Release v2.0.0

repository

  - Change HACS badge from Default to Custom
  - Add custom repository installation steps
  - Update installation instructions
  - Revise documentation format

README.md

@@ -2,159 +2,190 @@
 
 <div align="center">  
 
-![GitHub release](https://img.shields.io/github/release/smkrv/ha-text-ai.svg?style=flat-square)
+  ![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-Custom-41BDF5.svg?style=flat-square)](https://github.com/hacs/integration)
-![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)
 
 </div>
 
 <p align="center">
-Transform your smart home experience with powerful AI assistance powered by OpenAI's GPT models
+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>
 
 ---
 
 ## 🌟 Features
 
-- 🧠 **Advanced AI Integration**: Leverage OpenAI's powerful models (GPT-3.5, GPT-4) for smart home interactions
+- 🧠 **Multi-Provider AI Integration**:
-- 💬 **Natural Language Control**: Control your home and get information using everyday language
+  - Support for OpenAI GPT models
-- 📝 **Conversation Memory**: Maintain context with conversation history tracking
+  - Anthropic Claude integration
-- ⚡ **Real-time Responses**: Get quick, contextual responses to your queries
+  - Custom API endpoints
-- 🎯 **Customizable Behavior**: Fine-tune AI responses with adjustable parameters
+  - Flexible model selection
-- 🔒 **Secure Integration**: Your API key and data are handled securely
+- 💬 **Advanced Language Processing**:
-- 🎨 **Flexible Configuration**: Easy setup with multiple configuration options
+  - Context-aware responses
-- 🔄 **Automation Ready**: Integrate AI responses into your automations
+  - Multi-turn conversations
+  - Custom system instructions
+  - Natural conversation flow
+- 📝 **Enhanced Memory Management**:
+  - Persistent conversation history
+  - Context-aware responses
+  - Customizable history limits
+  - Model-specific filtering
+- ⚡ **Performance Optimization**:
+  - Efficient token usage
+  - Smart rate limiting
+  - Response caching
+  - Request interval control
+- 🎯 **Advanced Customization**:
+  - Per-request model selection
+  - Adjustable parameters
+  - Custom system prompts
+  - Temperature control
+- 🔒 **Enhanced Security**:
+  - Secure API key storage
+  - Rate limiting protection
+  - Error handling
+  - 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 installation (Core, OS, Container, or Supervised)
+- Home Assistant 2023.8.0 or newer
-- OpenAI API key ([Get one here](https://platform.openai.com/account/api-keys))
+- API key from supported providers:
+  - OpenAI ([Get key](https://platform.openai.com/account/api-keys))
+  - Anthropic ([Get key](https://console.anthropic.com/))
 - Python 3.9 or newer
+- Stable internet connection
 
-## ⚡ Quick Start
+## ⚡ Installation
+
+### HACS Installation (Recommended)  
+1. Open HACS in Home Assistant  
+2. Click on the three dots in the top right corner  
+3. Select "Custom repositories"  
+4. Add `https://github.com/smkrv/ha-text-ai` as Integration  
+5. Click "Add"  
+6. Click on "Integrations" in HACS  
+7. Search for "HA Text AI"  
+8. Click "Download"  
+9. Restart Home Assistant  
 
 ### Manual Installation
-1. Download the repository
+1. Download the latest release
-2. Copy `custom_components/ha_text_ai` to your `custom_components` directory
+2. Extract and copy `custom_components/ha_text_ai` to your `custom_components` directory
 3. Restart Home Assistant
-4. Add configuration to `configuration.yaml`:
+4. Add configuration via UI or YAML
+
+## ⚙️ Configuration
+
+### Via UI (Recommended)
+1. Go to Settings → Devices & Services
+2. Click "Add Integration"
+3. Search for "HA Text AI"
+4. Follow the configuration steps
+
+### Via YAML
 ```yaml
 ha_text_ai:
-  api_key: !secret openai_api_key
+  api_key: !secret ai_api_key
+  model: gpt-3.5-turbo  # or claude-3-sonnet
+  temperature: 0.7
+  max_tokens: 1000
+  request_interval: 1.0
+  api_endpoint: https://api.openai.com/v1  # optional, for custom endpoints
+  system_prompt: |
+    You are a home automation expert assistant.
+    Focus on practical and efficient solutions.
 ```
 
-## ⚙️ Configuration Options
-
-| Option | Type | Default | Description |
-|--------|------|---------|-------------|
-| `api_key` | string | Required | Your OpenAI API key |
-| `model` | string | `gpt-3.5-turbo` | AI model to use |
-| `temperature` | float | `0.7` | Response creativity (0-2) |
-| `max_tokens` | integer | `1000` | Maximum response length |
-| `request_interval` | float | `1.0` | Minimum seconds between requests |
-| `api_endpoint` | string | OpenAI default | Custom API endpoint URL |
-
 ## 🛠️ Available Services
 
 ### ask_question
-Ask the AI assistant a question:
 ```yaml
 service: ha_text_ai.ask_question
 data:
   question: "What's the optimal temperature for sleeping?"
-  model: "gpt-4"  # optional
+  model: "claude-3-sonnet"  # optional
   temperature: 0.5  # optional
   max_tokens: 500  # optional
+  system_prompt: "You are a sleep optimization expert"  # optional
 ```
 
 ### set_system_prompt
-Configure AI behavior:
 ```yaml
 service: ha_text_ai.set_system_prompt
 data:
-  prompt: "You are a home automation expert focused on energy efficiency"
+  prompt: |
+    You are a home automation expert focused on:
+    1. Energy efficiency
+    2. Comfort optimization
+    3. Security considerations
+    Provide practical, actionable advice.
 ```
 
 ### clear_history
-Reset conversation history:
 ```yaml
 service: ha_text_ai.clear_history
 ```
 
 ### get_history
-Retrieve conversation history:
 ```yaml
 service: ha_text_ai.get_history
 data:
   limit: 5  # optional
+  filter_model: "gpt-4"  # optional
 ```
 
-## 🔧 Practical Examples
+## 📘 FAQ
 
-### Smart Temperature Management
+**Q: Which AI providers are supported?**
-```yaml
-automation:
-  trigger:
-    platform: time_pattern
-    hours: "/1"
-  action:
-    service: ha_text_ai.ask_question
-    data:
-      question: >
-        Current temperature is {{ states('sensor.living_room_temperature') }}°C.
-        Should I adjust the thermostat for optimal comfort and energy savings?
-```
 
-### Smart Lighting Assistant
+A: Currently OpenAI (GPT models) and Anthropic (Claude models) are supported, with more providers planned.
-```yaml
-automation:
-  trigger:
-    platform: state
-    entity_id: binary_sensor.living_room_motion
-    to: 'on'
-  condition:
-    condition: template
-    value_template: "{{ states('sensor.illuminance') | float < 10 }}"
-  action:
-    service: ha_text_ai.ask_question
-    data:
-      question: >
-        Motion detected in living room with low light levels.
-        What's the best lighting scene to set based on the time of day?
-```
 
-## ❗ Common Issues
+**Q: How can I reduce API costs?**
 
-### API Rate Limits
+A: Use GPT-3.5-Turbo or Claude-3-Sonnet for most queries, implement caching, and optimize token usage.
-- Increase `request_interval` if hitting rate limits
-- Consider upgrading your OpenAI plan
-- Use caching for frequent queries
 
-### High Token Usage
+**Q: Can I use custom models?**
-- Reduce `max_tokens` parameter
-- Clear conversation history regularly
-- Use focused system prompts
 
-### Connection Issues
+A: Yes, you can configure custom endpoints and use any compatible model by specifying it in the configuration.
-- Check internet connectivity
+
-- Verify API key validity
+**Q: How do I switch between different AI providers?**
-- Ensure endpoint accessibility
+
+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.
+
+**Q: Can I use custom models?**
+
+A: Yes, configure custom endpoints and models via configuration options.
 
 ## 🤝 Contributing
 
-Contributions are welcome! Please feel free to submit a Pull Request.
+Contributions welcome! Please read our [Contributing Guide](CONTRIBUTING.md).
 
 1. Fork the repository
-2. Create your feature branch (`git checkout -b feature/AmazingFeature`)
+2. Create feature branch (`git checkout -b feature/Enhancement`)
-3. Commit your changes (`git commit -m 'Add some AmazingFeature'`)
+3. Commit changes (`git commit -m 'Add Enhancement'`)
-4. Push to the branch (`git push origin feature/AmazingFeature`)
+4. Push branch (`git push origin feature/Enhancement`)
-5. Open a Pull Request
+5. Open Pull Request
 
 ## 📝 License
 
-This project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.
+MIT License - see [LICENSE](LICENSE) for details.
 
 ---
 
@@ -162,4 +193,6 @@ This project is licensed under the MIT License - see the [LICENSE](LICENSE) file
 
 Made with ❤️ 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)
+
 </div>

custom_components/ha_text_ai/__init__.py

@@ -1,209 +1,375 @@
-"""The HA text AI integration."""
+"""The HA Text AI integration."""
 import logging
-from typing import Any
+from typing import Any, Dict, Optional
-
+import asyncio
 import voluptuous as vol
+import json
+from datetime import datetime
 
 from homeassistant.config_entries import ConfigEntry
 from homeassistant.const import CONF_API_KEY
-from homeassistant.core import HomeAssistant, ServiceCall
+from homeassistant.core import HomeAssistant, ServiceCall, callback
-import homeassistant.helpers.config_validation as cv
+from homeassistant.exceptions import ConfigEntryNotReady, HomeAssistantError
-from homeassistant.exceptions import HomeAssistantError, ConfigEntryNotReady
+from homeassistant.helpers import aiohttp_client
+from homeassistant.helpers import config_validation as cv
+from async_timeout import timeout
 
+from .coordinator import HATextAICoordinator
 from .const import (
     DOMAIN,
     PLATFORMS,
-    SERVICE_ASK_QUESTION,
-    SERVICE_CLEAR_HISTORY,
-    SERVICE_GET_HISTORY,
-    SERVICE_SET_SYSTEM_PROMPT,
     CONF_MODEL,
     CONF_TEMPERATURE,
     CONF_MAX_TOKENS,
     CONF_API_ENDPOINT,
     CONF_REQUEST_INTERVAL,
+    DEFAULT_MODEL,
+    DEFAULT_TEMPERATURE,
+    DEFAULT_MAX_TOKENS,
+    DEFAULT_API_ENDPOINT,
+    DEFAULT_REQUEST_INTERVAL,
+    API_VERSION,
+    API_MODELS_PATH,
+    API_CHAT_PATH,
+    API_TIMEOUT,
+    API_RETRY_COUNT,
+    API_BACKOFF_FACTOR,
+    LOGGER_NAME,
+    STATE_ERROR,
+    STATE_READY,
+    STATE_PROCESSING,
+    STATE_RATE_LIMITED,
+    STATE_MAINTENANCE,
+    STATE_DISCONNECTED,
+    STATE_RETRYING,
+    STATE_QUEUED,
+    STATE_UPDATING,
+    SUPPORTED_MODELS,
+    EVENT_RESPONSE_RECEIVED,
+    EVENT_ERROR_OCCURRED,
+    EVENT_STATE_CHANGED,
 )
 
-_LOGGER = logging.getLogger(__name__)
+_LOGGER = logging.getLogger(LOGGER_NAME)
 
-def get_coordinator():
+CONFIG_SCHEMA = cv.config_entry_only_config_schema(DOMAIN)
-    """Get coordinator class with lazy import to avoid circular deps."""
-    from .coordinator import HATextAICoordinator
-    return HATextAICoordinator
 
-CONFIG_SCHEMA = vol.Schema(
+# Service validation schemas
-    {
+SERVICE_SCHEMA_ASK_QUESTION = vol.Schema({
-        DOMAIN: vol.Schema(
+    vol.Required("question"): cv.string,
-            {
+    vol.Optional("system_prompt"): cv.string,
-                vol.Required(CONF_API_KEY): cv.string,
+    vol.Optional("model"): vol.In(SUPPORTED_MODELS),
-                vol.Optional(CONF_MODEL, default="gpt-3.5-turbo"): cv.string,
+    vol.Optional("temperature"): vol.All(
-                vol.Optional(CONF_TEMPERATURE, default=0.7): vol.Coerce(float),
+        vol.Coerce(float), vol.Range(min=0, max=2)
-                vol.Optional(CONF_MAX_TOKENS, default=1000): vol.Coerce(int),
+    ),
-                vol.Optional(CONF_REQUEST_INTERVAL, default=1.0): vol.Coerce(float),
+    vol.Optional("max_tokens"): vol.All(
-                vol.Optional(CONF_API_ENDPOINT): cv.string,
+        vol.Coerce(int), vol.Range(min=1, max=4096)
-            }
+    ),
-        )
+    vol.Optional("priority"): vol.Boolean,
-    },
+})
-    extra=vol.ALLOW_EXTRA,
+
-)
+SERVICE_SCHEMA_GET_HISTORY = vol.Schema({
+    vol.Optional("limit", default=10): vol.All(
+        vol.Coerce(int), vol.Range(min=1, max=100)
+    ),
+    vol.Optional("filter_model"): vol.In(SUPPORTED_MODELS),
+    vol.Optional("start_date"): cv.datetime,
+    vol.Optional("include_metadata"): vol.Boolean,
+})
+
+SERVICE_SCHEMA_SET_SYSTEM_PROMPT = vol.Schema({
+    vol.Required("prompt"): cv.string,
+})
+
+async def async_check_api(session, endpoint: str, headers: dict, is_anthropic: bool = False) -> bool:
+    """Check API availability for different providers."""
+    try:
+        if is_anthropic:
+            check_url = f"{endpoint}/v1/models"
+        else:
+            check_url = f"{endpoint}/{API_VERSION}/{API_MODELS_PATH}"
+
+        async with timeout(API_TIMEOUT):
+            async with session.get(check_url, headers=headers) as response:
+                if response.status == 200:
+                    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(hass: HomeAssistant, config: dict[str, Any]) -> bool:
-    """Set up the HA text AI component."""
+    """Set up the HA Text AI component."""
-    hass.data.setdefault(DOMAIN, {})
+    hass.data.setdefault(DOMAIN, {
-
+        "coordinators": {},
-    async def async_ask_question(call: ServiceCall) -> None:
+        "metrics": {
-        """Handle the ask_question service call."""
+            "total_requests": 0,
-        if not hass.data[DOMAIN]:
+            "total_tokens": 0,
-            raise HomeAssistantError("No AI Text integration configured")
+            "errors": {},
-
+            "model_usage": {},
-        coordinator = next(iter(hass.data[DOMAIN].values()))
-        question = call.data["question"]
-
-        original_params = {
-            "model": coordinator.model,
-            "temperature": coordinator.temperature,
-            "max_tokens": coordinator.max_tokens
         }
-
+    })
-        try:
-            if "model" in call.data:
-                coordinator.model = call.data["model"]
-            if "temperature" in call.data:
-                coordinator.temperature = call.data["temperature"]
-            if "max_tokens" in call.data:
-                coordinator.max_tokens = call.data["max_tokens"]
-
-            await coordinator.async_ask_question(question)
-        except Exception as ex:
-            _LOGGER.error("Error asking question: %s", str(ex))
-            raise HomeAssistantError(f"Failed to ask question: {str(ex)}") from ex
-        finally:
-            coordinator.model = original_params["model"]
-            coordinator.temperature = original_params["temperature"]
-            coordinator.max_tokens = original_params["max_tokens"]
-
-    async def async_clear_history(call: ServiceCall) -> None:
-        """Handle the clear_history service call."""
-        if not hass.data[DOMAIN]:
-            raise HomeAssistantError("No AI Text integration configured")
-
-        coordinator = next(iter(hass.data[DOMAIN].values()))
-        coordinator._responses.clear()
-        await coordinator.async_refresh()
-
-    async def async_get_history(call: ServiceCall) -> dict[str, list]:
-        """Handle the get_history service call."""
-        if not hass.data[DOMAIN]:
-            raise HomeAssistantError("No AI Text integration configured")
-
-        coordinator = next(iter(hass.data[DOMAIN].values()))
-        if not coordinator._responses:
-            return {"history": []}
-
-        limit = call.data.get("limit", 10)
-        history = list(coordinator._responses.items())
-        limited_history = history[-limit:] if len(history) > limit else history
-
-        return {
-            "history": [
-                {"question": q, "response": r} for q, r in limited_history
-            ]
-        }
-
-    async def async_set_system_prompt(call: ServiceCall) -> None:
-        """Handle the set_system_prompt service call."""
-        if not hass.data[DOMAIN]:
-            raise HomeAssistantError("No AI Text integration configured")
-
-        coordinator = next(iter(hass.data[DOMAIN].values()))
-        coordinator.system_prompt = call.data["prompt"]
-
-    hass.services.async_register(
-        DOMAIN,
-        SERVICE_ASK_QUESTION,
-        async_ask_question,
-        schema=vol.Schema({
-            vol.Required("question"): cv.string,
-            vol.Optional("model"): cv.string,
-            vol.Optional("temperature"): vol.All(
-                vol.Coerce(float), vol.Range(min=0, max=2)
-            ),
-            vol.Optional("max_tokens"): vol.All(
-                vol.Coerce(int), vol.Range(min=1, max=4096)
-            ),
-        })
-    )
-
-    hass.services.async_register(
-        DOMAIN,
-        SERVICE_CLEAR_HISTORY,
-        async_clear_history,
-        schema=vol.Schema({})
-    )
-
-    hass.services.async_register(
-        DOMAIN,
-        SERVICE_GET_HISTORY,
-        async_get_history,
-        schema=vol.Schema({
-            vol.Optional("limit", default=10): vol.All(
-                vol.Coerce(int), vol.Range(min=1)
-            ),
-        })
-    )
-
-    hass.services.async_register(
-        DOMAIN,
-        SERVICE_SET_SYSTEM_PROMPT,
-        async_set_system_prompt,
-        schema=vol.Schema({
-            vol.Required("prompt"): cv.string,
-        })
-    )
-
     return True
 
 async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
-    """Set up HA text AI from a config entry."""
+    """Set up HA Text AI from a config entry."""
-    HATextAICoordinator = get_coordinator()
     try:
+        session = aiohttp_client.async_get_clientsession(hass)
+
+        # Determine API type based on model
+        model = entry.data.get(CONF_MODEL, DEFAULT_MODEL)
+        is_anthropic = any(model.startswith("claude") for model in SUPPORTED_MODELS)
+
+        api_key = entry.data[CONF_API_KEY]
+        endpoint = entry.data.get(CONF_API_ENDPOINT, DEFAULT_API_ENDPOINT).rstrip('/')
+
+        # Configure headers based on API type
+        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}"
+
+        # Check API with retries
+        for attempt in range(API_RETRY_COUNT):
+            if await async_check_api(session, endpoint, headers, is_anthropic):
+                break
+            if attempt < API_RETRY_COUNT - 1:
+                delay = API_BACKOFF_FACTOR * (2 ** attempt)
+                await asyncio.sleep(delay)
+            else:
+                raise ConfigEntryNotReady("Failed to connect to API")
+
+        # Create and initialize coordinator
         coordinator = HATextAICoordinator(
             hass,
-            api_key=entry.data[CONF_API_KEY],
+            api_key=api_key,
-            endpoint=entry.data.get(CONF_API_ENDPOINT),
+            endpoint=endpoint,
-            model=entry.data.get(CONF_MODEL),
+            model=model,
-            temperature=entry.data.get(CONF_TEMPERATURE),
+            temperature=entry.data.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE),
-            max_tokens=entry.data.get(CONF_MAX_TOKENS),
+            max_tokens=entry.data.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS),
-            request_interval=entry.data.get(CONF_REQUEST_INTERVAL),
+            request_interval=entry.data.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL),
+            session=session,
+            is_anthropic=is_anthropic
         )
 
+        # Initialize coordinator
         await coordinator.async_config_entry_first_refresh()
+
+        # Check coordinator status
+        if coordinator.endpoint_status == "auth_error":
+            raise ConfigEntryNotReady("Authentication failed")
+        elif coordinator.endpoint_status == "rate_limited":
+            _LOGGER.warning("API rate limited during setup")
+        elif coordinator.endpoint_status == "maintenance":
+            raise ConfigEntryNotReady("API is in maintenance mode")
+        elif coordinator.endpoint_status == "error":
+            raise ConfigEntryNotReady("API error during setup")
+        elif not coordinator.last_update_success:
+            raise ConfigEntryNotReady("Failed to initialize coordinator")
+
         hass.data[DOMAIN][entry.entry_id] = coordinator
 
-        return await hass.config_entries.async_forward_entry_setups(entry, PLATFORMS)
+        await hass.config_entries.async_forward_entry_setups(entry, PLATFORMS)
+
+        # Register event handlers
+        @callback
+        def handle_state_change(event):
+            """Handle state changes."""
+            if event.data.get("entity_id").startswith(f"{DOMAIN}."):
+                _LOGGER.debug("State changed: %s", event.data)
+
+        hass.bus.async_listen(EVENT_STATE_CHANGED, handle_state_change)
+
+        # Register services
+        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
+
+            request_params = {}
+            for param in ["system_prompt", "model", "temperature", "max_tokens"]:
+                if param in call.data:
+                    request_params[param] = call.data[param]
+
+            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 = min(int(call.data.get("limit", 10)), 100)
+                filter_model = str(call.data.get("filter_model", ""))
+                start_date = call.data.get("start_date")
+                include_metadata = call.data.get("include_metadata", False)
+
+                responses = coordinator._responses
+                metrics = {
+                    "total_requests": coordinator.request_count,
+                    "total_tokens": coordinator.tokens_used,
+                    "api_version": coordinator.api_version,
+                    "endpoint_status": coordinator.endpoint_status,
+                    "error_count": coordinator.error_count
+                }
+
+                filtered_responses = responses.copy()
+
+                if filter_model:
+                    filtered_responses = {
+                        k: v for k, v in filtered_responses.items()
+                        if v.get("model") == filter_model
+                    }
+
+                if start_date:
+                    filtered_responses = {
+                        k: v for k, v in filtered_responses.items()
+                        if v.get("timestamp") >= start_date
+                    }
+
+                if not include_metadata:
+                    filtered_responses = {
+                        k: {
+                            "question": v["question"],
+                            "response": v["response"],
+                            "timestamp": v["timestamp"]
+                        } for k, v in filtered_responses.items()
+                    }
+
+                sorted_responses = dict(
+                    sorted(
+                        filtered_responses.items(),
+                        key=lambda x: x[1]["timestamp"],
+                        reverse=True
+                    )[:limit]
+                )
+
+                return {
+                    "metrics": metrics,
+                    "responses": 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."""
+            try:
+                prompt = str(call.data.get("prompt", "")).strip()
+                if prompt:
+                    coordinator.system_prompt = prompt
+                    _LOGGER.info("System prompt updated successfully")
+                else:
+                    _LOGGER.error("Empty prompt provided")
+            except Exception as err:
+                _LOGGER.error("Error setting system prompt: %s", str(err))
+
+        # Register services with validation
+        hass.services.async_register(
+            DOMAIN,
+            "ask_question",
+            async_ask_question,
+            schema=SERVICE_SCHEMA_ASK_QUESTION
+        )
+
+        hass.services.async_register(
+            DOMAIN,
+            "clear_history",
+            async_clear_history
+        )
+
+        hass.services.async_register(
+            DOMAIN,
+            "get_history",
+            async_get_history,
+            schema=SERVICE_SCHEMA_GET_HISTORY
+        )
+
+        hass.services.async_register(
+            DOMAIN,
+            "set_system_prompt",
+            async_set_system_prompt,
+            schema=SERVICE_SCHEMA_SET_SYSTEM_PROMPT
+        )
+
+        _LOGGER.info(
+            "Successfully set up HA Text AI with model: %s",
+            entry.data.get(CONF_MODEL, DEFAULT_MODEL)
+        )
+
+        return True
+
     except Exception as ex:
-        raise ConfigEntryNotReady(f"Failed to setup entry: {str(ex)}") from ex
+        _LOGGER.exception("Setup error: %s", str(ex))
+        raise ConfigEntryNotReady from ex
 
 async def async_unload_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
     """Unload a config entry."""
-    if entry.entry_id not in hass.data.get(DOMAIN, {}):
+    try:
-        return True
+        coordinator = hass.data[DOMAIN].get(entry.entry_id)
+        if coordinator:
+            # Clear queue and history
+            coordinator._responses.clear()
+            while not coordinator._question_queue.empty():
+                try:
+                    coordinator._question_queue.get_nowait()
+                    coordinator._question_queue.task_done()
+                except Exception:
+                    pass
 
-    unload_ok = await hass.config_entries.async_unload_platforms(entry, PLATFORMS)
+            # Close connection
-    if unload_ok:
+            await coordinator.async_shutdown()
-        hass.data[DOMAIN].pop(entry.entry_id)
 
-        # Remove services only if this was the last instance
+        # Remove services
-        if not hass.data[DOMAIN]:
+        for service in ["ask_question", "clear_history", "get_history", "set_system_prompt"]:
-            services = [
+            hass.services.async_remove(DOMAIN, service)
-                SERVICE_ASK_QUESTION,
-                SERVICE_CLEAR_HISTORY,
-                SERVICE_GET_HISTORY,
-                SERVICE_SET_SYSTEM_PROMPT
-            ]
-            for service in services:
-                if DOMAIN in hass.services.async_services() and \
-                   service in hass.services.async_services()[DOMAIN]:
-                    hass.services.async_remove(DOMAIN, service)
 
-    return unload_ok
+        unload_ok = await hass.config_entries.async_unload_platforms(entry, PLATFORMS)
+        if unload_ok:
+            hass.data[DOMAIN].pop(entry.entry_id)
+
+        return unload_ok
+
+    except Exception as ex:
+        _LOGGER.exception("Error unloading entry: %s", str(ex))
+        return False
+
+async def async_migrate_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
+    """Migrate old entry."""
+    _LOGGER.debug("Migrating from version %s", entry.version)
+
+    if entry.version == 1:
+        new = {**entry.data}
+
+        # Migrate settings
+        if CONF_MODEL in new and new[CONF_MODEL] not in SUPPORTED_MODELS:
+            new[CONF_MODEL] = DEFAULT_MODEL
+
+        entry.version = 2
+        hass.config_entries.async_update_entry(entry, data=new)
+
+    return True

custom_components/ha_text_ai/config_flow.py

@@ -1,12 +1,17 @@
 """Config flow for HA text AI integration."""
-from typing import Any, Dict, Optional
+from typing import Any, Dict, Optional, Tuple
 import voluptuous as vol
+import asyncio
+import aiohttp
+from async_timeout import timeout
+from urllib.parse import urlparse, urljoin
 
 from homeassistant import config_entries
 from homeassistant.const import CONF_API_KEY
 import homeassistant.helpers.config_validation as cv
 from homeassistant.core import callback
-import openai
+from homeassistant.data_entry_flow import FlowResult
+from homeassistant.helpers.aiohttp_client import async_get_clientsession
 
 from .const import (
     DOMAIN,
@@ -20,28 +25,136 @@ from .const import (
     DEFAULT_MAX_TOKENS,
     DEFAULT_API_ENDPOINT,
     DEFAULT_REQUEST_INTERVAL,
+    MIN_TEMPERATURE,
+    MAX_TEMPERATURE,
+    MIN_MAX_TOKENS,
+    MAX_MAX_TOKENS,
+    MIN_REQUEST_INTERVAL,
+    API_VERSION,
+    API_MODELS_PATH,
+    ERROR_INVALID_API_KEY,
+    ERROR_CANNOT_CONNECT,
+    ERROR_UNKNOWN,
+    ERROR_INVALID_MODEL,
+    ERROR_RATE_LIMIT,
+    ERROR_API_ERROR,
+    ERROR_TIMEOUT,
 )
 
 import logging
 _LOGGER = logging.getLogger(__name__)
 
-STEP_USER_DATA_SCHEMA = vol.Schema({
+STEP_USER_DATA_SCHEMA = vol.Schema(
-    vol.Required(CONF_API_KEY): str,
+    {
-    vol.Optional(CONF_MODEL, default=DEFAULT_MODEL): str,
+        vol.Required(CONF_API_KEY): cv.string,
-    vol.Optional(
+        vol.Optional(CONF_MODEL, default=DEFAULT_MODEL): cv.string,
-        CONF_TEMPERATURE,
+        vol.Optional(
-        default=DEFAULT_TEMPERATURE
+            CONF_TEMPERATURE,
-    ): vol.All(vol.Coerce(float), vol.Range(min=0, max=2)),
+            default=DEFAULT_TEMPERATURE
-    vol.Optional(
+        ): vol.All(
-        CONF_MAX_TOKENS,
+            vol.Coerce(float),
-        default=DEFAULT_MAX_TOKENS
+            vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
-    ): vol.All(vol.Coerce(int), vol.Range(min=1, max=4096)),
+        ),
-    vol.Optional(CONF_API_ENDPOINT, default=DEFAULT_API_ENDPOINT): str,
+        vol.Optional(
-    vol.Optional(
+            CONF_MAX_TOKENS,
-        CONF_REQUEST_INTERVAL,
+            default=DEFAULT_MAX_TOKENS
-        default=DEFAULT_REQUEST_INTERVAL
+        ): vol.All(
-    ): vol.All(vol.Coerce(float), vol.Range(min=0.1)),
+            vol.Coerce(int),
-})
+            vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
+        ),
+        vol.Optional(
+            CONF_API_ENDPOINT,
+            default=DEFAULT_API_ENDPOINT
+        ): cv.string,
+        vol.Optional(
+            CONF_REQUEST_INTERVAL,
+            default=DEFAULT_REQUEST_INTERVAL
+        ): vol.All(
+            vol.Coerce(float),
+            vol.Range(min=MIN_REQUEST_INTERVAL)
+        ),
+    }
+)
+
+async def validate_api_connection(
+    hass,
+    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."""
+    session = async_get_clientsession(hass)
+    headers = {
+        "Authorization": f"Bearer {api_key}",
+        "Content-Type": "application/json; charset=utf-8",
+        "Accept": "application/json; charset=utf-8",
+        "Accept-Charset": "utf-8"
+    }
+
+    base_url = endpoint.rstrip('/')
+    if not base_url.endswith(f"/{API_VERSION}"):
+        base_url = f"{base_url}/{API_VERSION}"
+
+    models_url = f"{base_url}/{API_MODELS_PATH}"
+    _LOGGER.debug("Attempting to connect to: %s", models_url)
+
+    for attempt in range(retry_count):
+        try:
+            async with timeout(10):
+                async with session.get(models_url, headers=headers) as response:
+                    if response.status == 200:
+                        data = await response.json()
+                        model_ids = [m["id"] for m in data.get("data", [])]
+
+                        _LOGGER.debug("Available models: %s", ", ".join(model_ids))
+
+                        if model not in model_ids:
+                            _LOGGER.warning(
+                                "Model %s not found in available models: %s",
+                                model,
+                                ", ".join(model_ids)
+                            )
+                            return False, ERROR_INVALID_MODEL, model_ids
+                        return True, "", model_ids
+
+                    elif response.status == 401:
+                        _LOGGER.error("Authentication failed")
+                        return False, ERROR_INVALID_API_KEY, []
+
+                    elif response.status == 429:
+                        _LOGGER.error("Rate limit exceeded")
+                        return False, ERROR_RATE_LIMIT, []
+
+                    else:
+                        response_text = await response.text()
+                        _LOGGER.error(
+                            "API error: %s - %s",
+                            response.status,
+                            response_text
+                        )
+                        return False, ERROR_API_ERROR, []
+
+        except asyncio.TimeoutError:
+            _LOGGER.warning(
+                "Timeout during API validation (attempt %d/%d)",
+                attempt + 1,
+                retry_count
+            )
+            if attempt == retry_count - 1:
+                return False, ERROR_TIMEOUT, []
+            await asyncio.sleep(retry_delay)
+
+        except aiohttp.ClientError as err:
+            _LOGGER.error("Connection error: %s", str(err))
+            return False, ERROR_CANNOT_CONNECT, []
+
+        except Exception as err:
+            _LOGGER.exception("Unexpected error during validation: %s", str(err))
+            return False, ERROR_UNKNOWN, []
+
+    return False, ERROR_UNKNOWN, []
 
 class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
     """Handle a config flow for HA text AI."""
@@ -51,47 +164,60 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
     async def async_step_user(
         self,
         user_input: Optional[Dict[str, Any]] = None
-    ) -> Dict[str, Any]:
+    ) -> FlowResult:
         """Handle the initial step."""
         errors: Dict[str, str] = {}
 
         if user_input is not None:
             try:
-                # Create OpenAI client
+                endpoint = user_input.get(CONF_API_ENDPOINT, DEFAULT_API_ENDPOINT)
-                client = openai.OpenAI(
+                try:
-                    api_key=user_input[CONF_API_KEY],
+                    result = urlparse(endpoint)
-                    base_url=user_input.get(CONF_API_ENDPOINT, DEFAULT_API_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
+                        )
+                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
+                    )
+
+                validated_input = STEP_USER_DATA_SCHEMA(user_input)
+
+                is_valid, error_code, available_models = await validate_api_connection(
+                    self.hass,
+                    validated_input[CONF_API_KEY],
+                    endpoint,
+                    validated_input[CONF_MODEL]
                 )
 
-                # Verify API connection and model availability
+                if is_valid:
-                models = await self.hass.async_add_executor_job(client.models.list)
+                    await self.async_set_unique_id(validated_input[CONF_API_KEY])
-                model_ids = [model.id for model in models.data]
-
-                if user_input[CONF_MODEL] not in model_ids:
-                    _LOGGER.warning(
-                        "Selected model %s not found in available models: %s",
-                        user_input[CONF_MODEL],
-                        ", ".join(model_ids)
-                    )
-                    errors["base"] = "invalid_model"
-                else:
-                    await self.async_set_unique_id(user_input[CONF_API_KEY])
                     self._abort_if_unique_id_configured()
 
                     return self.async_create_entry(
-                        title="HA text AI",
+                        title="HA Text AI",
-                        data=user_input
+                        data=validated_input
                     )
 
-            except openai.AuthenticationError as err:
+                errors["base"] = error_code
-                _LOGGER.error("Authentication failed: %s", str(err))
+                if error_code == ERROR_INVALID_MODEL:
-                errors["base"] = "invalid_auth"
+                    _LOGGER.warning(
-            except openai.APIError as err:
+                        "Selected model %s not found in available models: %s",
-                _LOGGER.error("API connection failed: %s", str(err))
+                        validated_input[CONF_MODEL],
-                errors["base"] = "cannot_connect"
+                        ", ".join(available_models)
-            except Exception as err:  # pylint: disable=broad-except
+                    )
-                _LOGGER.exception("Unexpected error: %s", str(err))
+
-                errors["base"] = "unknown"
+            except vol.Invalid as err:
+                _LOGGER.error("Validation error: %s", str(err))
+                errors["base"] = "invalid_input"
 
         return self.async_show_form(
             step_id="user",
@@ -121,7 +247,7 @@ class OptionsFlowHandler(config_entries.OptionsFlow):
     async def async_step_init(
         self,
         user_input: Optional[Dict[str, Any]] = None
-    ) -> Dict[str, Any]:
+    ) -> FlowResult:
         """Handle options flow."""
         if user_input is not None:
             return self.async_create_entry(title="", data=user_input)
@@ -132,22 +258,28 @@ class OptionsFlowHandler(config_entries.OptionsFlow):
                 default=self.config_entry.options.get(
                     CONF_TEMPERATURE, DEFAULT_TEMPERATURE
                 ),
-                description={"suggested_value": DEFAULT_TEMPERATURE},
+            ): vol.All(
-            ): vol.All(vol.Coerce(float), vol.Range(min=0, max=2)),
+                vol.Coerce(float),
+                vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
+            ),
             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.All(vol.Coerce(int), vol.Range(min=1, max=4096)),
+                vol.Coerce(int),
+                vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
+            ),
             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.All(vol.Coerce(float), vol.Range(min=0.1)),
+                vol.Coerce(float),
+                vol.Range(min=MIN_REQUEST_INTERVAL)
+            ),
         })
 
         return self.async_show_form(

custom_components/ha_text_ai/const.py

@@ -2,7 +2,7 @@
 from typing import Final
 from homeassistant.const import Platform
 
-# Domain
+# Domain and platforms
 DOMAIN: Final = "ha_text_ai"
 PLATFORMS: Final = [Platform.SENSOR]
 
@@ -13,12 +13,27 @@ CONF_MAX_TOKENS: Final = "max_tokens"
 CONF_API_ENDPOINT: Final = "api_endpoint"
 CONF_REQUEST_INTERVAL: Final = "request_interval"
 
+# Model constants
+SUPPORTED_MODELS: Final = [
+    "gpt-3.5-turbo",
+    "gpt-3.5-turbo-16k",
+    "gpt-4",
+    "gpt-4-32k",
+    "gpt-4-1106-preview",
+    "claude-3-sonnet",
+    "claude-3-opus"
+]
+
 # Default values
 DEFAULT_MODEL: Final = "gpt-3.5-turbo"
-DEFAULT_TEMPERATURE: Final = 0.7
+DEFAULT_TEMPERATURE: Final = 0.1
 DEFAULT_MAX_TOKENS: Final = 1000
-DEFAULT_API_ENDPOINT: Final = "https://api.openai.com/v1"
+DEFAULT_API_ENDPOINT: Final = "https://api.openai.com"
 DEFAULT_REQUEST_INTERVAL: Final = 1.0
+DEFAULT_TIMEOUT: Final = 30
+DEFAULT_QUEUE_SIZE: Final = 100
+DEFAULT_HISTORY_LIMIT: Final = 50
+DEFAULT_RETRY_COUNT: Final = 3
 
 # Parameter constraints
 MIN_TEMPERATURE: Final = 0.0
@@ -26,6 +41,25 @@ 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_PROMPT_LENGTH: Final = 1000
+MAX_HISTORY_LIMIT: Final = 100
+
+# API constants
+API_VERSION: Final = "v1"
+API_MODELS_PATH: Final = "models"
+API_CHAT_PATH: Final = "chat/completions"
+API_TIMEOUT: Final = 30
+API_RETRY_COUNT: Final = 3
+API_BACKOFF_FACTOR: Final = 1.5
+API_MAX_RETRIES: Final = 3
+
+# History constants
+HISTORY_FILTER_MODEL: Final = "filter_model"
+HISTORY_FILTER_DATE: Final = "start_date"
+HISTORY_SORT_ORDER: Final = "sort_order"
+HISTORY_INCLUDE_METADATA: Final = "include_metadata"
 
 # Service names
 SERVICE_ASK_QUESTION: Final = "ask_question"
@@ -49,6 +83,17 @@ 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_LAST_ERROR: Final = "last_error"
+ATTR_API_VERSION: Final = "api_version"
+ATTR_ENDPOINT_STATUS: Final = "endpoint_status"
+ATTR_REQUEST_COUNT: Final = "request_count"
+ATTR_TOKENS_USED: Final = "tokens_used"
+ATTR_RETRY_COUNT: Final = "retry_count"
+ATTR_QUEUE_POSITION: Final = "queue_position"
+ATTR_ESTIMATED_WAIT: Final = "estimated_wait"
 
 # Error messages
 ERROR_INVALID_API_KEY: Final = "invalid_api_key"
@@ -58,6 +103,11 @@ ERROR_INVALID_MODEL: Final = "invalid_model"
 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"
+ERROR_INVALID_PARAMETERS: Final = "invalid_parameters"
+ERROR_SERVICE_UNAVAILABLE: Final = "service_unavailable"
 
 # Configuration descriptions
 CONF_MODEL_DESCRIPTION: Final = "AI model to use for responses"
@@ -76,17 +126,59 @@ 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"
+ATTR_API_VERSION_DESCRIPTION: Final = "Current API version"
+ATTR_ENDPOINT_STATUS_DESCRIPTION: Final = "Current endpoint status"
+ATTR_REQUEST_COUNT_DESCRIPTION: Final = "Total number of API requests"
+ATTR_TOKENS_USED_DESCRIPTION: Final = "Total tokens used"
 
 # 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"
+ENTITY_ICON_OFFLINE: Final = "mdi:robot-off"
+ENTITY_ICON_QUEUE: Final = "mdi:robot-confused"
 
 # 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"
+STATE_MAINTENANCE: Final = "maintenance"
+STATE_RETRYING: Final = "retrying"
+STATE_QUEUED: Final = "queued"
+STATE_UPDATING: Final = "updating"
+
+# 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
+
+# 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"
+
+# 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"

custom_components/ha_text_ai/coordinator.py

@@ -1,50 +1,25 @@
-"""The HA Text AI integration."""
-from homeassistant.config_entries import ConfigEntry
-from homeassistant.core import HomeAssistant
-from homeassistant.exceptions import ConfigEntryNotReady
-from .const import DOMAIN, PLATFORMS
-
-async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
-    """Set up HA Text AI from a config entry."""
-    try:
-        coordinator = HATextAICoordinator(
-            hass,
-            api_key=entry.data["api_key"],
-            endpoint=entry.data.get("api_endpoint", "https://api.openai.com/v1"),
-            model=entry.data.get("model", "gpt-3.5-turbo"),
-            temperature=entry.data.get("temperature", 0.7),
-            max_tokens=entry.data.get("max_tokens", 1000),
-            request_interval=entry.data.get("request_interval", 1.0),
-        )
-
-        await coordinator.async_config_entry_first_refresh()
-
-        hass.data.setdefault(DOMAIN, {})
-        hass.data[DOMAIN][entry.entry_id] = coordinator
-
-        return await hass.config_entries.async_forward_entry_setups(entry, PLATFORMS)
-    except Exception as ex:
-        raise ConfigEntryNotReady(f"Failed to setup entry: {str(ex)}") from ex
-
-async def async_unload_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
-    """Unload a config entry."""
-    unload_ok = await hass.config_entries.async_unload_platforms(entry, PLATFORMS)
-    if unload_ok:
-        hass.data[DOMAIN].pop(entry.entry_id)
-    return unload_ok
-
 """Data coordinator for HA text AI."""
 import asyncio
 import logging
 from datetime import timedelta
-from typing import Any, Dict, Optional
+from typing import Any, Dict, Optional, List
+import time
 
-import openai
+from openai import AsyncOpenAI, APIError, AuthenticationError, RateLimitError
+from anthropic import AsyncAnthropic
 from homeassistant.core import HomeAssistant
 from homeassistant.helpers.update_coordinator import DataUpdateCoordinator
-from homeassistant.exceptions import ConfigEntryAuthFailed
+from homeassistant.util import dt as dt_util
+import async_timeout
 
-from .const import DOMAIN
+from .const import (
+    DOMAIN,
+    DEFAULT_TIMEOUT,
+    MAX_QUEUE_SIZE,
+    MAX_RETRIES,
+    RETRY_DELAY,
+    SUPPORTED_MODELS,
+)
 
 _LOGGER = logging.getLogger(__name__)
 
@@ -60,8 +35,22 @@ class HATextAICoordinator(DataUpdateCoordinator):
         temperature: float,
         max_tokens: int,
         request_interval: float,
+        session: Optional[Any] = None,
+        is_anthropic: bool = False,
     ) -> None:
-        """Initialize."""
+        """Initialize coordinator.
+
+        Args:
+            hass: HomeAssistant instance
+            api_key: API key for the service
+            endpoint: API endpoint URL
+            model: Model name to use
+            temperature: Temperature parameter for generation
+            max_tokens: Maximum tokens to generate
+            request_interval: Interval between requests
+            session: Optional session object
+            is_anthropic: Whether to use Anthropic API
+        """
         super().__init__(
             hass,
             _LOGGER,
@@ -69,6 +58,46 @@ class HATextAICoordinator(DataUpdateCoordinator):
             update_interval=timedelta(seconds=request_interval),
         )
 
+        self._validate_params(api_key, temperature, max_tokens)
+
+        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.PriorityQueue(maxsize=MAX_QUEUE_SIZE)
+        self._responses: Dict[str, Any] = {}
+        self.system_prompt: Optional[str] = None
+        self._is_ready = False
+        self._is_processing = False
+        self._is_rate_limited = False
+        self._is_maintenance = False
+        self._error_count = 0
+        self._MAX_ERRORS = 3
+        self._request_count = 0
+        self._tokens_used = 0
+        self._api_version = "v1"
+        self._endpoint_status = "disconnected"
+        self._performance_metrics: Dict[str, Any] = {
+            "avg_response_time": 0,
+            "total_errors": 0,
+            "success_rate": 100,
+            "requests_per_minute": 0,
+        }
+        self._last_request_time = 0
+        self._is_anthropic = is_anthropic
+
+        if is_anthropic:
+            self.client = AsyncAnthropic(api_key=self.api_key)
+        else:
+            self.client = AsyncOpenAI(
+                api_key=self.api_key,
+                base_url=self.endpoint,
+                http_client=session,
+            )
+
+    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:
@@ -76,58 +105,514 @@ class HATextAICoordinator(DataUpdateCoordinator):
         if not isinstance(max_tokens, int) or max_tokens < 1:
             raise ValueError("Max tokens must be a positive integer")
 
-        self.api_key = api_key
-        self.endpoint = endpoint or "https://api.openai.com/v1"
-        self.model = model or "gpt-3.5-turbo"
-        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.client = openai.OpenAI(
-            api_key=self.api_key,
-            base_url=self.endpoint
-        )
-
     async def _async_update_data(self) -> Dict[str, Any]:
-        """Update data via OpenAI API."""
+        """Update data via API."""
         if self._question_queue.empty():
             return self._responses
 
         try:
-            question = await self._question_queue.get()
+            async with async_timeout.timeout(DEFAULT_TIMEOUT):
-            response_content = await self.hass.async_add_executor_job(
+                self._is_processing = True
-                self._make_api_call, question
+                priority, question_data = await self._question_queue.get()
+                question = question_data["question"]
+                params = question_data["params"]
+
+                try:
+                    response_data = 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._update_metrics(response_data)
+                    self._responses[question] = {
+                        "question": question,
+                        "response": response_data["response"],
+                        "error": None,
+                        "timestamp": dt_util.utcnow(),
+                        "model": response_data["model"],
+                        "temperature": params.get("temperature", self.temperature),
+                        "max_tokens": params.get("max_tokens", self.max_tokens),
+                        "response_time": response_data.get("response_time"),
+                        "tokens": response_data.get("tokens", 0),
+                        "priority": priority
+                    }
+                    self._error_count = 0
+                    self._is_ready = True
+                    self._endpoint_status = "connected"
+                    self._request_count += 1
+                    self._tokens_used += response_data.get("tokens", 0)
+                    self._last_request_time = time.time()
+
+                    # Fire event for successful response
+                    self.hass.bus.async_fire(f"{DOMAIN}_response_received", {
+                        "question": question,
+                        "model": response_data["model"],
+                        "tokens": response_data.get("tokens", 0)
+                    })
+
+                    _LOGGER.debug("Response received for question: %s", question)
+
+                except Exception as err:
+                    await self._handle_api_error(question, err)
+                finally:
+                    self._is_processing = False
+                    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
+
+    async def _handle_api_error(self, question: str, error: Exception) -> None:
+        """Handle API errors with retry logic."""
+        self._error_count += 1
+        self._performance_metrics["total_errors"] += 1
+        error_msg = str(error)
+
+        if isinstance(error, AuthenticationError):
+            error_msg = "Authentication failed - invalid API key"
+            self._is_ready = False
+            self._endpoint_status = "auth_error"
+        elif isinstance(error, RateLimitError):
+            error_msg = "Rate limit exceeded"
+            self._is_rate_limited = True
+            self._endpoint_status = "rate_limited"
+            # Implement exponential backoff
+            await asyncio.sleep(RETRY_DELAY * (2 ** (self._error_count - 1)))
+        elif isinstance(error, APIError):
+            if "maintenance" in str(error).lower():
+                self._is_maintenance = True
+                self._endpoint_status = "maintenance"
+            error_msg = f"API error: {error}"
+        else:
+            self._endpoint_status = "error"
+
+        self._responses[question] = {
+            "question": question,
+            "response": None,
+            "error": error_msg,
+            "timestamp": dt_util.utcnow(),
+            "model": self.model,
+            "temperature": self.temperature,
+            "max_tokens": self.max_tokens
+        }
+
+        # Fire error event
+        self.hass.bus.async_fire(f"{DOMAIN}_error_occurred", {
+            "error_type": type(error).__name__,
+            "error_message": error_msg,
+            "question": question
+        })
+
+        _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
             )
-            self._responses[question] = {
-                "question": question,
-                "response": response_content
-            }
-            _LOGGER.debug("Response from API: %s", response_content)
-            return self._responses
 
-        except openai.AuthenticationError as err:
+    def _update_metrics(self, response_data: Dict[str, Any]) -> None:
-            raise ConfigEntryAuthFailed from err
+        """Update performance metrics."""
-        except Exception as err:
+        response_time = response_data.get("response_time", 0)
-            _LOGGER.error("Error communicating with API: %s", err)
+        current_avg = self._performance_metrics["avg_response_time"]
-            return self._responses
+        self._performance_metrics["avg_response_time"] = (
+            (current_avg * self._request_count + response_time) /
+            (self._request_count + 1)
+        )
 
-    def _make_api_call(self, question: str) -> str:
+        total_requests = self._request_count + 1
-        """Make API call to OpenAI."""
+        self._performance_metrics["success_rate"] = (
+            (total_requests - self._performance_metrics["total_errors"]) /
+            total_requests * 100
+        )
+
+        # Calculate requests per minute
+        if self._last_request_time:
+            time_diff = time.time() - self._last_request_time
+            if time_diff > 0:
+                self._performance_metrics["requests_per_minute"] = 60 / time_diff
+
+    async def _make_api_call(
+        self,
+        question: str,
+        model: Optional[str] = None,
+        temperature: Optional[float] = None,
+        max_tokens: Optional[int] = None,
+        system_prompt: Optional[str] = None
+    ) -> Dict[str, Any]:
+        """Make API call to the selected service."""
         try:
-            messages = []
+            start_time = dt_util.utcnow()
-            if self.system_prompt:
+
-                messages.append({"role": "system", "content": self.system_prompt})
+            if self._is_anthropic:
-            messages.append({"role": "user", "content": question})
+                response = await self._make_anthropic_call(
+                    question, model, temperature, max_tokens, system_prompt
+                )
+            else:
+                response = await self._make_openai_call(
+                    question, model, temperature, max_tokens, system_prompt
+                )
+
+            response_time = (dt_util.utcnow() - start_time).total_seconds()
+
+            return {
+                **response,
+                "response_time": response_time
+            }
 
-            completion = self.client.chat.completions.create(
-                model=self.model,
-                messages=messages,
-                temperature=self.temperature,
-                max_tokens=self.max_tokens,
-            )
-            return completion.choices[0].message.content
         except Exception as err:
             _LOGGER.error("Error in API call: %s", err)
             raise
+
+    async def _make_anthropic_call(
+        self,
+        question: str,
+        model: Optional[str],
+        temperature: Optional[float],
+        max_tokens: Optional[int],
+        system_prompt: Optional[str]
+    ) -> Dict[str, Any]:
+        """Make API call to Anthropic."""
+        messages = []
+        if system_prompt:
+            messages.append({"role": "system", "content": system_prompt})
+        messages.append({"role": "user", "content": question})
+
+        completion = await self.client.messages.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 {
+            "response": completion.content[0].text,
+            "model": completion.model,
+            "tokens": completion.usage.total_tokens if hasattr(completion, 'usage') else 0
+        }
+
+    async def _make_openai_call(
+        self,
+        question: str,
+        model: Optional[str],
+        temperature: Optional[float],
+        max_tokens: Optional[int],
+        system_prompt: Optional[str]
+    ) -> Dict[str, Any]:
+        """Make API call to OpenAI."""
+        messages = []
+        if system_prompt:
+            messages.append({"role": "system", "content": system_prompt})
+        messages.append({"role": "user", "content": question})
+
+        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 {
+            "response": completion.choices[0].message.content,
+            "model": completion.model,
+            "tokens": completion.usage.total_tokens if hasattr(completion, 'usage') else 0
+        }
+
+    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,
+        priority: bool = False
+    ) -> None:
+        """Add question to queue with priority support."""
+        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
+            }
+        }
+
+        # Priority: 0 for high priority, 1 for normal
+        priority_level = 0 if priority else 1
+
+        try:
+            await self._question_queue.put((priority_level, question_data))
+            await self.async_refresh()
+        except asyncio.QueueFull:
+            _LOGGER.error("Question queue is full. Try again later.")
+            raise RuntimeError("Queue is full")
+
+    async def async_shutdown(self) -> None:
+        """Shutdown the coordinator."""
+        try:
+            while not self._question_queue.empty():
+                try:
+                    self._question_queue.get_nowait()
+                    self._question_queue.task_done()
+                except asyncio.QueueEmpty:
+                    break
+
+            if hasattr(self.client, 'close'):
+                await self.client.close()
+
+            self._is_ready = False
+            self._endpoint_status = "disconnected"
+
+            # Final metrics update
+            self._update_final_metrics()
+
+        except Exception as err:
+            _LOGGER.error("Error during shutdown: %s", err)
+
+    def _update_final_metrics(self) -> None:
+        """Update final metrics before shutdown."""
+        if self._request_count > 0:
+            self._performance_metrics["final_success_rate"] = (
+                (self._request_count - self._performance_metrics["total_errors"]) /
+                self._request_count * 100
+            )
+            self._performance_metrics["total_requests"] = self._request_count
+            self._performance_metrics["total_tokens"] = self._tokens_used
+
+    @property
+    def performance_metrics(self) -> Dict[str, Any]:
+        """Return current performance metrics."""
+        return self._performance_metrics
+
+    @property
+    def queue_size(self) -> int:
+        """Return current queue size."""
+        return self._question_queue.qsize()
+
+    @property
+    def is_queue_full(self) -> bool:
+        """Return whether queue is full."""
+        return self._question_queue.full()
+
+    @property
+    def is_ready(self) -> bool:
+        """Return if coordinator is ready."""
+        return self._is_ready and self._error_count < self._MAX_ERRORS
+
+    @property
+    def is_processing(self) -> bool:
+        """Return if coordinator is processing."""
+        return self._is_processing
+
+    @property
+    def is_rate_limited(self) -> bool:
+        """Return if coordinator is rate limited."""
+        return self._is_rate_limited
+
+    @property
+    def is_maintenance(self) -> bool:
+        """Return if API is in maintenance."""
+        return self._is_maintenance
+
+    @property
+    def error_count(self) -> int:
+        """Return current error count."""
+        return self._error_count
+
+    @property
+    def request_count(self) -> int:
+        """Return total request count."""
+        return self._request_count
+
+    @property
+    def tokens_used(self) -> int:
+        """Return total tokens used."""
+        return self._tokens_used
+
+    @property
+    def api_version(self) -> str:
+        """Return API version."""
+        return self._api_version
+
+    @property
+    def endpoint_status(self) -> str:
+        """Return endpoint status."""
+        return self._endpoint_status
+
+    @property
+    def responses(self) -> Dict[str, Any]:
+        """Return all responses."""
+        return self._responses
+
+    @property
+    def last_response(self) -> Optional[Dict[str, Any]]:
+        """Return the last response."""
+        if not self._responses:
+            return None
+        return next(iter(self._responses.values()))
+
+    def reset_error_count(self) -> None:
+        """Reset error counter."""
+        self._error_count = 0
+        self._is_rate_limited = False
+        self._is_maintenance = False
+        if not self._is_ready:
+            self._is_ready = True
+            self._endpoint_status = "connected"
+
+    async def clear_queue(self) -> None:
+        """Clear the question queue."""
+        try:
+            while not self._question_queue.empty():
+                try:
+                    self._question_queue.get_nowait()
+                    self._question_queue.task_done()
+                except asyncio.QueueEmpty:
+                    break
+        except Exception as err:
+            _LOGGER.error("Error clearing queue: %s", err)
+
+    async def clear_history(self) -> None:
+        """Clear response history."""
+        self._responses.clear()
+        await self.async_refresh()
+
+    def get_response(self, question: str) -> Optional[Dict[str, Any]]:
+        """Get specific response by question."""
+        return self._responses.get(question)
+
+    def get_recent_responses(self, limit: int = 10) -> List[Dict[str, Any]]:
+        """Get most recent responses."""
+        return list(sorted(
+            self._responses.values(),
+            key=lambda x: x["timestamp"],
+            reverse=True
+        ))[:limit]
+
+    async def retry_failed_requests(self) -> None:
+        """Retry failed requests."""
+        failed_requests = [
+            (q, r) for q, r in self._responses.items()
+            if r.get("error") is not None
+        ]
+
+        for question, response in failed_requests:
+            await self.async_ask_question(
+                question,
+                system_prompt=response.get("system_prompt"),
+                model=response.get("model"),
+                temperature=response.get("temperature"),
+                max_tokens=response.get("max_tokens"),
+                priority=True
+            )
+
+    def update_system_prompt(self, new_prompt: str) -> None:
+        """Update system prompt."""
+        self.system_prompt = new_prompt
+        _LOGGER.info("System prompt updated")
+
+    async def health_check(self) -> Dict[str, Any]:
+        """Perform health check."""
+        health_status = {
+            "is_ready": self.is_ready,
+            "is_processing": self.is_processing,
+            "is_rate_limited": self.is_rate_limited,
+            "is_maintenance": self.is_maintenance,
+            "error_count": self.error_count,
+            "endpoint_status": self.endpoint_status,
+            "queue_size": self.queue_size,
+            "request_count": self.request_count,
+            "tokens_used": self.tokens_used,
+            "performance_metrics": self.performance_metrics
+        }
+
+        return health_status
+
+    async def _handle_timeout_error(self) -> None:
+        """Handle timeout errors."""
+        self._error_count += 1
+        self._endpoint_status = "timeout"
+        self._performance_metrics["total_errors"] += 1
+
+        if not self._question_queue.empty():
+            await self.clear_queue()
+
+        # Fire timeout event
+        self.hass.bus.async_fire(f"{DOMAIN}_timeout_error", {
+            "error_count": self._error_count,
+            "endpoint_status": self._endpoint_status
+        })
+
+    def export_metrics(self) -> Dict[str, Any]:
+        """Export all metrics and statistics."""
+        return {
+            "performance": self._performance_metrics,
+            "requests": {
+                "total": self._request_count,
+                "successful": self._request_count - self._performance_metrics["total_errors"],
+                "failed": self._performance_metrics["total_errors"]
+            },
+            "tokens": {
+                "total_used": self._tokens_used,
+                "average_per_request": self._tokens_used / self._request_count if self._request_count > 0 else 0
+            },
+            "status": {
+                "is_ready": self.is_ready,
+                "endpoint_status": self._endpoint_status,
+                "error_count": self._error_count
+            },
+            "queue": {
+                "size": self.queue_size,
+                "is_full": self.is_queue_full
+            }
+        }
+
+    async def validate_model(self, model: str) -> bool:
+        """Validate if model is supported."""
+        return model in SUPPORTED_MODELS
+
+    async def estimate_tokens(self, text: str) -> int:
+        """Estimate token count for text."""
+        # Простая оценка: примерно 4 символа на токен
+        return len(text) // 4
+
+    def get_rate_limit_info(self) -> Dict[str, Any]:
+        """Get rate limit information."""
+        return {
+            "is_rate_limited": self._is_rate_limited,
+            "retry_after": RETRY_DELAY * (2 ** (self._error_count - 1)) if self._is_rate_limited else 0
+        }
+
+    async def optimize_queue(self) -> None:
+        """Optimize queue by removing duplicate requests."""
+        if self._question_queue.empty():
+            return
+
+        seen_questions = set()
+        optimized_queue = asyncio.PriorityQueue(maxsize=MAX_QUEUE_SIZE)
+
+        while not self._question_queue.empty():
+            try:
+                priority, question_data = self._question_queue.get_nowait()
+                question = question_data["question"]
+
+                if question not in seen_questions:
+                    seen_questions.add(question)
+                    await optimized_queue.put((priority, question_data))
+
+                self._question_queue.task_done()
+            except asyncio.QueueEmpty:
+                break
+
+        self._question_queue = optimized_queue

custom_components/ha_text_ai/manifest.json

@@ -4,11 +4,39 @@
   "codeowners": ["@smkrv"],
   "config_flow": true,
   "dependencies": [],
-  "documentation": "https://github.com/smkrv/ha-text-ai/wiki",
+  "documentation": "https://github.com/smkrv/ha-text-ai",
+  "homepage": "https://github.com/smkrv/ha-text-ai",
   "iot_class": "cloud_polling",
   "issue_tracker": "https://github.com/smkrv/ha-text-ai/issues",
-  "requirements": ["openai>=1.0.0"],
+  "requirements": [
+    "openai>=1.12.0",
+    "anthropic>=0.8.0",
+    "aiohttp>=3.8.0",
+    "async-timeout>=4.0.0"
+  ],
+  "version": "2.0.0",
+  "homeassistant": "2024.1.0",
+  "quality_scale": "silver",
+  "integration_type": "service",
+  "translations": [
+    "en"
+  ],
+  "zeroconf": [],
   "ssdp": [],
-  "version": "1.0.3",
+  "usb": [],
-  "zeroconf": []
+  "bluetooth": [],
+  "mqtt": [],
+  "loggers": ["custom_components.ha_text_ai"],
+  "after_dependencies": ["http"],
+  "title": "Text AI Assistant",
+  "description": "AI-powered text assistant supporting multiple models including GPT and Claude",
+  "render_readme": true,
+  "tags": [
+    "ai",
+    "automation",
+    "chat",
+    "assistant",
+    "openai",
+    "claude"
+  ]
 }

custom_components/ha_text_ai/sensor.py

@@ -1,7 +1,7 @@
 """Sensor platform for HA text AI."""
 from datetime import datetime
 import logging
-from typing import Any, Callable, Dict, Optional
+from typing import Any, Dict, Optional
 
 from homeassistant.components.sensor import (
     SensorEntity,
@@ -24,6 +24,26 @@ from .const import (
     ATTR_TEMPERATURE,
     ATTR_MAX_TOKENS,
     ATTR_TOTAL_RESPONSES,
+    ATTR_SYSTEM_PROMPT,
+    ATTR_QUEUE_SIZE,
+    ATTR_API_STATUS,
+    ATTR_ERROR_COUNT,
+    ATTR_LAST_ERROR,
+    ATTR_RESPONSE_TIME,
+    ATTR_API_VERSION,
+    ATTR_ENDPOINT_STATUS,
+    ATTR_REQUEST_COUNT,
+    ATTR_TOKENS_USED,
+    ENTITY_ICON,
+    ENTITY_ICON_ERROR,
+    ENTITY_ICON_PROCESSING,
+    STATE_READY,
+    STATE_PROCESSING,
+    STATE_ERROR,
+    STATE_DISCONNECTED,
+    STATE_RATE_LIMITED,
+    STATE_INITIALIZING,
+    STATE_MAINTENANCE,
 )
 from .coordinator import HATextAICoordinator
 
@@ -38,13 +58,13 @@ async def async_setup_entry(
     coordinator = hass.data[DOMAIN][entry.entry_id]
     async_add_entities([HATextAISensor(coordinator, entry)], True)
 
+
 class HATextAISensor(CoordinatorEntity, SensorEntity):
     """HA text AI Sensor."""
 
     _attr_has_entity_name = True
     _attr_state_class = SensorStateClass.MEASUREMENT
     _attr_device_class = SensorDeviceClass.TIMESTAMP
-    _attr_icon = "mdi:robot"
 
     def __init__(
         self,
@@ -57,82 +77,159 @@ class HATextAISensor(CoordinatorEntity, SensorEntity):
         self._attr_unique_id = f"{config_entry.entry_id}"
         self._attr_name = "Last Response"
         self._attr_suggested_display_precision = 0
+        self._error_count = 0
+        self._last_error = None
+        self._state = STATE_INITIALIZING
+        self._attr_device_info = {
+            "identifiers": {(DOMAIN, self._attr_unique_id)},
+            "name": "HA Text AI",
+            "manufacturer": "Community",
+            "model": coordinator.model,
+            "sw_version": coordinator.api_version,
+        }
+
+    @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
 
     @property
     def state(self) -> StateType:
         """Return the state of the sensor."""
-        if not self.coordinator.data or not self.coordinator.last_update_success_time:
+        if not self.coordinator.data or not self.coordinator.last_update_success:
             return None
 
-        # Convert to local time
+        try:
-        if isinstance(self.coordinator.last_update_success_time, datetime):
+            if self.coordinator.data and isinstance(self.coordinator.data, dict):
-            return dt_util.as_local(self.coordinator.last_update_success_time)
+                last_update = self.coordinator.data.get("last_update")
-        return self.coordinator.last_update_success_time
+                if isinstance(last_update, datetime):
+                    return dt_util.as_local(last_update)
+                return last_update
+            return None
+        except Exception as err:
+            _LOGGER.error("Error getting state: %s", err, exc_info=True)
+            return None
 
     @property
-    def extra_state_attributes(self) -> Optional[Dict[str, Any]]:
+    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,
+            ATTR_API_VERSION: self.coordinator.api_version,
+            ATTR_ENDPOINT_STATUS: self.coordinator.endpoint_status,
+            ATTR_REQUEST_COUNT: self.coordinator.request_count,
+            ATTR_TOKENS_USED: self.coordinator.tokens_used,
+        }
+
         if not self.coordinator.data:
-            return {
+            return attributes
-                ATTR_TOTAL_RESPONSES: 0,
-                ATTR_MODEL: self.coordinator.model,
-                ATTR_TEMPERATURE: self.coordinator.temperature,
-                ATTR_MAX_TOKENS: self.coordinator.max_tokens,
-            }
 
         try:
-            history = list(self.coordinator.data.items())
+            history = list(self.coordinator._responses.items())
-            if not history:
+            if history:
-                return {
+                last_question, last_data = history[-1]
-                    ATTR_TOTAL_RESPONSES: 0,
-                    ATTR_MODEL: self.coordinator.model,
-                    ATTR_TEMPERATURE: self.coordinator.temperature,
-                    ATTR_MAX_TOKENS: self.coordinator.max_tokens,
-                }
 
-            last_question, last_data = history[-1]
+                if isinstance(last_data, dict):
+                    last_response = last_data.get("response", "")
+                    last_updated = last_data.get("timestamp") or self.coordinator.data.get("last_update")
+                    response_time = last_data.get("response_time")
 
-            # Handle different response formats
+                    model = last_data.get("model", self.coordinator.model)
-            if isinstance(last_data, dict):
+                    temperature = last_data.get("temperature", self.coordinator.temperature)
-                last_response = last_data.get("response", "")
+                    max_tokens = last_data.get("max_tokens", self.coordinator.max_tokens)
-                last_updated = last_data.get("timestamp", self.coordinator.last_update_success_time)
+                    error = last_data.get("error")
-            else:
-                last_response = str(last_data)
-                last_updated = self.coordinator.last_update_success_time
 
-            # Convert timestamp to local time if needed
+                    if error:
-            if isinstance(last_updated, datetime):
+                        self._last_error = error
-                last_updated = dt_util.as_local(last_updated)
+                        self._state = STATE_ERROR
+                else:
+                    last_response = str(last_data)
+                    last_updated = self.coordinator.data.get("last_update")
+                    response_time = None
+                    model = self.coordinator.model
+                    temperature = self.coordinator.temperature
+                    max_tokens = self.coordinator.max_tokens
+
+                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
 
-            return {
-                ATTR_QUESTION: last_question,
-                ATTR_RESPONSE: last_response,
-                ATTR_LAST_UPDATED: last_updated,
-                ATTR_TOTAL_RESPONSES: len(history),
-                ATTR_MODEL: self.coordinator.model,
-                ATTR_TEMPERATURE: self.coordinator.temperature,
-                ATTR_MAX_TOKENS: self.coordinator.max_tokens,
-            }
         except Exception as err:
             _LOGGER.error("Error getting attributes: %s", err, exc_info=True)
-            return {
+            self._error_count += 1
-                ATTR_TOTAL_RESPONSES: 0,
+            self._last_error = str(err)
-                ATTR_MODEL: self.coordinator.model,
+            self._state = STATE_ERROR
-                ATTR_TEMPERATURE: self.coordinator.temperature,
+            return attributes
-                ATTR_MAX_TOKENS: self.coordinator.max_tokens,
-            }
 
     @property
     def available(self) -> bool:
         """Return if entity is available."""
         return self.coordinator.last_update_success
 
-    @property
-    def should_poll(self) -> bool:
-        """No need to poll. Coordinator notifies entity of updates."""
-        return False
-
     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
+
+    def _handle_coordinator_update(self) -> None:
+        """Handle updated data from the coordinator."""
+        try:
+            if self.coordinator.data:
+                if self.coordinator._is_ready:
+                    if self.coordinator._is_processing:
+                        self._state = STATE_PROCESSING
+                    elif self.coordinator._is_rate_limited:
+                        self._state = STATE_RATE_LIMITED
+                    elif self.coordinator._is_maintenance:
+                        self._state = STATE_MAINTENANCE
+                    else:
+                        self._state = STATE_READY
+                else:
+                    self._state = STATE_DISCONNECTED
+            else:
+                self._state = STATE_DISCONNECTED
+
+            # Обновляем счетчик ошибок только если статус изменился на ошибку
+            if self._state == STATE_ERROR:
+                self._error_count += 1
+
+        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
+
+        self.async_write_ha_state()
+
+    async def async_reset_error_count(self) -> None:
+        """Reset the error counter."""
+        self._error_count = 0
+        self._last_error = None
+        self.async_write_ha_state()

custom_components/ha_text_ai/services.yaml

@@ -3,16 +3,24 @@ 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.
+    Supports various AI models with different capabilities and pricing.
   fields:
     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.
+        The system will maintain conversation context for follow-up questions.
       required: true
       example: |
         What automations would you recommend for a smart kitchen?
-        Consider energy efficiency and convenience.
+        Consider energy efficiency, convenience, and integration with:
+        - Smart lighting
+        - Appliance control
+        - Temperature monitoring
+        - Voice commands
       selector:
         text:
           multiline: true
@@ -22,28 +30,42 @@ ask_question:
       name: Model
       description: >-
         Select an AI model to use (optional, overrides default setting).
-        Different models have different capabilities and token limits.
+        Different models have different capabilities, context limits, and response characteristics:
+        - GPT-3.5 Turbo: Fast, efficient, good for most tasks
+        - GPT-4: More capable, better reasoning, slower
+        - Claude-3: Advanced capabilities, longer context
+        Note: More capable models may have longer response times and higher API costs.
       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 (Balanced)"
+              value: "claude-3-sonnet"
+            - label: "Claude-3 Opus (Most Advanced)"
+              value: "claude-3-opus"
           mode: dropdown
 
     temperature:
       name: Temperature
       description: >-
-        Controls response creativity (0-2):
+        Controls response creativity (0.0-2.0):
-        0.0-0.3: Focused, consistent responses
+        0.0-0.3: Focused, consistent responses (best for technical/factual queries)
-        0.4-0.7: Balanced responses
+        0.4-0.7: Balanced responses (recommended for most uses)
-        0.8-2.0: More creative, varied responses
+        0.8-2.0: More creative, varied responses (best for brainstorming)
+        Note: Higher values may produce less predictable results.
       required: false
       default: 0.7
       selector:
@@ -57,11 +79,12 @@ ask_question:
     max_tokens:
       name: Max Tokens
       description: >-
-        Maximum length of the response. Higher values allow longer responses but use more API tokens.
+        Maximum length of the response (1-4096 tokens).
         Recommended ranges:
-        - Short responses: 256-512
+        - Short (256-512): Quick answers, status updates
-        - Medium responses: 512-1024
+        - Medium (512-1024): Detailed explanations
-        - Long responses: 1024-4096
+        - Long (1024-4096): Complex analysis
+        Note: Token limits vary by model. Actual length may be shorter.
       required: false
       default: 1000
       selector:
@@ -71,24 +94,42 @@ 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.
+        Use this to specify expertise areas, response format, or special instructions.
+      required: false
+      example: "You are a home automation expert focused on energy efficiency and security"
+      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.
+    This action cannot be undone. Consider using 'get_history' first if you need to backup the data.
+    System prompt settings and configuration will be preserved.
   fields: {}
 
 get_history:
   name: Get History
   description: >-
-    Retrieve recent conversation history, including questions, responses, and timestamps.
+    Retrieve recent conversation history, including:
+    - Questions and responses
+    - Timestamps and response times
+    - Models used and token counts
+    - Temperature and other settings
     Results are ordered from newest to oldest.
   fields:
     limit:
       name: Limit
       description: >-
-        Number of most recent conversations to return.
+        Number of most recent conversations to return (1-100).
         Higher values return more history but may take longer to process.
+        Default: 10 conversations
       required: false
       default: 10
       selector:
@@ -98,17 +139,57 @@ get_history:
           step: 1
           mode: box
 
+    filter_model:
+      name: Filter by Model
+      description: >-
+        Only return conversations using a specific AI model.
+        Leave empty to show all models.
+      required: false
+      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: "GPT-4 Turbo"
+              value: "gpt-4-1106-preview"
+            - label: "Claude-3 Sonnet"
+              value: "claude-3-sonnet"
+            - label: "Claude-3 Opus"
+              value: "claude-3-opus"
+          mode: dropdown
+
+    start_date:
+      name: Start Date
+      description: >-
+        Optional start date for filtering history.
+        Format: YYYY-MM-DD
+      required: false
+      selector:
+        datetime:
+          type: date
+
 set_system_prompt:
   name: Set System Prompt
   description: >-
-    Configure the AI's behavior by setting a system prompt.
+    Set default system behavior instructions for all future conversations.
-    This affects how the AI interprets and responds to all future questions.
+    This defines how the AI should behave and respond to questions.
+    The prompt will be used for all models unless overridden per question.
   fields:
     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.
+        Be specific about:
+        - Desired expertise and knowledge areas
+        - Response tone and style
+        - Output format preferences
+        - Special handling instructions
+        Maximum length: 1000 characters
       required: true
       example: |
         You are a home automation expert assistant. Focus on:
@@ -117,7 +198,8 @@ set_system_prompt:
         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
-          type: text

custom_components/ha_text_ai/translations/en.json

@@ -1,142 +1,147 @@
 {
-  "config": {
+    "config": {
-    "step": {
+        "step": {
-      "user": {
+            "user": {
-        "title": "Set up HA text AI",
+                "title": "Set up HA Text AI",
-        "description": "Configure your OpenAI integration for smart home interactions. You'll need an OpenAI API key to proceed.",
+                "description": "Configure your AI integration for various providers (OpenAI, Anthropic, etc.). Different models have different capabilities and pricing.",
-        "data": {
+                "data": {
-          "api_key": {
+                    "api_key": "API key for authentication (required)",
-            "name": "OpenAI API Key",
+                    "model": "AI model to use (e.g., gpt-3.5-turbo, gpt-4, claude-3-sonnet, claude-3-opus)",
-            "description": "Your OpenAI API key from platform.openai.com"
+                    "temperature": "Response creativity (0-2, lower = more focused and consistent)",
-          },
+                    "max_tokens": "Maximum response length (1-4096 tokens)",
-          "model": {
+                    "api_endpoint": "Custom API endpoint URL (default varies by provider)",
-            "name": "AI Model",
+                    "request_interval": "Minimum time between requests in seconds (min: 0.1)",
-            "description": "Select the AI model to use. GPT-3.5-Turbo is recommended for most uses."
+                    "system_prompt": "Default instructions for AI behavior and expertise"
-          },
+                }
-          "temperature": {
+            }
-            "name": "Temperature",
+        },
-            "description": "Controls response creativity (0-2). Lower values for focused responses, higher for creative ones."
+        "error": {
-          },
+            "invalid_auth": "Authentication failed - check your API key",
-          "max_tokens": {
+            "invalid_api_key": "Invalid API key - please verify your credentials",
-            "name": "Max Tokens",
+            "cannot_connect": "Connection failed - check endpoint and network status",
-            "description": "Maximum length of responses. Higher values allow longer responses but use more API tokens."
+            "invalid_model": "Model unavailable or not supported by the API",
-          },
+            "rate_limit": "Rate limit exceeded - please reduce request frequency",
-          "api_endpoint": {
+            "context_length": "Input exceeds maximum context length for model",
-            "name": "API Endpoint",
+            "api_error": "API service error - check provider status",
-            "description": "OpenAI API endpoint URL. Leave default unless using a custom endpoint."
+            "timeout": "Request timeout - server not responding",
-          },
+            "queue_full": "Request queue full - try again later",
-          "request_interval": {
+            "invalid_prompt": "Invalid system prompt format or length",
-            "name": "Request Interval",
+            "invalid_url_format": "Invalid API endpoint URL format",
-            "description": "Minimum time between API requests in seconds. Increase if hitting rate limits."
+            "invalid_input": "Invalid configuration parameters",
-          }
+            "unknown": "Unexpected error - check logs for details"
         }
-      }
     },
-    "error": {
+    "options": {
-      "invalid_auth": "Invalid API key. Please check your OpenAI API key and try again.",
+        "step": {
-      "cannot_connect": "Failed to connect to API. Please check your internet connection and API endpoint.",
+            "init": {
-      "unknown": "Unexpected error occurred. Please check the logs for more details.",
+                "title": "HA Text AI Settings",
-      "already_exists": "This API key is already configured in another integration.",
+                "description": "Adjust your AI integration parameters and behavior",
-      "invalid_model": "Selected model is not available. Please choose a different model.",
+                "data": {
-      "rate_limit": "API rate limit exceeded. Please try again later or increase the request interval.",
+                    "model": "Select AI model for responses (capabilities vary)",
-      "context_length": "Input too long for selected model. Try reducing max tokens or using a model with larger context.",
+                    "temperature": "Response creativity (0-2, affects variation)",
-      "api_error": "OpenAI API error. Please check the logs for details."
+                    "max_tokens": "Maximum response length in tokens",
-    },
+                    "request_interval": "Minimum seconds between requests (rate limiting)",
-    "abort": {
+                    "system_prompt": "Default AI behavior and expertise instructions",
-      "already_configured": "This OpenAI integration is already configured",
+                    "timeout": "Request timeout in seconds (default: 30)",
-      "auth_failed": "Authentication failed. Please verify your API key.",
+                    "retry_count": "Number of retry attempts for failed requests",
-      "invalid_endpoint": "Invalid API endpoint URL provided"
+                    "queue_size": "Maximum pending requests in queue"
-    }
+                }
-  },
+            }
-  "options": {
-    "step": {
-      "init": {
-        "title": "HA text AI Options",
-        "description": "Adjust your OpenAI integration settings. Changes will apply to future requests.",
-        "data": {
-          "temperature": {
-            "name": "Temperature",
-            "description": "Controls response creativity (0-2). Lower values for focused responses, higher for creative ones."
-          },
-          "max_tokens": {
-            "name": "Max Tokens",
-            "description": "Maximum length of responses. Higher values allow longer responses but use more API tokens."
-          },
-          "request_interval": {
-            "name": "Request Interval",
-            "description": "Minimum time between API requests in seconds. Increase if hitting rate limits."
-          }
         }
-      }
+    },
-    }
+    "services": {
-  },
+        "ask_question": {
-  "entity": {
+            "name": "Ask Question",
-    "sensor": {
+            "description": "Send a question to the AI model and get a detailed response. Supports context awareness for follow-up questions.",
-      "last_response": {
+            "fields": {
-        "name": "Last Response",
+                "question": {
-        "state_attributes": {
+                    "name": "Question",
-          "last_updated": {
+                    "description": "Your question or prompt for the AI model. Be specific for better results."
-            "name": "Last Updated",
+                },
-            "description": "Time of the last AI response"
+                "system_prompt": {
-          },
+                    "name": "System Prompt",
-          "question": {
+                    "description": "Optional behavior instructions for this specific question"
-            "name": "Last Question",
+                },
-            "description": "Most recent question asked"
+                "model": {
-          },
+                    "name": "Model",
-          "response": {
+                    "description": "Optional specific AI model for this request (overrides default)"
-            "name": "AI Response",
+                },
-            "description": "Latest response from the AI"
+                "temperature": {
-          },
+                    "name": "Temperature",
-          "model": {
+                    "description": "Optional creativity setting (0-2, affects response variation)"
-            "name": "Current Model",
+                },
-            "description": "AI model currently in use"
+                "max_tokens": {
-          },
+                    "name": "Max Tokens",
-          "temperature": {
+                    "description": "Optional maximum response length (1-4096 tokens)"
-            "name": "Temperature Setting",
+                }
-            "description": "Current temperature parameter"
+            }
-          },
+        },
-          "max_tokens": {
+        "clear_history": {
-            "name": "Max Tokens Setting",
+            "name": "Clear History",
-            "description": "Current maximum tokens limit"
+            "description": "Delete all stored conversation history, responses, and metadata"
-          },
+        },
-          "total_responses": {
+        "get_history": {
-            "name": "Total Responses",
+            "name": "Get History",
-            "description": "Number of responses since last reset"
+            "description": "Retrieve conversation history with detailed metadata including timestamps",
-          },
+            "fields": {
-          "system_prompt": {
+                "limit": {
-            "name": "System Prompt",
+                    "name": "Limit",
-            "description": "Current system instructions for the AI"
+                    "description": "Maximum number of conversations to return (1-100)"
-          },
+                },
-          "response_time": {
+                "filter_model": {
-            "name": "Response Time",
+                    "name": "Filter Model",
-            "description": "Time taken to generate last response"
+                    "description": "Show only responses from a specific model"
-          }
+                },
+                "start_date": {
+                    "name": "Start Date",
+                    "description": "Filter conversations from this date (YYYY-MM-DD)"
+                }
+            }
+        },
+        "set_system_prompt": {
+            "name": "Set System Prompt",
+            "description": "Update default AI behavior and expertise instructions",
+            "fields": {
+                "prompt": {
+                    "name": "System Prompt",
+                    "description": "Instructions for AI behavior, expertise, and response style"
+                }
+            }
         }
-      }
+    },
-    }
+    "state": {
-  },
+        "ready": "Ready for requests",
-  "services": {
+        "processing": "Processing request",
-    "ask_question": {
+        "error": "Error occurred",
-      "name": "Ask Question",
+        "disconnected": "API disconnected",
-      "description": "Send a question to the AI model",
+        "rate_limited": "Rate limit reached",
-      "fields": {
+        "initializing": "Starting up",
-        "question": {
+        "retrying": "Retrying request",
-          "name": "Question",
+        "queued": "Request queued"
-          "description": "Your question for the AI"
+    },
+    "entity": {
+        "sensor": {
+            "status": {
+                "name": "AI Status",
+                "state": {
+                    "ready": "Ready",
+                    "processing": "Processing",
+                    "error": "Error",
+                    "disconnected": "Disconnected",
+                    "rate_limited": "Rate Limited",
+                    "initializing": "Initializing",
+                    "retrying": "Retrying",
+                    "queued": "Queued"
+                }
+            },
+            "last_response": {
+                "name": "Last Response",
+                "state": {
+                    "success": "Success",
+                    "error": "Error",
+                    "timeout": "Timeout"
+                }
+            }
         }
-      }
-    },
-    "clear_history": {
-      "name": "Clear History",
-      "description": "Clear conversation history"
-    },
-    "get_history": {
-      "name": "Get History",
-      "description": "Retrieve conversation history"
-    },
-    "set_system_prompt": {
-      "name": "Set System Prompt",
-      "description": "Set AI behavior instructions"
     }
-  }
 }

hacs.json

@@ -4,6 +4,6 @@
   "domains": ["sensor"],
   "homeassistant": "2024.11.0",
   "icon": "mdi:brain",
-  "version": "1.0.3",
+  "version": "2.0.0",
   "documentation": "https://github.com/smkrv/ha-text-ai"
 }

structure.md

@@ -0,0 +1,17 @@
+```
+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
+```