consciousness/src/search.rs

// Spreading activation search across the memory graph
//
// Same model as the old system but richer: uses graph edge strengths,
// supports circumscription parameter for blending associative vs
// causal walks, and benefits from community-aware result grouping.

use crate::capnp_store::StoreView;
use crate::graph::Graph;

use std::cmp::Ordering;
use std::collections::{HashMap, HashSet, VecDeque};

pub struct SearchResult {
    pub key: String,
    pub activation: f64,
    pub is_direct: bool,
    pub snippet: Option<String>,
}

/// Spreading activation with circumscription parameter.
///
/// circ = 0.0: field mode — all edges (default, broad resonance)
/// circ = 1.0: causal mode — prefer causal edges
fn spreading_activation(
    seeds: &[(String, f64)],
    graph: &Graph,
    store: &impl StoreView,
    _circumscription: f64,
) -> Vec<(String, f64)> {
    let params = store.params();

    let mut activation: HashMap<String, f64> = HashMap::new();
    let mut queue: VecDeque<(String, f64, u32)> = VecDeque::new();

    for (key, act) in seeds {
        let current = activation.entry(key.clone()).or_insert(0.0);
        if *act > *current {
            *current = *act;
            queue.push_back((key.clone(), *act, 0));
        }
    }

    while let Some((key, act, depth)) = queue.pop_front() {
        if depth >= params.max_hops { continue; }

        for (neighbor, strength) in graph.neighbors(&key) {
            let neighbor_weight = store.node_weight(neighbor.as_str());
            let propagated = act * params.edge_decay * neighbor_weight * strength as f64;
            if propagated < params.min_activation { continue; }

            let current = activation.entry(neighbor.clone()).or_insert(0.0);
            if propagated > *current {
                *current = propagated;
                queue.push_back((neighbor.clone(), propagated, depth + 1));
            }
        }
    }

    let mut results: Vec<_> = activation.into_iter().collect();
    results.sort_by(|a, b| b.1.partial_cmp(&a.1).unwrap_or(Ordering::Equal));
    results
}

/// Full search: find direct hits, spread activation, return ranked results
pub fn search(query: &str, store: &impl StoreView) -> Vec<SearchResult> {
    let graph = crate::graph::build_graph_fast(store);
    let query_lower = query.to_lowercase();
    let query_tokens: Vec<&str> = query_lower.split_whitespace().collect();

    let mut seeds: Vec<(String, f64)> = Vec::new();
    let mut snippets: HashMap<String, String> = HashMap::new();

    store.for_each_node(|key, content, weight| {
        let content_lower = content.to_lowercase();

        let exact_match = content_lower.contains(&query_lower);
        let token_match = query_tokens.len() > 1
            && query_tokens.iter().all(|t| content_lower.contains(t));

        if exact_match || token_match {
            let activation = if exact_match { weight as f64 } else { weight as f64 * 0.85 };
            seeds.push((key.to_owned(), activation));

            let snippet: String = content.lines()
                .filter(|l| {
                    let ll = l.to_lowercase();
                    if exact_match && ll.contains(&query_lower) { return true; }
                    query_tokens.iter().any(|t| ll.contains(t))
                })
                .take(3)
                .map(|l| {
                    let t = l.trim();
                    if t.len() > 100 {
                        let end = t.floor_char_boundary(97);
                        format!("{}...", &t[..end])
                    } else {
                        t.to_string()
                    }
                })
                .collect::<Vec<_>>()
                .join("\n         ");
            snippets.insert(key.to_owned(), snippet);
        }
    });

    if seeds.is_empty() {
        return Vec::new();
    }

    let direct_hits: HashSet<String> = seeds.iter().map(|(k, _)| k.clone()).collect();
    let raw_results = spreading_activation(&seeds, &graph, store, 0.0);

    raw_results.into_iter().map(|(key, activation)| {
        let is_direct = direct_hits.contains(&key);
        let snippet = snippets.get(&key).cloned();
        SearchResult { key, activation, is_direct, snippet }
    }).collect()
}

/// Extract meaningful search terms from natural language.
/// Strips common English stop words, returns up to max_terms words.
pub fn extract_query_terms(text: &str, max_terms: usize) -> String {
    const STOP_WORDS: &[&str] = &[
        "the", "a", "an", "is", "are", "was", "were", "do", "does", "did",
        "have", "has", "had", "will", "would", "could", "should", "can",
        "may", "might", "shall", "been", "being", "to", "of", "in", "for",
        "on", "with", "at", "by", "from", "as", "but", "or", "and", "not",
        "no", "if", "then", "than", "that", "this", "it", "its", "my",
        "your", "our", "we", "you", "i", "me", "he", "she", "they", "them",
        "what", "how", "why", "when", "where", "about", "just", "let",
        "want", "tell", "show", "think", "know", "see", "look", "make",
        "get", "go", "some", "any", "all", "very", "really", "also", "too",
        "so", "up", "out", "here", "there",
    ];

    text.to_lowercase()
        .split(|c: char| !c.is_alphanumeric())
        .filter(|w| !w.is_empty() && w.len() > 2 && !STOP_WORDS.contains(w))
        .take(max_terms)
        .collect::<Vec<_>>()
        .join(" ")
}