ai: Separate model settings for each feature (#28088)

Closes: https://github.com/zed-industries/zed/issues/20582

Allows users to select a specific model for each AI-powered feature:
- Agent panel
- Inline assistant
- Thread summarization
- Commit message generation

If unspecified for a given feature, it will use the `default_model`
setting.

Release Notes:

- Added support for configuring a specific model for each AI-powered
feature

---------

Co-authored-by: Danilo Leal <daniloleal09@gmail.com>
Co-authored-by: Bennet Bo Fenner <bennetbo@gmx.de>

crates/agent/src/terminal_inline_assistant.rs

@@ -13,8 +13,8 @@ use fs::Fs;
 use gpui::{App, Entity, Focusable, Global, Subscription, UpdateGlobal, WeakEntity};
 use language::Buffer;
 use language_model::{
-    LanguageModelRegistry, LanguageModelRequest, LanguageModelRequestMessage, Role,
-    report_assistant_event,
+    ConfiguredModel, LanguageModelRegistry, LanguageModelRequest, LanguageModelRequestMessage,
+    Role, report_assistant_event,
 };
 use prompt_store::PromptBuilder;
 use std::sync::Arc;
@@ -286,7 +286,9 @@ impl TerminalInlineAssistant {
                 })
                 .log_err();
 
-            if let Some(model) = LanguageModelRegistry::read_global(cx).active_model() {
+            if let Some(ConfiguredModel { model, .. }) =
+                LanguageModelRegistry::read_global(cx).inline_assistant_model()
+            {
                 let codegen = assist.codegen.read(cx);
                 let executor = cx.background_executor().clone();
                 report_assistant_event(