assistant: Overhaul provider infrastructure (#14929)

<img width="624" alt="image"
src="https://github.com/user-attachments/assets/f492b0bd-14c3-49e2-b2ff-dc78e52b0815">

- [x] Correctly set custom model token count
- [x] How to count tokens for Gemini models?
- [x] Feature flag zed.dev provider
- [x] Figure out how to configure custom models
- [ ] Update docs

Release Notes:

- Added support for quickly switching between multiple language model
providers in the assistant panel

---------

Co-authored-by: Antonio <antonio@zed.dev>

crates/feature_flags/src/feature_flags.rs

@@ -29,6 +29,11 @@ impl FeatureFlag for Remoting {
     const NAME: &'static str = "remoting";
 }
 
+pub struct LanguageModels {}
+impl FeatureFlag for LanguageModels {
+    const NAME: &'static str = "language-models";
+}
+
 pub struct TerminalInlineAssist {}
 impl FeatureFlag for TerminalInlineAssist {
     const NAME: &'static str = "terminal-inline-assist";
@@ -65,6 +70,10 @@ pub trait FeatureFlagAppExt {
     fn set_staff(&mut self, staff: bool);
     fn has_flag<T: FeatureFlag>(&self) -> bool;
     fn is_staff(&self) -> bool;
+
+    fn observe_flag<T: FeatureFlag, F>(&mut self, callback: F) -> Subscription
+    where
+        F: Fn(bool, &mut AppContext) + 'static;
 }
 
 impl FeatureFlagAppExt for AppContext {
@@ -90,4 +99,14 @@ impl FeatureFlagAppExt for AppContext {
             .map(|flags| flags.staff)
             .unwrap_or(false)
     }
+
+    fn observe_flag<T: FeatureFlag, F>(&mut self, callback: F) -> Subscription
+    where
+        F: Fn(bool, &mut AppContext) + 'static,
+    {
+        self.observe_global::<FeatureFlags>(move |cx| {
+            let feature_flags = cx.global::<FeatureFlags>();
+            callback(feature_flags.has_flag(<T as FeatureFlag>::NAME), cx);
+        })
+    }
 }