* 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>
203 lines
4.6 KiB
Go
203 lines
4.6 KiB
Go
package opslog
|
|
|
|
import (
|
|
"context"
|
|
"log/slog"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/Silo-Server/silo-server/internal/logredact"
|
|
)
|
|
|
|
type Handler struct {
|
|
inner slog.Handler
|
|
writer Writer
|
|
capture slog.Level
|
|
nodeID string
|
|
static map[string]any
|
|
groupNames []string
|
|
}
|
|
|
|
func NewHandler(inner slog.Handler, writer Writer, capture slog.Level, nodeID string) slog.Handler {
|
|
return &Handler{
|
|
inner: inner,
|
|
writer: writer,
|
|
capture: capture,
|
|
nodeID: nodeID,
|
|
static: map[string]any{},
|
|
}
|
|
}
|
|
|
|
func (h *Handler) Enabled(ctx context.Context, level slog.Level) bool {
|
|
return h.inner.Enabled(ctx, level) || level >= h.capture
|
|
}
|
|
|
|
func (h *Handler) Handle(ctx context.Context, r slog.Record) error {
|
|
if err := h.inner.Handle(ctx, r); err != nil {
|
|
return err
|
|
}
|
|
if h.writer == nil || r.Level < h.capture {
|
|
return nil
|
|
}
|
|
|
|
attrs := make(map[string]any, len(h.static)+8)
|
|
for k, v := range h.static {
|
|
attrs[k] = v
|
|
}
|
|
r.Attrs(func(attr slog.Attr) bool {
|
|
h.addAttr(attrs, attr, "")
|
|
return true
|
|
})
|
|
attrs = redactAttrs(attrs)
|
|
|
|
component, _ := attrs["component"].(string)
|
|
if component == "" {
|
|
component = inferComponent(r.Message)
|
|
}
|
|
requestID, _ := attrs["request_id"].(string)
|
|
sessionID, _ := attrs["session_id"].(string)
|
|
playbackSessionID, _ := attrs["playback_session_id"].(string)
|
|
clientIP, _ := attrs["client_ip"].(string)
|
|
if clientIP == "" {
|
|
clientIP, _ = attrs["remote_addr"].(string)
|
|
}
|
|
nodeID := h.nodeID
|
|
if attrNodeID, _ := attrs["node_id"].(string); attrNodeID != "" {
|
|
nodeID = attrNodeID
|
|
}
|
|
var userID *int
|
|
switch v := attrs["user_id"].(type) {
|
|
case int:
|
|
value := v
|
|
userID = &value
|
|
case int64:
|
|
value := int(v)
|
|
userID = &value
|
|
case float64:
|
|
value := int(v)
|
|
userID = &value
|
|
}
|
|
|
|
h.writer.Write(Entry{
|
|
Timestamp: time.Now().UTC(),
|
|
Level: strings.ToLower(r.Level.String()),
|
|
Component: component,
|
|
Message: r.Message,
|
|
RequestID: requestID,
|
|
UserID: userID,
|
|
SessionID: sessionID,
|
|
PlaybackSessionID: playbackSessionID,
|
|
ClientIP: clientIP,
|
|
NodeID: nodeID,
|
|
Attrs: attrs,
|
|
})
|
|
return nil
|
|
}
|
|
|
|
func (h *Handler) WithAttrs(attrs []slog.Attr) slog.Handler {
|
|
next := &Handler{
|
|
inner: h.inner.WithAttrs(attrs),
|
|
writer: h.writer,
|
|
capture: h.capture,
|
|
nodeID: h.nodeID,
|
|
static: map[string]any{},
|
|
groupNames: append([]string(nil), h.groupNames...),
|
|
}
|
|
for k, v := range h.static {
|
|
next.static[k] = v
|
|
}
|
|
for _, attr := range attrs {
|
|
next.addAttr(next.static, attr, "")
|
|
}
|
|
return next
|
|
}
|
|
|
|
func (h *Handler) WithGroup(name string) slog.Handler {
|
|
return &Handler{
|
|
inner: h.inner.WithGroup(name),
|
|
writer: h.writer,
|
|
capture: h.capture,
|
|
nodeID: h.nodeID,
|
|
static: cloneMap(h.static),
|
|
groupNames: append(append([]string(nil), h.groupNames...), name),
|
|
}
|
|
}
|
|
|
|
func (h *Handler) addAttr(dst map[string]any, attr slog.Attr, prefix string) {
|
|
attr.Value = attr.Value.Resolve()
|
|
key := attr.Key
|
|
if prefix != "" {
|
|
key = prefix + "." + key
|
|
}
|
|
if len(h.groupNames) > 0 && prefix == "" {
|
|
key = strings.Join(append(append([]string(nil), h.groupNames...), attr.Key), ".")
|
|
}
|
|
if attr.Value.Kind() == slog.KindGroup {
|
|
nextPrefix := key
|
|
for _, child := range attr.Value.Group() {
|
|
h.addAttr(dst, child, nextPrefix)
|
|
}
|
|
return
|
|
}
|
|
dst[key] = attrValue(attr.Value)
|
|
}
|
|
|
|
func attrValue(v slog.Value) any {
|
|
switch v.Kind() {
|
|
case slog.KindString:
|
|
return v.String()
|
|
case slog.KindInt64:
|
|
return v.Int64()
|
|
case slog.KindUint64:
|
|
return v.Uint64()
|
|
case slog.KindFloat64:
|
|
return v.Float64()
|
|
case slog.KindBool:
|
|
return v.Bool()
|
|
case slog.KindDuration:
|
|
return v.Duration().String()
|
|
case slog.KindTime:
|
|
return v.Time().UTC().Format(time.RFC3339Nano)
|
|
case slog.KindAny:
|
|
return v.Any()
|
|
default:
|
|
return v.String()
|
|
}
|
|
}
|
|
|
|
func inferComponent(message string) string {
|
|
if prefix, _, ok := strings.Cut(message, ":"); ok {
|
|
prefix = strings.TrimSpace(prefix)
|
|
if prefix != "" {
|
|
return prefix
|
|
}
|
|
}
|
|
return "app"
|
|
}
|
|
|
|
func redactAttrs(attrs map[string]any) map[string]any {
|
|
redacted := make(map[string]any, len(attrs))
|
|
for k, v := range attrs {
|
|
if shouldRedact(k) {
|
|
redacted[k] = "[REDACTED]"
|
|
continue
|
|
}
|
|
redacted[k] = v
|
|
}
|
|
return redacted
|
|
}
|
|
|
|
// shouldRedact delegates to the shared logredact detection so the DB path and
|
|
// the console/file/OTLP sinks stay in lock-step on what counts as a secret key.
|
|
func shouldRedact(key string) bool {
|
|
return logredact.SecretKey(key)
|
|
}
|
|
|
|
func cloneMap(src map[string]any) map[string]any {
|
|
dst := make(map[string]any, len(src))
|
|
for k, v := range src {
|
|
dst[k] = v
|
|
}
|
|
return dst
|
|
}
|