agent-manager/src/commands/models_cmd.rs

//! models: inventory of local model runtimes (ollama, llama.cpp, LM Studio)
//! and pruning of unused models (issues #70 #73, axe 11).

use super::*;
use crate::cli::ModelsArgs;
use crate::events::{Event, EventKind};
use crate::models::{self, RuntimeModel};
use crate::output::print_json;
use anyhow::Result;
use serde::Serialize;
use std::collections::BTreeMap;

#[derive(Serialize)]
struct ModelRow {
    runtime: String,
    name: String,
    size_bytes: Option<u64>,
    quantization: Option<String>,
    last_used: Option<String>,
}

#[derive(Serialize)]
struct RuntimeRow {
    runtime: String,
    detected: bool,
    note: Option<String>,
    models: usize,
}

pub fn run(app: &App, args: &ModelsArgs) -> Result<i32> {
    if args.prune {
        return prune(app, args);
    }
    let inventory = models::detect(app);
    if app.json() {
        print_json(&serde_json::json!({
            "runtimes": inventory.runtimes,
            "models": inventory.models,
        }));
        return Ok(0);
    }
    let theme = app.theme();
    let color = app.color();
    // Runtime status lines.
    for r in &inventory.runtimes {
        let icon = if r.detected { "✓" } else { "✗" };
        let note = r.note.as_deref().unwrap_or("");
        println!("  {icon} {} — {note}", r.runtime);
    }
    if !inventory.any_runtime() {
        app.log.info(
            "no local model runtime detected — install ollama, llama.cpp or LM Studio, or start their local API",
        );
        return Ok(0);
    }
    if inventory.models.is_empty() {
        app.log.info("runtimes detected but no models found");
        return Ok(0);
    }
    // Table: runtime | model | size | quant | last used.
    let rows: Vec<Vec<String>> = inventory
        .models
        .iter()
        .map(|m| {
            vec![
                m.runtime.clone(),
                m.name.clone(),
                human_size(m.size_bytes),
                m.quantization.clone().unwrap_or_else(|| "—".to_string()),
                m.last_used.clone().unwrap_or_else(|| "—".to_string()),
            ]
        })
        .collect();
    let _ = (theme, color);
    print!(
        "{}",
        crate::output::boxed_table(
            vec!["RUNTIME", "MODEL", "SIZE", "QUANT", "LAST USED"],
            rows,
            app.theme(),
            app.color(),
        )
    );
    println!(
        "\n  {} model(s) — 'am models --prune --dry-run' lists unused ones",
        inventory.models.len()
    );
    Ok(0)
}

/// prune: list unused models, then delete them after confirmation.
fn prune(app: &App, args: &ModelsArgs) -> Result<i32> {
    let days = args.days.unwrap_or_else(|| {
        app.config
            .settings
            .models_prune_days
            .unwrap_or(models::DEFAULT_PRUNE_DAYS)
    });
    let inventory = models::detect(app);
    let candidates = models::prune_candidates(&inventory.models, days);
    let _ = &inventory;
    if app.json() {
        let rows: Vec<ModelRow> = candidates
            .iter()
            .map(|m| ModelRow {
                runtime: m.runtime.clone(),
                name: m.name.clone(),
                size_bytes: m.size_bytes,
                quantization: m.quantization.clone(),
                last_used: m.last_used.clone(),
            })
            .collect();
        print_json(&rows);
        return Ok(if rows.is_empty() { 0 } else { 1 });
    }
    if candidates.is_empty() {
        app.log.success(&format!(
            "no unused model found (threshold: {days} days; ':latest' models are always kept)"
        ));
        return Ok(0);
    }
    println!(
        "{} model(s) unused for more than {days} days (':latest' models are protected):",
        candidates.len()
    );
    for m in &candidates {
        let size = human_size(m.size_bytes);
        let last = m.last_used.as_deref().unwrap_or("unknown");
        println!("  - [{}] {} ({size}, last used {last})", m.runtime, m.name);
    }
    if args.dry_run {
        app.log.info("dry-run: nothing was deleted — remove --dry-run to prune");
        return Ok(0);
    }
    let asked = app
        .confirm(&format!("delete these {} model(s)?", candidates.len()))?;
    if !asked {
        app.log.info("prune cancelled");
        return Ok(0);
    }
    let mut removed = 0;
    let mut errors = 0;
    for m in &candidates {
        match models::remove_model(m) {
            Ok(()) => {
                app.emit(
                    &Event::now(EventKind::Model)
                        .with_agent(m.runtime.clone())
                        .with_args(vec![m.name.clone()])
                        .with_reason("prune"),
                );
                app.log.success(&format!("removed {} ({})", m.name, m.runtime));
                removed += 1;
            }
            Err(e) => {
                app.log.error(&format!("{}: {e:#}", m.name));
                errors += 1;
            }
        }
    }
    // The inventory cache is stale after a prune: drop it so the next run
    // rescans the runtimes.
    let cache_path = app.events_dir().join("models-cache.json");
    let _ = std::fs::remove_file(&cache_path);
    if errors > 0 {
        app.log
            .error(&format!("{errors} model(s) could not be removed"));
        return Ok(1);
    }
    app.log
        .success(&format!("{removed} model(s) removed from the local runtimes"));
    Ok(0)
}

/// Human-readable size ("1.2 GB", "450 MB", "—" when unknown).
fn human_size(bytes: Option<u64>) -> String {
    match bytes {
        None => "—".to_string(),
        Some(b) => {
            let kb = b as f64 / 1024.0;
            let mb = kb / 1024.0;
            let gb = mb / 1024.0;
            if gb >= 1.0 {
                format!("{gb:.1} GB")
            } else if mb >= 1.0 {
                format!("{mb:.0} MB")
            } else {
                format!("{kb:.0} KB")
            }
        }
    }
}

/// Usage of each model name across sessions (for --json consumers).
#[allow(dead_code)]
fn usage_index(_app: &App, _models: &[RuntimeModel]) -> BTreeMap<String, u64> {
    BTreeMap::new()
}