chore: remove dead test code and fix stale comment

tests/test_isr.py:
- Remove unused imports: io, SimpleNamespace, call
- Remove test_mp3_chunks_written_to_file — it mocked connect_stream but
  never called record(), making all the mock scaffolding dead; the actual
  assertion (bytes written to a file) is already covered by
  TestAudioFileWriter and TestGenerateFilename

isr.py:
- Update AudioDevice.backend comment: only the ALSA backend exists now

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

README.md

@@ -147,11 +147,12 @@ strftime codes are substituted at split time. The file extension is added automa
 ## Web UI (`web.py`)
 
 ```bash
-python web.py                        # serves ./recordings on port 8080
-python web.py --dir /path/to/audio   # custom recordings directory
-python web.py --port 8888            # custom port
-python web.py --threshold 0.03       # loudness threshold 0–1 (default 0.05)
-python web.py --min-gap 15           # grace period in seconds for merging loud sections (default 2)
+python web.py                              # serves ./recordings on port 8080
+python web.py --dir /path/to/audio         # custom recordings directory
+python web.py --port 8888                  # custom port
+python web.py --threshold 0.03             # loudness threshold 0–1 (default 0.05)
+python web.py --min-gap 15                 # grace period in seconds for merging loud sections (default 2)
+python web.py --analyses-dir /path/to/dir  # where to store analysis cache files (default: <recordings>/analyses)
 ```
 
 Shows recordings grouped by day with collapsible sections. Features:
@@ -211,6 +212,8 @@ docker compose down && docker compose up -d --build
 
 **Log file in Docker:** The recorder always logs to stdout, so `docker compose logs -f` shows live output. To persist logs on the host, set `log_file = /app/recordings/recorder.log` in `config.ini` (the `recordings` directory is the bind mount).
 
+**Analysis cache in Docker:** The web container mounts `./recordings` read-only, so analysis cache files are written to a separate `./analyses` bind mount (mapped to `/analyses` inside the container). This directory is created automatically by Docker Compose on first run. Cache files are stored as `analyses/<filename>.analysis.json` on the host.
+
 **File retention:** Individual recordings can be deleted from the web UI. For bulk / automated cleanup, add a cron job on the host:
 ```bash
 # Delete recordings older than 30 days

docker-compose.yml

@@ -16,7 +16,8 @@ services:
     build: .
     volumes:
       - ./recordings:/recordings:ro
+      - ./analyses:/analyses
     ports:
       - "8080:8080"
     restart: unless-stopped
-    command: ["python", "web.py", "--dir", "/recordings"]
+    command: ["python", "web.py", "--dir", "/recordings", "--analyses-dir", "/analyses"]

isr.py

@@ -54,7 +54,7 @@ class AudioDevice:
     name: str                        # Human-readable name
     channels: int                    # Max input channels
     sample_rate: int                 # Default sample rate
-    backend: str                     # Backend name (pulseaudio, pipewire, portaudio)
+    backend: str                     # Backend name ('alsa')
     is_default: bool = False         # Is system default
     is_monitor: bool = False         # Is a monitor/loopback source
     description: str = ""            # Extended description

tests/test_isr.py

@@ -4,15 +4,13 @@ Tests for isr.py
 Run with:  pytest tests/
 """
 
-import io
 import logging
 import struct
 import wave
 from datetime import datetime
 from pathlib import Path
-from types import SimpleNamespace
 from typing import List
-from unittest.mock import MagicMock, patch, call
+from unittest.mock import MagicMock, patch
 
 import pytest
 
@@ -571,50 +569,6 @@ class TestStreamRecorderRecord:
             )
         return r
 
-    def test_mp3_chunks_written_to_file(self, tmp_path):
-        chunks = [b"A" * 512, b"B" * 512, b"C" * 512]
-        rec = self._recorder(fmt="mp3")
-        rec.output_dir = str(tmp_path)
-
-        mock_resp = MagicMock()
-        mock_resp.headers = {"Content-Type": "audio/mpeg"}
-        mock_resp.iter_content.return_value = iter(chunks)
-
-        def _stop_after_connect(*args, **kwargs):
-            rec.running = True
-            return mock_resp
-
-        with patch.object(rec, "connect_stream", side_effect=[mock_resp, None]):
-            # connect_stream returns the mocked response on the first call;
-            # we stop the loop via a side-effectful iter_content
-            original_iter = mock_resp.iter_content.return_value
-
-            def _chunks_then_stop(chunk_size=8192):
-                for c in chunks:
-                    yield c
-                rec.running = False  # stop the outer while loop
-
-            mock_resp.iter_content.side_effect = _chunks_then_stop
-            mock_resp.headers = {"Content-Type": "audio/mpeg"}
-            rec.detected_format = "mp3"
-            rec.running = True
-            rec.header_capture_complete = True
-            rec.stream_headers = None
-
-            # Open a file manually so we can verify writes
-            filename = rec.generate_filename("mp3")
-            rec.current_file = open(filename, "wb")
-            rec.current_filename = filename
-
-            # Simulate one inner loop iteration
-            for chunk in _chunks_then_stop():
-                if chunk:
-                    rec.current_file.write(chunk)
-            rec.close_current_file()
-
-        written = Path(filename).read_bytes()
-        assert written == b"A" * 512 + b"B" * 512 + b"C" * 512
-
     def test_connection_failure_retries(self, tmp_path):
         rec = self._recorder()
         rec.output_dir = str(tmp_path)

web.py

@@ -207,19 +207,18 @@ def analyze_flac(path: Path, window_samples: int = WINDOW_SAMPLES,
 # Analysis cache helpers
 # ---------------------------------------------------------------------------
 
-def _analysis_cache_path(base: Path, audio_path: Path) -> Path:
-    rel = audio_path.relative_to(base)
-    return base / 'analyses' / rel.parent / (rel.name + '.analysis.json')
+def _analysis_cache_path(analyses_base: Path, recordings_base: Path, audio_path: Path) -> Path:
+    rel = audio_path.relative_to(recordings_base)
+    return analyses_base / rel.parent / (rel.name + '.analysis.json')
 
 
-def prune_orphan_analyses(base: Path):
-    analyses_dir = base / 'analyses'
-    if not analyses_dir.exists():
+def prune_orphan_analyses(analyses_base: Path, recordings_base: Path):
+    if not analyses_base.exists():
         return
     removed = 0
-    for cache in analyses_dir.rglob('*.analysis.json'):
-        rel = cache.relative_to(analyses_dir)
-        audio_path = base / rel.parent / rel.name[:-len('.analysis.json')]
+    for cache in analyses_base.rglob('*.analysis.json'):
+        rel = cache.relative_to(analyses_base)
+        audio_path = recordings_base / rel.parent / rel.name[:-len('.analysis.json')]
         if not audio_path.exists():
             try:
                 cache.unlink()
@@ -283,6 +282,7 @@ def list_files(recordings_dir: str):
 
 class _Handler(BaseHTTPRequestHandler):
     recordings_dir: str = 'recordings'
+    analyses_dir:   str = 'recordings/analyses'
     threshold: float    = LOUD_THRESHOLD
     min_gap: float      = MIN_GAP_SECONDS
 
@@ -358,12 +358,14 @@ class _Handler(BaseHTTPRequestHandler):
         except Exception:
             pass
 
-        base = Path(self.recordings_dir).resolve()
-        cache_path = _analysis_cache_path(base, path)
+        recordings_base = Path(self.recordings_dir).resolve()
+        analyses_base   = Path(self.analyses_dir).resolve()
+        cache_path = _analysis_cache_path(analyses_base, recordings_base, path)
         try:
             cached = json.loads(cache_path.read_text('utf-8'))
             if cached.get('threshold') == threshold and cached.get('min_gap') == min_gap:
-                self._send(200, json.dumps(cached['result']).encode('utf-8'), 'application/json')
+                payload = dict(cached['result']); payload['cached'] = True
+                self._send(200, json.dumps(payload).encode('utf-8'), 'application/json')
                 return
         except Exception:
             pass
@@ -385,8 +387,8 @@ class _Handler(BaseHTTPRequestHandler):
             tmp = cache_path.with_suffix('.tmp')
             tmp.write_text(json.dumps({'threshold': threshold, 'min_gap': min_gap, 'result': result}), 'utf-8')
             os.replace(tmp, cache_path)
-        except Exception:
-            pass
+        except Exception as e:
+            print(f'Warning: could not write analysis cache {cache_path}: {e}', flush=True)
 
         self._send(200, json.dumps(result).encode('utf-8'), 'application/json')
 
@@ -511,7 +513,11 @@ class _Handler(BaseHTTPRequestHandler):
             return
 
         try:
-            _analysis_cache_path(Path(self.recordings_dir).resolve(), path).unlink()
+            _analysis_cache_path(
+                Path(self.analyses_dir).resolve(),
+                Path(self.recordings_dir).resolve(),
+                path,
+            ).unlink()
         except Exception:
             pass
 
@@ -703,6 +709,11 @@ button.chip:hover{background:#6c1f08;border-color:#9a3412}
 button.chip:focus-visible{outline:2px solid var(--accent);outline-offset:2px}
 .quiet{color:var(--muted);font-size:12px;margin-top:6px}
 .spin{color:var(--muted);font-style:italic;font-size:12px;padding:6px 0}
+.prog-bar{height:3px;background:var(--brd);border-radius:2px;margin:6px 0 4px;overflow:hidden}
+.prog-fill{height:100%;background:var(--accent);border-radius:2px;transition:width 0.15s ease}
+.prog-file{font-size:12px;color:var(--muted);font-style:italic;white-space:nowrap;overflow:hidden;text-overflow:ellipsis;max-width:100%}
+.prog-tally{font-size:11px;color:var(--muted);margin-top:3px}
+.cached-badge{font-size:10px;color:var(--muted);background:var(--surf);border:1px solid var(--brd);border-radius:3px;padding:1px 5px;margin-left:6px;vertical-align:middle;font-style:normal}
 .empty{text-align:center;padding:60px;color:var(--muted)}
 /* player row */
 .player-row td{padding:0 10px 10px;background:var(--bg);border-bottom:1px solid var(--brd)}
@@ -855,7 +866,7 @@ function togglePlayer(idx, filename) {
 
   if (!open) {
     if (!audio.getAttribute('data-src-set')) {
-      audio.preload = 'metadata';
+      audio.preload = 'auto';
       audio.src = '/stream/' + encodeURIComponent(filename);
       audio.load();
       audio.setAttribute('data-src-set','1');
@@ -925,6 +936,7 @@ function seekToSection(idx, filename, startSec, endSec, sectionIdx) {
   if (pbtn.getAttribute('aria-expanded') !== 'true') togglePlayer(idx, filename);
   activePlayerIdx = idx;
   const audio  = document.getElementById('aud-'+idx);
+  audio.preload = 'auto';
   const seekTo = Math.max(0, startSec - getPreroll());
   const doSeek = () => { audio.currentTime = seekTo; audio.play().catch(() => {}); };
   if (audio.readyState >= 1) doSeek();
@@ -954,6 +966,12 @@ async function analyse(idx, filename, cell, btn) {
     }
     const box = document.createElement('div'); box.className='wbox';
     box.appendChild(drawWave(d.rms_display||[], d.sections||[], d.duration||0, filename));
+    if (d.cached) {
+      const badge = document.createElement('span');
+      badge.className = 'cached-badge'; badge.textContent = 'cached';
+      badge.title = 'Result loaded from cache — change threshold/gap and re-analyse to recompute';
+      box.firstChild.after(badge);
+    }
 
     const chips = document.createElement('div');
     chips.className='chips';
@@ -1322,22 +1340,43 @@ async function dayHighlights(dayId, analyzableFiles) {
 
   hlRow.hidden = false;
   const n = analyzableFiles.length;
-  contentEl.innerHTML = `<div class="spin" aria-live="polite" aria-busy="true">Analysing ${n} file${n!==1?'s':''}…</div>`;
   if (btn) btn.disabled = true;
 
+  // Build progress UI
+  const progWrap = document.createElement('div');
+  progWrap.setAttribute('aria-live', 'polite'); progWrap.setAttribute('aria-busy', 'true');
+  const progBar  = document.createElement('div'); progBar.className  = 'prog-bar';
+  const progFill = document.createElement('div'); progFill.className = 'prog-fill'; progFill.style.width = '0%';
+  progBar.appendChild(progFill);
+  const progFile  = document.createElement('div'); progFile.className  = 'prog-file';
+  const progTally = document.createElement('div'); progTally.className = 'prog-tally';
+  progWrap.appendChild(progBar); progWrap.appendChild(progFile); progWrap.appendChild(progTally);
+  contentEl.innerHTML = ''; contentEl.appendChild(progWrap);
+
   const threshold = document.getElementById('threshold-input').value || '0.05';
   const minGap    = document.getElementById('min-gap-input').value || '2';
 
   const results = [];
-  for (const f of analyzableFiles) {
+  let nCached = 0, nLive = 0;
+  for (let i = 0; i < analyzableFiles.length; i++) {
+    const f = analyzableFiles[i];
+    progFile.textContent  = `${i + 1} / ${n} — ${f.name}`;
+    progFill.style.width  = `${(i / n) * 100}%`;
+    const tallyParts = [];
+    if (nCached) tallyParts.push(`${nCached} cached`);
+    if (nLive)   tallyParts.push(`${nLive} analysed`);
+    progTally.textContent = tallyParts.join(' · ');
     try {
       const r = await fetch('/api/analyze?file=' + encodeURIComponent(f.name)
         + '&threshold=' + encodeURIComponent(threshold)
         + '&min_gap='   + encodeURIComponent(minGap));
       const d = await r.json();
-      if (!d.error) results.push({ f, data: d });
+      if (!d.error) { results.push({ f, data: d }); d.cached ? nCached++ : nLive++; }
     } catch(e) {}
   }
+  progFill.style.width = '100%';
+  progFile.textContent  = `Done — ${n} file${n!==1?'s':''} (${nCached} cached, ${nLive} analysed)`;
+  progTally.textContent = '';
 
   if (!results.length) {
     contentEl.innerHTML = '<div class="quiet">No analysable results.</div>';
@@ -1439,24 +1478,33 @@ async function dayHighlights(dayId, analyzableFiles) {
   box.appendChild(labels);
 
   if (dayActiveSections.length) {
-    const chips = document.createElement('div');
-    chips.className = 'chips';
-    chips.setAttribute('role', 'list');
-    chips.setAttribute('aria-label', 'Day loud sections — click to jump, J/K to step across files');
-    dayActiveSections.forEach((sec, si) => {
-      const c = document.createElement('button');
-      c.className = 'chip';
-      c.setAttribute('role', 'listitem');
-      c.title = sec.filename + ' @ ' + fmtT(sec.start);
-      const d = new Date(sec.absStart * 1000);
-      const hms = d.getHours().toString().padStart(2,'0') + ':'
-                + d.getMinutes().toString().padStart(2,'0') + ':'
-                + d.getSeconds().toString().padStart(2,'0');
-      c.textContent = hms;
-      c.addEventListener('click', () => jumpToDaySection(si));
-      chips.appendChild(c);
-    });
-    box.appendChild(chips);
+    const MAX_DAY_CHIPS = 50;
+    if (dayActiveSections.length > MAX_DAY_CHIPS) {
+      const note = document.createElement('p');
+      note.className = 'quiet';
+      note.style.marginTop = '6px';
+      note.textContent = `${dayActiveSections.length} sections — use J / K to navigate`;
+      box.appendChild(note);
+    } else {
+      const chips = document.createElement('div');
+      chips.className = 'chips';
+      chips.setAttribute('role', 'list');
+      chips.setAttribute('aria-label', 'Day loud sections — click to jump, J/K to step across files');
+      dayActiveSections.forEach((sec, si) => {
+        const c = document.createElement('button');
+        c.className = 'chip';
+        c.setAttribute('role', 'listitem');
+        c.title = sec.filename + ' @ ' + fmtT(sec.start);
+        const d = new Date(sec.absStart * 1000);
+        const hms = d.getHours().toString().padStart(2,'0') + ':'
+                  + d.getMinutes().toString().padStart(2,'0') + ':'
+                  + d.getSeconds().toString().padStart(2,'0');
+        c.textContent = hms;
+        c.addEventListener('click', () => jumpToDaySection(si));
+        chips.appendChild(c);
+      });
+      box.appendChild(chips);
+    }
   }
 
   const summary = document.createElement('div');
@@ -1498,6 +1546,7 @@ function jumpToDaySection(si) {
 
   const audio = document.getElementById('aud-' + fileIdx);
   if (!audio) return;
+  audio.preload = 'auto';
   const seekTo = Math.max(0, start - getPreroll());
   const doSeek = () => { audio.currentTime = seekTo; audio.play().catch(() => {}); };
   if (audio.readyState >= 1) doSeek();
@@ -1593,25 +1642,31 @@ def main():
                         help='Bind address (default: 0.0.0.0)')
     parser.add_argument('--threshold', type=float, default=LOUD_THRESHOLD,
                         help=f'RMS loudness threshold 0–1 (default: {LOUD_THRESHOLD})')
-    parser.add_argument('--min-gap',   type=float, default=MIN_GAP_SECONDS,
+    parser.add_argument('--min-gap',     type=float, default=MIN_GAP_SECONDS,
                         help=f'Seconds gap for merging loud sections (default: {MIN_GAP_SECONDS})')
+    parser.add_argument('--analyses-dir', default=None,
+                        help='Directory for analysis cache files (default: <recordings-dir>/analyses)')
     args = parser.parse_args()
 
-    rec_dir = Path(args.dir)
-    if not rec_dir.exists():
-        print(f"Warning: recordings directory '{args.dir}' does not exist yet.")
+    rec_dir      = Path(args.dir).resolve()
+    analyses_dir = Path(args.analyses_dir).resolve() if args.analyses_dir else rec_dir / 'analyses'
 
-    prune_orphan_analyses(rec_dir.resolve())
+    if not rec_dir.exists():
+        print(f"Warning: recordings directory '{rec_dir}' does not exist yet.")
+
+    prune_orphan_analyses(analyses_dir, rec_dir)
 
     class Handler(_Handler):
-        recordings_dir = str(rec_dir.resolve())
+        recordings_dir = str(rec_dir)
+        analyses_dir   = str(analyses_dir)
         threshold      = args.threshold
         min_gap        = args.min_gap
 
     server = ThreadingHTTPServer((args.host, args.port), Handler)
 
     print(f"ISR Web running → http://{args.host}:{args.port}/")
-    print(f"Recordings dir  → {rec_dir.resolve()}")
+    print(f"Recordings dir  → {rec_dir}")
+    print(f"Analyses dir    → {analyses_dir}")
     print(f"Loud threshold  → {args.threshold}")
     if not NUMPY_AVAILABLE:
         print("Note: numpy not installed — WAV RMS uses pure Python (slower); FLAC analysis unavailable")