Spaces:
Running
Running
Upload 9 files
Browse filesPatch to add configurable API keys
- ui/__pycache__/handlers.cpython-313.pyc +0 -0
- ui/__pycache__/layout.cpython-313.pyc +0 -0
- ui/handlers.py +22 -0
- ui/layout.py +27 -0
- voice.py +34 -30
ui/__pycache__/handlers.cpython-313.pyc
CHANGED
|
Binary files a/ui/__pycache__/handlers.cpython-313.pyc and b/ui/__pycache__/handlers.cpython-313.pyc differ
|
|
|
ui/__pycache__/layout.cpython-313.pyc
CHANGED
|
Binary files a/ui/__pycache__/layout.cpython-313.pyc and b/ui/__pycache__/layout.cpython-313.pyc differ
|
|
|
ui/handlers.py
CHANGED
|
@@ -115,6 +115,28 @@ class UIHandlers:
|
|
| 115 |
return (f"ℹ️ Using Mock AI for demo (Error: {str(e)}) 🎭",
|
| 116 |
f"**AI Provider:** `MOCK AI (Error Fallback)`")
|
| 117 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 118 |
def process_onboarding(self, project_description: str) -> tuple:
|
| 119 |
"""Process onboarding and generate tasks."""
|
| 120 |
# Default UI updates for failure cases (no change to timer/monitoring)
|
|
|
|
| 115 |
return (f"ℹ️ Using Mock AI for demo (Error: {str(e)}) 🎭",
|
| 116 |
f"**AI Provider:** `MOCK AI (Error Fallback)`")
|
| 117 |
|
| 118 |
+
def reconfigure_agent(self, provider: str, api_key: str, eleven_key: str) -> tuple:
|
| 119 |
+
"""
|
| 120 |
+
Re-configure the agent with user-provided keys (Demo Mode).
|
| 121 |
+
"""
|
| 122 |
+
# Update Environment Variables
|
| 123 |
+
if api_key.strip():
|
| 124 |
+
if provider == "openai":
|
| 125 |
+
os.environ["OPENAI_API_KEY"] = api_key
|
| 126 |
+
elif provider == "anthropic":
|
| 127 |
+
os.environ["ANTHROPIC_API_KEY"] = api_key
|
| 128 |
+
elif provider == "gemini":
|
| 129 |
+
os.environ["GEMINI_API_KEY"] = api_key
|
| 130 |
+
|
| 131 |
+
if eleven_key.strip():
|
| 132 |
+
os.environ["ELEVEN_API_KEY"] = eleven_key
|
| 133 |
+
# Re-init voice
|
| 134 |
+
from voice import voice_generator
|
| 135 |
+
voice_generator.initialize()
|
| 136 |
+
|
| 137 |
+
# Re-initialize Agent
|
| 138 |
+
return self.initialize_agent(provider)
|
| 139 |
+
|
| 140 |
def process_onboarding(self, project_description: str) -> tuple:
|
| 141 |
"""Process onboarding and generate tasks."""
|
| 142 |
# Default UI updates for failure cases (no change to timer/monitoring)
|
ui/layout.py
CHANGED
|
@@ -95,6 +95,33 @@ def create_app(ui_handlers, pomodoro_timer: PomodoroTimer, launch_mode: str, ai_
|
|
| 95 |
gr.Markdown("""
|
| 96 |
> ℹ️ **Demo Mode**: Use the text area in Monitor tab to simulate your workspace.
|
| 97 |
""")
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 98 |
else:
|
| 99 |
gr.Markdown("""
|
| 100 |
> ℹ️ **Local Mode**: Monitor your actual project directory.
|
|
|
|
| 95 |
gr.Markdown("""
|
| 96 |
> ℹ️ **Demo Mode**: Use the text area in Monitor tab to simulate your workspace.
|
| 97 |
""")
|
| 98 |
+
|
| 99 |
+
with gr.Accordion("⚙️ Configure Demo (Add your keys)", open=False):
|
| 100 |
+
gr.Markdown("If the default demo keys are expired, enter your own here to enable AI features.")
|
| 101 |
+
with gr.Row():
|
| 102 |
+
config_provider = gr.Dropdown(
|
| 103 |
+
label="LLM Provider",
|
| 104 |
+
choices=["openai", "anthropic", "gemini"],
|
| 105 |
+
value=ai_provider
|
| 106 |
+
)
|
| 107 |
+
config_api_key = gr.Textbox(
|
| 108 |
+
label="LLM API Key",
|
| 109 |
+
placeholder="sk-...",
|
| 110 |
+
type="password"
|
| 111 |
+
)
|
| 112 |
+
config_eleven_key = gr.Textbox(
|
| 113 |
+
label="ElevenLabs Key (Optional)",
|
| 114 |
+
placeholder="sk-...",
|
| 115 |
+
type="password"
|
| 116 |
+
)
|
| 117 |
+
config_save_btn = gr.Button("💾 Save & Re-Initialize", variant="primary")
|
| 118 |
+
|
| 119 |
+
config_save_btn.click(
|
| 120 |
+
fn=ui_handlers.reconfigure_agent,
|
| 121 |
+
inputs=[config_provider, config_api_key, config_eleven_key],
|
| 122 |
+
outputs=[init_status, ai_provider_display],
|
| 123 |
+
api_name=False
|
| 124 |
+
)
|
| 125 |
else:
|
| 126 |
gr.Markdown("""
|
| 127 |
> ℹ️ **Local Mode**: Monitor your actual project directory.
|
voice.py
CHANGED
|
@@ -14,53 +14,57 @@ class VoiceGenerator:
|
|
| 14 |
Handles text-to-speech generation using ElevenLabs API.
|
| 15 |
Designed for graceful degradation - never crashes if voice unavailable.
|
| 16 |
"""
|
| 17 |
-
|
| 18 |
def __init__(self):
|
| 19 |
"""Initialize ElevenLabs client if API key available."""
|
|
|
|
|
|
|
|
|
|
|
|
|
| 20 |
self.client = None
|
| 21 |
self.available = False
|
| 22 |
self.voice_id = "JBFqnCBsd6RMkjVDRZzb" # George - friendly, clear voice
|
| 23 |
self.model_id = "eleven_turbo_v2_5" # Fast, low-latency model
|
| 24 |
-
|
| 25 |
try:
|
| 26 |
# Check for API key (demo key first, then user key)
|
| 27 |
api_key = os.getenv("DEMO_ELEVEN_API_KEY") or os.getenv("ELEVEN_API_KEY")
|
| 28 |
-
|
| 29 |
if not api_key:
|
| 30 |
print("ℹ️ ElevenLabs: No API key found. Voice feedback disabled (text-only mode).")
|
| 31 |
return
|
| 32 |
-
|
| 33 |
# Try to initialize client
|
| 34 |
from elevenlabs.client import ElevenLabs
|
| 35 |
self.client = ElevenLabs(api_key=api_key)
|
| 36 |
self.available = True
|
| 37 |
-
|
| 38 |
key_type = "demo" if os.getenv("DEMO_ELEVEN_API_KEY") else "user"
|
| 39 |
print(f"✅ ElevenLabs voice initialized ({key_type} key)")
|
| 40 |
-
|
| 41 |
except ImportError:
|
| 42 |
print("⚠️ ElevenLabs: Package not installed. Run: pip install elevenlabs")
|
| 43 |
except Exception as e:
|
| 44 |
print(f"⚠️ ElevenLabs: Initialization failed: {e}")
|
| 45 |
-
|
| 46 |
def text_to_speech(self, text: str, emotion: str = "neutral") -> Optional[str]:
|
| 47 |
"""
|
| 48 |
Convert text to speech and return path to temporary audio file.
|
| 49 |
-
|
| 50 |
Args:
|
| 51 |
text: Text to convert to speech
|
| 52 |
emotion: Emotion hint (not used in current implementation)
|
| 53 |
-
|
| 54 |
Returns:
|
| 55 |
Path to temporary MP3 file, or None if voice unavailable
|
| 56 |
"""
|
| 57 |
# Check if voice is enabled globally
|
| 58 |
if os.getenv("VOICE_ENABLED", "true").lower() == "false":
|
| 59 |
return None
|
| 60 |
-
|
| 61 |
if not self.available or not self.client:
|
| 62 |
return None
|
| 63 |
-
|
| 64 |
try:
|
| 65 |
# Generate audio using ElevenLabs API
|
| 66 |
audio = self.client.text_to_speech.convert(
|
|
@@ -69,10 +73,10 @@ class VoiceGenerator:
|
|
| 69 |
model_id=self.model_id,
|
| 70 |
output_format="mp3_44100_128"
|
| 71 |
)
|
| 72 |
-
|
| 73 |
# Convert generator/stream to bytes
|
| 74 |
audio_bytes = b"".join(audio)
|
| 75 |
-
|
| 76 |
# Save to temporary file (Gradio expects file path, not data URL)
|
| 77 |
temp_file = tempfile.NamedTemporaryFile(
|
| 78 |
delete=False,
|
|
@@ -81,63 +85,63 @@ class VoiceGenerator:
|
|
| 81 |
)
|
| 82 |
temp_file.write(audio_bytes)
|
| 83 |
temp_file.close()
|
| 84 |
-
|
| 85 |
return temp_file.name
|
| 86 |
-
|
| 87 |
except Exception as e:
|
| 88 |
# Graceful degradation - log error but don't crash
|
| 89 |
print(f"⚠️ ElevenLabs: TTS failed: {e}")
|
| 90 |
return None
|
| 91 |
-
|
| 92 |
def get_focus_message_audio(self, verdict: str, message: str) -> Optional[str]:
|
| 93 |
"""
|
| 94 |
Generate voice feedback for focus check results.
|
| 95 |
-
|
| 96 |
Args:
|
| 97 |
verdict: "On Track", "Distracted", or "Idle"
|
| 98 |
message: Text message to speak
|
| 99 |
-
|
| 100 |
Returns:
|
| 101 |
Path to temporary audio file or None
|
| 102 |
"""
|
| 103 |
if not self.available:
|
| 104 |
return None
|
| 105 |
-
|
| 106 |
# Add emotion/tone based on verdict (for future voice modulation)
|
| 107 |
emotion_map = {
|
| 108 |
"On Track": "cheerful",
|
| 109 |
"Distracted": "concerned",
|
| 110 |
"Idle": "motivating"
|
| 111 |
}
|
| 112 |
-
|
| 113 |
emotion = emotion_map.get(verdict, "neutral")
|
| 114 |
return self.text_to_speech(message, emotion=emotion)
|
| 115 |
-
|
| 116 |
def get_pomodoro_audio(self, event_type: str) -> Optional[str]:
|
| 117 |
"""
|
| 118 |
Generate voice alerts for Pomodoro timer events.
|
| 119 |
-
|
| 120 |
Args:
|
| 121 |
event_type: "work_complete" or "break_complete"
|
| 122 |
-
|
| 123 |
Returns:
|
| 124 |
Path to temporary audio file or None
|
| 125 |
"""
|
| 126 |
if not self.available:
|
| 127 |
return None
|
| 128 |
-
|
| 129 |
messages = {
|
| 130 |
"work_complete": "Great work! Time for a 5-minute break. You've earned it!",
|
| 131 |
"break_complete": "Break's over! Let's get back to work and stay focused!"
|
| 132 |
}
|
| 133 |
-
|
| 134 |
message = messages.get(event_type, "Timer complete!")
|
| 135 |
return self.text_to_speech(message, emotion="cheerful")
|
| 136 |
-
|
| 137 |
def test_voice(self) -> Dict[str, any]:
|
| 138 |
"""
|
| 139 |
Test voice generation (for setup/debugging).
|
| 140 |
-
|
| 141 |
Returns:
|
| 142 |
Dict with status, message, and optional audio data
|
| 143 |
"""
|
|
@@ -147,11 +151,11 @@ class VoiceGenerator:
|
|
| 147 |
"message": "Voice not available (no API key or initialization failed)",
|
| 148 |
"audio": None
|
| 149 |
}
|
| 150 |
-
|
| 151 |
try:
|
| 152 |
test_message = "Hello! FocusFlow voice is working perfectly!"
|
| 153 |
audio = self.text_to_speech(test_message)
|
| 154 |
-
|
| 155 |
if audio:
|
| 156 |
return {
|
| 157 |
"status": "success",
|
|
@@ -179,7 +183,7 @@ voice_generator = VoiceGenerator()
|
|
| 179 |
def get_voice_status() -> str:
|
| 180 |
"""
|
| 181 |
Get human-readable voice status for UI display.
|
| 182 |
-
|
| 183 |
Returns:
|
| 184 |
Status string like "✅ ElevenLabs Voice Enabled" or "ℹ️ Voice Disabled"
|
| 185 |
"""
|
|
|
|
| 14 |
Handles text-to-speech generation using ElevenLabs API.
|
| 15 |
Designed for graceful degradation - never crashes if voice unavailable.
|
| 16 |
"""
|
| 17 |
+
|
| 18 |
def __init__(self):
|
| 19 |
"""Initialize ElevenLabs client if API key available."""
|
| 20 |
+
self.initialize()
|
| 21 |
+
|
| 22 |
+
def initialize(self):
|
| 23 |
+
"""Initialize or re-initialize the client."""
|
| 24 |
self.client = None
|
| 25 |
self.available = False
|
| 26 |
self.voice_id = "JBFqnCBsd6RMkjVDRZzb" # George - friendly, clear voice
|
| 27 |
self.model_id = "eleven_turbo_v2_5" # Fast, low-latency model
|
| 28 |
+
|
| 29 |
try:
|
| 30 |
# Check for API key (demo key first, then user key)
|
| 31 |
api_key = os.getenv("DEMO_ELEVEN_API_KEY") or os.getenv("ELEVEN_API_KEY")
|
| 32 |
+
|
| 33 |
if not api_key:
|
| 34 |
print("ℹ️ ElevenLabs: No API key found. Voice feedback disabled (text-only mode).")
|
| 35 |
return
|
| 36 |
+
|
| 37 |
# Try to initialize client
|
| 38 |
from elevenlabs.client import ElevenLabs
|
| 39 |
self.client = ElevenLabs(api_key=api_key)
|
| 40 |
self.available = True
|
| 41 |
+
|
| 42 |
key_type = "demo" if os.getenv("DEMO_ELEVEN_API_KEY") else "user"
|
| 43 |
print(f"✅ ElevenLabs voice initialized ({key_type} key)")
|
| 44 |
+
|
| 45 |
except ImportError:
|
| 46 |
print("⚠️ ElevenLabs: Package not installed. Run: pip install elevenlabs")
|
| 47 |
except Exception as e:
|
| 48 |
print(f"⚠️ ElevenLabs: Initialization failed: {e}")
|
| 49 |
+
|
| 50 |
def text_to_speech(self, text: str, emotion: str = "neutral") -> Optional[str]:
|
| 51 |
"""
|
| 52 |
Convert text to speech and return path to temporary audio file.
|
| 53 |
+
|
| 54 |
Args:
|
| 55 |
text: Text to convert to speech
|
| 56 |
emotion: Emotion hint (not used in current implementation)
|
| 57 |
+
|
| 58 |
Returns:
|
| 59 |
Path to temporary MP3 file, or None if voice unavailable
|
| 60 |
"""
|
| 61 |
# Check if voice is enabled globally
|
| 62 |
if os.getenv("VOICE_ENABLED", "true").lower() == "false":
|
| 63 |
return None
|
| 64 |
+
|
| 65 |
if not self.available or not self.client:
|
| 66 |
return None
|
| 67 |
+
|
| 68 |
try:
|
| 69 |
# Generate audio using ElevenLabs API
|
| 70 |
audio = self.client.text_to_speech.convert(
|
|
|
|
| 73 |
model_id=self.model_id,
|
| 74 |
output_format="mp3_44100_128"
|
| 75 |
)
|
| 76 |
+
|
| 77 |
# Convert generator/stream to bytes
|
| 78 |
audio_bytes = b"".join(audio)
|
| 79 |
+
|
| 80 |
# Save to temporary file (Gradio expects file path, not data URL)
|
| 81 |
temp_file = tempfile.NamedTemporaryFile(
|
| 82 |
delete=False,
|
|
|
|
| 85 |
)
|
| 86 |
temp_file.write(audio_bytes)
|
| 87 |
temp_file.close()
|
| 88 |
+
|
| 89 |
return temp_file.name
|
| 90 |
+
|
| 91 |
except Exception as e:
|
| 92 |
# Graceful degradation - log error but don't crash
|
| 93 |
print(f"⚠️ ElevenLabs: TTS failed: {e}")
|
| 94 |
return None
|
| 95 |
+
|
| 96 |
def get_focus_message_audio(self, verdict: str, message: str) -> Optional[str]:
|
| 97 |
"""
|
| 98 |
Generate voice feedback for focus check results.
|
| 99 |
+
|
| 100 |
Args:
|
| 101 |
verdict: "On Track", "Distracted", or "Idle"
|
| 102 |
message: Text message to speak
|
| 103 |
+
|
| 104 |
Returns:
|
| 105 |
Path to temporary audio file or None
|
| 106 |
"""
|
| 107 |
if not self.available:
|
| 108 |
return None
|
| 109 |
+
|
| 110 |
# Add emotion/tone based on verdict (for future voice modulation)
|
| 111 |
emotion_map = {
|
| 112 |
"On Track": "cheerful",
|
| 113 |
"Distracted": "concerned",
|
| 114 |
"Idle": "motivating"
|
| 115 |
}
|
| 116 |
+
|
| 117 |
emotion = emotion_map.get(verdict, "neutral")
|
| 118 |
return self.text_to_speech(message, emotion=emotion)
|
| 119 |
+
|
| 120 |
def get_pomodoro_audio(self, event_type: str) -> Optional[str]:
|
| 121 |
"""
|
| 122 |
Generate voice alerts for Pomodoro timer events.
|
| 123 |
+
|
| 124 |
Args:
|
| 125 |
event_type: "work_complete" or "break_complete"
|
| 126 |
+
|
| 127 |
Returns:
|
| 128 |
Path to temporary audio file or None
|
| 129 |
"""
|
| 130 |
if not self.available:
|
| 131 |
return None
|
| 132 |
+
|
| 133 |
messages = {
|
| 134 |
"work_complete": "Great work! Time for a 5-minute break. You've earned it!",
|
| 135 |
"break_complete": "Break's over! Let's get back to work and stay focused!"
|
| 136 |
}
|
| 137 |
+
|
| 138 |
message = messages.get(event_type, "Timer complete!")
|
| 139 |
return self.text_to_speech(message, emotion="cheerful")
|
| 140 |
+
|
| 141 |
def test_voice(self) -> Dict[str, any]:
|
| 142 |
"""
|
| 143 |
Test voice generation (for setup/debugging).
|
| 144 |
+
|
| 145 |
Returns:
|
| 146 |
Dict with status, message, and optional audio data
|
| 147 |
"""
|
|
|
|
| 151 |
"message": "Voice not available (no API key or initialization failed)",
|
| 152 |
"audio": None
|
| 153 |
}
|
| 154 |
+
|
| 155 |
try:
|
| 156 |
test_message = "Hello! FocusFlow voice is working perfectly!"
|
| 157 |
audio = self.text_to_speech(test_message)
|
| 158 |
+
|
| 159 |
if audio:
|
| 160 |
return {
|
| 161 |
"status": "success",
|
|
|
|
| 183 |
def get_voice_status() -> str:
|
| 184 |
"""
|
| 185 |
Get human-readable voice status for UI display.
|
| 186 |
+
|
| 187 |
Returns:
|
| 188 |
Status string like "✅ ElevenLabs Voice Enabled" or "ℹ️ Voice Disabled"
|
| 189 |
"""
|