* feat(observability): OpenTelemetry logs+traces with secret redaction Part of #265. Adds opt-in OpenTelemetry (logs + traces) alongside the existing stderr + opslog pipeline, plus secret redaction on all sinks. Default-off: with no OTEL_* / SILO_OTEL_ENABLED config, behavior is unchanged. Bootstrap (internal/telemetry): - Setup() builds one shared resource, a TracerProvider (parent-based trace-id ratio sampler), a LoggerProvider, and the W3C TraceContext+Baggage propagator from env. It installs NO MeterProvider — metrics stay on Prometheus, and the built-in no-op global MeterProvider keeps the trace instrumentation libs from double-emitting. Shutdown is deferred with a flush timeout. - Logs are bridged via otelslog fan-out (slog.MultiHandler), level-gated by the shared LevelVar and best-effort so a failing collector can't break the console or DB branches. stderr + opslog stay untouched. Secret redaction (internal/logredact): - A slog.Handler masks secret-keyed attributes (password, token, api_key, authorization, cookie, ...) — including .With-bound attrs, nested groups, secret-keyed group subtrees, and values behind a LogValuer — on the console and OTLP sinks, with a no-op fast path when a record has no secret keys. opslog.shouldRedact delegates to logredact.SecretKey so all sinks share one marker list. Rotation is infra-managed (no custom file sink): container runtime for stderr, collector/backend for OTLP, opslog partition-pruning for the DB. Documented in docs/architecture/observability.md. Verification: go build ./..., go vet, gofmt -l — clean; go test ./internal/telemetry/ ./internal/logredact/ -race pass. AI-use disclosure: implemented with AI assistance (Claude Code), including adversarial reviews that hardened the bootstrap and fixed two redaction leak paths; reviewed by the author. * refactor(observability): slog context+component sweep, sloglint gate (phase 3) Part of #265. Builds on the OTel bootstrap + redaction commit. Standardizes every log call site onto the context-carrying slog variants so records correlate with the active OpenTelemetry trace, and locks the standard in with a machine gate so future code (human- or AI-authored) can't drift back. - Call-site sweep: converted the remaining slog.<Level>(...) calls to the slog.<Level>Context(ctx, ...) form wherever a context.Context is in scope (background/init calls with no ctx are left as-is), across 183 files. Applied via a type-aware AST codemod. Log levels and message strings are preserved verbatim; a component attr (canonical per-package name) is added to direct package-level slog calls. Bound-logger calls keep their existing .With bindings. The main.go and telemetry package conversions rode with their file in the previous commit to keep each file within a single commit. - Enforcement (.golangci.yml): enable sloglint with context=scope, static-msg, key-naming-case=snake, no-mixed-args. After the sweep all four report zero violations repo-wide (tests included), so make lint / CI now blocks any regression to the non-context form. The gate ships with the sweep because it cannot be green until the legacy sites are converted. Metrics remain on Prometheus; no behavior change to /metrics or Grafana. Verification: go build ./..., go vet ./..., gofmt -l — clean; sloglint (all 4 rules) 0 violations repo-wide; log levels verified unchanged. AI-use disclosure: implemented with AI assistance (Claude Code), including the codemod; reviewed by the author. * fix(observability): honor per-signal OTLP protocol and secret WithGroup names Two Codex review findings on PR #290: - telemetry: OTEL_EXPORTER_OTLP_{TRACES,LOGS}_PROTOCOL now override the generic OTEL_EXPORTER_OTLP_PROTOCOL per signal, so mixed collector setups (e.g. HTTP logs + gRPC traces) build the right exporter. - logredact: entering a group whose name is secret-bearing (e.g. WithGroup("authorization")) now masks every leaf in that subtree, matching how slog.Group("authorization", ...) is masked as a whole. * fix(observability): address review feedback on telemetry bootstrap - Telemetry setup failure no longer kills boot: Setup returns usable no-op providers alongside the error and main logs and continues with telemetry disabled, honoring the best-effort contract. - Honor OTEL_TRACES_SAMPLER (always_on/off, traceidratio, parentbased_* variants); unsupported values fall back to parentbased_traceidratio. - Attach node identity as semconv service.instance.id instead of the non-semconv node.name. - Rename opslog retention-scope log attrs to target_component/target_level so they no longer collide with the canonical component routing key, and tag those lines with component=opslog. - Fix stale levelGated comment casing; use WarnContext in the telemetry shutdown defer; document the LogValuer double-resolve on the redaction slow path. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> --------- Co-authored-by: Quick <31828688+Quick104@users.noreply.github.com> Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
102 lines
2.6 KiB
Go
102 lines
2.6 KiB
Go
package catalog
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"fmt"
|
|
"log/slog"
|
|
"time"
|
|
|
|
"github.com/jackc/pgx/v5/pgxpool"
|
|
)
|
|
|
|
type SmartCountRefresher struct {
|
|
Pool *pgxpool.Pool
|
|
Executor *QueryExecutor
|
|
}
|
|
|
|
func (r *SmartCountRefresher) RefreshAll(ctx context.Context) (refreshed int, errs int) {
|
|
if r == nil || r.Pool == nil || r.Executor == nil {
|
|
return 0, 0
|
|
}
|
|
rows, err := r.Pool.Query(ctx, `
|
|
SELECT id, query_definition
|
|
FROM library_collections
|
|
WHERE collection_type = 'smart'
|
|
`)
|
|
if err != nil {
|
|
slog.WarnContext(ctx, "smart-count refresher: list query failed", "component", "catalog", "error", err)
|
|
return 0, 1
|
|
}
|
|
defer rows.Close()
|
|
|
|
type entry struct {
|
|
id string
|
|
def []byte
|
|
}
|
|
var batch []entry
|
|
for rows.Next() {
|
|
var e entry
|
|
if err := rows.Scan(&e.id, &e.def); err != nil {
|
|
slog.WarnContext(ctx, "smart-count refresher: scan failed", "component", "catalog", "error", err)
|
|
return refreshed, errs + 1
|
|
}
|
|
batch = append(batch, e)
|
|
}
|
|
if err := rows.Err(); err != nil {
|
|
slog.WarnContext(ctx, "smart-count refresher: row iter failed", "component", "catalog", "error", err)
|
|
return refreshed, errs + 1
|
|
}
|
|
|
|
for _, e := range batch {
|
|
if err := r.refreshOne(ctx, e.id, e.def); err != nil {
|
|
slog.WarnContext(ctx, "smart-count refresher: collection failed", "component", "catalog", "collection_id", e.id, "error", err)
|
|
errs++
|
|
continue
|
|
}
|
|
refreshed++
|
|
}
|
|
return refreshed, errs
|
|
}
|
|
|
|
func (r *SmartCountRefresher) RefreshOne(ctx context.Context, collectionID string) error {
|
|
if r == nil || r.Pool == nil || r.Executor == nil {
|
|
return nil
|
|
}
|
|
var def []byte
|
|
var typ string
|
|
if err := r.Pool.QueryRow(ctx, `
|
|
SELECT collection_type, query_definition
|
|
FROM library_collections
|
|
WHERE id = $1
|
|
`, collectionID).Scan(&typ, &def); err != nil {
|
|
return fmt.Errorf("loading collection: %w", err)
|
|
}
|
|
if typ != "smart" {
|
|
return nil
|
|
}
|
|
return r.refreshOne(ctx, collectionID, def)
|
|
}
|
|
|
|
func (r *SmartCountRefresher) refreshOne(ctx context.Context, id string, defJSON []byte) error {
|
|
var def QueryDefinition
|
|
if err := json.Unmarshal(defJSON, &def); err != nil {
|
|
return fmt.Errorf("unmarshal query_definition: %w", err)
|
|
}
|
|
def = ApplySmartCollectionItemLimit(def.Normalize())
|
|
queryCtx, cancel := context.WithTimeout(ctx, 30*time.Second)
|
|
defer cancel()
|
|
_, total, err := r.Executor.Preview(queryCtx, def, AccessFilter{}, 1)
|
|
if err != nil {
|
|
return fmt.Errorf("preview: %w", err)
|
|
}
|
|
if _, err := r.Pool.Exec(ctx, `
|
|
UPDATE library_collections
|
|
SET item_count_cached = $1, item_count_cached_at = NOW()
|
|
WHERE id = $2
|
|
`, total, id); err != nil {
|
|
return fmt.Errorf("update cache: %w", err)
|
|
}
|
|
return nil
|
|
}
|