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/app.py

@@ -47,7 +47,7 @@ from fastapi.middleware.cors import CORSMiddleware
 from urllib.parse import quote
 
 from . import __version__, config, database
-from .services import tts, transcribe
+from .services import tts, transcribe, llm
 from .database import get_db
 from .utils.platform_detect import get_backend_type
 from .utils.progress import get_progress_manager
@@ -276,6 +276,10 @@ def _register_lifecycle(application: FastAPI) -> None:
             transcribe.unload_whisper_model()
         except Exception:
             logger.exception("Failed to unload Whisper model")
+        try:
+            llm.unload_llm_model()
+        except Exception:
+            logger.exception("Failed to unload LLM model")
 
 
 app = create_app()