Improve goal completion usage reporting (#22907)

## Why

Goal completion follow-up turns currently receive a preformatted English
usage sentence such as `time used: 2586 seconds`. That nudges the model
to echo an awkward raw seconds count in the final reply, even though the
tool result already exposes structured usage fields like
`goal.timeUsedSeconds`, `goal.tokensUsed`, and `goal.tokenBudget`.

## What changed

- Replace the preformatted completion usage sentence with guidance to
read the structured goal fields from the tool result.
- Preserve token-budget reporting while allowing the model to phrase
elapsed time in a concise, human-friendly way that fits the response
language.
- Update core coverage for both the generated completion guidance and
the session flow that forwards it back to the model.

## Verification

Previously, it would have output a final message indicating that it
"worked for 303 seconds". Now it shows the following:

<img width="286" height="35" alt="image"
src="https://github.com/user-attachments/assets/d7011880-9449-46a7-856f-4e50ae00eb45"
/>

codex-rs/core/src/session/tests.rs

@@ -8893,7 +8893,7 @@ async fn completed_goal_accounts_current_turn_tokens_before_tool_response() -> a
     assert_eq!(complete_output["remainingTokens"], 0);
     assert_eq!(
         complete_output["completionBudgetReport"],
-        "Goal achieved. Report final budget usage to the user: tokens used: 580 of 500."
+        "Goal achieved. Report final usage from this tool result's structured goal fields. If `goal.tokenBudget` is present, include token usage from `goal.tokensUsed` and `goal.tokenBudget`. If `goal.timeUsedSeconds` is greater than 0, summarize elapsed time in a concise, human-friendly form appropriate to the response language."
     );
     let requests = responses.requests();
     let completion_followup_request = requests