consciousness/src/subconscious/hook.rs

// hook — session hook: context injection + agent orchestration
//
// Called on each UserPromptSubmit to inject memory context and
// orchestrate subconscious agents (surface-observe, journal, reflect).
// Lives in subconscious/ because it's agent orchestration, not
// memory storage. The memory-search binary is a thin CLI wrapper.

use std::collections::HashSet;
use std::fs;
use std::fs::File;
use std::io::Write;
use std::path::Path;
use std::process::Command;
use std::time::{Duration, Instant, SystemTime};


/// Max bytes per context chunk (hook output limit is ~10K chars)
const CHUNK_SIZE: usize = 9000;

pub use crate::session::HookSession;

/// Run the hook logic on parsed JSON input. Returns output to inject.
pub fn run_hook(input: &str) -> String {
    let Some(session) = HookSession::from_json(input) else { return String::new() };
    hook(&session)
}

/// Split context output into chunks of approximately `max_bytes`, breaking
/// at section boundaries ("--- KEY (group) ---" lines).
fn chunk_context(ctx: &str, max_bytes: usize) -> Vec<String> {
    let mut sections: Vec<String> = Vec::new();
    let mut current = String::new();

    for line in ctx.lines() {
        if line.starts_with("--- ") && line.ends_with(" ---") && !current.is_empty() {
            sections.push(std::mem::take(&mut current));
        }
        if !current.is_empty() {
            current.push('\n');
        }
        current.push_str(line);
    }
    if !current.is_empty() {
        sections.push(current);
    }

    let mut chunks: Vec<String> = Vec::new();
    let mut chunk = String::new();
    for section in sections {
        if !chunk.is_empty() && chunk.len() + section.len() + 1 > max_bytes {
            chunks.push(std::mem::take(&mut chunk));
        }
        if !chunk.is_empty() {
            chunk.push('\n');
        }
        chunk.push_str(&section);
    }
    if !chunk.is_empty() {
        chunks.push(chunk);
    }
    chunks
}

fn save_pending_chunks(dir: &Path, session_id: &str, chunks: &[String]) {
    let chunks_dir = dir.join(format!("chunks-{}", session_id));
    let _ = fs::remove_dir_all(&chunks_dir);
    if chunks.is_empty() { return; }
    fs::create_dir_all(&chunks_dir).ok();
    for (i, chunk) in chunks.iter().enumerate() {
        let path = chunks_dir.join(format!("{:04}", i));
        fs::write(path, chunk).ok();
    }
}

fn pop_pending_chunk(dir: &Path, session_id: &str) -> Option<String> {
    let chunks_dir = dir.join(format!("chunks-{}", session_id));
    if !chunks_dir.exists() { return None; }

    let mut entries: Vec<_> = fs::read_dir(&chunks_dir).ok()?
        .flatten()
        .filter(|e| e.file_type().map(|t| t.is_file()).unwrap_or(false))
        .collect();
    entries.sort_by_key(|e| e.file_name());

    let first = entries.first()?;
    let content = fs::read_to_string(first.path()).ok()?;
    fs::remove_file(first.path()).ok();

    if fs::read_dir(&chunks_dir).ok().map(|mut d| d.next().is_none()).unwrap_or(true) {
        fs::remove_dir(&chunks_dir).ok();
    }

    Some(content)
}

fn generate_cookie() -> String {
    uuid::Uuid::new_v4().as_simple().to_string()[..12].to_string()
}

fn parse_seen_line(line: &str) -> &str {
    line.split_once('\t').map(|(_, key)| key).unwrap_or(line)
}

pub fn load_seen(dir: &Path, session_id: &str) -> HashSet<String> {
    let path = dir.join(format!("seen-{}", session_id));
    if path.exists() {
        fs::read_to_string(&path)
            .unwrap_or_default()
            .lines()
            .filter(|s| !s.is_empty())
            .map(|s| parse_seen_line(s).to_string())
            .collect()
    } else {
        HashSet::new()
    }
}

fn mark_seen(dir: &Path, session_id: &str, key: &str, seen: &mut HashSet<String>) {
    if !seen.insert(key.to_string()) { return; }
    let path = dir.join(format!("seen-{}", session_id));
    if let Ok(mut f) = fs::OpenOptions::new().create(true).append(true).open(path) {
        let ts = chrono::Local::now().format("%Y-%m-%dT%H:%M:%S");
        writeln!(f, "{}\t{}", ts, key).ok();
    }
}

/// Output from a single agent orchestration cycle.
pub struct AgentCycleOutput {
    /// Memory node keys surfaced by surface-observe.
    pub surfaced_keys: Vec<String>,
    /// Freeform reflection text from the reflect agent.
    pub reflection: Option<String>,
    /// How long we slept waiting for observe to catch up, if at all.
    pub sleep_secs: Option<f64>,
}

/// Per-agent runtime state visible to the TUI.
#[derive(Clone, Debug)]
pub struct AgentInfo {
    pub name: &'static str,
    pub pid: Option<u32>,
    pub phase: Option<String>,
    /// Path to the most recent agent log file.
    pub log_path: Option<std::path::PathBuf>,
}

/// Persistent state for the agent orchestration cycle.
/// Created once, `trigger()` called on each user message.
/// TUI reads `agents` and `last_output` for display.
pub struct AgentCycleState {
    output_dir: std::path::PathBuf,
    log_file: Option<File>,
    pub agents: Vec<AgentInfo>,
    pub last_output: AgentCycleOutput,
}

const AGENT_CYCLE_NAMES: &[&str] = &["surface-observe", "journal", "reflect"];

impl AgentCycleState {
    pub fn new(session_id: &str) -> Self {
        let output_dir = crate::store::memory_dir().join("agent-output");
        let log_dir = dirs::home_dir().unwrap_or_default().join(".consciousness/logs");
        fs::create_dir_all(&log_dir).ok();
        let log_path = log_dir.join(format!("hook-{}", session_id));
        let log_file = fs::OpenOptions::new()
            .create(true).append(true).open(log_path).ok();

        let agents = AGENT_CYCLE_NAMES.iter()
            .map(|&name| AgentInfo { name, pid: None, phase: None, log_path: None })
            .collect();

        AgentCycleState {
            output_dir,
            log_file,
            agents,
            last_output: AgentCycleOutput {
                surfaced_keys: vec![],
                reflection: None,
                sleep_secs: None,
            },
        }
    }

    fn log(&mut self, msg: std::fmt::Arguments) {
        if let Some(ref mut f) = self.log_file {
            let _ = write!(f, "{}", msg);
        }
    }

    fn update_agent(&mut self, name: &str, pid: Option<u32>, phase: Option<String>,
                     log_path: Option<std::path::PathBuf>) {
        if let Some(agent) = self.agents.iter_mut().find(|a| a.name == name) {
            agent.pid = pid;
            agent.phase = phase;
            agent.log_path = log_path;
        }
    }

    /// Run all agent cycles. Call on each user message.
    pub fn trigger(&mut self, session: &HookSession) {
        let ts = chrono::Local::now().format("%Y-%m-%dT%H:%M:%S");
        self.log(format_args!("\n=== {} agent_cycles ===\n", ts));

        cleanup_stale_files(&session.state_dir, Duration::from_secs(86400));

        let (surfaced_keys, sleep_secs) = self.surface_observe_cycle(session);
        let reflection = self.reflection_cycle(session);
        self.journal_cycle(session);

        self.last_output = AgentCycleOutput { surfaced_keys, reflection, sleep_secs };
    }
}

/// Standalone entry point for the Claude Code hook path.
pub fn run_agent_cycles(session: &HookSession) -> AgentCycleOutput {
    let mut state = AgentCycleState::new(&session.session_id);
    state.trigger(session);
    state.last_output
}

/// Format agent cycle output for injection into a Claude Code session.
pub fn format_agent_output(output: &AgentCycleOutput) -> String {
    let mut out = String::new();

    if let Some(secs) = output.sleep_secs {
        out.push_str(&format!("Slept {secs:.2}s to let observe catch up\n"));
    }

    if !output.surfaced_keys.is_empty() {
        if let Ok(store) = crate::store::Store::load() {
            for key in &output.surfaced_keys {
                if let Some(rendered) = crate::cli::node::render_node(&store, key) {
                    if !rendered.trim().is_empty() {
                        use std::fmt::Write as _;
                        writeln!(out, "--- {} (surfaced) ---", key).ok();
                        write!(out, "{}", rendered).ok();
                    }
                }
            }
        }
    }

    if let Some(ref reflection) = output.reflection {
        use std::fmt::Write as _;
        writeln!(out, "--- subconscious reflection ---").ok();
        write!(out, "{}", reflection.trim()).ok();
    }

    out
}

impl AgentCycleState {
    fn agent_dir(&self, name: &str) -> std::path::PathBuf {
        let dir = self.output_dir.join(name);
        fs::create_dir_all(&dir).ok();
        dir
    }

    fn surface_observe_cycle(&mut self, session: &HookSession) -> (Vec<String>, Option<f64>) {
        let state_dir = self.agent_dir("surface-observe");
        let transcript = session.transcript();
        let offset_path = state_dir.join("transcript-offset");
        let last_offset: u64 = fs::read_to_string(&offset_path).ok()
            .and_then(|s| s.trim().parse().ok())
            .unwrap_or(0);

        let timeout = crate::config::get()
            .surface_timeout_secs
            .unwrap_or(300) as u64;

        let live = crate::agents::knowledge::scan_pid_files(&state_dir, timeout);
        for (phase, pid) in &live {
            self.log(format_args!("alive pid-{}: phase={}\n", pid, phase));
        }

        // Read surfaced keys
        let mut surfaced_keys = Vec::new();
        let surface_path = state_dir.join("surface");
        if let Ok(content) = fs::read_to_string(&surface_path) {
            let mut seen = session.seen();
            let seen_path = session.path("seen");
            for key in content.lines().map(|l| l.trim()).filter(|l| !l.is_empty()) {
                if !seen.insert(key.to_string()) {
                    self.log(format_args!("  skip (seen): {}\n", key));
                    continue;
                }
                surfaced_keys.push(key.to_string());
                if let Ok(mut f) = fs::OpenOptions::new()
                    .create(true).append(true).open(&seen_path) {
                    let ts = chrono::Local::now().format("%Y-%m-%dT%H:%M:%S");
                    writeln!(f, "{}\t{}", ts, key).ok();
                }
                self.log(format_args!("  surfaced: {}\n", key));
            }
            fs::remove_file(&surface_path).ok();
        }

        // Spawn new agent if needed
        let live = crate::agents::knowledge::scan_pid_files(&state_dir, timeout);
        let any_in_surface = live.iter().any(|(p, _)| p == "surface");

        if any_in_surface {
            self.log(format_args!("agent in surface phase, waiting\n"));
        } else {
            if transcript.size > 0 {
                fs::write(&offset_path, transcript.size.to_string()).ok();
            }
            let spawned = crate::agents::knowledge::spawn_agent(
                "surface-observe", &state_dir, &session.session_id);
            self.update_agent("surface-observe",
                spawned.as_ref().map(|s| s.pid), Some("surface".into()),
                spawned.as_ref().map(|s| s.log_path.clone()));
            self.log(format_args!("spawned agent {:?}\n", spawned.as_ref().map(|s| s.pid)));
        }

        // Wait if agent is significantly behind
        let mut sleep_secs = None;
        let conversation_budget: u64 = 50_000;

        if !live.is_empty() && transcript.size > 0 {
            let behind = transcript.size.saturating_sub(last_offset);

            if behind > conversation_budget / 2 {
                let sleep_start = Instant::now();
                self.log(format_args!("agent {}KB behind\n", behind / 1024));

                for _ in 0..5 {
                    std::thread::sleep(std::time::Duration::from_secs(1));
                    let still_live = crate::agents::knowledge::scan_pid_files(&state_dir, timeout);
                    if still_live.is_empty() { break; }
                }

                let secs = (Instant::now() - sleep_start).as_secs_f64();
                self.log(format_args!("slept {secs:.2}s\n"));
                sleep_secs = Some(secs);
            }
        }

        (surfaced_keys, sleep_secs)
    }

    fn reflection_cycle(&mut self, session: &HookSession) -> Option<String> {
        let state_dir = self.agent_dir("reflect");
        let offset_path = state_dir.join("transcript-offset");
        let transcript = session.transcript();

        let last_offset: u64 = fs::read_to_string(&offset_path).ok()
            .and_then(|s| s.trim().parse().ok())
            .unwrap_or(0);

        const REFLECTION_INTERVAL: u64 = 100_000;
        if transcript.size.saturating_sub(last_offset) < REFLECTION_INTERVAL {
            return None;
        }

        let live = crate::agents::knowledge::scan_pid_files(&state_dir, 300);
        if let Some((phase, pid)) = live.first() {
            self.log(format_args!("reflect: already running pid {}\n", pid));
            return None;
        }

        // Copy walked nodes from surface-observe
        let so_state = self.agent_dir("surface-observe");
        if let Ok(walked) = fs::read_to_string(so_state.join("walked")) {
            fs::write(state_dir.join("walked"), &walked).ok();
        }

        // Read and consume pending reflection
        let reflection = fs::read_to_string(state_dir.join("reflection")).ok()
            .filter(|s| !s.trim().is_empty());
        if reflection.is_some() {
            fs::remove_file(state_dir.join("reflection")).ok();
            self.log(format_args!("reflect: consumed reflection\n"));
        }

        fs::write(&offset_path, transcript.size.to_string()).ok();
        let spawned = crate::agents::knowledge::spawn_agent(
            "reflect", &state_dir, &session.session_id);
        self.update_agent("reflect",
            spawned.as_ref().map(|s| s.pid), Some("step-0".into()),
            spawned.as_ref().map(|s| s.log_path.clone()));
        self.log(format_args!("reflect: spawned {:?}\n", spawned.as_ref().map(|s| s.pid)));

        reflection
    }

    fn journal_cycle(&mut self, session: &HookSession) {
        let state_dir = self.agent_dir("journal");
        let offset_path = state_dir.join("transcript-offset");
        let transcript = session.transcript();

        let last_offset: u64 = fs::read_to_string(&offset_path).ok()
            .and_then(|s| s.trim().parse().ok())
            .unwrap_or(0);

        const JOURNAL_INTERVAL: u64 = 20_000;
        if transcript.size.saturating_sub(last_offset) < JOURNAL_INTERVAL {
            return;
        }

        let live = crate::agents::knowledge::scan_pid_files(&state_dir, 300);
        if let Some((phase, pid)) = live.first() {
            self.log(format_args!("journal: already running pid {}\n", pid));
            return;
        }

        fs::write(&offset_path, transcript.size.to_string()).ok();
        let spawned = crate::agents::knowledge::spawn_agent(
            "journal", &state_dir, &session.session_id);
        self.update_agent("journal",
            spawned.as_ref().map(|s| s.pid), Some("step-0".into()),
            spawned.as_ref().map(|s| s.log_path.clone()));
        self.log(format_args!("journal: spawned {:?}\n", spawned.as_ref().map(|s| s.pid)));
    }
} // end impl AgentCycleState (cycle methods)

fn cleanup_stale_files(dir: &Path, max_age: Duration) {
    let entries = match fs::read_dir(dir) {
        Ok(e) => e,
        Err(_) => return,
    };
    let cutoff = SystemTime::now() - max_age;
    for entry in entries.flatten() {
        if let Ok(meta) = entry.metadata() {
            if let Ok(modified) = meta.modified() {
                if modified < cutoff {
                    fs::remove_file(entry.path()).ok();
                }
            }
        }
    }
}

fn hook(session: &HookSession) -> String {
    let start_time = Instant::now();

    let mut out = String::new();
    let is_compaction = crate::transcript::detect_new_compaction(
        &session.state_dir, &session.session_id, &session.transcript_path,
    );
    let cookie_path = session.path("cookie");
    let is_first = !cookie_path.exists();

    let log_dir = dirs::home_dir().unwrap_or_default().join(".consciousness/logs");
    fs::create_dir_all(&log_dir).ok();
    let log_path = log_dir.join(format!("hook-{}", session.session_id));
    let Ok(mut log_f) = fs::OpenOptions::new().create(true).append(true).open(log_path) else { return Default::default(); };
    let ts = chrono::Local::now().format("%Y-%m-%dT%H:%M:%S");
    let _ = writeln!(log_f, "\n=== {} ({}) {} bytes ===", ts, session.hook_event, out.len());

    let _ = writeln!(log_f, "is_first {is_first} is_compaction {is_compaction}");

    if is_first || is_compaction {
        if is_compaction {
            fs::rename(&session.path("seen"), &session.path("seen-prev")).ok();
        } else {
            fs::remove_file(&session.path("seen")).ok();
            fs::remove_file(&session.path("seen-prev")).ok();
        }
        fs::remove_file(&session.path("returned")).ok();

        if is_first {
            fs::write(&cookie_path, generate_cookie()).ok();
        }

        if let Ok(output) = Command::new("poc-memory").args(["admin", "load-context"]).output() {
            if output.status.success() {
                let ctx = String::from_utf8_lossy(&output.stdout).to_string();
                if !ctx.trim().is_empty() {
                    let mut ctx_seen = session.seen();
                    for line in ctx.lines() {
                        if line.starts_with("--- ") && line.ends_with(" ---") {
                            let inner = &line[4..line.len() - 4];
                            if let Some(paren) = inner.rfind(" (") {
                                let key = inner[..paren].trim();
                                mark_seen(&session.state_dir, &session.session_id, key, &mut ctx_seen);
                            }
                        }
                    }

                    let chunks = chunk_context(&ctx, CHUNK_SIZE);

                    if let Some(first) = chunks.first() {
                        out.push_str(first);
                    }
                    save_pending_chunks(&session.state_dir, &session.session_id, &chunks[1..]);
                }
            }
        }
    }

    if let Some(chunk) = pop_pending_chunk(&session.state_dir, &session.session_id) {
        out.push_str(&chunk);
    } else {
        let cfg = crate::config::get();
        if cfg.surface_hooks.iter().any(|h| h == &session.hook_event) {
            let cycle_output = run_agent_cycles(&session);
            out.push_str(&format_agent_output(&cycle_output));
        }
    }

    let _ = write!(log_f, "{}", out);

    let duration = (Instant::now() - start_time).as_secs_f64();
    let _ = writeln!(log_f, "\nran in {duration:.2}s");

    out
}