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>
This commit is contained in:
Kent Overstreet 2026-04-11 23:03:10 -04:00
parent 314ae9c4cb
commit f408bb5d86
4 changed files with 148 additions and 56 deletions

View file

@ -22,7 +22,8 @@ use super::Agent;
// Agent logging — shared by Mind and CLI paths
// ---------------------------------------------------------------------------
#[derive(Clone, Default, serde::Serialize)]
/// Stats from a single run.
#[derive(Clone, Default, serde::Serialize, serde::Deserialize)]
pub struct RunStats {
pub messages: usize,
pub tool_calls: usize,
@ -30,6 +31,57 @@ pub struct RunStats {
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 {
@ -109,13 +161,11 @@ pub struct AutoAgent {
pub current_phase: String,
pub turn: usize,
pub enabled: bool,
// Stats tracking
pub runs: usize,
pub last_stats: Option<RunStats>,
pub tool_calls_ewma: f64,
pub tool_failures_ewma: f64,
pub temperature: f32,
pub priority: i32,
}
/// Per-run conversation backend — wraps a forked agent.
struct Backend(std::sync::Arc<Agent>);
@ -178,18 +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,
runs: 0,
last_stats: None,
tool_calls_ewma: 0.0,
tool_failures_ewma: 0.0,
temperature,
priority,
}
}
@ -225,7 +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());
@ -265,14 +314,33 @@ impl AutoAgent {
}
/// Update stats after a run completes. Called with the stats from save_agent_log.
pub fn update_stats(&mut self, stats: RunStats) {
pub fn update_stats(&self, run_stats: RunStats) {
const ALPHA: f64 = 0.3;
self.runs += 1;
self.tool_calls_ewma = ALPHA * (stats.tool_calls as f64)
+ (1.0 - ALPHA) * self.tool_calls_ewma;
self.tool_failures_ewma = ALPHA * (stats.tool_failures as f64)
+ (1.0 - ALPHA) * self.tool_failures_ewma;
self.last_stats = Some(stats);
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(