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

@@ -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) {

View File

@@ -59,7 +59,7 @@ func newCmdList(f *cmdutil.Factory) *cobra.Command {
cmd.Flags().StringVar(&flagState, "state", "", "Filter by enrichment state (queued, enriched, unenriched)")
cmd.Flags().BoolVar(&flagWithCommonThirdParty, "with-common-third-party", false, "Filter by whether the pattern is linked to a common third party (true/false); ignored when not set")
cmd.Flags().BoolVar(&flagWithoutDescription, "without-description", false, "Only patterns with a blank description")
cmd.Flags().StringVar(&flagSort, "sort", "confidence", "Sort field: pattern, confidence, created, updated, enriched")
cmd.Flags().StringVar(&flagSort, "sort", "confidence", "Sort field: pattern, confidence, created, updated, attempted")
cmd.Flags().StringVar(&flagOrder, "order", "", "Sort order: asc, desc (default depends on field)")
pageFlags := cmdutil.AddPageFlags(cmd)
@@ -277,10 +277,10 @@ func parseOrderBy(sort, order string) (page.OrderBy[coredata.CommonTrackerPatter
field, defaultDesc = coredata.CommonTrackerPatternOrderFieldCreatedAt, true
case "updated":
field, defaultDesc = coredata.CommonTrackerPatternOrderFieldUpdatedAt, true
case "enriched":
field, defaultDesc = coredata.CommonTrackerPatternOrderFieldEnrichedAt, true
case "attempted":
field, defaultDesc = coredata.CommonTrackerPatternOrderFieldLastEnrichmentAttemptAt, true
default:
return zeroOrderBy, fmt.Errorf("invalid --sort value %q: valid values are pattern, confidence, created, updated, enriched", sort)
return zeroOrderBy, fmt.Errorf("invalid --sort value %q: valid values are pattern, confidence, created, updated, attempted", sort)
}
direction := page.OrderDirectionAsc

View File

@@ -16,8 +16,10 @@ package commontrackerpattern
import (
"context"
"encoding/json"
"errors"
"fmt"
"time"
"github.com/spf13/cobra"
"go.gearno.de/kit/pg"
@@ -26,6 +28,41 @@ import (
"go.probo.inc/probo/pkg/proboctl/cmdutil"
)
// manualEnrichmentPayload builds the enrichment provenance written when an
// operator sets a description by hand. It records only the description
// outcome (resolved), so the row reads "enriched" and the enrichment
// worker leaves it alone, while marking the source as manual for audit.
func manualEnrichmentPayload() json.RawMessage {
now := time.Now()
payload := struct {
Status string `json:"status"`
Source string `json:"source"`
AttemptedAt time.Time `json:"attempted_at"`
Fields map[string]struct {
Status string `json:"status"`
UpdatedAt time.Time `json:"updated_at"`
} `json:"fields"`
}{
Status: "manual",
Source: "manual",
AttemptedAt: now,
Fields: map[string]struct {
Status string `json:"status"`
UpdatedAt time.Time `json:"updated_at"`
}{
"description": {Status: "found", UpdatedAt: now},
},
}
raw, err := json.Marshal(payload)
if err != nil {
return nil
}
return raw
}
func newCmdSetDescription(f *cmdutil.Factory) *cobra.Command {
var (
flagDescription string
@@ -83,7 +120,7 @@ func newCmdSetDescription(f *cmdutil.Factory) *cobra.Command {
return fmt.Errorf("cannot load common tracker pattern: %w", err)
}
if err := pattern.SetEnriched(ctx, tx, flagDescription, nil); err != nil {
if err := pattern.UpdateEnrichment(ctx, tx, flagDescription, nil, manualEnrichmentPayload()); err != nil {
return fmt.Errorf("cannot set common tracker pattern description: %w", err)
}

View File

@@ -127,12 +127,14 @@ func renderPatternDetail(f *cmdutil.Factory, p coredata.CommonTrackerPattern, th
row("Description:", description)
row("Enrichment attempts:", fmt.Sprintf("%d", p.EnrichmentAttempts))
if p.EnrichmentRequestedAt != nil {
row("Enrichment queued:", p.EnrichmentRequestedAt.Format("2006-01-02 15:04:05"))
}
if p.EnrichedAt != nil {
row("Enriched at:", p.EnrichedAt.Format("2006-01-02 15:04:05"))
if p.LastEnrichmentAttemptAt != nil {
row("Last attempt:", p.LastEnrichmentAttemptAt.Format("2006-01-02 15:04:05"))
}
row("Created:", p.CreatedAt.Format("2006-01-02 15:04:05"))