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/assistant_context_editor/src/context.rs

@@ -678,7 +678,7 @@ pub struct AssistantContext {
     summary_task: Task<Option<()>>,
     completion_count: usize,
     pending_completions: Vec<PendingCompletion>,
-    token_count: Option<usize>,
+    token_count: Option<u64>,
     pending_token_count: Task<Option<()>>,
     pending_save: Task<Result<()>>,
     pending_cache_warming_task: Task<Option<()>>,
@@ -1250,7 +1250,7 @@ impl AssistantContext {
         }
     }
 
-    pub fn token_count(&self) -> Option<usize> {
+    pub fn token_count(&self) -> Option<u64> {
         self.token_count
     }