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/language_models/src/provider/copilot_chat.rs

@@ -24,7 +24,7 @@ use language_model::{
     LanguageModelProviderName, LanguageModelProviderState, LanguageModelRequest,
     LanguageModelRequestMessage, LanguageModelToolChoice, LanguageModelToolResultContent,
     LanguageModelToolSchemaFormat, LanguageModelToolUse, MessageContent, RateLimiter, Role,
-    StopReason,
+    StopReason, TokenUsage,
 };
 use settings::SettingsStore;
 use std::time::Duration;
@@ -378,6 +378,17 @@ pub fn map_to_language_model_completion_events(
                             }
                         }
 
+                        if let Some(usage) = event.usage {
+                            events.push(Ok(LanguageModelCompletionEvent::UsageUpdate(
+                                TokenUsage {
+                                    input_tokens: usage.prompt_tokens,
+                                    output_tokens: usage.completion_tokens,
+                                    cache_creation_input_tokens: 0,
+                                    cache_read_input_tokens: 0,
+                                },
+                            )));
+                        }
+
                         match choice.finish_reason.as_deref() {
                             Some("stop") => {
                                 events.push(Ok(LanguageModelCompletionEvent::Stop(