Compare commits

...

2 commits

Author SHA1 Message Date
Kent Overstreet
f408bb5d86 Persist agent stats across restarts, add per-tool metrics grid
Stats now survive daemon restarts via ~/.consciousness/agent-stats.json,
loaded into a global Mutex<HashMap> on first access. Each tool type
tracks last count, EWMA (alpha=0.3), and total calls.

UI shows a grid view: tool | last | avg | total, sorted by total desc.
Failures row appears at bottom if any occurred.

Also fixes temperature/priority not being applied to spawned agents.

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-11 23:03:10 -04:00
Kent Overstreet
314ae9c4cb agent stats: track tool calls by type with EWMA, add Stats pane
- RunStats now includes tool_calls_by_type HashMap
- AutoAgent tracks runs, last_stats, and EWMA for tool calls/failures
- Removed duplicate stats fields from individual agent structs
- Fixed provenance to use bare agent name (no "agent:" prefix)
- Subconscious screen now displays both agent types consistently
- Added Stats pane showing tool call breakdown sorted by count

Co-Authored-By: Proof of Concept <poc@bcachefs.org>
2026-04-11 22:12:46 -04:00
4 changed files with 269 additions and 63 deletions

View file

@ -22,13 +22,66 @@ use super::Agent;
// Agent logging — shared by Mind and CLI paths
// ---------------------------------------------------------------------------
#[derive(Clone, serde::Serialize)]
/// Stats from a single run.
#[derive(Clone, Default, serde::Serialize, serde::Deserialize)]
pub struct RunStats {
pub messages: usize,
pub tool_calls: usize,
pub tool_failures: usize,
pub tool_calls_by_type: HashMap<String, usize>,
}
/// Per-tool accumulated stats.
#[derive(Clone, Default, serde::Serialize, serde::Deserialize)]
pub struct ToolStats {
pub last: usize,
pub ewma: f64,
pub total: usize,
}
/// Persisted stats for an agent (survives restarts).
#[derive(Clone, Default, serde::Serialize, serde::Deserialize)]
pub struct PersistedStats {
pub runs: usize,
pub last_stats: Option<RunStats>,
/// Per-tool-type stats: last, ewma, total.
pub by_tool: HashMap<String, ToolStats>,
/// Failed calls stats.
pub failures: ToolStats,
}
fn stats_path() -> std::path::PathBuf {
dirs::home_dir().unwrap_or_default()
.join(".consciousness/agent-stats.json")
}
static AGENT_STATS: std::sync::OnceLock<std::sync::Mutex<HashMap<String, PersistedStats>>> =
std::sync::OnceLock::new();
fn stats_map() -> &'static std::sync::Mutex<HashMap<String, PersistedStats>> {
AGENT_STATS.get_or_init(|| {
let map: HashMap<String, PersistedStats> = std::fs::read_to_string(stats_path()).ok()
.and_then(|s| serde_json::from_str(&s).ok())
.unwrap_or_default();
std::sync::Mutex::new(map)
})
}
pub fn get_stats(name: &str) -> PersistedStats {
stats_map().lock().ok()
.and_then(|m| m.get(name).cloned())
.unwrap_or_default()
}
pub fn set_stats(name: &str, stats: PersistedStats) {
if let Ok(mut map) = stats_map().lock() {
map.insert(name.to_string(), stats);
if let Ok(json) = serde_json::to_string_pretty(&*map) {
let _ = std::fs::write(stats_path(), json);
}
}
}
/// Save agent conversation to JSON log file.
/// Used by both mind-run agents and CLI-run agents.
pub async fn save_agent_log(name: &str, agent: &std::sync::Arc<Agent>) -> RunStats {
@ -57,6 +110,7 @@ fn compute_run_stats(conversation: &[super::context::AstNode]) -> RunStats {
let mut messages = 0usize;
let mut tool_calls = 0usize;
let mut tool_failures = 0usize;
let mut by_type: HashMap<String, usize> = HashMap::new();
for node in conversation {
@ -64,16 +118,27 @@ fn compute_run_stats(conversation: &[super::context::AstNode]) -> RunStats {
messages += 1;
for child in children {
if let AstNode::Leaf(leaf) = child {
if let NodeBody::ToolCall { name, .. } = leaf.body() {
tool_calls += 1;
*by_type.entry(name.to_string()).or_default() += 1;
match leaf.body() {
NodeBody::ToolCall { name, .. } => {
tool_calls += 1;
*by_type.entry(name.to_string()).or_default() += 1;
}
NodeBody::ToolResult(text) => {
// Detect failures from error patterns in result
let t = text.trim_start();
if t.starts_with("Error") || t.starts_with("error:") ||
t.starts_with("Failed") || t.contains("not found") {
tool_failures += 1;
}
}
_ => {}
}
}
}
}
}
RunStats { messages, tool_calls, tool_calls_by_type: by_type }
RunStats { messages, tool_calls, tool_failures, tool_calls_by_type: by_type }
}
// ---------------------------------------------------------------------------
@ -96,8 +161,11 @@ pub struct AutoAgent {
pub current_phase: String,
pub turn: usize,
pub enabled: bool,
pub temperature: f32,
pub priority: i32,
}
/// Per-run conversation backend — wraps a forked agent.
struct Backend(std::sync::Arc<Agent>);
@ -160,14 +228,16 @@ impl AutoAgent {
name: String,
tools: Vec<agent_tools::Tool>,
steps: Vec<AutoStep>,
_temperature: f32,
_priority: i32,
temperature: f32,
priority: i32,
) -> Self {
Self {
name, tools, steps,
current_phase: String::new(),
turn: 0,
enabled: true,
temperature,
priority,
}
}
@ -203,7 +273,8 @@ impl AutoAgent {
let mut st = agent.state.lock().await;
st.provenance = format!("standalone:{}", self.name);
st.tools = self.tools.clone();
st.priority = Some(10);
st.temperature = self.temperature;
st.priority = Some(self.priority);
}
let mut backend = Backend(agent.clone());
@ -242,6 +313,36 @@ impl AutoAgent {
result
}
/// Update stats after a run completes. Called with the stats from save_agent_log.
pub fn update_stats(&self, run_stats: RunStats) {
const ALPHA: f64 = 0.3;
let old = get_stats(&self.name);
// Update per-tool stats
let mut by_tool = old.by_tool;
for (tool, count) in &run_stats.tool_calls_by_type {
let entry = by_tool.entry(tool.clone()).or_default();
entry.last = *count;
entry.ewma = ALPHA * (*count as f64) + (1.0 - ALPHA) * entry.ewma;
entry.total += count;
}
// Update failure stats
let failures = ToolStats {
last: run_stats.tool_failures,
ewma: ALPHA * (run_stats.tool_failures as f64) + (1.0 - ALPHA) * old.failures.ewma,
total: old.failures.total + run_stats.tool_failures,
};
let new = PersistedStats {
runs: old.runs + 1,
last_stats: Some(run_stats),
by_tool,
failures,
};
set_stats(&self.name, new);
}
async fn run_with_backend(
&mut self,
backend: &mut Backend,

View file

@ -294,6 +294,7 @@ pub struct SubconsciousSnapshot {
pub enabled: bool,
pub current_phase: String,
pub turn: usize,
pub runs: usize,
pub last_run_secs_ago: Option<f64>,
/// Shared handle to the forked agent — UI locks to read entries.
pub forked_agent: Option<Arc<crate::agent::Agent>>,
@ -303,6 +304,9 @@ pub struct SubconsciousSnapshot {
pub state: std::collections::BTreeMap<String, String>,
/// Recent store activity for this agent: (key, timestamp), newest first.
pub history: Vec<(String, i64)>,
pub last_stats: Option<crate::agent::oneshot::RunStats>,
pub tool_calls_ewma: f64,
pub tool_failures_ewma: f64,
}
struct SubconsciousAgent {
@ -361,17 +365,23 @@ impl SubconsciousAgent {
}
fn snapshot(&self, state: &std::collections::BTreeMap<String, String>, history: Vec<(String, i64)>) -> SubconsciousSnapshot {
let stats = crate::agent::oneshot::get_stats(&self.name);
let tool_calls_ewma: f64 = stats.by_tool.values().map(|t| t.ewma).sum();
SubconsciousSnapshot {
name: self.name.clone(),
running: self.is_running(),
enabled: self.auto.enabled,
current_phase: self.auto.current_phase.clone(),
turn: self.auto.turn,
runs: stats.runs,
last_run_secs_ago: self.last_run.map(|t| t.elapsed().as_secs_f64()),
forked_agent: self.forked_agent.clone(),
fork_point: self.fork_point,
state: state.clone(),
history,
last_stats: stats.last_stats.clone(),
tool_calls_ewma,
tool_failures_ewma: stats.failures.ewma,
}
}
}
@ -477,7 +487,7 @@ impl Subconscious {
any_finished = true;
let (auto_back, result) = handle.await.unwrap_or_else(
|e| (AutoAgent::new(String::new(), vec![], vec![], 0.0, 0),
|e| (AutoAgent::new(String::new(), vec![], vec![], 0.6, 0),
Err(format!("task panicked: {}", e))));
self.agents[i].auto = auto_back;
@ -576,7 +586,7 @@ impl Subconscious {
self.agents[i].last_trigger_bytes = conversation_bytes;
let auto = std::mem::replace(&mut self.agents[i].auto,
AutoAgent::new(String::new(), vec![], vec![], 0.0, 0));
AutoAgent::new(String::new(), vec![], vec![], 0.6, 0));
to_run.push((i, auto));
}
@ -596,9 +606,10 @@ impl Subconscious {
{
let mut st = forked.state.lock().await;
st.provenance = auto.name.clone();
st.temperature = auto.temperature;
// Surface agent gets near-interactive priority;
// other subconscious agents get lower priority.
st.priority = Some(if auto.name == "surface" { 1 } else { 2 });
st.priority = Some(if auto.name == "surface" { 1 } else { auto.priority });
}
let fork_point = forked.context.lock().await.conversation().len();
@ -614,7 +625,8 @@ impl Subconscious {
self.agents[idx].handle = Some(tokio::spawn(async move {
let result = auto.run_forked_shared(&forked, &keys, &st, &recent).await;
crate::agent::oneshot::save_agent_log(&auto.name, &forked).await;
let stats = crate::agent::oneshot::save_agent_log(&auto.name, &forked).await;
auto.update_stats(stats);
(auto, result)
}));
}

View file

@ -34,12 +34,10 @@ struct UnconsciousAgent {
name: String,
enabled: bool,
auto: AutoAgent,
handle: Option<tokio::task::JoinHandle<(AutoAgent, Result<String, String>, RunStats)>>,
handle: Option<tokio::task::JoinHandle<(AutoAgent, Result<String, String>)>>,
/// Shared agent handle — UI locks to read context live.
pub agent: Option<std::sync::Arc<crate::agent::Agent>>,
last_run: Option<Instant>,
runs: usize,
last_stats: Option<RunStats>,
}
impl UnconsciousAgent {
@ -64,6 +62,8 @@ pub struct UnconsciousSnapshot {
pub last_stats: Option<RunStats>,
/// Recent store activity for this agent: (key, timestamp), newest first.
pub history: Vec<(String, i64)>,
pub tool_calls_ewma: f64,
pub tool_failures_ewma: f64,
}
pub struct Unconscious {
@ -107,8 +107,6 @@ impl Unconscious {
handle: None,
agent: None,
last_run: None,
runs: 0,
last_stats: None,
});
}
agents.sort_by(|a, b| a.name.cmp(&b.name));
@ -144,15 +142,19 @@ impl Unconscious {
self.agents.iter().map(|a| {
let history = store.map(|st| st.recent_by_provenance(&a.name, 30))
.unwrap_or_default();
let stats = crate::agent::oneshot::get_stats(&a.name);
let tool_calls_ewma: f64 = stats.by_tool.values().map(|t| t.ewma).sum();
UnconsciousSnapshot {
name: a.name.clone(),
running: a.is_running(),
enabled: a.enabled,
runs: a.runs,
runs: stats.runs,
last_run_secs_ago: a.last_run.map(|t| t.elapsed().as_secs_f64()),
agent: a.agent.clone(),
last_stats: a.last_stats.clone(),
last_stats: stats.last_stats.clone(),
history,
tool_calls_ewma,
tool_failures_ewma: stats.failures.ewma,
}
}).collect()
}
@ -180,15 +182,13 @@ impl Unconscious {
if agent.handle.as_ref().is_some_and(|h| h.is_finished()) {
let handle = agent.handle.take().unwrap();
agent.last_run = Some(Instant::now());
agent.runs += 1;
// Get the AutoAgent back from the finished task
// Get the AutoAgent back from the finished task (stats already updated)
match handle.now_or_never() {
Some(Ok((auto_back, result, stats))) => {
Some(Ok((auto_back, result))) => {
agent.auto = auto_back;
agent.last_stats = Some(stats);
match result {
Ok(_) => dbglog!("[unconscious] {} completed (run {})",
agent.name, agent.runs),
agent.name, crate::agent::oneshot::get_stats(&agent.name).runs),
Err(e) => dbglog!("[unconscious] {} failed: {}", agent.name, e),
}
}
@ -244,7 +244,7 @@ impl Unconscious {
// Swap auto out, replace steps with resolved prompts
let mut auto = std::mem::replace(&mut self.agents[idx].auto,
AutoAgent::new(String::new(), vec![], vec![], 0.0, 0));
AutoAgent::new(String::new(), vec![], vec![], 0.6, 0));
let orig_steps = std::mem::replace(&mut auto.steps,
batch.steps.iter().map(|s| AutoStep {
prompt: s.prompt.clone(),
@ -293,7 +293,8 @@ impl Unconscious {
{
let mut st = agent.state.lock().await;
st.provenance = auto.name.clone();
st.priority = Some(10);
st.priority = Some(auto.priority);
st.temperature = auto.temperature;
}
self.agents[idx].agent = Some(agent.clone());
@ -301,8 +302,9 @@ impl Unconscious {
self.agents[idx].handle = Some(tokio::spawn(async move {
let result = auto.run_shared(&agent).await;
let stats = crate::agent::oneshot::save_agent_log(&auto.name, &agent).await;
auto.update_stats(stats);
auto.steps = orig_steps;
(auto, result, stats)
(auto, result)
}));
}
}

View file

@ -18,10 +18,10 @@ use super::{App, ScreenView, screen_legend};
use super::widgets::{SectionTree, SectionView, section_to_view, pane_block_focused, tree_legend, format_age, format_ts_age};
#[derive(Clone, Copy, PartialEq)]
enum Pane { Agents, Outputs, History, Context }
enum Pane { Agents, Outputs, Stats, History, Context }
// Clockwise: top-left → right → bottom-left → middle-left
const PANE_ORDER: &[Pane] = &[Pane::Agents, Pane::Context, Pane::History, Pane::Outputs];
const PANE_ORDER: &[Pane] = &[Pane::Agents, Pane::Context, Pane::History, Pane::Stats, Pane::Outputs];
pub(crate) struct SubconsciousScreen {
focus: Pane,
@ -29,6 +29,7 @@ pub(crate) struct SubconsciousScreen {
output_tree: SectionTree,
context_tree: SectionTree,
history_scroll: super::scroll_pane::ScrollPaneState,
stats_scroll: super::scroll_pane::ScrollPaneState,
}
impl SubconsciousScreen {
@ -41,6 +42,7 @@ impl SubconsciousScreen {
output_tree: SectionTree::new(),
context_tree: SectionTree::new(),
history_scroll: super::scroll_pane::ScrollPaneState::new(),
stats_scroll: super::scroll_pane::ScrollPaneState::new(),
}
}
@ -87,6 +89,13 @@ impl ScreenView for SubconsciousScreen {
_ => {}
}
Pane::Outputs => self.output_tree.handle_nav(code, &output_sections, area.height),
Pane::Stats => match code {
KeyCode::Up => self.stats_scroll.scroll_up(3),
KeyCode::Down => self.stats_scroll.scroll_down(3),
KeyCode::PageUp => self.stats_scroll.scroll_up(20),
KeyCode::PageDown => self.stats_scroll.scroll_down(20),
_ => {}
}
Pane::History => match code {
KeyCode::Up => self.history_scroll.scroll_up(3),
KeyCode::Down => self.history_scroll.scroll_down(3),
@ -106,7 +115,7 @@ impl ScreenView for SubconsciousScreen {
Constraint::Percentage(62),
]).areas(area);
// Left column: agent list (top) | outputs (middle) | history (bottom, main)
// Left column: agent list | outputs | stats | history
let unc_count = if app.unconscious_state.is_empty() { 0 }
else { app.unconscious_state.len() + 1 }; // +1 for separator
let agent_count = (app.agent_state.len() + unc_count).max(1) as u16;
@ -114,15 +123,21 @@ impl ScreenView for SubconsciousScreen {
let output_lines = app.agent_state.get(self.selected())
.map(|s| s.state.values().map(|v| v.lines().count() + 1).sum::<usize>())
.unwrap_or(0);
let output_height = (output_lines as u16 + 2).min(left.height / 4).max(3);
let [list_area, output_area, history_area] = Layout::vertical([
let output_height = (output_lines as u16 + 2).min(left.height / 5).max(3);
let stats_lines = self.selected_persisted_stats(app)
.map(|s| s.by_tool.len())
.unwrap_or(0);
let stats_height = (stats_lines as u16 + 2).min(left.height / 5).max(3);
let [list_area, output_area, stats_area, history_area] = Layout::vertical([
Constraint::Length(list_height),
Constraint::Length(output_height),
Constraint::Length(stats_height),
Constraint::Min(5),
]).areas(left);
self.draw_list(frame, list_area, app);
self.draw_outputs(frame, output_area, app);
self.draw_stats(frame, stats_area, app);
self.draw_history(frame, history_area, app);
self.draw_context(frame, right, &context_sections, app);
}
@ -147,6 +162,7 @@ impl SubconsciousScreen {
self.output_tree = SectionTree::new();
self.context_tree = SectionTree::new();
self.history_scroll = super::scroll_pane::ScrollPaneState::new();
self.stats_scroll = super::scroll_pane::ScrollPaneState::new();
}
/// Get the agent Arc for the selected item, whether subconscious or unconscious.
@ -175,6 +191,12 @@ impl SubconsciousScreen {
.unwrap_or(&[])
}
/// Get persisted stats for the selected agent.
fn selected_persisted_stats(&self, app: &App) -> Option<crate::agent::oneshot::PersistedStats> {
let name = self.selected_agent_name(app)?;
Some(crate::agent::oneshot::get_stats(&name))
}
fn output_sections(&self, app: &App) -> Vec<SectionView> {
let snap = match app.agent_state.get(self.selected()) {
Some(s) => s,
@ -211,37 +233,39 @@ impl SubconsciousScreen {
fn draw_list(&mut self, frame: &mut Frame, area: Rect, app: &App) {
let mut items: Vec<ListItem> = app.agent_state.iter().map(|snap| {
if !snap.enabled {
ListItem::from(Line::from(vec![
Span::styled(&snap.name, Style::default().fg(Color::DarkGray)),
Span::styled(" ○ off", Style::default().fg(Color::DarkGray)),
]))
let (name_color, indicator) = if !snap.enabled {
(Color::DarkGray, "")
} else if snap.running {
ListItem::from(Line::from(vec![
Span::styled(&snap.name, Style::default().fg(Color::Green)),
Span::styled("", Style::default().fg(Color::Green)),
Span::styled(
format!("p:{} t:{}", snap.current_phase, snap.turn),
Style::default().fg(Color::DarkGray),
),
]))
(Color::Green, "")
} else {
let ago = snap.last_run_secs_ago
.map(|s| format_age(s))
.unwrap_or_else(|| "".to_string());
let entries = snap.forked_agent.as_ref()
.and_then(|a| a.context.try_lock().ok())
.map(|ctx| ctx.conversation().len().saturating_sub(snap.fork_point))
.unwrap_or(0);
ListItem::from(Line::from(vec![
Span::styled(&snap.name, Style::default().fg(Color::Gray)),
Span::styled("", Style::default().fg(Color::DarkGray)),
Span::styled(
format!("{} {}e", ago, entries),
Style::default().fg(Color::DarkGray),
),
]))
}
(Color::Gray, "")
};
let ago = snap.last_run_secs_ago
.map(|s| format_age(s))
.unwrap_or_else(|| "".to_string());
let detail = if snap.running {
format!("p:{} t:{}", snap.current_phase, snap.turn)
} else if !snap.enabled {
"off".to_string()
} else if let Some(ref stats) = snap.last_stats {
let fail_str = if stats.tool_failures > 0 {
format!(" {}fail", stats.tool_failures)
} else {
String::new()
};
format!("×{} {} {}tc{} avg:{:.1}",
snap.runs, ago,
stats.tool_calls, fail_str,
snap.tool_calls_ewma)
} else {
format!("×{} {}", snap.runs, ago)
};
ListItem::from(Line::from(vec![
Span::styled(&snap.name, Style::default().fg(name_color)),
Span::styled(format!(" {} ", indicator),
Style::default().fg(if snap.running { Color::Green } else { Color::DarkGray })),
Span::styled(detail, Style::default().fg(Color::DarkGray)),
]))
}).collect();
// Unconscious agents (graph maintenance)
@ -266,9 +290,15 @@ impl SubconsciousScreen {
} else if !snap.enabled {
"off".to_string()
} else if let Some(ref stats) = snap.last_stats {
format!("×{} {} {}msg {}tc",
let fail_str = if stats.tool_failures > 0 {
format!(" {}fail", stats.tool_failures)
} else {
String::new()
};
format!("×{} {} {}tc{} avg:{:.1}",
snap.runs, ago,
stats.messages, stats.tool_calls)
stats.tool_calls, fail_str,
snap.tool_calls_ewma)
} else {
format!("×{} {}", snap.runs, ago)
};
@ -316,6 +346,67 @@ impl SubconsciousScreen {
frame.render_stateful_widget(widget, area, &mut self.output_tree.scroll);
}
fn draw_stats(&mut self, frame: &mut Frame, area: Rect, app: &App) {
let dim = Style::default().fg(Color::DarkGray);
let header_style = Style::default().fg(Color::DarkGray);
let name_style = Style::default().fg(Color::Cyan);
let num_style = Style::default().fg(Color::Yellow);
let mut lines: Vec<Line> = Vec::new();
if let Some(stats) = self.selected_persisted_stats(app) {
if !stats.by_tool.is_empty() {
// Header
lines.push(Line::from(vec![
Span::styled(" tool ", header_style),
Span::styled("last ", header_style),
Span::styled(" avg ", header_style),
Span::styled("total", header_style),
]));
// Sort by total descending
let mut tools: Vec<_> = stats.by_tool.iter().collect();
tools.sort_by(|a, b| b.1.total.cmp(&a.1.total));
for (name, tool_stats) in tools {
let short_name = name.strip_prefix("memory_").unwrap_or(name);
lines.push(Line::from(vec![
Span::styled(format!(" {:<20} ", short_name), name_style),
Span::styled(format!("{:>4} ", tool_stats.last), num_style),
Span::styled(format!("{:>4.1} ", tool_stats.ewma), dim),
Span::styled(format!("{:>5}", tool_stats.total), num_style),
]));
}
// Failures row if any
if stats.failures.total > 0 {
lines.push(Line::raw(""));
lines.push(Line::from(vec![
Span::styled(" failures ", Style::default().fg(Color::Red)),
Span::styled(format!("{:>4} ", stats.failures.last), num_style),
Span::styled(format!("{:>4.1} ", stats.failures.ewma), dim),
Span::styled(format!("{:>5}", stats.failures.total), num_style),
]));
}
}
}
if lines.is_empty() {
lines.push(Line::styled(" (no tool calls)", dim));
}
let mut block = pane_block_focused("tool calls", self.focus == Pane::Stats);
if self.focus == Pane::Stats {
block = block.title_bottom(Line::styled(
" ↑↓:scroll PgUp/Dn ",
Style::default().fg(Color::DarkGray),
));
}
let widget = super::scroll_pane::ScrollPane::new(&lines)
.block(block);
frame.render_stateful_widget(widget, area, &mut self.stats_scroll);
}
fn draw_history(&mut self, frame: &mut Frame, area: Rect, app: &App) {
let dim = Style::default().fg(Color::DarkGray);
let key_style = Style::default().fg(Color::Yellow);