fix(app): log hub masks dotted tokens, keeps worker errors and drops the oldest lines by time

- redact: a token with sentence dots around it is masked too.
- Worker error messages are always logged (code and id), so the log screen
  and the error report show them without debug logging.
- The voice worker logs with stt, llm and tts categories, so its lines land
  in those tabs.
- The zip leaves out the oldest lines by the time they were logged, across
  every tab's file, not by file name.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
javis-bot
2026-11-12 13:43:01 +09:00
parent 390f6f0b86
commit eb0fa2f159
13 changed files with 143 additions and 37 deletions

View File

@@ -81,9 +81,12 @@ STT, LLM and TTS lines go to `stt`, `llm`, `tts` by their worker category), `bro
order), the app version and a short PC summary (OS, CPU count, memory); `None` without an error.
When it is over 2,000 characters (Discord's message limit) the screen offers a download instead.
- `export_zip(from, to, out)`: the log files of those days in a zip, at most 10 MB (Discord's file
limit): when larger, the oldest lines are left out and a note says so.
limit): when larger, the oldest lines by the time they were logged, across every tab's file, are
left out and a note says how many.
- Every copy and export runs through `redact`: each stored secret's value, and anything shaped like
a Discord bot token, becomes `[비밀값]`.
a Discord bot token (also with sentence dots around it), becomes `[비밀값]`.
- Errors the voice worker reports to the app (`error` messages: code and request id) are always
logged, debug logging or not, so the log screen and the error report show them.
## Tests

View File

@@ -213,19 +213,25 @@ impl LogHub {
}
}
/// The zip with the oldest `dropped` lines (oldest files first) left out.
/// The zip with the `dropped` oldest lines left out: oldest by the time each line was logged, across
/// every tab's file (a line's time is its first 23 characters, `YYYY-MM-DD HH:MM:SS.mmm`; lines
/// without one count as oldest).
fn build_zip(files: &[(NaiveDate, String, Vec<String>)], dropped: usize) -> std::io::Result<Vec<u8>> {
let mut order: Vec<(&str, usize, usize)> = files.iter().enumerate()
.flat_map(|(fi, (_, _, lines))| lines.iter().enumerate()
.map(move |(li, l)| (l.get(..23).filter(|t| line_time_ok(t)).unwrap_or(""), fi, li)))
.collect();
order.sort();
let gone: std::collections::HashSet<(usize, usize)> = order.iter().take(dropped).map(|&(_, f, l)| (f, l)).collect();
let mut zip = zip::ZipWriter::new(std::io::Cursor::new(Vec::new()));
let opts = zip::write::SimpleFileOptions::default().compression_method(zip::CompressionMethod::Deflated);
let mut skip = dropped;
for (_, name, lines) in files {
let cut = skip.min(lines.len());
skip -= cut;
if cut == lines.len() {
for (fi, (_, name, lines)) in files.iter().enumerate() {
let kept: Vec<&String> = lines.iter().enumerate().filter(|(li, _)| !gone.contains(&(fi, *li))).map(|(_, l)| l).collect();
if kept.is_empty() {
continue;
}
zip.start_file(name.as_str(), opts).map_err(std::io::Error::other)?;
for l in &lines[cut..] {
for l in kept {
zip.write_all(l.as_bytes())?;
zip.write_all(b"\n")?;
}
@@ -237,6 +243,10 @@ fn build_zip(files: &[(NaiveDate, String, Vec<String>)], dropped: usize) -> std:
Ok(zip.finish().map_err(std::io::Error::other)?.into_inner())
}
fn line_time_ok(t: &str) -> bool {
chrono::NaiveDateTime::parse_from_str(t, "%Y-%m-%d %H:%M:%S%.3f").is_ok()
}
fn file_day(name: &str) -> Option<NaiveDate> {
let stem = name.strip_suffix(".log")?;
let date = stem.get(stem.len().checked_sub(10)?..)?;
@@ -269,8 +279,18 @@ pub fn redact(text: &str, secrets: &[String]) -> String {
}
let mut result = String::with_capacity(out.len());
let mut word = String::new();
// A word may carry sentence dots around it ("token=<token>."): they are not part of the token.
let flush = |word: &mut String, result: &mut String| {
if looks_like_token(word) { result.push_str(SECRET_MARK) } else { result.push_str(word) }
let core = word.trim_matches('.');
if looks_like_token(core) {
let lead = word.len() - word.trim_start_matches('.').len();
let trail = word.len() - word.trim_end_matches('.').len();
result.push_str(&word[..lead]);
result.push_str(SECRET_MARK);
result.push_str(&word[word.len() - trail..]);
} else {
result.push_str(word)
}
word.clear();
};
for c in out.chars() {
@@ -402,6 +422,41 @@ mod tests {
let token = format!("{}.{}.{}", "M".repeat(24), "GabcdE", "x".repeat(30));
let out = redact(&format!("token={token}, ok id=123456789012345678 a.b.c"), &[]);
assert_eq!(out, "token=[비밀값], ok id=123456789012345678 a.b.c");
// Sentence dots around it do not hide it.
assert_eq!(redact(&format!("token={token}. next ...{token}..."), &[]), "token=[비밀값]. next ...[비밀값]...");
}
#[test]
fn the_zip_leaves_out_the_oldest_lines_by_time_across_tabs() {
let at_hm = |d: u32, h: u32, m: u32| Local.with_ymd_and_hms(2026, 5, d, h, m, 0).unwrap();
let dir = temp_dir("logorder");
let hub = LogHub::new(Some(&dir));
hub.push_at(at_hm(1, 0, 1), Level::Info, "chat", "first chat line");
hub.push_at(at_hm(1, 23, 59), Level::Info, "app", "late on the first");
hub.push_at(at_hm(2, 0, 1), Level::Info, "chat", "early on the second");
let mut files: Vec<(NaiveDate, String, Vec<String>)> = vec![];
for e in std::fs::read_dir(&dir).unwrap().flatten() {
let name = e.file_name().to_string_lossy().into_owned();
files.push((file_day(&name).unwrap(), name, std::fs::read_to_string(e.path()).unwrap().lines().map(str::to_owned).collect()));
}
files.sort();
// Leave out one line: the 00:01 chat line of the 1st, not a line of the app file.
let z = build_zip(&files, 1).unwrap();
let mut z = zip::ZipArchive::new(std::io::Cursor::new(z)).unwrap();
let mut all = String::new();
for i in 0..z.len() {
std::io::Read::read_to_string(&mut z.by_index(i).unwrap(), &mut all).unwrap();
}
assert!(!all.contains("first chat line"));
assert!(all.contains("late on the first") && all.contains("early on the second"));
// Two: then the 23:59 app line goes and the next day's chat line stays.
let z = build_zip(&files, 2).unwrap();
let mut z = zip::ZipArchive::new(std::io::Cursor::new(z)).unwrap();
let mut all = String::new();
for i in 0..z.len() {
std::io::Read::read_to_string(&mut z.by_index(i).unwrap(), &mut all).unwrap();
}
assert!(!all.contains("late on the first") && all.contains("early on the second"));
}
#[test]

View File

@@ -546,7 +546,8 @@ fn on_text(inner: &Inner, t: &str) {
inner.state.lock().unwrap().open_tts.remove(&d.id).then_some(WorkerEvent::TtsDone(d))
}),
"error" => serde_json::from_value::<WorkerError>(v).ok().map(|e| {
debug_log!("worker", "voice worker error {}", e.code);
// Always logged: the log screen and its error report must show what the worker refused.
error_log!("worker", "voice worker error {} id={}", e.code, e.id.as_deref().unwrap_or("-"));
// A request the worker refused outright never gets a tts_done.
if e.code == "tts_unavailable" || e.code == "brain_unavailable" {
if let Some(id) = &e.id {