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/agent/src/tool_use.rs

@@ -427,7 +427,7 @@ impl ToolUseState {
 
                 // Protect from overly large output
                 let tool_output_limit = configured_model
-                    .map(|model| model.model.max_token_count() * BYTES_PER_TOKEN_ESTIMATE)
+                    .map(|model| model.model.max_token_count() as usize * BYTES_PER_TOKEN_ESTIMATE)
                     .unwrap_or(usize::MAX);
 
                 let content = match tool_result {