* 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>
167 lines
4.8 KiB
Go
167 lines
4.8 KiB
Go
package logredact
|
|
|
|
import (
|
|
"bytes"
|
|
"context"
|
|
"encoding/json"
|
|
"log/slog"
|
|
"strings"
|
|
"testing"
|
|
"testing/slogtest"
|
|
)
|
|
|
|
func TestSlogtestConformance(t *testing.T) {
|
|
var buf bytes.Buffer
|
|
h := New(slog.NewJSONHandler(&buf, nil))
|
|
results := func() []map[string]any {
|
|
var ms []map[string]any
|
|
for _, line := range bytes.Split(bytes.TrimSpace(buf.Bytes()), []byte{'\n'}) {
|
|
if len(line) == 0 {
|
|
continue
|
|
}
|
|
var m map[string]any
|
|
if err := json.Unmarshal(line, &m); err != nil {
|
|
t.Fatalf("unmarshal %q: %v", line, err)
|
|
}
|
|
ms = append(ms, m)
|
|
}
|
|
return ms
|
|
}
|
|
if err := slogtest.TestHandler(h, results); err != nil {
|
|
t.Fatalf("slogtest: %v", err)
|
|
}
|
|
}
|
|
|
|
func TestSecretKey(t *testing.T) {
|
|
for _, k := range []string{"password", "api_key", "apiKey", "X-Authorization", "session_token", "Cookie", "client_secret"} {
|
|
if !SecretKey(k) {
|
|
t.Errorf("SecretKey(%q) = false, want true", k)
|
|
}
|
|
}
|
|
for _, k := range []string{"user_id", "request_id", "component", "folder", "count"} {
|
|
if SecretKey(k) {
|
|
t.Errorf("SecretKey(%q) = true, want false", k)
|
|
}
|
|
}
|
|
}
|
|
|
|
func logAndCapture(t *testing.T, fn func(l *slog.Logger)) map[string]any {
|
|
t.Helper()
|
|
var buf bytes.Buffer
|
|
base := slog.NewJSONHandler(&buf, nil)
|
|
l := slog.New(New(base))
|
|
fn(l)
|
|
var out map[string]any
|
|
if err := json.Unmarshal(buf.Bytes(), &out); err != nil {
|
|
t.Fatalf("unmarshal: %v (raw: %s)", err, buf.String())
|
|
}
|
|
return out
|
|
}
|
|
|
|
func TestHandlerRedactsRecordAttr(t *testing.T) {
|
|
out := logAndCapture(t, func(l *slog.Logger) {
|
|
l.InfoContext(context.Background(), "auth", "user_id", 7, "api_token", "s3cr3t")
|
|
})
|
|
if out["api_token"] != Placeholder {
|
|
t.Errorf("api_token = %v, want %s", out["api_token"], Placeholder)
|
|
}
|
|
if out["user_id"].(float64) != 7 {
|
|
t.Errorf("user_id = %v, want 7 (non-secret must pass through)", out["user_id"])
|
|
}
|
|
if strings.Contains(out["api_token"].(string), "s3cr3t") {
|
|
t.Error("secret value leaked")
|
|
}
|
|
}
|
|
|
|
func TestHandlerRedactsWithAttrs(t *testing.T) {
|
|
out := logAndCapture(t, func(l *slog.Logger) {
|
|
l.With("password", "hunter2", "component", "auth").InfoContext(context.Background(), "bound")
|
|
})
|
|
if out["password"] != Placeholder {
|
|
t.Errorf("bound password = %v, want %s", out["password"], Placeholder)
|
|
}
|
|
if out["component"] != "auth" {
|
|
t.Errorf("component = %v, want auth", out["component"])
|
|
}
|
|
}
|
|
|
|
func TestHandlerRedactsGroup(t *testing.T) {
|
|
out := logAndCapture(t, func(l *slog.Logger) {
|
|
l.InfoContext(context.Background(), "grp", slog.Group("creds", "authorization", "Bearer x", "kind", "oauth"))
|
|
})
|
|
creds, ok := out["creds"].(map[string]any)
|
|
if !ok {
|
|
t.Fatalf("creds group missing: %v", out)
|
|
}
|
|
if creds["authorization"] != Placeholder {
|
|
t.Errorf("grouped authorization = %v, want %s", creds["authorization"], Placeholder)
|
|
}
|
|
if creds["kind"] != "oauth" {
|
|
t.Errorf("grouped kind = %v, want oauth", creds["kind"])
|
|
}
|
|
}
|
|
|
|
func TestHandlerRedactsSecretGroupKey(t *testing.T) {
|
|
// A group whose OWN key is a secret marker must have its entire subtree
|
|
// masked, not just secret leaf keys within it.
|
|
out := logAndCapture(t, func(l *slog.Logger) {
|
|
l.InfoContext(context.Background(), "x",
|
|
slog.Group("authorization", "scheme", "Bearer", "value", "abc123SECRET"))
|
|
})
|
|
if out["authorization"] != Placeholder {
|
|
t.Errorf("secret group key = %v, want %s (whole subtree masked)", out["authorization"], Placeholder)
|
|
}
|
|
if strings.Contains(mustJSON(t, out), "abc123SECRET") {
|
|
t.Error("secret value leaked from secret-keyed group")
|
|
}
|
|
}
|
|
|
|
type secretValuer struct{ tok string }
|
|
|
|
func (s secretValuer) LogValue() slog.Value {
|
|
return slog.GroupValue(slog.String("token", s.tok))
|
|
}
|
|
|
|
func TestHandlerResolvesLogValuer(t *testing.T) {
|
|
out := logAndCapture(t, func(l *slog.Logger) {
|
|
l.InfoContext(context.Background(), "x", "creds", secretValuer{tok: "abc123SECRET"})
|
|
})
|
|
if strings.Contains(mustJSON(t, out), "abc123SECRET") {
|
|
t.Errorf("secret behind LogValuer leaked: %v", out)
|
|
}
|
|
}
|
|
|
|
func TestHandlerRedactsUnderWithGroup(t *testing.T) {
|
|
out := logAndCapture(t, func(l *slog.Logger) {
|
|
l.WithGroup("req").InfoContext(context.Background(), "x", "api_key", "abc123SECRET", "path", "/v1")
|
|
})
|
|
req, ok := out["req"].(map[string]any)
|
|
if !ok {
|
|
t.Fatalf("req group missing: %v", out)
|
|
}
|
|
if req["api_key"] != Placeholder {
|
|
t.Errorf("api_key under WithGroup = %v, want %s", req["api_key"], Placeholder)
|
|
}
|
|
if req["path"] != "/v1" {
|
|
t.Errorf("path under WithGroup = %v, want /v1", req["path"])
|
|
}
|
|
}
|
|
|
|
func mustJSON(t *testing.T, v any) string {
|
|
t.Helper()
|
|
b, err := json.Marshal(v)
|
|
if err != nil {
|
|
t.Fatalf("marshal: %v", err)
|
|
}
|
|
return string(b)
|
|
}
|
|
|
|
func TestHandlerPassThroughWhenClean(t *testing.T) {
|
|
out := logAndCapture(t, func(l *slog.Logger) {
|
|
l.InfoContext(context.Background(), "clean", "user_id", 1, "component", "api")
|
|
})
|
|
if out["user_id"].(float64) != 1 || out["component"] != "api" {
|
|
t.Errorf("clean record altered: %v", out)
|
|
}
|
|
}
|