agent: Fix issues with usage display sometimes showing initially fetched usage (#33125)

Having `Thread::last_usage` as an override of the initially fetched
usage could cause the initial usage to be displayed when the current
thread is empty or in text threads. Fix is to just store last usage info
in `UserStore` and not have these overrides

Release Notes:

- Agent: Fixed request usage display to always include the most recently
known usage - there were some cases where it would show the initially
requested usage.

crates/inline_completion/src/inline_completion.rs

@@ -1,14 +1,9 @@
 use std::ops::Range;
-use std::str::FromStr as _;
 
-use anyhow::{Context as _, Result};
-use gpui::http_client::http::{HeaderMap, HeaderValue};
+use client::EditPredictionUsage;
 use gpui::{App, Context, Entity, SharedString};
 use language::Buffer;
 use project::Project;
-use zed_llm_client::{
-    EDIT_PREDICTIONS_USAGE_AMOUNT_HEADER_NAME, EDIT_PREDICTIONS_USAGE_LIMIT_HEADER_NAME, UsageLimit,
-};
 
 // TODO: Find a better home for `Direction`.
 //
@@ -59,39 +54,6 @@ impl DataCollectionState {
     }
 }
 
-#[derive(Debug, Clone, Copy)]
-pub struct EditPredictionUsage {
-    pub limit: UsageLimit,
-    pub amount: i32,
-}
-
-impl EditPredictionUsage {
-    pub fn from_headers(headers: &HeaderMap<HeaderValue>) -> Result<Self> {
-        let limit = headers
-            .get(EDIT_PREDICTIONS_USAGE_LIMIT_HEADER_NAME)
-            .with_context(|| {
-                format!("missing {EDIT_PREDICTIONS_USAGE_LIMIT_HEADER_NAME:?} header")
-            })?;
-        let limit = UsageLimit::from_str(limit.to_str()?)?;
-
-        let amount = headers
-            .get(EDIT_PREDICTIONS_USAGE_AMOUNT_HEADER_NAME)
-            .with_context(|| {
-                format!("missing {EDIT_PREDICTIONS_USAGE_AMOUNT_HEADER_NAME:?} header")
-            })?;
-        let amount = amount.to_str()?.parse::<i32>()?;
-
-        Ok(Self { limit, amount })
-    }
-
-    pub fn over_limit(&self) -> bool {
-        match self.limit {
-            UsageLimit::Limited(limit) => self.amount >= limit,
-            UsageLimit::Unlimited => false,
-        }
-    }
-}
-
 pub trait EditPredictionProvider: 'static + Sized {
     fn name() -> &'static str;
     fn display_name() -> &'static str;