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:
@@ -16,6 +16,7 @@ package commontrackerpattern
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"fmt"
|
||||
|
||||
@@ -47,20 +48,62 @@ func NewCmdCommonTrackerPattern(f *cmdutil.Factory) *cobra.Command {
|
||||
}
|
||||
|
||||
// enrichmentState classifies a pattern's position in the enrichment
|
||||
// lifecycle for display.
|
||||
// lifecycle for display. A row that has been through the workflow (it
|
||||
// carries an enrichment payload) reads "enriched" only when every field
|
||||
// the last run recorded an outcome for resolved a value; otherwise it
|
||||
// reads "partial (X/Y)".
|
||||
func enrichmentState(p *coredata.CommonTrackerPattern) string {
|
||||
switch {
|
||||
case p.EnrichmentRequestedAt != nil:
|
||||
return "queued"
|
||||
case p.EnrichedAt != nil && p.Description == "":
|
||||
return "enriched (no description)"
|
||||
case p.EnrichedAt != nil:
|
||||
return "enriched"
|
||||
case len(p.Enrichment) > 0:
|
||||
resolved, total := enrichmentCompleteness(p)
|
||||
if total == 0 || resolved == total {
|
||||
return "enriched"
|
||||
}
|
||||
|
||||
return fmt.Sprintf("partial (%d/%d)", resolved, total)
|
||||
default:
|
||||
return "unenriched"
|
||||
}
|
||||
}
|
||||
|
||||
// resolvedFieldStatuses are the per-field enrichment statuses that carry a
|
||||
// value, as opposed to not_found.
|
||||
var resolvedFieldStatuses = map[string]struct{}{
|
||||
"found": {},
|
||||
"exists_external": {},
|
||||
}
|
||||
|
||||
// enrichmentCompleteness counts how many of the fields the last enrichment
|
||||
// run recorded an outcome for resolved a value (X) versus the total it
|
||||
// recorded (Y), parsed from the enrichment payload's per-field provenance.
|
||||
func enrichmentCompleteness(p *coredata.CommonTrackerPattern) (resolved, total int) {
|
||||
if len(p.Enrichment) == 0 {
|
||||
return 0, 0
|
||||
}
|
||||
|
||||
var meta struct {
|
||||
Fields map[string]struct {
|
||||
Status string `json:"status"`
|
||||
} `json:"fields"`
|
||||
}
|
||||
|
||||
if err := json.Unmarshal(p.Enrichment, &meta); err != nil {
|
||||
return 0, 0
|
||||
}
|
||||
|
||||
for _, f := range meta.Fields {
|
||||
total++
|
||||
|
||||
if _, ok := resolvedFieldStatuses[f.Status]; ok {
|
||||
resolved++
|
||||
}
|
||||
}
|
||||
|
||||
return resolved, total
|
||||
}
|
||||
|
||||
// resolveCommonThirdPartyID accepts either a common third party GID or a
|
||||
// slug and returns the corresponding id.
|
||||
func resolveCommonThirdPartyID(ctx context.Context, conn pg.Querier, value string) (gid.GID, error) {
|
||||
|
||||
Reference in New Issue
Block a user