Release v2.0.3-beta

- Add comprehensive explanations for HA Text AI sensor attributes
- Improve readability of README.md documentation
- Provide context and usage details for each sensor attribute
- Translate comments to English with technical clarity

Changes include:
* Detailed descriptions for Model and Provider Information
* Expanded System Status attribute explanations
* Clarified Performance Metrics comments
* Added context for Conversation and Token Usage
* Improved Last Interaction Details descriptions
* Enhanced System Health attribute documentation

.github/ISSUE_TEMPLATE/bug_report.md

@@ -3,7 +3,7 @@ name: Bug report
 about: Create a report to help us improve
 title: ''
 labels: bug
-assignees: ''
+assignees: '' 
 
 ---
 

.github/ISSUE_TEMPLATE/feature_request.md

@@ -3,7 +3,7 @@ name: Feature request
 about: Suggest an idea for this project
 title: ''
 labels: enhancement
-assignees: ''
+assignees: '' 
 
 ---
 

.github/workflows/validate.yaml

@@ -0,0 +1,17 @@
+name: Validate
+
+on:
+  push:
+  pull_request:
+  schedule:
+    - cron: "0 0 * * *"
+  workflow_dispatch:
+
+jobs:
+  validate-hacs:
+    runs-on: "ubuntu-latest"
+    steps:
+      - name: HACS validation
+        uses: "hacs/action@main"
+        with:
+          category: "integration"

.gitignore

@@ -1,8 +1,40 @@
+# Python
 __pycache__/
 *.py[cod]
 *$py.class
+*.so
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Home Assistant
+.storage
+.cloud
+.google.token
+
+# IDE
+.idea/
+.vscode/
+*.swp
+*.swo
+*~
+
+# OS
 .DS_Store
-.env
-.venv
-venv/
-ENV/
+Thumbs.db
+*.psd
+*.zip
+*.txt

CONTRIBUTING.md

@@ -0,0 +1,110 @@
+# 🤝 Contributing Guide
+
+We welcome contributions to the HA Text AI project! This document will help you contribute to the project's development.
+
+## 🌟 How to Contribute
+
+### 1. Preparation
+
+1. Fork the Repository
+   - Go to the repository page on GitHub
+   - Click the "Fork" button in the top right corner
+
+2. Clone Your Fork
+   ```bash
+   git clone https://github.com/YOUR_USERNAME/ha-text-ai.git
+   cd ha-text-ai
+   ```
+
+3. Set Up Remote Repositories
+   ```bash
+   git remote add upstream https://github.com/smkrv/ha-text-ai.git
+   ```
+
+### 2. Creating a Development Branch 
+
+```bash
+# Update the main branch
+git checkout main
+git pull upstream main
+
+# Create a new branch for your feature
+git checkout -b feature/short-description-of-changes
+```
+
+### 3. Development
+
+- Follow the project's coding standards
+- Write clean and understandable code
+- Add comments when necessary
+- Create unit tests for new functionality
+
+### 4. Committing Changes
+
+```bash
+# Add modified files
+git add .
+
+# Create a meaningful commit
+git commit -m "Feat: Add [short feature description]"
+```
+
+### 5. Commit Message Style
+
+Use the following prefixes:
+- `Feat:` - new feature
+- `Fix:` - bug fixes
+- `Docs:` - documentation updates
+- `Style:` - formatting changes
+- `Refactor:` - code refactoring
+- `Test:` - adding tests
+- `Chore:` - project maintenance
+
+### 6. Pushing Changes
+
+```bash
+# Push changes to your fork
+git push origin feature/short-description-of-changes
+```
+
+### 7. Creating a Pull Request (PR)
+
+1. Go to your fork on GitHub
+2. Click "New Pull Request"
+3. Select the base branch `main` of the original repository
+4. Fill out the PR description:
+   - Brief description of changes
+   - Motivation for changes
+   - Screenshots (if applicable)
+
+### 8. Review Process
+
+- Project maintainers will review your PR
+- There may be comments and requests for changes
+- After approval, the PR will be merged
+
+## 🛠 Code Requirements
+
+- Follow PEP 8 for Python
+- Write clear and self-documenting code
+- Add type hints
+- Cover code with tests
+
+## 🐛 Found a Bug?
+
+1. Check existing Issues
+2. Create a new Issue with:
+   - Bug description
+   - Reproduction steps
+   - Home Assistant version
+   - Plugin version
+
+## 📜 License
+
+By contributing to the project, you agree to the [project's license](LICENSE).
+
+## 🤔 Questions?
+
+If you have any questions, create an Issue or contact the project maintainers.
+
+**Thank you for your contribution!** 🎉

LICENSE

@@ -19,3 +19,4 @@ AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
 LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
 OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
 SOFTWARE.
+ 

README.md

@@ -1,73 +1,132 @@
 # 🤖 HA Text AI for Home Assistant
 
-<div align="center">
+<div align="center">  
 
-![GitHub release](https://img.shields.io/github/release/smkrv/ha-text-ai.svg?style=flat-square)
-![GitHub downloads](https://img.shields.io/github/downloads/smkrv/ha-text-ai/total.svg?style=flat-square)
-![GitHub stars](https://img.shields.io/github/stars/smkrv/ha-text-ai.svg?style=social)
-![GitHub last commit](https://img.shields.io/github/last-commit/smkrv/ha-text-ai.svg?style=flat-square)
-[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](https://opensource.org/licenses/MIT)
-[![hacs_badge](https://img.shields.io/badge/HACS-Default-orange.svg?style=flat-square)](https://github.com/hacs/integration)
-[![Community Forum](https://img.shields.io/badge/Community-Forum-blue.svg?style=flat-square)](https://community.home-assistant.io/t/ha-text-ai-integration)
+![GitHub release](https://img.shields.io/github/release/smkrv/ha-text-ai.svg?style=flat-square) ![GitHub last commit](https://img.shields.io/github/last-commit/smkrv/ha-text-ai.svg?style=flat-square) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](https://opensource.org/licenses/MIT) [![hacs_badge](https://img.shields.io/badge/HACS-Custom-41BDF5.svg?style=flat-square)](https://github.com/hacs/integration) ![/README.md](https://img.shields.io/badge/language-English-green?style=flat-square) ![/README_RU.md](https://img.shields.io/badge/language-Russian-green?style=flat-square) ![](https://img.shields.io/badge/language-Deutch-green?style=flat-square)
 
+  <img src="https://github.com/smkrv/ha-text-ai/blob/524849f6a945ec62c2cf6a6b7ecd9a28b37bf0fa/misc/icons/logo.jpg" alt="HA Text AI" height="160"/>
+
+### Advanced AI Integration for Home Assistant with LLM multi-provider support
 </div>
 
 <p align="center">
-Transform your smart home experience with powerful AI assistance powered by OpenAI's GPT models. Get intelligent responses, automate complex scenarios, and enhance your home automation with natural language processing.
+Transform your smart home experience with powerful AI assistance powered by multiple AI providers including OpenAI GPT and Anthropic Claude models. Get intelligent responses, automate complex scenarios, and enhance your home automation with advanced natural language processing.
+
 </p>
 
 ---
 
+> [!IMPORTANT]
+> 🚧 ALPHA VERSION 🚧  
+> Expect: potential bugs, frequent changes, incomplete features.  
+> 🤝 Community Driven  
+>
+>  <a href="https://community.home-assistant.io/t/ha-text-ai-transforming-home-automation-with-multi-provider-language-models/799741"><img src="https://img.shields.io/badge/Community-blue?style=for-the-badge&logo=homeassistant&logoColor=white&color=03a9f4"/></a>  
+
 ## 🌟 Features
 
-- 🧠 **Advanced AI Integration**:
-  - Support for latest GPT models
+- 🧠 **Multi-Provider AI Integration**:
+  - Support for OpenAI GPT models
+  - Anthropic Claude integration
+  - Custom API endpoints
+  - Flexible model selection
+
+- 💬 **Advanced Language Processing**:
   - Context-aware responses
   - Multi-turn conversations
-- 💬 **Natural Language Control**:
-  - Control devices using everyday language
-  - Get detailed explanations and recommendations
+  - Custom system instructions
   - Natural conversation flow
-- 📝 **Smart Memory Management**:
+
+- 📝 **Enhanced Memory Management**:
   - Persistent conversation history
   - Context-aware responses
   - Customizable history limits
-- ⚡ **Performance Optimized**:
+  - Model-specific filtering
+
+- ⚡ **Performance Optimization**:
   - Efficient token usage
-  - Rate limit handling
+  - Smart rate limiting
   - Response caching
+  - Request interval control
+
 - 🎯 **Advanced Customization**:
-  - Adjustable response parameters
+  - Per-request model selection
+  - Adjustable parameters
   - Custom system prompts
-  - Model selection per request
+  - Temperature control
+
 - 🔒 **Enhanced Security**:
   - Secure API key storage
   - Rate limiting protection
   - Error handling
-- 🎨 **User Experience**:
+  - Usage monitoring
+
+- 🎨 **Improved User Experience**:
   - Intuitive configuration UI
   - Detailed sensor attributes
   - Rich service interface
+  - Model selection UI
+
 - 🔄 **Automation Integration**:
   - Event-driven responses
   - Conditional logic support
   - Template compatibility
+  - Model-specific automation
 
 ## 📋 Prerequisites
 
-- Home Assistant 2023.8.0 or newer
-- OpenAI API key ([Get one here](https://platform.openai.com/account/api-keys))
+- Home Assistant 2024.11 or later
+- Active API key from:
+  - OpenAI ([Get key](https://platform.openai.com/account/api-keys))
+  - Anthropic ([Get key](https://console.anthropic.com/))
+  - OpenRouter ([Get key](https://openrouter.ai/keys))
 - Python 3.9 or newer
 - Stable internet connection
 
+### Configuration Options
+- API Provider (OpenAI/Anthropic)
+- API Key (provider-specific)
+- Model Selection (flexible, provider-specific models)
+- Temperature (Creativity control, 0.0-2.0)
+- Max Tokens (Response length limit)
+- Request Interval (API call throttling)
+- Custom API Endpoint (optional)
+
+#### ⓘ Potentially Compatible Providers  
+The integration is designed to be flexible and may work with other providers offering OpenAI-compatible APIs:  
+- Groq  
+- Together AI  
+- Perplexity AI  
+- Mistral AI  
+- Google AI  
+- Local AI servers (like Ollama)  
+- Custom OpenAI-compatible endpoints  
+
+#### Additional Notes  
+- Not all providers guarantee full compatibility  
+- Performance may vary between providers  
+- Check individual provider's documentation  
+- Ensure your API key has sufficient credits/quota
+
+#### Provider Compatibility Requirements  
+To be compatible, a provider should support:  
+- OpenAI-like REST API structure  
+- JSON request/response format  
+- Standard authentication method  
+- Similar model parameter handling
+
 ## ⚡ Installation
 
 ### HACS Installation (Recommended)
+<a href="https://my.home-assistant.io/redirect/hacs_repository/?owner=smkrv&repository=ha-text-ai&category=Integration"><img src="https://my.home-assistant.io/badges/hacs_repository.svg" width="170" height="auto"></a>
 1. Open HACS in Home Assistant
-2. Click the "+" button
-3. Search for "HA Text AI"
-4. Click "Install"
-5. Restart Home Assistant
+2. Click on "Integrations"
+3. Click "..." in top right corner
+4. Select "Custom repositories"
+5. Add repository URL: `https://github.com/smkrv/ha-text-ai`
+6. Choose "Integration" as category
+7. Click "Download"
+8. Restart Home Assistant
 
 ### Manual Installation
 1. Download the latest release
@@ -84,16 +143,61 @@ Transform your smart home experience with powerful AI assistance powered by Open
 4. Follow the configuration steps
 
 ### Via YAML
+
+### Platform Configuration (Global Settings)
+
 ```yaml
 ha_text_ai:
-  api_key: !secret openai_api_key
-  model: gpt-3.5-turbo
-  temperature: 0.7
-  max_tokens: 1000
-  request_interval: 1.0
-  api_endpoint: https://api.openai.com/v1  # optional
+  api_provider: openai  # Required
+  api_key: !secret ai_api_key  # Required
+  model: gpt-4o-mini  # Strongly recommended
+  temperature: 0.7  # Optional
+  max_tokens: 1000  # Optional
+  request_interval: 1.0  # Optional
+  api_endpoint: https://api.openai.com/v1  # Required
+  system_prompt: |  # Optional
+    You are a home automation expert assistant.
+    Focus on practical and efficient solutions.
 ```
 
+### Sensor Configuration
+
+```yaml
+sensor:
+  - platform: ha_text_ai
+    name: "My AI Assistant"  # Required, unique identifier
+    api_provider: openai  # Optional (inherits from platform)
+    model: "gpt-4o-mini"  # Optional
+    temperature: 0.7  # Optional
+    max_tokens: 1000  # Optional
+```
+
+### 📋 Configuration Parameters
+
+#### Platform Configuration
+
+| Parameter | Type | Required | Default | Description |
+|-----------|------|----------|---------|-------------|
+| `api_provider` | String | ✅ | - | AI service provider (openai, anthropic) |
+| `api_key` | String | ✅ | - | Authentication key for AI service |
+| `model` | String | ⚠️ | Provider default | Strongly recommended: Specific AI model to use. If not specified, the provider's default model will be used |
+| `temperature` | Float | ❌ | 0.7 | Response creativity level (0.0-2.0) |
+| `max_tokens` | Integer | ❌ | 1000 | Maximum response length |
+| `request_interval` | Float | ❌ | 1.0 | Delay between API requests |
+| `api_endpoint` | URL | ⚠️ | Provider default | Custom API endpoint |
+| `system_prompt` | String | ❌ | - | Default context for AI interactions |
+
+#### Sensor Configuration
+
+| Parameter | Type | Required | Default | Description |
+|-----------|------|----------|---------|-------------|
+| `platform` | String | ✅ | - | Must be `ha_text_ai` |
+| `name` | String | ✅ | - | Unique sensor identifier |
+| `api_provider` | String | ❌ | Platform setting | Override global provider |
+| `model` | String | ⚠️ | Platform setting | Recommended: Override global model. If not specified, uses platform or provider default |
+| `temperature` | Float | ❌ | Platform setting | Override global temperature |
+| `max_tokens` | Integer | ❌ | Platform setting | Override global max tokens |
+
 ## 🛠️ Available Services
 
 ### ask_question
@@ -101,9 +205,11 @@ ha_text_ai:
 service: ha_text_ai.ask_question
 data:
   question: "What's the optimal temperature for sleeping?"
-  model: "gpt-4o"  # optional
+  model: "claude-3-sonnet"  # optional
   temperature: 0.5  # optional
   max_tokens: 500  # optional
+  context_messages: 10  #optional, number of previous messages to include in context, default: 5
+  system_prompt: "You are a sleep optimization expert"  # optional
 ```
 
 ### set_system_prompt
@@ -128,115 +234,171 @@ service: ha_text_ai.clear_history
 service: ha_text_ai.get_history
 data:
   limit: 5  # optional
+  filter_model: "gpt-4o"  # optional
 ```
 
-## 🔧 Advanced Examples
+### 🏷️ HA Text AI Sensor Naming Convention
 
-### Smart Energy Management
+#### Character Restrictions  
+- Only lowercase letters (a-z)  
+- Numbers (0-9)  
+- Underscore (_)  
+- Maximum length: 50 characters (including `ha_text_ai_` prefix (14 characters)
+
+#### Sensor Name Structure
+```yaml
+# Always starts with 'sensor.ha_text_ai_'
+# You define only the part after the underscore
+sensor.ha_text_ai_YOUR_UNIQUE_SUFFIX
+
+# Examples:
+sensor.ha_text_ai_gpt      # GPT-based sensor
+sensor.ha_text_ai_claude   # Claude-based sensor
+sensor.ha_text_ai_gpt   # Custom suffix
+```
+
+#### Response Retrieval
+```yaml
+# Use your specific sensor name
+{{ state_attr('sensor.ha_text_ai_gpt', 'response') }}
+```
+
+#### Practical Usage
 ```yaml
 automation:
-  alias: "AI Energy Optimization"
-  trigger:
-    platform: time_pattern
-    hours: "/2"
-  action:
-    - service: ha_text_ai.ask_question
-      data:
-        question: >
-          Current power usage: {{ states('sensor.total_power') }}W
-          Temperature: {{ states('sensor.indoor_temperature') }}°C
-          Time: {{ now().strftime('%H:%M') }}
-          Occupancy: {{ states('binary_sensor.occupancy') }}
-
-          Analyze current energy usage and suggest optimizations
-          considering comfort and efficiency.
-        temperature: 0.3
-        max_tokens: 200
-    - service: notify.mobile_app
-      data:
-        message: "{{ states.sensor.ha_text_ai.attributes.response }}"
+  - alias: "AI Response with Custom Sensor"
+    action:
+      - service: ha_text_ai.ask_question
+        data:
+          question: "Home automation advice"
+      - service: notify.mobile
+        data:
+          message: >
+            AI Tip:
+            {{ state_attr('sensor.ha_text_ai_gpt', 'response') }}
 ```
 
-### Contextual Lighting Control
+### 💡 Naming Rules
+- Prefix is always `sensor.ha_text_ai_`
+- Add your unique identifier after the underscore
+- Use lowercase
+- No spaces allowed
+- Keep it descriptive but concise
+
+### 🔍 HA Text AI Sensor Attributes
+
+#### Model and Provider Information
 ```yaml
-automation:
-  alias: "AI Lighting Assistant"
-  trigger:
-    platform: state
-    entity_id: binary_sensor.motion
-  variables:
-    context: >
-      Time: {{ now().strftime('%H:%M') }}
-      Light Level: {{ states('sensor.illuminance') }}
-      Room: {{ trigger.to_state.attributes.room }}
-      Activity: {{ states('input_select.current_activity') }}
-      Weather: {{ states('weather.home') }}
-  action:
-    - service: ha_text_ai.ask_question
-      data:
-        question: >
-          Based on this context:
-          {{ context }}
+# Name of the AI model currently in use (e.g., latest version of GPT)  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Model') }}           # gpt-4o  
 
-          Suggest optimal lighting settings for current conditions.
-        model: gpt-3.5-turbo
-        temperature: 0.4
-    - service: scene.turn_on
-      data:
-        entity_id: >
-          {{ states.sensor.ha_text_ai.attributes.response | regex_findall('scene\.[a-z_]+') | first }}
+# Service provider for the AI model (determines API endpoint and authentication)  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Api provider') }}    # openai  
+
+# Previous or alternative model configuration  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Last model') }}      # gpt-4o
 ```
 
-## 📊 Performance Optimization
+#### System Status
+```yaml
+# Current operational readiness of the AI service API  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Api status') }}      # ready  
 
-### Token Usage
-- Use focused system prompts
-- Implement response caching
-- Clear history periodically
-- Monitor token usage
+# Indicates if a request is currently being processed  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Is processing') }}   # false  
 
-### Response Time
-- Adjust request_interval
-- Use faster models for simple queries
-- Implement timeout handling
-- Cache frequent responses
+# Shows if the API has hit its request rate limit  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Is rate limited') }} # false  
 
-### Memory Management
-- Set appropriate history limits
-- Clear unused contexts
-- Monitor memory usage
-- Use efficient data structures
+# Status of the specific API endpoint being used  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Endpoint status') }} # ready
+```
 
-## ❗ Troubleshooting
+#### Performance Metrics
+```yaml
+# Total number of successfully completed API requests  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Successful requests') }}   # 0  
 
-### API Issues
-- Verify API key validity
-- Check rate limits
-- Monitor usage quotas
-- Test endpoint accessibility
+# Number of API requests that encountered errors  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Failed requests') }}       # 0  
 
-### Performance Issues
-- Reduce max_tokens
-- Increase request_interval
-- Clear conversation history
-- Check network connectivity
+# Mean time taken to receive a response from the AI service  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Average latency') }}       # 0  
+
+# Maximum time taken for a single request-response cycle  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Max latency') }}           # 0
+```
+
+#### Conversation and Token Usage
+```yaml
+# Number of previous interactions stored in conversation context  
+{{ state_attr('sensor.ha_text_ai_gpt', 'History size') }}          # 0  
+
+# Total number of tokens used across all interactions  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Total tokens') }}          # 0  
+
+# Tokens used in the input prompts  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Prompt tokens') }}         # 0  
+
+# Tokens used in the AI's generated responses  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Completion tokens') }}     # 0
+```
+
+#### Last Interaction Details
+```yaml
+# Most recent complete response generated by the AI service  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Response') }}        # Last AI response  
+
+# The most recently processed user query or prompt  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Question') }}        # Last asked question  
+
+# Precise moment when the last interaction occurred (useful for tracking and logging)  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Last timestamp') }}  # Timestamp
+```
+
+#### System Health
+```yaml
+# Cumulative count of all errors encountered during AI service interactions  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Total errors') }}    # 0  
+
+# Indicates if the AI service is currently undergoing scheduled or emergency maintenance  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Is maintenance') }}  # false  
+
+# Total continuous operational time of the AI service (in hours or days)  
+{{ state_attr('sensor.ha_text_ai_gpt', 'Uptime') }}          # 547,58
+```
+
+### 💡 Pro Tips
+- Always check attribute existence
+- Use these attributes for monitoring and automation
+- Some values might be 0 or empty initially
 
-### Integration Issues
-- Verify HA version compatibility
-- Check component dependencies
-- Review log files
-- Update configuration
 
 ## 📘 FAQ
 
+**Q: Which AI providers are supported?**
+A: Currently OpenAI (GPT models) and Anthropic (Claude models) are supported, with more providers planned.
+
+**Q: How can I reduce API costs?**
+A: Use GPT-3.5-Turbo or Claude-3-Sonnet for most queries, implement caching, and optimize token usage.
+
+**Q: Are there limitations on the number of requests?**
+A: Depends on your API provider's plan. We recommend monitoring usage and implementing request throttling via `request_interval` configuration.
+
+**Q: Can I use custom models?**
+A: Yes, you can configure custom endpoints and use any compatible model by specifying it in the configuration.
+
+**Q: How do I switch between different AI providers?**
+A: Simply change the model parameter in your configuration or service calls to use the desired provider's model.
+
 **Q: How can I reduce API costs?**
 A: Use GPT-3.5-Turbo for most queries, implement caching, and optimize token usage.
 
 **Q: Is my data secure?**
-A: Yes, API keys are stored securely and data is transmitted via encrypted connections.
+A: Yes, your data is secure. The system operates entirely on your local machine, keeping your data under your control. API keys are stored securely and all external communications use encrypted connections.
 
-**Q: Can I use custom models?**
-A: Yes, configure custom endpoints and models via configuration options.
+**Q: How do context messages work?**
+A: Context messages allow the AI to remember and reference previous conversation history. By default, 5 previous messages are included, but you can customize this from 1 to 20 messages to control the conversation depth and token usage.
 
 ## 🤝 Contributing
 
@@ -252,11 +414,27 @@ Contributions welcome! Please read our [Contributing Guide](CONTRIBUTING.md).
 
 MIT License - see [LICENSE](LICENSE) for details.
 
+## 💡 Support the Project
+
+The best support is:
+- Sharing feedback
+- Contributing ideas
+- Recommending to friends
+- Reporting issues
+- Star the repository
+
+If you want to say thanks financially, you can send a small token of appreciation in USDT:
+
+**USDT Wallet (TRC10/TRC20):**
+`TXC9zYHYPfWUGi4Sv4R1ctTBGScXXQk5HZ`
+
+*Open-source is built by community passion!* 🚀
+
 ---
 
 <div align="center">
 
-Made with ❤️ for the Home Assistant Community
+Made with ❤️ and Claude 3.5 Sonnet for the Home Assistant Community
 
 [Report Bug](https://github.com/smkrv/ha-text-ai/issues) · [Request Feature](https://github.com/smkrv/ha-text-ai/issues)
 

custom_components/ha_text_ai/__init__.py

@@ -1,16 +1,24 @@
 """The HA Text AI integration."""
+from __future__ import annotations
+
 import logging
-from typing import Any, Dict, Optional
+import os
+import shutil
+from datetime import datetime, timedelta
+from typing import Any, Dict
+
+import voluptuous as vol
+from async_timeout import timeout
 
 from homeassistant.config_entries import ConfigEntry
-from homeassistant.const import CONF_API_KEY
-from homeassistant.core import HomeAssistant, ServiceCall, callback
-from homeassistant.exceptions import ConfigEntryNotReady
-from homeassistant.helpers import aiohttp_client
+from homeassistant.const import CONF_API_KEY, CONF_NAME, Platform
+from homeassistant.core import HomeAssistant, ServiceCall
+from homeassistant.exceptions import ConfigEntryNotReady, HomeAssistantError
 from homeassistant.helpers import config_validation as cv
+from homeassistant.helpers import aiohttp_client
 
 from .coordinator import HATextAICoordinator
-
+from .api_client import APIClient
 from .const import (
     DOMAIN,
     PLATFORMS,
@@ -19,208 +27,273 @@ from .const import (
     CONF_MAX_TOKENS,
     CONF_API_ENDPOINT,
     CONF_REQUEST_INTERVAL,
+    CONF_API_PROVIDER,
+    CONF_CONTEXT_MESSAGES,
+    API_PROVIDER_OPENAI,
+    API_PROVIDER_ANTHROPIC,
     DEFAULT_MODEL,
     DEFAULT_TEMPERATURE,
     DEFAULT_MAX_TOKENS,
-    DEFAULT_API_ENDPOINT,
+    DEFAULT_OPENAI_ENDPOINT,
+    DEFAULT_ANTHROPIC_ENDPOINT,
     DEFAULT_REQUEST_INTERVAL,
+    DEFAULT_CONTEXT_MESSAGES,
+    API_TIMEOUT,
+    SERVICE_ASK_QUESTION,
+    SERVICE_CLEAR_HISTORY,
+    SERVICE_GET_HISTORY,
+    SERVICE_SET_SYSTEM_PROMPT,
+    DEFAULT_MAX_HISTORY,
+    CONF_MAX_HISTORY_SIZE,
 )
 
 _LOGGER = logging.getLogger(__name__)
 
 CONFIG_SCHEMA = cv.config_entry_only_config_schema(DOMAIN)
 
-async def async_setup(hass: HomeAssistant, config: dict[str, Any]) -> bool:
+SERVICE_SCHEMA_ASK_QUESTION = vol.Schema({
+    vol.Required("instance"): cv.string,
+    vol.Required("question"): cv.string,
+    vol.Optional("system_prompt"): cv.string,
+    vol.Optional("model"): cv.string,
+    vol.Optional("temperature"): cv.positive_float,
+    vol.Optional("max_tokens"): cv.positive_int,
+    vol.Optional("context_messages"): cv.positive_int,
+})
+
+SERVICE_SCHEMA_SET_SYSTEM_PROMPT = vol.Schema({
+    vol.Required("instance"): cv.string,
+    vol.Required("prompt"): cv.string,
+})
+
+SERVICE_SCHEMA_GET_HISTORY = vol.Schema({
+    vol.Required("instance"): cv.string,
+    vol.Optional("limit"): cv.positive_int,
+    vol.Optional("filter_model"): cv.string,
+})
+
+def get_coordinator_by_instance(hass: HomeAssistant, instance: str) -> HATextAICoordinator:
+    """Get coordinator by instance name."""
+    if instance.startswith("sensor."):
+        instance = instance.replace("sensor.ha_text_ai_", "", 1)
+
+    for entry_id, coord in hass.data[DOMAIN].items():
+        if isinstance(coord, HATextAICoordinator) and coord.instance_name.lower() == instance.lower():
+            return coord
+
+    raise HomeAssistantError(f"Instance {instance} not found")
+
+async def async_setup(hass: HomeAssistant, config: Dict[str, Any]) -> bool:
     """Set up the HA Text AI component."""
     hass.data.setdefault(DOMAIN, {})
+
+    try:
+        source = os.path.join(os.path.dirname(__file__), 'icons', 'icon.svg')
+        dest_dir = os.path.join(hass.config.path('www'), 'icons')
+        os.makedirs(dest_dir, exist_ok=True)
+        dest = os.path.join(dest_dir, 'icon.png')
+        if not os.path.exists(dest):
+            shutil.copyfile(source, dest)
+    except Exception as ex:
+        _LOGGER.warning("Failed to copy custom icon: %s", str(ex))
+
+    async def async_ask_question(call: ServiceCall) -> None:
+        """Handle ask_question service."""
+        try:
+            coordinator = get_coordinator_by_instance(hass, call.data["instance"])
+            await coordinator.async_ask_question(
+                question=call.data["question"],
+                model=call.data.get("model"),
+                temperature=call.data.get("temperature"),
+                max_tokens=call.data.get("max_tokens"),
+                system_prompt=call.data.get("system_prompt"),
+                context_messages=call.data.get("context_messages"),
+            )
+        except Exception as err:
+            _LOGGER.error("Error asking question: %s", str(err))
+            raise HomeAssistantError(f"Failed to process question: {str(err)}")
+
+    async def async_clear_history(call: ServiceCall) -> None:
+        """Handle clear_history service."""
+        try:
+            coordinator = get_coordinator_by_instance(hass, call.data["instance"])
+            await coordinator.async_clear_history()
+        except Exception as err:
+            _LOGGER.error("Error clearing history: %s", str(err))
+            raise HomeAssistantError(f"Failed to clear history: {str(err)}")
+
+    async def async_get_history(call: ServiceCall) -> list:
+        """Handle get_history service."""
+        try:
+            coordinator = get_coordinator_by_instance(hass, call.data["instance"])
+            return await coordinator.async_get_history(
+                limit=call.data.get("limit"),
+                filter_model=call.data.get("filter_model")
+            )
+        except Exception as err:
+            _LOGGER.error("Error getting history: %s", str(err))
+            raise HomeAssistantError(f"Failed to get history: {str(err)}")
+
+    async def async_set_system_prompt(call: ServiceCall) -> None:
+        """Handle set_system_prompt service."""
+        try:
+            coordinator = get_coordinator_by_instance(hass, call.data["instance"])
+            await coordinator.async_set_system_prompt(call.data["prompt"])
+        except Exception as err:
+            _LOGGER.error("Error setting system prompt: %s", str(err))
+            raise HomeAssistantError(f"Failed to set system prompt: {str(err)}")
+
+    hass.services.async_register(
+        DOMAIN,
+        SERVICE_ASK_QUESTION,
+        async_ask_question,
+        schema=SERVICE_SCHEMA_ASK_QUESTION
+    )
+
+    hass.services.async_register(
+        DOMAIN,
+        SERVICE_CLEAR_HISTORY,
+        async_clear_history,
+        schema=vol.Schema({vol.Required("instance"): cv.string})
+    )
+
+    hass.services.async_register(
+        DOMAIN,
+        SERVICE_GET_HISTORY,
+        async_get_history,
+        schema=SERVICE_SCHEMA_GET_HISTORY
+    )
+
+    hass.services.async_register(
+        DOMAIN,
+        SERVICE_SET_SYSTEM_PROMPT,
+        async_set_system_prompt,
+        schema=SERVICE_SCHEMA_SET_SYSTEM_PROMPT
+    )
+
     return True
 
+async def async_check_api(session, endpoint: str, headers: dict, provider: str) -> bool:
+    """Check API availability for different providers."""
+    try:
+        if provider == API_PROVIDER_ANTHROPIC:
+            check_url = f"{endpoint}/v1/models"
+        else:  # OpenAI
+            check_url = f"{endpoint}/models"
+
+        async with timeout(API_TIMEOUT):
+            async with session.get(check_url, headers=headers) as response:
+                if response.status in [200, 404]:
+                    return True
+                elif response.status == 401:
+                    raise ConfigEntryNotReady("Invalid API key")
+                elif response.status == 429:
+                    _LOGGER.warning("Rate limit exceeded during API check")
+                    return False
+                else:
+                    _LOGGER.error("API check failed with status: %d", response.status)
+                    return False
+    except Exception as ex:
+        _LOGGER.error("API check error: %s", str(ex))
+        return False
+
 async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
     """Set up HA Text AI from a config entry."""
+    _LOGGER.debug(f"Setting up HA Text AI entry: {entry.data}")
+
     try:
+        if CONF_API_PROVIDER not in entry.data:
+            _LOGGER.error("API provider not specified")
+            raise ConfigEntryNotReady("API provider is required")
+
+        # Get configuration
         session = aiohttp_client.async_get_clientsession(hass)
+        api_provider = entry.data.get(CONF_API_PROVIDER)
+        model = entry.data.get(CONF_MODEL, DEFAULT_MODEL)
+        endpoint = entry.data.get(
+            CONF_API_ENDPOINT,
+            DEFAULT_OPENAI_ENDPOINT if api_provider == API_PROVIDER_OPENAI
+            else DEFAULT_ANTHROPIC_ENDPOINT
+        ).rstrip('/')
+        api_key = entry.data[CONF_API_KEY]
+        instance_name = entry.data.get(CONF_NAME, entry.entry_id)
+        request_interval = entry.data.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)
+        max_tokens = entry.data.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)
+        temperature = entry.data.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)
+        max_history_size = entry.data.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY)
+        context_messages = entry.data.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES)
+        is_anthropic = api_provider == API_PROVIDER_ANTHROPIC
+
+        headers = {
+            "Content-Type": "application/json",
+            "Accept": "application/json"
+        }
+
+        if is_anthropic:
+            headers["x-api-key"] = api_key
+            headers["anthropic-version"] = "2023-06-01"
+        else:
+            headers["Authorization"] = f"Bearer {api_key}"
+
+        if not await async_check_api(session, endpoint, headers, api_provider):
+            raise ConfigEntryNotReady("API connection failed")
+
+        _LOGGER.debug("Creating API client for %s with endpoint %s", api_provider, endpoint)
+
+        api_client = APIClient(
+            session=session,
+            endpoint=endpoint,
+            headers=headers,
+            api_provider=api_provider,
+            model=model,
+        )
 
         coordinator = HATextAICoordinator(
-            hass,
-            api_key=entry.data[CONF_API_KEY],
-            endpoint=entry.data.get(CONF_API_ENDPOINT, DEFAULT_API_ENDPOINT),
-            model=entry.data.get(CONF_MODEL, DEFAULT_MODEL),
-            temperature=entry.data.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE),
-            max_tokens=entry.data.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS),
-            request_interval=entry.data.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL),
-            session=session,
+            hass=hass,
+            client=api_client,
+            model=model,
+            update_interval=request_interval,
+            instance_name=instance_name,
+            max_tokens=max_tokens,
+            temperature=temperature,
+            max_history_size=max_history_size,
+            context_messages=context_messages,
+            is_anthropic=is_anthropic,
         )
 
-        try:
-            await coordinator.async_config_entry_first_refresh()
-        except Exception as refresh_ex:
-            _LOGGER.error("Failed to refresh coordinator: %s", str(refresh_ex))
-            raise ConfigEntryNotReady from refresh_ex
-
-        if not coordinator.last_update_success:
-            raise ConfigEntryNotReady("Failed to communicate with OpenAI API")
+        _LOGGER.debug(f"Created coordinator for {instance_name}")
 
+        # Store coordinator
+        hass.data.setdefault(DOMAIN, {})
         hass.data[DOMAIN][entry.entry_id] = coordinator
 
+        _LOGGER.debug(f"Stored coordinator in hass.data[{DOMAIN}][{entry.entry_id}]")
+
+        # Set up platforms
         await hass.config_entries.async_forward_entry_setups(entry, PLATFORMS)
 
-        async def async_ask_question(call: ServiceCall) -> None:
-            """Handle the ask_question service call."""
-            question = call.data.get("question", "")
-            if not question:
-                _LOGGER.error("No question provided in service call")
-                return
-
-            # Собираем все опциональные параметры
-            request_params = {}
-
-            # Обработка system_prompt
-            system_prompt = call.data.get("system_prompt")
-            if system_prompt is not None:
-                request_params["system_prompt"] = system_prompt
-
-            # Обработка model
-            model = call.data.get("model")
-            if model is not None:
-                request_params["model"] = model
-
-            # Обработка temperature
-            temperature = call.data.get("temperature")
-            if temperature is not None:
-                try:
-                    request_params["temperature"] = float(temperature)
-                except ValueError:
-                    _LOGGER.error("Invalid temperature value: %s", temperature)
-                    return
-
-            # Обработка max_tokens
-            max_tokens = call.data.get("max_tokens")
-            if max_tokens is not None:
-                try:
-                    request_params["max_tokens"] = int(max_tokens)
-                except ValueError:
-                    _LOGGER.error("Invalid max_tokens value: %s", max_tokens)
-                    return
-
-            try:
-                await coordinator.async_ask_question(question, **request_params)
-            except Exception as err:
-                _LOGGER.error("Error asking question: %s", str(err))
-
-        async def async_clear_history(call: ServiceCall) -> None:
-            """Handle the clear_history service call."""
-            try:
-                coordinator._responses.clear()
-                await coordinator.async_refresh()
-                _LOGGER.info("History cleared successfully")
-            except Exception as err:
-                _LOGGER.error("Error clearing history: %s", str(err))
-
-        async def async_get_history(call: ServiceCall) -> dict:
-            """Handle the get_history service call."""
-            try:
-                limit = call.data.get("limit", 10)
-                filter_model = call.data.get("filter_model", "")
-
-                responses = coordinator._responses
-
-                # Применяем фильтрацию по модели
-                if filter_model:
-                    filtered_responses = {
-                        k: v for k, v in responses.items()
-                        if v.get("model") == filter_model
-                    }
-                else:
-                    filtered_responses = responses.copy()
-
-                # Сортируем по времени и ограничиваем количество
-                sorted_responses = dict(
-                    sorted(
-                        filtered_responses.items(),
-                        key=lambda x: x[1]["timestamp"],
-                        reverse=True
-                    )[:limit]
-                )
-
-                return sorted_responses
-            except Exception as err:
-                _LOGGER.error("Error getting history: %s", str(err))
-                return {}
-
-        async def async_set_system_prompt(call: ServiceCall) -> None:
-            """Handle the set_system_prompt service call."""
-            prompt = call.data.get("prompt", "")
-            if prompt:
-                try:
-                    coordinator.system_prompt = prompt
-                    _LOGGER.info("System prompt updated successfully")
-                except Exception as err:
-                    _LOGGER.error("Error setting system prompt: %s", str(err))
-            else:
-                _LOGGER.error("No prompt provided in service call")
-
-        # Регистрация сервисов
-        hass.services.async_register(
-            DOMAIN,
-            "ask_question",
-            async_ask_question
-        )
-
-        hass.services.async_register(
-            DOMAIN,
-            "clear_history",
-            async_clear_history
-        )
-
-        hass.services.async_register(
-            DOMAIN,
-            "get_history",
-            async_get_history
-        )
-
-        hass.services.async_register(
-            DOMAIN,
-            "set_system_prompt",
-            async_set_system_prompt
-        )
-
-        _LOGGER.info(
-            "Successfully set up HA Text AI with model: %s",
-            entry.data.get(CONF_MODEL, DEFAULT_MODEL)
-        )
+        _LOGGER.debug(f"Setup completed for {instance_name}")
 
         return True
 
-    except Exception as ex:
-        _LOGGER.exception("Unexpected error setting up entry: %s", str(ex))
-        raise ConfigEntryNotReady from ex
+    except Exception as err:
+        _LOGGER.exception(f"Error setting up HA Text AI: {err}")
+        raise
 
 async def async_unload_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
     """Unload a config entry."""
     try:
-        if entry.entry_id not in hass.data.get(DOMAIN, {}):
-            return True
+        if entry.entry_id in hass.data[DOMAIN]:
+            coordinator = hass.data[DOMAIN][entry.entry_id]
 
-        # Удаляем все сервисы при выгрузке интеграции
-        services = ["ask_question", "clear_history", "get_history", "set_system_prompt"]
-        for service in services:
-            hass.services.async_remove(DOMAIN, service)
+            if hasattr(coordinator.client, 'shutdown'):
+                await coordinator.client.shutdown()
 
-        unload_ok = await hass.config_entries.async_unload_platforms(entry, PLATFORMS)
-        if unload_ok:
-            coordinator = hass.data[DOMAIN].pop(entry.entry_id)
             await coordinator.async_shutdown()
+            hass.data[DOMAIN].pop(entry.entry_id)
 
-        return unload_ok
+        return await hass.config_entries.async_unload_platforms(entry, PLATFORMS)
 
     except Exception as ex:
         _LOGGER.exception("Error unloading entry: %s", str(ex))
         return False
-
-async def async_reload_entry(hass: HomeAssistant, entry: ConfigEntry) -> None:
-    """Reload config entry."""
-    try:
-        await async_unload_entry(hass, entry)
-        await async_setup_entry(hass, entry)
-    except Exception as ex:
-        _LOGGER.exception("Error reloading entry: %s", str(ex))  # убрано лишнее двоеточие

custom_components/ha_text_ai/api_client.py

@@ -0,0 +1,205 @@
+"""API Client for HA Text AI."""
+import logging
+import asyncio
+from typing import Any, Dict, List, Optional
+from aiohttp import ClientSession, ClientTimeout
+from async_timeout import timeout
+
+from homeassistant.core import HomeAssistant
+from homeassistant.exceptions import HomeAssistantError
+from .const import (
+    API_TIMEOUT,
+    API_RETRY_COUNT,
+    API_PROVIDER_ANTHROPIC,
+    MIN_TEMPERATURE,
+    MAX_TEMPERATURE,
+    MIN_MAX_TOKENS,
+    MAX_MAX_TOKENS,
+)
+
+_LOGGER = logging.getLogger(__name__)
+
+
+class APIClient:
+    """API Client for OpenAI and Anthropic."""
+
+    def __init__(
+        self,
+        session: ClientSession,
+        endpoint: str,
+        headers: Dict[str, str],
+        api_provider: str,
+        model: str,
+    ) -> None:
+        """Initialize API client."""
+        self.session = session
+        self.endpoint = endpoint
+        self.headers = headers
+        self.api_provider = api_provider
+        self.model = model
+        self.timeout = ClientTimeout(total=API_TIMEOUT)
+
+    def _validate_parameters(
+        self,
+        temperature: float,
+        max_tokens: int,
+    ) -> None:
+        """Validate API parameters."""
+        if not MIN_TEMPERATURE <= temperature <= MAX_TEMPERATURE:
+            raise ValueError(
+                f"Temperature must be between {MIN_TEMPERATURE} and {MAX_TEMPERATURE}"
+            )
+        if not MIN_MAX_TOKENS <= max_tokens <= MAX_MAX_TOKENS:
+            raise ValueError(
+                f"Max tokens must be between {MIN_MAX_TOKENS} and {MAX_MAX_TOKENS}"
+            )
+
+    async def _make_request(
+        self,
+        url: str,
+        payload: Dict[str, Any],
+    ) -> Dict[str, Any]:
+        """Make API request with retry logic."""
+        _LOGGER.debug(f"API Request: URL={url}, Payload={payload}")
+        for attempt in range(API_RETRY_COUNT):
+            try:
+                async with timeout(API_TIMEOUT):
+                    async with self.session.post(
+                        url,
+                        json=payload,
+                        headers=self.headers,
+                        timeout=self.timeout,
+                    ) as response:
+                        _LOGGER.debug(f"Response status: {response.status}")
+                        if response.status != 200:
+                            error_data = await response.json()
+                            _LOGGER.error(f"API error: {error_data}")
+                            raise HomeAssistantError(f"API error: {error_data}")
+                        return await response.json()
+            except asyncio.TimeoutError:
+                _LOGGER.warning(f"Timeout on attempt {attempt + 1}")
+                if attempt == API_RETRY_COUNT - 1:
+                    raise HomeAssistantError("API request timed out")
+                await asyncio.sleep(1 * (attempt + 1))
+            except Exception as e:
+                _LOGGER.warning(f"API request failed on attempt {attempt + 1}: {str(e)}")
+                if attempt == API_RETRY_COUNT - 1:
+                    raise
+                await asyncio.sleep(1 * (attempt + 1))
+
+    async def create(
+        self,
+        model: str,
+        messages: List[Dict[str, str]],
+        temperature: float,
+        max_tokens: int,
+    ) -> Dict[str, Any]:
+        """Create completion using appropriate API."""
+        try:
+            self._validate_parameters(temperature, max_tokens)
+
+            if self.api_provider == API_PROVIDER_ANTHROPIC:
+                return await self._create_anthropic_completion(
+                    model, messages, temperature, max_tokens
+                )
+            else:
+                return await self._create_openai_completion(
+                    model, messages, temperature, max_tokens
+                )
+        except (KeyError, IndexError) as e:
+            if "'choices'" in str(e) or "'message'" in str(e):
+                raise HomeAssistantError("Failed to get a response from the AI model. Please check your internet connection and try again later.")
+            else:
+                raise
+        except Exception as e:
+            _LOGGER.error("API request failed: %s", str(e))
+            raise HomeAssistantError(f"API request failed: {str(e)}")
+
+    async def _create_openai_completion(
+        self,
+        model: str,
+        messages: List[Dict[str, str]],
+        temperature: float,
+        max_tokens: int,
+    ) -> Dict[str, Any]:
+        """Create completion using OpenAI API."""
+        url = f"{self.endpoint}/chat/completions"
+        payload = {
+            "model": model,
+            "messages": messages,
+            "temperature": temperature,
+            "max_tokens": max_tokens,
+        }
+
+        data = await self._make_request(url, payload)
+        return {
+            "choices": [
+                {
+                    "message": {"content": data["choices"][0]["message"]["content"]},
+                }
+            ],
+            "usage": {
+                "prompt_tokens": data["usage"]["prompt_tokens"],
+                "completion_tokens": data["usage"]["completion_tokens"],
+                "total_tokens": data["usage"]["total_tokens"],
+            },
+        }
+
+    async def _create_anthropic_completion(
+        self,
+        model: str,
+        messages: List[Dict[str, str]],
+        temperature: float,
+        max_tokens: int,
+    ) -> Dict[str, Any]:
+        """Create completion using Anthropic API."""
+        url = f"{self.endpoint}/v1/messages"
+
+        system_prompt = None
+        filtered_messages = []
+        for msg in messages:
+            if msg['role'] == 'system':
+                if system_prompt is None:
+                    system_prompt = msg['content']
+                else:
+                    system_prompt += f" {msg['content']}"
+            else:
+                filtered_messages.append(msg)
+
+        payload = {
+            "model": model,
+            "messages": filtered_messages,
+            "max_tokens": max_tokens,
+            "temperature": temperature,
+        }
+
+        if system_prompt:
+            payload["system"] = system_prompt
+
+        data = await self._make_request(url, payload)
+        return {
+            "choices": [
+                {
+                    "message": {"content": data["content"][0]["text"]},
+                }
+            ],
+            "usage": {
+                "prompt_tokens": data["usage"]["input_tokens"],
+                "completion_tokens": data["usage"]["output_tokens"],
+                "total_tokens": data["usage"]["input_tokens"] + data["usage"]["output_tokens"],
+            },
+        }
+
+    async def check_connection(self) -> bool:
+        """Check API connection."""
+        try:
+            await self._make_request(self.endpoint, {"test": "connection"})
+            return True
+        except Exception as e:
+            _LOGGER.error(f"Connection check failed: {str(e)}")
+            return False
+
+    async def shutdown(self) -> None:
+        """Shutdown API client."""
+        _LOGGER.debug("Shutting down API client")
+        await self.session.close()

custom_components/ha_text_ai/config_flow.py

@@ -1,19 +1,14 @@
 """Config flow for HA text AI integration."""
-from typing import Any, Dict, Optional, Tuple
-import voluptuous as vol
-import ssl
-import certifi
-import asyncio
-from async_timeout import timeout
-import aiohttp
-from urllib.parse import urlparse
+import logging
+from typing import Any, Dict, Optional
 
+import voluptuous as vol
 from homeassistant import config_entries
-from homeassistant.const import CONF_API_KEY
-import homeassistant.helpers.config_validation as cv
+from homeassistant.const import CONF_API_KEY, CONF_NAME
 from homeassistant.core import callback
-from openai import AsyncOpenAI
-from openai import OpenAIError, APIError, APIConnectionError, AuthenticationError, RateLimitError
+from homeassistant.data_entry_flow import FlowResult
+from homeassistant.helpers.aiohttp_client import async_get_clientsession
+from homeassistant.helpers import selector
 
 from .const import (
     DOMAIN,
@@ -22,235 +17,326 @@ from .const import (
     CONF_MAX_TOKENS,
     CONF_API_ENDPOINT,
     CONF_REQUEST_INTERVAL,
+    CONF_API_PROVIDER,
+    CONF_CONTEXT_MESSAGES,
+    API_PROVIDER_OPENAI,
+    API_PROVIDER_ANTHROPIC,
+    API_PROVIDERS,
     DEFAULT_MODEL,
     DEFAULT_TEMPERATURE,
     DEFAULT_MAX_TOKENS,
-    DEFAULT_API_ENDPOINT,
     DEFAULT_REQUEST_INTERVAL,
+    DEFAULT_OPENAI_ENDPOINT,
+    DEFAULT_ANTHROPIC_ENDPOINT,
+    DEFAULT_CONTEXT_MESSAGES,
+    MIN_TEMPERATURE,
+    MAX_TEMPERATURE,
+    MIN_MAX_TOKENS,
+    MAX_MAX_TOKENS,
+    MIN_REQUEST_INTERVAL,
+    DEFAULT_NAME_PREFIX,
+    DEFAULT_MAX_HISTORY,
+    CONF_MAX_HISTORY_SIZE,
 )
 
-import logging
 _LOGGER = logging.getLogger(__name__)
 
-# Create SSL context at module level
-SSL_CONTEXT = ssl.create_default_context(cafile=certifi.where())
 
-STEP_USER_DATA_SCHEMA = vol.Schema({
-    vol.Required(CONF_API_KEY): str,
-    vol.Optional(CONF_MODEL, default=DEFAULT_MODEL): str,
-    vol.Optional(
-        CONF_TEMPERATURE,
-        default=DEFAULT_TEMPERATURE
-    ): vol.All(
-        vol.Coerce(float),
-        vol.Range(min=0, max=2)
-    ),
-    vol.Optional(
-        CONF_MAX_TOKENS,
-        default=DEFAULT_MAX_TOKENS
-    ): vol.All(
-        vol.Coerce(int),
-        vol.Range(min=1, max=4096)
-    ),
-    vol.Optional(CONF_API_ENDPOINT, default=DEFAULT_API_ENDPOINT): str,
-    vol.Optional(
-        CONF_REQUEST_INTERVAL,
-        default=DEFAULT_REQUEST_INTERVAL
-    ): vol.All(
-        vol.Coerce(float),
-        vol.Range(min=0.1)
-    ),
-})
+def normalize_name(name: str) -> str:
+    """Normalize name to conform to HA naming convention using underscores."""
+    normalized = ''.join(c if c.isalnum() or c == '_' else '_' for c in name)
+    normalized = '_'.join(filter(None, normalized.split('_')))
+    return normalized.lower()
 
-async def validate_api_connection(
-    api_key: str,
-    endpoint: str,
-    model: str,
-    retry_count: int = 3,
-    retry_delay: float = 1.0
-) -> Tuple[bool, str, list]:
-    """Validate API connection with retry logic."""
-    for attempt in range(retry_count):
-        try:
-            async with timeout(10):
-                client = AsyncOpenAI(
-                    api_key=api_key,
-                    base_url=endpoint,
-                )
-
-                models = await client.models.list()
-                model_ids = [model.id for model in models.data]
-
-                if model not in model_ids:
-                    _LOGGER.warning(
-                        "Model %s not found in available models: %s",
-                        model,
-                        ", ".join(model_ids)
-                    )
-                    return False, "invalid_model", model_ids
-                return True, "", model_ids
-
-        except asyncio.TimeoutError:
-            _LOGGER.warning(
-                "Timeout during API validation (attempt %d/%d)",
-                attempt + 1,
-                retry_count
-            )
-            if attempt == retry_count - 1:
-                return False, "timeout", []
-            await asyncio.sleep(retry_delay)
-
-        except AuthenticationError as err:
-            _LOGGER.error("Authentication error: %s", str(err))
-            return False, "invalid_auth", []
-
-        except RateLimitError as err:
-            _LOGGER.error("Rate limit exceeded: %s", str(err))
-            return False, "rate_limit", []
-
-        except APIConnectionError as err:
-            _LOGGER.error("API connection error: %s", str(err))
-            return False, "cannot_connect", []
-
-        except APIError as err:
-            _LOGGER.error("API error: %s", str(err))
-            return False, "api_error", []
-
-        except Exception as err:
-            _LOGGER.exception("Unexpected error during validation: %s", str(err))
-            return False, "unknown", []
 
 class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
     """Handle a config flow for HA text AI."""
 
     VERSION = 1
 
-    async def async_step_user(
-        self,
-        user_input: Optional[Dict[str, Any]] = None
-    ) -> Dict[str, Any]:
+    def __init__(self) -> None:
+        """Initialize flow."""
+        self._errors = {}
+        self._data = {}
+        self._provider = None
+
+    async def async_step_user(self, user_input: Optional[Dict[str, Any]] = None) -> FlowResult:
         """Handle the initial step."""
-        errors: Dict[str, str] = {}
-
-        if user_input is not None:
-            try:
-                # Validate URL format
-                endpoint = user_input.get(CONF_API_ENDPOINT, DEFAULT_API_ENDPOINT)
-                try:
-                    result = urlparse(endpoint)
-                    if not all([result.scheme, result.netloc]):
-                        errors["base"] = "invalid_url_format"
-                        return self.async_show_form(
-                            step_id="user",
-                            data_schema=STEP_USER_DATA_SCHEMA,
-                            errors=errors
+        if user_input is None:
+            return self.async_show_form(
+                step_id="user",
+                data_schema=vol.Schema({
+                    vol.Required(CONF_API_PROVIDER): selector.SelectSelector(
+                        selector.SelectSelectorConfig(
+                            options=API_PROVIDERS,
+                            translation_key="api_provider"
                         )
-                except Exception as e:
-                    _LOGGER.error("URL parsing error: %s", str(e))
-                    errors["base"] = "invalid_url_format"
-                    return self.async_show_form(
-                        step_id="user",
-                        data_schema=STEP_USER_DATA_SCHEMA,
-                        errors=errors
-                    )
+                    ),
+                })
+            )
 
-                # Validate input data
-                user_input = STEP_USER_DATA_SCHEMA(user_input)
+        self._provider = user_input[CONF_API_PROVIDER]
+        return await self.async_step_provider()
 
-                is_valid, error_code, available_models = await validate_api_connection(
-                    user_input[CONF_API_KEY],
-                    endpoint,
-                    user_input[CONF_MODEL]
+    async def async_step_provider(self, user_input: Optional[Dict[str, Any]] = None) -> FlowResult:
+        """Handle provider configuration step."""
+        self._errors = {}
+
+        if user_input is None:
+            default_endpoint = (
+                DEFAULT_OPENAI_ENDPOINT if self._provider == API_PROVIDER_OPENAI
+                else DEFAULT_ANTHROPIC_ENDPOINT
+            )
+
+            return self.async_show_form(
+                step_id="provider",
+                data_schema=vol.Schema({
+                    vol.Required(CONF_NAME, default="my_assistant"): str,
+                    vol.Required(CONF_API_KEY): str,
+                    vol.Required(CONF_MODEL, default=DEFAULT_MODEL): str,
+                    vol.Required(CONF_API_ENDPOINT, default=default_endpoint): str,
+                    vol.Optional(CONF_TEMPERATURE, default=DEFAULT_TEMPERATURE): vol.All(
+                        vol.Coerce(float),
+                        vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
+                    ),
+                    vol.Optional(CONF_MAX_TOKENS, default=DEFAULT_MAX_TOKENS): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
+                    ),
+                    vol.Optional(CONF_REQUEST_INTERVAL, default=DEFAULT_REQUEST_INTERVAL): vol.All(
+                        vol.Coerce(float),
+                        vol.Range(min=MIN_REQUEST_INTERVAL)
+                    ),
+                    vol.Optional(
+                        CONF_CONTEXT_MESSAGES,
+                        default=DEFAULT_CONTEXT_MESSAGES
+                    ): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=1, max=20)
+                    ),
+                    vol.Optional(
+                        CONF_MAX_HISTORY_SIZE,
+                        default=DEFAULT_MAX_HISTORY
+                    ): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=1, max=100)
+                    ),
+                })
+            )
+
+        input_copy = user_input.copy()
+
+        try:
+            normalized_name = self._validate_and_normalize_name(input_copy[CONF_NAME])
+            input_copy[CONF_NAME] = normalized_name
+        except ValueError as e:
+            return self.async_show_form(
+                step_id="provider",
+                data_schema=vol.Schema({
+                    vol.Required(CONF_NAME, default=input_copy[CONF_NAME]): str,
+                    vol.Required(CONF_API_KEY, default=input_copy[CONF_API_KEY]): str,
+                    vol.Required(CONF_MODEL, default=input_copy[CONF_MODEL]): str,
+                    vol.Required(CONF_API_ENDPOINT, default=input_copy[CONF_API_ENDPOINT]): str,
+                    vol.Optional(CONF_TEMPERATURE, default=input_copy.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)): vol.All(
+                        vol.Coerce(float),
+                        vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
+                    ),
+                }),
+                errors={"name": str(e)}
+            )
+
+        try:
+            if not await self._async_validate_api(input_copy):
+                return self.async_show_form(
+                    step_id="provider",
+                    data_schema=vol.Schema({
+                    }),
+                    errors=self._errors
                 )
+        except Exception as e:
+            return self.async_show_form(
+                step_id="provider",
+                data_schema=vol.Schema({
+                }),
+                errors={"base": str(e)}
+            )
 
-                if is_valid:
-                    await self.async_set_unique_id(user_input[CONF_API_KEY])
-                    self._abort_if_unique_id_configured()
+        return await self._create_entry(input_copy)
 
-                    return self.async_create_entry(
-                        title="HA text AI",
-                        data=user_input
-                    )
+    def _validate_and_normalize_name(self, name: str) -> str:
+        """
+        Validate and normalize name with detailed error handling.
 
-                errors["base"] = error_code
-                if error_code == "invalid_model":
-                    _LOGGER.warning(
-                        "Selected model %s not found in available models: %s",
-                        user_input[CONF_MODEL],
-                        ", ".join(available_models)
-                    )
+        Raises:
+            ValueError: If name is invalid
 
-            except vol.Invalid as err:
-                _LOGGER.error("Validation error: %s", str(err))
-                errors["base"] = "invalid_input"
+        Returns:
+            Normalized name
+        """
+        if not name:
+            raise ValueError("empty")
 
-        return self.async_show_form(
-            step_id="user",
-            data_schema=STEP_USER_DATA_SCHEMA,
-            errors=errors,
-            description_placeholders={
-                "default_model": DEFAULT_MODEL,
-                "default_endpoint": DEFAULT_API_ENDPOINT,
+        name = name.strip()
+        normalized = ''.join(
+            c if c.isalnum() or c in ' _' else '_'  # Only allow underscores
+            for c in name
+        )
+
+        normalized = normalized.replace(' ', '_').lower()
+
+        for entry in self._async_current_entries():
+            if entry.data.get(CONF_NAME, "") == normalized:
+                raise ValueError("name_exists")
+
+        normalized = normalized[:50]
+
+        if not normalized:
+            raise ValueError("empty")
+
+        return normalized
+
+    async def _async_validate_api(self, user_input: Dict[str, Any]) -> bool:
+        """Validate API connection."""
+        try:
+            session = async_get_clientsession(self.hass)
+            headers = self._get_api_headers(user_input)
+            endpoint = user_input[CONF_API_ENDPOINT].rstrip('/')
+
+            check_url = (
+                f"{endpoint}/v1/models" if self._provider == API_PROVIDER_ANTHROPIC
+                else f"{endpoint}/models"
+            )
+
+            async with session.get(check_url, headers=headers) as response:
+                if response.status == 401:
+                    self._errors["base"] = "invalid_auth"
+                    return False
+                elif response.status not in [200, 404]:
+                    self._errors["base"] = "cannot_connect"
+                    return False
+                return True
+
+        except Exception as err:
+            _LOGGER.error("API validation error: %s", str(err))
+            self._errors["base"] = "cannot_connect"
+            return False
+
+    def _get_api_headers(self, user_input: Dict[str, Any]) -> Dict[str, str]:
+        """Get API headers based on provider."""
+        api_key = user_input[CONF_API_KEY]
+
+        if self._provider == API_PROVIDER_ANTHROPIC:
+            return {
+                "x-api-key": api_key,
+                "anthropic-version": "2023-06-01",
+                "Content-Type": "application/json"
             }
+        return {
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json"
+        }
+
+    async def _create_entry(self, user_input: Dict[str, Any]) -> FlowResult:
+        """Create the config entry with comprehensive data preservation."""
+        instance_name = user_input[CONF_NAME]
+        normalized_name = normalize_name(instance_name)
+
+        unique_id = f"{DOMAIN}_{normalized_name}_{self._provider}".lower()
+
+        entry_data = {
+            CONF_API_PROVIDER: self._provider,
+            CONF_NAME: instance_name,
+            "normalized_name": normalized_name,
+            CONF_API_KEY: user_input.get(CONF_API_KEY),
+            CONF_API_ENDPOINT: user_input.get(CONF_API_ENDPOINT),
+            "unique_id": unique_id,
+            CONF_MODEL: user_input.get(CONF_MODEL, DEFAULT_MODEL),
+            CONF_TEMPERATURE: user_input.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE),
+            CONF_MAX_TOKENS: user_input.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS),
+            CONF_REQUEST_INTERVAL: user_input.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL),
+            CONF_CONTEXT_MESSAGES: user_input.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES),
+            CONF_MAX_HISTORY_SIZE: user_input.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY),
+        }
+
+        for key, value in user_input.items():
+            if key not in entry_data:
+                entry_data[key] = value
+
+        _LOGGER.debug(f"Creating config entry with data: {entry_data}")
+
+        return self.async_create_entry(
+            title=instance_name,
+            data=entry_data
         )
 
     @staticmethod
     @callback
-    def async_get_options_flow(
-        config_entry: config_entries.ConfigEntry,
-    ) -> config_entries.OptionsFlow:
+    def async_get_options_flow(config_entry: config_entries.ConfigEntry) -> config_entries.OptionsFlow:
         """Get the options flow for this handler."""
         return OptionsFlowHandler(config_entry)
 
+
 class OptionsFlowHandler(config_entries.OptionsFlow):
-    """Handle options flow for HA text AI."""
+    """Handle options flow."""
 
     def __init__(self, config_entry: config_entries.ConfigEntry) -> None:
         """Initialize options flow."""
         self.config_entry = config_entry
 
-    async def async_step_init(
-        self,
-        user_input: Optional[Dict[str, Any]] = None
-    ) -> Dict[str, Any]:
-        """Handle options flow."""
+    async def async_step_init(self, user_input: Optional[Dict[str, Any]] = None) -> FlowResult:
+        """Manage the options."""
         if user_input is not None:
             return self.async_create_entry(title="", data=user_input)
 
-        options_schema = vol.Schema({
-            vol.Optional(
-                CONF_TEMPERATURE,
-                default=self.config_entry.options.get(
-                    CONF_TEMPERATURE, DEFAULT_TEMPERATURE
-                ),
-                description={"suggested_value": DEFAULT_TEMPERATURE},
-            ): vol.All(
-                vol.Coerce(float),
-                vol.Range(min=0, max=2)
-            ),
-            vol.Optional(
-                CONF_MAX_TOKENS,
-                default=self.config_entry.options.get(
-                    CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS
-                ),
-                description={"suggested_value": DEFAULT_MAX_TOKENS},
-            ): vol.All(
-                vol.Coerce(int),
-                vol.Range(min=1, max=4096)
-            ),
-            vol.Optional(
-                CONF_REQUEST_INTERVAL,
-                default=self.config_entry.options.get(
-                    CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL
-                ),
-                description={"suggested_value": DEFAULT_REQUEST_INTERVAL},
-            ): vol.All(
-                vol.Coerce(float),
-                vol.Range(min=0.1)
-            ),
-        })
+        current_data = {**self.config_entry.data, **self.config_entry.options}
 
         return self.async_show_form(
             step_id="init",
-            data_schema=options_schema,
+            data_schema=vol.Schema({
+                vol.Optional(
+                    CONF_MODEL,
+                    default=current_data.get(CONF_MODEL, DEFAULT_MODEL)
+                ): str,
+                vol.Optional(
+                    CONF_TEMPERATURE,
+                    default=current_data.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)
+                ): vol.All(
+                    vol.Coerce(float),
+                    vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
+                ),
+                vol.Optional(
+                    CONF_MAX_TOKENS,
+                    default=current_data.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)
+                ): vol.All(
+                    vol.Coerce(int),
+                    vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
+                ),
+                vol.Optional(
+                    CONF_REQUEST_INTERVAL,
+                    default=current_data.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)
+                ): vol.All(
+                    vol.Coerce(float),
+                    vol.Range(min=MIN_REQUEST_INTERVAL)
+                ),
+                vol.Optional(
+                    CONF_CONTEXT_MESSAGES,
+                    default=current_data.get(
+                        CONF_CONTEXT_MESSAGES,
+                        DEFAULT_CONTEXT_MESSAGES
+                    )
+                ): vol.All(
+                    vol.Coerce(int),
+                    vol.Range(min=1, max=20)
+                ),
+                vol.Optional(
+                    CONF_MAX_HISTORY_SIZE,
+                    default=current_data.get(
+                        CONF_MAX_HISTORY_SIZE,
+                        DEFAULT_MAX_HISTORY
+                    )
+                ): vol.All(
+                    vol.Coerce(int),
+                    vol.Range(min=1, max=100)
+                ),
+            })
         )

custom_components/ha_text_ai/const.py

@@ -1,10 +1,26 @@
 """Constants for the HA text AI integration."""
 from typing import Final
-from homeassistant.const import Platform
+import voluptuous as vol
+from homeassistant.const import Platform, CONF_API_KEY, CONF_NAME
+from homeassistant.helpers import config_validation as cv
 
 # Domain and platforms
 DOMAIN: Final = "ha_text_ai"
-PLATFORMS: Final = [Platform.SENSOR]
+PLATFORMS: list[str] = ["sensor"]
+
+# Provider configuration
+CONF_API_PROVIDER: Final = "api_provider"
+API_PROVIDER_OPENAI: Final = "openai"
+API_PROVIDER_ANTHROPIC: Final = "anthropic"
+
+API_PROVIDERS: Final = [
+    API_PROVIDER_OPENAI,
+    API_PROVIDER_ANTHROPIC
+]
+
+# Default endpoints
+DEFAULT_OPENAI_ENDPOINT: Final = "https://api.openai.com/v1"
+DEFAULT_ANTHROPIC_ENDPOINT: Final = "https://api.anthropic.com"
 
 # Configuration constants
 CONF_MODEL: Final = "model"
@@ -12,16 +28,21 @@ CONF_TEMPERATURE: Final = "temperature"
 CONF_MAX_TOKENS: Final = "max_tokens"
 CONF_API_ENDPOINT: Final = "api_endpoint"
 CONF_REQUEST_INTERVAL: Final = "request_interval"
+CONF_INSTANCE: Final = "instance"
+CONF_MAX_HISTORY_SIZE: Final = "max_history_size"  # Correct constant name
+CONF_IS_ANTHROPIC: Final = "is_anthropic"
+CONF_CONTEXT_MESSAGES: Final = "context_messages"
 
 # Default values
-DEFAULT_MODEL: Final = "gpt-3.5-turbo"
-DEFAULT_TEMPERATURE: Final = 0.7
+DEFAULT_MODEL: Final = "gpt-4o-mini"
+DEFAULT_TEMPERATURE: Final = 0.1
 DEFAULT_MAX_TOKENS: Final = 1000
-DEFAULT_API_ENDPOINT: Final = "https://api.openai.com/v1"
 DEFAULT_REQUEST_INTERVAL: Final = 1.0
 DEFAULT_TIMEOUT: Final = 30
-DEFAULT_QUEUE_SIZE: Final = 100
-DEFAULT_HISTORY_LIMIT: Final = 50
+DEFAULT_MAX_HISTORY: Final = 50
+DEFAULT_NAME: Final = "HA Text AI"
+DEFAULT_NAME_PREFIX = "ha_text_ai"
+DEFAULT_CONTEXT_MESSAGES: Final = 5
 
 # Parameter constraints
 MIN_TEMPERATURE: Final = 0.0
@@ -29,8 +50,11 @@ MAX_TEMPERATURE: Final = 2.0
 MIN_MAX_TOKENS: Final = 1
 MAX_MAX_TOKENS: Final = 4096
 MIN_REQUEST_INTERVAL: Final = 0.1
-MIN_TIMEOUT: Final = 5
-MAX_TIMEOUT: Final = 120
+MAX_REQUEST_INTERVAL: Final = 60.0
+
+# API constants
+API_TIMEOUT: Final = 30
+API_RETRY_COUNT: Final = 3
 
 # Service names
 SERVICE_ASK_QUESTION: Final = "ask_question"
@@ -38,26 +62,48 @@ SERVICE_CLEAR_HISTORY: Final = "clear_history"
 SERVICE_GET_HISTORY: Final = "get_history"
 SERVICE_SET_SYSTEM_PROMPT: Final = "set_system_prompt"
 
-# Service descriptions
-SERVICE_ASK_QUESTION_DESCRIPTION: Final = "Ask a question to the AI model"
-SERVICE_CLEAR_HISTORY_DESCRIPTION: Final = "Clear conversation history"
-SERVICE_GET_HISTORY_DESCRIPTION: Final = "Get conversation history"
-SERVICE_SET_SYSTEM_PROMPT_DESCRIPTION: Final = "Set system prompt for AI model"
-
 # Attribute keys
 ATTR_QUESTION: Final = "question"
 ATTR_RESPONSE: Final = "response"
-ATTR_LAST_UPDATED: Final = "last_updated"
+ATTR_INSTANCE: Final = "instance"
 ATTR_MODEL: Final = "model"
 ATTR_TEMPERATURE: Final = "temperature"
 ATTR_MAX_TOKENS: Final = "max_tokens"
-ATTR_TOTAL_RESPONSES: Final = "total_responses"
 ATTR_SYSTEM_PROMPT: Final = "system_prompt"
-ATTR_RESPONSE_TIME: Final = "response_time"
-ATTR_QUEUE_SIZE: Final = "queue_size"
 ATTR_API_STATUS: Final = "api_status"
 ATTR_ERROR_COUNT: Final = "error_count"
+ATTR_CONVERSATION_HISTORY: Final = "conversation_history"
+
+# Sensor attributes
+ATTR_TOTAL_RESPONSES: Final = "total_responses"
+ATTR_TOTAL_ERRORS: Final = "total_errors"
+ATTR_AVG_RESPONSE_TIME: Final = "average_response_time"
+ATTR_LAST_REQUEST_TIME: Final = "last_request_time"
 ATTR_LAST_ERROR: Final = "last_error"
+ATTR_IS_PROCESSING: Final = "is_processing"
+ATTR_IS_RATE_LIMITED: Final = "is_rate_limited"
+ATTR_IS_MAINTENANCE: Final = "is_maintenance"
+ATTR_API_VERSION: Final = "api_version"
+ATTR_ENDPOINT_STATUS: Final = "endpoint_status"
+ATTR_PERFORMANCE_METRICS: Final = "performance_metrics"
+ATTR_HISTORY_SIZE: Final = "history_size"
+ATTR_UPTIME: Final = "uptime"
+ATTR_API_PROVIDER: Final = "api_provider"
+ATTR_METRICS: Final = "metrics"
+ATTR_STATE: Final = "state"
+ATTR_LAST_RESPONSE: Final = "last_response"
+ATTR_ERROR: Final = "error"
+ATTR_TIMESTAMP: Final = "timestamp"
+
+# Sensor metrics
+METRIC_TOTAL_TOKENS: Final = "total_tokens"
+METRIC_PROMPT_TOKENS: Final = "prompt_tokens"
+METRIC_COMPLETION_TOKENS: Final = "completion_tokens"
+METRIC_SUCCESSFUL_REQUESTS: Final = "successful_requests"
+METRIC_FAILED_REQUESTS: Final = "failed_requests"
+METRIC_AVERAGE_LATENCY: Final = "average_latency"
+METRIC_MAX_LATENCY: Final = "max_latency"
+METRIC_MIN_LATENCY: Final = "min_latency"
 
 # Error messages
 ERROR_INVALID_API_KEY: Final = "invalid_api_key"
@@ -68,74 +114,89 @@ ERROR_RATE_LIMIT: Final = "rate_limit_exceeded"
 ERROR_CONTEXT_LENGTH: Final = "context_length_exceeded"
 ERROR_API_ERROR: Final = "api_error"
 ERROR_TIMEOUT: Final = "timeout_error"
-ERROR_QUEUE_FULL: Final = "queue_full"
-ERROR_INVALID_PROMPT: Final = "invalid_prompt"
-
-# Configuration descriptions
-CONF_MODEL_DESCRIPTION: Final = "AI model to use for responses"
-CONF_TEMPERATURE_DESCRIPTION: Final = "Temperature for response generation (0-2)"
-CONF_MAX_TOKENS_DESCRIPTION: Final = "Maximum tokens in response (1-4096)"
-CONF_API_ENDPOINT_DESCRIPTION: Final = "API endpoint URL"
-CONF_REQUEST_INTERVAL_DESCRIPTION: Final = "Minimum time between API requests (seconds)"
-
-# Entity attributes descriptions
-ATTR_QUESTION_DESCRIPTION: Final = "Last question asked"
-ATTR_RESPONSE_DESCRIPTION: Final = "Last response received"
-ATTR_LAST_UPDATED_DESCRIPTION: Final = "Time of last update"
-ATTR_MODEL_DESCRIPTION: Final = "Current AI model in use"
-ATTR_TEMPERATURE_DESCRIPTION: Final = "Current temperature setting"
-ATTR_MAX_TOKENS_DESCRIPTION: Final = "Current max tokens setting"
-ATTR_TOTAL_RESPONSES_DESCRIPTION: Final = "Total number of responses"
-ATTR_SYSTEM_PROMPT_DESCRIPTION: Final = "Current system prompt"
-ATTR_RESPONSE_TIME_DESCRIPTION: Final = "Time taken for last response"
-ATTR_QUEUE_SIZE_DESCRIPTION: Final = "Current size of question queue"
-ATTR_API_STATUS_DESCRIPTION: Final = "Current API connection status"
-ATTR_ERROR_COUNT_DESCRIPTION: Final = "Total number of errors"
-ATTR_LAST_ERROR_DESCRIPTION: Final = "Last error message"
+ERROR_INVALID_INSTANCE: Final = "invalid_instance"
+ERROR_NAME_EXISTS: Final = "name_exists"
 
 # Entity attributes
-ENTITY_NAME: Final = "HA Text AI"
 ENTITY_ICON: Final = "mdi:robot"
 ENTITY_ICON_ERROR: Final = "mdi:robot-dead"
 ENTITY_ICON_PROCESSING: Final = "mdi:robot-excited"
 
-# Translation keys
-TRANSLATION_KEY_CONFIG: Final = "config"
-TRANSLATION_KEY_OPTIONS: Final = "options"
-TRANSLATION_KEY_ERROR: Final = "error"
-TRANSLATION_KEY_STATE: Final = "state"
-TRANSLATION_KEY_SERVICES: Final = "services"
-
 # State attributes
 STATE_READY: Final = "ready"
 STATE_PROCESSING: Final = "processing"
 STATE_ERROR: Final = "error"
-STATE_DISCONNECTED: Final = "disconnected"
-STATE_RATE_LIMITED: Final = "rate_limited"
 STATE_INITIALIZING: Final = "initializing"
-
-# Logging
-LOGGER_NAME: Final = "custom_components.ha_text_ai"
-LOG_LEVEL_DEFAULT: Final = "INFO"
-
-# Queue constants
-QUEUE_TIMEOUT: Final = 5
-QUEUE_MAX_SIZE: Final = 100
-
-# API constants
-API_TIMEOUT: Final = 30
-API_RETRY_COUNT: Final = 3
-API_BACKOFF_FACTOR: Final = 1.5
-
-# Service schema constants
-SCHEMA_QUESTION: Final = "question"
-SCHEMA_MODEL: Final = "model"
-SCHEMA_TEMPERATURE: Final = "temperature"
-SCHEMA_MAX_TOKENS: Final = "max_tokens"
-SCHEMA_PROMPT: Final = "prompt"
-SCHEMA_LIMIT: Final = "limit"
+STATE_MAINTENANCE: Final = "maintenance"
+STATE_RATE_LIMITED: Final = "rate_limited"
+STATE_DISCONNECTED: Final = "disconnected"
 
 # Event names
 EVENT_RESPONSE_RECEIVED: Final = f"{DOMAIN}_response_received"
 EVENT_ERROR_OCCURRED: Final = f"{DOMAIN}_error_occurred"
 EVENT_STATE_CHANGED: Final = f"{DOMAIN}_state_changed"
+
+# Service schema constants
+SERVICE_SCHEMA_ASK_QUESTION = vol.Schema({
+    vol.Required(CONF_INSTANCE): cv.string,
+    vol.Required("question"): cv.string,
+    vol.Optional("system_prompt"): cv.string,
+    vol.Optional("model"): cv.string,
+    vol.Optional("temperature"): vol.All(
+        vol.Coerce(float),
+        vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
+    ),
+    vol.Optional("max_tokens"): vol.All(
+        vol.Coerce(int),
+        vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
+    ),
+    vol.Optional("context_messages"): vol.All(
+        vol.Coerce(int),
+        vol.Range(min=1, max=20)
+    )
+})
+
+SERVICE_SCHEMA_SET_SYSTEM_PROMPT = vol.Schema({
+    vol.Required(CONF_INSTANCE): cv.string,
+    vol.Required("prompt"): cv.string
+})
+
+SERVICE_SCHEMA_GET_HISTORY = vol.Schema({
+    vol.Required(CONF_INSTANCE): cv.string,
+    vol.Optional("limit", default=10): vol.All(
+        vol.Coerce(int),
+        vol.Range(min=1, max=100),
+    ),
+    vol.Optional("filter_model"): cv.string
+})
+
+# Configuration schema
+CONFIG_SCHEMA = vol.Schema({
+    DOMAIN: vol.Schema({
+        vol.Required(CONF_NAME): cv.string,
+        vol.Required(CONF_API_KEY): cv.string,
+        vol.Required(CONF_API_PROVIDER): vol.In(API_PROVIDERS),
+        vol.Optional(CONF_MODEL, default=DEFAULT_MODEL): cv.string,
+        vol.Optional(CONF_TEMPERATURE, default=DEFAULT_TEMPERATURE): vol.All(
+            vol.Coerce(float),
+            vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
+        ),
+        vol.Optional(CONF_MAX_TOKENS, default=DEFAULT_MAX_TOKENS): vol.All(
+            vol.Coerce(int),
+            vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
+        ),
+        vol.Optional(CONF_API_ENDPOINT): cv.string,
+        vol.Optional(CONF_REQUEST_INTERVAL, default=DEFAULT_REQUEST_INTERVAL): vol.All(
+            vol.Coerce(float),
+            vol.Range(min=MIN_REQUEST_INTERVAL, max=MAX_REQUEST_INTERVAL)
+        ),
+        vol.Optional(CONF_MAX_HISTORY_SIZE, default=DEFAULT_MAX_HISTORY): vol.All(  # Correct usage
+            vol.Coerce(int),
+            vol.Range(min=1, max=100),
+        ),
+        vol.Optional(CONF_CONTEXT_MESSAGES, default=DEFAULT_CONTEXT_MESSAGES): vol.All(
+            vol.Coerce(int),
+            vol.Range(min=1, max=20)
+        )
+    })
+}, extra=vol.ALLOW_EXTRA)

custom_components/ha_text_ai/coordinator.py

@@ -1,235 +1,555 @@
-"""Data coordinator for HA text AI."""
-import asyncio
+"""The HA Text AI coordinator."""
+from __future__ import annotations
+
 import logging
-from datetime import timedelta
-from typing import Any, Dict, Optional
+import traceback
+from datetime import datetime, timedelta
+from typing import Any, Dict, List, Optional
 
-from openai import AsyncOpenAI, APIError, AuthenticationError, RateLimitError
 from homeassistant.core import HomeAssistant
 from homeassistant.helpers.update_coordinator import DataUpdateCoordinator
-import async_timeout
+from homeassistant.util import dt as dt_util
+from homeassistant.exceptions import HomeAssistantError
+from homeassistant.const import CONF_NAME
+from .config_flow import normalize_name 
 
-from .const import DOMAIN
+from .const import (
+    DOMAIN,
+    STATE_READY,
+    STATE_PROCESSING,
+    STATE_ERROR,
+    STATE_RATE_LIMITED,
+    STATE_MAINTENANCE,
+    DEFAULT_MAX_TOKENS,
+    DEFAULT_TEMPERATURE,
+    DEFAULT_MAX_HISTORY,
+    DEFAULT_CONTEXT_MESSAGES,
+    DEFAULT_NAME_PREFIX,
+    CONF_MAX_HISTORY_SIZE,
+)
 
 _LOGGER = logging.getLogger(__name__)
 
+
 class HATextAICoordinator(DataUpdateCoordinator):
-    """Class to manage fetching data from the API."""
+    """The HA Text AI coordinator."""
 
     def __init__(
         self,
         hass: HomeAssistant,
-        api_key: str,
-        endpoint: str,
+        client: Any,
         model: str,
-        temperature: float,
-        max_tokens: int,
-        request_interval: float,
-        session: Optional[Any] = None,
+        update_interval: int,
+        instance_name: str,
+        max_tokens: int = DEFAULT_MAX_TOKENS,
+        temperature: float = DEFAULT_TEMPERATURE,
+        max_history_size: int = DEFAULT_MAX_HISTORY,
+        context_messages: int = DEFAULT_CONTEXT_MESSAGES,
+        is_anthropic: bool = False,
     ) -> None:
-        """Initialize."""
+        """Initialize coordinator."""
+        self.instance_name = instance_name
+        self.normalized_name = None
+
+        # Use the normalize_name function from config_flow to ensure consistency
+        from .config_flow import normalize_name
+        self.normalized_name = normalize_name(instance_name)
+
+        self.hass = hass
+        self.client = client
+        self.model = model
+        self.temperature = temperature
+        self.max_tokens = max_tokens
+        self.max_history_size = max_history_size
+        self.is_anthropic = is_anthropic
+
+        # Initialize with default state
+        self._initial_state = {
+            "state": STATE_READY,
+            "metrics": {
+                "total_tokens": 0,
+                "prompt_tokens": 0,
+                "completion_tokens": 0,
+                "successful_requests": 0,
+                "failed_requests": 0,
+                "total_errors": 0,
+                "average_latency": 0,
+                "max_latency": 0,
+                "min_latency": float("inf"),
+            },
+            "last_response": {
+                "timestamp": dt_util.utcnow().isoformat(),
+                "question": "",
+                "response": "",
+                "model": model,
+                "instance": instance_name,
+                "normalized_name": self.normalized_name,
+                "error": None,
+            },
+            "is_processing": False,
+            "is_rate_limited": False,
+            "is_maintenance": False,
+            "endpoint_status": "ready",
+            "uptime": 0,
+            "system_prompt": None,
+            "history_size": 0,
+            "conversation_history": [],
+        }
+
+        update_interval_td = timedelta(seconds=update_interval)
+
         super().__init__(
             hass,
             _LOGGER,
-            name=DOMAIN,
-            update_interval=timedelta(seconds=request_interval),
+            name=instance_name,
+            update_interval=update_interval_td,
         )
 
-        self._validate_params(api_key, temperature, max_tokens)
+        # Register instance
+        self.hass.data.setdefault(DOMAIN, {})
+        self.hass.data[DOMAIN][instance_name] = self
+        self.context_messages = context_messages
 
-        self.api_key = api_key
-        self.endpoint = endpoint
-        self.model = model
-        self.temperature = float(temperature)
-        self.max_tokens = int(max_tokens)
-        self._question_queue = asyncio.Queue()
-        self._responses: Dict[str, Any] = {}
-        self.system_prompt: Optional[str] = None
-        self._is_ready = False
-        self._error_count = 0
-        self._MAX_ERRORS = 3
+        self._system_prompt = None
+        self._conversation_history = []
+        self._performance_metrics = self._initial_state["metrics"].copy()
+        self._is_processing = False
+        self._is_rate_limited = False
+        self._is_maintenance = False
+        self.endpoint_status = "ready"
+        self.last_response = self._initial_state["last_response"].copy()
+        self._start_time = dt_util.utcnow()
 
-        self.client = AsyncOpenAI(
-            api_key=self.api_key,
-            base_url=self.endpoint,
-            http_client=session,
+        _LOGGER.info(
+            f"Initialized HA Text AI coordinator with instance: {instance_name}"
         )
 
-    def _validate_params(self, api_key: str, temperature: float, max_tokens: int) -> None:
-        """Validate initialization parameters."""
-        if not api_key:
-            raise ValueError("API key is required")
-        if not isinstance(temperature, (int, float)) or not 0 <= temperature <= 2:
-            raise ValueError("Temperature must be between 0 and 2")
-        if not isinstance(max_tokens, int) or max_tokens < 1:
-            raise ValueError("Max tokens must be a positive integer")
-
     async def _async_update_data(self) -> Dict[str, Any]:
-        """Update data via OpenAI API."""
-        if self._question_queue.empty():
-            return self._responses
-
+        """Update data via library."""
         try:
-            async with async_timeout.timeout(30):
-                question_data = await self._question_queue.get()
-                question = question_data["question"]
-                params = question_data["params"]
-
-                try:
-                    response_content = await self._make_api_call(
-                        question,
-                        model=params.get("model"),
-                        temperature=params.get("temperature"),
-                        max_tokens=params.get("max_tokens"),
-                        system_prompt=params.get("system_prompt")
-                    )
-
-                    self._responses[question] = {
-                        "question": question,
-                        "response": response_content,
-                        "error": None,
-                        "timestamp": self.hass.loop.time(),
-                        "model": params.get("model", self.model),
-                        "temperature": params.get("temperature", self.temperature),
-                        "max_tokens": params.get("max_tokens", self.max_tokens)
-                    }
-                    self._error_count = 0
-                    self._is_ready = True
-                    _LOGGER.debug("Response received for question: %s", question)
-
-                except Exception as err:
-                    self._handle_api_error(question, err)
-                finally:
-                    self._question_queue.task_done()
-
-                return self._responses
-
-        except asyncio.TimeoutError as err:
-            _LOGGER.error("Timeout while processing question")
-            await self._handle_timeout_error()
-            return self._responses
-
-    def _handle_api_error(self, question: str, error: Exception) -> None:
-        """Handle API errors."""
-        self._error_count += 1
-        error_msg = str(error)
-
-        if isinstance(error, AuthenticationError):
-            error_msg = "Authentication failed - invalid API key"
-            self._is_ready = False
-        elif isinstance(error, RateLimitError):
-            error_msg = "Rate limit exceeded"
-        elif isinstance(error, APIError):
-            error_msg = f"API error: {error}"
-
-        self._responses[question] = {
-            "question": question,
-            "response": None,
-            "error": error_msg,
-            "timestamp": self.hass.loop.time(),
-            "model": self.model,
-            "temperature": self.temperature,
-            "max_tokens": self.max_tokens
-        }
-
-        _LOGGER.error("API error (%s): %s", type(error).__name__, error_msg)
-
-        if self._error_count >= self._MAX_ERRORS:
-            _LOGGER.warning(
-                "Multiple errors occurred (%d). Coordinator needs attention.",
-                self._error_count
+            current_state = self._get_current_state()
+            _LOGGER.debug(
+                f"Updating data for {self.instance_name}, current state: {current_state}"
             )
 
-    async def _handle_timeout_error(self) -> None:
-        """Handle timeout errors."""
-        self._error_count += 1
-        if not self._question_queue.empty():
-            try:
-                # Clear the queue if we have timeout issues
-                while not self._question_queue.empty():
-                    self._question_queue.get_nowait()
-                    self._question_queue.task_done()
-            except Exception as err:
-                _LOGGER.error("Error clearing question queue: %s", err)
+            data = {
+                "state": current_state,
+                "metrics": self._performance_metrics,
+                "last_response": self.last_response,
+                "is_processing": self._is_processing,
+                "is_rate_limited": self._is_rate_limited,
+                "is_maintenance": self._is_maintenance,
+                "endpoint_status": self.endpoint_status,
+                "uptime": (dt_util.utcnow() - self._start_time).total_seconds(),
+                "system_prompt": self._system_prompt,
+                "history_size": len(self._conversation_history),
+                "conversation_history": self._conversation_history,
+                "normalized_name": self.normalized_name,
+            }
 
-    async def _make_api_call(
+            # Validate data
+            if not isinstance(data, dict):
+                raise ValueError("Invalid data format")
+
+            _LOGGER.debug(f"Updated data for {self.instance_name}: {data}")
+            return data
+
+        except Exception as err:
+            _LOGGER.error(f"Error updating data for {self.instance_name}: {err}")
+            return self._initial_state
+
+    async def async_update_ha_state(self) -> None:
+        """Update Home Assistant state."""
+        try:
+            _LOGGER.debug(
+                f"Requesting state update for {self.instance_name} (normalized: {self.normalized_name})"
+            )
+            await self.async_request_refresh()
+
+            # Force update of all entities
+            entity_id_base = f"sensor.ha_text_ai_{self.normalized_name.lower()}"
+            for entity_id in self.hass.states.async_entity_ids():
+                if entity_id.startswith(entity_id_base):
+                    self.hass.states.async_set(entity_id, self._get_current_state())
+
+        except Exception as err:
+            _LOGGER.error(f"Error updating HA state for {self.instance_name}: {err}")
+
+    def _get_current_state(self) -> str:
+        """Get current state based on internal flags."""
+        if self._is_processing:
+            return STATE_PROCESSING
+        elif self._is_rate_limited:
+            return STATE_RATE_LIMITED
+        elif self._is_maintenance:
+            return STATE_MAINTENANCE
+        elif self.last_response.get("error"):
+            return STATE_ERROR
+        return STATE_READY
+
+    def _calculate_context_tokens(self, messages: List[Dict[str, str]], model: str = None) -> int:
+        """
+        Estimate tokens for conversation context.
+
+        Args:
+            messages: List of message dictionaries
+            model: Optional model name for provider-specific estimation
+
+        Returns:
+            Estimated number of tokens
+        """
+        try:
+            # Anthropic specific token counting
+            if self.is_anthropic and hasattr(self.client, 'count_tokens'):
+                return sum(self.client.count_tokens(msg['content']) for msg in messages)
+
+            def estimate_tokens(text: str) -> int:
+                """
+                Flexible token estimation algorithm.
+
+                Heuristics:
+                - Count words
+                - Estimate special characters
+                - Fallback to character-based estimation
+                """
+                # Word-based estimation
+                words = len(text.split())
+
+                # Special character handling
+                special_chars = sum(1 for char in text if not char.isalnum())
+
+                # Character-based fallback
+                char_tokens = len(text) // 4
+
+                # Combine estimations with bias towards words
+                total_tokens = (words * 1.5) + (special_chars * 0.5) + char_tokens
+
+                return max(int(total_tokens), words)
+
+            # Calculate total tokens across all messages
+            total_tokens = sum(estimate_tokens(msg['content']) for msg in messages)
+
+            # Logging for debugging
+            _LOGGER.debug(
+                f"Token Estimation: "
+                f"Messages: {len(messages)}, "
+                f"Estimated Tokens: {total_tokens}"
+            )
+
+            return total_tokens
+
+        except Exception as e:
+            # Safe fallback with detailed logging
+            _LOGGER.warning(
+                f"Token estimation failed. "
+                f"Error: {e}. "
+                f"Using conservative estimation."
+            )
+
+            # Conservative token estimation
+            return len(messages) * 100
+
+    async def async_ask_question(
         self,
         question: str,
         model: Optional[str] = None,
         temperature: Optional[float] = None,
         max_tokens: Optional[int] = None,
-        system_prompt: Optional[str] = None
-    ) -> str:
-        """Make API call to OpenAI."""
-        try:
-            messages = []
-            current_system_prompt = system_prompt if system_prompt is not None else self.system_prompt
-            if current_system_prompt:
-                messages.append({"role": "system", "content": current_system_prompt})
-            messages.append({"role": "user", "content": question})
+        system_prompt: Optional[str] = None,
+        context_messages: Optional[int] = None,
+    ) -> dict:
+        """
+        Process a question with optional parameters.
 
-            completion = await self.client.chat.completions.create(
-                model=model or self.model,
-                messages=messages,
-                temperature=temperature if temperature is not None else self.temperature,
-                max_tokens=max_tokens if max_tokens is not None else self.max_tokens,
-            )
-            return completion.choices[0].message.content
+        This method is a direct wrapper around async_process_question,
+        allowing flexible AI interaction with optional model, temperature,
+        and context customization.
+
+        Args:
+            question: The input question or prompt
+            model: Optional AI model to use
+            temperature: Optional response creativity level
+            max_tokens: Optional maximum response length
+            system_prompt: Optional system-level instruction
+            context_messages: Optional number of context messages to include
+
+        Returns:
+            Full response dictionary from the AI
+        """
+        return await self.async_process_question(
+            question, model, temperature, max_tokens, system_prompt, context_messages
+        )
+
+    async def async_process_question(
+            self,
+            question: str,
+            model: Optional[str] = None,
+            temperature: Optional[float] = None,
+            max_tokens: Optional[int] = None,
+            system_prompt: Optional[str] = None,
+            context_messages: Optional[int] = None,
+        ) -> dict:
+            """
+            Enhanced question processing with intelligent token management.
+            """
+            try:
+                self._is_processing = True
+                await self.async_update_ha_state()
+
+                temp_context_messages = context_messages or self.context_messages
+                temp_model = model or self.model
+                temp_temperature = temperature or self.temperature
+                temp_max_tokens = max_tokens or self.max_tokens
+                temp_system_prompt = system_prompt or self._system_prompt
+
+                # Start timing
+                start_time = dt_util.utcnow()
+
+                # Prepare messages with system prompt
+                messages = []
+                if temp_system_prompt:
+                    messages.append({"role": "system", "content": temp_system_prompt})
+
+                # Context history management
+                context_history = self._conversation_history[-temp_context_messages:]
+
+                # Comprehensive token calculation
+                context_tokens = self._calculate_context_tokens(
+                    [{"content": entry["question"]} for entry in context_history] +
+                    [{"content": entry["response"]} for entry in context_history] +
+                    [{"content": question}],
+                    temp_model
+                )
+
+                # Dynamic token allocation
+                available_tokens = max(0, temp_max_tokens - context_tokens)
+
+                # Context trimming if over token limit
+                if context_tokens > temp_max_tokens:
+                    _LOGGER.warning(
+                        f"Token limit exceeded. "
+                        f"Context: {context_tokens}, "
+                        f"Max: {temp_max_tokens}"
+                    )
+
+                    # Intelligent context reduction
+                    while context_tokens > temp_max_tokens // 2 and context_history:
+                        context_history.pop(0)
+                        context_tokens = self._calculate_context_tokens(
+                            [{"content": entry["question"]} for entry in context_history] +
+                            [{"content": entry["response"]} for entry in context_history] +
+                            [{"content": question}],
+                            temp_model
+                        )
+
+                # Rebuild messages with trimmed context
+                for entry in context_history:
+                    messages.append({"role": "user", "content": entry["question"]})
+                    messages.append({"role": "assistant", "content": entry["response"]})
+
+                messages.append({"role": "user", "content": question})
+
+                # Detailed token logging
+                _LOGGER.debug(
+                    f"Token Analysis: "
+                    f"Context Tokens: {context_tokens}, "
+                    f"Max Tokens: {temp_max_tokens}, "
+                    f"Available Tokens: {available_tokens}"
+                )
+
+                # Prepare API call with dynamic token management
+                kwargs = {
+                    "model": temp_model,
+                    "temperature": temp_temperature,
+                    "max_tokens": min(temp_max_tokens, available_tokens),
+                    "messages": messages,
+                }
+
+                # Process message
+                response = await self.async_process_message(question, **kwargs)
+
+                # Update metrics
+                end_time = dt_util.utcnow()
+                latency = (end_time - start_time).total_seconds()
+                self._update_metrics(latency, response)
+
+                # Update history
+                self._update_history(question, response)
+
+                return response
+
+            except Exception as err:
+                self._handle_error(err)
+                raise HomeAssistantError(f"Failed to process question: {err}")
+
+            finally:
+                self._is_processing = False
+                await self.async_update_ha_state()
+
+    async def async_process_message(self, question: str, **kwargs) -> dict:
+        """Process message using the AI client."""
+        try:
+            if self.is_anthropic:
+                response = await self._process_anthropic_message(question, **kwargs)
+            else:
+                response = await self._process_openai_message(question, **kwargs)
+
+            self.last_response = {
+                "timestamp": dt_util.utcnow().isoformat(),
+                "question": question,
+                "response": response["content"],
+                "model": kwargs.get("model", self.model),
+                "instance": self.instance_name,
+                "error": None,
+            }
+
+            return response
 
         except Exception as err:
-            _LOGGER.error("Error in API call: %s", err)
+            self._handle_error(err)
             raise
 
-    async def async_ask_question(
-        self,
-        question: str,
-        system_prompt: Optional[str] = None,
-        model: Optional[str] = None,
-        temperature: Optional[float] = None,
-        max_tokens: Optional[int] = None
-    ) -> None:
-        """Add question to queue with optional parameters."""
-        if not self._is_ready and self._error_count >= self._MAX_ERRORS:
-            _LOGGER.warning("Coordinator is not ready due to previous errors")
-            return
-
-        question_data = {
-            "question": question,
-            "params": {
-                "system_prompt": system_prompt,
-                "model": model,
-                "temperature": temperature,
-                "max_tokens": max_tokens
+    async def _process_anthropic_message(self, question: str, **kwargs) -> dict:
+        """Process message using Anthropic API."""
+        try:
+            _LOGGER.debug(f"Anthropic API call: model={kwargs['model']}, max_tokens={kwargs['max_tokens']}")
+            response = await self.client.messages.create(
+                model=kwargs["model"],
+                max_tokens=kwargs["max_tokens"],
+                messages=kwargs["messages"],
+                temperature=kwargs["temperature"],
+            )
+            _LOGGER.debug(f"Anthropic response: tokens={response.usage}")
+            return {
+                "content": response.content[0].text,
+                "tokens": {
+                    "prompt": response.usage.input_tokens,
+                    "completion": response.usage.output_tokens,
+                    "total": response.usage.input_tokens + response.usage.output_tokens,
+                },
             }
+        except Exception as e:
+            _LOGGER.error(f"Anthropic API error: {str(e)}")
+            raise
+
+    async def _process_openai_message(self, question: str, **kwargs) -> dict:
+        """Process message using OpenAI API."""
+        try:
+            response = await self.client.create(
+                model=kwargs["model"],
+                messages=kwargs["messages"],
+                temperature=kwargs["temperature"],
+                max_tokens=kwargs["max_tokens"],
+            )
+
+            return {
+                "content": response["choices"][0]["message"]["content"],
+                "tokens": {
+                    "prompt": response["usage"]["prompt_tokens"],
+                    "completion": response["usage"]["completion_tokens"],
+                    "total": response["usage"]["total_tokens"],
+                },
+            }
+        except Exception as e:
+            _LOGGER.error(f"Error in OpenAI API call: {str(e)}")
+            raise
+
+    def _update_metrics(self, latency: float, response: dict) -> None:
+        """Update performance metrics."""
+        metrics = self._performance_metrics
+        tokens = response.get("tokens", {})
+
+        metrics["total_tokens"] += tokens.get("total", 0)
+        metrics["prompt_tokens"] += tokens.get("prompt", 0)
+        metrics["completion_tokens"] += tokens.get("completion", 0)
+        metrics["successful_requests"] += 1
+
+        metrics["average_latency"] = (
+            (metrics["average_latency"] * (metrics["successful_requests"] - 1) + latency)
+            / metrics["successful_requests"]
+        )
+        metrics["max_latency"] = max(metrics["max_latency"], latency)
+        metrics["min_latency"] = min(metrics["min_latency"], latency)
+
+    def _update_history(self, question: str, response: dict) -> None:
+        """Update conversation history."""
+        self._conversation_history.append(
+            {
+                "timestamp": dt_util.utcnow().isoformat(),
+                "question": question,
+                "response": response["content"],
+            }
+        )
+
+        while len(self._conversation_history) > self.max_history_size:
+            self._conversation_history.pop(0)
+
+    def _handle_error(self, error: Exception) -> None:
+        """
+        Enhanced error handling with comprehensive diagnostics.
+
+        Captures detailed error information, tracks error metrics,
+        and provides context for troubleshooting AI processing issues.
+        """
+        self._performance_metrics["total_errors"] += 1
+        self._performance_metrics["failed_requests"] += 1
+
+        error_details = {
+            "timestamp": dt_util.utcnow().isoformat(),
+            "model": self.model,
+            "instance": self.instance_name,
+            "error_message": str(error),
+            "error_type": type(error).__name__,
+            "traceback": traceback.format_exc() if _LOGGER.isEnabledFor(logging.DEBUG) else None,
         }
 
-        await self._question_queue.put(question_data)
-        await self.async_refresh()
+        # Specific error type handling
+        error_mapping = {
+            HomeAssistantError: {"is_ha_error": True},
+            ConnectionError: {
+                "is_connection_error": True,
+                "is_rate_limited": True
+            },
+            TimeoutError: {"is_timeout": True},
+            PermissionError: {"is_permission_denied": True},
+            ValueError: {"is_validation_error": True}
+        }
+
+        for error_type, error_flags in error_mapping.items():
+            if isinstance(error, error_type):
+                error_details.update(error_flags)
+                break
+
+        # Update system state based on error type
+        if error_details.get("is_rate_limited"):
+            self._is_rate_limited = True
+            _LOGGER.warning(f"Rate limit detected for {self.instance_name}")
+
+        if error_details.get("is_connection_error"):
+            self.endpoint_status = "unavailable"
+
+        self.last_response = error_details
+        _LOGGER.error(f"AI Processing Error: {error_details}")
+
+        # Optional: Add more sophisticated error tracking or notification logic
+        if _LOGGER.isEnabledFor(logging.DEBUG):
+            _LOGGER.debug(f"Full Error Traceback: {error_details['traceback']}")
+
+    async def async_clear_history(self) -> None:
+        """Clear conversation history."""
+        self._conversation_history = []
+        await self.async_update_ha_state()
+
+    async def async_get_history(self) -> List[Dict[str, str]]:
+        """Get conversation history."""
+        return self._conversation_history
+
+    async def async_set_system_prompt(self, prompt: str) -> None:
+        """Set system prompt."""
+        self._system_prompt = prompt
+        await self.async_update_ha_state()
 
     async def async_shutdown(self) -> None:
-        """Shutdown the coordinator."""
-        try:
-            # Clear the queue
-            while not self._question_queue.empty():
-                self._question_queue.get_nowait()
-                self._question_queue.task_done()
-
-            await self.client.close()
-            self._is_ready = False
-
-        except Exception as err:
-            _LOGGER.error("Error during shutdown: %s", err)
-
-    @property
-    def is_ready(self) -> bool:
-        """Return if coordinator is ready."""
-        return self._is_ready
-
-    @property
-    def error_count(self) -> int:
-        """Return current error count."""
-        return self._error_count
-
-    def reset_error_count(self) -> None:
-        """Reset error counter."""
-        self._error_count = 0
+        """Shutdown coordinator."""
+        _LOGGER.debug(f"Shutting down coordinator for {self.instance_name}")
+        self.hass.data[DOMAIN].pop(self.instance_name, None)

custom_components/ha_text_ai/manifest.json

@@ -1,14 +1,28 @@
 {
   "domain": "ha_text_ai",
   "name": "HA Text AI",
+  "after_dependencies": ["http"],
+  "bluetooth": [],
   "codeowners": ["@smkrv"],
   "config_flow": true,
   "dependencies": [],
-  "documentation": "https://github.com/smkrv/ha-text-ai/wiki",
+  "documentation": "https://github.com/smkrv/ha-text-ai",
+  "integration_type": "service",
   "iot_class": "cloud_polling",
   "issue_tracker": "https://github.com/smkrv/ha-text-ai/issues",
-  "requirements": ["openai>=1.0.0"],
+  "loggers": ["custom_components.ha_text_ai"],
+  "mqtt": [],
+  "quality_scale": "silver",
+  "requirements": [
+    "openai>=1.12.0",
+    "anthropic>=0.8.0",
+    "aiohttp>=3.8.0",
+    "async-timeout>=4.0.0",
+    "certifi>=2024.2.2"
+  ],
+  "single_config_entry": false,
   "ssdp": [],
-  "version": "1.1.0",
+  "usb": [],
+  "version": "2.0.3-beta",
   "zeroconf": []
 }

custom_components/ha_text_ai/sensor.py

@@ -1,64 +1,101 @@
-"""Sensor platform for HA text AI."""
-from datetime import datetime
+"""Sensor platform for HA Text AI."""
 import logging
-from typing import Any, Dict, Optional
+import math
+from typing import Any, Dict
 
 from homeassistant.components.sensor import (
     SensorEntity,
-    SensorStateClass,
-    SensorDeviceClass,
+    SensorEntityDescription,
 )
 from homeassistant.config_entries import ConfigEntry
 from homeassistant.core import HomeAssistant
+from homeassistant.helpers.device_registry import DeviceInfo
 from homeassistant.helpers.entity_platform import AddEntitiesCallback
 from homeassistant.helpers.typing import StateType
 from homeassistant.helpers.update_coordinator import CoordinatorEntity
 from homeassistant.util import dt as dt_util
+from homeassistant.util import slugify
 
 from .const import (
     DOMAIN,
-    ATTR_QUESTION,
-    ATTR_RESPONSE,
-    ATTR_LAST_UPDATED,
-    ATTR_MODEL,
-    ATTR_TEMPERATURE,
-    ATTR_MAX_TOKENS,
+    CONF_MODEL,
+    CONF_API_PROVIDER,
     ATTR_TOTAL_RESPONSES,
-    ATTR_SYSTEM_PROMPT,
-    ATTR_QUEUE_SIZE,
-    ATTR_API_STATUS,
-    ATTR_ERROR_COUNT,
+    ATTR_TOTAL_ERRORS,
+    ATTR_AVG_RESPONSE_TIME,
+    ATTR_LAST_REQUEST_TIME,
     ATTR_LAST_ERROR,
-    ATTR_RESPONSE_TIME,
-    ENTITY_ICON,
-    ENTITY_ICON_ERROR,
-    ENTITY_ICON_PROCESSING,
+    ATTR_IS_PROCESSING,
+    ATTR_IS_RATE_LIMITED,
+    ATTR_IS_MAINTENANCE,
+    ATTR_API_VERSION,
+    ATTR_ENDPOINT_STATUS,
+    ATTR_PERFORMANCE_METRICS,
+    ATTR_HISTORY_SIZE,
+    ATTR_UPTIME,
+    ATTR_API_PROVIDER,
+    ATTR_MODEL,
+    ATTR_SYSTEM_PROMPT,
+    ATTR_API_STATUS,
+    ATTR_RESPONSE,
+    ATTR_QUESTION,
+    ATTR_CONVERSATION_HISTORY,
+    METRIC_TOTAL_TOKENS,
+    METRIC_PROMPT_TOKENS,
+    METRIC_COMPLETION_TOKENS,
+    METRIC_SUCCESSFUL_REQUESTS,
+    METRIC_FAILED_REQUESTS,
+    METRIC_AVERAGE_LATENCY,
+    METRIC_MAX_LATENCY,
+    METRIC_MIN_LATENCY,
     STATE_READY,
     STATE_PROCESSING,
     STATE_ERROR,
-    STATE_DISCONNECTED,
-    STATE_RATE_LIMITED,
     STATE_INITIALIZING,
+    STATE_MAINTENANCE,
+    STATE_RATE_LIMITED,
+    STATE_DISCONNECTED,
+    ENTITY_ICON,
+    ENTITY_ICON_ERROR,
+    ENTITY_ICON_PROCESSING,
+    DEFAULT_NAME_PREFIX,
+    CONF_MAX_HISTORY_SIZE,
 )
+
 from .coordinator import HATextAICoordinator
 
 _LOGGER = logging.getLogger(__name__)
 
+
 async def async_setup_entry(
     hass: HomeAssistant,
     entry: ConfigEntry,
     async_add_entities: AddEntitiesCallback,
 ) -> None:
-    """Set up the HA text AI sensor."""
-    coordinator = hass.data[DOMAIN][entry.entry_id]
-    async_add_entities([HATextAISensor(coordinator, entry)], True)
+    """Set up the HA Text AI sensor."""
+    _LOGGER.debug(f"Starting sensor setup for entry: {entry.entry_id}")
+
+    try:
+        coordinator = hass.data[DOMAIN][entry.entry_id]
+        _LOGGER.debug(f"Found coordinator for entry {entry.entry_id}")
+
+        instance_name = coordinator.instance_name
+        _LOGGER.debug(f"Setting up sensor with instance: {instance_name}")
+
+        sensor = HATextAISensor(coordinator, entry)
+        _LOGGER.debug(f"Created sensor instance: {sensor.entity_id}")
+
+        async_add_entities([sensor], True)
+        _LOGGER.debug(f"Added sensor entity: {sensor.entity_id}")
+
+    except Exception as err:
+        _LOGGER.exception(f"Error setting up sensor: {err}")
+        raise
 
 class HATextAISensor(CoordinatorEntity, SensorEntity):
-    """HA text AI Sensor."""
+    """HA Text AI Sensor."""
 
-    _attr_has_entity_name = True
-    _attr_state_class = SensorStateClass.MEASUREMENT
-    _attr_device_class = SensorDeviceClass.TIMESTAMP
+    coordinator: HATextAICoordinator
 
     def __init__(
         self,
@@ -66,136 +103,230 @@ class HATextAISensor(CoordinatorEntity, SensorEntity):
         config_entry: ConfigEntry,
     ) -> None:
         """Initialize the sensor."""
+        _LOGGER.debug(f"Initializing sensor with config entry: {config_entry.data}")
+
         super().__init__(coordinator)
+
         self._config_entry = config_entry
+        self._instance_name = coordinator.instance_name
+        self._normalized_name = coordinator.normalized_name
+
+        _LOGGER.debug(f"Instance name: {self._instance_name}")
+        _LOGGER.debug(f"Normalized name: {self._normalized_name}")
+
+        self._conversation_history = []
+        self._system_prompt = None
+
+        self._attr_name = f"HA Text AI {self._instance_name}"
+        self.entity_id = f"sensor.ha_text_ai_{self._normalized_name}"
         self._attr_unique_id = f"{config_entry.entry_id}"
-        self._attr_name = "Last Response"
-        self._attr_suggested_display_precision = 0
+
+        _LOGGER.debug(f"Created sensor with entity_id: {self.entity_id}")
+        _LOGGER.debug(f"Sensor name: {self._attr_name}")
+        _LOGGER.debug(f"Unique ID: {self._attr_unique_id}")
+
+        self.entity_description = SensorEntityDescription(
+            key=f"ha_text_ai_{self._normalized_name.lower()}",
+            entity_registry_enabled_default=True,
+        )
+
+        self._current_state = STATE_INITIALIZING
         self._error_count = 0
         self._last_error = None
-        self._state = STATE_INITIALIZING
+        self._last_update = None
+        self._is_processing = False
+        self._last_response = {}
+        self._metrics = {}
 
-    @property
-    def icon(self) -> str:
-        """Return the icon based on the current state."""
-        if self._state == STATE_PROCESSING:
-            return ENTITY_ICON_PROCESSING
-        elif self._state in [STATE_ERROR, STATE_DISCONNECTED, STATE_RATE_LIMITED]:
-            return ENTITY_ICON_ERROR
-        return ENTITY_ICON
+        model = config_entry.data.get(CONF_MODEL, "Unknown")
+        api_provider = config_entry.data.get(CONF_API_PROVIDER, "Unknown")
 
-    @property
-    def state(self) -> StateType:
-        """Return the state of the sensor."""
-        if not self.coordinator.data or not self.coordinator.last_update_success_time:
-            return None
+        self._attr_device_info = DeviceInfo(
+            identifiers={(DOMAIN, self._attr_unique_id)},
+            name=self._attr_name,
+            manufacturer="Community",
+            model=f"{model} ({api_provider} provider)",
+            sw_version="1.0.0",
+        )
 
-        try:
-            if isinstance(self.coordinator.last_update_success_time, datetime):
-                return dt_util.as_local(self.coordinator.last_update_success_time)
-            return self.coordinator.last_update_success_time
-        except Exception as err:
-            _LOGGER.error("Error getting state: %s", err, exc_info=True)
-            return None
-
-    @property
-    def extra_state_attributes(self) -> Dict[str, Any]:
-        """Return entity specific state attributes."""
-        attributes = {
-            ATTR_TOTAL_RESPONSES: 0,
-            ATTR_MODEL: self.coordinator.model,
-            ATTR_TEMPERATURE: self.coordinator.temperature,
-            ATTR_MAX_TOKENS: self.coordinator.max_tokens,
-            ATTR_SYSTEM_PROMPT: self.coordinator.system_prompt,
-            ATTR_QUEUE_SIZE: self.coordinator._question_queue.qsize(),
-            ATTR_API_STATUS: self._state,
-            ATTR_ERROR_COUNT: self._error_count,
-            ATTR_LAST_ERROR: self._last_error,
-        }
-
-        if not self.coordinator.data:
-            return attributes
-
-        try:
-            # Получаем историю ответов
-            history = list(self.coordinator._responses.items())
-            if history:
-                last_question, last_data = history[-1]
-
-                # Обработка формата ответа
-                if isinstance(last_data, dict):
-                    last_response = last_data.get("response", "")
-                    last_updated = last_data.get("timestamp", self.coordinator.last_update_success_time)
-                    response_time = last_data.get("response_time")
-
-                    # Добавляем новые метаданные
-                    model = last_data.get("model", self.coordinator.model)
-                    temperature = last_data.get("temperature", self.coordinator.temperature)
-                    max_tokens = last_data.get("max_tokens", self.coordinator.max_tokens)
-                    error = last_data.get("error")
-
-                    if error:
-                        self._last_error = error
-                        self._state = STATE_ERROR
-                else:
-                    last_response = str(last_data)
-                    last_updated = self.coordinator.last_update_success_time
-                    response_time = None
-                    model = self.coordinator.model
-                    temperature = self.coordinator.temperature
-                    max_tokens = self.coordinator.max_tokens
-
-                # Конвертация времени в локальный формат
-                if isinstance(last_updated, datetime):
-                    last_updated = dt_util.as_local(last_updated)
-
-                attributes.update({
-                    ATTR_QUESTION: last_question,
-                    ATTR_RESPONSE: last_response,
-                    ATTR_LAST_UPDATED: last_updated,
-                    ATTR_TOTAL_RESPONSES: len(history),
-                    ATTR_MODEL: model,
-                    ATTR_TEMPERATURE: temperature,
-                    ATTR_MAX_TOKENS: max_tokens,
-                })
-
-                if response_time is not None:
-                    attributes[ATTR_RESPONSE_TIME] = response_time
-
-            return attributes
-
-        except Exception as err:
-            _LOGGER.error("Error getting attributes: %s", err, exc_info=True)
-            self._error_count += 1
-            self._last_error = str(err)
-            self._state = STATE_ERROR
-            return attributes
+        _LOGGER.debug(
+            f"Initialized sensor: {self.entity_id} for instance: {self._instance_name}"
+        )
 
     @property
     def available(self) -> bool:
         """Return if entity is available."""
-        return self.coordinator.last_update_success
+        return (
+            self.coordinator.last_update_success
+            and self.coordinator.data is not None
+            and self._current_state != STATE_DISCONNECTED
+        )
+
+    def _sanitize_value(self, value: Any) -> Any:
+        """Sanitize values for JSON serialization."""
+        if isinstance(value, float):
+            if math.isinf(value) or math.isnan(value):
+                return None
+        return value
+
+    def _sanitize_attributes(self, attributes: Dict[str, Any]) -> Dict[str, Any]:
+        """Sanitize all attributes for JSON serialization."""
+        return {
+            key: self._sanitize_value(value)
+            for key, value in attributes.items()
+            if value is not None
+        }
+
+    @property
+    def native_value(self) -> StateType:
+        """Return the native value of the sensor."""
+        if not self.coordinator.last_update_success or not self.coordinator.data:
+            self._current_state = STATE_DISCONNECTED
+            return self._current_state
+
+        status = self.coordinator.data.get("state", STATE_READY)
+        self._current_state = status
+        return status
+
+    @property
+    def icon(self) -> str:
+        """Return the icon based on the current state."""
+        if self._current_state == STATE_ERROR:
+            return ENTITY_ICON_ERROR
+        elif self._current_state == STATE_PROCESSING:
+            return ENTITY_ICON_PROCESSING
+        return ENTITY_ICON
+
+    @property
+    def extra_state_attributes(self) -> Dict[str, Any]:
+        """Return entity specific state attributes."""
+        if not self.coordinator.data:
+            return {}
+
+        try:
+            data = self.coordinator.data
+            attributes = {
+                ATTR_MODEL: self._config_entry.data.get(CONF_MODEL, "Unknown"),
+                ATTR_API_PROVIDER: self._config_entry.data.get(
+                    CONF_API_PROVIDER, "Unknown"
+                ),
+                ATTR_API_STATUS: self._current_state,
+                ATTR_TOTAL_ERRORS: self._error_count,
+                ATTR_LAST_ERROR: self._last_error,
+                "instance_name": self._instance_name,
+                "normalized_name": self._normalized_name,
+                ATTR_SYSTEM_PROMPT: data.get("system_prompt"),
+                ATTR_IS_PROCESSING: data.get("is_processing", False),
+                ATTR_IS_RATE_LIMITED: data.get("is_rate_limited", False),
+                ATTR_IS_MAINTENANCE: data.get("is_maintenance", False),
+                ATTR_ENDPOINT_STATUS: data.get("endpoint_status", "unknown"),
+                ATTR_UPTIME: data.get("uptime", 0),
+                ATTR_HISTORY_SIZE: data.get("history_size", 0),
+                ATTR_CONVERSATION_HISTORY: data.get("conversation_history", []),
+            }
+
+            # Add metrics
+            metrics = data.get("metrics", {})
+            if isinstance(metrics, dict):
+                self._metrics = metrics
+                attributes.update(
+                    {
+                        METRIC_TOTAL_TOKENS: metrics.get("total_tokens", 0),
+                        METRIC_PROMPT_TOKENS: metrics.get("prompt_tokens", 0),
+                        METRIC_COMPLETION_TOKENS: metrics.get("completion_tokens", 0),
+                        METRIC_SUCCESSFUL_REQUESTS: metrics.get(
+                            "successful_requests", 0
+                        ),
+                        METRIC_FAILED_REQUESTS: metrics.get("failed_requests", 0),
+                        METRIC_AVERAGE_LATENCY: metrics.get("average_latency", 0),
+                        METRIC_MAX_LATENCY: metrics.get("max_latency", 0),
+                        METRIC_MIN_LATENCY: metrics.get("min_latency", float("inf")),
+                    }
+                )
+
+            # Add last response
+            last_response = data.get("last_response", {})
+            if isinstance(last_response, dict):
+                self._last_response = last_response
+                attributes.update(
+                    {
+                        ATTR_RESPONSE: last_response.get("response", ""),
+                        ATTR_QUESTION: last_response.get("question", ""),
+                        "last_model": last_response.get("model", ""),
+                        "last_timestamp": last_response.get("timestamp", ""),
+                        "last_error": last_response.get("error"),
+                    }
+                )
+
+            # Add performance metrics if available
+            if ATTR_PERFORMANCE_METRICS in data:
+                attributes[ATTR_PERFORMANCE_METRICS] = data[
+                    ATTR_PERFORMANCE_METRICS
+                ]
+
+            # Add API version if available
+            if ATTR_API_VERSION in data:
+                attributes[ATTR_API_VERSION] = data[ATTR_API_VERSION]
+
+            return self._sanitize_attributes(attributes)
+
+        except Exception as err:
+            _LOGGER.error("Error preparing attributes: %s", err, exc_info=True)
+            return {}
 
     async def async_added_to_hass(self) -> None:
         """When entity is added to hass."""
         await super().async_added_to_hass()
         self._handle_coordinator_update()
-        self._state = STATE_READY
+        _LOGGER.debug(f"Entity {self.entity_id} added to Home Assistant")
 
     def _handle_coordinator_update(self) -> None:
         """Handle updated data from the coordinator."""
         try:
-            if self.coordinator.data:
-                if self.coordinator._is_ready:
-                    self._state = STATE_READY
-                else:
-                    self._state = STATE_DISCONNECTED
-            else:
-                self._state = STATE_DISCONNECTED
-        except Exception as err:
-            _LOGGER.error("Error handling update: %s", err, exc_info=True)
-            self._error_count += 1
-            self._last_error = str(err)
-            self._state = STATE_ERROR
+            data = self.coordinator.data
+            if not self.coordinator.last_update_success or not data:
+                self._current_state = STATE_DISCONNECTED
+                _LOGGER.warning(f"No data available for {self.entity_id}")
+                self.async_write_ha_state()
+                return
 
-        self.async_write_ha_state()  # Исправлено лишнее двоеточие
+            self._is_processing = data.get("is_processing", False)
+
+            # Update conversation history and system prompt
+            self._conversation_history = data.get("conversation_history", [])
+            self._system_prompt = data.get("system_prompt")
+
+            # Update state based on conditions
+            if self._is_processing:
+                self._current_state = STATE_PROCESSING
+            elif data.get("is_rate_limited"):
+                self._current_state = STATE_RATE_LIMITED
+            elif data.get("is_maintenance"):
+                self._current_state = STATE_MAINTENANCE
+            elif data.get("error"):
+                self._current_state = STATE_ERROR
+                self._last_error = data["error"]
+                self._error_count += 1
+            else:
+                self._current_state = data.get("state", STATE_READY)
+
+            # Update last update timestamp
+            self._last_update = dt_util.utcnow()
+
+            _LOGGER.debug(
+                f"Updated {self.entity_id} state to: {self._current_state} "
+                f"(available: {self.available})"
+            )
+
+        except Exception as err:
+            self._current_state = STATE_ERROR
+            self._last_error = str(err)
+            self._error_count += 1
+            _LOGGER.error(
+                "Error handling update for %s: %s",
+                self.entity_id,
+                err,
+                exc_info=True,
+            )
+
+        self.async_write_ha_state()

custom_components/ha_text_ai/services.yaml

@@ -3,63 +3,55 @@ ask_question:
   description: >-
     Send a question to the AI model and receive a detailed response.
     The response will be stored in the conversation history and can be retrieved later.
-    Response time may vary based on model selection and server load.
   fields:
+    instance:
+      name: Instance
+      description: Name of the HA Text AI instance to use
+      required: true
+      selector:
+        entity:
+          integration: ha_text_ai
+          domain: sensor
+
     question:
       name: Question
-      description: >-
-        Your question or prompt for the AI assistant. Be specific and clear for better results.
-        You can ask about home automation, technical advice, or general questions.
-        For complex queries, consider breaking them into smaller parts.
+      description: Your question or prompt for the AI assistant
       required: true
-      example: |
-        What automations would you recommend for a smart kitchen?
-        Consider energy efficiency, convenience, and integration with:
-        - Smart lighting
-        - Appliance control
-        - Temperature monitoring
-        - Voice commands
       selector:
         text:
           multiline: true
           type: text
 
+    system_prompt:
+      name: System Prompt
+      description: Optional system prompt to set context for this specific question
+      required: false
+      selector:
+        text:
+          multiline: true
+
+    context_messages:
+      name: Context Messages
+      description: Number of previous messages to include in context (1-20)
+      required: false
+      default: 5
+      selector:
+        number:
+          min: 1
+          max: 20
+          step: 1
+          mode: slider
+
     model:
       name: Model
-      description: >-
-        Select an AI model to use (optional, overrides default setting).
-        You can choose from predefined models or enter your own model identifier.
-        Different models have different capabilities and token limits.
-        Note: More capable models may have longer response times and higher API costs.
+      description: "Select AI model to use (optional, overrides default setting)"
       required: false
-      example: "gpt-3.5-turbo"
-      default: "gpt-3.5-turbo"
       selector:
-        select:
-          custom_value: true
-          options:
-            - label: "GPT-3.5 Turbo (Fast & Efficient)"
-              value: "gpt-3.5-turbo"
-            - label: "GPT-3.5 Turbo 16K (Extended)"
-              value: "gpt-3.5-turbo-16k"
-            - label: "GPT-4 (Most Capable)"
-              value: "gpt-4"
-            - label: "GPT-4 32K (Extended Context)"
-              value: "gpt-4-32k"
-            - label: "GPT-4 Turbo (Latest)"
-              value: "gpt-4-1106-preview"
-            - label: "Claude-3 Sonnet"
-              value: "claude-3-sonnet"
-          mode: dropdown
+        text: {}
 
     temperature:
       name: Temperature
-      description: >-
-        Controls response creativity (0-2):
-        0.0-0.3: Focused, consistent responses (best for technical/factual queries)
-        0.4-0.7: Balanced responses (recommended for most uses)
-        0.8-2.0: More creative, varied responses (best for brainstorming)
-        Note: Higher values may produce less predictable results.
+      description: Controls response creativity (0.0-2.0)
       required: false
       default: 0.7
       selector:
@@ -68,17 +60,10 @@ ask_question:
           max: 2.0
           step: 0.1
           mode: slider
-          unit_of_measurement: ""
 
     max_tokens:
       name: Max Tokens
-      description: >-
-        Maximum length of the response. Higher values allow longer responses but use more API tokens.
-        Recommended ranges:
-        - Short responses (256-512): Quick answers, status updates
-        - Medium responses (512-1024): Detailed explanations, instructions
-        - Long responses (1024-4096): Complex analysis, multiple examples
-        Note: Actual response length may be shorter based on content.
+      description: Maximum length of the response (1-4096 tokens)
       required: false
       default: 1000
       selector:
@@ -88,37 +73,36 @@ ask_question:
           step: 1
           mode: box
 
-    system_prompt:
-      name: System Prompt
-      description: >-
-        Optional system prompt to set context for this specific question.
-        This will temporarily override the default system prompt.
-      required: false
-      example: "You are a home automation expert focused on energy efficiency"
-      selector:
-        text:
-          multiline: true
-
 clear_history:
   name: Clear History
   description: >-
-    Delete all stored questions and responses from the conversation history.
-    This action cannot be undone. Consider using 'get_history' first if you need to backup the data.
-    System prompt settings will be preserved.
-  fields: {}
+    Delete all stored questions and responses from the conversation history
+  fields:
+    instance:
+      name: Instance
+      description: Name of the HA Text AI instance to clear history for
+      required: true
+      selector:
+        entity:
+          integration: ha_text_ai
+          domain: sensor
 
 get_history:
   name: Get History
-  description: >-
-    Retrieve recent conversation history, including questions, responses, and timestamps.
-    Results are ordered from newest to oldest and include metadata like model used and response times.
+  description: Retrieve conversation history with optional filtering and sorting
   fields:
+    instance:
+      name: Instance
+      description: Name of the HA Text AI instance to get history from
+      required: true
+      selector:
+        entity:
+          integration: ha_text_ai
+          domain: sensor
+
     limit:
       name: Limit
-      description: >-
-        Number of most recent conversations to return (1-100).
-        Higher values return more history but may take longer to process.
-        Default: 10 conversations
+      description: Number of conversations to return (1-100)
       required: false
       default: 10
       selector:
@@ -129,47 +113,57 @@ get_history:
           mode: box
 
     filter_model:
-      name: Filter by Model
-      description: >-
-        Only return conversations using a specific AI model.
-        Leave empty to show all models.
+      name: Filter Model
+      description: Filter conversations by specific AI model
       required: false
+      selector:
+        text:
+          multiline: false
+
+    start_date:
+      name: Start Date
+      description: Filter conversations starting from this date/time
+      required: false
+      selector:
+        text:
+          multiline: false
+
+    include_metadata:
+      name: Include Metadata
+      description: Include additional information like tokens used, response time, etc.
+      required: false
+      default: false
+      selector:
+        boolean:
+
+    sort_order:
+      name: Sort Order
+      description: Sort order for results (newest or oldest first)
+      required: false
+      default: newest
       selector:
         select:
-          custom_value: true
           options:
-            - label: "All Models"
-              value: ""
-            - label: "GPT-3.5 Turbo"
-              value: "gpt-3.5-turbo"
-            - label: "GPT-4"
-              value: "gpt-4"
-            - label: "Claude-3 Sonnet"
-              value: "claude-3-sonnet"
-          mode: dropdown
+            - newest
+            - oldest
 
 set_system_prompt:
   name: Set System Prompt
-  description: >-
-    Set default system behavior instructions for all future conversations.
-    This defines how the AI should behave and respond to questions.
+  description: Set default system behavior instructions for all future conversations
   fields:
+    instance:
+      name: Instance
+      description: Name of the HA Text AI instance to set system prompt for
+      required: true
+      selector:
+        entity:
+          integration: ha_text_ai
+          domain: sensor
+
     prompt:
       name: System Prompt
-      description: >-
-        Instructions that define how the AI should behave and respond.
-        Be specific about the desired expertise, tone, and format of responses.
-        Maximum length: 1000 characters.
+      description: Instructions that define how the AI should behave and respond
       required: true
-      example: |
-        You are a home automation expert assistant. Focus on:
-        1. Practical and efficient solutions
-        2. Energy-saving recommendations
-        3. Integration with popular smart home platforms
-        4. Security and privacy considerations
-        Provide detailed but concise responses with clear steps when applicable.
-        Format complex responses with bullet points or numbered lists.
-        Include warnings about potential risks or limitations.
       selector:
         text:
           multiline: true

custom_components/ha_text_ai/translations/de.json

@@ -0,0 +1,266 @@
+{
+  "config": {
+    "step": {
+      "provider": {
+        "title": "KI-Anbieter auswählen",
+        "description": "Wählen Sie den KI-Dienstanbieter für diese Instanz aus.",
+        "data": {
+          "api_provider": "API-Anbieter",
+          "context_messages": "Anzahl der zu behaltenden Kontextnachrichten (1-20)"
+        }
+      },
+      "user": {
+        "title": "HA Text AI-Instanz konfigurieren",
+        "description": "Richten Sie eine neue KI-Assistenteninstanz mit Ihrem ausgewählten Anbieter ein.",
+        "data": {
+          "name": "Instanzname (z. B. 'GPT-Assistent', 'Claude-Helfer')",
+          "api_key": "API-Schlüssel zur Authentifizierung",
+          "model": "Zu verwendendes KI-Modell",
+          "temperature": "Antwortkreativität (0-2, niedriger = fokussierter)",
+          "max_tokens": "Maximale Antwortlänge (1-4096 Token)",
+          "api_endpoint": "Benutzerdefinierte API-Endpunkt-URL (optional)",
+          "api_provider": "API-Anbieter",
+          "request_interval": "Mindestzeit zwischen Anfragen (0,1-60 Sekunden)",
+          "context_messages": "Anzahl der zu behaltenden Kontextnachrichten (1-20)",
+          "max_history_size": "Maximale Größe des Konversationsverlaufs (1-100)"
+        }
+      }
+    },
+    "error": {
+      "name_exists": "Eine Instanz mit diesem Namen existiert bereits",
+      "invalid_name": "Ungültiger Instanzname",
+      "invalid_auth": "Authentifizierung fehlgeschlagen - überprüfen Sie Ihren API-Schlüssel",
+      "invalid_api_key": "Ungültiger API-Schlüssel - überprüfen Sie Ihre Anmeldedaten",
+      "cannot_connect": "Verbindung zum API-Dienst fehlgeschlagen",
+      "invalid_model": "Das ausgewählte Modell ist nicht verfügbar",
+      "rate_limit": "Ratenlimit überschritten",
+      "context_length": "Kontextlänge überschritten",
+      "rate_limit_exceeded": "API-Ratenlimit überschritten",
+      "maintenance": "Dienst befindet sich in der Wartung",
+      "invalid_response": "Ungültige API-Antwort empfangen",
+      "api_error": "Fehler im API-Dienst aufgetreten",
+      "timeout": "Anfrage ist abgelaufen",
+      "invalid_instance": "Ungültige Instanz angegeben",
+      "unknown": "Es ist ein unerwarteter Fehler aufgetreten",
+      "empty": "Name darf nicht leer sein",
+      "invalid_characters": "Name darf nur Buchstaben, Zahlen, Leerzeichen, Unterstriche und Bindestriche enthalten",
+      "name_too_long": "Name darf maximal 50 Zeichen lang sein"
+    }
+  },
+  "options": {
+    "step": {
+      "init": {
+        "title": "Instanzeinstellungen aktualisieren",
+        "description": "Ändern Sie die Einstellungen für diese KI-Assistenteninstanz.",
+        "data": {
+          "model": "KI-Modell",
+          "temperature": "Antwortkreativität (0-2)",
+          "max_tokens": "Maximale Antwortlänge (1-4096)",
+          "request_interval": "Mindestzeitraum zwischen Anfragen (0,1-60 Sekunden)",
+          "context_messages": "Anzahl der vorherigen Nachrichten, die im Kontext enthalten sein sollen (1-20)",
+          "max_history_size": "Maximale Größe des Konversationsverlaufs (1-100)"
+        }
+      }
+    }
+  },
+  "services": {
+    "ask_question": {
+      "name": "Frage stellen (HA Text AI)",
+      "description": "Senden Sie eine Frage an das KI-Modell und erhalten Sie eine detaillierte Antwort. Die Antwort wird im Konversationsverlauf gespeichert und kann später abgerufen werden.",
+      "fields": {
+        "instance": {
+          "name": "Instanz",
+          "description": "Name der zu verwendenden HA Text AI-Instanz"
+        },
+        "question": {
+          "name": "Frage",
+          "description": "Ihre Frage oder Aufforderung an den KI-Assistenten"
+        },
+        "context_messages": {
+          "name": "Kontextnachrichten",
+          "description": "Anzahl der vorherigen Nachrichten, die im Kontext enthalten sein sollen (1-20)"
+        },
+        "system_prompt": {
+          "name": "Systemprompt",
+          "description": "Optionaler Systemprompt, um den Kontext für diese spezielle Frage festzulegen"
+        },
+        "model": {
+          "name": "Modell",
+          "description": "Wählen Sie das zu verwendende KI-Modell aus (optional, überschreibt die Standardeinstellung)"
+        },
+        "temperature": {
+          "name": "Temperatur",
+          "description": "Steuert die Antwortkreativität (0.0-2.0)"
+        },
+        "max_tokens": {
+          "name": "Max. Token",
+          "description": "Maximale Länge der Antwort (1-4096 Token)"
+        }
+      }
+    },
+    "clear_history": {
+      "name": "Verlauf löschen",
+      "description": "Alle gespeicherten Fragen und Antworten aus dem Konversationsverlauf löschen",
+      "fields": {
+        "instance": {
+          "name": "Instanz",
+          "description": "Name der HA Text AI-Instanz, deren Verlauf gelöscht werden soll"
+        }
+      }
+    },
+    "get_history": {
+      "name": "Verlauf abrufen",
+      "description": "Konversationsverlauf mit optionalem Filtern und Sortieren abrufen",
+      "fields": {
+        "instance": {
+          "name": "Instanz",
+          "description": "Name der HA Text AI-Instanz, von der der Verlauf abgerufen werden soll"
+        },
+        "limit": {
+          "name": "Limit",
+          "description": "Anzahl der zurückzugebenden Konversationen (1-100)"
+        },
+        "filter_model": {
+          "name": "Modell filtern",
+          "description": "Konversationen nach einem bestimmten KI-Modell filtern"
+        },
+        "start_date": {
+          "name": "Startdatum",
+          "description": "Konversationen ab diesem Datum/Uhrzeit filtern"
+        },
+        "include_metadata": {
+          "name": "Metadaten einschließen",
+          "description": "Zusätzliche Informationen wie verwendete Token, Antwortzeit usw. einschließen"
+        },
+        "sort_order": {
+          "name": "Sortierreihenfolge",
+          "description": "Sortierreihenfolge für die Ergebnisse (neueste oder älteste zuerst)"
+        }
+      }
+    },
+    "set_system_prompt": {
+      "name": "Systemprompt festlegen",
+      "description": "Legen Sie Standardanweisungen für das Systemverhalten für alle zukünftigen Konversationen fest",
+      "fields": {
+        "instance": {
+          "name": "Instanz",
+          "description": "Name der HA Text AI-Instanz, für die der Systemprompt festgelegt werden soll"
+        },
+        "prompt": {
+          "name": "Systemprompt",
+          "description": "Anweisungen, die definieren, wie sich die KI verhalten und antworten soll"
+        }
+      }
+    }
+  },
+  "entity": {
+    "sensor": {
+      "ha_text_ai": {
+        "name": "{name}",
+        "state": {
+          "ready": "Bereit",
+          "processing": "Verarbeitung",
+          "error": "Fehler",
+          "disconnected": "Getrennt",
+          "rate_limited": "Ratenlimit",
+          "maintenance": "Wartung",
+          "initializing": "Initialisierung",
+          "retrying": "Wiederholen",
+          "queued": "Warteschlange"
+        },
+        "state_attributes": {
+          "question": {
+            "name": "Letzte Frage"
+          },
+          "response": {
+            "name": "Letzte Antwort"
+          },
+          "model": {
+            "name": "Aktuelles Modell"
+          },
+          "temperature": {
+            "name": "Temperatur"
+          },
+          "max_tokens": {
+            "name": "Max. Token"
+          },
+          "system_prompt": {
+            "name": "Systemprompt"
+          },
+          "response_time": {
+            "name": "Letzte Antwortzeit"
+          },
+          "total_responses": {
+            "name": "Gesamtzahl der Antworten"
+          },
+          "error_count": {
+            "name": "Fehleranzahl"
+          },
+          "last_error": {
+            "name": "Letzter Fehler"
+          },
+          "api_status": {
+            "name": "API-Status"
+          },
+          "tokens_used": {
+            "name": "Verwendete Token insgesamt"
+          },
+          "average_response_time": {
+            "name": "Durchschnittliche Antwortzeit"
+          },
+          "last_request_time": {
+            "name": "Zeitpunkt der letzten Anfrage"
+          },
+          "is_processing": {
+            "name": "Verarbeitungsstatus"
+          },
+          "is_rate_limited": {
+            "name": "Ratenlimit-Status"
+          },
+          "is_maintenance": {
+            "name": "Wartungsstatus"
+          },
+          "api_version": {
+            "name": "API-Version"
+          },
+          "endpoint_status": {
+            "name": "Endpunkt-Status"
+          },
+          "performance_metrics": {
+            "name": "Leistungsmetriken"
+          },
+          "history_size": {
+            "name": "Verlaufsgröße"
+          },
+          "uptime": {
+            "name": "Betriebszeit"
+          },
+          "total_tokens": {
+            "name": "Gesamtzahl der Token"
+          },
+          "prompt_tokens": {
+            "name": "Prompt-Token"
+          },
+          "completion_tokens": {
+            "name": "Completion-Token"
+          },
+          "successful_requests": {
+            "name": "Erfolgreiche Anfragen"
+          },
+          "failed_requests": {
+            "name": "Fehlgeschlagene Anfragen"
+          },
+          "average_latency": {
+            "name": "Durchschnittliche Latenz"
+          },
+          "max_latency": {
+            "name": "Maximale Latenz"
+          },
+          "min_latency": {
+            "name": "Minimale Latenz"
+          }
+        }
+      }
+    }
+  }
+}

custom_components/ha_text_ai/translations/en.json

@@ -1,96 +1,266 @@
 {
-    "config": {
-        "step": {
-            "user": {
-                "title": "Set up HA Text AI",
-                "description": "Configure your AI integration (OpenAI, Anthropic, etc.)",
-                "data": {
-                    "api_key": "Your API key",
-                    "model": "AI model to use for responses (e.g., gpt-3.5-turbo, claude-3-sonnet)",
-                    "temperature": "Temperature for response generation (0-2)",
-                    "max_tokens": "Maximum tokens in response (1-4096)",
-                    "api_endpoint": "API endpoint URL (optional, for custom endpoints)",
-                    "request_interval": "Minimum time between API requests (seconds)",
-                    "system_prompt": "Default system prompt for all conversations"
-                }
-            }
-        },
-        "error": {
-            "invalid_api_key": "Invalid API key - please check your credentials",
-            "cannot_connect": "Failed to connect to API - check endpoint and network",
-            "invalid_model": "Selected model is not available or invalid",
-            "rate_limit": "API rate limit exceeded - please wait",
-            "unknown": "Unexpected error occurred - check logs for details"
+  "config": {
+    "step": {
+      "provider": {
+        "title": "Select AI Provider",
+        "description": "Choose which AI service provider to use for this instance.",
+        "data": {
+          "api_provider": "API Provider",
+          "context_messages": "Number of context messages to retain (1-20)"
         }
+      },
+      "user": {
+        "title": "Configure HA Text AI Instance",
+        "description": "Set up a new AI assistant instance with your selected provider.",
+        "data": {
+          "name": "Instance name (e.g., 'GPT Assistant', 'Claude Helper')",
+          "api_key": "API key for authentication",
+          "model": "AI model to use",
+          "temperature": "Response creativity (0-2, lower = more focused)",
+          "max_tokens": "Maximum response length (1-4096 tokens)",
+          "api_endpoint": "Custom API endpoint URL (optional)",
+          "api_provider": "API Provider",
+          "request_interval": "Minimum time between requests (0.1-60 seconds)",
+          "context_messages": "Number of context messages to retain (1-20)",
+          "max_history_size": "Maximum conversation history size (1-100)"
+        }
+      }
     },
-    "options": {
-        "step": {
-            "init": {
-                "title": "HA Text AI Options",
-                "data": {
-                    "model": "AI model selection",
-                    "temperature": "Response temperature (0-2)",
-                    "max_tokens": "Maximum response length",
-                    "request_interval": "Time between requests (seconds)",
-                    "system_prompt": "Default system instructions"
-                }
-            }
-        }
-    },
-    "services": {
-        "ask_question": {
-            "name": "Ask Question",
-            "description": "Send a question to the AI model and receive a response",
-            "fields": {
-                "question": {
-                    "name": "Question",
-                    "description": "Your question or prompt for the AI"
-                },
-                "system_prompt": {
-                    "name": "System Prompt",
-                    "description": "Optional system prompt to override default for this question"
-                },
-                "model": {
-                    "name": "Model",
-                    "description": "Optional AI model to use for this question"
-                },
-                "temperature": {
-                    "name": "Temperature",
-                    "description": "Optional temperature setting for this question (0-2)"
-                },
-                "max_tokens": {
-                    "name": "Max Tokens",
-                    "description": "Optional maximum token limit for this response"
-                }
-            }
-        },
-        "clear_history": {
-            "name": "Clear History",
-            "description": "Delete all stored conversation history"
-        },
-        "get_history": {
-            "name": "Get History",
-            "description": "Retrieve conversation history with metadata",
-            "fields": {
-                "limit": {
-                    "name": "Limit",
-                    "description": "Maximum number of conversations to return"
-                },
-                "filter_model": {
-                    "name": "Filter Model",
-                    "description": "Optional filter to show only specific model responses"
-                }
-            }
-        },
-        "set_system_prompt": {
-            "name": "Set System Prompt",
-            "description": "Set default system behavior instructions",
-            "fields": {
-                "prompt": {
-                    "name": "System Prompt",
-                    "description": "Instructions defining AI behavior and response style"
-                }
-            }
-        }
+    "error": {
+      "name_exists": "An instance with this name already exists",
+      "invalid_name": "Invalid instance name",
+      "invalid_auth": "Authentication failed - check your API key",
+      "invalid_api_key": "Invalid API key - please verify your credentials",
+      "cannot_connect": "Failed to connect to API service",
+      "invalid_model": "Selected model is not available",
+      "rate_limit": "Rate limit exceeded",
+      "context_length": "Context length exceeded",
+      "rate_limit_exceeded": "API rate limit exceeded",
+      "maintenance": "Service is under maintenance",
+      "invalid_response": "Invalid API response received",
+      "api_error": "API service error occurred",
+      "timeout": "Request timed out",
+      "invalid_instance": "Invalid instance specified",
+      "unknown": "Unexpected error occurred",
+      "empty": "Name cannot be empty",
+      "invalid_characters": "Name can only contain letters, numbers, spaces, underscores and hyphens",
+      "name_too_long": "Name must be 50 characters or less"
     }
+  },
+  "options": {
+    "step": {
+      "init": {
+        "title": "Update Instance Settings",
+        "description": "Modify settings for this AI assistant instance.",
+        "data": {
+          "model": "AI model",
+          "temperature": "Response creativity (0-2)",
+          "max_tokens": "Maximum response length (1-4096)",
+          "request_interval": "Minimum request interval (0.1-60 seconds)",
+          "context_messages": "Number of previous messages to include in context (1-20)",
+          "max_history_size": "Maximum conversation history size (1-100)"
+        }
+      }
+    }
+  },
+  "services": {
+    "ask_question": {
+      "name": "Ask Question (HA Text AI)",
+      "description": "Send a question to the AI model and receive a detailed response. The response will be stored in the conversation history and can be retrieved later.",
+      "fields": {
+        "instance": {
+          "name": "Instance",
+          "description": "Name of the HA Text AI instance to use"
+        },
+        "question": {
+          "name": "Question",
+          "description": "Your question or prompt for the AI assistant"
+        },
+        "context_messages": {
+          "name": "Context Messages",
+          "description": "Number of previous messages to include in context (1-20)"
+        },
+        "system_prompt": {
+          "name": "System Prompt",
+          "description": "Optional system prompt to set context for this specific question"
+        },
+        "model": {
+          "name": "Model",
+          "description": "Select AI model to use (optional, overrides default setting)"
+        },
+        "temperature": {
+          "name": "Temperature",
+          "description": "Controls response creativity (0.0-2.0)"
+        },
+        "max_tokens": {
+          "name": "Max Tokens",
+          "description": "Maximum length of the response (1-4096 tokens)"
+        }
+      }
+    },
+    "clear_history": {
+      "name": "Clear History",
+      "description": "Delete all stored questions and responses from the conversation history",
+      "fields": {
+        "instance": {
+          "name": "Instance",
+          "description": "Name of the HA Text AI instance to clear history for"
+        }
+      }
+    },
+    "get_history": {
+      "name": "Get History",
+      "description": "Retrieve conversation history with optional filtering and sorting",
+      "fields": {
+        "instance": {
+          "name": "Instance",
+          "description": "Name of the HA Text AI instance to get history from"
+        },
+        "limit": {
+          "name": "Limit",
+          "description": "Number of conversations to return (1-100)"
+        },
+        "filter_model": {
+          "name": "Filter Model",
+          "description": "Filter conversations by specific AI model"
+        },
+        "start_date": {
+          "name": "Start Date",
+          "description": "Filter conversations starting from this date/time"
+        },
+        "include_metadata": {
+          "name": "Include Metadata",
+          "description": "Include additional information like tokens used, response time, etc."
+        },
+        "sort_order": {
+          "name": "Sort Order",
+          "description": "Sort order for results (newest or oldest first)"
+        }
+      }
+    },
+    "set_system_prompt": {
+      "name": "Set System Prompt",
+      "description": "Set default system behavior instructions for all future conversations",
+      "fields": {
+        "instance": {
+          "name": "Instance",
+          "description": "Name of the HA Text AI instance to set system prompt for"
+        },
+        "prompt": {
+          "name": "System Prompt",
+          "description": "Instructions that define how the AI should behave and respond"
+        }
+      }
+    }
+  },
+  "entity": {
+    "sensor": {
+      "ha_text_ai": {
+        "name": "{name}",
+        "state": {
+          "ready": "Ready",
+          "processing": "Processing",
+          "error": "Error",
+          "disconnected": "Disconnected",
+          "rate_limited": "Rate Limited",
+          "maintenance": "Maintenance",
+          "initializing": "Initializing",
+          "retrying": "Retrying",
+          "queued": "Queued"
+        },
+        "state_attributes": {
+          "question": {
+            "name": "Last Question"
+          },
+          "response": {
+            "name": "Last Response"
+          },
+          "model": {
+            "name": "Current Model"
+          },
+          "temperature": {
+            "name": "Temperature"
+          },
+          "max_tokens": {
+            "name": "Max Tokens"
+          },
+          "system_prompt": {
+            "name": "System Prompt"
+          },
+          "response_time": {
+            "name": "Last Response Time"
+          },
+          "total_responses": {
+            "name": "Total Responses"
+          },
+          "error_count": {
+            "name": "Error Count"
+          },
+          "last_error": {
+            "name": "Last Error"
+          },
+          "api_status": {
+            "name": "API Status"
+          },
+          "tokens_used": {
+            "name": "Total Tokens Used"
+          },
+          "average_response_time": {
+            "name": "Average Response Time"
+          },
+          "last_request_time": {
+            "name": "Last Request Time"
+          },
+          "is_processing": {
+            "name": "Processing Status"
+          },
+          "is_rate_limited": {
+            "name": "Rate Limited Status"
+          },
+          "is_maintenance": {
+            "name": "Maintenance Status"
+          },
+          "api_version": {
+            "name": "API Version"
+          },
+          "endpoint_status": {
+            "name": "Endpoint Status"
+          },
+          "performance_metrics": {
+            "name": "Performance Metrics"
+          },
+          "history_size": {
+            "name": "History Size"
+          },
+          "uptime": {
+            "name": "Uptime"
+          },
+          "total_tokens": {
+            "name": "Total Tokens"
+          },
+          "prompt_tokens": {
+            "name": "Prompt Tokens"
+          },
+          "completion_tokens": {
+            "name": "Completion Tokens"
+          },
+          "successful_requests": {
+            "name": "Successful Requests"
+          },
+          "failed_requests": {
+            "name": "Failed Requests"
+          },
+          "average_latency": {
+            "name": "Average Latency"
+          },
+          "max_latency": {
+            "name": "Maximum Latency"
+          },
+          "min_latency": {
+            "name": "Minimum Latency"
+          }
+        }
+      }
+    }
+  }
 }

custom_components/ha_text_ai/translations/ru.json

@@ -1,96 +1,266 @@
 {
-    "config": {
-        "step": {
-            "user": {
-                "title": "Настройка HA Text AI",
-                "description": "Настройка интеграции с AI-сервисами (OpenAI, Anthropic и др.)",
-                "data": {
-                    "api_key": "Ваш API-ключ",
-                    "model": "Модель AI для ответов (например, gpt-3.5-turbo, claude-3-sonnet)",
-                    "temperature": "Температура генерации ответов (0-2)",
-                    "max_tokens": "Максимальное количество токенов в ответе (1-4096)",
-                    "api_endpoint": "URL конечной точки API (необязательно, для пользовательских endpoint)",
-                    "request_interval": "Минимальный интервал между запросами к API (секунды)",
-                    "system_prompt": "Системная инструкция по умолчанию для всех диалогов"
-                }
-            }
-        },
-        "error": {
-            "invalid_api_key": "Недействительный API-ключ - проверьте учетные данные",
-            "cannot_connect": "Не удалось подключиться к API - проверьте endpoint и сеть",
-            "invalid_model": "Выбранная модель недоступна или некорректна",
-            "rate_limit": "Превышен лимит запросов API - пожалуйста, подождите",
-            "unknown": "Произошла непредвиденная ошибка - проверьте логи"
+  "config": {
+    "step": {
+      "provider": {
+        "title": "Выбор поставщика ИИ",
+        "description": "Выберите поставщика услуг ИИ для этой инстанции.",
+        "data": {
+          "api_provider": "Поставщик API",
+          "context_messages": "Количество контекстных сообщений для сохранения (1-20)"
         }
+      },
+      "user": {
+        "title": "Настройка инстанции HA Text AI",
+        "description": "Настройте новую инстанцию помощника ИИ с выбранным вами поставщиком.",
+        "data": {
+          "name": "Имя инстанции (например, 'GPT Assistant', 'Claude Helper')",
+          "api_key": "API-ключ для аутентификации",
+          "model": "Используемая модель ИИ",
+          "temperature": "Креативность ответа (0-2, чем ниже, тем больше фокусировки)",
+          "max_tokens": "Максимальная длина ответа (1-4096 токенов)",
+          "api_endpoint": "Пользовательский URL-адрес конечной точки API (необязательно)",
+          "api_provider": "Поставщик API",
+          "request_interval": "Минимальное время между запросами (0,1-60 секунд)",
+          "context_messages": "Количество контекстных сообщений для сохранения (1-20)",
+          "max_history_size": "Максимальный размер истории разговора (1-100)"
+        }
+      }
     },
-    "options": {
-        "step": {
-            "init": {
-                "title": "Настройки HA Text AI",
-                "data": {
-                    "model": "Выбор модели AI",
-                    "temperature": "Температура ответов (0-2)",
-                    "max_tokens": "Максимальная длина ответа",
-                    "request_interval": "Интервал между запросами (секунды)",
-                    "system_prompt": "Системные инструкции по умолчанию"
-                }
-            }
-        }
-    },
-    "services": {
-        "ask_question": {
-            "name": "Задать вопрос",
-            "description": "Отправить вопрос модели AI и получить ответ",
-            "fields": {
-                "question": {
-                    "name": "Вопрос",
-                    "description": "Ваш вопрос или запрос для AI"
-                },
-                "system_prompt": {
-                    "name": "Системная инструкция",
-                    "description": "Необязательная системная инструкция, заменяющая инструкцию по умолчанию для этого вопроса"
-                },
-                "model": {
-                    "name": "Модель",
-                    "description": "Необязательная модель AI для этого вопроса"
-                },
-                "temperature": {
-                    "name": "Температура",
-                    "description": "Необязательная настройка температуры для этого вопроса (0-2)"
-                },
-                "max_tokens": {
-                    "name": "Макс. токенов",
-                    "description": "Необязательное ограничение количества токенов для этого ответа"
-                }
-            }
-        },
-        "clear_history": {
-            "name": "Очистить историю",
-            "description": "Удалить всю сохраненную историю диалогов"
-        },
-        "get_history": {
-            "name": "Получить историю",
-            "description": "Получить историю диалогов с метаданными",
-            "fields": {
-                "limit": {
-                    "name": "Лимит",
-                    "description": "Максимальное количество диалогов для возврата"
-                },
-                "filter_model": {
-                    "name": "Фильтр по модели",
-                    "description": "Необязательный фильтр для показа ответов только от определенной модели"
-                }
-            }
-        },
-        "set_system_prompt": {
-            "name": "Установить системную инструкцию",
-            "description": "Задать системные инструкции по умолчанию",
-            "fields": {
-                "prompt": {
-                    "name": "Системная инструкция",
-                    "description": "Инструкции, определяющие поведение AI и стиль ответов"
-                }
-            }
-        }
+    "error": {
+      "name_exists": "Инстанция с таким именем уже существует",
+      "invalid_name": "Некорректное имя инстанции",
+      "invalid_auth": "Аутентификация не удалась - проверьте ваш API-ключ",
+      "invalid_api_key": "Неверный API-ключ - проверьте ваши учетные данные",
+      "cannot_connect": "Не удалось подключиться к службе API",
+      "invalid_model": "Выбранная модель недоступна",
+      "rate_limit": "Превышен лимит запросов",
+      "context_length": "Превышена длина контекста",
+      "rate_limit_exceeded": "Превышен лимит запросов API",
+      "maintenance": "Сервис находится на техническом обслуживании",
+      "invalid_response": "Получен неверный ответ API",
+      "api_error": "Произошла ошибка службы API",
+      "timeout": "Запрос превысил время ожидания",
+      "invalid_instance": "Указана неверная инстанция",
+      "unknown": "Произошла непредвиденная ошибка",
+      "empty": "Имя не может быть пустым",
+      "invalid_characters": "Имя может содержать только буквы, цифры, пробелы, подчеркивания и дефисы",
+      "name_too_long": "Имя должно быть не более 50 символов"
     }
+  },
+  "options": {
+    "step": {
+      "init": {
+        "title": "Обновление настроек инстанции",
+        "description": "Измените настройки для этой инстанции помощника ИИ.",
+        "data": {
+          "model": "Модель ИИ",
+          "temperature": "Креативность ответа (0-2)",
+          "max_tokens": "Максимальная длина ответа (1-4096)",
+          "request_interval": "Минимальный интервал между запросами (0,1-60 секунд)",
+          "context_messages": "Количество предыдущих сообщений для включения в контекст (1-20)",
+          "max_history_size": "Максимальный размер истории разговора (1-100)"
+        }
+      }
+    }
+  },
+  "services": {
+    "ask_question": {
+      "name": "Задать вопрос (HA Text AI)",
+      "description": "Отправьте вопрос модели ИИ и получите подробный ответ. Ответ будет сохранен в истории разговора и может быть извлечен позже.",
+      "fields": {
+        "instance": {
+          "name": "Инстанция",
+          "description": "Имя используемой инстанции HA Text AI"
+        },
+        "question": {
+          "name": "Вопрос",
+          "description": "Ваш вопрос или запрос к помощнику ИИ"
+        },
+        "context_messages": {
+          "name": "Контекстные сообщения",
+          "description": "Количество предыдущих сообщений для включения в контекст (1-20)"
+        },
+        "system_prompt": {
+          "name": "Системный запрос",
+          "description": "Необязательный системный запрос для установки контекста для этого конкретного вопроса"
+        },
+        "model": {
+          "name": "Модель",
+          "description": "Выберите модель ИИ для использования (необязательно, переопределяет настройку по умолчанию)"
+        },
+        "temperature": {
+          "name": "Температура",
+          "description": "Управляет креативностью ответа (0.0-2.0)"
+        },
+        "max_tokens": {
+          "name": "Макс. токенов",
+          "description": "Максимальная длина ответа (1-4096 токенов)"
+        }
+      }
+    },
+    "clear_history": {
+      "name": "Очистить историю",
+      "description": "Удалить все сохраненные вопросы и ответы из истории разговора",
+      "fields": {
+        "instance": {
+          "name": "Инстанция",
+          "description": "Имя инстанции HA Text AI, для которой нужно очистить историю"
+        }
+      }
+    },
+    "get_history": {
+      "name": "Получить историю",
+      "description": "Извлечь историю разговора с возможностью фильтрации и сортировки",
+      "fields": {
+        "instance": {
+          "name": "Инстанция",
+          "description": "Имя инстанции HA Text AI, из которой нужно получить историю"
+        },
+        "limit": {
+          "name": "Лимит",
+          "description": "Количество разговоров для возврата (1-100)"
+        },
+        "filter_model": {
+          "name": "Фильтр модели",
+          "description": "Фильтрация разговоров по определенной модели ИИ"
+        },
+        "start_date": {
+          "name": "Дата начала",
+          "description": "Фильтрация разговоров, начиная с этой даты/времени"
+        },
+        "include_metadata": {
+          "name": "Включить метаданные",
+          "description": "Включить дополнительную информацию, такую как использованные токены, время ответа и т.д."
+        },
+        "sort_order": {
+          "name": "Порядок сортировки",
+          "description": "Порядок сортировки результатов (самые новые или самые старые)"
+        }
+      }
+    },
+    "set_system_prompt": {
+      "name": "Установить системный запрос",
+      "description": "Установить инструкции по умолчанию для поведения системы для всех будущих разговоров",
+      "fields": {
+        "instance": {
+          "name": "Инстанция",
+          "description": "Имя инстанции HA Text AI, для которой нужно установить системный запрос"
+        },
+        "prompt": {
+          "name": "Системный запрос",
+          "description": "Инструкции, определяющие, как ИИ должен себя вести и отвечать"
+        }
+      }
+    }
+  },
+  "entity": {
+    "sensor": {
+      "ha_text_ai": {
+        "name": "{name}",
+        "state": {
+          "ready": "Готов",
+          "processing": "Обработка",
+          "error": "Ошибка",
+          "disconnected": "Отключен",
+          "rate_limited": "Лимит запросов",
+          "maintenance": "Техническое обслуживание",
+          "initializing": "Инициализация",
+          "retrying": "Повторная попытка",
+          "queued": "В очереди"
+        },
+        "state_attributes": {
+          "question": {
+            "name": "Последний вопрос"
+          },
+          "response": {
+            "name": "Последний ответ"
+          },
+          "model": {
+            "name": "Текущая модель"
+          },
+          "temperature": {
+            "name": "Температура"
+          },
+          "max_tokens": {
+            "name": "Макс. токенов"
+          },
+          "system_prompt": {
+            "name": "Системный запрос"
+          },
+          "response_time": {
+            "name": "Время последнего ответа"
+          },
+          "total_responses": {
+            "name": "Всего ответов"
+          },
+          "error_count": {
+            "name": "Количество ошибок"
+          },
+          "last_error": {
+            "name": "Последняя ошибка"
+          },
+          "api_status": {
+            "name": "Статус API"
+          },
+          "tokens_used": {
+            "name": "Использовано токенов всего"
+          },
+          "average_response_time": {
+            "name": "Среднее время ответа"
+          },
+          "last_request_time": {
+            "name": "Время последнего запроса"
+          },
+          "is_processing": {
+            "name": "Статус обработки"
+          },
+          "is_rate_limited": {
+            "name": "Статус ограничения запросов"
+          },
+          "is_maintenance": {
+            "name": "Статус технического обслуживания"
+          },
+          "api_version": {
+            "name": "Версия API"
+          },
+          "endpoint_status": {
+            "name": "Статус конечной точки"
+          },
+          "performance_metrics": {
+            "name": "Метрики производительности"
+          },
+          "history_size": {
+            "name": "Размер истории"
+          },
+          "uptime": {
+            "name": "Время работы"
+          },
+          "total_tokens": {
+            "name": "Всего токенов"
+          },
+          "prompt_tokens": {
+            "name": "Токены запроса"
+          },
+          "completion_tokens": {
+            "name": "Токены завершения"
+          },
+          "successful_requests": {
+            "name": "Успешных запросов"
+          },
+          "failed_requests": {
+            "name": "Неудачных запросов"
+          },
+          "average_latency": {
+            "name": "Средняя задержка"
+          },
+          "max_latency": {
+            "name": "Максимальная задержка"
+          },
+          "min_latency": {
+            "name": "Минимальная задержка"
+          }
+        }
+      }
+    }
+  }
 }

hacs.json

@@ -1,9 +1,5 @@
 {
   "name": "HA text AI",
   "render_readme": true,
-  "domains": ["sensor"],
-  "homeassistant": "2024.11.0",
-  "icon": "mdi:brain",
-  "version": "1.1.0",
-  "documentation": "https://github.com/smkrv/ha-text-ai"
+  "homeassistant": "2024.11.0"
 }

requirements.txt

@@ -1,3 +0,0 @@
-pytest
-pytest-asyncio
-homeassistant

structure.md

@@ -2,16 +2,24 @@
 ha-text-ai/
 │
 ├── custom_components/
-│   └── ha_text_ai/
-│       ├── __init__.py
-│       ├── config_flow.py
-│       ├── coordinator.py
-│       ├── manifest.json
-│       ├── sensor.py
-│       ├── services.yaml
-│       └── const.py
-│
-└── strings/
-    ├── en.json
-    └── ru.json
+    ├── ha_text_ai/
+    │   ├── __init__.py
+    │   ├── config_flow.py
+    │   ├── coordinator.py
+    │   ├── manifest.json
+    │   ├── sensor.py
+    │   ├── services.yaml
+    │   ├── const.py
+    │   └── api_client.py
+    │
+    ├── translations/
+    │   ├── en.json
+    │   ├── de.json
+    │   └── ru.json
+    │
+    └── icons/
+        ├── icon.png
+        ├── icon@2x.png
+        ├── logo.png
+        └── logo@2x.png
 ```