Fix Warping indicator stuck after Bedrock LLM finishes responding

Bedrock was calling suggest_next_prompt tool which created a SuggestPrompt
action that waited forever on a oneshot channel for UI interaction that
never fires in the Bedrock path, keeping the conversation permanently
InProgress. Fixed by filtering the tool from the Bedrock tool list and
skipping it at the stream level when the LLM calls it from context history.

Also includes: Bedrock cache token tracking, cost estimation, LSP
improvements, conversation usage view updates, and external config support.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

app/src/ai/agent/conversation.rs

@@ -3062,6 +3062,20 @@ impl AIConversation {
         self.total_token_usage_by_model.values().cloned().collect()
     }
 
+    pub fn total_tokens(&self) -> u32 {
+        self.total_token_usage_by_model
+            .values()
+            .map(Self::total_tokens_for_usage)
+            .sum()
+    }
+
+    pub fn total_cost_cents(&self) -> f32 {
+        self.total_token_usage_by_model
+            .values()
+            .map(|u| u.cost_in_cents)
+            .sum()
+    }
+
     fn total_tokens_for_usage(usage: &TokenUsage) -> u32 {
         usage.total_input + usage.output + usage.input_cache_read + usage.input_cache_write
     }