transcript: extract JSONL backward scanner and compaction detection into library

Move JsonlBackwardIter and find_last_compaction() from
parse-claude-conversation into a shared transcript module. Both
memory-search and parse-claude-conversation now use the same robust
compaction detection: mmap-based backward scan, JSON parsing to
verify user-type message, content prefix check.

Replaces memory-search's old detect_compaction() which did a forward
scan with raw string matching on "continued from a previous
conversation" — that could false-positive on the string appearing
in assistant output or tool results.

Add parse-claude-conversation as a new binary for debugging what's
in the context window post-compaction.

Co-Authored-By: ProofOfConcept <poc@bcachefs.org>

poc-memory/src/bin/memory-search.rs

@@ -31,6 +31,10 @@ struct Args {
     #[arg(long)]
     seen: bool,
 
+    /// Show full seen set (list all keys)
+    #[arg(long)]
+    seen_full: bool,
+
     /// Max results to return
     #[arg(long, default_value = "5")]
     max_results: usize,
@@ -50,7 +54,7 @@ fn main() {
 
     let args = Args::parse();
 
-    if args.seen {
+    if args.seen || args.seen_full {
         show_seen();
         return;
     }
@@ -87,8 +91,11 @@ fn main() {
     let state_dir = PathBuf::from("/tmp/claude-memory-search");
     fs::create_dir_all(&state_dir).ok();
 
-    // Detect post-compaction reload
-    let is_compaction = prompt.contains("continued from a previous conversation");
+    // Detect post-compaction reload via mmap backward scan
+    let transcript_path = json["transcript_path"].as_str().unwrap_or("");
+    let is_compaction = poc_memory::transcript::detect_new_compaction(
+        &state_dir, session_id, transcript_path,
+    );
 
     // First prompt or post-compaction: load full context
     let cookie_path = state_dir.join(format!("cookie-{}", session_id));
@@ -155,7 +162,6 @@ fn main() {
     };
 
     // Search for node keys in last ~150k tokens of transcript
-    let transcript_path = json["transcript_path"].as_str().unwrap_or("");
     if debug { println!("[memory-search] transcript: {}", transcript_path); }
     let terms = extract_weighted_terms(transcript_path, 150_000, &store);
 
@@ -363,7 +369,7 @@ fn extract_key_from_line(line: &str) -> Option<String> {
     let rest = &line[after_bracket + 2..];
     let key_end = rest.find("  (c").unwrap_or(rest.len());
     let key = rest[..key_end].trim();
-    if key.is_empty() || !key.contains('.') {
+    if key.is_empty() {
         None
     } else {
         Some(key.to_string())
@@ -374,13 +380,19 @@ fn generate_cookie() -> String {
     uuid::Uuid::new_v4().as_simple().to_string()[..12].to_string()
 }
 
+/// Parse a seen-file line: "TIMESTAMP\tKEY" or legacy "KEY"
+fn parse_seen_line(line: &str) -> &str {
+    line.split_once('\t').map(|(_, key)| key).unwrap_or(line)
+}
+
 fn load_seen(dir: &Path, session_id: &str) -> HashSet<String> {
     let path = dir.join(format!("seen-{}", session_id));
     if path.exists() {
         fs::read_to_string(path)
             .unwrap_or_default()
             .lines()
-            .map(|s| s.to_string())
+            .filter(|s| !s.is_empty())
+            .map(|s| parse_seen_line(s).to_string())
             .collect()
     } else {
         HashSet::new()
@@ -390,7 +402,8 @@ fn load_seen(dir: &Path, session_id: &str) -> HashSet<String> {
 fn mark_seen(dir: &Path, session_id: &str, key: &str) {
     let path = dir.join(format!("seen-{}", session_id));
     if let Ok(mut f) = fs::OpenOptions::new().create(true).append(true).open(path) {
-        writeln!(f, "{}", key).ok();
+        let ts = chrono::Local::now().format("%Y-%m-%dT%H:%M:%S");
+        writeln!(f, "{}\t{}", ts, key).ok();
     }
 }
 
@@ -454,8 +467,29 @@ fn show_seen() {
         }
     }
 
-    let seen = load_seen(&state_dir, session_id);
-    println!("\nSeen set ({} total, {} pre-seeded):", seen.len(), seen.len() - returned.len());
+    // Read seen file in insertion order (append-only file)
+    let seen_path = state_dir.join(format!("seen-{}", session_id));
+    let seen_lines: Vec<String> = fs::read_to_string(&seen_path)
+        .unwrap_or_default()
+        .lines()
+        .filter(|s| !s.is_empty())
+        .map(|s| s.to_string())
+        .collect();
+    let returned_set: HashSet<_> = returned.iter().cloned().collect();
+    println!("\nSeen set ({} total, {} pre-seeded):", seen_lines.len(), seen_lines.len() - returned.len());
+
+    if Args::parse().seen_full {
+        for line in &seen_lines {
+            let key = parse_seen_line(line);
+            let marker = if returned_set.contains(key) { "→ " } else { "  " };
+            // Show timestamp if present, otherwise just key
+            if let Some((ts, k)) = line.split_once('\t') {
+                println!("  {} {}{}", ts, marker, k);
+            } else {
+                println!("  (no ts) {}{}", marker, line);
+            }
+        }
+    }
 }
 
 fn cleanup_stale_files(dir: &Path, max_age: Duration) {