* 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>
122 lines
3.2 KiB
Go
122 lines
3.2 KiB
Go
package requests
|
|
|
|
import (
|
|
"context"
|
|
"log/slog"
|
|
"strconv"
|
|
"strings"
|
|
|
|
"github.com/Silo-Server/silo-server/internal/catalog"
|
|
)
|
|
|
|
type PresenceCandidate struct {
|
|
TMDBID int
|
|
TVDBID *int
|
|
IMDbID string
|
|
}
|
|
|
|
type PresenceMatch struct {
|
|
Available bool
|
|
ContentID string
|
|
MatchedProvider string
|
|
}
|
|
|
|
type PresenceResolver interface {
|
|
Lookup(ctx context.Context, mediaType MediaType, candidates []PresenceCandidate) (map[int]PresenceMatch, error)
|
|
}
|
|
|
|
type presenceItemLookup interface {
|
|
LookupExternalIDs(ctx context.Context, mediaType string, candidates []catalog.ExternalIDLookupCandidate) ([]catalog.ExternalIDMatchRow, error)
|
|
}
|
|
|
|
type tmdbBackfiller interface {
|
|
AttachTMDBID(ctx context.Context, contentID, itemType string, tmdbID int) error
|
|
}
|
|
|
|
type CatalogPresence struct {
|
|
items presenceItemLookup
|
|
tmdbBackfill tmdbBackfiller
|
|
}
|
|
|
|
func NewCatalogPresence(items *catalog.ItemRepository, providerIDs ...*catalog.ProviderIDRepository) *CatalogPresence {
|
|
var itemLookup presenceItemLookup
|
|
if items != nil {
|
|
itemLookup = items
|
|
}
|
|
var backfill tmdbBackfiller
|
|
if len(providerIDs) > 0 && providerIDs[0] != nil {
|
|
backfill = providerIDs[0]
|
|
}
|
|
return &CatalogPresence{items: itemLookup, tmdbBackfill: backfill}
|
|
}
|
|
|
|
func (p *CatalogPresence) Lookup(ctx context.Context, mediaType MediaType, candidates []PresenceCandidate) (map[int]PresenceMatch, error) {
|
|
out := map[int]PresenceMatch{}
|
|
if p == nil || p.items == nil || len(candidates) == 0 {
|
|
return out, nil
|
|
}
|
|
|
|
lookupCandidates := make([]catalog.ExternalIDLookupCandidate, 0, len(candidates))
|
|
for _, candidate := range candidates {
|
|
if candidate.TMDBID <= 0 {
|
|
continue
|
|
}
|
|
row := catalog.ExternalIDLookupCandidate{
|
|
TMDBID: strconv.Itoa(candidate.TMDBID),
|
|
IMDbID: strings.TrimSpace(candidate.IMDbID),
|
|
}
|
|
if candidate.TVDBID != nil && *candidate.TVDBID > 0 {
|
|
row.TVDBID = strconv.Itoa(*candidate.TVDBID)
|
|
}
|
|
lookupCandidates = append(lookupCandidates, row)
|
|
}
|
|
if len(lookupCandidates) == 0 {
|
|
return out, nil
|
|
}
|
|
|
|
rows, err := p.items.LookupExternalIDs(ctx, string(mediaType), lookupCandidates)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
for _, row := range rows {
|
|
id, err := strconv.Atoi(row.QueryTMDBID)
|
|
if err != nil || id <= 0 {
|
|
continue
|
|
}
|
|
out[id] = PresenceMatch{
|
|
Available: true,
|
|
ContentID: row.MediaID,
|
|
MatchedProvider: row.MatchedProvider,
|
|
}
|
|
if row.MatchedProvider != "tmdb" && p.tmdbBackfill != nil {
|
|
if err := p.tmdbBackfill.AttachTMDBID(ctx, row.MediaID, string(mediaType), id); err != nil {
|
|
slog.WarnContext(ctx, "requests: failed to backfill tmdb id from presence lookup", "component", "requests",
|
|
"content_id", row.MediaID,
|
|
"media_type", mediaType,
|
|
"tmdb_id", id,
|
|
"matched_provider", row.MatchedProvider,
|
|
"error", err)
|
|
}
|
|
}
|
|
}
|
|
return out, nil
|
|
}
|
|
|
|
func (p *CatalogPresence) LookupTMDB(ctx context.Context, mediaType MediaType, tmdbIDs []int) (map[int]bool, error) {
|
|
candidates := make([]PresenceCandidate, 0, len(tmdbIDs))
|
|
for _, id := range tmdbIDs {
|
|
if id > 0 {
|
|
candidates = append(candidates, PresenceCandidate{TMDBID: id})
|
|
}
|
|
}
|
|
matches, err := p.Lookup(ctx, mediaType, candidates)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
out := map[int]bool{}
|
|
for id, match := range matches {
|
|
out[id] = match.Available
|
|
}
|
|
return out, nil
|
|
}
|