poc-memory v0.4.0: graph-structured memory with consolidation pipeline

Rust core:
- Cap'n Proto append-only storage (nodes + relations)
- Graph algorithms: clustering coefficient, community detection,
  schema fit, small-world metrics, interference detection
- BM25 text similarity with Porter stemming
- Spaced repetition replay queue
- Commands: search, init, health, status, graph, categorize,
  link-add, link-impact, decay, consolidate-session, etc.

Python scripts:
- Episodic digest pipeline: daily/weekly/monthly-digest.py
- retroactive-digest.py for backfilling
- consolidation-agents.py: 3 parallel Sonnet agents
- apply-consolidation.py: structured action extraction + apply
- digest-link-parser.py: extract ~400 explicit links from digests
- content-promotion-agent.py: promote episodic obs to semantic files
- bulk-categorize.py: categorize all nodes via single Sonnet call
- consolidation-loop.py: multi-round automated consolidation

Co-Authored-By: Kent Overstreet <kent.overstreet@linux.dev>
This commit is contained in:
ProofOfConcept 2026-02-28 22:17:00 -05:00
commit 23fac4e5fe
35 changed files with 9388 additions and 0 deletions

146
src/search.rs Normal file
View file

@ -0,0 +1,146 @@
// 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::Store;
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: &Store,
_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.nodes.get(neighbor.as_str())
.map(|n| n.weight as f64)
.unwrap_or(params.default_weight);
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: &Store) -> Vec<SearchResult> {
let graph = store.build_graph();
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();
for (key, node) in &store.nodes {
let content_lower = node.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 weight = node.weight as f64;
let activation = if exact_match { weight } else { weight * 0.85 };
seeds.push((key.clone(), activation));
let snippet: String = node.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.clone(), 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(" ")
}