Display blended token count in status line (#21669)

## Why

The configurable `/statusline` and terminal title can display session
token usage. That display was using the raw total token count, which
includes cached input tokens, so it significantly overstated the token
usage compared with the blended token count shown elsewhere (in
`/status` and tracked in goals). This inconsistency resulted in user
confusion. We don't want to report cached tokens because we don't charge
for them and they are somewhat of an implementation detail that users
shouldn't care about.

## What changed

- Use `TokenUsage::blended_total()` for the `used-tokens` status surface
item so cached input is excluded.
- Add a brief comment to `tokens_in_context_window()` clarifying that it
returns raw `total_tokens`, whose meaning depends on whether the caller
has last-turn or accumulated usage.

codex-rs/tui/src/chatwidget/status_surfaces.rs

@@ -592,7 +592,7 @@ impl ChatWidget {
             StatusLineItem::Status => Some(self.run_state_status_text()),
             StatusLineItem::UsedTokens => {
                 let usage = self.status_line_total_usage();
-                let total = usage.tokens_in_context_window();
+                let total = usage.blended_total();
                 if total <= 0 {
                     None
                 } else {

codex-rs/tui/src/token_usage.rs

@@ -34,6 +34,8 @@ impl TokenUsage {
         (self.non_cached_input() + self.output_tokens.max(0)).max(0)
     }
 
+    /// Returns the raw `total_tokens` value. For `last_token_usage`, this is the latest active
+    /// context size; for `total_token_usage`, this is the accumulated session total.
     pub(crate) fn tokens_in_context_window(&self) -> i64 {
         self.total_tokens
     }