language_models: Improve token counting for providers (#32853)

We push the usage data whenever we receive it from the provider to make
sure the counting is correct after the turn has ended.

- [x] Ollama 
- [x] Copilot 
- [x] Mistral 
- [x] OpenRouter 
- [x] LMStudio

Put all the changes into a single PR open to move these to separate PR
if that makes the review and testing easier.

Release Notes:

- N/A

crates/ollama/src/ollama.rs

@@ -183,6 +183,8 @@ pub struct ChatResponseDelta {
     pub done_reason: Option<String>,
     #[allow(unused)]
     pub done: bool,
+    pub prompt_eval_count: Option<u32>,
+    pub eval_count: Option<u32>,
 }
 
 #[derive(Serialize, Deserialize)]