mavend: run the fact vector repair on start, and test what it does (V-493)
Automatic rather than a flag, unlike -reembed: only voice-tapped facts are in this index, so it is tens of embeddings rather than thousands of notes. And waiting for an operator to know the repair exists is the failure being fixed. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
@@ -146,6 +146,7 @@ func wireVoice(cfg *config.Config, coreAPI ipc.CoreAPI, phr phraser.Phraser, mem
|
||||
emb = router.NewHashEmbedder(1024)
|
||||
}
|
||||
w.embedder = emb
|
||||
repairFactVectors(dataStore, emb)
|
||||
checkStoredEmbedder(dataStore, emb)
|
||||
|
||||
// ----- tool executor (the enabled act allowlist, store-backed) -----
|
||||
@@ -473,6 +474,36 @@ func seedTools(api ipc.CoreAPI, tools []config.ToolConfig) {
|
||||
log.Printf("voice: seeded %d act tools from config", n)
|
||||
}
|
||||
|
||||
// repairFactVectors brings stored fact vectors in line with the facts they name
|
||||
// (#493), once per box, before the embedder marker is even looked at.
|
||||
//
|
||||
// Automatic and not a flag, unlike -reembed: only voice-tapped facts are in
|
||||
// this index, so the work is tens of embeddings rather than the thousands of
|
||||
// notes that made the backfill a deliberate act. And the box that needs it is
|
||||
// broken in a way nobody can see — recall answers with the wrong text and
|
||||
// nothing logs an error — so waiting for an operator to know to run it is how
|
||||
// the defect survived four restarts in the first place.
|
||||
func repairFactVectors(dataStore *store.Store, emb router.Embedder) {
|
||||
if dataStore == nil {
|
||||
return
|
||||
}
|
||||
res, err := dataStore.RepairFactVectors(context.Background(),
|
||||
// EmbedPassage, the stored side, same as every other writer of these
|
||||
// vectors.
|
||||
func(ctx context.Context, text string) ([]float32, error) {
|
||||
return router.EmbedPassage(ctx, emb, text)
|
||||
})
|
||||
if err != nil {
|
||||
log.Printf("voice: fact vector repair failed, no marker written and nothing half-done — retried next start: %v", err)
|
||||
return
|
||||
}
|
||||
if res.Skipped || res.Rewritten+res.Dropped == 0 {
|
||||
return
|
||||
}
|
||||
log.Printf("voice: fact vector repair — %d re-embedded from the fact they name, %d dropped as voided or superseded, %d already right, took %s (#493)",
|
||||
res.Rewritten, res.Dropped, res.Kept, res.Took.Round(time.Millisecond))
|
||||
}
|
||||
|
||||
// reembedOnStart is the -reembed flag (set in run()). Opt-in on purpose: see
|
||||
// runReembed.
|
||||
var reembedOnStart bool
|
||||
|
||||
Reference in New Issue
Block a user