// Append-only Cap'n Proto storage + derived KV cache
//
// Two log files are source of truth:
//   nodes.capnp     - ContentNode messages
//   relations.capnp - Relation messages
//
// The Store struct is the derived cache: latest version per UUID,
// rebuilt from logs when stale. Persisted as serde_json for now
// (state.json), will move to bincode/capnp later.

use crate::memory_capnp;
use crate::graph::{self, Graph};

use capnp::message;
use capnp::serialize;
use regex::Regex;
use serde::{Deserialize, Serialize};
use uuid::Uuid;

use std::collections::HashMap;
use std::env;
use std::fs;
use std::io::{BufReader, BufWriter, Write as IoWrite};
use std::os::unix::io::AsRawFd;
use std::path::{Path, PathBuf};
use std::process::Command;
use std::time::{SystemTime, UNIX_EPOCH};

// Data dir: ~/.claude/memory/
fn memory_dir() -> PathBuf {
    PathBuf::from(env::var("HOME").expect("HOME not set"))
        .join(".claude/memory")
}

fn nodes_path() -> PathBuf { memory_dir().join("nodes.capnp") }
fn relations_path() -> PathBuf { memory_dir().join("relations.capnp") }
fn state_path() -> PathBuf { memory_dir().join("state.json") }
fn lock_path() -> PathBuf { memory_dir().join(".store.lock") }

/// RAII file lock using flock(2). Dropped when scope exits.
struct StoreLock {
    _file: fs::File,
}

impl StoreLock {
    fn acquire() -> Result<Self, String> {
        let path = lock_path();
        let file = fs::OpenOptions::new()
            .create(true).write(true).open(&path)
            .map_err(|e| format!("open lock {}: {}", path.display(), e))?;

        // Blocking exclusive lock
        let ret = unsafe { libc::flock(file.as_raw_fd(), libc::LOCK_EX) };
        if ret != 0 {
            return Err(format!("flock: {}", std::io::Error::last_os_error()));
        }
        Ok(StoreLock { _file: file })
    }
    // Lock released automatically when _file is dropped (flock semantics)
}

fn now_epoch() -> f64 {
    SystemTime::now()
        .duration_since(UNIX_EPOCH)
        .unwrap()
        .as_secs_f64()
}

fn today() -> String {
    let out = Command::new("date").arg("+%Y-%m-%d")
        .output().expect("date command failed");
    String::from_utf8_lossy(&out.stdout).trim().to_string()
}

// In-memory node representation
#[derive(Clone, Debug, Serialize, Deserialize)]
pub struct Node {
    pub uuid: [u8; 16],
    pub version: u32,
    pub timestamp: f64,
    pub node_type: NodeType,
    pub provenance: Provenance,
    pub key: String,
    pub content: String,
    pub weight: f32,
    pub category: Category,
    pub emotion: f32,
    pub deleted: bool,
    pub source_ref: String,
    pub created: String,
    pub retrievals: u32,
    pub uses: u32,
    pub wrongs: u32,
    pub state_tag: String,
    pub last_replayed: f64,
    pub spaced_repetition_interval: u32,

    // Derived fields (not in capnp, computed from graph)
    #[serde(default)]
    pub community_id: Option<u32>,
    #[serde(default)]
    pub clustering_coefficient: Option<f32>,
    #[serde(default)]
    pub schema_fit: Option<f32>,
    #[serde(default)]
    pub degree: Option<u32>,
}

#[derive(Clone, Debug, Serialize, Deserialize)]
pub struct Relation {
    pub uuid: [u8; 16],
    pub version: u32,
    pub timestamp: f64,
    pub source: [u8; 16],
    pub target: [u8; 16],
    pub rel_type: RelationType,
    pub strength: f32,
    pub provenance: Provenance,
    pub deleted: bool,
    pub source_key: String,
    pub target_key: String,
}

#[derive(Clone, Copy, Debug, PartialEq, Serialize, Deserialize)]
pub enum NodeType {
    EpisodicSession,
    EpisodicDaily,
    EpisodicWeekly,
    Semantic,
}

#[derive(Clone, Copy, Debug, PartialEq, Serialize, Deserialize)]
pub enum Provenance {
    Manual,
    Journal,
    Agent,
    Dream,
    Derived,
}

#[derive(Clone, Copy, Debug, PartialEq, Eq, Hash, Serialize, Deserialize)]
pub enum Category {
    General,
    Core,
    Technical,
    Observation,
    Task,
}

impl Category {
    pub fn decay_factor(&self, base: f64) -> f64 {
        match self {
            Category::Core        => 1.0 - (1.0 - base) * 0.2,
            Category::Technical   => 1.0 - (1.0 - base) * 0.5,
            Category::General     => base,
            Category::Observation => 1.0 - (1.0 - base) * 1.5,
            Category::Task        => 1.0 - (1.0 - base) * 2.5,
        }
    }

    pub fn label(&self) -> &str {
        match self {
            Category::Core => "core",
            Category::Technical => "tech",
            Category::General => "gen",
            Category::Observation => "obs",
            Category::Task => "task",
        }
    }

    pub fn from_str(s: &str) -> Option<Self> {
        match s {
            "core" => Some(Category::Core),
            "tech" | "technical" => Some(Category::Technical),
            "gen" | "general" => Some(Category::General),
            "obs" | "observation" => Some(Category::Observation),
            "task" => Some(Category::Task),
            _ => None,
        }
    }
}

#[derive(Clone, Copy, Debug, PartialEq, Serialize, Deserialize)]
pub enum RelationType {
    Link,
    Causal,
    Auto,
}

#[derive(Clone, Debug, Serialize, Deserialize)]
pub struct RetrievalEvent {
    pub query: String,
    pub timestamp: String,
    pub results: Vec<String>,
    pub used: Option<Vec<String>>,
}

#[derive(Clone, Debug, Serialize, Deserialize)]
pub struct Params {
    pub default_weight: f64,
    pub decay_factor: f64,
    pub use_boost: f64,
    pub prune_threshold: f64,
    pub edge_decay: f64,
    pub max_hops: u32,
    pub min_activation: f64,
}

impl Default for Params {
    fn default() -> Self {
        Params {
            default_weight: 0.7,
            decay_factor: 0.95,
            use_boost: 0.15,
            prune_threshold: 0.1,
            edge_decay: 0.3,
            max_hops: 3,
            min_activation: 0.05,
        }
    }
}

// Gap record — something we looked for but didn't find
#[derive(Clone, Debug, Serialize, Deserialize)]
pub struct GapRecord {
    pub description: String,
    pub timestamp: String,
}

// The full in-memory store
#[derive(Serialize, Deserialize)]
pub struct Store {
    pub nodes: HashMap<String, Node>,          // key → latest node
    #[serde(skip)]
    pub uuid_to_key: HashMap<[u8; 16], String>, // uuid → key (rebuilt from nodes)
    pub relations: Vec<Relation>,              // all active relations
    pub retrieval_log: Vec<RetrievalEvent>,
    pub gaps: Vec<GapRecord>,
    pub params: Params,
}

impl Default for Store {
    fn default() -> Self {
        Store {
            nodes: HashMap::new(),
            uuid_to_key: HashMap::new(),
            relations: Vec::new(),
            retrieval_log: Vec::new(),
            gaps: Vec::new(),
            params: Params::default(),
        }
    }
}

impl Store {
    /// Load store: try state.json cache first, rebuild from capnp logs if stale
    pub fn load() -> Result<Store, String> {
        let state = state_path();
        let nodes_p = nodes_path();
        let rels_p = relations_path();

        // Check if cache is up to date
        let cache_fresh = state.exists() && {
            let cache_mtime = fs::metadata(&state).ok()
                .and_then(|m| m.modified().ok())
                .unwrap_or(UNIX_EPOCH);
            let nodes_mtime = fs::metadata(&nodes_p).ok()
                .and_then(|m| m.modified().ok())
                .unwrap_or(UNIX_EPOCH);
            let rels_mtime = fs::metadata(&rels_p).ok()
                .and_then(|m| m.modified().ok())
                .unwrap_or(UNIX_EPOCH);
            cache_mtime >= nodes_mtime && cache_mtime >= rels_mtime
        };

        if cache_fresh {
            let data = fs::read_to_string(&state)
                .map_err(|e| format!("read state.json: {}", e))?;
            let mut store: Store = serde_json::from_str(&data)
                .map_err(|e| format!("parse state.json: {}", e))?;
            store.rebuild_uuid_index();
            return Ok(store);
        }

        // Rebuild from capnp logs
        let mut store = Store::default();

        if nodes_p.exists() {
            store.replay_nodes(&nodes_p)?;
        }
        if rels_p.exists() {
            store.replay_relations(&rels_p)?;
        }

        // Save cache
        store.save()?;
        Ok(store)
    }

    /// Replay node log, keeping latest version per UUID
    fn replay_nodes(&mut self, path: &Path) -> Result<(), String> {
        let file = fs::File::open(path)
            .map_err(|e| format!("open {}: {}", path.display(), e))?;
        let mut reader = BufReader::new(file);

        while let Ok(msg) = serialize::read_message(&mut reader, message::ReaderOptions::new()) {
            let log = msg.get_root::<memory_capnp::node_log::Reader>()
                .map_err(|e| format!("read node log: {}", e))?;
            for node_reader in log.get_nodes()
                .map_err(|e| format!("get nodes: {}", e))? {
                let node = read_content_node(node_reader)?;
                let existing_version = self.nodes.get(&node.key)
                    .map(|n| n.version)
                    .unwrap_or(0);
                if node.version >= existing_version {
                    if node.deleted {
                        self.nodes.remove(&node.key);
                        self.uuid_to_key.remove(&node.uuid);
                    } else {
                        self.uuid_to_key.insert(node.uuid, node.key.clone());
                        self.nodes.insert(node.key.clone(), node);
                    }
                }
            }
        }
        Ok(())
    }

    /// Replay relation log, keeping latest version per UUID
    fn replay_relations(&mut self, path: &Path) -> Result<(), String> {
        let file = fs::File::open(path)
            .map_err(|e| format!("open {}: {}", path.display(), e))?;
        let mut reader = BufReader::new(file);

        // Collect all, then deduplicate by UUID keeping latest version
        let mut by_uuid: HashMap<[u8; 16], Relation> = HashMap::new();

        while let Ok(msg) = serialize::read_message(&mut reader, message::ReaderOptions::new()) {
            let log = msg.get_root::<memory_capnp::relation_log::Reader>()
                .map_err(|e| format!("read relation log: {}", e))?;
            for rel_reader in log.get_relations()
                .map_err(|e| format!("get relations: {}", e))? {
                let rel = read_relation(rel_reader)?;
                let existing_version = by_uuid.get(&rel.uuid)
                    .map(|r| r.version)
                    .unwrap_or(0);
                if rel.version >= existing_version {
                    by_uuid.insert(rel.uuid, rel);
                }
            }
        }

        self.relations = by_uuid.into_values()
            .filter(|r| !r.deleted)
            .collect();
        Ok(())
    }

    /// Append nodes to the log file
    pub fn append_nodes(&self, nodes: &[Node]) -> Result<(), String> {
        let _lock = StoreLock::acquire()?;

        let path = nodes_path();
        let file = fs::OpenOptions::new()
            .create(true).append(true).open(&path)
            .map_err(|e| format!("open {}: {}", path.display(), e))?;
        let mut writer = BufWriter::new(file);

        let mut msg = message::Builder::new_default();
        {
            let log = msg.init_root::<memory_capnp::node_log::Builder>();
            let mut list = log.init_nodes(nodes.len() as u32);
            for (i, node) in nodes.iter().enumerate() {
                write_content_node(list.reborrow().get(i as u32), node);
            }
        }
        serialize::write_message(&mut writer, &msg)
            .map_err(|e| format!("write nodes: {}", e))?;
        writer.flush().map_err(|e| format!("flush: {}", e))?;
        Ok(())
    }

    /// Append relations to the log file
    pub fn append_relations(&self, relations: &[Relation]) -> Result<(), String> {
        let _lock = StoreLock::acquire()?;

        let path = relations_path();
        let file = fs::OpenOptions::new()
            .create(true).append(true).open(&path)
            .map_err(|e| format!("open {}: {}", path.display(), e))?;
        let mut writer = BufWriter::new(file);

        let mut msg = message::Builder::new_default();
        {
            let log = msg.init_root::<memory_capnp::relation_log::Builder>();
            let mut list = log.init_relations(relations.len() as u32);
            for (i, rel) in relations.iter().enumerate() {
                write_relation(list.reborrow().get(i as u32), rel);
            }
        }
        serialize::write_message(&mut writer, &msg)
            .map_err(|e| format!("write relations: {}", e))?;
        writer.flush().map_err(|e| format!("flush: {}", e))?;
        Ok(())
    }

    /// Save the derived cache (state.json)
    pub fn save(&self) -> Result<(), String> {
        let _lock = StoreLock::acquire()?;

        let path = state_path();
        if let Some(parent) = path.parent() {
            fs::create_dir_all(parent).ok();
        }
        let json = serde_json::to_string(self)
            .map_err(|e| format!("serialize: {}", e))?;
        fs::write(&path, json)
            .map_err(|e| format!("write {}: {}", path.display(), e))?;
        Ok(())
    }

    /// Add or update a node (appends to log + updates cache)
    pub fn upsert_node(&mut self, mut node: Node) -> Result<(), String> {
        if let Some(existing) = self.nodes.get(&node.key) {
            node.uuid = existing.uuid;
            node.version = existing.version + 1;
        }
        self.append_nodes(&[node.clone()])?;
        self.uuid_to_key.insert(node.uuid, node.key.clone());
        self.nodes.insert(node.key.clone(), node);
        Ok(())
    }

    /// Add a relation (appends to log + updates cache)
    pub fn add_relation(&mut self, rel: Relation) -> Result<(), String> {
        self.append_relations(&[rel.clone()])?;
        self.relations.push(rel);
        Ok(())
    }

    /// Create a new node with defaults
    pub fn new_node(key: &str, content: &str) -> Node {
        Node {
            uuid: *Uuid::new_v4().as_bytes(),
            version: 1,
            timestamp: now_epoch(),
            node_type: NodeType::Semantic,
            provenance: Provenance::Manual,
            key: key.to_string(),
            content: content.to_string(),
            weight: 0.7,
            category: Category::General,
            emotion: 0.0,
            deleted: false,
            source_ref: String::new(),
            created: today(),
            retrievals: 0,
            uses: 0,
            wrongs: 0,
            state_tag: String::new(),
            last_replayed: 0.0,
            spaced_repetition_interval: 1,
            community_id: None,
            clustering_coefficient: None,
            schema_fit: None,
            degree: None,
        }
    }

    /// Create a new relation
    pub fn new_relation(
        source_uuid: [u8; 16],
        target_uuid: [u8; 16],
        rel_type: RelationType,
        strength: f32,
        source_key: &str,
        target_key: &str,
    ) -> Relation {
        Relation {
            uuid: *Uuid::new_v4().as_bytes(),
            version: 1,
            timestamp: now_epoch(),
            source: source_uuid,
            target: target_uuid,
            rel_type,
            strength,
            provenance: Provenance::Manual,
            deleted: false,
            source_key: source_key.to_string(),
            target_key: target_key.to_string(),
        }
    }

    /// Scan markdown files and index all memory units
    pub fn init_from_markdown(&mut self) -> Result<usize, String> {
        let dir = memory_dir();
        let mut count = 0;
        if dir.exists() {
            count = self.scan_dir_for_init(&dir)?;
        }
        Ok(count)
    }

    fn scan_dir_for_init(&mut self, dir: &Path) -> Result<usize, String> {
        let mut count = 0;
        let entries = fs::read_dir(dir)
            .map_err(|e| format!("read dir {}: {}", dir.display(), e))?;

        for entry in entries.flatten() {
            let path = entry.path();
            if path.is_dir() {
                count += self.scan_dir_for_init(&path)?;
                continue;
            }
            let Some(ext) = path.extension() else { continue };
            if ext != "md" { continue }

            let filename = path.file_name().unwrap().to_string_lossy().to_string();
            let content = fs::read_to_string(&path)
                .map_err(|e| format!("read {}: {}", path.display(), e))?;

            let units = parse_units(&filename, &content);
            let mut new_nodes = Vec::new();
            let mut new_relations = Vec::new();

            // Determine node type from filename
            let node_type = if filename.starts_with("daily-") {
                NodeType::EpisodicDaily
            } else if filename.starts_with("weekly-") {
                NodeType::EpisodicWeekly
            } else if filename == "journal.md" {
                NodeType::EpisodicSession
            } else {
                NodeType::Semantic
            };

            for unit in &units {
                if !self.nodes.contains_key(&unit.key) {
                    let mut node = Store::new_node(&unit.key, &unit.content);
                    node.node_type = node_type;
                    if let Some(ref state) = unit.state {
                        node.state_tag = state.clone();
                    }
                    if let Some(ref src) = unit.source_ref {
                        node.source_ref = src.clone();
                    }
                    new_nodes.push(node);
                }
            }

            // Batch append new nodes
            if !new_nodes.is_empty() {
                self.append_nodes(&new_nodes)?;
                for node in &new_nodes {
                    self.uuid_to_key.insert(node.uuid, node.key.clone());
                    self.nodes.insert(node.key.clone(), node.clone());
                }
                count += new_nodes.len();
            }

            // Create relations from links
            for unit in &units {
                let source_uuid = match self.nodes.get(&unit.key) {
                    Some(n) => n.uuid,
                    None => continue,
                };

                for link in unit.marker_links.iter().chain(unit.md_links.iter()) {
                    let target_uuid = match self.nodes.get(link) {
                        Some(n) => n.uuid,
                        None => continue,
                    };
                    // Check if relation already exists
                    let exists = self.relations.iter().any(|r|
                        (r.source == source_uuid && r.target == target_uuid) ||
                        (r.source == target_uuid && r.target == source_uuid));
                    if !exists {
                        let rel = Store::new_relation(
                            source_uuid, target_uuid,
                            RelationType::Link, 1.0,
                            &unit.key, link,
                        );
                        new_relations.push(rel);
                    }
                }

                for cause in &unit.causes {
                    let target_uuid = match self.nodes.get(cause) {
                        Some(n) => n.uuid,
                        None => continue,
                    };
                    let exists = self.relations.iter().any(|r|
                        r.source == target_uuid && r.target == source_uuid
                        && r.rel_type == RelationType::Causal);
                    if !exists {
                        let rel = Store::new_relation(
                            target_uuid, source_uuid,
                            RelationType::Causal, 1.0,
                            cause, &unit.key,
                        );
                        new_relations.push(rel);
                    }
                }
            }

            if !new_relations.is_empty() {
                self.append_relations(&new_relations)?;
                self.relations.extend(new_relations);
            }
        }
        Ok(count)
    }

    fn rebuild_uuid_index(&mut self) {
        self.uuid_to_key.clear();
        for (key, node) in &self.nodes {
            self.uuid_to_key.insert(node.uuid, key.clone());
        }
    }

    pub fn build_graph(&self) -> Graph {
        graph::build_graph(self)
    }

    pub fn node_weight(&self, key: &str) -> Option<f32> {
        self.nodes.get(key).map(|n| n.weight)
    }

    pub fn node_community(&self, key: &str) -> Option<u32> {
        self.nodes.get(key).and_then(|n| n.community_id)
    }

    pub fn resolve_key(&self, target: &str) -> Result<String, String> {
        let normalized = if target.contains('#') {
            let parts: Vec<&str> = target.splitn(2, '#').collect();
            let file = if parts[0].ends_with(".md") {
                parts[0].to_string()
            } else {
                format!("{}.md", parts[0])
            };
            format!("{}#{}", file, parts[1])
        } else if target.ends_with(".md") {
            target.to_string()
        } else {
            format!("{}.md", target)
        };

        if self.nodes.contains_key(&normalized) {
            return Ok(normalized);
        }

        let matches: Vec<_> = self.nodes.keys()
            .filter(|k| k.to_lowercase().contains(&target.to_lowercase()))
            .cloned().collect();

        match matches.len() {
            0 => Err(format!("No entry for '{}'. Run 'init'?", target)),
            1 => Ok(matches[0].clone()),
            n if n <= 10 => {
                let list = matches.join("\n  ");
                Err(format!("Ambiguous '{}'. Matches:\n  {}", target, list))
            }
            n => Err(format!("Too many matches for '{}' ({}). Be more specific.", target, n)),
        }
    }

    pub fn log_retrieval(&mut self, query: &str, results: &[String]) {
        self.retrieval_log.push(RetrievalEvent {
            query: query.to_string(),
            timestamp: today(),
            results: results.to_vec(),
            used: None,
        });
        // Keep last 100
        if self.retrieval_log.len() > 100 {
            let start = self.retrieval_log.len() - 100;
            self.retrieval_log = self.retrieval_log[start..].to_vec();
        }
    }

    pub fn mark_used(&mut self, key: &str) {
        if let Some(node) = self.nodes.get_mut(key) {
            node.uses += 1;
            node.weight = (node.weight + self.params.use_boost as f32).min(1.0);
            // Reset spaced repetition — used successfully, move up interval
            if node.spaced_repetition_interval < 30 {
                node.spaced_repetition_interval = match node.spaced_repetition_interval {
                    1 => 3, 3 => 7, 7 => 14, 14 => 30, _ => 30,
                };
            }
            node.last_replayed = now_epoch();
        }
    }

    pub fn mark_wrong(&mut self, key: &str, _ctx: Option<&str>) {
        if let Some(node) = self.nodes.get_mut(key) {
            node.wrongs += 1;
            node.weight = (node.weight - 0.1).max(0.0);
            // Reset spaced repetition interval — needs review
            node.spaced_repetition_interval = 1;
        }
    }

    pub fn record_gap(&mut self, desc: &str) {
        self.gaps.push(GapRecord {
            description: desc.to_string(),
            timestamp: today(),
        });
    }

    pub fn categorize(&mut self, key: &str, cat_str: &str) -> Result<(), String> {
        let cat = Category::from_str(cat_str)
            .ok_or_else(|| format!("Unknown category '{}'. Use: core/tech/gen/obs/task", cat_str))?;
        if let Some(node) = self.nodes.get_mut(key) {
            node.category = cat;
            Ok(())
        } else {
            Err(format!("No node '{}'", key))
        }
    }

    pub fn decay(&mut self) -> (usize, usize) {
        let base = self.params.decay_factor;
        let threshold = self.params.prune_threshold as f32;
        let mut decayed = 0;
        let mut pruned = 0;
        let mut to_remove = Vec::new();

        for (key, node) in &mut self.nodes {
            let factor = node.category.decay_factor(base) as f32;
            node.weight *= factor;
            decayed += 1;
            if node.weight < threshold {
                to_remove.push(key.clone());
                pruned += 1;
            }
        }

        // Don't actually remove — just mark very low weight
        // Actual pruning happens during GC
        for key in &to_remove {
            if let Some(node) = self.nodes.get_mut(key) {
                node.weight = node.weight.max(0.01);
            }
        }

        (decayed, pruned)
    }

    pub fn category_counts(&self) -> HashMap<&str, usize> {
        let mut counts = HashMap::new();
        for node in self.nodes.values() {
            *counts.entry(node.category.label()).or_insert(0) += 1;
        }
        counts
    }

    /// Update graph-derived fields on all nodes
    pub fn update_graph_metrics(&mut self) {
        let g = self.build_graph();
        let communities = g.communities();
        let fits = graph::schema_fit_all(&g);

        for (key, node) in &mut self.nodes {
            node.community_id = communities.get(key).copied();
            node.clustering_coefficient = Some(g.clustering_coefficient(key));
            node.degree = Some(g.degree(key) as u32);
            node.schema_fit = fits.get(key).copied();
        }
    }
}

// Markdown parsing — same as old system but returns structured units

pub struct MemoryUnit {
    pub key: String,
    pub content: String,
    pub marker_links: Vec<String>,
    pub md_links: Vec<String>,
    pub causes: Vec<String>,
    pub state: Option<String>,
    pub source_ref: Option<String>,
}

pub fn parse_units(filename: &str, content: &str) -> Vec<MemoryUnit> {
    let marker_re = Regex::new(
        r"<!--\s*mem:\s*((?:id|links|tags|causes|state)\s*=\s*[^\s].*?)-->"
    ).unwrap();
    let source_re = Regex::new(r"<!--\s*source:\s*(.+?)\s*-->").unwrap();
    let md_link_re = Regex::new(r"\[[^\]]*\]\(([^)]*\.md(?:#[^)]*)?)\)").unwrap();

    let markers: Vec<_> = marker_re.captures_iter(content)
        .map(|cap| {
            let full_match = cap.get(0).unwrap();
            let attrs_str = &cap[1];
            (full_match.start(), full_match.end(), parse_marker_attrs(attrs_str))
        })
        .collect();

    // Helper: extract source ref from a content block
    let find_source = |text: &str| -> Option<String> {
        source_re.captures(text).map(|c| c[1].trim().to_string())
    };

    if markers.is_empty() {
        let source_ref = find_source(content);
        let md_links = extract_md_links(content, &md_link_re, filename);
        return vec![MemoryUnit {
            key: filename.to_string(),
            content: content.to_string(),
            marker_links: Vec::new(),
            md_links,
            causes: Vec::new(),
            state: None,
            source_ref,
        }];
    }

    let mut units = Vec::new();

    let first_start = markers[0].0;
    let pre_content = content[..first_start].trim();
    if !pre_content.is_empty() {
        let source_ref = find_source(pre_content);
        let md_links = extract_md_links(pre_content, &md_link_re, filename);
        units.push(MemoryUnit {
            key: filename.to_string(),
            content: pre_content.to_string(),
            marker_links: Vec::new(),
            md_links,
            causes: Vec::new(),
            state: None,
            source_ref,
        });
    }

    for (i, (_, end, attrs)) in markers.iter().enumerate() {
        let unit_end = if i + 1 < markers.len() {
            markers[i + 1].0
        } else {
            content.len()
        };
        let unit_content = content[*end..unit_end].trim();

        let id = attrs.get("id").cloned().unwrap_or_default();
        let key = if id.is_empty() {
            format!("{}#unnamed-{}", filename, i)
        } else {
            format!("{}#{}", filename, id)
        };

        let marker_links = attrs.get("links")
            .map(|l| l.split(',').map(|s| normalize_link(s.trim(), filename)).collect())
            .unwrap_or_default();

        let causes = attrs.get("causes")
            .map(|l| l.split(',').map(|s| normalize_link(s.trim(), filename)).collect())
            .unwrap_or_default();

        let state = attrs.get("state").cloned();
        let source_ref = find_source(unit_content);
        let md_links = extract_md_links(unit_content, &md_link_re, filename);

        units.push(MemoryUnit {
            key,
            content: unit_content.to_string(),
            marker_links,
            md_links,
            causes,
            state,
            source_ref,
        });
    }

    units
}

fn parse_marker_attrs(attrs_str: &str) -> HashMap<String, String> {
    let attr_re = Regex::new(r"(\w+)\s*=\s*(\S+)").unwrap();
    let mut attrs = HashMap::new();
    for cap in attr_re.captures_iter(attrs_str) {
        attrs.insert(cap[1].to_string(), cap[2].to_string());
    }
    attrs
}

fn extract_md_links(content: &str, re: &Regex, source_file: &str) -> Vec<String> {
    re.captures_iter(content)
        .map(|cap| normalize_link(&cap[1], source_file))
        .filter(|link| !link.starts_with(source_file) || link.contains('#'))
        .collect()
}

pub fn normalize_link(target: &str, source_file: &str) -> String {
    if target.starts_with('#') {
        return format!("{}{}", source_file, target);
    }

    let (path_part, fragment) = if let Some(hash_pos) = target.find('#') {
        (&target[..hash_pos], Some(&target[hash_pos..]))
    } else {
        (target, None)
    };

    let basename = Path::new(path_part)
        .file_name()
        .map(|f| f.to_string_lossy().to_string())
        .unwrap_or_else(|| path_part.to_string());

    match fragment {
        Some(frag) => format!("{}{}", basename, frag),
        None => basename,
    }
}

// Cap'n Proto serialization helpers

/// Read a capnp text field, returning empty string on any error
fn read_text(result: capnp::Result<capnp::text::Reader>) -> String {
    result.ok()
        .and_then(|t| t.to_str().ok())
        .unwrap_or("")
        .to_string()
}

/// Read a capnp data field as [u8; 16], zero-padded
fn read_uuid(result: capnp::Result<&[u8]>) -> [u8; 16] {
    let mut out = [0u8; 16];
    if let Ok(data) = result {
        if data.len() >= 16 {
            out.copy_from_slice(&data[..16]);
        }
    }
    out
}

fn read_content_node(r: memory_capnp::content_node::Reader) -> Result<Node, String> {
    Ok(Node {
        uuid: read_uuid(r.get_uuid()),
        version: r.get_version(),
        timestamp: r.get_timestamp(),
        node_type: match r.get_node_type().map_err(|_| "bad node_type")? {
            memory_capnp::NodeType::EpisodicSession => NodeType::EpisodicSession,
            memory_capnp::NodeType::EpisodicDaily => NodeType::EpisodicDaily,
            memory_capnp::NodeType::EpisodicWeekly => NodeType::EpisodicWeekly,
            memory_capnp::NodeType::Semantic => NodeType::Semantic,
        },
        provenance: read_provenance(r.get_provenance().map_err(|_| "bad provenance")?)?,
        key: read_text(r.get_key()),
        content: read_text(r.get_content()),
        weight: r.get_weight(),
        category: match r.get_category().map_err(|_| "bad category")? {
            memory_capnp::Category::General => Category::General,
            memory_capnp::Category::Core => Category::Core,
            memory_capnp::Category::Technical => Category::Technical,
            memory_capnp::Category::Observation => Category::Observation,
            memory_capnp::Category::Task => Category::Task,
        },
        emotion: r.get_emotion(),
        deleted: r.get_deleted(),
        source_ref: read_text(r.get_source_ref()),
        created: read_text(r.get_created()),
        retrievals: r.get_retrievals(),
        uses: r.get_uses(),
        wrongs: r.get_wrongs(),
        state_tag: read_text(r.get_state_tag()),
        last_replayed: r.get_last_replayed(),
        spaced_repetition_interval: r.get_spaced_repetition_interval(),
        community_id: None,
        clustering_coefficient: None,
        schema_fit: None,
        degree: None,
    })
}

fn read_provenance(p: memory_capnp::Provenance) -> Result<Provenance, String> {
    Ok(match p {
        memory_capnp::Provenance::Manual => Provenance::Manual,
        memory_capnp::Provenance::Journal => Provenance::Journal,
        memory_capnp::Provenance::Agent => Provenance::Agent,
        memory_capnp::Provenance::Dream => Provenance::Dream,
        memory_capnp::Provenance::Derived => Provenance::Derived,
    })
}

fn write_content_node(mut b: memory_capnp::content_node::Builder, node: &Node) {
    b.set_uuid(&node.uuid);
    b.set_version(node.version);
    b.set_timestamp(node.timestamp);
    b.set_node_type(match node.node_type {
        NodeType::EpisodicSession => memory_capnp::NodeType::EpisodicSession,
        NodeType::EpisodicDaily => memory_capnp::NodeType::EpisodicDaily,
        NodeType::EpisodicWeekly => memory_capnp::NodeType::EpisodicWeekly,
        NodeType::Semantic => memory_capnp::NodeType::Semantic,
    });
    b.set_provenance(match node.provenance {
        Provenance::Manual => memory_capnp::Provenance::Manual,
        Provenance::Journal => memory_capnp::Provenance::Journal,
        Provenance::Agent => memory_capnp::Provenance::Agent,
        Provenance::Dream => memory_capnp::Provenance::Dream,
        Provenance::Derived => memory_capnp::Provenance::Derived,
    });
    b.set_key(&node.key);
    b.set_content(&node.content);
    b.set_weight(node.weight);
    b.set_category(match node.category {
        Category::General => memory_capnp::Category::General,
        Category::Core => memory_capnp::Category::Core,
        Category::Technical => memory_capnp::Category::Technical,
        Category::Observation => memory_capnp::Category::Observation,
        Category::Task => memory_capnp::Category::Task,
    });
    b.set_emotion(node.emotion);
    b.set_deleted(node.deleted);
    b.set_source_ref(&node.source_ref);
    b.set_created(&node.created);
    b.set_retrievals(node.retrievals);
    b.set_uses(node.uses);
    b.set_wrongs(node.wrongs);
    b.set_state_tag(&node.state_tag);
    b.set_last_replayed(node.last_replayed);
    b.set_spaced_repetition_interval(node.spaced_repetition_interval);
}

fn read_relation(r: memory_capnp::relation::Reader) -> Result<Relation, String> {
    Ok(Relation {
        uuid: read_uuid(r.get_uuid()),
        version: r.get_version(),
        timestamp: r.get_timestamp(),
        source: read_uuid(r.get_source()),
        target: read_uuid(r.get_target()),
        rel_type: match r.get_rel_type().map_err(|_| "bad rel_type")? {
            memory_capnp::RelationType::Link => RelationType::Link,
            memory_capnp::RelationType::Causal => RelationType::Causal,
            memory_capnp::RelationType::Auto => RelationType::Auto,
        },
        strength: r.get_strength(),
        provenance: read_provenance(r.get_provenance().map_err(|_| "bad provenance")?)?,
        deleted: r.get_deleted(),
        source_key: read_text(r.get_source_key()),
        target_key: read_text(r.get_target_key()),
    })
}

fn write_relation(mut b: memory_capnp::relation::Builder, rel: &Relation) {
    b.set_uuid(&rel.uuid);
    b.set_version(rel.version);
    b.set_timestamp(rel.timestamp);
    b.set_source(&rel.source);
    b.set_target(&rel.target);
    b.set_rel_type(match rel.rel_type {
        RelationType::Link => memory_capnp::RelationType::Link,
        RelationType::Causal => memory_capnp::RelationType::Causal,
        RelationType::Auto => memory_capnp::RelationType::Auto,
    });
    b.set_strength(rel.strength);
    b.set_provenance(match rel.provenance {
        Provenance::Manual => memory_capnp::Provenance::Manual,
        Provenance::Journal => memory_capnp::Provenance::Journal,
        Provenance::Agent => memory_capnp::Provenance::Agent,
        Provenance::Dream => memory_capnp::Provenance::Dream,
        Provenance::Derived => memory_capnp::Provenance::Derived,
    });
    b.set_deleted(rel.deleted);
    b.set_source_key(&rel.source_key);
    b.set_target_key(&rel.target_key);
}