Kristian WindandClaude Opus 5
c2e2d66e76
Release / Build and publish image (push) Failing after 12m56s
The panel's watcher reported four 5xx today — twice from one address at 11:49, twice from another at 10:45 — and there is no way to find out what any of them were. verdande logs the real cause of every 500, but on a Rune the log belongs to the container and the container is replaced on every restart. So an operator is told that something broke and given nothing to act on, which is the worst of both: alarming and useless. Every 500 now writes a row: what the handler was attempting in its own words, the error it hit, the method and path, who was asking, and the request id that ties it back to the log line for whoever still has it. The "what" is the part a status code cannot give — "list projects" and "move task" are the difference between a fault you can find and one you can only count. Written best-effort and never checked. This is the path that is already reporting a failure, and a diagnostic that can itself fail the request would turn one broken screen into two. Threading the request through `internal()` and `storeError()` touched 108 call sites across 19 files, which is the price of not having had it there from the start. It is mechanical and the compiler checked all of it. Kept for thirty days by the nightly sweep: long enough to answer "what happened last week", short enough that a fault loop cannot fill the volume the tasks live on. Read at Indstillinger → Fejl, administrators only — it carries paths, account names and the server's own error strings. The empty state says "Ingen fejl registreret. Det er den rigtige tilstand", because a blank panel should not read as a broken one. The test drops a table and asks for the endpoint that reads it: the same code path a disk error takes, and the row that comes back has to name the operation, the account and the request. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
78 lines
2.2 KiB
Go
78 lines
2.2 KiB
Go
package store
|
|
|
|
import (
|
|
"context"
|
|
"time"
|
|
)
|
|
|
|
// A ServerError is one 500 the API answered, kept so it can be read after the
|
|
// container that produced it has gone.
|
|
type ServerError struct {
|
|
ID string
|
|
At time.Time
|
|
Method string
|
|
Path string
|
|
Status int
|
|
What string
|
|
Message string
|
|
UserID string
|
|
UserName string
|
|
RequestID string
|
|
}
|
|
|
|
// RecordError stores one failure.
|
|
//
|
|
// Errors here are dropped rather than returned: this is called from the path that
|
|
// is already reporting a failure to somebody, and a diagnostic that can itself
|
|
// fail the request would turn one broken screen into two.
|
|
func (db *DB) RecordError(ctx context.Context, e ServerError) {
|
|
var user any
|
|
if e.UserID != "" {
|
|
user = e.UserID
|
|
}
|
|
_, _ = db.ExecContext(ctx,
|
|
`INSERT INTO error_log (id, at, method, path, status, what, message, user_id, request_id)
|
|
VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)`,
|
|
NewID(), time.Now().Unix(), e.Method, truncate(e.Path, 500), e.Status,
|
|
truncate(e.What, 200), truncate(e.Message, 2000), user, truncate(e.RequestID, 100))
|
|
}
|
|
|
|
// ListErrors returns the most recent failures, newest first.
|
|
func (db *DB) ListErrors(ctx context.Context, limit int) ([]ServerError, error) {
|
|
rows, err := db.QueryContext(ctx, `
|
|
SELECT e.id, e.at, e.method, e.path, e.status, e.what, e.message,
|
|
COALESCE(e.user_id, ''), COALESCE(u.name, ''), e.request_id
|
|
FROM error_log e
|
|
LEFT JOIN users u ON u.id = e.user_id
|
|
ORDER BY e.at DESC
|
|
LIMIT ?`, limit)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
defer rows.Close()
|
|
|
|
out := []ServerError{}
|
|
for rows.Next() {
|
|
var e ServerError
|
|
var at int64
|
|
if err := rows.Scan(&e.ID, &at, &e.Method, &e.Path, &e.Status, &e.What,
|
|
&e.Message, &e.UserID, &e.UserName, &e.RequestID); err != nil {
|
|
return nil, err
|
|
}
|
|
e.At = time.Unix(at, 0).UTC()
|
|
out = append(out, e)
|
|
}
|
|
return out, rows.Err()
|
|
}
|
|
|
|
// PurgeOldErrors is run by the nightly sweep. A diagnostic that grows without
|
|
// limit is a disk that fills for a reason nobody expected.
|
|
func (db *DB) PurgeOldErrors(ctx context.Context, keep time.Duration) (int64, error) {
|
|
res, err := db.ExecContext(ctx,
|
|
`DELETE FROM error_log WHERE at < ?`, time.Now().Add(-keep).Unix())
|
|
if err != nil {
|
|
return 0, err
|
|
}
|
|
return res.RowsAffected()
|
|
}
|