160 lines
6.3 KiB
C#
160 lines
6.3 KiB
C#
using System;
|
|
using System.Diagnostics;
|
|
using System.IO;
|
|
using System.Threading.Tasks;
|
|
using Spectre.Console;
|
|
using Toak.Audio;
|
|
using Toak.Configuration;
|
|
using Toak.Api;
|
|
using Toak.Core;
|
|
using Toak.IO;
|
|
|
|
namespace Toak.Commands;
|
|
|
|
public static class ToggleCommand
|
|
{
|
|
public static async Task ExecuteAsync(bool pipeToStdout, bool copyToClipboard, bool verbose)
|
|
{
|
|
Logger.Verbose = verbose;
|
|
|
|
if (StateTracker.IsRecording())
|
|
{
|
|
var config = ConfigManager.LoadConfig();
|
|
Notifications.PlaySound(config.StopSoundPath);
|
|
|
|
if (!pipeToStdout) AnsiConsole.MarkupLine("[yellow]Stopping recording and transcribing...[/]");
|
|
if (!pipeToStdout) Notifications.Notify("Toak", "Transcribing...");
|
|
|
|
AudioRecorder.StopRecording();
|
|
|
|
Logger.LogDebug($"Loaded configuration: LLM={config.LlmModel}, Whisper={config.WhisperModel}, Typing={config.TypingBackend}");
|
|
|
|
if (string.IsNullOrWhiteSpace(config.GroqApiKey))
|
|
{
|
|
Notifications.Notify("Toak Error", "Groq API Key is not configured. Run 'toak onboard'.");
|
|
AnsiConsole.MarkupLine("[red]Groq API Key is not configured.[/] Run 'toak onboard'.");
|
|
return;
|
|
}
|
|
|
|
var groq = new GroqApiClient(config.GroqApiKey);
|
|
var wavPath = AudioRecorder.GetWavPath();
|
|
|
|
if (!File.Exists(wavPath) || new FileInfo(wavPath).Length == 0)
|
|
{
|
|
if (!pipeToStdout) Notifications.Notify("Toak", "No audio recorded.");
|
|
return;
|
|
}
|
|
|
|
try
|
|
{
|
|
var stopWatch = Stopwatch.StartNew();
|
|
|
|
// 1. STT
|
|
Logger.LogDebug($"Starting STT transcription via Whisper for {wavPath}...");
|
|
|
|
string transcript = string.Empty;
|
|
|
|
if (!pipeToStdout)
|
|
{
|
|
await AnsiConsole.Status().StartAsync("Transcribing...", async ctx => {
|
|
transcript = await groq.TranscribeAsync(wavPath, config.WhisperLanguage, config.WhisperModel);
|
|
});
|
|
}
|
|
else
|
|
{
|
|
transcript = await groq.TranscribeAsync(wavPath, config.WhisperLanguage, config.WhisperModel);
|
|
}
|
|
|
|
Logger.LogDebug($"Raw transcript received: '{transcript}'");
|
|
|
|
if (string.IsNullOrWhiteSpace(transcript))
|
|
{
|
|
if (!pipeToStdout) Notifications.Notify("Toak", "No speech detected.");
|
|
return;
|
|
}
|
|
|
|
// 2. LLM Refinement
|
|
var detectedSkill = Toak.Core.Skills.SkillRegistry.DetectSkill(transcript, config.ActiveSkills);
|
|
string systemPrompt;
|
|
if (detectedSkill != null)
|
|
{
|
|
Logger.LogDebug($"Skill detected: {detectedSkill.Name}");
|
|
if (!pipeToStdout) Notifications.Notify("Toak Skill Detected", detectedSkill.Name);
|
|
systemPrompt = detectedSkill.GetSystemPrompt(transcript);
|
|
}
|
|
else
|
|
{
|
|
systemPrompt = PromptBuilder.BuildPrompt(config);
|
|
}
|
|
|
|
bool isExecutionSkill = detectedSkill != null && detectedSkill.HandlesExecution;
|
|
|
|
// 3. Output
|
|
if (isExecutionSkill || pipeToStdout || copyToClipboard)
|
|
{
|
|
Logger.LogDebug("Starting LLM text refinement (synchronous)...");
|
|
|
|
string finalText = string.Empty;
|
|
if (!pipeToStdout) {
|
|
await AnsiConsole.Status().StartAsync("Refining text...", async ctx => {
|
|
finalText = await groq.RefineTextAsync(transcript, systemPrompt, config.LlmModel);
|
|
});
|
|
} else {
|
|
finalText = await groq.RefineTextAsync(transcript, systemPrompt, config.LlmModel);
|
|
}
|
|
|
|
Logger.LogDebug($"Refined text received: '{finalText}'");
|
|
if (string.IsNullOrWhiteSpace(finalText))
|
|
{
|
|
if (!pipeToStdout) Notifications.Notify("Toak", "Dropped short or empty audio.");
|
|
return;
|
|
}
|
|
|
|
if (isExecutionSkill)
|
|
{
|
|
detectedSkill!.Execute(finalText);
|
|
stopWatch.Stop();
|
|
Notifications.Notify("Toak", $"Skill executed in {stopWatch.ElapsedMilliseconds}ms");
|
|
}
|
|
else if (pipeToStdout)
|
|
{
|
|
Console.WriteLine(finalText);
|
|
}
|
|
else
|
|
{
|
|
ClipboardManager.Copy(finalText);
|
|
stopWatch.Stop();
|
|
Notifications.Notify("Toak", $"Copied to clipboard in {stopWatch.ElapsedMilliseconds}ms");
|
|
}
|
|
}
|
|
else
|
|
{
|
|
Logger.LogDebug("Starting LLM text refinement (streaming)...");
|
|
var tokenStream = groq.RefineTextStreamAsync(transcript, systemPrompt, config.LlmModel);
|
|
Logger.LogDebug("Starting to inject text...");
|
|
await TextInjector.InjectStreamAsync(tokenStream, config.TypingBackend);
|
|
stopWatch.Stop();
|
|
Notifications.Notify("Toak", $"Done in {stopWatch.ElapsedMilliseconds}ms");
|
|
}
|
|
}
|
|
catch (Exception ex)
|
|
{
|
|
if (!pipeToStdout) Notifications.Notify("Toak Error", ex.Message);
|
|
if (!pipeToStdout) AnsiConsole.MarkupLine($"[red]Error:[/] {ex.Message}");
|
|
}
|
|
finally
|
|
{
|
|
if (File.Exists(wavPath)) File.Delete(wavPath);
|
|
}
|
|
}
|
|
else
|
|
{
|
|
// Start recording
|
|
if (!pipeToStdout) AnsiConsole.MarkupLine("[green]Starting recording...[/]");
|
|
var config = ConfigManager.LoadConfig();
|
|
Notifications.PlaySound(config.StartSoundPath);
|
|
AudioRecorder.StartRecording();
|
|
}
|
|
}
|
|
}
|