setup project with daemon, socket, cmd, air, notifying, state

2025-08-07 00:01:49 +02:00
parent d3fc5ee3a4
commit f7936610c9
11 changed files with 457 additions and 25 deletions
@@ -0,0 +1,46 @@
+root = "."
+testdata_dir = "testdata"
+tmp_dir = "tmp"
+
+[build]
+  args_bin = ["serve"]
+  bin = "./tmp/hyprvoice"
+  cmd = "go install ./cmd/hyprvoice && go build -o ./tmp/hyprvoice ./cmd/hyprvoice"
+  delay = 100
+  exclude_dir = ["assets", "tmp", "vendor", "testdata"]
+  exclude_file = []
+  exclude_regex = ["_test.go"]
+  exclude_unchanged = false
+  follow_symlink = false
+  full_bin = ""
+  include_dir = []
+  include_ext = ["go", "mod", "sum"]
+  include_file = []
+  kill_delay = "1s"
+  log = "build-errors.log"
+  poll = false
+  poll_interval = 0
+  post_cmd = []
+  pre_cmd = ["./tmp/hyprvoice stop 2>/dev/null || true"]
+  rerun = true
+  rerun_delay = 200
+  send_interrupt = false
+  stop_on_error = false
+
+[color]
+  app = ""
+  build = "yellow"
+  main = "magenta"
+  runner = "green"
+  watcher = "cyan"
+
+[log]
+  main_only = false
+  time = false
+
+[misc]
+  clean_on_exit = false
+
+[screen]
+  clear_on_rebuild = false
+  keep_scroll = true
@@ -0,0 +1,33 @@
+# Binaries for programs and plugins
+*.exe
+*.exe~
+*.dll
+*.so
+*.dylib
+
+# Test binary, built with `go test -c`
+*.test
+
+# Code coverage profiles and other test artifacts
+*.out
+coverage.*
+*.coverprofile
+profile.cov
+
+# Dependency directories (remove the comment below to include it)
+# vendor/
+
+# Go workspace file
+go.work
+go.work.sum
+
+# env file
+.env
+
+# Editor/IDE
+# .idea/
+# .vscode/
+
+# Output binaries
+hyprvoice
+tmp/*
@@ -1,26 +1,28 @@
 # Hyprvoice

-> **Voice‑powered typing for Wayland/Hyprland desktops** — press a global shortcut, speak, and watch words appear in whatever window you’re focused on.
+> **Voice‑powered typing for Wayland/Hyprland desktops** — press a global shortcut, speak, and watch words appear in whatever window you're focused on.
+
+**🚧 Early Development Status:** This project is currently in early development. Not ready for production use yet.

 ---

 ## Why does this hyprvoice exist?

-Typing is slow, repetitive strain injuries are real, and proprietary speech‑to‑text solutions leak your data. This project aims to give Wayland users a fast, privacy‑respecting alternative that works entirely on their own hardware _or_ any cloud ASR they trust.
+Typing is slow, repetitive strain injuries are real. This project aims to give Wayland users a fast, privacy‑respecting alternative that works entirely on their own hardware _or_ any cloud ASR they trust.

 ---

-## Key Features
+## Current Implementation Status

-| Category                  | Highlights                                                                                                   |
-| ------------------------- | ------------------------------------------------------------------------------------------------------------ |
-| **Hot‑key daemon**        | Background service triggered by a global shortcut (via `hyprctl dispatch exec …` or other compositor hooks). |
-| **Live audio capture**    | Low‑latency PipeWire input with optional VAD/noise gate.                                                     |
-| **Pluggable ASR**         | 🔌 Local Whisper (via `whisper.cpp`) or cloud APIs (OpenAI, Deepgram, AssemblyAI). Select at runtime.        |
-| **Optional LLM polish**   | Feed raw transcript into a local Ollama model or GPT‑4o to add punctuation, change tone, etc.                |
-| **Text injection**        | `wtype`/`ydotool` sends keystrokes to the focused surface; clipboard fallback for stubborn clients.          |
-| **Zero‑friction config**  | Single `~/.config/hyprvoice/config.toml` with sensible defaults and live reload on SIGHUP.                   |
-| **Cross‑platform binary** | Static Go build; no Python environment required.                                                             |
+| Component                 | Status  | Description                                                  |
+| ------------------------- | ------- | ------------------------------------------------------------ |
+| **Hot‑key daemon**        | ✅ Done | Background service with Unix socket IPC for command handling |
+| **Desktop notifications** | ✅ Done | Recording state changes via `notify-send`                    |
+| **Service management**    | ✅ Done | Install/remove systemd user service with embedded unit file  |
+| **Live audio capture**    | 🔄 TODO | PipeWire input with VAD/noise gate                           |
+| **ASR backends**          | 🔄 TODO | Local Whisper or cloud APIs (OpenAI, Deepgram, AssemblyAI)   |
+| **Text injection**        | 🔄 TODO | `wtype`/`ydotool` keystrokes to focused window               |
+| **Configuration**         | 🔄 TODO | TOML config file with runtime reload                         |

 ---

@@ -39,13 +41,15 @@ hyprvoice-install run --backend whispercpp
 systemctl --user enable --now hyprvoice.service

 # 4. Add a key binding in Hyprland conf
-bind = $mod, R, exec, hyprvoice toggle
+bind = SUPER, R, exec, hyprvoice toggle
 ```

 ---

 ## Configuration file (`~/.config/hyprvoice/config.toml`)

+**Note:** Configuration file support is not yet implemented. This shows the planned format:
+
 ```toml
 [asr]
 backend = "whispercpp"      # whispercpp | openai
@@ -68,22 +72,46 @@ All options are documented in the sample config generated by `--init`.

 ---

-## Architecture Overview
+## Architecture

 ```
-┌──────────┐   PCM    ┌──────────┐  chunks  ┌──────────┐  text  ┌──────────┐
-│ Hot‑key  │────────▶│  Audio   │────────▶│   ASR    │──────▶│  Inject  │
-│ Listener │         │ Capture  │         │ Adapter  │       │  (wtype) │
-└──────────┘         └──────────┘         └──────────┘       └──────────┘
-                         ▲                       │                │
-                         │  stats / errors       │                ▼
-                         └──────────────┬────────┘         ┌──────────┐
-                                        │                  │ Desktop  │
-                                        └──────────────────▶   UI     │
-                                                           └──────────┘
+┌──────────────┐   Unix Socket   ┌──────────────┐   PCM    ┌──────────┐
+│ CLI Client   │◄────────────────│ Hot‑key      │────────▶│  Audio   │
+│ (toggle/stop)│                 │ Daemon       │         │ Capture  │
+└──────────────┘                 │ (hotkeydaemon│         │ (pipewire│
+                                 │ + bus)       │         │ + VAD)   │
+                                 └──────────────┘         └──────────┘
+                                        │                       │
+                                        │ notify-send           │ chunks
+                                        ▼                       ▼
+                                 ┌──────────────┐         ┌──────────┐
+                                 │ Desktop      │         │   ASR    │
+                                 │ Notification │         │ Adapter  │
+                                 └──────────────┘         │(whisper/ │
+                                                          │ openai)  │
+                                                          └──────────┘
+                                                                 │
+                                                                 │ text
+                                                                 ▼
+                                                          ┌──────────┐
+                                                          │  Inject  │
+                                                          │ (wtype/  │
+                                                          │ ydotool) │
+                                                          └──────────┘
 ```

-Each box is a Go package inside `internal/` so you can swap implementations without touching public APIs.
+**Planned Components:**
+
+- `cmd/hyprvoice`: CLI with Cobra commands (existing: `serve`, `toggle`, `stop`)
+- `internal/bus`: Unix socket IPC for daemon communication (✅ implemented)
+- `internal/hotkeydaemon`: Background service managing recording state (✅ implemented)
+- `internal/notify`: Desktop notifications via `notify-send` (✅ implemented)
+- `internal/audiocapture`: PipeWire input with VAD/noise gate (🔄 TODO)
+- `internal/asr`: ASR backends (Whisper, OpenAI, etc.) (🔄 TODO)
+- `internal/inject`: Text injection via wtype/ydotool (🔄 TODO)
+- `internal/config`: TOML configuration with runtime reload (🔄 TODO)
+
+Each box will be a Go package inside `internal/` so you can swap implementations without touching public APIs.

 ---

@@ -0,0 +1,98 @@
+package main
+
+import (
+	"fmt"
+
+	"github.com/leonardotrapani/hyprvoice/internal/bus"
+	"github.com/leonardotrapani/hyprvoice/internal/hotkeydaemon"
+	"github.com/spf13/cobra"
+)
+
+func main() {
+	_ = rootCmd.Execute()
+}
+
+var rootCmd = &cobra.Command{
+	Use:   "hyprvoice",
+	Short: "Voice-powered typing for Wayland/Hyprland",
+}
+
+func init() {
+	rootCmd.AddCommand(
+		serveCmd(),
+		toggleCmd(),
+		statusCmd(),
+		versionCmd(),
+		stopCmd(),
+	)
+}
+
+func serveCmd() *cobra.Command {
+	return &cobra.Command{
+		Use:   "serve",
+		Short: "Run the hotkey daemon",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			return (hotkeydaemon.New(nil)).Run()
+		},
+	}
+}
+
+func toggleCmd() *cobra.Command {
+	return &cobra.Command{
+		Use:   "toggle",
+		Short: "Toggle recording on/off",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			resp, err := bus.SendCommand('t')
+			if err != nil {
+				return fmt.Errorf("failed to toggle: %w", err)
+			}
+			fmt.Print(resp) // print STATUS line
+			return nil
+		},
+	}
+}
+
+func statusCmd() *cobra.Command {
+	return &cobra.Command{
+		Use:   "status",
+		Short: "Get current recording status",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			resp, err := bus.SendCommand('s')
+			if err != nil {
+				return fmt.Errorf("failed to get status: %w", err)
+			}
+			fmt.Print(resp) // print STATUS line
+			return nil
+		},
+	}
+}
+
+func versionCmd() *cobra.Command {
+	return &cobra.Command{
+		Use:   "version",
+		Short: "Get protocol version",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			resp, err := bus.SendCommand('v')
+			if err != nil {
+				return fmt.Errorf("failed to get version: %w", err)
+			}
+			fmt.Print(resp) // print STATUS proto= line
+			return nil
+		},
+	}
+}
+
+func stopCmd() *cobra.Command {
+	return &cobra.Command{
+		Use:   "stop",
+		Short: "Stop the hotkey daemon",
+		RunE: func(cmd *cobra.Command, args []string) error {
+			resp, err := bus.SendCommand('q')
+			if err != nil {
+				return fmt.Errorf("failed to stop daemon: %w", err)
+			}
+			fmt.Print(resp) // print OK quitting
+			return nil
+		},
+	}
+}
@@ -0,0 +1,9 @@
+module github.com/leonardotrapani/hyprvoice
+
+go 1.24.5
+
+require (
+	github.com/inconshreveable/mousetrap v1.1.0 // indirect
+	github.com/spf13/cobra v1.9.1 // indirect
+	github.com/spf13/pflag v1.0.6 // indirect
+)
@@ -0,0 +1,10 @@
+github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
+github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
+github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
+github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
+github.com/spf13/cobra v1.9.1 h1:CXSaggrXdbHK9CF+8ywj8Amf7PBRmPCOJugH954Nnlo=
+github.com/spf13/cobra v1.9.1/go.mod h1:nDyEzZ8ogv936Cinf6g1RU9MRY64Ir93oCnqb9wxYW0=
+github.com/spf13/pflag v1.0.6 h1:jFzHGLGAlb3ruxLB8MhbI6A8+AQX/2eW4qeyNZXNp2o=
+github.com/spf13/pflag v1.0.6/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
+gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
@@ -0,0 +1,57 @@
+package bus
+
+import (
+	"bufio"
+	"net"
+	"os"
+	"path/filepath"
+)
+
+const SockName = "control.sock"
+const ProtoVer = "0.1"
+
+// ~/.cache/hyprvoice/control.sock
+func SockPath() (string, error) {
+	dir, err := os.UserCacheDir()
+	if err != nil {
+		return "", err
+	}
+	hd := filepath.Join(dir, "hyprvoice")
+	return filepath.Join(hd, SockName), nil
+}
+
+func Listen() (net.Listener, error) {
+	sp, err := SockPath()
+	if err != nil {
+		return nil, err
+	}
+	if err := os.MkdirAll(filepath.Dir(sp), 0o700); err != nil {
+		return nil, err
+	}
+	_ = os.Remove(sp) // stale socket from last run
+	return net.Listen("unix", sp)
+}
+
+func Dial() (net.Conn, error) {
+	sp, err := SockPath()
+	if err != nil {
+		return nil, err
+	}
+	return net.Dial("unix", sp)
+}
+
+func SendCommand(cmd byte) (string, error) {
+	c, err := Dial()
+	if err != nil {
+		return "", err
+	}
+	defer c.Close()
+
+	_, err = c.Write([]byte{cmd, '\n'})
+	if err != nil {
+		return "", err
+	}
+
+	resp, err := bufio.NewReader(c).ReadString('\n')
+	return resp, err
+}
@@ -0,0 +1,9 @@
+package bus
+
+import "testing"
+
+func TestSockPath(t *testing.T) {
+	if _, err := SockPath(); err != nil {
+		t.Fatalf("SockPath: %v", err)
+	}
+}
@@ -0,0 +1,80 @@
+package hotkeydaemon
+
+import (
+	"bufio"
+	"fmt"
+	"net"
+	"sync"
+	"time"
+
+	"github.com/leonardotrapani/hyprvoice/internal/bus"
+	"github.com/leonardotrapani/hyprvoice/internal/notify"
+)
+
+type Daemon struct {
+	mu        sync.Mutex
+	recording bool
+	notifier  notify.Notifier
+}
+
+func New(n notify.Notifier) *Daemon {
+	if n == nil {
+		n = notify.Desktop{}
+	}
+	return &Daemon{
+		notifier: n,
+	}
+}
+
+func (d *Daemon) Rec() bool {
+	d.mu.Lock()
+	defer d.mu.Unlock()
+	return d.recording
+}
+
+func (d *Daemon) Run() error {
+	ln, err := bus.Listen()
+	if err != nil {
+		return err
+	}
+	for {
+		c, err := ln.Accept()
+		if err != nil {
+			continue
+		}
+		go d.handle(c)
+	}
+}
+
+func (d *Daemon) handle(c net.Conn) {
+	defer c.Close()
+
+	line, _ := bufio.NewReader(c).ReadString('\n')
+	if len(line) == 0 {
+		fmt.Fprint(c, "ERR empty\n")
+		return
+	}
+	cmd := line[0]
+
+	d.mu.Lock()
+	defer d.mu.Unlock()
+
+	switch cmd {
+	case 't': // toggle
+		d.recording = !d.recording
+		d.notifier.RecordingChanged(d.recording)
+		fmt.Fprintf(c, "STATUS recording=%t\n", d.recording)
+	case 's': // status
+		fmt.Fprintf(c, "STATUS recording=%t\n", d.recording)
+	case 'v': // protocol version
+		fmt.Fprintf(c, "STATUS proto=%s\n", bus.ProtoVer)
+	case 'q': // quit daemon
+		fmt.Fprint(c, "OK quitting\n")
+		go func() {
+			time.Sleep(100 * time.Millisecond) // give time for client to read
+			panic("daemon exit requested")
+		}()
+	default:
+		fmt.Fprintf(c, "ERR unknown=%q\n", cmd)
+	}
+}
@@ -0,0 +1,29 @@
+package hotkeydaemon
+
+import (
+	"testing"
+	"time"
+
+	"github.com/leonardotrapani/hyprvoice/internal/bus"
+	"github.com/leonardotrapani/hyprvoice/internal/notify"
+)
+
+func TestToggle(t *testing.T) {
+	d := New(notify.Nop{})
+	go d.Run()
+	time.Sleep(50 * time.Millisecond) // give listener time to start
+	defer bus.SendCommand('q')
+
+	if out, _ := bus.SendCommand('t'); out != "STATUS recording=true\n" {
+		t.Fatalf("unexpected: %s", out)
+	}
+	if !d.Rec() {
+		t.Fatalf("state should be true after first toggle")
+	}
+	if out, _ := bus.SendCommand('t'); out != "STATUS recording=false\n" {
+		t.Fatalf("unexpected: %s", out)
+	}
+	if d.Rec() {
+		t.Fatalf("state should be false after second toggle")
+	}
+}
@@ -0,0 +1,33 @@
+package notify
+
+import (
+	"fmt"
+	"os/exec"
+)
+
+type Notifier interface {
+	RecordingChanged(on bool)
+	Error(msg string)
+}
+
+type Desktop struct{}
+
+func (Desktop) RecordingChanged(on bool) {
+	state := "Stopped"
+	if on {
+		state = "Started"
+	}
+	exec.Command("notify-send", "-a", "Hyprvoice",
+		fmt.Sprintf("Hyprvoice: %s Recording", state)).Run()
+}
+
+func (Desktop) Error(msg string) {
+	exec.Command("notify-send", "-a", "Hyprvoice", "-u", "critical", msg).Run()
+}
+
+// Nop is a Notifier that does absolutely nothing.
+// Useful in unit tests or headless builds.
+type Nop struct{}
+
+func (Nop) RecordingChanged(on bool) {}
+func (Nop) Error(msg string)         {}