Add common catalog query layer and enricher service

Introduce an API-style data layer for the global common tracker pattern
and common third party catalogs: typed filters, order fields, CursorKey,
cursor-paginated Load and CountAll, plus by-id enrichment re-queue and a
scoped reset/remap helper for a banner's tracker patterns. These reuse
the same page.Cursor/filter/order types the GraphQL API consumes, so a
future proboctl API can back them unchanged.

Extract the common-pattern enrichment logic out of the worker into a
CommonPatternEnricher service so it can run either from the background
queue or synchronously over a known set of ids; the worker becomes a
thin poller that delegates to it.

Extract the LLM client and tracker-agents config wiring into
pkg/agentsbuild so probod and other binaries build agents identically;
probod now delegates to it.

Signed-off-by: Émile Ré <emile@probo.com>
This commit is contained in:
Émile Ré
2026-06-03 13:37:36 +02:00
parent aebb2a1ed0
commit 662c0ae428
13 changed files with 1452 additions and 335 deletions

View File

@@ -295,6 +295,99 @@ LIMIT @limit;
return ids, nil
}
// LoadAllByTrackerPatternID returns every detected tracker linked to the
// pattern, with no pagination. It backs the banner-reset rebuild, which
// recreates exact patterns from a glob's detections.
func (dts *DetectedTrackers) LoadAllByTrackerPatternID(
ctx context.Context,
conn pg.Querier,
scope Scoper,
trackerPatternID gid.GID,
) error {
q := `
SELECT
id,
cookie_banner_id,
tracker_pattern_id,
tracker_type,
identifier,
max_age_seconds,
source,
value_size,
initiator_url,
initiator_domain,
last_detected_at,
created_at,
updated_at
FROM
detected_trackers
WHERE
%s
AND tracker_pattern_id = @tracker_pattern_id
ORDER BY
identifier ASC, id ASC
`
q = fmt.Sprintf(q, scope.SQLFragment())
args := pgx.StrictNamedArgs{"tracker_pattern_id": trackerPatternID}
maps.Copy(args, scope.SQLArguments())
rows, err := conn.Query(ctx, q, args)
if err != nil {
return fmt.Errorf("cannot query detected trackers: %w", err)
}
trackers, err := pgx.CollectRows(rows, pgx.RowToAddrOfStructByName[DetectedTracker])
if err != nil {
return fmt.Errorf("cannot collect detected trackers: %w", err)
}
*dts = trackers
return nil
}
// UpdateTrackerPatternID repoints a single detected tracker at another
// pattern. It is the per-row counterpart of RelinkByTrackerPatternID,
// used by the banner-reset rebuild where each detection of a glob moves
// to its own recreated exact pattern.
func (dt *DetectedTracker) UpdateTrackerPatternID(
ctx context.Context,
tx pg.Tx,
scope Scoper,
) error {
q := `
UPDATE detected_trackers
SET
tracker_pattern_id = @tracker_pattern_id,
updated_at = @updated_at
WHERE
%s
AND id = @id
`
q = fmt.Sprintf(q, scope.SQLFragment())
args := pgx.StrictNamedArgs{
"id": dt.ID,
"tracker_pattern_id": dt.TrackerPatternID,
"updated_at": time.Now(),
}
maps.Copy(args, scope.SQLArguments())
result, err := tx.Exec(ctx, q, args)
if err != nil {
return fmt.Errorf("cannot update detected tracker pattern: %w", err)
}
if result.RowsAffected() == 0 {
return ErrResourceNotFound
}
return nil
}
func (dts *DetectedTrackers) RelinkByTrackerPatternID(
ctx context.Context,
tx pg.Tx,