feat: record control and voice-note history marker

2 files changed, 103 insertions, 1 deletions

diff --git a/llamachat/ui.py b/llamachat/ui.py
index 9a7aa0d..101f1a8 100644
--- a/llamachat/ui.py
+++ b/llamachat/ui.py
@@ -36,6 +36,7 @@ from PySide6.QtWidgets import (
     QVBoxLayout, QWidget,
 )
 
+from . import audio
 from . import backend, models as models_mod, prompts, skills
 from . import providers as providers_mod
 from .backend import Attachment, BackendError, SearchConfig
@@ -96,6 +97,14 @@ def _button_icon(kind: str) -> QIcon:
         path.lineTo(9.5, 19.5)
         path.closeSubpath()
         painter.drawPath(path)
+    elif kind == "record":
+        # A microphone: capsule, cradle arc and stand.
+        capsule = QPainterPath()
+        capsule.addRoundedRect(QRectF(9.5, 4.0, 5.0, 9.5), 2.5, 2.5)
+        painter.drawPath(capsule)
+        painter.drawArc(QRectF(7.0, 7.0, 10.0, 9.5), 200 * 16, 140 * 16)
+        painter.drawLine(12, 17, 12, 20)
+        painter.drawLine(9, 20, 15, 20)
     elif kind == "stop":
         painter.setBrush(colour)
         painter.drawRoundedRect(QRectF(6.5, 6.5, 11, 11), 2, 2)
@@ -522,6 +531,11 @@ class ChatWindow(QMainWindow):
         # Router-reported input modalities per model id, refreshed on listing.
         self.modalities: dict[str, frozenset[str]] = {}
 
+        self.recording = False
+        self.recorder = audio.AudioRecorder(self) if audio.AVAILABLE else None
+        if self.recorder is not None:
+            self.recorder.capped.connect(self._finish_recording)
+
         # Which system prompt this conversation uses: a name from the store,
         # the NONE sentinel, or CUSTOM with text held in prompt_custom.
         self.prompt_name = cfg.default_prompt
@@ -754,6 +768,13 @@ class ChatWindow(QMainWindow):
         self.new_button.clicked.connect(self.new_session)
         buttons.addWidget(self.new_button)
 
+        self.record_button = QPushButton("Record")
+        self.record_button.setIcon(_button_icon("record"))
+        self.record_button.setToolTip("Record audio for an audio-capable model")
+        self.record_button.clicked.connect(self._toggle_record)
+        self.record_button.hide()
+        buttons.addWidget(self.record_button)
+
         self.attach_button = QPushButton("Attach…")
         self.attach_button.setIcon(_button_icon("attach"))
         self.attach_button.clicked.connect(self._on_attach_clicked)
@@ -926,6 +947,7 @@ class ChatWindow(QMainWindow):
         else:
             self.hide_status()
         self.update_cost()
+        self._update_record_button()
 
     def current_model(self) -> str:
         return self.model_box.currentData() or self.model_box.currentText()
@@ -1004,6 +1026,7 @@ class ChatWindow(QMainWindow):
         if self.session_id is not None and not self.read_only:
             self.history.touch_session(self.session_id, self.current_model())
         self.update_meter()
+        self._update_record_button()
 
     # -- system prompts ---------------------------------------------------
 
@@ -1179,7 +1202,7 @@ class ChatWindow(QMainWindow):
             return
         names = []
         for att in self.attachments:
-            mark = "🖼" if att.kind == "image" else "📄"
+            mark = {"image": "🖼", "audio": "🎙"}.get(att.kind, "📄")
             suffix = " (truncated)" if att.truncated else ""
             names.append(f"{mark} {att.path.name}{suffix}")
         self.attach_label.setText("Attached: " + ", ".join(names))
@@ -1187,6 +1210,57 @@ class ChatWindow(QMainWindow):
         self.clear_attach_button.show()
         self.update_meter()
 
+    # -- recording --------------------------------------------------------
+
+    def _update_record_button(self) -> None:
+        """Show the record control only for an audio-capable model."""
+        if not hasattr(self, "record_button"):
+            return  # still building the window
+        can = self.recorder is not None and self.current_info().audio is True
+        self.record_button.setVisible(can)
+        self.record_button.setText("Stop" if self.recording else "Record")
+        self.record_button.setIcon(
+            _button_icon("stop" if self.recording else "record")
+        )
+
+    def _toggle_record(self) -> None:
+        """Start a recording, or finish the one in progress."""
+        if self.recording:
+            self._finish_recording()
+            return
+        if self.recorder is None or self.current_info().audio is not True:
+            return
+        if not self.recorder.start():
+            self.show_status("No microphone available.", error=True)
+            return
+        self.recording = True
+        self.show_status("Recording. Click Stop when done.")
+        self._update_record_button()
+
+    @Slot()
+    def _finish_recording(self) -> None:
+        """Stop capture and hold the clip as a pending attachment."""
+        if not self.recording:
+            return
+        pcm = self.recorder.stop()
+        self.recording = False
+        self._update_record_button()
+
+        seconds = len(pcm) / (audio.RATE * audio.CHANNELS * audio.SAMPLE_BYTES)
+        if seconds < audio.MIN_SECONDS:
+            self.show_status("Recording too short, discarded.", error=True)
+            return
+        if self.recorder.timed_out:
+            self.show_status(
+                f"Recording stopped at the {audio.MAX_SECONDS}s limit."
+            )
+        else:
+            self.hide_status()
+        self.attachments.append(
+            backend.audio_attachment(audio.to_wav(pcm), round(seconds))
+        )
+        self.update_attach_label()
+
     # -- drag and drop ----------------------------------------------------
 
     def dragEnterEvent(self, event) -> None:
@@ -2346,6 +2420,10 @@ def _bubble_html(
     elif saved_rows:
         parts = []
         for row in saved_rows:
+            if row["kind"] == "audio":
+                # A recording is discarded, so there is no file to check for.
+                parts.append("🎙 " + html.escape(row["path"]))
+                continue
             missing = "" if Path(row["path"]).exists() else " (missing)"
             parts.append(html.escape(row["path"]) + missing)
         files = f"<br><i>files: {', '.join(parts)}</i>"
diff --git a/test_llamachat.py b/test_llamachat.py
index 04c1bc5..20aea57 100755
--- a/test_llamachat.py
+++ b/test_llamachat.py
@@ -497,6 +497,29 @@ def test_markdown_rendering():
     print("ok  markdown rendering")
 
 
+def test_audio_bubble_marker():
+    """A discarded recording shows as a voice note, not a missing file."""
+    import os
+
+    os.environ.setdefault("QT_QPA_PLATFORM", "offscreen")
+    from PySide6.QtWidgets import QApplication
+
+    from llamachat.ui import _bubble_html
+
+    app = QApplication.instance() or QApplication([])
+    assert app is not None
+
+    rendered = _bubble_html(
+        "user",
+        "Listen to this audio and respond.",
+        saved_rows=[{"kind": "audio", "path": "voice-note-4s.wav"}],
+    )
+    assert "🎙 voice-note-4s.wav" in rendered
+    # The synthetic path is not on disk, so it must not read as missing.
+    assert "missing" not in rendered
+    print("ok  audio bubble marker")
+
+
 def test_unbalanced_backticks():
     """An odd backtick cannot reflow the rest of a reply as code."""
     import os
@@ -4041,6 +4064,7 @@ if __name__ == "__main__":
     test_session_prompt_storage()
     test_prompt_column_migration()
     test_markdown_rendering()
+    test_audio_bubble_marker()
     test_unbalanced_backticks()
     test_sidebar_toggle()
     test_shortcuts()