telemetry: fix log deduplication — strip ANSI codes, tz offsets, mid-line timestamps (v0.30.6)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

CHANGELOG.md

@@ -1,5 +1,15 @@
 ## Changelog
 
+### v0.30.6 — Telemetry: Better Log Deduplication (2026-02-25)
+
+#### Fixed
+- **ANSI escape code stripping** — Log scanner now strips ANSI color codes (e.g. `\x1b[35m`) before classifying and fingerprinting lines, preventing color codes from polluting error messages and breaking deduplication
+- **Timezone offset in timestamps** — ISO timestamp regex now handles `+01:00`/`-0500` timezone offsets and optional trailing colons (fixes Vikunja-style log entries)
+- **Mid-line timestamps** — Removed `^` anchor from both ISO and syslog timestamp regexes, so timestamps embedded after log-level keywords (e.g. `ERROR 2026-02-24T21:27:05`) are now stripped correctly
+
+#### Improved
+- **`cleanLine()` helper** — Consolidated ANSI + timestamp stripping into a single reusable function used by both message display and fingerprint deduplication
+
 ### v0.30.5 — Health Probe: Fast Initial Checking (2026-02-25)
 
 #### Improved

controller/README.md

@@ -892,7 +892,7 @@ Each report push now includes per-app telemetry data:
 **Log scanning** (`logscanner.go`):
 - `ScanContainerLogs(containerNames, since, logger)` runs `docker logs --since=15m --tail=1000` sequentially on all non-protected deployed containers.
 - Classifies lines by keyword match (errors: `error`, `fatal`, `panic`, `crit`, `oom`, `killed`, `exception`, `traceback`; warnings: `warn`, `warning`) on the first 5 words (case-insensitive).
-- Deduplicates via fingerprinting: strips timestamps, replaces 6+ digit numbers with `<N>`, 8+ char hex with `<HEX>`, UUIDs with `<UUID>`. Groups identical fingerprints, keeps top 10 per container.
+- Deduplicates via fingerprinting: strips ANSI escape codes, ISO timestamps (with timezone offsets), and syslog timestamps (including mid-line); replaces 6+ digit numbers with `<N>`, 8+ char hex with `<HEX>`, UUIDs with `<UUID>`. Groups identical fingerprints, keeps top 10 per container.
 - Returns `[]ContainerLogSummary` with `ErrorCount`, `WarnCount`, `RecentIssues []LogIssue`.
 
 **Report integration** (`report/telemetry.go`):

controller/internal/metrics/logscanner.go

@@ -29,10 +29,12 @@ type LogIssue struct {
 }
 
 var (
-	// Strip leading ISO timestamp: 2006-01-02T15:04:05 or 2006/01/02 15:04:05 etc.
+	// Strip ANSI escape codes (color, bold, etc.)
-	reTimestamp = regexp.MustCompile(`^\d{4}[-/]\d{2}[-/]\d{2}[T ]\d{2}:\d{2}:\d{2}[.\d]*[Z ]?`)
+	reANSI = regexp.MustCompile(`\x1b\[[0-9;]*m`)
+	// Strip ISO timestamp: 2006-01-02T15:04:05 or 2006/01/02 15:04:05, with optional tz offset
+	reTimestamp = regexp.MustCompile(`\d{4}[-/]\d{2}[-/]\d{2}[T ]\d{2}:\d{2}:\d{2}[.\d]*([+-]\d{2}:?\d{2})?[Z ]?:? ?`)
 	// Strip syslog-style timestamp: Jan  2 15:04:05
-	reSyslog = regexp.MustCompile(`^[A-Z][a-z]{2}\s+\d{1,2} \d{2}:\d{2}:\d{2} `)
+	reSyslog = regexp.MustCompile(`[A-Z][a-z]{2}\s+\d{1,2} \d{2}:\d{2}:\d{2} `)
 	// Replace 6+ digit sequences with <N> (avoids mangling 4-digit HTTP codes/ports)
 	reNumbers = regexp.MustCompile(`\b\d{6,}\b`)
 	// Replace 8+ char hex strings
@@ -121,10 +123,7 @@ func scanOneContainer(name string, since time.Duration, logger *log.Logger) Cont
 			e.count++
 			e.lastSeen = time.Now()
 		} else {
-			// Use original line trimmed as message (strip timestamp)
+			msg := cleanLine(line)
-			msg := reTimestamp.ReplaceAllString(line, "")
-			msg = reSyslog.ReplaceAllString(msg, "")
-			msg = strings.TrimSpace(msg)
 			if len(msg) > 200 {
 				msg = msg[:200]
 			}
@@ -161,9 +160,18 @@ func scanOneContainer(name string, since time.Duration, logger *log.Logger) Cont
 	return summary
 }
 
+// cleanLine strips ANSI escape codes and timestamps from a log line.
+func cleanLine(line string) string {
+	s := reANSI.ReplaceAllString(line, "")
+	s = reTimestamp.ReplaceAllString(s, "")
+	s = reSyslog.ReplaceAllString(s, "")
+	return strings.TrimSpace(s)
+}
+
 // classifyLine returns "error", "warn", or "" based on first 5 words of the line.
 func classifyLine(line string) string {
-	lower := strings.ToLower(line)
+	cleaned := reANSI.ReplaceAllString(line, "")
+	lower := strings.ToLower(cleaned)
 	words := strings.Fields(lower)
 	if len(words) > 5 {
 		words = words[:5]
@@ -185,9 +193,7 @@ func classifyLine(line string) string {
 
 // fingerprint produces a deduplication key for a log line.
 func fingerprint(line string) string {
-	// Strip leading timestamp
+	s := cleanLine(line)
-	s := reTimestamp.ReplaceAllString(line, "")
-	s = reSyslog.ReplaceAllString(s, "")
 	// Replace UUIDs before hex to avoid partial matches
 	s = reUUID.ReplaceAllString(s, "<UUID>")
 	s = reHex.ReplaceAllString(s, "<HEX>")