tiletopia/src-tauri/src/probe.rs

//! "Is a watched process running in distro X?" probe for the idle-detection
//! filter.
//!
//! Background: tiletopia's idle indicator fires whenever a pane goes 5s
//! without PTY output. When the user is reading a long `claude` response,
//! the pane is silent but there's nothing actionable to surface — the
//! indicator becomes noise. This module lets the frontend ask the backend
//! "is `claude` (or any other watched process) running in this distro?"
//! before flagging a pane idle, and suppresses the indicator if so.
//!
//! Granularity is per-distro, not per-pane. Identifying which Windows pane
//! corresponds to which Linux-side shell inside the distro is too complex
//! (PIDs aren't visible from Windows; ProcMon-style probes are fragile). If
//! `claude` is running anywhere in distro X, idle is suppressed for ALL
//! panes in distro X. Over-suppression for multi-pane-same-distro users is
//! the agreed trade-off; the previous bug (always notify) was worse.
//!
//! PowerShell + SSH panes don't go through this probe — the frontend short-
//! circuits to "always idle" for them. (PowerShell has no portable `ps`
//! equivalent; SSH processes live on a remote box and would need a separate
//! transport.)
//!
//! The probe shells out (`wsl.exe -d <distro> -- pgrep -x ...`), which costs
//! ~100-300ms per call. We cache the answer per-distro for a few seconds so
//! the frontend can poll on every idle tick without storming `wsl.exe`.

use std::collections::HashMap;
use std::time::{Duration, Instant};

use parking_lot::Mutex;

/// Built-in list of process names that suppress idle when running. v1 ships
/// with just `claude`; the user can extend it via the workspace config later.
///
/// [[user-watch-list]] TODO: surface this as a user-editable list (workspace
/// config field or dedicated `watch.json`). For now the constant covers the
/// only real-world use case (Anthropic's `claude` CLI taking its time on a
/// long response). Adding entries to the constant is the only knob.
pub const DEFAULT_WATCH_PROCESSES: &[&str] = &["claude"];

/// How long a per-distro probe result is reused before we re-shell. Sized
/// against the frontend's 1s idle-tick interval — 3s means roughly one
/// probe per distro per 3 ticks even with many panes polling, while still
/// reacting to "claude just finished" within a few seconds. Trade-off: too
/// short = wsl.exe spam, too long = stale "claude is running" once the
/// process actually exits.
const CACHE_TTL: Duration = Duration::from_secs(3);

/// Cache entry: timestamp the probe ran + whether any watched process was
/// found in the distro.
#[derive(Clone, Copy)]
struct CacheEntry {
    at: Instant,
    running: bool,
}

/// Per-distro probe cache. Keyed by distro name (the same string the user
/// sees in the shell picker; the same string we pass as `wsl.exe -d`).
pub struct ProbeCache {
    cache: Mutex<HashMap<String, CacheEntry>>,
}

impl ProbeCache {
    pub fn new() -> Self {
        Self {
            cache: Mutex::new(HashMap::new()),
        }
    }

    /// Returns true iff one of the watched processes is running in the
    /// distro. Cached for {@link CACHE_TTL}; cache misses (or stale entries)
    /// trigger a fresh probe. On probe failure the result is `true` —
    /// **fail-safe is to suppress** the idle indicator, matching the
    /// agreed trade-off ("over-suppression beats the previous always-notify
    /// behaviour").
    pub fn is_watch_process_running(&self, distro: &str) -> bool {
        // Fast path: fresh cached answer.
        {
            let guard = self.cache.lock();
            if let Some(entry) = guard.get(distro) {
                if entry.at.elapsed() < CACHE_TTL {
                    return entry.running;
                }
            }
        }

        // Slow path: re-probe. Drop the lock before shelling out so other
        // distros' probes aren't blocked.
        let running = probe_distro(distro, DEFAULT_WATCH_PROCESSES);

        let mut guard = self.cache.lock();
        guard.insert(
            distro.to_string(),
            CacheEntry {
                at: Instant::now(),
                running,
            },
        );
        running
    }
}

impl Default for ProbeCache {
    fn default() -> Self {
        Self::new()
    }
}

/// Run `wsl.exe -d <distro> -- pgrep -x <name>` for each watched name.
/// Returns true on the first hit. On any failure (wsl.exe missing, distro
/// not running, pgrep not installed, timeout) returns true — fail-safe is
/// suppression.
fn probe_distro(distro: &str, watched: &[&str]) -> bool {
    if !cfg!(windows) {
        // Non-Windows builds don't actually ship the app; pretend no watched
        // process so the idle indicator works for developer test runs.
        return false;
    }
    if distro.is_empty() {
        // We can't probe an empty distro name; treat as "no info" → fail-safe.
        tracing::debug!("probe: empty distro name; defaulting to suppression");
        return true;
    }

    for name in watched {
        match probe_one(distro, name) {
            Ok(true) => return true,
            Ok(false) => continue,
            Err(e) => {
                tracing::debug!(
                    "probe: wsl pgrep for {name:?} in {distro:?} failed: {e} — suppressing idle"
                );
                return true;
            }
        }
    }
    false
}

/// Single `pgrep -x <name>` invocation. Ok(true) on a match, Ok(false) on
/// exit code 1 (no match), Err on anything else. Wrapped in our standard
/// `quiet_command` so the console window doesn't flash on the Windows
/// desktop every probe.
fn probe_one(distro: &str, name: &str) -> std::io::Result<bool> {
    // `pgrep -x` matches the exact comm (no substring), which avoids
    // `claude-something-else` false-positives. Stdout/stderr are silenced
    // — exit code carries the answer.
    //
    // Note: `name` is a compile-time string literal in DEFAULT_WATCH_PROCESSES
    // (no user input), so shell-quoting concerns don't apply. If we ever
    // wire user-supplied process names through here we MUST validate / shell-
    // quote them before this point.
    let out = crate::pty::quiet_command_pub("wsl.exe")
        .args(["-d", distro, "--", "pgrep", "-x", name])
        .stdout(std::process::Stdio::null())
        .stderr(std::process::Stdio::null())
        .output()?;

    match out.status.code() {
        Some(0) => Ok(true),  // pgrep found at least one match
        Some(1) => Ok(false), // pgrep ran but found nothing
        Some(other) => {
            // 2 = syntax error in pgrep itself; 3 = fatal error; 127 = command
            // not found. None of these mean "definitively no claude running",
            // so treat as a probe failure (caller fails-safe to true).
            Err(std::io::Error::other(format!(
                "pgrep exit code {other}"
            )))
        }
        None => Err(std::io::Error::other("pgrep killed by signal")),
    }
}