consciousness/src/neuro/scoring.rs

// Consolidation scoring, replay queues, interference detection, and
// graph health metrics. Pure analysis — no store mutations.

use crate::store::{Store, now_epoch};
use crate::graph::{self, Graph};
use crate::spectral::{self, SpectralEmbedding, SpectralPosition};

use std::collections::HashMap;

const SECS_PER_DAY: f64 = 86400.0;

/// Consolidation priority: how urgently a node needs attention.
///
/// With spectral data:
///   priority = spectral_displacement × overdue × emotion
/// Without:
///   priority = (1 - cc) × overdue × emotion
///
/// Spectral displacement is the outlier_score clamped and normalized —
/// it measures how far a node sits from its community center in the
/// eigenspace. This is a global signal (considers all graph structure)
/// vs CC which is local (only immediate neighbors).
pub fn consolidation_priority(
    store: &Store,
    key: &str,
    graph: &Graph,
    spectral_outlier: Option<f64>,
) -> f64 {
    let node = match store.nodes.get(key) {
        Some(n) => n,
        None => return 0.0,
    };

    // Integration factor: how poorly integrated is this node?
    let displacement = if let Some(outlier) = spectral_outlier {
        // outlier_score = dist_to_center / median_dist_in_community
        // 1.0 = typical position, >2 = unusual, >5 = extreme outlier
        // Use log scale for dynamic range: the difference between
        // outlier=5 and outlier=10 matters less than 1 vs 2.
        (outlier / 3.0).min(3.0)
    } else {
        let cc = graph.clustering_coefficient(key) as f64;
        1.0 - cc
    };

    // Spaced repetition: how overdue is this node for replay?
    let interval_secs = node.spaced_repetition_interval as f64 * SECS_PER_DAY;
    let time_since_replay = if node.last_replayed > 0 {
        (now_epoch() - node.last_replayed).max(0) as f64
    } else {
        interval_secs * 3.0
    };
    let overdue_ratio = (time_since_replay / interval_secs).min(5.0);

    // Emotional intensity: higher emotion = higher priority
    let emotion_factor = 1.0 + (node.emotion as f64 / 10.0);

    displacement * overdue_ratio * emotion_factor
}

/// Item in the replay queue
pub struct ReplayItem {
    pub key: String,
    pub priority: f64,
    pub interval_days: u32,
    pub emotion: f32,
    pub cc: f32,
    /// Spectral classification: "bridge", "outlier", "core", "peripheral"
    pub classification: &'static str,
    /// Raw spectral outlier score (distance / median)
    pub outlier_score: f64,
}

/// Generate the replay queue: nodes ordered by consolidation priority.
/// Automatically loads spectral embedding if available.
pub fn replay_queue(store: &Store, count: usize) -> Vec<ReplayItem> {
    let graph = store.build_graph();
    let emb = spectral::load_embedding().ok();
    replay_queue_with_graph(store, count, &graph, emb.as_ref())
}

/// Generate the replay queue using pre-built graph and optional spectral data.
pub fn replay_queue_with_graph(
    store: &Store,
    count: usize,
    graph: &Graph,
    emb: Option<&SpectralEmbedding>,
) -> Vec<ReplayItem> {
    // Build spectral position map if embedding is available
    let positions: HashMap<String, SpectralPosition> = if let Some(emb) = emb {
        let communities = graph.communities().clone();
        spectral::analyze_positions(emb, &communities)
            .into_iter()
            .map(|p| (p.key.clone(), p))
            .collect()
    } else {
        HashMap::new()
    };

    let mut items: Vec<ReplayItem> = store.nodes.iter()
        .map(|(key, node)| {
            let pos = positions.get(key);
            let outlier_score = pos.map(|p| p.outlier_score).unwrap_or(0.0);
            let classification = pos
                .map(|p| spectral::classify_position(p))
                .unwrap_or("unknown");

            let priority = consolidation_priority(
                store, key, graph,
                pos.map(|p| p.outlier_score),
            );
            ReplayItem {
                key: key.clone(),
                priority,
                interval_days: node.spaced_repetition_interval,
                emotion: node.emotion,
                cc: graph.clustering_coefficient(key),
                classification,
                outlier_score,
            }
        })
        .collect();

    items.sort_by(|a, b| b.priority.total_cmp(&a.priority));
    items.truncate(count);
    items
}

/// Detect interfering memory pairs: high text similarity but different communities
pub fn detect_interference(
    store: &Store,
    graph: &Graph,
    threshold: f32,
) -> Vec<(String, String, f32)> {
    use crate::similarity;

    let communities = graph.communities();

    // Only compare nodes within a reasonable set — take the most active ones
    let mut docs: Vec<(String, String)> = store.nodes.iter()
        .filter(|(_, n)| n.content.len() > 50) // skip tiny nodes
        .map(|(k, n)| (k.clone(), n.content.clone()))
        .collect();

    // For large stores, sample to keep pairwise comparison feasible
    if docs.len() > 200 {
        docs.sort_by(|a, b| b.1.len().cmp(&a.1.len()));
        docs.truncate(200);
    }

    let similar = similarity::pairwise_similar(&docs, threshold);

    // Filter to pairs in different communities
    similar.into_iter()
        .filter(|(a, b, _)| {
            let ca = communities.get(a);
            let cb = communities.get(b);
            match (ca, cb) {
                (Some(a), Some(b)) => a != b,
                _ => true, // if community unknown, flag it
            }
        })
        .collect()
}

/// Schema assimilation scoring for a new node.
/// Returns how easily the node integrates into existing structure.
///
/// High fit (>0.5): auto-link, done
/// Medium fit (0.2-0.5): agent reviews, proposes links
/// Low fit (<0.2): deep examination needed — new schema seed, bridge, or noise?
pub fn schema_assimilation(store: &Store, key: &str) -> (f32, &'static str) {
    let graph = store.build_graph();
    let fit = graph.clustering_coefficient(key);

    let recommendation = if fit > 0.5 {
        "auto-integrate"
    } else if fit > 0.2 {
        "agent-review"
    } else if graph.degree(key) > 0 {
        "deep-examine-bridge"
    } else {
        "deep-examine-orphan"
    };

    (fit, recommendation)
}

/// Agent allocation from the control loop
pub struct ConsolidationPlan {
    pub replay_count: usize,
    pub linker_count: usize,
    pub separator_count: usize,
    pub transfer_count: usize,
    pub run_health: bool,
    pub rationale: Vec<String>,
}

/// Analyze metrics and decide how much each agent needs to run.
///
/// This is the control loop: metrics → error signal → agent allocation.
/// Target values are based on healthy small-world networks.
pub fn consolidation_plan(store: &Store) -> ConsolidationPlan {
    let graph = store.build_graph();
    let alpha = graph.degree_power_law_exponent();
    let gini = graph.degree_gini();
    let avg_cc = graph.avg_clustering_coefficient();
    let interference_pairs = detect_interference(store, &graph, 0.5);
    let interference_count = interference_pairs.len();

    // Count episodic vs semantic nodes
    let episodic_count = store.nodes.iter()
        .filter(|(k, _)| k.contains("journal") || k.contains("session"))
        .count();
    let _semantic_count = store.nodes.len() - episodic_count;
    let episodic_ratio = if store.nodes.is_empty() { 0.0 }
        else { episodic_count as f32 / store.nodes.len() as f32 };

    let mut plan = ConsolidationPlan {
        replay_count: 0,
        linker_count: 0,
        separator_count: 0,
        transfer_count: 0,
        run_health: true, // always run health first
        rationale: Vec::new(),
    };

    // Target: α ≥ 2.5 (healthy scale-free)
    if alpha < 2.0 {
        plan.replay_count += 10;
        plan.linker_count += 5;
        plan.rationale.push(format!(
            "α={:.2} (target ≥2.5): extreme hub dominance → 10 replay + 5 linker for lateral links",
            alpha));
    } else if alpha < 2.5 {
        plan.replay_count += 5;
        plan.linker_count += 3;
        plan.rationale.push(format!(
            "α={:.2} (target ≥2.5): moderate hub dominance → 5 replay + 3 linker",
            alpha));
    } else {
        plan.replay_count += 3;
        plan.rationale.push(format!(
            "α={:.2}: healthy — 3 replay for maintenance", alpha));
    }

    // Target: Gini ≤ 0.4
    if gini > 0.5 {
        plan.replay_count += 3;
        plan.rationale.push(format!(
            "Gini={:.3} (target ≤0.4): high inequality → +3 replay (lateral focus)",
            gini));
    }

    // Target: avg CC ≥ 0.2
    if avg_cc < 0.1 {
        plan.replay_count += 5;
        plan.rationale.push(format!(
            "CC={:.3} (target ≥0.2): very poor integration → +5 replay",
            avg_cc));
    } else if avg_cc < 0.2 {
        plan.replay_count += 2;
        plan.rationale.push(format!(
            "CC={:.3} (target ≥0.2): low integration → +2 replay",
            avg_cc));
    }

    // Interference: >100 pairs is a lot, <10 is clean
    if interference_count > 100 {
        plan.separator_count += 10;
        plan.rationale.push(format!(
            "Interference: {} pairs (target <50) → 10 separator",
            interference_count));
    } else if interference_count > 20 {
        plan.separator_count += 5;
        plan.rationale.push(format!(
            "Interference: {} pairs (target <50) → 5 separator",
            interference_count));
    } else if interference_count > 0 {
        plan.separator_count += interference_count.min(3);
        plan.rationale.push(format!(
            "Interference: {} pairs → {} separator",
            interference_count, plan.separator_count));
    }

    // Episodic → semantic transfer
    if episodic_ratio > 0.6 {
        plan.transfer_count += 10;
        plan.rationale.push(format!(
            "Episodic ratio: {:.0}% ({}/{}) → 10 transfer (knowledge extraction needed)",
            episodic_ratio * 100.0, episodic_count, store.nodes.len()));
    } else if episodic_ratio > 0.4 {
        plan.transfer_count += 5;
        plan.rationale.push(format!(
            "Episodic ratio: {:.0}% → 5 transfer",
            episodic_ratio * 100.0));
    }

    plan
}

/// Format the consolidation plan for display
pub fn format_plan(plan: &ConsolidationPlan) -> String {
    let mut out = String::from("Consolidation Plan\n==================\n\n");

    out.push_str("Analysis:\n");
    for r in &plan.rationale {
        out.push_str(&format!("  • {}\n", r));
    }

    out.push_str("\nAgent allocation:\n");
    if plan.run_health {
        out.push_str("  1. health        — system audit\n");
    }
    let mut step = 2;
    if plan.replay_count > 0 {
        out.push_str(&format!("  {}. replay ×{:2}    — schema assimilation + lateral linking\n",
            step, plan.replay_count));
        step += 1;
    }
    if plan.linker_count > 0 {
        out.push_str(&format!("  {}. linker ×{:2}    — relational binding from episodes\n",
            step, plan.linker_count));
        step += 1;
    }
    if plan.separator_count > 0 {
        out.push_str(&format!("  {}. separator ×{} — pattern separation\n",
            step, plan.separator_count));
        step += 1;
    }
    if plan.transfer_count > 0 {
        out.push_str(&format!("  {}. transfer ×{:2} — episodic→semantic extraction\n",
            step, plan.transfer_count));
    }

    let total = plan.replay_count + plan.linker_count
        + plan.separator_count + plan.transfer_count
        + if plan.run_health { 1 } else { 0 };
    out.push_str(&format!("\nTotal agent runs: {}\n", total));

    out
}

/// Brief daily check: compare current metrics to last snapshot
pub fn daily_check(store: &Store) -> String {
    let graph_obj = store.build_graph();
    let snap = graph::current_metrics(&graph_obj);

    let history = graph::load_metrics_history();
    let prev = history.last();

    let mut out = String::from("Memory daily check\n");

    // Current state
    out.push_str(&format!("  σ={:.1}  α={:.2}  gini={:.3}  cc={:.4}\n",
        snap.sigma, snap.alpha, snap.gini, snap.avg_cc));

    // Trend
    if let Some(p) = prev {
        let d_sigma = snap.sigma - p.sigma;
        let d_alpha = snap.alpha - p.alpha;
        let d_gini = snap.gini - p.gini;

        out.push_str(&format!("  Δσ={:+.1}  Δα={:+.2}  Δgini={:+.3}\n",
            d_sigma, d_alpha, d_gini));

        // Assessment
        let mut issues = Vec::new();
        if snap.alpha < 2.0 { issues.push("hub dominance critical"); }
        if snap.gini > 0.5 { issues.push("high inequality"); }
        if snap.avg_cc < 0.1 { issues.push("poor integration"); }
        if d_sigma < -5.0 { issues.push("σ declining"); }
        if d_alpha < -0.1 { issues.push("α declining"); }
        if d_gini > 0.02 { issues.push("inequality increasing"); }

        if issues.is_empty() {
            out.push_str("  Status: healthy\n");
        } else {
            out.push_str(&format!("  Status: needs attention — {}\n", issues.join(", ")));
            out.push_str("  Run: poc-memory consolidate-session\n");
        }
    } else {
        out.push_str("  (first snapshot, no trend data yet)\n");
    }

    // Persist the snapshot
    graph::save_metrics_snapshot(&snap);

    out
}