mirror of
https://github.com/hanzoai/o11y.git
synced 2026-10-15 12:58:33 +00:00
zeekay
31aa82a3c8
New pkg/modules/errortracking + pkg/types/errortrackingtypes: grouped-error
Issues over the ONE o11y plane. Occurrences stay in the telemetry store; only
non-derivable lifecycle (status/assignee/first-last-seen/count/regression) is
the net-new o11y_issues table.
- Fingerprint grouping at ingest (exception.type + normalized crash frame,
message fallback; honors client fingerprint + {{ default }}).
- Sentry-envelope + legacy /store/ ingest shim -> normalize -> upsert issue.
Public routes (OpenAccess) authenticated by the DSN public key
(HMAC-SHA256 over the org, KMS platform secret, constant-time, fail-closed);
org resolved from the DSN project via iamidentn's exact UUIDv5 so ingest and
the IAM read align. No gateway change: DSN path /v1/o11y/<org> makes the SDK
POST /v1/o11y/api/<org>/envelope/, which the existing mount forwards.
- Read routes (ListIssues/GetIssue/UpdateIssue) behind Hanzo IAM authz,
org-scoped in SQL EXACTLY like llmobs (Where org_id = ?, fail-closed).
- Occurrence sink seam (default no-op; ClickHouse o11y_logs writer gated).
- 100_add_error_tracking migration: o11y_issues + unique (org_id,fingerprint).
- Tests (54): two-org isolation, upsert grouping, regression reopen, DSN auth
(accept/reject/cross-org/disabled), fingerprint stability, envelope/store
parsing (gzip/deflate), normalize (ts/message/tags/exception polymorphism).
83 lines
4.0 KiB
Go
83 lines
4.0 KiB
Go
package implerrortracking
|
|
|
|
import (
|
|
"testing"
|
|
|
|
"github.com/hanzoai/o11y/pkg/types/errortrackingtypes"
|
|
"github.com/stretchr/testify/assert"
|
|
"github.com/stretchr/testify/require"
|
|
)
|
|
|
|
func frame(fn, module, file string, inApp bool) errortrackingtypes.Frame {
|
|
return errortrackingtypes.Frame{Function: fn, Module: module, Filename: file, InApp: inApp}
|
|
}
|
|
|
|
// Same crash site (type + top frame) groups even when the message varies.
|
|
func TestFingerprint_GroupsBySameCrashFrame(t *testing.T) {
|
|
a := &errortrackingtypes.Occurrence{Type: "ValueError", Value: "id 12 bad", Frames: []errortrackingtypes.Frame{frame("handle", "app.svc", "svc.py", true)}}
|
|
b := &errortrackingtypes.Occurrence{Type: "ValueError", Value: "id 999 bad", Frames: []errortrackingtypes.Frame{frame("handle", "app.svc", "svc.py", true)}}
|
|
assert.Equal(t, computeFingerprint(a, nil), computeFingerprint(b, nil), "same type+frame must group regardless of message")
|
|
}
|
|
|
|
func TestFingerprint_DistinctForDifferentTypes(t *testing.T) {
|
|
a := &errortrackingtypes.Occurrence{Type: "ValueError", Frames: []errortrackingtypes.Frame{frame("handle", "app.svc", "svc.py", true)}}
|
|
b := &errortrackingtypes.Occurrence{Type: "KeyError", Frames: []errortrackingtypes.Frame{frame("handle", "app.svc", "svc.py", true)}}
|
|
assert.NotEqual(t, computeFingerprint(a, nil), computeFingerprint(b, nil))
|
|
}
|
|
|
|
// The crash frame is the innermost in-app frame (Sentry orders caller→callee).
|
|
func TestFingerprint_PicksInnermostInAppFrame(t *testing.T) {
|
|
frames := []errortrackingtypes.Frame{
|
|
frame("main", "app", "main.go", true),
|
|
frame("libcall", "vendor.lib", "lib.go", false),
|
|
frame("crashHere", "app.worker", "worker.go", true),
|
|
frame("runtimePanic", "runtime", "panic.go", false),
|
|
}
|
|
got := pickCrashFrame(frames)
|
|
require.NotNil(t, got)
|
|
assert.Equal(t, "crashHere", got.Function, "innermost in-app frame is the crash site, not the runtime frame")
|
|
}
|
|
|
|
// Message-only errors group by normalized message (numbers/uuids masked).
|
|
func TestFingerprint_MessageFallbackMasksVariadic(t *testing.T) {
|
|
a := &errortrackingtypes.Occurrence{Type: "Message", Value: "user 123 not found in shard 7"}
|
|
b := &errortrackingtypes.Occurrence{Type: "Message", Value: "user 456 not found in shard 9"}
|
|
assert.Equal(t, computeFingerprint(a, nil), computeFingerprint(b, nil))
|
|
|
|
c := &errortrackingtypes.Occurrence{Type: "Message", Value: "totally different failure"}
|
|
assert.NotEqual(t, computeFingerprint(a, nil), computeFingerprint(c, nil))
|
|
}
|
|
|
|
func TestFingerprint_CustomHonored(t *testing.T) {
|
|
a := &errortrackingtypes.Occurrence{Type: "ValueError", Value: "x"}
|
|
b := &errortrackingtypes.Occurrence{Type: "KeyError", Value: "y"}
|
|
// Same explicit fingerprint => same group despite different types.
|
|
assert.Equal(t, computeFingerprint(a, []string{"my-group"}), computeFingerprint(b, []string{"my-group"}))
|
|
assert.NotEqual(t, computeFingerprint(a, []string{"g1"}), computeFingerprint(a, []string{"g2"}))
|
|
}
|
|
|
|
// "{{ default }}" expands to the computed default, so ["{{ default }}", "tenant"]
|
|
// subdivides the default group by tenant.
|
|
func TestFingerprint_DefaultTokenExpands(t *testing.T) {
|
|
occ := &errortrackingtypes.Occurrence{Type: "ValueError", Frames: []errortrackingtypes.Frame{frame("h", "m", "f.go", true)}}
|
|
base := computeFingerprint(occ, nil)
|
|
withToken := computeFingerprint(occ, []string{defaultFingerprintToken})
|
|
assert.Equal(t, base, withToken, "bare {{ default }} equals the default fingerprint")
|
|
|
|
subdivided := computeFingerprint(occ, []string{defaultFingerprintToken, "tenant-a"})
|
|
assert.NotEqual(t, base, subdivided, "adding a component must change the group")
|
|
}
|
|
|
|
func TestNormalizeMessage_Masks(t *testing.T) {
|
|
assert.Equal(t, normalizeMessage("id 42 at 0xdeadbeef"), normalizeMessage("id 7 at 0xcafef00d"))
|
|
assert.Equal(t,
|
|
normalizeMessage("row 550e8400-e29b-41d4-a716-446655440000 gone"),
|
|
normalizeMessage("row 550e8400-e29b-41d4-a716-000000000000 gone"),
|
|
)
|
|
}
|
|
|
|
func TestFingerprint_IsHex(t *testing.T) {
|
|
fp := computeFingerprint(&errortrackingtypes.Occurrence{Type: "E"}, nil)
|
|
assert.Len(t, fp, 64)
|
|
}
|