consciousness/src/subconscious/prompts.rs

// Agent prompt generation and formatting. Presentation logic —
// builds text prompts from store data for consolidation agents.

use crate::store::Store;
use crate::graph::Graph;

use crate::neuro::ReplayItem;

/// Result of building an agent prompt — includes both the prompt text
/// and the keys of nodes selected for processing, so the caller can
/// record visits after successful completion.
/// A resolved step ready for execution.
pub struct ResolvedStep {
    pub prompt: String,
    pub phase: String,
}

pub struct AgentBatch {
    pub steps: Vec<ResolvedStep>,
    pub node_keys: Vec<String>,
}

pub fn format_topology_header(store: &Store, graph: &Graph) -> String {
    let sigma = graph.small_world_sigma();
    let alpha = graph.degree_power_law_exponent();
    let gini = graph.degree_gini();
    let avg_cc = graph.avg_clustering_coefficient();
    let n = graph.nodes().len();
    let e = graph.edge_count();

    // Type counts
    let mut type_counts: std::collections::HashMap<&str, usize> = std::collections::HashMap::new();
    let all_keys = store.all_keys().unwrap_or_default();
    for key in &all_keys {
        if let Ok(Some(node)) = store.get_node(key) {
            let label = match node.node_type {
                crate::store::NodeType::Semantic => "semantic",
                crate::store::NodeType::EpisodicSession
                | crate::store::NodeType::EpisodicDaily
                | crate::store::NodeType::EpisodicWeekly
                | crate::store::NodeType::EpisodicMonthly => "episodic",
            };
            *type_counts.entry(label).or_default() += 1;
        }
    }
    let mut types: Vec<_> = type_counts.iter().collect();
    types.sort_by_key(|(_, c)| std::cmp::Reverse(**c));
    let type_str: String = types.iter()
        .map(|(t, c)| format!("{}={}", t, c))
        .collect::<Vec<_>>()
        .join(" ");

    // Identify saturated hubs — nodes with degree well above threshold
    let threshold = graph.hub_threshold();
    let mut hubs: Vec<_> = graph.nodes().iter()
        .map(|k| (k.clone(), graph.degree(k)))
        .filter(|(_, d)| *d >= threshold)
        .collect();
    hubs.sort_by(|a, b| b.1.cmp(&a.1));
    hubs.truncate(15);

    let hub_list = if hubs.is_empty() {
        String::new()
    } else {
        let lines: Vec<String> = hubs.iter()
            .map(|(k, d)| format!("  - {} (degree {})", k, d))
            .collect();
        format!(
            "### SATURATED HUBS — DO NOT LINK TO THESE\n\
             The following nodes are already over-connected. Adding more links\n\
             to them makes the graph worse (star topology). Find lateral\n\
             connections between peripheral nodes instead.\n\n{}\n\n\
             Only link to a hub if it is genuinely the ONLY reasonable target.\n\n",
            lines.join("\n"))
    };

    format!(
        "## Current graph topology\n\
         Nodes: {}  Edges: {}  Communities: {}  Types: {}\n\
         Small-world σ: {:.1}  Power-law α: {:.2}  Degree Gini: {:.3}\n\
         Avg clustering coefficient: {:.4}\n\n\
         {}\
         Each node below shows its hub-link ratio (fraction of edges to top-5% degree nodes).\n\
         Use `poc-memory link-impact SOURCE TARGET` to evaluate proposed links.\n\n",
        n, e, graph.community_count(), type_str, sigma, alpha, gini, avg_cc, hub_list)
}

pub fn format_nodes_section(store: &Store, items: &[ReplayItem], graph: &Graph) -> String {
    let hub_thresh = graph.hub_threshold();
    let mut out = String::new();
    for item in items {
        let node = match store.get_node(&item.key).ok().flatten() {
            Some(n) => n,
            None => continue,
        };

        out.push_str(&format!("## {} \n", item.key));
        out.push_str(&format!("Priority: {:.3}  CC: {:.3}  Emotion: {:.1}  ",
            item.priority, item.cc, item.emotion));
        out.push_str(&format!("Interval: {}d\n",
            node.spaced_repetition_interval));
        if item.outlier_score > 0.0 {
            out.push_str(&format!("Spectral: {} (outlier={:.1})\n",
                item.classification, item.outlier_score));
        }

        if let Some(community) = node.community_id {
            out.push_str(&format!("Community: {}  ", community));
        }
        let deg = graph.degree(&item.key);
        let cc = graph.clustering_coefficient(&item.key);

        // Hub-link ratio: what fraction of this node's edges go to hubs?
        let neighbors = graph.neighbors(&item.key);
        let hub_links = neighbors.iter()
            .filter(|(n, _)| graph.degree(n) >= hub_thresh)
            .count();
        let hub_ratio = if deg > 0 { hub_links as f32 / deg as f32 } else { 0.0 };
        let is_hub = deg >= hub_thresh;

        out.push_str(&format!("Degree: {}  CC: {:.3}  Hub-link ratio: {:.0}% ({}/{})",
            deg, cc, hub_ratio * 100.0, hub_links, deg));
        if is_hub {
            out.push_str("  ← THIS IS A HUB");
        } else if hub_ratio > 0.6 {
            out.push_str("  ← mostly hub-connected, needs lateral links");
        }
        out.push('\n');

        let hits = crate::counters::search_hit_count(&item.key);
        if hits > 0 {
            out.push_str(&format!("Search hits: {} ← actively found by search, prefer to keep\n", hits));
        }

        // Full content — the agent needs to see everything to do quality work
        let content = &node.content;
        out.push_str(&format!("\nContent:\n{}\n\n", content));

        // Neighbors
        let neighbors = graph.neighbors(&item.key);
        if !neighbors.is_empty() {
            out.push_str("Neighbors:\n");
            for (n, strength) in neighbors.iter().take(15) {
                let n_cc = graph.clustering_coefficient(n);
                let n_community = store.get_node(n)
                    .ok()
                    .flatten()
                    .and_then(|n| n.community_id);
                out.push_str(&format!("  - {} (str={:.2}, cc={:.3}",
                    n, strength, n_cc));
                if let Some(c) = n_community {
                    out.push_str(&format!(", c{}", c));
                }
                out.push_str(")\n");
            }
        }

        out.push_str("\n---\n\n");
    }
    out
}

pub fn format_health_section(store: &Store, graph: &Graph) -> String {
    use crate::graph;

    let health = graph::health_report(graph, store);

    let mut out = health;
    out.push_str("\n\n## Weight distribution\n");

    // Weight histogram
    let mut buckets = [0u32; 10]; // 0.0-0.1, 0.1-0.2, ..., 0.9-1.0
    let all_keys = store.all_keys().unwrap_or_default();
    for key in &all_keys {
        if let Ok(Some(node)) = store.get_node(key) {
            let bucket = ((node.weight * 10.0) as usize).min(9);
            buckets[bucket] += 1;
        }
    }
    for (i, &count) in buckets.iter().enumerate() {
        let lo = i as f32 / 10.0;
        let hi = (i + 1) as f32 / 10.0;
        let bar = "█".repeat((count as usize) / 10);
        out.push_str(&format!("  {:.1}-{:.1}: {:4} {}\n", lo, hi, count, bar));
    }

    // Near-prune nodes
    let near_prune: Vec<_> = all_keys.iter()
        .filter_map(|k| store.get_node(k).ok()?.map(|n| (k.clone(), n.weight)))
        .filter(|(_, w)| *w < 0.15)
        .collect();
    if !near_prune.is_empty() {
        out.push_str(&format!("\n## Near-prune nodes ({} total)\n", near_prune.len()));
        for (k, w) in near_prune.iter().take(20) {
            out.push_str(&format!("  [{:.3}] {}\n", w, k));
        }
    }

    // Community sizes
    let communities = graph.communities();
    let mut comm_sizes: std::collections::HashMap<u32, Vec<String>> = std::collections::HashMap::new();
    for (key, &label) in communities {
        comm_sizes.entry(label).or_default().push(key.clone());
    }
    let mut sizes: Vec<_> = comm_sizes.iter()
        .map(|(id, members)| (*id, members.len(), members.clone()))
        .collect();
    sizes.sort_by(|a, b| b.1.cmp(&a.1));

    out.push_str("\n## Largest communities\n");
    for (id, size, members) in sizes.iter().take(10) {
        out.push_str(&format!("  Community {} ({} nodes): ", id, size));
        let sample: Vec<_> = members.iter().take(5).map(|s| s.as_str()).collect();
        out.push_str(&sample.join(", "));
        if *size > 5 { out.push_str(", ..."); }
        out.push('\n');
    }

    out
}

/// Generate a specific agent prompt with filled-in data.
pub async fn agent_prompt(agent: &str, count: usize) -> Result<AgentBatch, String> {
    let def = super::defs::get_def(agent)
        .ok_or_else(|| format!("Unknown agent: {}", agent))?;
    super::defs::run_agent(&def, count, &Default::default()).await
}