Add recovery for missing oneliners
This commit introduces a recovery mechanism to regenerate `oneliner.txt` files for cases where transcription was successful but the oneliner generation failed due to a crash between writing the transcript and the oneliner. The `transcribe::recovery::regenerate_missing_oneliners` function is added and called at startup after `scan_and_enqueue`. This function identifies cases with non-empty transcripts but missing oneliners and triggers their regeneration. The `transcribe::worker::update_oneliner` function is refactored to always regenerate the oneliner from all available transcripts in a case, ensuring that later recordings can correct earlier ones. This replaces the previous `ensure_oneliner` logic which only generated the oneliner if it didn't exist. New helper functions `cases_needing_oneliner` and `all_transcripts_joined` are introduced to support these changes. Comprehensive unit tests are included for the new recovery and file processing logic.
This commit is contained in:
+127
-15
@@ -71,12 +71,12 @@ pub async fn run(
|
||||
"Transcript written"
|
||||
);
|
||||
|
||||
// Silent recording: Whisper returned an empty string. Skip the
|
||||
// oneliner step — otherwise the LLM echoes the system prompt back.
|
||||
if !text.trim().is_empty()
|
||||
&& let Some(case_dir) = audio_path.parent()
|
||||
{
|
||||
ensure_oneliner(case_dir, &text, &client, &config).await;
|
||||
// Regenerate the oneliner from all transcripts of the case. Later
|
||||
// recordings override earlier ones — symmetric to the analyze-LLM
|
||||
// rule "Spätere Aufnahmen haben Vorrang". Silent / empty cases are
|
||||
// no-ops; LLM errors leave any existing oneliner untouched.
|
||||
if let Some(case_dir) = audio_path.parent() {
|
||||
update_oneliner(case_dir, &client, &config).await;
|
||||
}
|
||||
}
|
||||
|
||||
@@ -106,25 +106,31 @@ async fn mark_failed(audio_path: &Path) {
|
||||
}
|
||||
}
|
||||
|
||||
/// Generate `case_dir/oneliner.txt` from the given transcript iff the file
|
||||
/// does not already exist. Errors are non-fatal: logged and swallowed.
|
||||
async fn ensure_oneliner(
|
||||
/// Regenerate `case_dir/oneliner.txt` from **all** non-empty transcripts in
|
||||
/// the case, joined chronologically. Called after every successful transcript
|
||||
/// write so later recordings can correct earlier ones (mirror of the
|
||||
/// analyze-LLM rule "later recordings override"). Overwrites any existing
|
||||
/// oneliner on success; LLM errors are non-fatal and leave the previous
|
||||
/// oneliner (if any) untouched. Silent case (no non-empty transcript) is a
|
||||
/// no-op — next transcript write retries.
|
||||
pub(crate) async fn update_oneliner(
|
||||
case_dir: &Path,
|
||||
transcript: &str,
|
||||
client: &reqwest::Client,
|
||||
config: &Config,
|
||||
) {
|
||||
let path = case_dir.join("oneliner.txt");
|
||||
if path.exists() {
|
||||
return;
|
||||
}
|
||||
|
||||
let transcript = match all_transcripts_joined(case_dir).await {
|
||||
Some(t) => t,
|
||||
None => return,
|
||||
};
|
||||
|
||||
match ollama::generate_oneliner(
|
||||
client,
|
||||
&config.ollama_url,
|
||||
&config.ollama_model,
|
||||
config.ollama_keep_alive,
|
||||
transcript,
|
||||
&transcript,
|
||||
ONELINER_TIMEOUT,
|
||||
)
|
||||
.await
|
||||
@@ -133,7 +139,7 @@ async fn ensure_oneliner(
|
||||
if let Err(e) = tokio::fs::write(&path, &line).await {
|
||||
error!(path = %path.display(), error = %e, "writing oneliner failed");
|
||||
} else {
|
||||
info!(path = %path.display(), chars = line.chars().count(), "Oneliner written");
|
||||
info!(path = %path.display(), chars = line.chars().count(), "Oneliner updated");
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
@@ -141,3 +147,109 @@ async fn ensure_oneliner(
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Read every non-empty `*.transcript.txt` in `case_dir`, ordered
|
||||
/// chronologically (ISO-8601 filename sort equals chronological order), and
|
||||
/// join them with `\n\n---\n\n`. Empty / whitespace-only transcripts (silent
|
||||
/// recordings) are skipped. Returns None if no non-empty transcript exists.
|
||||
pub(crate) async fn all_transcripts_joined(case_dir: &Path) -> Option<String> {
|
||||
let mut entries = tokio::fs::read_dir(case_dir).await.ok()?;
|
||||
let mut files: Vec<std::path::PathBuf> = Vec::new();
|
||||
while let Ok(Some(entry)) = entries.next_entry().await {
|
||||
let name = entry.file_name();
|
||||
let Some(s) = name.to_str() else { continue };
|
||||
if s.ends_with(".transcript.txt") {
|
||||
files.push(entry.path());
|
||||
}
|
||||
}
|
||||
files.sort();
|
||||
|
||||
let mut parts: Vec<String> = Vec::with_capacity(files.len());
|
||||
for path in files {
|
||||
if let Ok(text) = tokio::fs::read_to_string(&path).await {
|
||||
let trimmed = text.trim();
|
||||
if !trimmed.is_empty() {
|
||||
parts.push(trimmed.to_string());
|
||||
}
|
||||
}
|
||||
}
|
||||
if parts.is_empty() {
|
||||
return None;
|
||||
}
|
||||
Some(parts.join("\n\n---\n\n"))
|
||||
}
|
||||
|
||||
#[cfg(test)]
|
||||
mod tests {
|
||||
use super::*;
|
||||
use tempfile::tempdir;
|
||||
|
||||
/// Regression guard for the Womax bug: the joined transcript must
|
||||
/// include ALL recordings in chronological order, so the LLM sees
|
||||
/// both the initial term and any later correction.
|
||||
#[tokio::test]
|
||||
async fn all_transcripts_joined_includes_all_in_order() {
|
||||
let dir = tempdir().unwrap();
|
||||
tokio::fs::write(
|
||||
dir.path().join("2026-04-16T10-05-00Z.transcript.txt"),
|
||||
"Korrektur. Das Mittel heißt Vomex.",
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
tokio::fs::write(
|
||||
dir.path().join("2026-04-16T10-00-00Z.transcript.txt"),
|
||||
"Jetzt weiß ich es wieder. Es heißt Womax.",
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let got = all_transcripts_joined(dir.path()).await.expect("Some");
|
||||
assert_eq!(
|
||||
got,
|
||||
"Jetzt weiß ich es wieder. Es heißt Womax.\n\n---\n\nKorrektur. Das Mittel heißt Vomex."
|
||||
);
|
||||
}
|
||||
|
||||
/// Silent recordings are skipped, not treated as end-of-stream — a
|
||||
/// later non-empty recording still contributes.
|
||||
#[tokio::test]
|
||||
async fn all_transcripts_joined_skips_empty_recordings() {
|
||||
let dir = tempdir().unwrap();
|
||||
tokio::fs::write(
|
||||
dir.path().join("2026-04-16T10-00-00Z.transcript.txt"),
|
||||
"",
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
tokio::fs::write(
|
||||
dir.path().join("2026-04-16T10-05-00Z.transcript.txt"),
|
||||
"non-empty content",
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
|
||||
let got = all_transcripts_joined(dir.path()).await.expect("Some");
|
||||
assert_eq!(got, "non-empty content");
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn all_transcripts_joined_is_none_when_all_empty() {
|
||||
let dir = tempdir().unwrap();
|
||||
tokio::fs::write(
|
||||
dir.path().join("2026-04-16T10-00-00Z.transcript.txt"),
|
||||
" \n ",
|
||||
)
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(all_transcripts_joined(dir.path()).await.is_none());
|
||||
}
|
||||
|
||||
#[tokio::test]
|
||||
async fn all_transcripts_joined_is_none_when_no_transcripts() {
|
||||
let dir = tempdir().unwrap();
|
||||
tokio::fs::write(dir.path().join("2026-04-16T10-00-00Z.m4a"), b"audio")
|
||||
.await
|
||||
.unwrap();
|
||||
assert!(all_transcripts_joined(dir.path()).await.is_none());
|
||||
}
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user