public/galaxy
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

Fix Warping indicator stuck after Bedrock LLM finishes responding

Browse Source 
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>
This commit is contained in:
Ryan Ward
2026-05-18 12:13:05 -05:00
co-authored by Claude Opus 4.6
parent 95b4708e44
commit f37a744692
27 changed files with 2423 additions and 65 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/src/ai/blocklist/usage/conversation_usage_view.rs
+55 -1
View File
@@ -1,5 +1,5 @@
use crate::ai::blocklist::usage::render_context_window_usage_icon;
use crate::ai::blocklist::view_util::format_credits;
use crate::ai::blocklist::view_util::{format_cost_cents, format_credits, format_token_count};
use crate::appearance::Appearance;
use crate::persistence::model::{
token_usage_category_display_name, ModelTokenUsage, FULL_TERMINAL_USE_CATEGORY,
@@ -37,6 +37,11 @@ pub struct ConversationUsageInfo {
pub lines_added: i32,
pub lines_removed: i32,
pub commands_executed: i32,
pub total_input_tokens: u32,
pub total_output_tokens: u32,
pub total_cache_read_tokens: u32,
pub total_cache_write_tokens: u32,
pub estimated_cost_cents: f32,
}
/// Timing information for the last set of agent responses
@@ -263,6 +268,55 @@ impl ConversationUsageView {
);
}
// Token usage section
let total_tokens = self.usage_info.total_input_tokens
+ self.usage_info.total_output_tokens
+ self.usage_info.total_cache_read_tokens
+ self.usage_info.total_cache_write_tokens;
if total_tokens > 0 {
labels.push(render_label_text("Total tokens", appearance));
values.push(render_value_text(
format_token_count(total_tokens),
appearance,
));
labels.push(render_label_text(" Input", appearance));
values.push(render_value_text(
format_token_count(self.usage_info.total_input_tokens),
appearance,
));
labels.push(render_label_text(" Output", appearance));
values.push(render_value_text(
format_token_count(self.usage_info.total_output_tokens),
appearance,
));
if self.usage_info.total_cache_read_tokens > 0 {
labels.push(render_label_text(" Cache read", appearance));
values.push(render_value_text(
format_token_count(self.usage_info.total_cache_read_tokens),
appearance,
));
}
if self.usage_info.total_cache_write_tokens > 0 {
labels.push(render_label_text(" Cache write", appearance));
values.push(render_value_text(
format_token_count(self.usage_info.total_cache_write_tokens),
appearance,
));
}
if self.usage_info.estimated_cost_cents > 0.0 {
labels.push(render_label_text("Estimated cost", appearance));
values.push(render_value_text(
format_cost_cents(self.usage_info.estimated_cost_cents),
appearance,
));
}
}
labels.push(render_label_text("Context window used", appearance));
let context_usage_str =
format!("{}%", (self.usage_info.context_window_usage * 100.).round());