Unify enrichment tracking and outcome-based status

Make common_tracker_patterns and common_third_parties share one
enrichment-tracking model and fix the misleading proboctl status.

Both tables now carry the enrichment JSONB provenance payload, an
enrichment_attempts counter, and a last_enrichment_attempt_at clock.
On common_tracker_patterns the enriched_at done-flag is renamed to
last_enrichment_attempt_at and stamped at claim time, so it is truthful
to "attempt" rather than "success". A row is considered to have been
through the workflow when it carries an enrichment payload, not when a
timestamp is set, which lets stale recovery key off the payload being
absent with budget remaining, exactly like common_third_parties.

The claim path reads the attempt counter and timestamp back via
RETURNING so the in-memory receiver matches the database clock instead
of a separate app-side time.Now.

The enricher builds a per-field provenance payload (description and
third-party outcomes plus the mapping attribution) and persists it via
UpdateEnrichment, named to mirror the common-third-party sibling. The
common pattern enrichment worker gains a max-attempts ceiling so a
permanently failing row stops looping.

proboctl now shows "enriched" only when every field the last run
recorded an outcome for resolved a value, otherwise "partial (X/Y)",
replacing the misleading "enriched (no description)" label.

Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
Émile Ré
2026-06-15 16:25:53 +02:00
parent a6ed64caaf
commit ef6cead482
17 changed files with 705 additions and 155 deletions

View File

@@ -26,17 +26,25 @@ import (
"go.probo.inc/probo/pkg/coredata"
)
const defaultEnrichmentStaleAfter = 10 * time.Minute
const (
defaultEnrichmentStaleAfter = 10 * time.Minute
// defaultEnrichmentMaxAttempts caps how many times a row is retried
// before stale recovery leaves it alone, so a permanently failing row
// does not loop forever.
defaultEnrichmentMaxAttempts = 3
)
// commonPatternEnrichmentHandler is the queue poller for common tracker
// pattern enrichment. It owns only the claim/dequeue and stale-recovery
// mechanics; the enrichment work itself lives in CommonPatternEnricher so
// it can also run synchronously from operator tooling.
type commonPatternEnrichmentHandler struct {
pg *pg.Client
logger *log.Logger
enricher *CommonPatternEnricher
staleAfter time.Duration
pg *pg.Client
logger *log.Logger
enricher *CommonPatternEnricher
staleAfter time.Duration
maxAttempts int
}
// NewCommonPatternEnrichmentWorker builds the worker that fills
@@ -52,17 +60,23 @@ func NewCommonPatternEnrichmentWorker(
enrichmentCfg TrackerEnrichmentAgentConfig,
mappingCfg TrackerMappingAgentConfig,
staleAfter time.Duration,
maxAttempts int,
opts ...worker.Option,
) *worker.Worker[coredata.CommonTrackerPattern] {
if staleAfter <= 0 {
staleAfter = defaultEnrichmentStaleAfter
}
if maxAttempts <= 0 {
maxAttempts = defaultEnrichmentMaxAttempts
}
h := &commonPatternEnrichmentHandler{
pg: pgClient,
logger: logger,
enricher: NewCommonPatternEnricher(pgClient, logger, enrichmentCfg, mappingCfg),
staleAfter: staleAfter,
pg: pgClient,
logger: logger,
enricher: NewCommonPatternEnricher(pgClient, logger, enrichmentCfg, mappingCfg),
staleAfter: staleAfter,
maxAttempts: maxAttempts,
}
return worker.New(
@@ -108,7 +122,7 @@ func (h *commonPatternEnrichmentHandler) RecoverStale(ctx context.Context) error
return h.pg.WithConn(
ctx,
func(ctx context.Context, conn pg.Querier) error {
if err := coredata.ResetStaleEnrichments(ctx, conn, h.staleAfter); err != nil {
if err := coredata.ResetStaleEnrichments(ctx, conn, h.staleAfter, h.maxAttempts); err != nil {
return fmt.Errorf("cannot reset stale common tracker pattern enrichments: %w", err)
}