Standardize on u64 for token counts (#32869)

Previously we were using a mix of `u32` and `usize`, e.g. `max_tokens:
usize, max_output_tokens: Option<u32>` in the same `struct`.

Although [tiktoken](https://github.com/openai/tiktoken) uses `usize`,
token counts should be consistent across targets (e.g. the same model
doesn't suddenly get a smaller context window if you're compiling for
wasm32), and these token counts could end up getting serialized using a
binary protocol, so `usize` is not the right choice for token counts.

I chose to standardize on `u64` over `u32` because we don't store many
of them (so the extra size should be insignificant) and future models
may exceed `u32::MAX` tokens.

Release Notes:

- N/A

crates/language_models/src/provider/mistral.rs

@@ -43,9 +43,9 @@ pub struct MistralSettings {
 pub struct AvailableModel {
     pub name: String,
     pub display_name: Option<String>,
-    pub max_tokens: usize,
-    pub max_output_tokens: Option<u32>,
-    pub max_completion_tokens: Option<u32>,
+    pub max_tokens: u64,
+    pub max_output_tokens: Option<u64>,
+    pub max_completion_tokens: Option<u64>,
     pub supports_tools: Option<bool>,
     pub supports_images: Option<bool>,
 }
@@ -322,11 +322,11 @@ impl LanguageModel for MistralLanguageModel {
         format!("mistral/{}", self.model.id())
     }
 
-    fn max_token_count(&self) -> usize {
+    fn max_token_count(&self) -> u64 {
         self.model.max_token_count()
     }
 
-    fn max_output_tokens(&self) -> Option<u32> {
+    fn max_output_tokens(&self) -> Option<u64> {
         self.model.max_output_tokens()
     }
 
@@ -334,7 +334,7 @@ impl LanguageModel for MistralLanguageModel {
         &self,
         request: LanguageModelRequest,
         cx: &App,
-    ) -> BoxFuture<'static, Result<usize>> {
+    ) -> BoxFuture<'static, Result<u64>> {
         cx.background_spawn(async move {
             let messages = request
                 .messages
@@ -351,7 +351,7 @@ impl LanguageModel for MistralLanguageModel {
                 })
                 .collect::<Vec<_>>();
 
-            tiktoken_rs::num_tokens_from_messages("gpt-4", &messages)
+            tiktoken_rs::num_tokens_from_messages("gpt-4", &messages).map(|tokens| tokens as u64)
         })
         .boxed()
     }
@@ -386,7 +386,7 @@ impl LanguageModel for MistralLanguageModel {
 pub fn into_mistral(
     request: LanguageModelRequest,
     model: String,
-    max_output_tokens: Option<u32>,
+    max_output_tokens: Option<u64>,
 ) -> mistral::Request {
     let stream = true;