feat: M1 determinism fixes for gossip

Refs #1

- F1: canonical fingerprints (git identity by remote URL, log by
  basename, obsidian by relative vault path) so identical facts get
  identical ids across machines
- F2: node_id (persisted in settings) + Hybrid Logical Clock in all
  observation "when" columns; removed time.Now() fact-time fallbacks
- F3: stable TF-IDF tie-break sort (score desc, term asc)
- F4: observations carry (node_id, hcl) locator; dedup ordered by hcl
This commit is contained in:
2026-08-29 03:51:02 -07:00
parent f5766aa6d8
commit 2c0f8fa257
9 changed files with 162 additions and 30 deletions
+12 -2
View File
@@ -123,7 +123,12 @@ func (idx *TFIDFIndex) TopTerms(docIdx int, n int) []struct {
}{t, s})
}
}
sort.Slice(scored, func(i, j int) bool { return scored[i].Score > scored[j].Score })
sort.Slice(scored, func(i, j int) bool {
if scored[i].Score != scored[j].Score {
return scored[i].Score > scored[j].Score
}
return scored[i].Term < scored[j].Term
})
if len(scored) > n {
scored = scored[:n]
}
@@ -220,7 +225,12 @@ func (idx *TFIDFIndex) Cluster(minSharedTerms int, maxTopics int) []TopicCluster
for k, v := range allTerms {
sorted = append(sorted, kv{k, v})
}
sort.Slice(sorted, func(i, j int) bool { return sorted[i].v > sorted[j].v })
sort.Slice(sorted, func(i, j int) bool {
if sorted[i].v != sorted[j].v {
return sorted[i].v > sorted[j].v
}
return sorted[i].k < sorted[j].k
})
var nameParts []string
for _, kv := range sorted {