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/copilot_chat.rs

@@ -237,7 +237,7 @@ impl LanguageModel for CopilotChatLanguageModel {
         format!("copilot_chat/{}", self.model.id())
     }
 
-    fn max_token_count(&self) -> usize {
+    fn max_token_count(&self) -> u64 {
         self.model.max_token_count()
     }
 
@@ -245,7 +245,7 @@ impl LanguageModel for CopilotChatLanguageModel {
         &self,
         request: LanguageModelRequest,
         cx: &App,
-    ) -> BoxFuture<'static, Result<usize>> {
+    ) -> BoxFuture<'static, Result<u64>> {
         match self.model.vendor() {
             ModelVendor::Anthropic => count_anthropic_tokens(request, cx),
             ModelVendor::Google => count_google_tokens(request, cx),