refactor(core): Standardize model representation as an object olimorris#1521

This commit refactors the handling of model identifiers to consistently
support model objects. Previously, models were often treated as simple
strings. This change ensures that if a model is represented as an
object (e.g., `{ name = "model-id", ... }`), its `name` property is
correctly used.

Key changes:
- In `http.lua`, the request building logic now explicitly extracts
  `model.name` if `model` is an object, ensuring the correct string
  identifier is sent in the API request.
- Adapters for Copilot and OpenAI have been updated to access
  `model.name` for internal logic that relies on the model identifier,
  such as conditional parameter availability or message role
  transformations.

This change improves the robustness and flexibility of model handling
within the system, paving the way for more structured model metadata.

Author: dhruvinsh

lua/codecompanion/adapters/copilot.lua

@@ -336,7 +336,7 @@ return {
         if type(model) == "function" then
           model = model()
         end
-        return not vim.startswith(model, "o1")
+        return not vim.startswith(model.name, "o1")
       end,
       desc = "What sampling temperature to use, between 0 and 2. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. We generally recommend altering this or top_p but not both.",
     },
@@ -358,7 +358,7 @@ return {
         if type(model) == "function" then
           model = model()
         end
-        return not vim.startswith(model, "o1")
+        return not vim.startswith(model.name, "o1")
       end,
       desc = "An alternative to sampling with temperature, called nucleus sampling, where the model considers the results of the tokens with top_p probability mass. So 0.1 means only the tokens comprising the top 10% probability mass are considered. We generally recommend altering this or temperature but not both.",
     },
@@ -373,7 +373,7 @@ return {
         if type(model) == "function" then
           model = model()
         end
-        return not vim.startswith(model, "o1")
+        return not vim.startswith(model.name, "o1")
       end,
       desc = "How many chat completions to generate for each prompt.",
     },

lua/codecompanion/adapters/openai.lua

@@ -80,7 +80,7 @@ return {
       messages = vim
         .iter(messages)
         :map(function(m)
-          if vim.startswith(model, "o1") and m.role == "system" then
+          if vim.startswith(model.name, "o1") and m.role == "system" then
             m.role = self.roles.user
           end
 

lua/codecompanion/http.lua

@@ -86,18 +86,21 @@ function Client:request(payload, actions, opts)
 
   adapter:get_env_vars()
 
-  local body = self.opts.encode(
-    vim.tbl_extend(
-      "keep",
-      handlers.form_parameters
-          and handlers.form_parameters(adapter, adapter:set_env_vars(adapter.parameters), payload.messages)
-        or {},
-      handlers.form_messages and handlers.form_messages(adapter, payload.messages) or {},
-      handlers.form_tools and handlers.form_tools(adapter, payload.tools) or {},
-      adapter.body and adapter.body or {},
-      handlers.set_body and handlers.set_body(adapter, payload) or {}
-    )
+  local body_tbl = vim.tbl_extend(
+    "keep",
+    handlers.form_parameters
+        and handlers.form_parameters(adapter, adapter:set_env_vars(adapter.parameters), payload.messages)
+      or {},
+    handlers.form_messages and handlers.form_messages(adapter, payload.messages) or {},
+    handlers.form_tools and handlers.form_tools(adapter, payload.tools) or {},
+    adapter.body and adapter.body or {},
+    handlers.set_body and handlers.set_body(adapter, payload) or {}
   )
+  if body_tbl.model and type(body_tbl.model) == "table" then
+    body_tbl.model = body_tbl.model.name
+  end
+
+  local body = self.opts.encode(body_tbl)
 
   local body_file = Path.new(vim.fn.tempname() .. ".json")
   body_file:write(vim.split(body, "\n"), "w")