🤖 Auto-deploy from GitHub (push) - 4cfe07e - 2025-08-05 00:42:03 UTC

README.md

@@ -11,33 +11,13 @@ license: mit
 
 # Fitness AI Assistant
 
-Your personal AI-powered fitness and nutrition coach built with Gradio.
-
-## Features
-
-- **Personalized Fitness Plans**: Get customized workout routines based on your goals and fitness level
-- **Nutrition Guidance**: Receive tailored dietary advice and meal planning suggestions  
-- **Progress Tracking**: Monitor your fitness journey with AI-powered insights
-- **Expert Knowledge**: Access evidence-based fitness and nutrition information
+Your personal AI-powered fitness and nutrition coach.
 
 ## How to Use
 
-1. Start a conversation by describing your fitness goals
-2. Ask questions about workouts, nutrition, or health
-3. Get personalized recommendations and guidance
-4. Follow up with specific questions for detailed advice
-
-## Technology
-
-This app is built using:
-- **Gradio** for the web interface
-- **OpenAI GPT models** for intelligent conversations
-- **Custom fitness knowledge base** for specialized guidance
-
-## Getting Started
-
-Simply type your fitness-related question or goal in the chat interface below!
-
----
+1. Describe your fitness goals
+2. Ask about workouts or nutrition  
+3. Get personalized recommendations
+4. Use voice input by clicking the microphone
 
-*Note: This AI assistant provides general fitness and nutrition guidance. Always consult with healthcare professionals for medical advice or before starting new exercise programs.*
+*Always consult healthcare professionals before starting new exercise programs.*

README_HF.md

@@ -11,33 +11,13 @@ license: mit
 
 # Fitness AI Assistant
 
-Your personal AI-powered fitness and nutrition coach built with Gradio.
-
-## Features
-
-- **Personalized Fitness Plans**: Get customized workout routines based on your goals and fitness level
-- **Nutrition Guidance**: Receive tailored dietary advice and meal planning suggestions  
-- **Progress Tracking**: Monitor your fitness journey with AI-powered insights
-- **Expert Knowledge**: Access evidence-based fitness and nutrition information
+Your personal AI-powered fitness and nutrition coach.
 
 ## How to Use
 
-1. Start a conversation by describing your fitness goals
-2. Ask questions about workouts, nutrition, or health
-3. Get personalized recommendations and guidance
-4. Follow up with specific questions for detailed advice
-
-## Technology
-
-This app is built using:
-- **Gradio** for the web interface
-- **OpenAI GPT models** for intelligent conversations
-- **Custom fitness knowledge base** for specialized guidance
-
-## Getting Started
-
-Simply type your fitness-related question or goal in the chat interface below!
-
----
+1. Describe your fitness goals
+2. Ask about workouts or nutrition  
+3. Get personalized recommendations
+4. Use voice input by clicking the microphone
 
-*Note: This AI assistant provides general fitness and nutrition guidance. Always consult with healthcare professionals for medical advice or before starting new exercise programs.*
+*Always consult healthcare professionals before starting new exercise programs.*

apps/gradio-app/README.md

@@ -1,50 +0,0 @@
-# Fitness Gradio App
-
-Web interface for the Fitness AI Assistant using Gradio with voice input and text-to-speech support.
-
-## Features
-
-- Interactive chat interface with multimodal input
-- **Voice input** via microphone button (powered by Groq Whisper)
-- **Text-to-Speech output** with 19 English and 4 Arabic voices (powered by Groq PlayAI TTS)
-- Multi-provider model support (Groq, Anthropic, OpenAI)
-- Real-time streaming responses
-- Fitness plan generation
-- Mobile-friendly design
-
-## Quick Start
-
-```bash
-# Set your API key for voice functionality and TTS
-$env:GROQ_API_KEY = "your-groq-api-key"
-
-# Install and run
-poetry install
-poetry run python -m fitness_gradio.main
-```
-
-## Voice & TTS Setup
-
-1. Get a [Groq API key](https://console.groq.com/keys)
-2. Set `GROQ_API_KEY` environment variable
-3. **Voice Input**: Click the microphone button in the chat interface
-4. **Text-to-Speech**: Enable the "🔊 Enable Text-to-Speech" checkbox
-5. Allow browser microphone access when prompted (for voice input)
-
-### Available TTS Voices
-
-**English (playai-tts)**: 19 voices including Celeste-PlayAI (default), Fritz-PlayAI, Arista-PlayAI, Atlas-PlayAI, Basil-PlayAI, Briggs-PlayAI, Calum-PlayAI, Cheyenne-PlayAI, and more.
-
-**Arabic (playai-tts-arabic)**: 4 voices including Amira-PlayAI (default), Ahmad-PlayAI, Khalid-PlayAI, Nasser-PlayAI.
-
-See [VOICE_SETUP.md](VOICE_SETUP.md) for detailed setup instructions.
-
-## Configuration
-
-Optional environment variables:
-```bash
-GROQ_API_KEY=your-groq-key          # Required for voice input
-AI_MODEL=llama-3.3-70b-versatile    # Optional model selection
-ANTHROPIC_API_KEY=your-anthropic-key # For Claude models
-OPENAI_API_KEY=your-openai-key       # For GPT models
-```

shared/README.md

@@ -1,20 +1,8 @@
 # Fitness Core Library
 
-Shared business logic, AI agents, and utilities for the Fitness App ecosystem.
-
-## Components
-
-- **agents/**: AI agent implementations and model management
-- **models/**: Pydantic data models 
-- **services/**: Core business logic and conversation management
-- **utils/**: Configuration, logging, and utility functions
-
-## Usage
-
-This library is designed to be imported by various frontend applications (Gradio, FastAPI, CLI, etc.)
+Shared AI agents and business logic.
 
 ```python
 from fitness_core.agents import FitnessAgent
-from fitness_core.models import FitnessPlan
 from fitness_core.services import ConversationManager
 ```

shared/src/fitness_core/agents/__init__.py

@@ -2,7 +2,8 @@
 Agents module for the fitness core library.
 """
 from .fitness_agent import FitnessAgent
-from .models import FitnessPlan, AgentResponse, ConversationMessage, AgentConfig
+from .models import AgentResponse, ConversationMessage, AgentConfig
+from .structured_output_models import FitnessPlan
 from .providers import ModelProvider
 
 __all__ = [

shared/src/fitness_core/agents/models.py

@@ -4,13 +4,11 @@ Pydantic models for the fitness agent.
 from pydantic import BaseModel, Field
 from typing import Optional, List
 from datetime import datetime, date
-from .structured_output_models import FitnessPlan
 
 
 class AgentResponse(BaseModel):
     """Standard agent response format."""
     content: str
-    plan: Optional[FitnessPlan] = None
     metadata: Optional[dict] = None
 
 

shared/src/fitness_core/agents/tools.py

@@ -6,8 +6,7 @@ from dataclasses import dataclass
 from datetime import date, timedelta
 from agents import function_tool, RunContextWrapper
 
-from .models import FitnessPlan
-from .structured_output_models import TrainingDay
+from .structured_output_models import FitnessPlan, TrainingDay
 
 
 @dataclass
@@ -56,7 +55,6 @@ def build_fitness_schedule(fitness_plan: FitnessPlan, start_date: Optional[date]
         split_current_date = split_start_date
         
         # Calculate how many days this split's cycle is
-        days_per_cycle = len(split.training_days)
         week_number = 1
         
         # Continue cycling through the split until we reach the end date or run out of splits
@@ -225,7 +223,7 @@ FITNESS_TOOLS = {
         - training_plan: Detailed training/workout information with splits and days
         - meal_plan: Comprehensive nutrition and meal planning details
         - start_date: When the plan should begin (defaults to today)
-        - total_duration_weeks: Total duration of the plan
+        - target_date: Optional end date for the plan
 
         This tool automatically builds a date-based schedule and saves the plan to the FitnessAgent class.