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/open_router/src/open_router.rs

@@ -50,7 +50,7 @@ impl From<Role> for String {
 pub struct Model {
     pub name: String,
     pub display_name: Option<String>,
-    pub max_tokens: usize,
+    pub max_tokens: u64,
     pub supports_tools: Option<bool>,
     pub supports_images: Option<bool>,
 }
@@ -73,7 +73,7 @@ impl Model {
     pub fn new(
         name: &str,
         display_name: Option<&str>,
-        max_tokens: Option<usize>,
+        max_tokens: Option<u64>,
         supports_tools: Option<bool>,
         supports_images: Option<bool>,
     ) -> Self {
@@ -94,11 +94,11 @@ impl Model {
         self.display_name.as_ref().unwrap_or(&self.name)
     }
 
-    pub fn max_token_count(&self) -> usize {
+    pub fn max_token_count(&self) -> u64 {
         self.max_tokens
     }
 
-    pub fn max_output_tokens(&self) -> Option<u32> {
+    pub fn max_output_tokens(&self) -> Option<u64> {
         None
     }
 
@@ -117,7 +117,7 @@ pub struct Request {
     pub messages: Vec<RequestMessage>,
     pub stream: bool,
     #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub max_tokens: Option<u32>,
+    pub max_tokens: Option<u64>,
     #[serde(default, skip_serializing_if = "Vec::is_empty")]
     pub stop: Vec<String>,
     pub temperature: f32,
@@ -318,9 +318,9 @@ pub struct FunctionChunk {
 
 #[derive(Serialize, Deserialize, Debug)]
 pub struct Usage {
-    pub prompt_tokens: u32,
-    pub completion_tokens: u32,
-    pub total_tokens: u32,
+    pub prompt_tokens: u64,
+    pub completion_tokens: u64,
+    pub total_tokens: u64,
 }
 
 #[derive(Serialize, Deserialize, Debug)]
@@ -369,7 +369,7 @@ pub struct ModelEntry {
     pub created: usize,
     pub description: String,
     #[serde(default, skip_serializing_if = "Option::is_none")]
-    pub context_length: Option<usize>,
+    pub context_length: Option<u64>,
     #[serde(default, skip_serializing_if = "Vec::is_empty")]
     pub supported_parameters: Vec<String>,
     #[serde(default, skip_serializing_if = "Option::is_none")]