//! External agent detection: PATH lookup for unmanaged agents, version
//! probing in parallel (one thread per binary), and an on-disk cache keyed
//! by the PATH string and by binary identity (path + mtime + size), so
//! repeated runs never re-scan the PATH or re-probe versions.

use crate::app::App;
use serde::{Deserialize, Serialize};
use std::collections::BTreeMap;
use std::path::{Path, PathBuf};
use wait_timeout::ChildExt;

#[derive(Debug, Default)]
pub struct ExternalInfo {
    /// agent name -> binary path (catalog agents found on PATH, unmanaged).
    pub paths: BTreeMap<String, PathBuf>,
    /// agent name -> detected version (None = unknown).
    pub versions: BTreeMap<String, Option<String>>,
}

impl ExternalInfo {
    pub fn path_of(&self, name: &str) -> Option<&PathBuf> {
        self.paths.get(name)
    }

    pub fn version_of(&self, name: &str) -> Option<&Option<String>> {
        self.versions.get(name)
    }
}

/// Detect the version of an external binary (--version), bounded by a
/// timeout so a misbehaving agent can never hang the whole listing.
pub fn detect_external_version(bin_path: &Path) -> Option<String> {
    let (prog, prefix) = crate::runner::resolve_program(&bin_path.display().to_string());
    let mut cmd = std::process::Command::new(&prog);
    cmd.args(&prefix)
        .arg("--version")
        .stdin(std::process::Stdio::null())
        .stdout(std::process::Stdio::piped())
        .stderr(std::process::Stdio::piped());
    let Ok(mut child) = cmd.spawn() else {
        return None;
    };
    let stdout_pipe = child.stdout.take();
    let stderr_pipe = child.stderr.take();

    let stdout_handle = std::thread::spawn(move || {
        let mut out = String::new();
        if let Some(mut pipe) = stdout_pipe {
            let _ = std::io::Read::read_to_string(&mut pipe, &mut out);
        }
        out
    });
    let stderr_handle = std::thread::spawn(move || {
        let mut err = String::new();
        if let Some(mut pipe) = stderr_pipe {
            let _ = std::io::Read::read_to_string(&mut pipe, &mut err);
        }
        err
    });

    const PROBE_TIMEOUT: std::time::Duration = std::time::Duration::from_secs(4);
    let status: Option<std::process::ExitStatus> = match child.wait_timeout(PROBE_TIMEOUT) {
        Ok(Some(s)) => Some(s),
        Ok(None) => {
            let _ = child.kill();
            let _ = child.wait();
            None
        }
        Err(_) => None,
    };
    let stdout = stdout_handle.join().unwrap_or_default();
    let stderr = stderr_handle.join().unwrap_or_default();

    let status = status?;
    if !status.success() {
        return None;
    }
    let combined = format!("{stdout}\n{stderr}");
    crate::version::find_version(&combined)
}

// ---------------------------------------------------------------------------
// On-disk cache
// ---------------------------------------------------------------------------

#[derive(Debug, Default, Serialize, Deserialize)]
struct ProbeCache {
    /// FNV-1a hash of the PATH string the token index was built from.
    #[serde(default)]
    path_hash: u64,
    /// FNV-1a hash of the catalog's detect tokens. When the catalog changes
    /// which binaries it probes (new agent, `detect` added), the token
    /// index must be rebuilt even if the PATH is unchanged.
    #[serde(default)]
    token_hash: u64,
    /// Catalog run-command first token -> resolved path (null = not found).
    #[serde(default)]
    tokens: BTreeMap<String, Option<String>>,
    /// Binary identity key -> detected version.
    #[serde(default)]
    versions: BTreeMap<String, Option<String>>,
}

fn path_hash() -> u64 {
    let mut h: u64 = 0xcbf2_9ce4_8422_2325;
    if let Some(p) = std::env::var_os("PATH") {
        for b in p.to_string_lossy().bytes() {
            h ^= b as u64;
            h = h.wrapping_mul(0x0000_0100_0000_01b3);
        }
    }
    h
}

/// Hash of the sorted catalog detect tokens: cache invalidation for catalog
/// changes (new agent, added `detect` field) without re-scanning the PATH.
fn catalog_token_hash(app: &App) -> u64 {
    let mut h: u64 = 0xcbf2_9ce4_8422_2325;
    let mut tokens: Vec<String> = app
        .catalog
        .agents()
        .iter()
        .filter_map(|a| a.detect_token())
        .collect();
    tokens.sort();
    for t in tokens {
        for b in t.bytes() {
            h ^= b as u64;
            h = h.wrapping_mul(0x0000_0100_0000_01b3);
        }
    }
    h
}

/// Build an index of every executable on the PATH in a single pass.
/// Much cheaper than one which() call per agent when the catalog is large.
fn build_path_index() -> BTreeMap<String, PathBuf> {
    let mut map: BTreeMap<String, PathBuf> = BTreeMap::new();
    let Some(path) = std::env::var_os("PATH") else {
        return map;
    };
    for dir in std::env::split_paths(&path) {
        let Ok(rd) = std::fs::read_dir(&dir) else {
            continue;
        };
        for entry in rd.flatten() {
            let p = entry.path();
            if !p.is_file() {
                continue;
            }
            let Some(name) = p.file_name().and_then(|n| n.to_str()) else {
                continue;
            };
            let lower = name.to_lowercase();
            #[cfg(windows)]
            {
                let stem = if lower.ends_with(".exe") {
                    lower[..lower.len() - 4].to_string()
                } else if lower.ends_with(".cmd") {
                    lower[..lower.len() - 4].to_string()
                } else if lower.ends_with(".bat") {
                    lower[..lower.len() - 4].to_string()
                } else if lower.ends_with(".com") {
                    lower[..lower.len() - 4].to_string()
                } else {
                    continue;
                };
                map.entry(stem).or_insert(p);
            }
            #[cfg(not(windows))]
            {
                use std::os::unix::fs::PermissionsExt;
                let executable = std::fs::metadata(&p)
                    .map(|m| m.permissions().mode() & 0o111 != 0)
                    .unwrap_or(false);
                if executable {
                    map.entry(lower).or_insert(p);
                }
            }
        }
    }
    map
}

/// Detect every unmanaged catalog agent present on the PATH.
///
/// The PATH is scanned once and its result cached (invalidated by the PATH
/// string hash); version probes run in parallel and are cached by binary
/// identity. A steady-state run does no PATH scanning and no subprocess.
pub fn detect_externals(app: &App) -> ExternalInfo {
    let managed: BTreeMap<String, crate::state::InstalledEntry> =
        app.state.all().unwrap_or_default();
    let cache_path = app.paths.probe_cache_file.clone();
    let mut cache: ProbeCache = std::fs::read_to_string(&cache_path)
        .ok()
        .and_then(|t| serde_json::from_str(&t).ok())
        .unwrap_or_default();
    let mut dirty = false;

    // Resolve the detect tokens of the catalog (once per PATH change or
    // catalog change).
    let current_hash = path_hash();
    let current_tokens = catalog_token_hash(app);
    if cache.path_hash != current_hash || cache.token_hash != current_tokens {
        let index = build_path_index();
        cache.tokens.clear();
        for agent in app.catalog.agents() {
            let Some(token) = agent.detect_token() else {
                continue;
            };
            if !cache.tokens.contains_key(&token) {
                let found = index
                    .get(&token.to_lowercase())
                    .map(|p| p.display().to_string());
                cache.tokens.insert(token, found);
            }
        }
        cache.path_hash = current_hash;
        cache.token_hash = current_tokens;
        dirty = true;
    }

    let mut info = ExternalInfo::default();
    // Stale cached paths (binary removed since the cache was built) force a
    // rebuild of the token index.
    let stale = cache
        .tokens
        .values()
        .flatten()
        .any(|p| !Path::new(p).exists());
    if stale {
        let index = build_path_index();
        cache.tokens.clear();
        for agent in app.catalog.agents() {
            let Some(token) = agent.detect_token() else {
                continue;
            };
            if !cache.tokens.contains_key(&token) {
                let found = index
                    .get(&token.to_lowercase())
                    .map(|p| p.display().to_string());
                cache.tokens.insert(token, found);
            }
        }
        dirty = true;
    }
    for agent in app.catalog.agents() {
        if agent.hidden || !agent.installable || managed.contains_key(&agent.name) {
            continue;
        }
        let Some(token) = agent.detect_token() else {
            continue;
        };
        if let Some(Some(path)) = cache.tokens.get(&token) {
            info.paths.insert(agent.name.clone(), PathBuf::from(path));
        }
    }

    // Versions: on-disk cache first, then parallel probes for the misses.
    let mut missing: Vec<(String, PathBuf)> = Vec::new();
    for (name, bin) in &info.paths {
        let key = bin_key(bin);
        match cache.versions.get(&key) {
            Some(v) => {
                info.versions.insert(name.clone(), v.clone());
            }
            None => missing.push((name.clone(), bin.clone())),
        }
    }
    if !missing.is_empty() {
        let results = std::sync::Mutex::new(Vec::new());
        std::thread::scope(|s| {
            for (name, bin) in &missing {
                let results = &results;
                let name = name.clone();
                let bin = bin.clone();
                s.spawn(move || {
                    let version = detect_external_version(&bin);
                    results.lock().unwrap().push((name, bin, version));
                });
            }
        });
        for (name, bin, version) in results.into_inner().unwrap_or_default() {
            let key = bin_key(&bin);
            cache.versions.insert(key.clone(), version.clone());
            info.versions.insert(name, version);
            dirty = true;
        }
    }
    // Keep the caches bounded.
    if cache.versions.len() > 500 {
        cache.versions.clear();
        dirty = true;
    }
    if dirty {
        if let Ok(text) = serde_json::to_string_pretty(&cache) {
            if let Some(parent) = cache_path.parent() {
                let _ = std::fs::create_dir_all(parent);
            }
            let _ = std::fs::write(&cache_path, text);
        }
    }
    info
}

/// Identity key for a binary: path + modification time + size, so a stale
/// cache entry is never reused after the binary changed.
fn bin_key(bin: &Path) -> String {
    let meta = std::fs::metadata(bin).ok();
    let mtime = meta
        .as_ref()
        .and_then(|m| m.modified().ok())
        .and_then(|t| t.duration_since(std::time::UNIX_EPOCH).ok())
        .map(|d| d.as_secs())
        .unwrap_or(0);
    let size = meta.map(|m| m.len()).unwrap_or(0);
    format!("{}|{mtime}|{size}", bin.display())
}

#[cfg(test)]
mod tests {
    use super::*;

    #[test]
    fn bin_key_is_stable_and_distinct() {
        let dir = tempfile::tempdir().unwrap();
        let a = dir.path().join("a.exe");
        std::fs::write(&a, b"abc").unwrap();
        let k1 = bin_key(&a);
        let k2 = bin_key(&a);
        assert_eq!(k1, k2);
        std::fs::write(&a, b"abcd").unwrap();
        let k3 = bin_key(&a);
        assert_ne!(k1, k3);
    }

    #[test]
    fn probe_cache_roundtrip() {
        let mut cache = ProbeCache::default();
        cache
            .versions
            .insert("C:/x|1|2".to_string(), Some("1.2.3".to_string()));
        cache.tokens.insert("node".to_string(), None);
        let text = serde_json::to_string(&cache).unwrap();
        let back: ProbeCache = serde_json::from_str(&text).unwrap();
        assert_eq!(
            back.versions.get("C:/x|1|2").unwrap().as_deref(),
            Some("1.2.3")
        );
        assert!(back.tokens.contains_key("node"));
    }

    #[test]
    fn old_cache_format_is_ignored() {
        // The previous cache format had only an "entries" field; loading it
        // must not fail.
        let text = r#"{ "entries": { "a": "1.0" } }"#;
        let back: ProbeCache = serde_json::from_str(text).unwrap();
        assert!(back.versions.is_empty());
        assert!(back.tokens.is_empty());
    }
}