning models)
     reasoning_effort = "medium", -- low|medium|high, only used for reasoning models
   },
   ---@type AvanteSupportedProvider

lua/avante/providers/azure.lua

@@ -2,7 +2,7 @@
 ---@field deployment string
 ---@field api_version string
 ---@field temperature number
----@field max_completion_tokens number
+---@field max_tokens number
 ---@field reasoning_effort? string
 
 local Utils = require("avante.utils")

lua/avante/providers/openai.lua

@@ -67,8 +67,6 @@ function M.set_allowed_params(provider_conf, request_body)
   else
     request_body.reasoning_effort = nil
   end
-  -- If max_tokens is set in config, unset max_completion_tokens
-  if request_body.max_tokens then request_body.max_completion_tokens = nil end
 end
 
 function M:parse_messages(opts)

lua/avante/types.lua

@@ -217,7 +217,6 @@ vim.g.avante_login = vim.g.avante_login
 ---@field __inherited_from? string
 ---@field temperature? number
 ---@field max_tokens? number
----@field max_completion_tokens? number
 ---@field reasoning_effort? string
 ---@field display_name? string
 ---