kent/consciousness
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

store: strip .md suffix from all keys

Browse source 
Keys were a vestige of the file-based era. resolve_key() added .md
to lookups while upsert() used bare keys, creating phantom duplicate
nodes (the instructions bug: writes went to "instructions", reads
found "instructions.md").

- Remove .md normalization from resolve_key, strip instead
- Update all hardcoded key patterns (journal.md# → journal#, etc)
- Add strip_md_keys() migration to fsck: renames nodes and relations
- Add broken link detection to health report
- Delete redirect table (no longer needed)
- Update config defaults and config.jsonl

Migration: run `poc-memory fsck` to rename existing keys.

Co-Authored-By: ProofOfConcept <poc@bcachefs.org>
This commit is contained in:
Kent Overstreet 2026-03-08 19:41:26 -04:00
parent 77fc533631
commit 46f8fe662e
12 changed files with 289 additions and 132 deletions
Download patch file Download diff file Expand all files Collapse all files

14
src/knowledge.rs
View file

@ -515,10 +515,10 @@ fn spectral_distance(embedding: &HashMap<String, Vec<f64>>, a: &str, b: &str) ->
fn select_extractor_clusters(_store: &Store, n: usize) -> Vec<Vec<String>> {
let embedding = load_spectral_embedding();
let skip = ["journal.md", "MEMORY.md", "where-am-i.md", "work-queue.md"];
let skip = ["journal", "MEMORY", "where-am-i", "work-queue"];
let semantic_keys: Vec<&String> = embedding.keys()
.filter(|k| !k.starts_with("journal.md#") && !skip.contains(&k.as_str()))
.filter(|k| !k.starts_with("journal#") && !skip.contains(&k.as_str()))
.collect();
let cluster_size = 5;
@ -578,9 +578,9 @@ pub fn run_extractor(store: &Store, graph: &Graph, batch_size: usize) -> Result<
fn select_connector_pairs(store: &Store, graph: &Graph, n: usize) -> Vec<(Vec<String>, Vec<String>)> {
let embedding = load_spectral_embedding();
let skip_prefixes = ["journal.md#", "daily-", "weekly-", "monthly-", "all-sessions"];
let skip_exact: HashSet<&str> = ["journal.md", "MEMORY.md", "where-am-i.md",
"work-queue.md", "work-state"].iter().copied().collect();
let skip_prefixes = ["journal#", "daily-", "weekly-", "monthly-", "all-sessions"];
let skip_exact: HashSet<&str> = ["journal", "MEMORY", "where-am-i",
"work-queue", "work-state"].iter().copied().collect();
let semantic_keys: Vec<&String> = embedding.keys()
.filter(|k| {
@ -656,8 +656,8 @@ pub fn run_challenger(store: &Store, graph: &Graph, batch_size: usize) -> Result
let mut candidates: Vec<(&String, usize)> = store.nodes.iter()
.filter(|(k, _)| {
!k.starts_with("journal.md#")
&& !["journal.md", "MEMORY.md", "where-am-i.md"].contains(&k.as_str())
!k.starts_with("journal#")
&& !["journal", "MEMORY", "where-am-i"].contains(&k.as_str())
})
.map(|(k, _)| (k, graph.degree(k)))
.collect();