From 55e83d6bfd379a829b81ea6a14b0cec31d199f2d Mon Sep 17 00:00:00 2001 From: Admin <1+admin@noreply.git.dcntrlized.org> Date: Mon, 19 Oct 2026 02:28:59 +0100 Subject: [PATCH] [feat](alarm): hash client identifiers in stdout request logs A request log should not name a client directly, and the durable event log deliberately has no network columns. Hash the IP and user agent with internal/loghash for the stdout line; empty values stay empty rather than logging a constant digest. This is record anonymisation, not cryptographic protection, and the package says so. --- src/internal/loghash/loghash.go | 38 ++++++++++++++++++++++++++++ src/internal/loghash/loghash_test.go | 34 +++++++++++++++++++++++++ src/logger/logger.go | 3 ++- src/middleware/logger.go | 20 ++++++++++++--- 4 files changed, 91 insertions(+), 4 deletions(-) create mode 100644 src/internal/loghash/loghash.go create mode 100644 src/internal/loghash/loghash_test.go diff --git a/src/internal/loghash/loghash.go b/src/internal/loghash/loghash.go new file mode 100644 index 0000000..3df2a43 --- /dev/null +++ b/src/internal/loghash/loghash.go @@ -0,0 +1,38 @@ +// Copyright (C) 2026 Dcntrlized +// +// This program is free software: you can redistribute it and/or modify +// it under the terms of the GNU Affero General Public License as published +// by the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// This program is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU Affero General Public License for more details. +// +// You should have received a copy of the GNU Affero General Public License +// along with this program. If not, see . + +// Package loghash anonymises client identifiers for stdout request lines: plain +// SHA-256 hex, no salt, no key, no work factor (user ruling: keep it simple). +// +// Honest limitation, recorded so nobody mistakes it for more than it is: a plain +// digest of a low-entropy value such as an IPv4 address is enumerable by anyone +// who can run 2^32 hashes. This anonymises *records* (a log dump does not +// directly name a client); it is not cryptographic protection. +package loghash + +import ( + "crypto/sha256" + "encoding/hex" +) + +// Hash returns the SHA-256 hex digest of raw, or "" for an empty value so callers +// can omit the field rather than log a constant digest. +func Hash(raw string) string { + if raw == "" { + return "" + } + sum := sha256.Sum256([]byte(raw)) + return hex.EncodeToString(sum[:]) +} diff --git a/src/internal/loghash/loghash_test.go b/src/internal/loghash/loghash_test.go new file mode 100644 index 0000000..f648909 --- /dev/null +++ b/src/internal/loghash/loghash_test.go @@ -0,0 +1,34 @@ +// Copyright (C) 2026 Dcntrlized +// +// This program is free software: you can redistribute it and/or modify +// it under the terms of the GNU Affero General Public License as published +// by the Free Software Foundation, either version 3 of the License, or +// (at your option) any later version. +// +// This program is distributed in the hope that it will be useful, +// but WITHOUT ANY WARRANTY; without even the implied warranty of +// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +// GNU Affero General Public License for more details. +// +// You should have received a copy of the GNU Affero General Public License +// along with this program. If not, see . + +package loghash + +import "testing" + +func TestHashIsStableSha256(t *testing.T) { + got := Hash("192.0.2.10") + if len(got) != 64 { + t.Fatalf("digest length = %d, want 64 hex chars", len(got)) + } + if got != Hash("192.0.2.10") { + t.Fatal("hash is not stable") + } + if Hash("192.0.2.11") == got { + t.Fatal("different addresses collided") + } + if Hash("") != "" { + t.Fatal("empty identifier should map to empty") + } +} diff --git a/src/logger/logger.go b/src/logger/logger.go index c728c50..2832dd5 100644 --- a/src/logger/logger.go +++ b/src/logger/logger.go @@ -157,7 +157,8 @@ func Warn(format string, v ...any) { func Error(format string, v ...any) { once.Do(initLogger) file, line := callSite() - errorLogger.Output(0, fmt.Sprintf("%s:%d: %s", filepath.Base(file), line, fmt.Sprintf(format, v...))) + msg := fmt.Sprintf(format, v...) + errorLogger.Output(0, fmt.Sprintf("%s:%d: %s", filepath.Base(file), line, msg)) } // Debug accepts a format string and an optional, arbitrary number of arguments. diff --git a/src/middleware/logger.go b/src/middleware/logger.go index fce9f7c..ca2b399 100644 --- a/src/middleware/logger.go +++ b/src/middleware/logger.go @@ -17,11 +17,13 @@ package middleware import ( "bufio" + "fmt" "net" "net/http" "strings" "time" + "git.dcntrlized.org/Dcntrlized/Alarm/internal/loghash" "git.dcntrlized.org/Dcntrlized/Alarm/logger" ) @@ -49,19 +51,31 @@ func LoggingMiddleware(next http.Handler) http.Handler { rec := &statusRecorder{ResponseWriter: w, status: http.StatusOK} next.ServeHTTP(rec, r) - logger.Info("%s request=%s %s path=%s status=%d ua=%q ip=%s duration=%s", + // Identifiers are not written in the clear on stdout: IP and user agent + // go through plain SHA-256 (internal/loghash). They never reach durable + // storage at all — the event_log table has no network columns. + ipHash, uaHash := hashClient(ip, r.UserAgent()) + line := fmt.Sprintf("%s request=%s %s path=%s status=%d ua=%s ip=%s duration=%s", time.Now().Format(time.RFC3339), r.Method, r.Proto, r.URL.Path, rec.status, - r.UserAgent(), - ip, + uaHash, + ipHash, time.Since(start), ) + logger.Info("%s", line) }) } +// hashClient anonymises request identifiers for stdout. The durable event log +// never stores network identifiers at all; this is only so a stdout request line +// does not name a client directly. +func hashClient(ip, ua string) (ipHash, uaHash string) { + return loghash.Hash(ip), loghash.Hash(ua) +} + // statusRecorder captures the response status without altering the response. // It preserves http.Hijacker so the /ws/alarm upgrade still works when the // route is mounted behind this middleware.