feat(capture): dictation, personalities, 0.5.0

Ships the Capture release end to end. Global-hotkey dictation with
synthetic paste into the focused app on macOS and Windows, an on-screen
pill across recording / transcribing / refining, customizable push-to-
talk and toggle chords, and an accessibility-permission prompt scoped to
Settings → Captures with inline re-check feedback.

Voice profiles gain optional personalities that power compose / rewrite /
respond actions via a local Qwen3 LLM — shared with refinement, so there
is one local LLM in the app, not two.

Refinement hardened with deterministic Whisper-loop collapse before the
LLM sees the transcript, per-capture flag snapshots for re-runs, and a
ten-transcript evaluation harness across every bundled refinement size.

Version bump 0.4.5 → 0.5.0.

Co-Authored-By: Claude Opus 4.7 (1M context) <[email protected]>

backend/database/__init__.py

@@ -8,9 +8,12 @@ without changing any importers.
 from .models import (
     Base,
     AudioChannel,
+    Capture,
+    CaptureSettings,
     ChannelDeviceMapping,
     EffectPreset,
     Generation,
+    GenerationSettings,
     GenerationVersion,
     ProfileChannelMapping,
     ProfileSample,
@@ -25,9 +28,12 @@ __all__ = [
     # Models
     "Base",
     "AudioChannel",
+    "Capture",
+    "CaptureSettings",
     "ChannelDeviceMapping",
     "EffectPreset",
     "Generation",
+    "GenerationSettings",
     "GenerationVersion",
     "ProfileChannelMapping",
     "ProfileSample",

backend/database/migrations.py

@@ -34,6 +34,7 @@ def run_migrations(engine) -> None:
     _migrate_generations(engine, inspector, tables)
     _migrate_effect_presets(engine, inspector, tables)
     _migrate_generation_versions(engine, inspector, tables)
+    _migrate_capture_settings(engine, inspector, tables)
     _normalize_storage_paths(engine, tables)
 
 
@@ -146,6 +147,8 @@ def _migrate_profiles(engine, inspector, tables: set[str]) -> None:
         _add_column(engine, "profiles", "design_prompt TEXT", "design_prompt")
     if "default_engine" not in columns:
         _add_column(engine, "profiles", "default_engine VARCHAR", "default_engine")
+    if "personality" not in columns:
+        _add_column(engine, "profiles", "personality TEXT", "personality")
 
 
 def _migrate_generations(engine, inspector, tables: set[str]) -> None:
@@ -164,6 +167,13 @@ def _migrate_generations(engine, inspector, tables: set[str]) -> None:
         _add_column(engine, "generations", "model_size VARCHAR", "model_size")
     if "is_favorited" not in columns:
         _add_column(engine, "generations", "is_favorited BOOLEAN DEFAULT 0", "is_favorited")
+    if "source" not in columns:
+        _add_column(
+            engine,
+            "generations",
+            "source VARCHAR NOT NULL DEFAULT 'manual'",
+            "source",
+        )
 
 
 def _migrate_effect_presets(engine, inspector, tables: set[str]) -> None:
@@ -182,6 +192,40 @@ def _migrate_generation_versions(engine, inspector, tables: set[str]) -> None:
         _add_column(engine, "generation_versions", "source_version_id VARCHAR", "source_version_id")
 
 
+def _migrate_capture_settings(engine, inspector, tables: set[str]) -> None:
+    if "capture_settings" not in tables:
+        return
+    columns = _get_columns(inspector, "capture_settings")
+    if "allow_auto_paste" not in columns:
+        _add_column(
+            engine,
+            "capture_settings",
+            "allow_auto_paste BOOLEAN NOT NULL DEFAULT 1",
+            "allow_auto_paste",
+        )
+    if "default_playback_voice_id" not in columns:
+        _add_column(
+            engine,
+            "capture_settings",
+            "default_playback_voice_id VARCHAR",
+            "default_playback_voice_id",
+        )
+    if "chord_push_to_talk_keys" not in columns:
+        _add_column(
+            engine,
+            "capture_settings",
+            "chord_push_to_talk_keys TEXT NOT NULL DEFAULT '[\"MetaRight\",\"AltGr\"]'",
+            "chord_push_to_talk_keys",
+        )
+    if "chord_toggle_to_talk_keys" not in columns:
+        _add_column(
+            engine,
+            "capture_settings",
+            "chord_toggle_to_talk_keys TEXT NOT NULL DEFAULT '[\"MetaRight\",\"AltGr\",\"Space\"]'",
+            "chord_toggle_to_talk_keys",
+        )
+
+
 def _normalize_storage_paths(engine, tables: set[str]) -> None:
     """Normalize stored file paths to be relative to the configured data dir."""
     from pathlib import Path

backend/database/models.py

@@ -3,7 +3,7 @@
 from datetime import datetime
 import uuid
 
-from sqlalchemy import Column, String, Integer, Float, DateTime, Text, ForeignKey, Boolean
+from sqlalchemy import Column, String, Integer, Float, DateTime, Text, ForeignKey, Boolean, JSON
 from sqlalchemy.ext.declarative import declarative_base
 
 Base = declarative_base()
@@ -33,6 +33,10 @@ class VoiceProfile(Base):
     preset_voice_id = Column(String, nullable=True)  # e.g. "am_adam" — only for preset
     design_prompt = Column(Text, nullable=True)      # text description — only for designed
     default_engine = Column(String, nullable=True)   # auto-selected engine, locked for preset
+    # Free-form character prompt used by the compose / rewrite / respond / speak
+    # endpoints. Describes *what* this voice says and how, orthogonal to how
+    # it sounds (which is handled by the preset / cloning metadata above).
+    personality = Column(Text, nullable=True)
 
     created_at = Column(DateTime, default=datetime.utcnow)
     updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
@@ -67,6 +71,10 @@ class Generation(Base):
     status = Column(String, default="completed")
     error = Column(Text, nullable=True)
     is_favorited = Column(Boolean, default=False)
+    # Origin of this generation — "manual" for regular /generate calls,
+    # "personality_speak" for rows created by POST /profiles/{id}/speak.
+    # Future sources (bulk import, agent replies, etc.) can extend this.
+    source = Column(String, nullable=False, default="manual")
     created_at = Column(DateTime, default=datetime.utcnow)
 
 
@@ -167,3 +175,70 @@ class ProfileChannelMapping(Base):
 
     profile_id = Column(String, ForeignKey("profiles.id"), primary_key=True)
     channel_id = Column(String, ForeignKey("audio_channels.id"), primary_key=True)
+
+
+class CaptureSettings(Base):
+    """Singleton row holding user defaults for the capture/refine flow.
+
+    Kept server-side so every window, CLI client, and API consumer reads the
+    same preferences. The ``id`` column is always 1.
+    """
+
+    __tablename__ = "capture_settings"
+
+    id = Column(Integer, primary_key=True, default=1)
+    stt_model = Column(String, nullable=False, default="turbo")
+    language = Column(String, nullable=False, default="auto")
+    auto_refine = Column(Boolean, nullable=False, default=True)
+    llm_model = Column(String, nullable=False, default="0.6B")
+    smart_cleanup = Column(Boolean, nullable=False, default=True)
+    self_correction = Column(Boolean, nullable=False, default=True)
+    preserve_technical = Column(Boolean, nullable=False, default=True)
+    allow_auto_paste = Column(Boolean, nullable=False, default=True)
+    default_playback_voice_id = Column(String, nullable=True)
+    # Lists of rdev::Key variant names (e.g. "MetaRight", "AltGr"). Right-hand
+    # modifiers by default so they don't collide with left-hand system
+    # shortcuts (Cmd+Opt+I devtools, Cmd+Opt+Esc force-quit).
+    chord_push_to_talk_keys = Column(
+        JSON, nullable=False, default=lambda: ["MetaRight", "AltGr"]
+    )
+    chord_toggle_to_talk_keys = Column(
+        JSON, nullable=False, default=lambda: ["MetaRight", "AltGr", "Space"]
+    )
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+
+
+class GenerationSettings(Base):
+    """Singleton row for long-form TTS generation preferences."""
+
+    __tablename__ = "generation_settings"
+
+    id = Column(Integer, primary_key=True, default=1)
+    max_chunk_chars = Column(Integer, nullable=False, default=800)
+    crossfade_ms = Column(Integer, nullable=False, default=50)
+    normalize_audio = Column(Boolean, nullable=False, default=True)
+    autoplay_on_generate = Column(Boolean, nullable=False, default=True)
+    updated_at = Column(DateTime, default=datetime.utcnow, onupdate=datetime.utcnow)
+
+
+class Capture(Base):
+    """A single voice input capture (dictation, recording, or uploaded file).
+
+    Stores the original audio alongside the raw transcript and, optionally, a
+    refined version produced by the LLM. Refinement flags are serialized as
+    JSON so we can reproduce the prompt that generated the refined text.
+    """
+
+    __tablename__ = "captures"
+
+    id = Column(String, primary_key=True, default=lambda: str(uuid.uuid4()))
+    audio_path = Column(String, nullable=False)
+    source = Column(String, nullable=False, default="file")  # dictation | recording | file
+    language = Column(String, nullable=True)
+    duration_ms = Column(Integer, nullable=True)
+    transcript_raw = Column(Text, nullable=False, default="")
+    transcript_refined = Column(Text, nullable=True)
+    stt_model = Column(String, nullable=True)
+    llm_model = Column(String, nullable=True)
+    refinement_flags = Column(Text, nullable=True)  # JSON blob
+    created_at = Column(DateTime, default=datetime.utcnow)