Bump to version 2.1.6

fix: correct field naming in Gemini API requests from camelCase to snake_case and improve message handling
fix(api_client): correct Google Gemini API integration
2026-07-22 15:14:01 +08:00 · 2025-05-20 01:50:06 +03:00 · 2025-05-20 01:42:38 +03:00 · 2025-05-20 01:16:41 +03:00 · 2025-05-19 23:20:27 +03:00 · 2025-05-19 23:12:55 +03:00
34 changed files with 2221 additions and 1005 deletions
@@ -1,40 +0,0 @@
-# Python
-__pycache__/
-*.py[cod]
-*$py.class
-*.so
-.Python
-build/
-develop-eggs/
-dist/
-downloads/
-eggs/
-.eggs/
-lib/
-lib64/
-parts/
-sdist/
-var/
-wheels/
-*.egg-info/
-.installed.cfg
-*.egg
-
-# Home Assistant
-.storage
-.cloud
-.google.token
-
-# IDE
-.idea/
-.vscode/
-*.swp
-*.swo
-*~
-
-# OS
-.DS_Store
-Thumbs.db
-*.psd
-*.zip
-*.txt
@@ -0,0 +1,128 @@
+# Contributor Covenant Code of Conduct
+
+## Our Pledge
+
+We as members, contributors, and leaders pledge to make participation in our
+community a harassment-free experience for everyone, regardless of age, body
+size, visible or invisible disability, ethnicity, sex characteristics, gender
+identity and expression, level of experience, education, socio-economic status,
+nationality, personal appearance, race, religion, or sexual identity
+and orientation.
+
+We pledge to act and interact in ways that contribute to an open, welcoming,
+diverse, inclusive, and healthy community.
+
+## Our Standards
+
+Examples of behavior that contributes to a positive environment for our
+community include:
+
+* Demonstrating empathy and kindness toward other people
+* Being respectful of differing opinions, viewpoints, and experiences
+* Giving and gracefully accepting constructive feedback
+* Accepting responsibility and apologizing to those affected by our mistakes,
+  and learning from the experience
+* Focusing on what is best not just for us as individuals, but for the
+  overall community
+
+Examples of unacceptable behavior include:
+
+* The use of sexualized language or imagery, and sexual attention or
+  advances of any kind
+* Trolling, insulting or derogatory comments, and personal or political attacks
+* Public or private harassment
+* Publishing others' private information, such as a physical or email
+  address, without their explicit permission
+* Other conduct which could reasonably be considered inappropriate in a
+  professional setting
+
+## Enforcement Responsibilities
+
+Community leaders are responsible for clarifying and enforcing our standards of
+acceptable behavior and will take appropriate and fair corrective action in
+response to any behavior that they deem inappropriate, threatening, offensive,
+or harmful.
+
+Community leaders have the right and responsibility to remove, edit, or reject
+comments, commits, code, wiki edits, issues, and other contributions that are
+not aligned to this Code of Conduct, and will communicate reasons for moderation
+decisions when appropriate.
+
+## Scope
+
+This Code of Conduct applies within all community spaces, and also applies when
+an individual is officially representing the community in public spaces.
+Examples of representing our community include using an official e-mail address,
+posting via an official social media account, or acting as an appointed
+representative at an online or offline event.
+
+## Enforcement
+
+Instances of abusive, harassing, or otherwise unacceptable behavior may be
+reported to the community leaders responsible for enforcement at
+issue tracker.
+All complaints will be reviewed and investigated promptly and fairly.
+
+All community leaders are obligated to respect the privacy and security of the
+reporter of any incident.
+
+## Enforcement Guidelines
+
+Community leaders will follow these Community Impact Guidelines in determining
+the consequences for any action they deem in violation of this Code of Conduct:
+
+### 1. Correction
+
+**Community Impact**: Use of inappropriate language or other behavior deemed
+unprofessional or unwelcome in the community.
+
+**Consequence**: A private, written warning from community leaders, providing
+clarity around the nature of the violation and an explanation of why the
+behavior was inappropriate. A public apology may be requested.
+
+### 2. Warning
+
+**Community Impact**: A violation through a single incident or series
+of actions.
+
+**Consequence**: A warning with consequences for continued behavior. No
+interaction with the people involved, including unsolicited interaction with
+those enforcing the Code of Conduct, for a specified period of time. This
+includes avoiding interactions in community spaces as well as external channels
+like social media. Violating these terms may lead to a temporary or
+permanent ban.
+
+### 3. Temporary Ban
+
+**Community Impact**: A serious violation of community standards, including
+sustained inappropriate behavior.
+
+**Consequence**: A temporary ban from any sort of interaction or public
+communication with the community for a specified period of time. No public or
+private interaction with the people involved, including unsolicited interaction
+with those enforcing the Code of Conduct, is allowed during this period.
+Violating these terms may lead to a permanent ban.
+
+### 4. Permanent Ban
+
+**Community Impact**: Demonstrating a pattern of violation of community
+standards, including sustained inappropriate behavior,  harassment of an
+individual, or aggression toward or disparagement of classes of individuals.
+
+**Consequence**: A permanent ban from any sort of public interaction within
+the community.
+
+## Attribution
+
+This Code of Conduct is adapted from the [Contributor Covenant][homepage],
+version 2.0, available at
+https://www.contributor-covenant.org/version/2/0/code_of_conduct.html.
+
+Community Impact Guidelines were inspired by [Mozilla's code of conduct
+enforcement ladder](https://github.com/mozilla/diversity).
+
+[homepage]: https://www.contributor-covenant.org
+
+For answers to common questions about this code of conduct, see the FAQ at
+https://www.contributor-covenant.org/faq. Translations are available at
+https://www.contributor-covenant.org/translations.
@@ -2,124 +2,167 @@

 <div align="center">  

-![GitHub release](https://img.shields.io/github/release/smkrv/ha-text-ai.svg?style=flat-square) ![GitHub last commit](https://img.shields.io/github/last-commit/smkrv/ha-text-ai.svg?style=flat-square) [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](https://opensource.org/licenses/MIT) [![hacs_badge](https://img.shields.io/badge/HACS-Custom-41BDF5.svg?style=flat-square)](https://github.com/hacs/integration) ![/README.md](https://img.shields.io/badge/language-English-green?style=flat-square) ![/README_RU.md](https://img.shields.io/badge/language-Russian-green?style=flat-square) ![](https://img.shields.io/badge/language-Deutch-green?style=flat-square)
+  ![GitHub release](https://img.shields.io/github/v/release/smkrv/ha-text-ai?style=flat-square) ![GitHub last commit](https://img.shields.io/github/last-commit/smkrv/ha-text-ai?style=flat-square) [![License: CC BY-NC-SA 4.0](https://img.shields.io/badge/License-CC%20BY--NC--SA%204.0-lightgrey.svg?style=flat-square)](https://creativecommons.org/licenses/by-nc-sa/4.0/) [![hacs_badge](https://img.shields.io/badge/HACS-Custom-41BDF5.svg?style=flat-square)](https://github.com/hacs/integration)  
+  ![Deutsch](https://img.shields.io/badge/lang-DE-blue?style=flat-square) ![English](https://img.shields.io/badge/lang-EN-blue?style=flat-square) ![Español](https://img.shields.io/badge/lang-ES-blue?style=flat-square) ![हिन्दी](https://img.shields.io/badge/lang-HI-blue?style=flat-square) ![Italiano](https://img.shields.io/badge/lang-IT-blue?style=flat-square) ![Русский](https://img.shields.io/badge/lang-RU-blue?style=flat-square) ![Српски](https://img.shields.io/badge/lang-SR-blue?style=flat-square) ![中文](https://img.shields.io/badge/lang-ZH-blue?style=flat-square)

-  <img src="https://github.com/smkrv/ha-text-ai/blob/524849f6a945ec62c2cf6a6b7ecd9a28b37bf0fa/misc/icons/logo.jpg" alt="HA Text AI" height="160"/>
+
+  <img src="https://github.com/smkrv/ha-text-ai/blob/15c717fcb0204bf4a0d4b4b4c6f0bb93e9f6c9a9/custom_components/ha_text_ai/icons/logo%402x.png" alt="HA Text AI" style="width: 50%; max-width: 256px; max-height: 128px; aspect-ratio: 2/1; object-fit: contain;"/>

 ### Advanced AI Integration for [Home Assistant](https://www.home-assistant.io/) with LLM multi-provider support
 </div>

 <p align="center">
-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.
+Transform your smart home experience with powerful AI assistance powered by multiple AI providers including OpenAI GPT, DeepSeek and Anthropic Claude models. Get intelligent responses, automate complex scenarios, and enhance your home automation with advanced natural language processing.

 </p>

 ---

 > [!IMPORTANT]
-> 🚧 ALPHA VERSION 🚧  
-> Expect: potential bugs, frequent changes, incomplete features.  
-> 🤝 Community Driven  
+> 🤝 Community Driven: for more details on the integration,   
+> check out the discussion on the **[Home Assistant Community forum](https://community.home-assistant.io/t/ha-text-ai-transforming-home-automation-through-multi-llm-integration/799741)**
 >
->  <a href="https://community.home-assistant.io/t/ha-text-ai-transforming-home-automation-with-multi-provider-language-models/799741"><img src="https://img.shields.io/badge/Community-blue?style=for-the-badge&logo=homeassistant&logoColor=white&color=03a9f4"/></a>  
+>  <a href="https://my.home-assistant.io/redirect/hacs_repository/?owner=smkrv&repository=ha-text-ai&category=Integration"><img src="https://my.home-assistant.io/badges/hacs_repository.svg" width="210" height="auto"></a>
 >  
-> [Screenshots](misc/screenshots/screenshot.jpg)
+> [Screenshots](assets/images/screenshots/screenshot.jpg)

 ## 🌟 Features

- 🧠 **Multi-Provider AI Integration**:
-  - Support for OpenAI GPT models
-  - Anthropic Claude integration
-  - Custom API endpoints
-  - Flexible model selection
+- 🧠 **Multi-Provider AI Integration**: Support for OpenAI GPT, DeepSeek and Anthropic Claude models
+- 💬 **Advanced Language Processing**: Context-aware, multi-turn conversations
+- 📝 **Enhanced Memory Management**: Secure file-based history storage
+- ⚡ **Performance Optimization**: Efficient token usage and smart rate limiting
+- 🎯 **Advanced Customization**: Per-request model and parameter selection
+- 🔒 **Enhanced Security**: Secure API key management and usage monitoring
+- 🎨 **Improved User Experience**: Intuitive configuration and rich interfaces
+- 🔄 **Automation Integration**: Event-driven responses and template compatibility

- 💬 **Advanced Language Processing**:
-  - Context-aware responses
-  - Multi-turn conversations
-  - Custom system instructions
-  - Natural conversation flow
+<details>
+<summary>📦 Detailed Feature Breakdown</summary>

- 📝 **Enhanced Memory Management**:
-  - Persistent conversation history
-  - Context-aware responses
-  - Customizable history limits
-  - Model-specific filtering
+### 🧠 **Multi-Provider AI Integration**
+- Support for OpenAI GPT models
+- Anthropic Claude integration
+- DeepSeek integration
+- Custom API endpoints
+- Flexible model selection

- ⚡ **Performance Optimization**:
-  - Efficient token usage
-  - Smart rate limiting
-  - Response caching
-  - Request interval control
+### 💬 **Advanced Language Processing**
+- Context-aware responses
+- Multi-turn conversations
+- Custom system instructions
+- Natural conversation flow

- 🎯 **Advanced Customization**:
-  - Per-request model selection
-  - Adjustable parameters
-  - Custom system prompts
-  - Temperature control
+### 📝 **Enhanced Memory Management**
+- File-based conversation history storage
+- Automatic history rotation
+- Configurable history size limits
+- Secure storage in Home Assistant

- 🔒 **Enhanced Security**:
-  - Secure API key storage
-  - Rate limiting protection
-  - Error handling
-  - Usage monitoring
+### ⚡ **Performance Optimization**
+- Efficient token usage
+- Smart rate limiting
+- Response caching
+- Request interval control

- 🎨 **Improved User Experience**:
-  - Intuitive configuration UI
-  - Detailed sensor attributes
-  - Rich service interface
-  - Model selection UI
+### 🎯 **Advanced Customization**
+- Per-request model selection
+- Adjustable parameters
+- Custom system prompts
+- Temperature control

- 🔄 **Automation Integration**:
-  - Event-driven responses
-  - Conditional logic support
-  - Template compatibility
-  - Model-specific automation
+### 🔒 **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
+
+</details>
+
+#### 🌐 Translations
+
+| Code | Language | Status |
+|------|----------|--------|
+| 🇩🇪 de | Deutsch | Full |
+| 🇬🇧 en | English | Primary |
+| 🇪🇸 es | Español | Full |
+| 🇮🇳 hi | हिन्दी | Full |
+| 🇮🇹 it | Italiano | Full |
+| 🇷🇺 ru | Русский | Full |
+| 🇷🇸 sr | Српски | Full |
+| 🇨🇳 zh | 中文 | Full |

 ## 📋 Prerequisites

- Home Assistant 2024.11 or later
+- Home Assistant 2024.2.2 or later
 - Active API key from:
  - OpenAI ([Get key](https://platform.openai.com/account/api-keys))
  - Anthropic ([Get key](https://console.anthropic.com/))
+  - DeepSeek ([Get key](https://platform.deepseek.com/api_keys))
  - OpenRouter ([Get key](https://openrouter.ai/keys))
+  - Google Gemini 🆕 ([Get key](https://ai.google.dev/gemini-api/docs/api-key)) thanks to ([@Azzedde](https://github.com/Azzedde))
+  - Any OpenAI-compatible API provider
 - Python 3.9 or newer
 - Stable internet connection

-### Configuration Options
- API Provider (OpenAI/Anthropic)
- API Key (provider-specific)
- Model Selection (flexible, provider-specific models)
- Temperature (Creativity control, 0.0-2.0)
- Max Tokens (Response length limit)
- Request Interval (API call throttling)
- Custom API Endpoint (optional)
+## Configuration Options

-#### ⓘ Potentially Compatible Providers  
-The integration is designed to be flexible and may work with other providers offering OpenAI-compatible APIs:  
- Groq  
- Together AI  
- Perplexity AI  
- Mistral AI  
- Google AI  
- Local AI servers (like Ollama)  
- Custom OpenAI-compatible endpoints  
+### 🔧 **Core Configuration Settings**
+- 🌐 **API Provider**: OpenAI/Anthropic/DeepSeek
+- 🔑 **API Key**: Provider-specific authentication
+- 🤖 **Model Selection**: Flexible, provider-specific models
+- 🌡️ **Temperature**: Creativity control (0.0-2.0)
+- 📏 **Max Tokens**: Response length limit (passed directly to the LLM API to control the maximum length of the response)
+- ⏱️ **Request Interval**: API call throttling
+- 💾 **History Size**: Number of messages to retain
+- 🌍 **Custom API Endpoint**: Optional advanced configuration

-#### Additional Notes  
- Not all providers guarantee full compatibility  
- Performance may vary between providers  
- Check individual provider's documentation  
+<details>
+<summary>🌐 Potentially Compatible Providers</summary>
+
+#### Flexible Provider Ecosystem
+The integration is designed to be flexible and may work with other providers offering OpenAI-compatible APIs:
+- Groq
+- Together AI
+- Perplexity AI
+- Mistral AI
+- Google AI
+- Local AI servers (like Ollama)
+- Custom OpenAI-compatible endpoints
+
+#### 🚨 Compatibility Notes
+- Not all providers guarantee full compatibility
+- Performance may vary between providers
+- Check individual provider's documentation
 - Ensure your API key has sufficient credits/quota

-#### Provider Compatibility Requirements  
-To be compatible, a provider should support:  
- OpenAI-like REST API structure  
- JSON request/response format  
- Standard authentication method  
+#### 🔍 Provider Compatibility Requirements
+To be compatible, a provider should support:
+- OpenAI-like REST API structure
+- JSON request/response format
+- Standard authentication method
 - Similar model parameter handling

+</details>
+
 ## ⚡ Installation

 ### HACS Installation (Recommended)
+>[!TIP]
+>HA Text AI is available in the default HACS repository. You can install it directly through HACS or click the button below to open it there.
+
 <a href="https://my.home-assistant.io/redirect/hacs_repository/?owner=smkrv&repository=ha-text-ai&category=Integration"><img src="https://my.home-assistant.io/badges/hacs_repository.svg" width="170" height="auto"></a>
 1. Open HACS in Home Assistant
 2. Click on "Integrations"
@@ -144,7 +187,8 @@ To be compatible, a provider should support:
 3. Search for "HA Text AI"
 4. Follow the configuration steps

-### Via YAML
+<details>
+<summary>📦 Via YAML (Advanced)</summary>

 ### Platform Configuration (Global Settings)

@@ -188,6 +232,8 @@ sensor:
 | `request_interval` | Float | ❌ | 1.0 | Delay between API requests |
 | `api_endpoint` | URL | ⚠️ | Provider default | Custom API endpoint |
 | `system_prompt` | String | ❌ | - | Default context for AI interactions |
+| `max_history_size` | Integer | ❌ | 100 | Maximum number of conversation entries to store |
+| `history_file_size` | Integer | ⚠️  | 1 | Maximum history file size in MB |

 #### Sensor Configuration

@@ -200,6 +246,8 @@ sensor:
 | `temperature` | Float | ❌ | Platform setting | Override global temperature |
 | `max_tokens` | Integer | ❌ | Platform setting | Override global max tokens |

+</details>
+
 ## 🛠️ Available Services

 ### ask_question
@@ -212,12 +260,14 @@ data:
  max_tokens: 500  # optional
  context_messages: 10  #optional, number of previous messages to include in context, default: 5
  system_prompt: "You are a sleep optimization expert"  # optional
+  instance: sensor.ha_text_ai_gpt
 ```

 ### set_system_prompt
 ```yaml
 service: ha_text_ai.set_system_prompt
 data:
+  instance: sensor.ha_text_ai_gpt
  prompt: |
    You are a home automation expert focused on:
    1. Energy efficiency
@@ -229,6 +279,8 @@ data:
 ### clear_history
 ```yaml
 service: ha_text_ai.clear_history
+data:
+  instance: sensor.ha_text_ai_gpt
 ```

 ### get_history
@@ -237,6 +289,7 @@ service: ha_text_ai.get_history
 data:
  limit: 5  # optional
  filter_model: "gpt-4o"  # optional
+  instance: sensor.ha_text_ai_gpt
 ```

 ### 🏷️ HA Text AI Sensor Naming Convention
@@ -256,7 +309,7 @@ sensor.ha_text_ai_YOUR_UNIQUE_SUFFIX
 # Examples:
 sensor.ha_text_ai_gpt      # GPT-based sensor
 sensor.ha_text_ai_claude   # Claude-based sensor
-sensor.ha_text_ai_gpt   # Custom suffix
+sensor.ha_text_ai_abc      # Custom suffix
 ```

 #### Response Retrieval
@@ -273,6 +326,7 @@ automation:
      - service: ha_text_ai.ask_question
        data:
          question: "Home automation advice"
+          instance: sensor.ha_text_ai_gpt
      - service: notify.mobile
        data:
          message: >
@@ -289,6 +343,16 @@ automation:

 ### 🔍 HA Text AI Sensor Attributes

+- 🤖 **Model and Provider Information**: Tracking current AI model and service provider
+- 🚦 **System Status**: Real-time API and processing readiness
+- 📊 **Performance Metrics**: Request success rates and response times
+- 💬 **Conversation Tracking**: Token usage and interaction history are estimated using a heuristic method based on word count and specific word characteristics, which may differ from actual token usage.
+- 🕒 **Last Interaction Details**: Recent query and response tracking
+- ❤️ **System Health**: Error monitoring and service uptime
+
+<details>
+<summary>📦 Detailed Sensor Attributes</summary>
+
 #### Model and Provider Information
 ```yaml
 # Name of the AI model currently in use (e.g., latest version of GPT)  
@@ -344,6 +408,12 @@ automation:

 # Tokens used in the AI's generated responses  
 {{ state_attr('sensor.ha_text_ai_gpt', 'Completion tokens') }}     # 0
+
+# Number of entries in current history file
+{{ state_attr('sensor.ha_text_ai_gpt', 'History size') }}          # 0  
+
+# Last few conversation entries (limited to 1 for performance)
+{{ state_attr('sensor.ha_text_ai_gpt', 'conversation_history') }}  # [...]
 ```

 #### Last Interaction Details
@@ -370,11 +440,19 @@ automation:
 {{ state_attr('sensor.ha_text_ai_gpt', 'Uptime') }}          # 547,58
 ```

+### History Storage
+Conversation history stored in `.storage/ha_text_ai_history/` directory:
+- Each instance has its own history file (JSON)
+- Files are automatically rotated when size limit is reached
+- Archived history files are timestamped
+- Default maximum file size: 1MB
+
 ### 💡 Pro Tips
 - Always check attribute existence
 - Use these attributes for monitoring and automation
 - Some values might be 0 or empty initially

+</details>

 ## 📘 FAQ

@@ -402,6 +480,15 @@ A: Yes, your data is secure. The system operates entirely on your local machine,
 **Q: How do context messages work?**
 A: Context messages allow the AI to remember and reference previous conversation history. By default, 5 previous messages are included, but you can customize this from 1 to 20 messages to control the conversation depth and token usage.

+**Q: Where is conversation history stored?**  
+A: History is stored in files under the `.storage/ha_text_ai_history/` directory, with automatic rotation and size management.
+
+**Q: Can I access old conversation history?**  
+A: Yes, archived history files are stored with timestamps and can be accessed manually if needed.
+
+**Q: How much history is kept?**  
+A: By default, up to 100 conversations are stored, but this can be configured. Files are automatically rotated when they reach 1MB.
+
 ## 🤝 Contributing

 Contributions welcome! Please read our [Contributing Guide](CONTRIBUTING.md).
@@ -428,7 +515,7 @@ DEALINGS IN THE SOFTWARE.
 ## 📝 License

 Author: SMKRV
-[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) - see [LICENSE](LICENSE) for details. 
+[CC BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/) - see [LICENSE](LICENSE) for details.

 ## 💡 Support the Project

@@ -448,9 +535,11 @@ If you want to say thanks financially, you can send a small token of appreciatio

 ---

+<div align="center"><img src="https://github.com/smkrv/ha-text-ai/blob/2aaf3405759eb2d97624834594e24ace896131df/assets/images/icons/footer_icon.png" alt="HA Text AI" style="width: 128px; height: auto;"/></div>  
 <div align="center">

-Made with ❤️ and Claude 3.5 Sonnet for the Home Assistant Community
+Made with ❤️ for the Home Assistant Community,  
+utilizing Claude 3.5 Sonnet, Gemini Pro 1.5, and Qwen 2.5 Coder 32B Instruct.

 [Report Bug](https://github.com/smkrv/ha-text-ai/issues) · [Request Feature](https://github.com/smkrv/ha-text-ai/issues)

@@ -11,8 +11,9 @@ from __future__ import annotations
 import logging
 import os
 import shutil
+import hashlib
 from datetime import datetime, timedelta
-from typing import Any, Dict
+from typing import Any, Dict, TypeVar

 import voluptuous as vol
 from async_timeout import timeout
@@ -38,11 +39,17 @@ from .const import (
    CONF_CONTEXT_MESSAGES,
    API_PROVIDER_OPENAI,
    API_PROVIDER_ANTHROPIC,
+    API_PROVIDER_DEEPSEEK,
+    API_PROVIDER_GEMINI,
    DEFAULT_MODEL,
+    DEFAULT_DEEPSEEK_MODEL,
+    DEFAULT_GEMINI_MODEL,
    DEFAULT_TEMPERATURE,
    DEFAULT_MAX_TOKENS,
    DEFAULT_OPENAI_ENDPOINT,
    DEFAULT_ANTHROPIC_ENDPOINT,
+    DEFAULT_DEEPSEEK_ENDPOINT,
+    DEFAULT_GEMINI_ENDPOINT,
    DEFAULT_REQUEST_INTERVAL,
    DEFAULT_CONTEXT_MESSAGES,
    API_TIMEOUT,
@@ -52,11 +59,13 @@ from .const import (
    SERVICE_SET_SYSTEM_PROMPT,
    DEFAULT_MAX_HISTORY,
    CONF_MAX_HISTORY_SIZE,
+    ICONS_SUBDOMAIN,
 )

 _LOGGER = logging.getLogger(__name__)

 CONFIG_SCHEMA = cv.config_entry_only_config_schema(DOMAIN)
+ConfigType = TypeVar("ConfigType", bound=Dict[str, Any])

 SERVICE_SCHEMA_ASK_QUESTION = vol.Schema({
    vol.Required("instance"): cv.string,
@@ -90,19 +99,18 @@ def get_coordinator_by_instance(hass: HomeAssistant, instance: str) -> HATextAIC

    raise HomeAssistantError(f"Instance {instance} not found")

-async def async_setup(hass: HomeAssistant, config: Dict[str, Any]) -> bool:
-    """Set up the HA Text AI component."""
-    hass.data.setdefault(DOMAIN, {})
+def get_file_hash(file_path: str) -> str:
+    """Calculate SHA256 hash of file."""
+    sha256_hash = hashlib.sha256()
+    with open(file_path, "rb") as f:
+        for byte_block in iter(lambda: f.read(4096), b""):
+            sha256_hash.update(byte_block)
+    return sha256_hash.hexdigest()

-    try:
-        source = os.path.join(os.path.dirname(__file__), 'icons', 'icon.svg')
-        dest_dir = os.path.join(hass.config.path('www'), 'icons')
-        os.makedirs(dest_dir, exist_ok=True)
-        dest = os.path.join(dest_dir, 'icon.png')
-        if not os.path.exists(dest):
-            shutil.copyfile(source, dest)
-    except Exception as ex:
-        _LOGGER.warning("Failed to copy custom icon: %s", str(ex))
+async def async_setup(hass: HomeAssistant, config: ConfigType) -> bool:
+    """Set up the Home Assistant Text AI component."""
+    # Initialize domain data storage
+    hass.data.setdefault(DOMAIN, {})

    async def async_ask_question(call: ServiceCall) -> None:
        """Handle ask_question service."""
@@ -150,6 +158,7 @@ async def async_setup(hass: HomeAssistant, config: Dict[str, Any]) -> bool:
            _LOGGER.error("Error setting system prompt: %s", str(err))
            raise HomeAssistantError(f"Failed to set system prompt: {str(err)}")

+    # Register services
    hass.services.async_register(
        DOMAIN,
        SERVICE_ASK_QUESTION,
@@ -178,6 +187,53 @@ async def async_setup(hass: HomeAssistant, config: Dict[str, Any]) -> bool:
        schema=SERVICE_SCHEMA_SET_SYSTEM_PROMPT
    )

+    # Handle icons
+    try:
+        source_icon_path = os.path.join(
+            os.path.dirname(__file__),
+            ICONS_SUBDOMAIN,
+            'icon@2x.png'
+        )
+
+        destination_directory = os.path.join(
+            hass.config.path('www'),
+            DOMAIN,
+            ICONS_SUBDOMAIN
+        )
+
+        destination_icon_path = os.path.join(
+            destination_directory,
+            'icon.png'
+        )
+
+        if not os.path.exists(source_icon_path):
+            _LOGGER.error("Source icon not found: %s", source_icon_path)
+            return True
+
+        def create_directory():
+            os.makedirs(destination_directory, exist_ok=True)
+
+        await hass.async_add_executor_job(create_directory)
+
+        should_copy = True
+
+        if os.path.exists(destination_icon_path):
+            source_hash = await hass.async_add_executor_job(get_file_hash, source_icon_path)
+            dest_hash = await hass.async_add_executor_job(get_file_hash, destination_icon_path)
+            should_copy = source_hash != dest_hash
+
+        if should_copy:
+            def copy_file():
+                shutil.copyfile(source_icon_path, destination_icon_path)
+
+            await hass.async_add_executor_job(copy_file)
+            _LOGGER.debug("Icon updated: %s", destination_icon_path)
+
+    except PermissionError as e:
+        _LOGGER.error("Permission denied when managing icons: %s", str(e))
+    except Exception as e:
+        _LOGGER.error("Failed to manage icons: %s", str(e))
+
    return True

 async def async_check_api(session, endpoint: str, headers: dict, provider: str) -> bool:
@@ -185,6 +241,8 @@ async def async_check_api(session, endpoint: str, headers: dict, provider: str)
    try:
        if provider == API_PROVIDER_ANTHROPIC:
            check_url = f"{endpoint}/v1/models"
+        elif provider == API_PROVIDER_DEEPSEEK:
+            check_url = f"{endpoint}/models"  # DeepSeek
        else:  # OpenAI
            check_url = f"{endpoint}/models"

@@ -18,6 +18,9 @@ from .const import (
    API_TIMEOUT,
    API_RETRY_COUNT,
    API_PROVIDER_ANTHROPIC,
+    API_PROVIDER_DEEPSEEK,
+    API_PROVIDER_OPENAI,
+    API_PROVIDER_GEMINI,
    MIN_TEMPERATURE,
    MAX_TEMPERATURE,
    MIN_MAX_TOKENS,
@@ -109,19 +112,53 @@ class APIClient:
                return await self._create_anthropic_completion(
                    model, messages, temperature, max_tokens
                )
+            elif self.api_provider == API_PROVIDER_DEEPSEEK:
+                return await self._create_deepseek_completion(
+                    model, messages, temperature, max_tokens
+                )
+            elif self.api_provider == API_PROVIDER_GEMINI:
+                return await self._create_gemini_completion(
+                    model, messages, temperature, max_tokens
+                )
            else:
                return await self._create_openai_completion(
                    model, messages, temperature, max_tokens
                )
-        except (KeyError, IndexError) as e:
-            if "'choices'" in str(e) or "'message'" in str(e):
-                raise HomeAssistantError("Failed to get a response from the AI model. Please check your internet connection and try again later.")
-            else:
-                raise
        except Exception as e:
            _LOGGER.error("API request failed: %s", str(e))
            raise HomeAssistantError(f"API request failed: {str(e)}")

+    async def _create_deepseek_completion(
+        self,
+        model: str,
+        messages: List[Dict[str, str]],
+        temperature: float,
+        max_tokens: int,
+    ) -> Dict[str, Any]:
+        """Create completion using DeepSeek API."""
+        url = f"{self.endpoint}/chat/completions"
+        payload = {
+            "model": model,
+            "messages": messages,
+            "temperature": temperature,
+            "max_tokens": max_tokens,
+            "stream": False
+        }
+
+        data = await self._make_request(url, payload)
+        return {
+            "choices": [
+                {
+                    "message": {"content": data["choices"][0]["message"]["content"]},
+                }
+            ],
+            "usage": {
+                "prompt_tokens": data["usage"]["prompt_tokens"],
+                "completion_tokens": data["usage"]["completion_tokens"],
+                "total_tokens": data["usage"]["total_tokens"],
+            },
+        }
+
    async def _create_openai_completion(
        self,
        model: str,
@@ -206,6 +243,100 @@ class APIClient:
            _LOGGER.error(f"Connection check failed: {str(e)}")
            return False

+    async def _create_gemini_completion(
+        self,
+        model: str,
+        messages: List[Dict[str, str]],
+        temperature: float,
+        max_tokens: int,
+    ) -> Dict[str, Any]:
+        """Create completion using Gemini API."""
+        # Extract API key from headers (Bearer token)
+        api_key = self.headers.get("Authorization", "").replace("Bearer ", "")
+        url = f"{self.endpoint}/models/{model}:generateContent?key={api_key}"
+
+        # Convert messages to Gemini format
+        contents = []
+        system_instruction = ""
+
+        # Process messages
+        for msg in messages:
+            if msg['role'] == 'system':
+                system_instruction += msg['content'] + "\n"
+            else:
+                # Convert role: 'user' stays 'user', anything else becomes 'model'
+                role = "user" if msg['role'] == 'user' else "model"
+                contents.append({
+                    "role": role,
+                    "parts": [{"text": msg['content']}]
+                })
+
+        # Ensure contents starts with a user message if not empty
+        if contents and contents[0]["role"] != "user":
+            # Add a placeholder user message
+            contents.insert(0, {
+                "role": "user",
+                "parts": [{"text": "I need your assistance."}]
+            })
+
+        # Ensure contents is not empty
+        if not contents:
+            contents.append({
+                "role": "user",
+                "parts": [{"text": "I need your assistance."}]
+            })
+
+        # Create payload with snake_case keys as required by Gemini API
+        payload = {
+            "contents": contents,
+            "generation_config": {  # Changed from camelCase to snake_case
+                "temperature": temperature,
+                "max_output_tokens": max_tokens  # Changed from camelCase to snake_case
+            }
+        }
+
+        if system_instruction:
+            payload["system_instruction"] = {  # Changed from camelCase to snake_case
+                "parts": [{"text": system_instruction.strip()}]
+            }
+
+        try:
+            data = await self._make_request(url, payload)
+
+            # Safely extract response data
+            candidates = data.get("candidates", [])
+            if not candidates:
+                raise HomeAssistantError("Gemini API returned no candidates")
+
+            content = candidates[0].get("content", {})
+            parts = content.get("parts", [])
+            if not parts:
+                raise HomeAssistantError("Gemini API response contains no content parts")
+
+            answer_text = parts[0].get("text", "")
+
+            # Safely extract usage data
+            usage = data.get("usageMetadata", {})
+            prompt_tokens = usage.get("promptTokenCount", 0)
+            completion_tokens = usage.get("candidatesTokenCount", 0)
+            total_tokens = usage.get("totalTokenCount", prompt_tokens + completion_tokens)
+
+            return {
+                "choices": [{
+                    "message": {
+                        "content": answer_text
+                    }
+                }],
+                "usage": {
+                    "prompt_tokens": prompt_tokens,
+                    "completion_tokens": completion_tokens,
+                    "total_tokens": total_tokens
+                }
+            }
+        except Exception as e:
+            _LOGGER.error(f"Gemini API error: {str(e)}")
+            raise HomeAssistantError(f"Gemini API error: {str(e)}")
+
    async def shutdown(self) -> None:
        """Shutdown API client."""
        _LOGGER.debug("Shutting down API client")
@@ -28,13 +28,19 @@ from .const import (
    CONF_CONTEXT_MESSAGES,
    API_PROVIDER_OPENAI,
    API_PROVIDER_ANTHROPIC,
+    API_PROVIDER_DEEPSEEK,
+    API_PROVIDER_GEMINI,
    API_PROVIDERS,
    DEFAULT_MODEL,
+    DEFAULT_DEEPSEEK_MODEL,
+    DEFAULT_GEMINI_MODEL,
    DEFAULT_TEMPERATURE,
    DEFAULT_MAX_TOKENS,
    DEFAULT_REQUEST_INTERVAL,
    DEFAULT_OPENAI_ENDPOINT,
    DEFAULT_ANTHROPIC_ENDPOINT,
+    DEFAULT_DEEPSEEK_ENDPOINT,
+    DEFAULT_GEMINI_ENDPOINT,
    DEFAULT_CONTEXT_MESSAGES,
    MIN_TEMPERATURE,
    MAX_TEMPERATURE,
@@ -90,9 +96,19 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
        self._errors = {}

        if user_input is None:
-            default_endpoint = (
-                DEFAULT_OPENAI_ENDPOINT if self._provider == API_PROVIDER_OPENAI
-                else DEFAULT_ANTHROPIC_ENDPOINT
+            # Selecting an endpoint by provider
+            default_endpoint = {
+                API_PROVIDER_OPENAI: DEFAULT_OPENAI_ENDPOINT,
+                API_PROVIDER_ANTHROPIC: DEFAULT_ANTHROPIC_ENDPOINT,
+                API_PROVIDER_DEEPSEEK: DEFAULT_DEEPSEEK_ENDPOINT,
+                API_PROVIDER_GEMINI: DEFAULT_GEMINI_ENDPOINT,
+            }.get(self._provider, DEFAULT_OPENAI_ENDPOINT)
+
+            # Selecting the default model by provider
+            default_model = (
+                DEFAULT_DEEPSEEK_MODEL if self._provider == API_PROVIDER_DEEPSEEK else
+                DEFAULT_GEMINI_MODEL if self._provider == API_PROVIDER_GEMINI else
+                DEFAULT_MODEL
            )

            return self.async_show_form(
@@ -100,7 +116,7 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
                data_schema=vol.Schema({
                    vol.Required(CONF_NAME, default="my_assistant"): str,
                    vol.Required(CONF_API_KEY): str,
-                    vol.Required(CONF_MODEL, default=DEFAULT_MODEL): str,
+                    vol.Required(CONF_MODEL, default=default_model): str,
                    vol.Required(CONF_API_ENDPOINT, default=default_endpoint): str,
                    vol.Optional(CONF_TEMPERATURE, default=DEFAULT_TEMPERATURE): vol.All(
                        vol.Coerce(float),
@@ -156,15 +172,13 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
            if not await self._async_validate_api(input_copy):
                return self.async_show_form(
                    step_id="provider",
-                    data_schema=vol.Schema({
-                    }),
+                    data_schema=vol.Schema({}),
                    errors=self._errors
                )
        except Exception as e:
            return self.async_show_form(
                step_id="provider",
-                data_schema=vol.Schema({
-                }),
+                data_schema=vol.Schema({}),
                errors={"base": str(e)}
            )

@@ -250,6 +264,12 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):

        unique_id = f"{DOMAIN}_{normalized_name}_{self._provider}".lower()

+        default_model = (
+            DEFAULT_DEEPSEEK_MODEL if self._provider == API_PROVIDER_DEEPSEEK else
+            DEFAULT_GEMINI_MODEL if self._provider == API_PROVIDER_GEMINI else
+            DEFAULT_MODEL
+        )
+
        entry_data = {
            CONF_API_PROVIDER: self._provider,
            CONF_NAME: instance_name,
@@ -257,7 +277,7 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
            CONF_API_KEY: user_input.get(CONF_API_KEY),
            CONF_API_ENDPOINT: user_input.get(CONF_API_ENDPOINT),
            "unique_id": unique_id,
-            CONF_MODEL: user_input.get(CONF_MODEL, DEFAULT_MODEL),
+            CONF_MODEL: user_input.get(CONF_MODEL, default_model),
            CONF_TEMPERATURE: user_input.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE),
            CONF_MAX_TOKENS: user_input.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS),
            CONF_REQUEST_INTERVAL: user_input.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL),
@@ -296,13 +316,20 @@ class OptionsFlowHandler(config_entries.OptionsFlow):
            return self.async_create_entry(title="", data=user_input)

        current_data = {**self.config_entry.data, **self.config_entry.options}
+        provider = current_data.get(CONF_API_PROVIDER)
+
+        default_model = (
+            DEFAULT_DEEPSEEK_MODEL if provider == API_PROVIDER_DEEPSEEK else
+            DEFAULT_GEMINI_MODEL if provider == API_PROVIDER_GEMINI else
+            DEFAULT_MODEL
+        )

        return self.async_show_form(
            step_id="init",
            data_schema=vol.Schema({
                vol.Optional(
                    CONF_MODEL,
-                    default=current_data.get(CONF_MODEL, DEFAULT_MODEL)
+                    default=current_data.get(CONF_MODEL, default_model)
                ): str,
                vol.Optional(
                    CONF_TEMPERATURE,
@@ -6,10 +6,14 @@ Constants for the HA text AI integration.
@github: https://github.com/smkrv/ha-text-ai
@source: https://github.com/smkrv/ha-text-ai
 """
+import os
+import json
 from typing import Final
 import voluptuous as vol
 from homeassistant.const import Platform, CONF_API_KEY, CONF_NAME
 from homeassistant.helpers import config_validation as cv
+import logging
+_LOGGER = logging.getLogger(__name__)

 # Domain and platforms
 DOMAIN: Final = "ha_text_ai"
@@ -19,15 +23,37 @@ PLATFORMS: list[str] = ["sensor"]
 CONF_API_PROVIDER: Final = "api_provider"
 API_PROVIDER_OPENAI: Final = "openai"
 API_PROVIDER_ANTHROPIC: Final = "anthropic"
+API_PROVIDER_DEEPSEEK: Final = "deepseek"
+API_PROVIDER_GEMINI: Final = "gemini"

 API_PROVIDERS: Final = [
    API_PROVIDER_OPENAI,
-    API_PROVIDER_ANTHROPIC
+    API_PROVIDER_ANTHROPIC,
+    API_PROVIDER_DEEPSEEK,
+    API_PROVIDER_GEMINI
 ]

+# Read version from manifest.json
+MANIFEST_PATH = os.path.join(os.path.dirname(__file__), "manifest.json")
+try:
+    with open(MANIFEST_PATH) as manifest_file:
+        manifest = json.load(manifest_file)
+        VERSION = manifest.get("version", "unknown")
+except FileNotFoundError:
+    VERSION = "unknown"
+    _LOGGER.warning("manifest.json not found at %s", MANIFEST_PATH)
+except json.JSONDecodeError as err:
+    VERSION = "unknown"
+    _LOGGER.error("Error decoding JSON from manifest.json: %s", err)
+except Exception as err:
+    VERSION = "unknown"
+    _LOGGER.error("Error reading manifest.json: %s", err)
+
 # Default endpoints
 DEFAULT_OPENAI_ENDPOINT: Final = "https://api.openai.com/v1"
 DEFAULT_ANTHROPIC_ENDPOINT: Final = "https://api.anthropic.com"
+DEFAULT_DEEPSEEK_ENDPOINT: Final = "https://api.deepseek.com"
+DEFAULT_GEMINI_ENDPOINT: Final = "https://generativelanguage.googleapis.com/v1beta"

 # Configuration constants
 CONF_MODEL: Final = "model"
@@ -40,8 +66,15 @@ CONF_MAX_HISTORY_SIZE: Final = "max_history_size"  # Correct constant name
 CONF_IS_ANTHROPIC: Final = "is_anthropic"
 CONF_CONTEXT_MESSAGES: Final = "context_messages"

+ABSOLUTE_MAX_HISTORY_SIZE = 500
+MAX_ATTRIBUTE_SIZE = 4 * 1024
+MAX_HISTORY_FILE_SIZE = 1 * 1024 * 1024
+ICONS_SUBDOMAIN = "icons"
+
 # Default values
 DEFAULT_MODEL: Final = "gpt-4o-mini"
+DEFAULT_DEEPSEEK_MODEL: Final = "deepseek-chat"
+DEFAULT_GEMINI_MODEL: Final = "gemini-pro"
 DEFAULT_TEMPERATURE: Final = 0.1
 DEFAULT_MAX_TOKENS: Final = 1000
 DEFAULT_REQUEST_INTERVAL: Final = 1.0
@@ -51,11 +84,13 @@ DEFAULT_NAME: Final = "HA Text AI"
 DEFAULT_NAME_PREFIX = "ha_text_ai"
 DEFAULT_CONTEXT_MESSAGES: Final = 5

+TRUNCATION_INDICATOR = " ... "
+
 # Parameter constraints
 MIN_TEMPERATURE: Final = 0.0
 MAX_TEMPERATURE: Final = 2.0
 MIN_MAX_TOKENS: Final = 1
-MAX_MAX_TOKENS: Final = 4096
+MAX_MAX_TOKENS: Final = 100000
 MIN_REQUEST_INTERVAL: Final = 0.1
 MAX_REQUEST_INTERVAL: Final = 60.0

@@ -13,16 +13,17 @@
  "loggers": ["custom_components.ha_text_ai"],
  "mqtt": [],
  "quality_scale": "silver",
-  "requirements": [
-    "openai>=1.12.0",
-    "anthropic>=0.8.0",
-    "aiohttp>=3.8.0",
-    "async-timeout>=4.0.0",
-    "certifi>=2024.2.2"
-  ],
+    "requirements": [
+      "openai>=1.12.0",
+      "anthropic>=0.8.0",
+      "google-generativeai>=0.3.0",
+      "aiohttp>=3.8.0",
+      "async-timeout>=4.0.0",
+      "certifi>=2024.2.2"
+    ],
  "single_config_entry": false,
  "ssdp": [],
  "usb": [],
-  "version": "2.0.4-beta",
+  "version": "2.1.6",
  "zeroconf": []
 }
@@ -67,6 +67,8 @@ from .const import (
    ENTITY_ICON_PROCESSING,
    DEFAULT_NAME_PREFIX,
    CONF_MAX_HISTORY_SIZE,
+    MAX_ATTRIBUTE_SIZE,
+    VERSION,
 )

 from .coordinator import HATextAICoordinator
@@ -153,7 +155,7 @@ class HATextAISensor(CoordinatorEntity, SensorEntity):
            name=self._attr_name,
            manufacturer="Community",
            model=f"{model} ({api_provider} provider)",
-            sw_version="1.0.0",
+            sw_version=VERSION,
        )

        _LOGGER.debug(
@@ -178,12 +180,29 @@ class HATextAISensor(CoordinatorEntity, SensorEntity):

    def _sanitize_attributes(self, attributes: Dict[str, Any]) -> Dict[str, Any]:
        """Sanitize all attributes for JSON serialization."""
-        return {
+        sanitized = {
            key: self._sanitize_value(value)
            for key, value in attributes.items()
            if value is not None
        }

+        # Log metrics for debugging
+        metrics_keys = [
+            METRIC_TOTAL_TOKENS,
+            METRIC_PROMPT_TOKENS,
+            METRIC_COMPLETION_TOKENS,
+            METRIC_SUCCESSFUL_REQUESTS,
+            METRIC_FAILED_REQUESTS,
+            METRIC_AVERAGE_LATENCY,
+            METRIC_MAX_LATENCY,
+            METRIC_MIN_LATENCY,
+        ]
+
+        metrics_values = {k: sanitized.get(k) for k in metrics_keys if k in sanitized}
+        _LOGGER.debug(f"Metrics for {self.entity_id}: {metrics_values}")
+
+        return sanitized
+
    @property
    def native_value(self) -> StateType:
        """Return the native value of the sensor."""
@@ -212,68 +231,65 @@ class HATextAISensor(CoordinatorEntity, SensorEntity):

        try:
            data = self.coordinator.data
+            metrics = data.get("metrics", {})
+
+            # Base attributes
            attributes = {
                ATTR_MODEL: self._config_entry.data.get(CONF_MODEL, "Unknown"),
-                ATTR_API_PROVIDER: self._config_entry.data.get(
-                    CONF_API_PROVIDER, "Unknown"
-                ),
+                ATTR_API_PROVIDER: self._config_entry.data.get(CONF_API_PROVIDER, "Unknown"),
                ATTR_API_STATUS: self._current_state,
-                ATTR_TOTAL_ERRORS: self._error_count,
-                ATTR_LAST_ERROR: self._last_error,
+                ATTR_TOTAL_ERRORS: metrics.get("total_errors", 0),
                "instance_name": self._instance_name,
                "normalized_name": self._normalized_name,
-                ATTR_SYSTEM_PROMPT: data.get("system_prompt"),
+                ATTR_SYSTEM_PROMPT: (data.get("system_prompt", "")[:MAX_ATTRIBUTE_SIZE]
+                                   if data.get("system_prompt") else None),
                ATTR_IS_PROCESSING: data.get("is_processing", False),
                ATTR_IS_RATE_LIMITED: data.get("is_rate_limited", False),
                ATTR_IS_MAINTENANCE: data.get("is_maintenance", False),
                ATTR_ENDPOINT_STATUS: data.get("endpoint_status", "unknown"),
-                ATTR_UPTIME: data.get("uptime", 0),
+                ATTR_UPTIME: round(data.get("uptime", 0), 2),
                ATTR_HISTORY_SIZE: data.get("history_size", 0),
-                ATTR_CONVERSATION_HISTORY: data.get("conversation_history", []),
            }

-            # Add metrics
-            metrics = data.get("metrics", {})
-            if isinstance(metrics, dict):
-                self._metrics = metrics
-                attributes.update(
-                    {
-                        METRIC_TOTAL_TOKENS: metrics.get("total_tokens", 0),
-                        METRIC_PROMPT_TOKENS: metrics.get("prompt_tokens", 0),
-                        METRIC_COMPLETION_TOKENS: metrics.get("completion_tokens", 0),
-                        METRIC_SUCCESSFUL_REQUESTS: metrics.get(
-                            "successful_requests", 0
-                        ),
-                        METRIC_FAILED_REQUESTS: metrics.get("failed_requests", 0),
-                        METRIC_AVERAGE_LATENCY: metrics.get("average_latency", 0),
-                        METRIC_MAX_LATENCY: metrics.get("max_latency", 0),
-                        METRIC_MIN_LATENCY: metrics.get("min_latency", float("inf")),
+            # History limit
+            conversation_history = data.get("conversation_history", [])
+            if conversation_history:
+                limited_history = []
+                for entry in conversation_history:
+                    limited_entry = {
+                        "timestamp": entry["timestamp"],
+                        "question": entry["question"][:MAX_ATTRIBUTE_SIZE],
+                        "response": entry["response"][:MAX_ATTRIBUTE_SIZE]
                    }
-                )
+                    limited_history.append(limited_entry)
+                attributes[ATTR_CONVERSATION_HISTORY] = limited_history

-            # Add last response
+            # Metrics
+            if isinstance(metrics, dict):
+                attributes.update({
+                    METRIC_TOTAL_TOKENS: metrics.get("total_tokens", 0),
+                    METRIC_PROMPT_TOKENS: metrics.get("prompt_tokens", 0),
+                    METRIC_COMPLETION_TOKENS: metrics.get("completion_tokens", 0),
+                    METRIC_SUCCESSFUL_REQUESTS: metrics.get("successful_requests", 0),
+                    METRIC_FAILED_REQUESTS: metrics.get("failed_requests", 0),
+                    METRIC_AVERAGE_LATENCY: round(metrics.get("average_latency", 0), 2),
+                    METRIC_MAX_LATENCY: round(metrics.get("max_latency", 0), 2),
+                    METRIC_MIN_LATENCY: (metrics.get("min_latency")
+                                       if metrics.get("min_latency") != float("inf")
+                                       else None),
+                })
+
+            # Last response handling
            last_response = data.get("last_response", {})
            if isinstance(last_response, dict):
-                self._last_response = last_response
-                attributes.update(
-                    {
-                        ATTR_RESPONSE: last_response.get("response", ""),
-                        ATTR_QUESTION: last_response.get("question", ""),
-                        "last_model": last_response.get("model", ""),
-                        "last_timestamp": last_response.get("timestamp", ""),
-                        "last_error": last_response.get("error"),
-                    }
-                )
-
-            # Add performance metrics if available
-            if ATTR_PERFORMANCE_METRICS in data:
-                attributes[ATTR_PERFORMANCE_METRICS] = data[
-                    ATTR_PERFORMANCE_METRICS
-                ]
-
-            # Add API version if available
-            if ATTR_API_VERSION in data:
-                attributes[ATTR_API_VERSION] = data[ATTR_API_VERSION]
+                attributes.update({
+                    ATTR_RESPONSE: last_response.get("response", "")[:MAX_ATTRIBUTE_SIZE],
+                    ATTR_QUESTION: last_response.get("question", "")[:MAX_ATTRIBUTE_SIZE],
+                    "last_model": last_response.get("model", ""),
+                    "last_timestamp": last_response.get("timestamp", ""),
+                    "last_error": (last_response.get("error", "")[:MAX_ATTRIBUTE_SIZE]
+                                 if last_response.get("error") else None),
+                })

            return self._sanitize_attributes(attributes)

@@ -299,6 +315,12 @@ class HATextAISensor(CoordinatorEntity, SensorEntity):

            self._is_processing = data.get("is_processing", False)

+            # Update metrics
+            metrics = data.get("metrics", {})
+            if isinstance(metrics, dict):
+                self._metrics.update(metrics)
+                _LOGGER.debug(f"Updated metrics for {self.entity_id}: {self._metrics}")
+
            # Update conversation history and system prompt
            self._conversation_history = data.get("conversation_history", [])
            self._system_prompt = data.get("system_prompt")
@@ -63,13 +63,13 @@ ask_question:

    max_tokens:
      name: Max Tokens
-      description: Maximum length of the response (1-4096 tokens)
+      description: Maximum length of the response (tokens)
      required: false
      default: 1000
      selector:
        number:
          min: 1
-          max: 4096
+          max: 100000
          step: 1
          mode: box

@@ -2,71 +2,103 @@
  "config": {
    "step": {
      "provider": {
-        "title": "KI-Anbieter auswählen",
-        "description": "Wählen Sie den KI-Dienstanbieter für diese Instanz aus.",
+        "title": "Wählen Sie AI-Anbieter",
+        "description": "Wählen Sie, welchen AI-Dienstanbieter Sie für diese Instanz verwenden möchten.",
        "data": {
          "api_provider": "API-Anbieter",
-          "context_messages": "Anzahl der zu behaltenden Kontextnachrichten (1-20)"
+          "context_messages": "Anzahl der zu behaltenden Kontextnachrichten (1-20)",
+          "max_history_size": "Maximale Größe des Gesprächsverlaufs (1-100)"
+        }
+      },
+      "provider": {
+        "title": "Anbieter-Einstellungen",
+        "description": "Geben Sie die Verbindungsdetails für Ihren gewählten AI-Anbieter an.",
+        "data": {
+          "name": "Instanzname (z. B. 'GPT Assistant', 'Claude Helper')",
+          "api_key": "API-Schlüssel zur Authentifizierung",
+          "model": "Zu verwendendes AI-Modell",
+          "api_endpoint": "Benutzerdefinierte API-Endpunkt-URL (optional)",
+          "temperature": "Kreativität der Antwort (0-2, niedriger = fokussierter)",
+          "max_tokens": "Maximale Länge der Antwort (1-100000 Token)",
+          "request_interval": "Minimale Zeit zwischen Anfragen (0,1-60 Sekunden)",
+          "context_messages": "Anzahl der zu behaltenden Kontextnachrichten (1-20)",
+          "max_history_size": "Maximale Größe des Gesprächsverlaufs (1-100)"
        }
      },
      "user": {
-        "title": "HA Text AI-Instanz konfigurieren",
-        "description": "Richten Sie eine neue KI-Assistenteninstanz mit Ihrem ausgewählten Anbieter ein.",
+        "title": "HA Text AI Instanz konfigurieren",
+        "description": "Richten Sie eine neue AI-Assistenteninstanz mit Ihrem ausgewählten Anbieter ein.",
        "data": {
-          "name": "Instanzname (z. B. 'GPT-Assistent', 'Claude-Helfer')",
+          "name": "Instanzname (z. B. 'GPT Assistant', 'Claude Helper')",
          "api_key": "API-Schlüssel zur Authentifizierung",
-          "model": "Zu verwendendes KI-Modell",
-          "temperature": "Antwortkreativität (0-2, niedriger = fokussierter)",
-          "max_tokens": "Maximale Antwortlänge (1-4096 Token)",
+          "model": "Zu verwendendes AI-Modell",
+          "temperature": "Kreativität der Antwort (0-2, niedriger = fokussierter)",
+          "max_tokens": "Maximale Länge der Antwort (1-100000 Token)",
          "api_endpoint": "Benutzerdefinierte API-Endpunkt-URL (optional)",
          "api_provider": "API-Anbieter",
-          "request_interval": "Mindestzeit zwischen Anfragen (0,1-60 Sekunden)",
+          "request_interval": "Minimale Zeit zwischen Anfragen (0,1-60 Sekunden)",
          "context_messages": "Anzahl der zu behaltenden Kontextnachrichten (1-20)",
-          "max_history_size": "Maximale Größe des Konversationsverlaufs (1-100)"
+          "max_history_size": "Maximale Größe des Gesprächsverlaufs (1-100)"
        }
      }
    },
    "error": {
+      "history_storage_error": "Fehler beim Initialisieren des Verlaufspeichers. Überprüfen Sie die Berechtigungen.",
+      "history_rotation_error": "Fehler beim Drehen der Verlaufsdatei.",
+      "history_file_access_error": "Zugriff auf das Verzeichnis für den Verlaufsspeicher nicht möglich.",
      "name_exists": "Eine Instanz mit diesem Namen existiert bereits",
      "invalid_name": "Ungültiger Instanzname",
      "invalid_auth": "Authentifizierung fehlgeschlagen - überprüfen Sie Ihren API-Schlüssel",
-      "invalid_api_key": "Ungültiger API-Schlüssel - überprüfen Sie Ihre Anmeldedaten",
+      "invalid_api_key": "Ungültiger API-Schlüssel - bitte überprüfen Sie Ihre Anmeldeinformationen",
      "cannot_connect": "Verbindung zum API-Dienst fehlgeschlagen",
-      "invalid_model": "Das ausgewählte Modell ist nicht verfügbar",
-      "rate_limit": "Ratenlimit überschritten",
+      "invalid_model": "Ausgewähltes Modell ist nicht verfügbar",
+      "rate_limit": "Rate-Limit überschritten",
      "context_length": "Kontextlänge überschritten",
-      "rate_limit_exceeded": "API-Ratenlimit überschritten",
-      "maintenance": "Dienst befindet sich in der Wartung",
-      "invalid_response": "Ungültige API-Antwort empfangen",
-      "api_error": "Fehler im API-Dienst aufgetreten",
-      "timeout": "Anfrage ist abgelaufen",
+      "rate_limit_exceeded": "API-Rate-Limit überschritten",
+      "maintenance": "Dienst ist in Wartung",
+      "invalid_response": "Ungültige API-Antwort erhalten",
+      "api_error": "Ein Fehler im API-Dienst ist aufgetreten",
+      "timeout": "Zeitüberschreitung bei der Anfrage",
      "invalid_instance": "Ungültige Instanz angegeben",
-      "unknown": "Es ist ein unerwarteter Fehler aufgetreten",
+      "unknown": "Unerwarteter Fehler aufgetreten",
      "empty": "Name darf nicht leer sein",
      "invalid_characters": "Name darf nur Buchstaben, Zahlen, Leerzeichen, Unterstriche und Bindestriche enthalten",
-      "name_too_long": "Name darf maximal 50 Zeichen lang sein"
+      "name_too_long": "Name darf höchstens 50 Zeichen lang sein"
+    },
+    "abort": {
+      "already_configured": "Instanz bereits konfiguriert"
    }
  },
  "options": {
    "step": {
      "init": {
        "title": "Instanzeinstellungen aktualisieren",
-        "description": "Ändern Sie die Einstellungen für diese KI-Assistenteninstanz.",
+        "description": "Ändern Sie die Einstellungen für diese AI-Assistenteninstanz.",
        "data": {
-          "model": "KI-Modell",
-          "temperature": "Antwortkreativität (0-2)",
-          "max_tokens": "Maximale Antwortlänge (1-4096)",
-          "request_interval": "Mindestzeitraum zwischen Anfragen (0,1-60 Sekunden)",
+          "model": "AI-Modell",
+          "temperature": "Kreativität der Antwort (0-2)",
+          "max_tokens": "Maximale Länge der Antwort (1-100000)",
+          "request_interval": "Minimale Anfrageintervall (0,1-60 Sekunden)",
          "context_messages": "Anzahl der vorherigen Nachrichten, die im Kontext enthalten sein sollen (1-20)",
-          "max_history_size": "Maximale Größe des Konversationsverlaufs (1-100)"
+          "max_history_size": "Maximale Größe des Gesprächsverlaufs (1-100)"
        }
      }
    }
  },
+  "selector": {
+    "api_provider": {
+      "options": {
+        "openai": "OpenAI (compatible)",
+        "anthropic": "Anthropic (compatible)",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
+    }
+  }
+},
  "services": {
    "ask_question": {
      "name": "Frage stellen (HA Text AI)",
-      "description": "Senden Sie eine Frage an das KI-Modell und erhalten Sie eine detaillierte Antwort. Die Antwort wird im Konversationsverlauf gespeichert und kann später abgerufen werden.",
+      "description": "Stellen Sie eine Frage an das AI-Modell und erhalten Sie eine detaillierte Antwort. Die Antwort wird im Gesprächsverlauf gespeichert und kann später abgerufen werden.",
      "fields": {
        "instance": {
          "name": "Instanz",
@@ -74,43 +106,43 @@
        },
        "question": {
          "name": "Frage",
-          "description": "Ihre Frage oder Aufforderung an den KI-Assistenten"
+          "description": "Ihre Frage oder Aufforderung für den AI-Assistenten"
        },
        "context_messages": {
          "name": "Kontextnachrichten",
          "description": "Anzahl der vorherigen Nachrichten, die im Kontext enthalten sein sollen (1-20)"
        },
        "system_prompt": {
-          "name": "Systemprompt",
-          "description": "Optionaler Systemprompt, um den Kontext für diese spezielle Frage festzulegen"
+          "name": "Systemaufforderung",
+          "description": "Optionale Systemaufforderung zur Festlegung des Kontexts für diese spezifische Frage"
        },
        "model": {
          "name": "Modell",
-          "description": "Wählen Sie das zu verwendende KI-Modell aus (optional, überschreibt die Standardeinstellung)"
+          "description": "Wählen Sie das zu verwendende AI-Modell (optional, überschreibt die Standardeinstellung)"
        },
        "temperature": {
          "name": "Temperatur",
-          "description": "Steuert die Antwortkreativität (0.0-2.0)"
+          "description": "Steuert die Kreativität der Antwort (0,0-2,0)"
        },
        "max_tokens": {
-          "name": "Max. Token",
-          "description": "Maximale Länge der Antwort (1-4096 Token)"
+          "name": "Max Tokens",
+          "description": "Maximale Länge der Antwort (1-100000 Token)"
        }
      }
    },
    "clear_history": {
      "name": "Verlauf löschen",
-      "description": "Alle gespeicherten Fragen und Antworten aus dem Konversationsverlauf löschen",
+      "description": "Löschen Sie alle gespeicherten Fragen und Antworten aus dem Gesprächsverlauf",
      "fields": {
        "instance": {
          "name": "Instanz",
-          "description": "Name der HA Text AI-Instanz, deren Verlauf gelöscht werden soll"
+          "description": "Name der HA Text AI-Instanz, für die der Verlauf gelöscht werden soll"
        }
      }
    },
    "get_history": {
      "name": "Verlauf abrufen",
-      "description": "Konversationsverlauf mit optionalem Filtern und Sortieren abrufen",
+      "description": "Rufen Sie den Gesprächsverlauf mit optionaler Filterung und Sortierung ab",
      "fields": {
        "instance": {
          "name": "Instanz",
@@ -118,19 +150,19 @@
        },
        "limit": {
          "name": "Limit",
-          "description": "Anzahl der zurückzugebenden Konversationen (1-100)"
+          "description": "Anzahl der zurückzugebenden Gespräche (1-100)"
        },
        "filter_model": {
          "name": "Modell filtern",
-          "description": "Konversationen nach einem bestimmten KI-Modell filtern"
+          "description": "Gespräche nach spezifischem AI-Modell filtern"
        },
        "start_date": {
          "name": "Startdatum",
-          "description": "Konversationen ab diesem Datum/Uhrzeit filtern"
+          "description": "Gespräche ab diesem Datum/Zeit filtern"
        },
        "include_metadata": {
-          "name": "Metadaten einschließen",
-          "description": "Zusätzliche Informationen wie verwendete Token, Antwortzeit usw. einschließen"
+          "name": "Metadaten einbeziehen",
+          "description": "Zusätzliche Informationen wie verwendete Tokens, Antwortzeit usw. einbeziehen"
        },
        "sort_order": {
          "name": "Sortierreihenfolge",
@@ -139,16 +171,16 @@
      }
    },
    "set_system_prompt": {
-      "name": "Systemprompt festlegen",
-      "description": "Legen Sie Standardanweisungen für das Systemverhalten für alle zukünftigen Konversationen fest",
+      "name": "Systemaufforderung festlegen",
+      "description": "Standardverhaltensanweisungen für alle zukünftigen Gespräche festlegen",
      "fields": {
        "instance": {
          "name": "Instanz",
-          "description": "Name der HA Text AI-Instanz, für die der Systemprompt festgelegt werden soll"
+          "description": "Name der HA Text AI-Instanz, für die die Systemaufforderung festgelegt werden soll"
        },
        "prompt": {
-          "name": "Systemprompt",
-          "description": "Anweisungen, die definieren, wie sich die KI verhalten und antworten soll"
+          "name": "Systemaufforderung",
+          "description": "Anweisungen, die definieren, wie die AI sich verhalten und antworten soll"
        }
      }
    }
@@ -162,11 +194,11 @@
          "processing": "Verarbeitung",
          "error": "Fehler",
          "disconnected": "Getrennt",
-          "rate_limited": "Ratenlimit",
+          "rate_limited": "Rate limitiert",
          "maintenance": "Wartung",
          "initializing": "Initialisierung",
          "retrying": "Wiederholen",
-          "queued": "Warteschlange"
+          "queued": "In der Warteschlange"
        },
        "state_attributes": {
          "question": {
@@ -182,16 +214,16 @@
            "name": "Temperatur"
          },
          "max_tokens": {
-            "name": "Max. Token"
+            "name": "Max Tokens"
          },
          "system_prompt": {
-            "name": "Systemprompt"
+            "name": "Systemaufforderung"
          },
          "response_time": {
            "name": "Letzte Antwortzeit"
          },
          "total_responses": {
-            "name": "Gesamtzahl der Antworten"
+            "name": "Gesamtantworten"
          },
          "error_count": {
            "name": "Fehleranzahl"
@@ -203,19 +235,19 @@
            "name": "API-Status"
          },
          "tokens_used": {
-            "name": "Verwendete Token insgesamt"
+            "name": "Gesamte verwendete Tokens"
          },
          "average_response_time": {
            "name": "Durchschnittliche Antwortzeit"
          },
          "last_request_time": {
-            "name": "Zeitpunkt der letzten Anfrage"
+            "name": "Letzte Anfragezeit"
          },
          "is_processing": {
            "name": "Verarbeitungsstatus"
          },
          "is_rate_limited": {
-            "name": "Ratenlimit-Status"
+            "name": "Rate-limitiert Status"
          },
          "is_maintenance": {
            "name": "Wartungsstatus"
@@ -224,25 +256,25 @@
            "name": "API-Version"
          },
          "endpoint_status": {
-            "name": "Endpunkt-Status"
+            "name": "Endpunktstatus"
          },
          "performance_metrics": {
-            "name": "Leistungsmetriken"
+            "name": "Leistungskennzahlen"
          },
          "history_size": {
-            "name": "Verlaufsgröße"
+            "name": "Größe des Verlaufs"
          },
          "uptime": {
            "name": "Betriebszeit"
          },
          "total_tokens": {
-            "name": "Gesamtzahl der Token"
+            "name": "Gesamte Tokens"
          },
          "prompt_tokens": {
-            "name": "Prompt-Token"
+            "name": "Eingabe Tokens"
          },
          "completion_tokens": {
-            "name": "Completion-Token"
+            "name": "Vervollständigungs Tokens"
          },
          "successful_requests": {
            "name": "Erfolgreiche Anfragen"
@@ -6,7 +6,23 @@
        "description": "Choose which AI service provider to use for this instance.",
        "data": {
          "api_provider": "API Provider",
-          "context_messages": "Number of context messages to retain (1-20)"
+          "context_messages": "Number of context messages to retain (1-20)",
+          "max_history_size": "Maximum conversation history size (1-100)"
+        }
+      },
+      "provider": {
+        "title": "Provider Settings",
+        "description": "Provide connection details for your chosen AI provider.",
+        "data": {
+          "name": "Instance name (e.g., 'GPT Assistant', 'Claude Helper')",
+          "api_key": "API key for authentication",
+          "model": "AI model to use",
+          "api_endpoint": "Custom API endpoint URL (optional)",
+          "temperature": "Response creativity (0-2, lower = more focused)",
+          "max_tokens": "Maximum response length (1-100000 tokens)",
+          "request_interval": "Minimum time between requests (0.1-60 seconds)",
+          "context_messages": "Number of context messages to retain (1-20)",
+          "max_history_size": "Maximum conversation history size (1-100)"
        }
      },
      "user": {
@@ -17,7 +33,7 @@
          "api_key": "API key for authentication",
          "model": "AI model to use",
          "temperature": "Response creativity (0-2, lower = more focused)",
-          "max_tokens": "Maximum response length (1-4096 tokens)",
+          "max_tokens": "Maximum response length (1-100000 tokens)",
          "api_endpoint": "Custom API endpoint URL (optional)",
          "api_provider": "API Provider",
          "request_interval": "Minimum time between requests (0.1-60 seconds)",
@@ -27,6 +43,9 @@
      }
    },
    "error": {
+      "history_storage_error": "Failed to initialize history storage. Check permissions.",
+      "history_rotation_error": "Error during history file rotation.",
+      "history_file_access_error": "Cannot access history storage directory.",
      "name_exists": "An instance with this name already exists",
      "invalid_name": "Invalid instance name",
      "invalid_auth": "Authentication failed - check your API key",
@@ -45,6 +64,9 @@
      "empty": "Name cannot be empty",
      "invalid_characters": "Name can only contain letters, numbers, spaces, underscores and hyphens",
      "name_too_long": "Name must be 50 characters or less"
+    },
+    "abort": {
+      "already_configured": "Instance already configured"
    }
  },
  "options": {
@@ -55,7 +77,7 @@
        "data": {
          "model": "AI model",
          "temperature": "Response creativity (0-2)",
-          "max_tokens": "Maximum response length (1-4096)",
+          "max_tokens": "Maximum response length (1-100000)",
          "request_interval": "Minimum request interval (0.1-60 seconds)",
          "context_messages": "Number of previous messages to include in context (1-20)",
          "max_history_size": "Maximum conversation history size (1-100)"
@@ -63,6 +85,16 @@
      }
    }
  },
+  "selector": {
+    "api_provider": {
+      "options": {
+        "openai": "OpenAI (compatible)",
+        "anthropic": "Anthropic (compatible)",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
+    }
+  }
+},
  "services": {
    "ask_question": {
      "name": "Ask Question (HA Text AI)",
@@ -94,7 +126,7 @@
        },
        "max_tokens": {
          "name": "Max Tokens",
-          "description": "Maximum length of the response (1-4096 tokens)"
+          "description": "Maximum length of the response (1-100000 tokens)"
        }
      }
    },
@@ -3,151 +3,183 @@
    "step": {
      "provider": {
        "title": "Seleccionar proveedor de IA",
-        "description": "Elige qué proveedor de servicios de IA usar para esta instancia.",
+        "description": "Elige qué proveedor de servicio de IA utilizar para esta instancia.",
        "data": {
          "api_provider": "Proveedor de API",
-          "context_messages": "Número de mensajes de contexto que conservar (1-20)"
+          "context_messages": "Número de mensajes de contexto a retener (1-20)",
+          "max_history_size": "Tamaño máximo del historial de conversación (1-100)"
+        }
+      },
+      "provider": {
+        "title": "Configuración del proveedor",
+        "description": "Proporciona los detalles de conexión para tu proveedor de IA elegido.",
+        "data": {
+          "name": "Nombre de la instancia (por ejemplo, 'Asistente GPT', 'Ayudante Claude')",
+          "api_key": "Clave API para autenticación",
+          "model": "Modelo de IA a utilizar",
+          "api_endpoint": "URL del endpoint de API personalizado (opcional)",
+          "temperature": "Creatividad de la respuesta (0-2, menor = más enfocado)",
+          "max_tokens": "Longitud máxima de la respuesta (1-100000 tokens)",
+          "request_interval": "Tiempo mínimo entre solicitudes (0.1-60 segundos)",
+          "context_messages": "Número de mensajes de contexto a retener (1-20)",
+          "max_history_size": "Tamaño máximo del historial de conversación (1-100)"
        }
      },
      "user": {
-        "title": "Configurar instancia de HA Text AI",
-        "description": "Configura una nueva instancia de asistente de IA con el proveedor seleccionado.",
+        "title": "Configurar instancia de IA de texto de HA",
+        "description": "Configura una nueva instancia de asistente de IA con tu proveedor seleccionado.",
        "data": {
-          "name": "Nombre de la instancia (p. ej., 'Asistente GPT', 'Ayudante de Claude')",
-          "api_key": "Clave API para la autenticación",
-          "model": "Modelo de IA a usar",
-          "temperature": "Creatividad de la respuesta (0-2, cuanto menor, más enfocada)",
-          "max_tokens": "Longitud máxima de la respuesta (1-4096 tokens)",
-          "api_endpoint": "URL del punto final de la API personalizada (opcional)",
+          "name": "Nombre de la instancia (por ejemplo, 'Asistente GPT', 'Ayudante Claude')",
+          "api_key": "Clave API para autenticación",
+          "model": "Modelo de IA a utilizar",
+          "temperature": "Creatividad de la respuesta (0-2, menor = más enfocado)",
+          "max_tokens": "Longitud máxima de la respuesta (1-100000 tokens)",
+          "api_endpoint": "URL del endpoint de API personalizado (opcional)",
          "api_provider": "Proveedor de API",
-          "request_interval": "Tiempo mínimo entre solicitudes (0,1-60 segundos)",
-          "context_messages": "Número de mensajes de contexto que conservar (1-20)",
+          "request_interval": "Tiempo mínimo entre solicitudes (0.1-60 segundos)",
+          "context_messages": "Número de mensajes de contexto a retener (1-20)",
          "max_history_size": "Tamaño máximo del historial de conversación (1-100)"
        }
      }
    },
    "error": {
+      "history_storage_error": "Error al inicializar el almacenamiento del historial. Verifica los permisos.",
+      "history_rotation_error": "Error durante la rotación del archivo de historial.",
+      "history_file_access_error": "No se puede acceder al directorio de almacenamiento del historial.",
      "name_exists": "Ya existe una instancia con este nombre",
      "invalid_name": "Nombre de instancia no válido",
-      "invalid_auth": "Error de autenticación: comprueba tu clave API",
-      "invalid_api_key": "Clave API no válida: verifica tus credenciales",
-      "cannot_connect": "No se pudo conectar al servicio API",
+      "invalid_auth": "La autenticación falló - verifica tu clave API",
+      "invalid_api_key": "Clave API no válida - verifica tus credenciales",
+      "cannot_connect": "Error al conectar con el servicio de API",
      "invalid_model": "El modelo seleccionado no está disponible",
      "rate_limit": "Límite de tasa excedido",
-      "context_length": "Longitud de contexto excedida",
+      "context_length": "Longitud del contexto excedida",
      "rate_limit_exceeded": "Límite de tasa de API excedido",
      "maintenance": "El servicio está en mantenimiento",
-      "invalid_response": "Se recibió una respuesta de API no válida",
-      "api_error": "Se produjo un error en el servicio API",
-      "timeout": "Tiempo de espera de la solicitud agotado",
-      "invalid_instance": "Instancia especificada no válida",
-      "unknown": "Se produjo un error inesperado",
+      "invalid_response": "Respuesta de API no válida recibida",
+      "api_error": "Ocurrió un error en el servicio de API",
+      "timeout": "Se agotó el tiempo de la solicitud",
+      "invalid_instance": "Instancia no válida especificada",
+      "unknown": "Ocurrió un error inesperado",
      "empty": "El nombre no puede estar vacío",
      "invalid_characters": "El nombre solo puede contener letras, números, espacios, guiones bajos y guiones",
      "name_too_long": "El nombre debe tener 50 caracteres o menos"
+    },
+    "abort": {
+      "already_configured": "Instancia ya configurada"
    }
  },
  "options": {
    "step": {
      "init": {
        "title": "Actualizar configuración de la instancia",
-        "description": "Modifica la configuración de esta instancia de asistente de IA.",
+        "description": "Modifica la configuración para esta instancia de asistente de IA.",
        "data": {
          "model": "Modelo de IA",
          "temperature": "Creatividad de la respuesta (0-2)",
-          "max_tokens": "Longitud máxima de la respuesta (1-4096)",
-          "request_interval": "Intervalo mínimo de solicitud (0,1-60 segundos)",
-          "context_messages": "Número de mensajes anteriores que se incluirán en el contexto (1-20)",
+          "max_tokens": "Longitud máxima de la respuesta (1-100000)",
+          "request_interval": "Intervalo mínimo de solicitud (0.1-60 segundos)",
+          "context_messages": "Número de mensajes anteriores a incluir en el contexto (1-20)",
          "max_history_size": "Tamaño máximo del historial de conversación (1-100)"
        }
      }
    }
  },
+  "selector": {
+    "api_provider": {
+      "options": {
+        "openai": "OpenAI (compatible)",
+        "anthropic": "Anthropic (compatible)",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
+    }
+  }
+},
  "services": {
    "ask_question": {
-      "name": "Hacer pregunta (HA Text AI)",
+      "name": "Hacer Pregunta (HA Text AI)",
      "description": "Envía una pregunta al modelo de IA y recibe una respuesta detallada. La respuesta se almacenará en el historial de conversación y se podrá recuperar más tarde.",
      "fields": {
        "instance": {
          "name": "Instancia",
-          "description": "Nombre de la instancia de HA Text AI a utilizar"
+          "description": "Nombre de la instancia de IA de Texto de HA a utilizar"
        },
        "question": {
          "name": "Pregunta",
-          "description": "Tu pregunta o indicación para el asistente de IA"
+          "description": "Tu pregunta o solicitud para el asistente de IA"
        },
        "context_messages": {
-          "name": "Mensajes de contexto",
-          "description": "Número de mensajes anteriores que se incluirán en el contexto (1-20)"
+          "name": "Mensajes de Contexto",
+          "description": "Número de mensajes anteriores a incluir en el contexto (1-20)"
        },
        "system_prompt": {
-          "name": "Indicación del sistema",
-          "description": "Indicación del sistema opcional para establecer el contexto de esta pregunta específica"
+          "name": "Indicaciones del Sistema",
+          "description": "Indicaciones opcionales para establecer contexto para esta pregunta específica"
        },
        "model": {
          "name": "Modelo",
-          "description": "Selecciona el modelo de IA que se va a utilizar (opcional, anula la configuración predeterminada)"
+          "description": "Selecciona el modelo de IA a utilizar (opcional, anula la configuración predeterminada)"
        },
        "temperature": {
          "name": "Temperatura",
          "description": "Controla la creatividad de la respuesta (0.0-2.0)"
        },
        "max_tokens": {
-          "name": "Máx. tokens",
-          "description": "Longitud máxima de la respuesta (1-4096 tokens)"
+          "name": "Máx. Tokens",
+          "description": "Longitud máxima de la respuesta (1-100000 tokens)"
        }
      }
    },
    "clear_history": {
-      "name": "Borrar historial",
+      "name": "Borrar Historial",
      "description": "Elimina todas las preguntas y respuestas almacenadas del historial de conversación",
      "fields": {
        "instance": {
          "name": "Instancia",
-          "description": "Nombre de la instancia de HA Text AI para la que se va a borrar el historial"
+          "description": "Nombre de la instancia de IA de Texto de HA para borrar el historial"
        }
      }
    },
    "get_history": {
-      "name": "Obtener historial",
-      "description": "Recupera el historial de conversaciones con filtrado y ordenación opcionales",
+      "name": "Obtener Historial",
+      "description": "Recupera el historial de conversación con filtrado y ordenación opcionales",
      "fields": {
        "instance": {
          "name": "Instancia",
-          "description": "Nombre de la instancia de HA Text AI de la que se va a obtener el historial"
+          "description": "Nombre de la instancia de IA de Texto de HA para obtener historial"
        },
        "limit": {
          "name": "Límite",
-          "description": "Número de conversaciones que se van a devolver (1-100)"
+          "description": "Número de conversaciones a devolver (1-100)"
        },
        "filter_model": {
-          "name": "Filtrar modelo",
-          "description": "Filtra las conversaciones por un modelo de IA específico"
+          "name": "Filtrar Modelo",
+          "description": "Filtrar conversaciones por modelo de IA específico"
        },
        "start_date": {
-          "name": "Fecha de inicio",
-          "description": "Filtra las conversaciones a partir de esta fecha/hora"
+          "name": "Fecha de Inicio",
+          "description": "Filtrar conversaciones a partir de esta fecha/hora"
        },
        "include_metadata": {
-          "name": "Incluir metadatos",
-          "description": "Incluir información adicional como los tokens utilizados, el tiempo de respuesta, etc."
+          "name": "Incluir Metadatos",
+          "description": "Incluir información adicional como tokens utilizados, tiempo de respuesta, etc."
        },
        "sort_order": {
-          "name": "Orden de clasificación",
-          "description": "Orden de clasificación de los resultados (más recientes o más antiguos primero)"
+          "name": "Orden de Clasificación",
+          "description": "Orden de clasificación para los resultados (más recientes o más antiguos primero)"
        }
      }
    },
    "set_system_prompt": {
-      "name": "Establecer indicación del sistema",
-      "description": "Establece instrucciones predeterminadas de comportamiento del sistema para todas las conversaciones futuras",
+      "name": "Establecer Indicaciones del Sistema",
+      "description": "Establecer instrucciones de comportamiento del sistema predeterminadas para todas las futuras conversaciones",
      "fields": {
        "instance": {
          "name": "Instancia",
-          "description": "Nombre de la instancia de HA Text AI para la que se va a establecer la indicación del sistema"
+          "description": "Nombre de la instancia de IA de Texto de HA para establecer indicaciones del sistema"
        },
        "prompt": {
-          "name": "Indicación del sistema",
+          "name": "Indicaciones del Sistema",
          "description": "Instrucciones que definen cómo debe comportarse y responder la IA"
        }
      }
@@ -162,7 +194,7 @@
          "processing": "Procesando",
          "error": "Error",
          "disconnected": "Desconectado",
-          "rate_limited": "Límite de tasa alcanzado",
+          "rate_limited": "Limitado por tasa",
          "maintenance": "Mantenimiento",
          "initializing": "Inicializando",
          "retrying": "Reintentando",
@@ -170,94 +202,94 @@
        },
        "state_attributes": {
          "question": {
-            "name": "Última pregunta"
+            "name": "Última Pregunta"
          },
          "response": {
-            "name": "Última respuesta"
+            "name": "Última Respuesta"
          },
          "model": {
-            "name": "Modelo actual"
+            "name": "Modelo Actual"
          },
          "temperature": {
            "name": "Temperatura"
          },
          "max_tokens": {
-            "name": "Máx. tokens"
+            "name": "Máx. Tokens"
          },
          "system_prompt": {
-            "name": "Indicación del sistema"
+            "name": "Indicaciones del Sistema"
          },
          "response_time": {
-            "name": "Tiempo de la última respuesta"
+            "name": "Último Tiempo de Respuesta"
          },
          "total_responses": {
-            "name": "Total de respuestas"
+            "name": "Total de Respuestas"
          },
          "error_count": {
-            "name": "Recuento de errores"
+            "name": "Conteo de Errores"
          },
          "last_error": {
-            "name": "Último error"
+            "name": "Último Error"
          },
          "api_status": {
-            "name": "Estado de la API"
+            "name": "Estado de API"
          },
          "tokens_used": {
-            "name": "Total de tokens usados"
+            "name": "Total de Tokens Usados"
          },
          "average_response_time": {
-            "name": "Tiempo medio de respuesta"
+            "name": "Tiempo de Respuesta Promedio"
          },
          "last_request_time": {
-            "name": "Tiempo de la última solicitud"
+            "name": "Último Tiempo de Solicitud"
          },
          "is_processing": {
-            "name": "Estado de procesamiento"
+            "name": "Estado de Procesamiento"
          },
          "is_rate_limited": {
-            "name": "Estado de límite de tasa"
+            "name": "Estado Limitado por Tasa"
          },
          "is_maintenance": {
-            "name": "Estado de mantenimiento"
+            "name": "Estado de Mantenimiento"
          },
          "api_version": {
-            "name": "Versión de la API"
+            "name": "Versión de API"
          },
          "endpoint_status": {
-            "name": "Estado del punto final"
+            "name": "Estado del Endpoint"
          },
          "performance_metrics": {
-            "name": "Métricas de rendimiento"
+            "name": "Métricas de Rendimiento"
          },
          "history_size": {
-            "name": "Tamaño del historial"
+            "name": "Tamaño del Historial"
          },
          "uptime": {
-            "name": "Tiempo de actividad"
+            "name": "Tiempo de Actividad"
          },
          "total_tokens": {
-            "name": "Total de tokens"
+            "name": "Total de Tokens"
          },
          "prompt_tokens": {
-            "name": "Tokens de indicación"
+            "name": "Tokens de Solicitud"
          },
          "completion_tokens": {
-            "name": "Tokens de compleción"
+            "name": "Tokens de Finalización"
          },
          "successful_requests": {
-            "name": "Solicitudes exitosas"
+            "name": "Solicitudes Exitosas"
          },
          "failed_requests": {
-            "name": "Solicitudes fallidas"
+            "name": "Solicitudes Fallidas"
          },
          "average_latency": {
-            "name": "Latencia media"
+            "name": "Latencia Promedio"
          },
          "max_latency": {
-            "name": "Latencia máxima"
+            "name": "Latencia Máxima"
          },
          "min_latency": {
-            "name": "Latencia mínima"
+            "name": "Latencia Mínima"
          }
        }
      }
@@ -2,79 +2,111 @@
  "config": {
    "step": {
      "provider": {
-        "title": "AI प्रदाता का चयन करें",
-        "description": "इस उदाहरण के लिए उपयोग करने के लिए AI सेवा प्रदाता चुनें।",
+        "title": "एआई प्रदाता चुनें",
+        "description": "इस उदाहरण के लिए किस एआई सेवा प्रदाता का उपयोग करना है, चुनें।",
        "data": {
-          "api_provider": "API प्रदाता",
-          "context_messages": "बनाए रखने के लिए संदर्भ संदेशों की संख्या (1-20)"
+          "api_provider": "एपीआई प्रदाता",
+          "context_messages": "रखने के लिए संदर्भ संदेशों की संख्या (1-20)",
+          "max_history_size": "अधिकतम बातचीत इतिहास आकार (1-100)"
+        }
+      },
+      "provider": {
+        "title": "प्रदाता सेटिंग्स",
+        "description": "आपके द्वारा चुने गए एआई प्रदाता के लिए कनेक्शन विवरण प्रदान करें।",
+        "data": {
+          "name": "उदाहरण का नाम (जैसे, 'जीपीटी सहायक', 'क्लॉड सहायक')",
+          "api_key": "प्रमाणीकरण के लिए एपीआई कुंजी",
+          "model": "उपयोग करने के लिए एआई मॉडल",
+          "api_endpoint": "कस्टम एपीआई एंडपॉइंट यूआरएल (वैकल्पिक)",
+          "temperature": "प्रतिक्रिया की रचनात्मकता (0-2, कम = अधिक केंद्रित)",
+          "max_tokens": "प्रतिक्रिया की अधिकतम लंबाई (1-100000 टोकन)",
+          "request_interval": "अनुरोधों के बीच न्यूनतम समय (0.1-60 सेकंड)",
+          "context_messages": "रखने के लिए संदर्भ संदेशों की संख्या (1-20)",
+          "max_history_size": "अधिकतम बातचीत इतिहास आकार (1-100)"
        }
      },
      "user": {
-        "title": "HA टेक्स्ट AI उदाहरण को कॉन्फ़िगर करें",
-        "description": "अपने चयनित प्रदाता के साथ एक नया AI सहायक उदाहरण सेट करें।",
+        "title": "एचए टेक्स्ट एआई उदाहरण कॉन्फ़िगर करें",
+        "description": "अपने चुने हुए प्रदाता के साथ एक नया एआई सहायक उदाहरण सेट करें।",
        "data": {
-          "name": "उदाहरण का नाम (जैसे, 'GPT सहायक', 'क्लाउड सहायक')",
-          "api_key": "प्रमाणीकरण के लिए API कुंजी",
-          "model": "उपयोग करने के लिए AI मॉडल",
-          "temperature": "प्रतिक्रिया रचनात्मकता (0-2, कम = अधिक केंद्रित)",
-          "max_tokens": "अधिकतम प्रतिक्रिया लंबाई (1-4096 टोकन)",
-          "api_endpoint": "कस्टम API एंडपॉइंट URL (वैकल्पिक)",
-          "api_provider": "API प्रदाता",
+          "name": "उदाहरण का नाम (जैसे, 'जीपीटी सहायक', 'क्लॉड सहायक')",
+          "api_key": "प्रमाणीकरण के लिए एपीआई कुंजी",
+          "model": "उपयोग करने के लिए एआई मॉडल",
+          "temperature": "प्रतिक्रिया की रचनात्मकता (0-2, कम = अधिक केंद्रित)",
+          "max_tokens": "प्रतिक्रिया की अधिकतम लंबाई (1-100000 टोकन)",
+          "api_endpoint": "कस्टम एपीआई एंडपॉइंट यूआरएल (वैकल्पिक)",
+          "api_provider": "एपीआई प्रदाता",
          "request_interval": "अनुरोधों के बीच न्यूनतम समय (0.1-60 सेकंड)",
-          "context_messages": "बनाए रखने के लिए संदर्भ संदेशों की संख्या (1-20)",
-          "max_history_size": "अधिकतम वार्तालाप इतिहास आकार (1-100)"
+          "context_messages": "रखने के लिए संदर्भ संदेशों की संख्या (1-20)",
+          "max_history_size": "अधिकतम बातचीत इतिहास आकार (1-100)"
        }
      }
    },
    "error": {
-      "name_exists": "इस नाम का एक उदाहरण पहले से मौजूद है",
+      "history_storage_error": "इतिहास भंडारण प्रारंभ करने में विफल। अनुमतियों की जांच करें।",
+      "history_rotation_error": "इतिहास फ़ाइल घुमाने के दौरान त्रुटि।",
+      "history_file_access_error": "इतिहास भंडारण निर्देशिका तक पहुंच नहीं है।",
+      "name_exists": "इस नाम के साथ एक उदाहरण पहले से मौजूद है",
      "invalid_name": "अमान्य उदाहरण नाम",
-      "invalid_auth": "प्रमाणीकरण विफल - अपनी API कुंजी जांचें",
-      "invalid_api_key": "अमान्य API कुंजी - कृपया अपनी क्रेडेंशियल सत्यापित करें",
-      "cannot_connect": "API सेवा से कनेक्ट करने में विफल",
-      "invalid_model": "चयनित मॉडल उपलब्ध नहीं है",
-      "rate_limit": "दर सीमा पार हो गई",
-      "context_length": "संदर्भ लंबाई पार हो गई",
-      "rate_limit_exceeded": "API दर सीमा पार हो गई",
-      "maintenance": "सेवा रखरखाव के अधीन है",
-      "invalid_response": "अमान्य API प्रतिक्रिया प्राप्त हुई",
-      "api_error": "API सेवा त्रुटि हुई",
-      "timeout": "अनुरोध समय समाप्त हो गया",
+      "invalid_auth": "प्रमाणीकरण विफल - अपनी एपीआई कुंजी की जांच करें",
+      "invalid_api_key": "अमान्य एपीआई कुंजी - कृपया अपनी क्रेडेंशियल्स की पुष्टि करें",
+      "cannot_connect": "एपीआई सेवा से कनेक्ट करने में विफल",
+      "invalid_model": "चुना हुआ मॉडल उपलब्ध नहीं है",
+      "rate_limit": "रेट सीमा पार",
+      "context_length": "संदर्भ लंबाई पार",
+      "rate_limit_exceeded": "एपीआई रेट सीमा पार",
+      "maintenance": "सेवा रखरखाव में है",
+      "invalid_response": "अमान्य एपीआई प्रतिक्रिया प्राप्त हुई",
+      "api_error": "एपीआई सेवा में त्रुटि हुई",
+      "timeout": "अनुरोध समय सीमा समाप्त",
      "invalid_instance": "अमान्य उदाहरण निर्दिष्ट किया गया",
      "unknown": "अप्रत्याशित त्रुटि हुई",
      "empty": "नाम खाली नहीं हो सकता",
-      "invalid_characters": "नाम में केवल अक्षर, संख्या, रिक्त स्थान, अंडरस्कोर और हाइफ़न हो सकते हैं",
-      "name_too_long": "नाम 50 वर्ण या उससे कम होना चाहिए"
+      "invalid_characters": "नाम में केवल अक्षर, अंक, रिक्त स्थान, अंडरस्कोर और हाइफन हो सकते हैं",
+      "name_too_long": "नाम 50 अक्षरों या उससे कम होना चाहिए"
+    },
+    "abort": {
+      "already_configured": "उदाहरण पहले से कॉन्फ़िगर किया गया है"
    }
  },
  "options": {
    "step": {
      "init": {
        "title": "उदाहरण सेटिंग्स अपडेट करें",
-        "description": "इस AI सहायक उदाहरण के लिए सेटिंग्स संशोधित करें।",
+        "description": "इस एआई सहायक उदाहरण के लिए सेटिंग्स संशोधित करें।",
        "data": {
-          "model": "AI मॉडल",
-          "temperature": "प्रतिक्रिया रचनात्मकता (0-2)",
-          "max_tokens": "अधिकतम प्रतिक्रिया लंबाई (1-4096)",
+          "model": "एआई मॉडल",
+          "temperature": "प्रतिक्रिया की रचनात्मकता (0-2)",
+          "max_tokens": "प्रतिक्रिया की अधिकतम लंबाई (1-100000)",
          "request_interval": "न्यूनतम अनुरोध अंतराल (0.1-60 सेकंड)",
          "context_messages": "संदर्भ में शामिल करने के लिए पिछले संदेशों की संख्या (1-20)",
-          "max_history_size": "अधिकतम वार्तालाप इतिहास आकार (1-100)"
+          "max_history_size": "अधिकतम बातचीत इतिहास आकार (1-100)"
        }
      }
    }
  },
+  "selector": {
+    "api_provider": {
+      "options": {
+        "openai": "OpenAI (अनुकूलित)",
+        "anthropic": "Anthropic (अनुकूलित)",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
+      }
+    }
+  },
  "services": {
    "ask_question": {
-      "name": "प्रश्न पूछें (HA टेक्स्ट AI)",
-      "description": "AI मॉडल को एक प्रश्न भेजें और एक विस्तृत प्रतिक्रिया प्राप्त करें। प्रतिक्रिया वार्तालाप इतिहास में संग्रहीत की जाएगी और बाद में पुनर्प्राप्त की जा सकती है।",
+      "name": "प्रश्न पूछें (HA Text AI)",
+      "description": "एआई मॉडल को एक प्रश्न भेजें और विस्तृत प्रतिक्रिया प्राप्त करें। प्रतिक्रिया बातचीत के इतिहास में संग्रहीत की जाएगी और बाद में पुनर्प्राप्त की जा सकती है।",
      "fields": {
        "instance": {
          "name": "उदाहरण",
-          "description": "उपयोग करने के लिए HA टेक्स्ट AI उदाहरण का नाम"
+          "description": "उपयोग करने के लिए एचए टेक्स्ट एआई उदाहरण का नाम"
        },
        "question": {
          "name": "प्रश्न",
-          "description": "AI सहायक के लिए आपका प्रश्न या संकेत"
+          "description": "आपका प्रश्न या एआई सहायक के लिए प्रॉम्प्ट"
        },
        "context_messages": {
          "name": "संदर्भ संदेश",
@@ -82,73 +114,73 @@
        },
        "system_prompt": {
          "name": "सिस्टम प्रॉम्प्ट",
-          "description": "इस विशिष्ट प्रश्न के लिए संदर्भ सेट करने के लिए वैकल्पिक सिस्टम प्रॉम्प्ट"
+          "description": "इस विशेष प्रश्न के लिए संदर्भ सेट करने के लिए वैकल्पिक सिस्टम प्रॉम्प्ट"
        },
        "model": {
          "name": "मॉडल",
-          "description": "उपयोग करने के लिए AI मॉडल का चयन करें (वैकल्पिक, डिफ़ॉल्ट सेटिंग को ओवरराइड करता है)"
+          "description": "उपयोग करने के लिए एआई मॉडल का चयन करें (वैकल्पिक, डिफ़ॉल्ट सेटिंग को ओवरराइड करता है)"
        },
        "temperature": {
          "name": "तापमान",
-          "description": "प्रतिक्रिया रचनात्मकता को नियंत्रित करता है (0.0-2.0)"
+          "description": "प्रतिक्रिया की रचनात्मकता को नियंत्रित करता है (0.0-2.0)"
        },
        "max_tokens": {
          "name": "अधिकतम टोकन",
-          "description": "प्रतिक्रिया की अधिकतम लंबाई (1-4096 टोकन)"
+          "description": "प्रतिक्रिया की अधिकतम लंबाई (1-100000 टोकन)"
        }
      }
    },
    "clear_history": {
-      "name": "इतिहास साफ़ करें",
-      "description": "वार्तालाप इतिहास से सभी संग्रहीत प्रश्न और प्रतिक्रियाएँ हटाएँ",
+      "name": "इतिहास साफ करें",
+      "description": "बातचीत के इतिहास से सभी संग्रहीत प्रश्नों और प्रतिक्रियाओं को हटाएं",
      "fields": {
        "instance": {
          "name": "उदाहरण",
-          "description": "इतिहास साफ़ करने के लिए HA टेक्स्ट AI उदाहरण का नाम"
+          "description": "इतिहास साफ़ करने के लिए एचए टेक्स्ट एआई उदाहरण का नाम"
        }
      }
    },
    "get_history": {
      "name": "इतिहास प्राप्त करें",
-      "description": "वैकल्पिक फ़िल्टरिंग और सॉर्टिंग के साथ वार्तालाप इतिहास पुनर्प्राप्त करें",
+      "description": "वैकल्पिक फ़िल्टरिंग और छंटाई के साथ बातचीत का इतिहास प्राप्त करें",
      "fields": {
        "instance": {
          "name": "उदाहरण",
-          "description": "इतिहास प्राप्त करने के लिए HA टेक्स्ट AI उदाहरण का नाम"
+          "description": "इतिहास प्राप्त करने के लिए एचए टेक्स्ट एआई उदाहरण का नाम"
        },
        "limit": {
          "name": "सीमा",
-          "description": "वापस करने के लिए वार्तालापों की संख्या (1-100)"
+          "description": "वापस करने के लिए बातचीत की संख्या (1-100)"
        },
        "filter_model": {
-          "name": "फ़िल्टर मॉडल",
-          "description": "विशिष्ट AI मॉडल द्वारा वार्तालापों को फ़िल्टर करें"
+          "name": "फिल्टर मॉडल",
+          "description": "विशिष्ट एआई मॉडल द्वारा बातचीत को फ़िल्टर करें"
        },
        "start_date": {
-          "name": "प्रारंभ तिथि",
-          "description": "इस तिथि/समय से शुरू होने वाले वार्तालापों को फ़िल्टर करें"
+          "name": "शुरुआत की तारीख",
+          "description": "इस दिन/समय से शुरू होने वाली बातचीत को फ़िल्टर करें"
        },
        "include_metadata": {
          "name": "मेटाडेटा शामिल करें",
-          "description": "उपयोग किए गए टोकन, प्रतिक्रिया समय, आदि जैसी अतिरिक्त जानकारी शामिल करें।"
+          "description": "उपयोग किए गए टोकन, प्रतिक्रिया समय आदि जैसी अतिरिक्त जानकारी शामिल करें।"
        },
        "sort_order": {
-          "name": "क्रमबद्ध करें",
-          "description": "परिणामों के लिए क्रमबद्ध क्रम (नवीनतम या सबसे पुराना पहले)"
+          "name": "छंटाई क्रम",
+          "description": "परिणामों के लिए छंटाई क्रम (नवीनतम या सबसे पुराना पहले)"
        }
      }
    },
    "set_system_prompt": {
      "name": "सिस्टम प्रॉम्प्ट सेट करें",
-      "description": "सभी भविष्य के वार्तालापों के लिए डिफ़ॉल्ट सिस्टम व्यवहार निर्देश सेट करें",
+      "description": "सभी भविष्य की बातचीत के लिए डिफ़ॉल्ट सिस्टम व्यवहार निर्देश सेट करें",
      "fields": {
        "instance": {
          "name": "उदाहरण",
-          "description": "सिस्टम प्रॉम्प्ट सेट करने के लिए HA टेक्स्ट AI उदाहरण का नाम"
+          "description": "सिस्टम प्रॉम्प्ट सेट करने के लिए एचए टेक्स्ट एआई उदाहरण का नाम"
        },
        "prompt": {
          "name": "सिस्टम प्रॉम्प्ट",
-          "description": "निर्देश जो परिभाषित करते हैं कि AI को कैसे व्यवहार करना चाहिए और जवाब देना चाहिए"
+          "description": "निर्देश जो यह परिभाषित करते हैं कि एआई को कैसे व्यवहार करना चाहिए और प्रतिक्रिया देनी चाहिए"
        }
      }
    }
@@ -159,14 +191,14 @@
        "name": "{name}",
        "state": {
          "ready": "तैयार",
-          "processing": "प्रक्रियाधीन",
+          "processing": "प्रसंस्करण",
          "error": "त्रुटि",
-          "disconnected": "डिस्कनेक्टेड",
-          "rate_limited": "दर सीमित",
+          "disconnected": "असंयुक्त",
+          "rate_limited": "रेट सीमित",
          "maintenance": "रखरखाव",
-          "initializing": "आरंभिकरण",
+          "initializing": "प्रारंभिककरण",
          "retrying": "पुनः प्रयास कर रहा है",
-          "queued": "कतारबद्ध"
+          "queued": "क्यू में"
        },
        "state_attributes": {
          "question": {
@@ -188,46 +220,46 @@
            "name": "सिस्टम प्रॉम्प्ट"
          },
          "response_time": {
-            "name": "अंतिम प्रतिक्रिया समय"
+            "name": "अंतिम प्रतिक्रिया का समय"
          },
          "total_responses": {
-            "name": "कुल प्रतिक्रियाएँ"
+            "name": "कुल प्रतिक्रियाएं"
          },
          "error_count": {
-            "name": "त्रुटि गणना"
+            "name": "त्रुटियों की संख्या"
          },
          "last_error": {
            "name": "अंतिम त्रुटि"
          },
          "api_status": {
-            "name": "API स्थिति"
+            "name": "एपीआई स्थिति"
          },
          "tokens_used": {
-            "name": "कुल टोकन उपयोग किए गए"
+            "name": "कुल उपयोग किए गए टोकन"
          },
          "average_response_time": {
            "name": "औसत प्रतिक्रिया समय"
          },
          "last_request_time": {
-            "name": "अंतिम अनुरोध समय"
+            "name": "अंतिम अनुरोध का समय"
          },
          "is_processing": {
            "name": "प्रसंस्करण स्थिति"
          },
          "is_rate_limited": {
-            "name": "दर सीमित स्थिति"
+            "name": "रेट सीमित स्थिति"
          },
          "is_maintenance": {
            "name": "रखरखाव स्थिति"
          },
          "api_version": {
-            "name": "API संस्करण"
+            "name": "एपीआई संस्करण"
          },
          "endpoint_status": {
            "name": "एंडपॉइंट स्थिति"
          },
          "performance_metrics": {
-            "name": "प्रदर्शन मेट्रिक्स"
+            "name": "प्रदर्शन मैट्रिक्स"
          },
          "history_size": {
            "name": "इतिहास का आकार"
@@ -242,13 +274,13 @@
            "name": "प्रॉम्प्ट टोकन"
          },
          "completion_tokens": {
-            "name": "पूर्ण टोकन"
+            "name": "पूर्णता टोकन"
          },
          "successful_requests": {
            "name": "सफल अनुरोध"
          },
          "failed_requests": {
-            "name": "असफल अनुरोध"
+            "name": "विफल अनुरोध"
          },
          "average_latency": {
            "name": "औसत विलंबता"
@@ -2,86 +2,118 @@
  "config": {
    "step": {
      "provider": {
-        "title": "Seleziona Provider AI",
-        "description": "Scegli quale provider di servizio AI utilizzare per questa istanza.",
+        "title": "Seleziona fornitore AI",
+        "description": "Scegli quale fornitore di servizi AI utilizzare per questa istanza.",
        "data": {
-          "api_provider": "Provider API",
-          "context_messages": "Numero di messaggi di contesto da conservare (1-20)"
+          "api_provider": "Fornitore API",
+          "context_messages": "Numero di messaggi di contesto da mantenere (1-20)",
+          "max_history_size": "Dimensione massima della cronologia delle conversazioni (1-100)"
+        }
+      },
+      "provider": {
+        "title": "Impostazioni fornitore",
+        "description": "Fornisci i dettagli di connessione per il tuo fornitore di AI scelto.",
+        "data": {
+          "name": "Nome dell'istanza (es. 'Assistente GPT', 'Aiuto Claude')",
+          "api_key": "Chiave API per l'autenticazione",
+          "model": "Modello AI da utilizzare",
+          "api_endpoint": "URL dell'endpoint API personalizzato (opzionale)",
+          "temperature": "Creatività della risposta (0-2, più basso = più focalizzato)",
+          "max_tokens": "Lunghezza massima della risposta (1-100000 token)",
+          "request_interval": "Tempo minimo tra le richieste (0.1-60 secondi)",
+          "context_messages": "Numero di messaggi di contesto da mantenere (1-20)",
+          "max_history_size": "Dimensione massima della cronologia delle conversazioni (1-100)"
        }
      },
      "user": {
-        "title": "Configura Istanza HA Text AI",
-        "description": "Configura una nuova istanza di assistente AI con il provider selezionato.",
+        "title": "Configura istanza AI di testo HA",
+        "description": "Imposta una nuova istanza di assistente AI con il fornitore selezionato.",
        "data": {
-          "name": "Nome dell'istanza (es. 'Assistente GPT', 'Aiutante Claude')",
+          "name": "Nome dell'istanza (es. 'Assistente GPT', 'Aiuto Claude')",
          "api_key": "Chiave API per l'autenticazione",
          "model": "Modello AI da utilizzare",
          "temperature": "Creatività della risposta (0-2, più basso = più focalizzato)",
-          "max_tokens": "Lunghezza massima della risposta (1-4096 token)",
-          "api_endpoint": "URL endpoint API personalizzato (opzionale)",
-          "api_provider": "Provider API",
-          "request_interval": "Tempo minimo tra le richieste (0,1-60 secondi)",
-          "context_messages": "Numero di messaggi di contesto da conservare (1-20)",
+          "max_tokens": "Lunghezza massima della risposta (1-100000 token)",
+          "api_endpoint": "URL dell'endpoint API personalizzato (opzionale)",
+          "api_provider": "Fornitore API",
+          "request_interval": "Tempo minimo tra le richieste (0.1-60 secondi)",
+          "context_messages": "Numero di messaggi di contesto da mantenere (1-20)",
          "max_history_size": "Dimensione massima della cronologia delle conversazioni (1-100)"
        }
      }
    },
    "error": {
-      "name_exists": "Un'istanza con questo nome esiste già",
+      "history_storage_error": "Impossibile inizializzare la memorizzazione della cronologia. Controlla i permessi.",
+      "history_rotation_error": "Errore durante la rotazione del file di cronologia.",
+      "history_file_access_error": "Impossibile accedere alla directory di memorizzazione della cronologia.",
+      "name_exists": "Esiste già un'istanza con questo nome",
      "invalid_name": "Nome dell'istanza non valido",
      "invalid_auth": "Autenticazione fallita - controlla la tua chiave API",
      "invalid_api_key": "Chiave API non valida - verifica le tue credenziali",
      "cannot_connect": "Impossibile connettersi al servizio API",
      "invalid_model": "Il modello selezionato non è disponibile",
-      "rate_limit": "Limite di velocità superato",
+      "rate_limit": "Limite di frequenza superato",
      "context_length": "Lunghezza del contesto superata",
-      "rate_limit_exceeded": "Limite di velocità API superato",
+      "rate_limit_exceeded": "Limite di frequenza API superato",
      "maintenance": "Il servizio è in manutenzione",
      "invalid_response": "Risposta API non valida ricevuta",
-      "api_error": "Si è verificato un errore del servizio API",
+      "api_error": "Si è verificato un errore nel servizio API",
      "timeout": "Richiesta scaduta",
-      "invalid_instance": "Istanza non valida specificata",
+      "invalid_instance": "Istanze specificata non valida",
      "unknown": "Si è verificato un errore imprevisto",
      "empty": "Il nome non può essere vuoto",
      "invalid_characters": "Il nome può contenere solo lettere, numeri, spazi, trattini bassi e trattini",
-      "name_too_long": "Il nome non può superare i 50 caratteri"
+      "name_too_long": "Il nome deve essere lungo 50 caratteri o meno"
+    },
+    "abort": {
+      "already_configured": "Istanze già configurata"
    }
  },
  "options": {
    "step": {
      "init": {
-        "title": "Aggiorna Impostazioni Istanza",
+        "title": "Aggiorna impostazioni dell'istanza",
        "description": "Modifica le impostazioni per questa istanza di assistente AI.",
        "data": {
          "model": "Modello AI",
          "temperature": "Creatività della risposta (0-2)",
-          "max_tokens": "Lunghezza massima della risposta (1-4096)",
-          "request_interval": "Intervallo minimo tra le richieste (0,1-60 secondi)",
+          "max_tokens": "Lunghezza massima della risposta (1-100000)",
+          "request_interval": "Intervallo minimo di richiesta (0.1-60 secondi)",
          "context_messages": "Numero di messaggi precedenti da includere nel contesto (1-20)",
          "max_history_size": "Dimensione massima della cronologia delle conversazioni (1-100)"
        }
      }
    }
  },
+  "selector": {
+    "api_provider": {
+      "options": {
+        "openai": "OpenAI (compatibile)",
+        "anthropic": "Anthropic (compatibile)",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
+      }
+    }
+  },
  "services": {
    "ask_question": {
-      "name": "Fai una Domanda (HA Text AI)",
-      "description": "Invia una domanda al modello AI e ricevi una risposta dettagliata. La risposta verrà memorizzata nella cronologia delle conversazioni e potrà essere recuperata in seguito.",
+      "name": "Fai una domanda (HA Text AI)",
+      "description": "Invia una domanda al modello AI e ricevi una risposta dettagliata. La risposta sarà memorizzata nella cronologia delle conversazioni e potrà essere recuperata in seguito.",
      "fields": {
        "instance": {
-          "name": "Istanza",
+          "name": "Istanze",
          "description": "Nome dell'istanza HA Text AI da utilizzare"
        },
        "question": {
          "name": "Domanda",
-          "description": "La tua domanda o prompt per l'assistente AI"
+          "description": "La tua domanda o richiesta per l'assistente AI"
        },
        "context_messages": {
-          "name": "Messaggi di Contesto",
+          "name": "Messaggi di contesto",
          "description": "Numero di messaggi precedenti da includere nel contesto (1-20)"
        },
        "system_prompt": {
-          "name": "Prompt di Sistema",
+          "name": "Prompt di sistema",
          "description": "Prompt di sistema opzionale per impostare il contesto per questa specifica domanda"
        },
        "model": {
@@ -93,62 +125,62 @@
          "description": "Controlla la creatività della risposta (0.0-2.0)"
        },
        "max_tokens": {
-          "name": "Max Token",
-          "description": "Lunghezza massima della risposta (1-4096 token)"
+          "name": "Token massimi",
+          "description": "Lunghezza massima della risposta (1-100000 token)"
        }
      }
    },
    "clear_history": {
-      "name": "Cancella Cronologia",
-      "description": "Elimina tutte le domande e le risposte memorizzate dalla cronologia delle conversazioni",
+      "name": "Cancella cronologia",
+      "description": "Elimina tutte le domande e risposte memorizzate dalla cronologia delle conversazioni",
      "fields": {
        "instance": {
-          "name": "Istanza",
+          "name": "Istanze",
          "description": "Nome dell'istanza HA Text AI per cui cancellare la cronologia"
        }
      }
    },
    "get_history": {
-      "name": "Ottieni Cronologia",
-      "description": "Recupera la cronologia delle conversazioni con filtro e ordinamento opzionali",
+      "name": "Ottieni cronologia",
+      "description": "Recupera la cronologia delle conversazioni con opzioni di filtro e ordinamento",
      "fields": {
        "instance": {
-          "name": "Istanza",
-          "description": "Nome dell'istanza HA Text AI da cui ottenere la cronologia"
+          "name": "Istanze",
+          "description": "Nome dell'istanza HA Text AI da cui recuperare la cronologia"
        },
        "limit": {
          "name": "Limite",
          "description": "Numero di conversazioni da restituire (1-100)"
        },
        "filter_model": {
-          "name": "Filtro Modello",
-          "description": "Filtra le conversazioni per specifico modello AI"
+          "name": "Filtra modello",
+          "description": "Filtra le conversazioni per modello AI specifico"
        },
        "start_date": {
-          "name": "Data di Inizio",
+          "name": "Data di inizio",
          "description": "Filtra le conversazioni a partire da questa data/ora"
        },
        "include_metadata": {
-          "name": "Includi Metadati",
+          "name": "Includi metadati",
          "description": "Includi informazioni aggiuntive come token utilizzati, tempo di risposta, ecc."
        },
        "sort_order": {
-          "name": "Ordine di Ordinamento",
-          "description": "Ordine di ordinamento per i risultati (più recente o più vecchio per primo)"
+          "name": "Ordine di ordinamento",
+          "description": "Ordine di ordinamento per i risultati (più recenti o più vecchi per primi)"
        }
      }
    },
    "set_system_prompt": {
-      "name": "Imposta Prompt di Sistema",
-      "description": "Imposta le istruzioni di comportamento predefinite del sistema per tutte le future conversazioni",
+      "name": "Imposta prompt di sistema",
+      "description": "Imposta le istruzioni di comportamento predefinite per tutte le future conversazioni",
      "fields": {
        "instance": {
-          "name": "Istanza",
+          "name": "Istanze",
          "description": "Nome dell'istanza HA Text AI per cui impostare il prompt di sistema"
        },
        "prompt": {
-          "name": "Prompt di Sistema",
-          "description": "Istruzioni che definiscono come l'IA dovrebbe comportarsi e rispondere"
+          "name": "Prompt di sistema",
+          "description": "Istruzioni che definiscono come l'AI dovrebbe comportarsi e rispondere"
        }
      }
    }
@@ -159,108 +191,108 @@
        "name": "{name}",
        "state": {
          "ready": "Pronto",
-          "processing": "In elaborazione",
+          "processing": "Elaborazione",
          "error": "Errore",
          "disconnected": "Disconnesso",
-          "rate_limited": "Limite di Velocità Raggiunto",
+          "rate_limited": "Limite di frequenza",
          "maintenance": "Manutenzione",
          "initializing": "Inizializzazione",
-          "retrying": "Riprovando",
+          "retrying": "Riprova",
          "queued": "In coda"
        },
        "state_attributes": {
          "question": {
-            "name": "Ultima Domanda"
+            "name": "Ultima domanda"
          },
          "response": {
-            "name": "Ultima Risposta"
+            "name": "Ultima risposta"
          },
          "model": {
-            "name": "Modello Attuale"
+            "name": "Modello attuale"
          },
          "temperature": {
            "name": "Temperatura"
          },
          "max_tokens": {
-            "name": "Max Token"
+            "name": "Token massimi"
          },
          "system_prompt": {
-            "name": "Prompt di Sistema"
+            "name": "Prompt di sistema"
          },
          "response_time": {
-            "name": "Tempo di Risposta Ultima"
+            "name": "Ultimo tempo di risposta"
          },
          "total_responses": {
-            "name": "Totale Risposte"
+            "name": "Risposte totali"
          },
          "error_count": {
-            "name": "Numero di Errori"
+            "name": "Conteggio errori"
          },
          "last_error": {
-            "name": "Ultimo Errore"
+            "name": "Ultimo errore"
          },
          "api_status": {
            "name": "Stato API"
          },
          "tokens_used": {
-            "name": "Totale Token Utilizzati"
+            "name": "Token totali utilizzati"
          },
          "average_response_time": {
-            "name": "Tempo di Risposta Medio"
+            "name": "Tempo medio di risposta"
          },
          "last_request_time": {
-            "name": "Tempo Ultima Richiesta"
+            "name": "Ultimo tempo di richiesta"
          },
          "is_processing": {
-            "name": "Stato Elaborazione"
+            "name": "Stato di elaborazione"
          },
          "is_rate_limited": {
-            "name": "Stato Limite Velocità"
+            "name": "Stato limite di frequenza"
          },
          "is_maintenance": {
-            "name": "Stato Manutenzione"
+            "name": "Stato di manutenzione"
          },
          "api_version": {
            "name": "Versione API"
          },
          "endpoint_status": {
-            "name": "Stato Endpoint"
+            "name": "Stato dell'endpoint"
          },
          "performance_metrics": {
-            "name": "Metriche Prestazioni"
+            "name": "Metriche di prestazione"
          },
          "history_size": {
-            "name": "Dimensione Cronologia"
+            "name": "Dimensione della cronologia"
          },
          "uptime": {
-            "name": "Tempo di Funzionamento"
+            "name": "Tempo di attività"
          },
          "total_tokens": {
-            "name": "Totale Token"
+            "name": "Token totali"
          },
          "prompt_tokens": {
-            "name": "Token Prompt"
+            "name": "Token di prompt"
          },
          "completion_tokens": {
-            "name": "Token Completamento"
+            "name": "Token di completamento"
          },
          "successful_requests": {
-            "name": "Richieste Riuscite"
+            "name": "Richieste riuscite"
          },
          "failed_requests": {
-            "name": "Richieste Fallite"
+            "name": "Richieste fallite"
          },
          "average_latency": {
-            "name": "Latency Media"
+            "name": "Latenza media"
          },
          "max_latency": {
-            "name": "Latency Massima"
+            "name": "Latenza massima"
          },
          "min_latency": {
-            "name": "Latency Minima"
-            }
+            "name": "Latenza minima"
          }
        }
      }
    }
  }
+}
@@ -2,99 +2,131 @@
  "config": {
    "step": {
      "provider": {
-        "title": "Выбор поставщика ИИ",
-        "description": "Выберите поставщика услуг ИИ для этой инстанции.",
+        "title": "Выбор провайдера ИИ",
+        "description": "Выберите сервис искусственного интеллекта для этого экземпляра.",
        "data": {
-          "api_provider": "Поставщик API",
-          "context_messages": "Количество контекстных сообщений для сохранения (1-20)"
+          "api_provider": "Провайдер API",
+          "context_messages": "Количество сохраняемых контекстных сообщений (1-20)",
+          "max_history_size": "Максимальный размер истории разговора (1-100)"
+        }
+      },
+      "provider": {
+        "title": "Настройки провайдера",
+        "description": "Укажите параметры подключения для выбранного провайдера ИИ.",
+        "data": {
+          "name": "Название экземпляра (например, 'GPT Помощник', 'Клод Ассистент')",
+          "api_key": "API-ключ для аутентификации",
+          "model": "Модель ИИ для использования",
+          "api_endpoint": "Пользовательский URL-адрес конечной точки API (необязательно)",
+          "temperature": "Креативность ответа (0-2, меньше = более сфокусированно)",
+          "max_tokens": "Максимальная длина ответа (1-100000 токенов)",
+          "request_interval": "Минимальный интервал между запросами (0.1-60 секунд)",
+          "context_messages": "Количество сохраняемых контекстных сообщений (1-20)",
+          "max_history_size": "Максимальный размер истории разговора (1-100)"
        }
      },
      "user": {
-        "title": "Настройка инстанции HA Text AI",
-        "description": "Настройте новую инстанцию помощника ИИ с выбранным вами поставщиком.",
+        "title": "Настройка экземпляра текстового ИИ для Home Assistant",
+        "description": "Настройте новый экземпляр ИИ-помощника с выбранным провайдером.",
        "data": {
-          "name": "Имя инстанции (например, 'GPT Assistant', 'Claude Helper')",
+          "name": "Название экземпляра (например, 'GPT Помощник', 'Клод Ассистент')",
          "api_key": "API-ключ для аутентификации",
-          "model": "Используемая модель ИИ",
-          "temperature": "Креативность ответа (0-2, чем ниже, тем больше фокусировки)",
-          "max_tokens": "Максимальная длина ответа (1-4096 токенов)",
+          "model": "Модель ИИ для использования",
+          "temperature": "Креативность ответа (0-2, меньше = более сфокусированно)",
+          "max_tokens": "Максимальная длина ответа (1-100000 токенов)",
          "api_endpoint": "Пользовательский URL-адрес конечной точки API (необязательно)",
-          "api_provider": "Поставщик API",
-          "request_interval": "Минимальное время между запросами (0,1-60 секунд)",
-          "context_messages": "Количество контекстных сообщений для сохранения (1-20)",
+          "api_provider": "Провайдер API",
+          "request_interval": "Минимальный интервал между запросами (0.1-60 секунд)",
+          "context_messages": "Количество сохраняемых контекстных сообщений (1-20)",
          "max_history_size": "Максимальный размер истории разговора (1-100)"
        }
      }
    },
    "error": {
-      "name_exists": "Инстанция с таким именем уже существует",
-      "invalid_name": "Некорректное имя инстанции",
-      "invalid_auth": "Аутентификация не удалась - проверьте ваш API-ключ",
-      "invalid_api_key": "Неверный API-ключ - проверьте ваши учетные данные",
-      "cannot_connect": "Не удалось подключиться к службе API",
+      "history_storage_error": "Не удалось инициализировать хранилище истории. Проверьте разрешения.",
+      "history_rotation_error": "Ошибка при ротации файла истории.",
+      "history_file_access_error": "Невозможно получить доступ к директории хранения истории.",
+      "name_exists": "Экземпляр с таким именем уже существует",
+      "invalid_name": "Недопустимое имя экземпляра",
+      "invalid_auth": "Ошибка аутентификации - проверьте API-ключ",
+      "invalid_api_key": "Недопустимый API-ключ - пожалуйста, проверьте учетные данные",
+      "cannot_connect": "Не удалось подключиться к сервису API",
      "invalid_model": "Выбранная модель недоступна",
      "rate_limit": "Превышен лимит запросов",
      "context_length": "Превышена длина контекста",
      "rate_limit_exceeded": "Превышен лимит запросов API",
      "maintenance": "Сервис находится на техническом обслуживании",
-      "invalid_response": "Получен неверный ответ API",
-      "api_error": "Произошла ошибка службы API",
-      "timeout": "Запрос превысил время ожидания",
-      "invalid_instance": "Указана неверная инстанция",
+      "invalid_response": "Получен некорректный ответ API",
+      "api_error": "Произошла ошибка сервиса API",
+      "timeout": "Время ожидания запроса истекло",
+      "invalid_instance": "Указан некорректный экземпляр",
      "unknown": "Произошла непредвиденная ошибка",
      "empty": "Имя не может быть пустым",
      "invalid_characters": "Имя может содержать только буквы, цифры, пробелы, подчеркивания и дефисы",
-      "name_too_long": "Имя должно быть не более 50 символов"
+      "name_too_long": "Имя должно быть не длиннее 50 символов"
+    },
+    "abort": {
+      "already_configured": "Экземпляр уже настроен"
    }
  },
  "options": {
    "step": {
      "init": {
-        "title": "Обновление настроек инстанции",
-        "description": "Измените настройки для этой инстанции помощника ИИ.",
+        "title": "Обновление настроек экземпляра",
+        "description": "Измените настройки для этого экземпляра ИИ-помощника.",
        "data": {
          "model": "Модель ИИ",
          "temperature": "Креативность ответа (0-2)",
-          "max_tokens": "Максимальная длина ответа (1-4096)",
-          "request_interval": "Минимальный интервал между запросами (0,1-60 секунд)",
+          "max_tokens": "Максимальная длина ответа (1-100000)",
+          "request_interval": "Минимальный интервал между запросами (0.1-60 секунд)",
          "context_messages": "Количество предыдущих сообщений для включения в контекст (1-20)",
          "max_history_size": "Максимальный размер истории разговора (1-100)"
        }
      }
    }
  },
+  "selector": {
+    "api_provider": {
+      "options": {
+        "openai": "OpenAI (совместимый)",
+        "anthropic": "Anthropic (совместимый)",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
+      }
+    }
+  },
  "services": {
    "ask_question": {
      "name": "Задать вопрос (HA Text AI)",
-      "description": "Отправьте вопрос модели ИИ и получите подробный ответ. Ответ будет сохранен в истории разговора и может быть извлечен позже.",
+      "description": "Отправить вопрос модели ИИ и получить подробный ответ. Ответ будет сохранен в истории разговора и может быть получен позже.",
      "fields": {
        "instance": {
-          "name": "Инстанция",
-          "description": "Имя используемой инстанции HA Text AI"
+          "name": "Экземпляр",
+          "description": "Название экземпляра текстового ИИ для использования"
        },
        "question": {
          "name": "Вопрос",
-          "description": "Ваш вопрос или запрос к помощнику ИИ"
+          "description": "Ваш вопрос или запрос к ИИ-помощнику"
        },
        "context_messages": {
          "name": "Контекстные сообщения",
          "description": "Количество предыдущих сообщений для включения в контекст (1-20)"
        },
        "system_prompt": {
-          "name": "Системный запрос",
-          "description": "Необязательный системный запрос для установки контекста для этого конкретного вопроса"
+          "name": "Системный промпт",
+          "description": "Необязательный системный промпт для установки контекста для этого конкретного вопроса"
        },
        "model": {
          "name": "Модель",
-          "description": "Выберите модель ИИ для использования (необязательно, переопределяет настройку по умолчанию)"
+          "description": "Выберите модель ИИ для использования (необязательно, переопределяет настройки по умолчанию)"
        },
        "temperature": {
          "name": "Температура",
-          "description": "Управляет креативностью ответа (0.0-2.0)"
+          "description": "Управление креативностью ответа (0.0-2.0)"
        },
        "max_tokens": {
-          "name": "Макс. токенов",
-          "description": "Максимальная длина ответа (1-4096 токенов)"
+          "name": "Максимум токенов",
+          "description": "Максимальная длина ответа (1-100000 токенов)"
        }
      }
    },
@@ -103,18 +135,18 @@
      "description": "Удалить все сохраненные вопросы и ответы из истории разговора",
      "fields": {
        "instance": {
-          "name": "Инстанция",
-          "description": "Имя инстанции HA Text AI, для которой нужно очистить историю"
+          "name": "Экземпляр",
+          "description": "Название экземпляра текстового ИИ для очистки истории"
        }
      }
    },
    "get_history": {
      "name": "Получить историю",
-      "description": "Извлечь историю разговора с возможностью фильтрации и сортировки",
+      "description": "Получить историю разговора с дополнительной фильтрацией и сортировкой",
      "fields": {
        "instance": {
-          "name": "Инстанция",
-          "description": "Имя инстанции HA Text AI, из которой нужно получить историю"
+          "name": "Экземпляр",
+          "description": "Название экземпляра текстового ИИ для получения истории"
        },
        "limit": {
          "name": "Лимит",
@@ -122,33 +154,33 @@
        },
        "filter_model": {
          "name": "Фильтр модели",
-          "description": "Фильтрация разговоров по определенной модели ИИ"
+          "description": "Фильтрация разговоров по конкретной модели ИИ"
        },
        "start_date": {
-          "name": "Дата начала",
-          "description": "Фильтрация разговоров, начиная с этой даты/времени"
+          "name": "Начальная дата",
+          "description": "Фильтрация разговоров, начиная с указанной даты/времени"
        },
        "include_metadata": {
          "name": "Включить метаданные",
-          "description": "Включить дополнительную информацию, такую как использованные токены, время ответа и т.д."
+          "description": "Включить дополнительную информацию, например, использованные токены, время ответа и т.д."
        },
        "sort_order": {
          "name": "Порядок сортировки",
-          "description": "Порядок сортировки результатов (самые новые или самые старые)"
+          "description": "Порядок сортировки результатов (сначала новые или старые)"
        }
      }
    },
    "set_system_prompt": {
-      "name": "Установить системный запрос",
-      "description": "Установить инструкции по умолчанию для поведения системы для всех будущих разговоров",
+      "name": "Установить системный промпт",
+      "description": "Установить инструкции по умолчанию для поведения ИИ во всех будущих разговорах",
      "fields": {
        "instance": {
-          "name": "Инстанция",
-          "description": "Имя инстанции HA Text AI, для которой нужно установить системный запрос"
+          "name": "Экземпляр",
+          "description": "Название экземпляра текстового ИИ для установки системного промпта"
        },
        "prompt": {
-          "name": "Системный запрос",
-          "description": "Инструкции, определяющие, как ИИ должен себя вести и отвечать"
+          "name": "Системный промпт",
+          "description": "Инструкции, определяющие, как ИИ должен вести себя и отвечать"
        }
      }
    }
@@ -182,10 +214,10 @@
            "name": "Температура"
          },
          "max_tokens": {
-            "name": "Макс. токенов"
+            "name": "Максимум токенов"
          },
          "system_prompt": {
-            "name": "Системный запрос"
+            "name": "Системный промпт"
          },
          "response_time": {
            "name": "Время последнего ответа"
@@ -203,7 +235,7 @@
            "name": "Статус API"
          },
          "tokens_used": {
-            "name": "Использовано токенов всего"
+            "name": "Всего использовано токенов"
          },
          "average_response_time": {
            "name": "Среднее время ответа"
@@ -215,10 +247,10 @@
            "name": "Статус обработки"
          },
          "is_rate_limited": {
-            "name": "Статус ограничения запросов"
+            "name": "Статус лимита запросов"
          },
          "is_maintenance": {
-            "name": "Статус технического обслуживания"
+            "name": "Статус обслуживания"
          },
          "api_version": {
            "name": "Версия API"
@@ -227,7 +259,7 @@
            "name": "Статус конечной точки"
          },
          "performance_metrics": {
-            "name": "Метрики производительности"
+            "name": "Показатели производительности"
          },
          "history_size": {
            "name": "Размер истории"
@@ -239,16 +271,16 @@
            "name": "Всего токенов"
          },
          "prompt_tokens": {
-            "name": "Токены запроса"
+            "name": "Токены промпта"
          },
          "completion_tokens": {
            "name": "Токены завершения"
          },
          "successful_requests": {
-            "name": "Успешных запросов"
+            "name": "Успешные запросы"
          },
          "failed_requests": {
-            "name": "Неудачных запросов"
+            "name": "Неудачные запросы"
          },
          "average_latency": {
            "name": "Средняя задержка"
@@ -2,153 +2,185 @@
  "config": {
    "step": {
      "provider": {
-        "title": "Изаберите добављача вештачке интелигенције",
-        "description": "Изаберите добављача услуга вештачке интелигенције који ћете користити за ову инстанцу.",
+        "title": "Изаберите AI провајдера",
+        "description": "Изаберите који AI сервис провајдер да користите за ову инстанцу.",
        "data": {
-          "api_provider": "Добављач API-ја",
-          "context_messages": "Број порука контекста које треба задржати (1-20)"
+          "api_provider": "API провајдер",
+          "context_messages": "Број контекстуалних порука које треба задржати (1-20)",
+          "max_history_size": "Максимална величина историје разговора (1-100)"
+        }
+      },
+      "provider": {
+        "title": "Подешавања провајдера",
+        "description": "Обезбедите детаље о вези за изабраног AI провајдера.",
+        "data": {
+          "name": "Име инстанце (нпр. 'GPT Асистент', 'Claude Помоћник')",
+          "api_key": "API кључ за аутентификацију",
+          "model": "AI модел који ће се користити",
+          "api_endpoint": "Прилагођени URL API крајње тачке (опционо)",
+          "temperature": "Креативност одговора (0-2, нижа = фокусираније)",
+          "max_tokens": "Максимална дужина одговора (1-100000 токена)",
+          "request_interval": "Минимално време између захтева (0.1-60 секунди)",
+          "context_messages": "Број контекстуалних порука које треба задржати (1-20)",
+          "max_history_size": "Максимална величина историје разговора (1-100)"
        }
      },
      "user": {
-        "title": "Конфигуришите инстанцу HA Text AI",
-        "description": "Поставите нову инстанцу асистента вештачке интелигенције са изабраним добављачем.",
+        "title": "Конфигуришите HA Text AI инстанцу",
+        "description": "Подесите нову AI асистент инстанцу са изабраним провајдером.",
        "data": {
-          "name": "Назив инстанце (нпр. 'GPT Assistant', 'Claude Helper')",
+          "name": "Име инстанце (нпр. 'GPT Асистент', 'Claude Помоћник')",
          "api_key": "API кључ за аутентификацију",
-          "model": "Модел вештачке интелигенције који треба користити",
-          "temperature": "Креативност одговора (0-2, нижа = више фокусирана)",
-          "max_tokens": "Максимална дужина одговора (1-4096 токена)",
-          "api_endpoint": "Прилагођени URL завршног тачка API-ја (опционо)",
-          "api_provider": "Добављач API-ја",
+          "model": "AI модел који ће се користити",
+          "temperature": "Креативност одговора (0-2, нижа = фокусираније)",
+          "max_tokens": "Максимална дужина одговора (1-100000 токена)",
+          "api_endpoint": "Прилагођени URL API крајње тачке (опционо)",
+          "api_provider": "API провајдер",
          "request_interval": "Минимално време између захтева (0.1-60 секунди)",
-          "context_messages": "Број порука контекста које треба задржати (1-20)",
+          "context_messages": "Број контекстуалних порука које треба задржати (1-20)",
          "max_history_size": "Максимална величина историје разговора (1-100)"
        }
      }
    },
    "error": {
-      "name_exists": "Инстанца са овим називом већ постоји",
-      "invalid_name": "Неважећи назив инстанце",
-      "invalid_auth": "Аутентификација није успела - проверите свој API кључ",
-      "invalid_api_key": "Неважећи API кључ - проверите своје податке о верификацији",
-      "cannot_connect": "Није могуће успоставити везу са услугом API-ја",
+      "history_storage_error": "Неуспела инициализација складишта историје. Проверите дозволе.",
+      "history_rotation_error": "Грешка током ротације историјских датотека.",
+      "history_file_access_error": "Немогуће приступити директоријуму складишта историје.",
+      "name_exists": "Инстанца са овим именом већ постоји",
+      "invalid_name": "Неважеће име инстанце",
+      "invalid_auth": "Аутентификација није успела - проверите ваш API кључ",
+      "invalid_api_key": "Неважећи API кључ - молимо проверите ваше акредитиве",
+      "cannot_connect": "Неуспело повезивање са API сервисом",
      "invalid_model": "Изабрани модел није доступан",
-      "rate_limit": "Прекорачен је лимит стопе",
-      "context_length": "Прекорачена је дужина контекста",
-      "rate_limit_exceeded": "Прекорачен је лимит стопе API-ја",
-      "maintenance": "Услуга је у фази одржавања",
-      "invalid_response": "Примљен је неважећи одговор API-ја",
-      "api_error": "Догодила се грешка у услузи API-ја",
-      "timeout": "Захтев је истекао",
-      "invalid_instance": "Наведена је неважећа инстанца",
-      "unknown": "Догодила се неочекивана грешка",
-      "empty": "Назив не може бити празан",
-      "invalid_characters": "Назив може да садржи само слова, бројеве, размаке, цртице и цртице",
-      "name_too_long": "Назив мора бити 50 карактера или мање"
+      "rate_limit": "Пређена граница захтева",
+      "context_length": "Дужина контекста пређена",
+      "rate_limit_exceeded": "Пређена граница API захтева",
+      "maintenance": "Сервис је у одржавању",
+      "invalid_response": "Примљен неважећи API одговор",
+      "api_error": "Дошло је до грешке у API сервису",
+      "timeout": "Време захтева је истекло",
+      "invalid_instance": "Неважећа инстанца је назначена",
+      "unknown": "Дошло је до неочекиване грешке",
+      "empty": "Име не може бити празно",
+      "invalid_characters": "Име може садржавати само слова, цифре, размаке, подцрта и цртице",
+      "name_too_long": "Име мора бити 50 знакова или мање"
+    },
+    "abort": {
+      "already_configured": "Инстанца је већ конфигурисана"
    }
  },
  "options": {
    "step": {
      "init": {
        "title": "Ажурирајте подешавања инстанце",
-        "description": "Измените подешавања за ову инстанцу асистента вештачке интелигенције.",
+        "description": "Измените подешавања за ову AI асистент инстанцу.",
        "data": {
-          "model": "Модел вештачке интелигенције",
+          "model": "AI модел",
          "temperature": "Креативност одговора (0-2)",
-          "max_tokens": "Максимална дужина одговора (1-4096)",
-          "request_interval": "Минимални интервал захтева (0.1-60 секунди)",
+          "max_tokens": "Максимална дужина одговора (1-100000)",
+          "request_interval": "Минимално време између захтева (0.1-60 секунди)",
          "context_messages": "Број претходних порука које треба укључити у контекст (1-20)",
          "max_history_size": "Максимална величина историје разговора (1-100)"
        }
      }
    }
  },
+  "selector": {
+    "api_provider": {
+      "options": {
+        "openai": "OpenAI (компатибилан)",
+        "anthropic": "Anthropic (компатибилан)",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
+      }
+    }
+  },
  "services": {
    "ask_question": {
      "name": "Поставите питање (HA Text AI)",
-      "description": "Пошаљите питање моделу вештачке интелигенције и добијте детаљан одговор. Одговор ће бити сачуван у историји разговора и може се касније преузети.",
+      "description": "Пошаљите питање AI моделу и примите детаљан одговор. Одговор ће бити сачуван у историји разговора и може се касније повратити.",
      "fields": {
        "instance": {
          "name": "Инстанца",
-          "description": "Назив инстанце HA Text AI коју треба користити"
+          "description": "Име HA Text AI инстанце коју ћете користити"
        },
        "question": {
          "name": "Питање",
-          "description": "Ваше питање или наговештај за асистента вештачке интелигенције"
+          "description": "Ваше питање или упит за AI асистента"
        },
        "context_messages": {
-          "name": "Поруке контекста",
+          "name": "Контекстуалне поруке",
          "description": "Број претходних порука које треба укључити у контекст (1-20)"
        },
        "system_prompt": {
-          "name": "Системски наговештај",
-          "description": "Опциони системски наговештај за постављање контекста за ово одређено питање"
+          "name": "Системски упит",
+          "description": "Опционални системски упит за постављање контекста за ово конкретно питање"
        },
        "model": {
          "name": "Модел",
-          "description": "Изаберите модел вештачке интелигенције који треба користити (опционо, преклапа подразумевано подешавање)"
+          "description": "Изаберите AI модел који ћете користити (опционо, надмашује подразумевану поставку)"
        },
        "temperature": {
          "name": "Температура",
          "description": "Контролише креативност одговора (0.0-2.0)"
        },
        "max_tokens": {
-          "name": "Макс. токени",
-          "description": "Максимална дужина одговора (1-4096 токена)"
+          "name": "Максимални токени",
+          "description": "Максимална дужина одговора (1-100000 токена)"
        }
      }
    },
    "clear_history": {
      "name": "Обриши историју",
-      "description": "Обришите сва сачувана питања и одговоре из историје разговора",
+      "description": "Избришите све сачуване питања и одговоре из историје разговора",
      "fields": {
        "instance": {
          "name": "Инстанца",
-          "description": "Назив инстанце HA Text AI за коју треба очистити историју"
+          "description": "Име HA Text AI инстанце за коју желите да обришете историју"
        }
      }
    },
    "get_history": {
-      "name": "Добиј историју",
-      "description": "Преузмите историју разговора са опционом филтрацијом и сортирањем",
+      "name": "Добијте историју",
+      "description": "Повратите историју разговора уз опционално филтрирање и сортирање",
      "fields": {
        "instance": {
          "name": "Инстанца",
-          "description": "Назив инстанце HA Text AI из које треба добити историју"
+          "description": "Име HA Text AI инстанце из које желите да добијете историју"
        },
        "limit": {
          "name": "Лимит",
-          "description": "Број разговора који треба вратити (1-100)"
+          "description": "Број разговора које треба вратити (1-100)"
        },
        "filter_model": {
-          "name": "Филтер модела",
-          "description": "Филтрирајте разговоре по одређеном моделу вештачке интелигенције"
+          "name": "Филтер модел",
+          "description": "Филтрирајте разговоре по одређеном AI моделу"
        },
        "start_date": {
-          "name": "Почетни датум",
-          "description": "Филтрирајте разговоре почев од овог датума/времена"
+          "name": "Датум почетка",
+          "description": "Филтрирајте разговоре који почињу од овог датума/времена"
        },
        "include_metadata": {
          "name": "Укључи метаподатке",
-          "description": "Укључите додатне информације попут коришћених токена, времена одговора и слично."
+          "description": "Укључите додатне информације као што су коришћени токени, време одговора итд."
        },
        "sort_order": {
          "name": "Редослед сортирања",
-          "description": "Редослед сортирања за резултате (најновији или најстарији прво)"
+          "description": "Редослед сортирања за резултате (најновији или најстарији први)"
        }
      }
    },
    "set_system_prompt": {
-      "name": "Поставите системски наговештај",
-      "description": "Поставите подразумевана упутства за понашање система за све будуће разговоре",
+      "name": "Поставите системски упит",
+      "description": "Поставите подразумеване инструкције за системско понашање за све будуће разговоре",
      "fields": {
        "instance": {
          "name": "Инстанца",
-          "description": "Назив инстанце HA Text AI за коју треба поставити системски наговештај"
+          "description": "Име HA Text AI инстанце за коју желите да поставите системски упит"
        },
        "prompt": {
-          "name": "Системски наговештај",
-          "description": "Упутства која дефинишу како би се вештачка интелигенција требала понашати и одговарати"
+          "name": "Системски упит",
+          "description": "Инструкције које дефинишу како AI треба да се понаша и одговара"
        }
      }
    }
@@ -161,12 +193,12 @@
          "ready": "Спремно",
          "processing": "Обрада",
          "error": "Грешка",
-          "disconnected": "Искључено",
-          "rate_limited": "Лимит стопе",
+          "disconnected": "Прекључено",
+          "rate_limited": "Ограничење захтева",
          "maintenance": "Одржавање",
-          "initializing": "Иницијализација",
-          "retrying": "Понављање",
-          "queued": "У реду чекања"
+          "initializing": "Инициализује се",
+          "retrying": "Покушава поново",
+          "queued": "У реду"
        },
        "state_attributes": {
          "question": {
@@ -182,16 +214,16 @@
            "name": "Температура"
          },
          "max_tokens": {
-            "name": "Макс. токени"
+            "name": "Максимални токени"
          },
          "system_prompt": {
-            "name": "Системски наговештај"
+            "name": "Системски упит"
          },
          "response_time": {
            "name": "Време последњег одговора"
          },
          "total_responses": {
-            "name": "Укупан број одговора"
+            "name": "Укупно одговора"
          },
          "error_count": {
            "name": "Број грешака"
@@ -200,10 +232,10 @@
            "name": "Последња грешка"
          },
          "api_status": {
-            "name": "Статус API-ја"
+            "name": "Статус API"
          },
          "tokens_used": {
-            "name": "Укупно коришћених токена"
+            "name": "Укупно коришћени токени"
          },
          "average_response_time": {
            "name": "Просечно време одговора"
@@ -215,34 +247,34 @@
            "name": "Статус обраде"
          },
          "is_rate_limited": {
-            "name": "Статус ограничења стопе"
+            "name": "Статус ограничења захтева"
          },
          "is_maintenance": {
            "name": "Статус одржавања"
          },
          "api_version": {
-            "name": "Верзија API-ја"
+            "name": "Верзија API"
          },
          "endpoint_status": {
-            "name": "Статус завршне тачке"
+            "name": "Статус крајње тачке"
          },
          "performance_metrics": {
-            "name": "Метрике перформанси"
+            "name": "Перформансне метрике"
          },
          "history_size": {
            "name": "Величина историје"
          },
          "uptime": {
-            "name": "Време рада"
+            "name": "Уптиме"
          },
          "total_tokens": {
-            "name": "Укупан број токена"
+            "name": "Укупно токена"
          },
          "prompt_tokens": {
-            "name": "Токени наговештаја"
+            "name": "Токени упита"
          },
          "completion_tokens": {
-            "name": "Токени довршетака"
+            "name": "Токени завршетка"
          },
          "successful_requests": {
            "name": "Успешни захтеви"
@@ -2,153 +2,185 @@
  "config": {
    "step": {
      "provider": {
-        "title": "选择 AI 提供商",
-        "description": "选择要用于此实例的 AI 服务提供商。",
+        "title": "选择AI提供者",
+        "description": "选择要用于此实例的AI服务提供者。",
        "data": {
-          "api_provider": "API 提供商",
-          "context_messages": "要保留的上下文消息数量 (1-20)"
+          "api_provider": "API提供者",
+          "context_messages": "保留的上下文消息数量（1-20）",
+          "max_history_size": "最大对话历史大小（1-100）"
+        }
+      },
+      "provider": {
+        "title": "提供者设置",
+        "description": "提供所选AI提供者的连接详细信息。",
+        "data": {
+          "name": "实例名称（例如，'GPT助手'，'Claude助手'）",
+          "api_key": "用于身份验证的API密钥",
+          "model": "要使用的AI模型",
+          "api_endpoint": "自定义API端点URL（可选）",
+          "temperature": "响应创造力（0-2，越低越专注）",
+          "max_tokens": "最大响应长度（1-100000个标记）",
+          "request_interval": "请求之间的最小时间（0.1-60秒）",
+          "context_messages": "保留的上下文消息数量（1-20）",
+          "max_history_size": "最大对话历史大小（1-100）"
        }
      },
      "user": {
-        "title": "配置 HA Text AI 实例",
-        "description": "使用您选择的提供商设置新的 AI 助手实例。",
+        "title": "配置HA文本AI实例",
+        "description": "使用所选提供者设置新的AI助手实例。",
        "data": {
-          "name": "实例名称（例如，“GPT 助手”、“Claude 助手”）",
-          "api_key": "用于身份验证的 API 密钥",
-          "model": "要使用的 AI 模型",
-          "temperature": "回复创意度 (0-2，数值越低，回复越聚焦)",
-          "max_tokens": "最大回复长度（1-4096 个 Token）",
-          "api_endpoint": "自定义 API 端点 URL（可选）",
-          "api_provider": "API 提供商",
-          "request_interval": "请求之间的最短时间间隔（0.1-60 秒）",
-          "context_messages": "要保留的上下文消息数量 (1-20)",
-          "max_history_size": "最大对话历史记录大小 (1-100)"
+          "name": "实例名称（例如，'GPT助手'，'Claude助手'）",
+          "api_key": "用于身份验证的API密钥",
+          "model": "要使用的AI模型",
+          "temperature": "响应创造力（0-2，越低越专注）",
+          "max_tokens": "最大响应长度（1-100000个标记）",
+          "api_endpoint": "自定义API端点URL（可选）",
+          "api_provider": "API提供者",
+          "request_interval": "请求之间的最小时间（0.1-60秒）",
+          "context_messages": "保留的上下文消息数量（1-20）",
+          "max_history_size": "最大对话历史大小（1-100）"
        }
      }
    },
    "error": {
-      "name_exists": "已存在具有此名称的实例",
+      "history_storage_error": "无法初始化历史存储。检查权限。",
+      "history_rotation_error": "历史文件轮换时出错。",
+      "history_file_access_error": "无法访问历史存储目录。",
+      "name_exists": "具有此名称的实例已存在",
      "invalid_name": "无效的实例名称",
-      "invalid_auth": "身份验证失败 - 请检查您的 API 密钥",
-      "invalid_api_key": "无效的 API 密钥 - 请验证您的凭据",
-      "cannot_connect": "无法连接到 API 服务",
+      "invalid_auth": "身份验证失败 - 检查您的API密钥",
+      "invalid_api_key": "无效的API密钥 - 请验证您的凭据",
+      "cannot_connect": "无法连接到API服务",
      "invalid_model": "所选模型不可用",
      "rate_limit": "超出速率限制",
      "context_length": "上下文长度超出限制",
-      "rate_limit_exceeded": "API 速率限制已超出",
+      "rate_limit_exceeded": "API速率限制超出",
      "maintenance": "服务正在维护中",
-      "invalid_response": "收到无效的 API 响应",
-      "api_error": "发生 API 服务错误",
+      "invalid_response": "收到无效的API响应",
+      "api_error": "发生API服务错误",
      "timeout": "请求超时",
      "invalid_instance": "指定的实例无效",
      "unknown": "发生意外错误",
      "empty": "名称不能为空",
      "invalid_characters": "名称只能包含字母、数字、空格、下划线和连字符",
-      "name_too_long": "名称必须为 50 个字符或更少"
+      "name_too_long": "名称必须少于50个字符"
+    },
+    "abort": {
+      "already_configured": "实例已配置"
    }
  },
  "options": {
    "step": {
      "init": {
        "title": "更新实例设置",
-        "description": "修改此 AI 助手实例的设置。",
+        "description": "修改此AI助手实例的设置。",
        "data": {
-          "model": "AI 模型",
-          "temperature": "回复创意度 (0-2)",
-          "max_tokens": "最大回复长度 (1-4096)",
-          "request_interval": "最短请求间隔 (0.1-60 秒)",
-          "context_messages": "包含在上下文中的先前消息数 (1-20)",
-          "max_history_size": "最大对话历史记录大小 (1-100)"
+          "model": "AI模型",
+          "temperature": "响应创造力（0-2）",
+          "max_tokens": "最大响应长度（1-100000）",
+          "request_interval": "最小请求间隔（0.1-60秒）",
+          "context_messages": "要包含在上下文中的先前消息数量（1-20）",
+          "max_history_size": "最大对话历史大小（1-100）"
        }
      }
    }
  },
+  "selector": {
+    "api_provider": {
+      "options": {
+        "openai": "OpenAI（兼容）",
+        "anthropic": "Anthropic（兼容）",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
+      }
+    }
+  },
  "services": {
    "ask_question": {
      "name": "提问 (HA Text AI)",
-      "description": "向 AI 模型发送问题并接收详细的回复。回复将存储在对话历史记录中，以后可以检索。",
+      "description": "向AI模型发送问题并接收详细响应。响应将存储在对话历史中，可以稍后检索。",
      "fields": {
        "instance": {
          "name": "实例",
-          "description": "要使用的 HA Text AI 实例的名称"
+          "description": "要使用的HA文本AI实例名称"
        },
        "question": {
          "name": "问题",
-          "description": "您要向 AI 助手提出的问题或提示"
+          "description": "您对AI助手的问题或提示"
        },
        "context_messages": {
          "name": "上下文消息",
-          "description": "包含在上下文中的先前消息数 (1-20)"
+          "description": "要包含在上下文中的先前消息数量（1-20）"
        },
        "system_prompt": {
          "name": "系统提示",
-          "description": "可选系统提示，用于为特定问题设置上下文"
+          "description": "可选的系统提示，用于为此特定问题设置上下文"
        },
        "model": {
          "name": "模型",
-          "description": "选择要使用的 AI 模型（可选，覆盖默认设置）"
+          "description": "选择要使用的AI模型（可选，覆盖默认设置）"
        },
        "temperature": {
          "name": "温度",
-          "description": "控制回复创意度 (0.0-2.0)"
+          "description": "控制响应创造力（0.0-2.0）"
        },
        "max_tokens": {
-          "name": "最大 Token 数",
-          "description": "回复的最大长度（1-4096 个 Token）"
+          "name": "最大标记数",
+          "description": "响应的最大长度（1-100000个标记）"
        }
      }
    },
    "clear_history": {
-      "name": "清除历史记录",
-      "description": "删除对话历史记录中所有存储的问题和回复",
+      "name": "清除历史",
+      "description": "删除对话历史中存储的所有问题和响应",
      "fields": {
        "instance": {
          "name": "实例",
-          "description": "要清除历史记录的 HA Text AI 实例的名称"
+          "description": "要清除历史的HA文本AI实例名称"
        }
      }
    },
    "get_history": {
-      "name": "获取历史记录",
-      "description": "检索对话历史记录，并可选择进行过滤和排序",
+      "name": "获取历史",
+      "description": "检索对话历史，可选的过滤和排序",
      "fields": {
        "instance": {
          "name": "实例",
-          "description": "要从中获取历史记录的 HA Text AI 实例的名称"
+          "description": "要获取历史的HA文本AI实例名称"
        },
        "limit": {
          "name": "限制",
-          "description": "要返回的对话数量 (1-100)"
+          "description": "要返回的对话数量（1-100）"
        },
        "filter_model": {
-          "name": "筛选模型",
-          "description": "按特定 AI 模型筛选对话"
+          "name": "过滤模型",
+          "description": "按特定AI模型过滤对话"
        },
        "start_date": {
          "name": "开始日期",
-          "description": "从该日期/时间开始筛选对话"
+          "description": "过滤从此日期/时间开始的对话"
        },
        "include_metadata": {
          "name": "包含元数据",
-          "description": "包含其他信息，例如使用的 Token 数、响应时间等。"
+          "description": "包括额外信息，如使用的标记、响应时间等。"
        },
        "sort_order": {
          "name": "排序顺序",
-          "description": "结果的排序顺序（最新的或最早的优先）"
+          "description": "结果的排序顺序（最新或最旧优先）"
        }
      }
    },
    "set_system_prompt": {
      "name": "设置系统提示",
-      "description": "为所有将来的对话设置默认系统行为说明",
+      "description": "为所有未来的对话设置默认的系统行为指令",
      "fields": {
        "instance": {
          "name": "实例",
-          "description": "要为其设置系统提示的 HA Text AI 实例的名称"
+          "description": "要设置系统提示的HA文本AI实例名称"
        },
        "prompt": {
          "name": "系统提示",
-          "description": "定义 AI 如何行为和响应的说明"
+          "description": "定义AI应如何行为和响应的指令"
        }
      }
    }
@@ -158,22 +190,22 @@
      "ha_text_ai": {
        "name": "{name}",
        "state": {
-          "ready": "就绪",
+          "ready": "准备就绪",
          "processing": "处理中",
          "error": "错误",
          "disconnected": "已断开连接",
          "rate_limited": "速率限制",
-          "maintenance": "维护",
+          "maintenance": "维护中",
          "initializing": "初始化中",
          "retrying": "重试中",
          "queued": "排队中"
        },
        "state_attributes": {
          "question": {
-            "name": "最后一个问题"
+            "name": "最后问题"
          },
          "response": {
-            "name": "最后一个回复"
+            "name": "最后响应"
          },
          "model": {
            "name": "当前模型"
@@ -182,34 +214,34 @@
            "name": "温度"
          },
          "max_tokens": {
-            "name": "最大 Token 数"
+            "name": "最大标记数"
          },
          "system_prompt": {
            "name": "系统提示"
          },
          "response_time": {
-            "name": "上次回复时间"
+            "name": "最后响应时间"
          },
          "total_responses": {
-            "name": "总回复次数"
+            "name": "总响应数"
          },
          "error_count": {
            "name": "错误计数"
          },
          "last_error": {
-            "name": "上次错误"
+            "name": "最后错误"
          },
          "api_status": {
-            "name": "API 状态"
+            "name": "API状态"
          },
          "tokens_used": {
-            "name": "已使用的 Token 总数"
+            "name": "总使用标记数"
          },
          "average_response_time": {
-            "name": "平均回复时间"
+            "name": "平均响应时间"
          },
          "last_request_time": {
-            "name": "上次请求时间"
+            "name": "最后请求时间"
          },
          "is_processing": {
            "name": "处理状态"
@@ -221,7 +253,7 @@
            "name": "维护状态"
          },
          "api_version": {
-            "name": "API 版本"
+            "name": "API版本"
          },
          "endpoint_status": {
            "name": "端点状态"
@@ -230,19 +262,19 @@
            "name": "性能指标"
          },
          "history_size": {
-            "name": "历史记录大小"
+            "name": "历史大小"
          },
          "uptime": {
            "name": "正常运行时间"
          },
          "total_tokens": {
-            "name": "总 Token 数"
+            "name": "总标记数"
          },
          "prompt_tokens": {
-            "name": "提示 Token 数"
+            "name": "提示标记数"
          },
          "completion_tokens": {
-            "name": "完成 Token 数"
+            "name": "完成标记数"
          },
          "successful_requests": {
            "name": "成功请求数"
@@ -1,5 +1,5 @@
 {
-  "name": "HA text AI",
+  "name": "HA Text AI",
  "render_readme": true,
  "homeassistant": "2024.11.0"
 }
@@ -1,25 +1,30 @@
 ```
-ha-text-ai/
-│
-├── custom_components/
-    ├── ha_text_ai/
-    │   ├── __init__.py
-    │   ├── config_flow.py
-    │   ├── coordinator.py
-    │   ├── manifest.json
-    │   ├── sensor.py
-    │   ├── services.yaml
-    │   ├── const.py
-    │   └── api_client.py
-    │
-    ├── translations/
-    │   ├── en.json
-    │   ├── de.json
-    │   └── ru.json
-    │
-    └── icons/
-        ├── icon.png
-        ├── icon@2x.png
-        ├── logo.png
-        └── logo@2x.png
+ha_text_ai/
+├── __init__.py
+├── api_client.py
+├── config_flow.py
+├── const.py
+├── coordinator.py
+├── icons
+│   ├── dark_icon.png
+│   ├── dark_icon@2x.png
+│   ├── dark_logo.png
+│   ├── dark_logo@2x.png
+│   ├── icon.png
+│   ├── icon@2x.png
+│   ├── logo.png
+│   └── logo@2x.png
+├── manifest.json
+├── sensor.py
+├── services.yaml
+└── translations
+    ├── de.json
+    ├── en.json
+    ├── es.json
+    ├── hi.json
+    ├── it.json
+    ├── ru.json
+    ├── sr.json
+    └── zh.json
+
 ```
Author	SHA1	Message	Date
SMKRV	8cd876195a	Bump to version 2.1.6	2025-05-20 01:50:06 +03:00
SMKRV	376753e001	fix: correct field naming in Gemini API requests from camelCase to snake_case and improve message handling	2025-05-20 01:42:38 +03:00
SMKRV	b6e73e847d	fix(api_client): correct Google Gemini API integration - Change JSON field names from camelCase to snake_case as required by Gemini API (generation_config, max_output_tokens, system_instruction) - Improve message handling to ensure proper role alternation (user/model) - Add safety checks for empty contents and ensure first message is always from user - Implement robust error handling and response parsing - Handle edge cases where candidatesTokenCount might be returned as a list Fixes #6	2025-05-20 01:16:41 +03:00
SMKRV	440c734214	Bump release version to v2.1.4	2025-05-19 23:20:27 +03:00
SMKRV	73788373cd	Release v2.1.3	2025-05-19 23:12:55 +03:00
SMKRV	4bfc96019b	fix: DEFAULT_GEMINI_ENDPOINT	2025-05-19 15:53:43 +03:00
SMKRV	2138fc7654	fix: DEFAULT_GEMINI_ENDPOINT	2025-05-19 15:36:58 +03:00
SMKRV	95bd2ebb41	Add support for Google Gemini (thanks to @Azzedde) #5	2025-05-19 15:10:19 +03:00
smkrvandGitHub	cad0fd7031	Merge pull request #5 from Azzedde/main Add Gemini API provider support to HA Text AI integration by @Azzedde	2025-05-19 14:44:06 +03:00
Azzedde	c003b258f6	Add Gemini API provider support to HA Text AI integration	2025-05-18 13:23:55 +02:00
SMKRV	65a10c77f4	~	2025-01-30 01:15:13 +03:00
SMKRV	e1463828c9	~	2025-01-30 01:14:24 +03:00
SMKRV	5ebb9c9c66	fix: max_tokens value	2025-01-29 18:04:13 +03:00
SMKRV	f17c631a79	fix: max_tokens value	2025-01-29 18:02:42 +03:00
SMKRV	0e06794384	refactor(docs): shields & community links updated	2025-01-29 03:05:47 +03:00
SMKRV	d8a924909b	refactor(docs): shields & community links updated	2025-01-29 03:05:11 +03:00
SMKRV	29f1659a02	refactor(docs): shields & community links updated	2025-01-29 03:04:39 +03:00
SMKRV	5b7905de80	refactor(docs): shields & community links updated	2025-01-29 03:03:48 +03:00
SMKRV	cf9ac6dcea	refactor(docs): shields & community links updated	2025-01-29 01:08:45 +03:00
SMKRV	568eb3e16c	refactor(docs): shields updated	2025-01-29 00:58:27 +03:00
SMKRV	53fb150389	refactor(docs): shields updated	2025-01-29 00:58:09 +03:00
SMKRV	acbb53d2af	refactor(docs): shields updated	2025-01-29 00:57:27 +03:00
SMKRV	e19db29441	refactor(docs): DeepSeek Integration	2025-01-28 16:25:59 +03:00
SMKRV	bfd64d1122	Release v2.1.1: Token Handling Improvement and DeepSeek Support - Completely reworked token handling mechanism - Removed custom token calculation logic - Direct max_tokens passing to LLM APIs - Added support for DeepSeek provider - Integrated deepseek-chat and deepseek-reasoner models Thanks to @estiens for reporting token handling issues and providing valuable feedback (https://github.com/smkrv/ha-text-ai/issues/1).	2025-01-28 15:54:48 +03:00
SMKRV	82e1f0c4f9	Release v2.1.0	2024-12-13 00:06:08 +03:00
SMKRV	5c16eee6e4	fix: Read version from manifest.json	2024-12-12 16:03:15 +03:00
SMKRV	e988d445a4	- Fixed version reading from manifest.json implementation	2024-12-11 22:01:01 +03:00
SMKRV	f9bfb9ab7f	fix: correct sw_version syntax in device_info - Fixed version reading from manifest.json implementation	2024-12-11 21:57:27 +03:00
SMKRV	92dd1bc110	~	2024-12-11 00:00:12 +03:00
SMKRV	17d547325a	refactor(docs): updated README services examples with more detailed configuration	2024-12-10 23:33:32 +03:00
SMKRV	b8cb70217c	refactor(docs): updated README shields	2024-12-10 23:27:49 +03:00
SMKRV	530d04f25d	refactor(docs): updated README shields	2024-12-10 23:27:18 +03:00
SMKRV	b71083b9bf	bump to version 2.0.9	2024-12-10 17:25:47 +03:00
SMKRV	f9f7d10f7f	refactor(docs): updated README images	2024-12-10 17:21:41 +03:00
SMKRV	9f7cb20621	refactor(docs): updated README images	2024-12-10 17:19:52 +03:00
SMKRV	6fc3b23365	refactor(docs): updated README images	2024-12-10 17:18:55 +03:00
SMKRV	15c717fcb0	fix: Display only last Q&A in sensor state to prevent data truncation - Show only the latest question and answer in sensor state - Keep full conversation history in attributes - Fix truncation issues in Home Assistant UI - Maintain backwards compatibility - No configuration changes required	2024-12-10 17:02:48 +03:00
SMKRV	be06fddce1	fix: Display only last Q&A in sensor state to prevent data truncation - Show only the latest question and answer in sensor state - Keep full conversation history in attributes - Fix truncation issues in Home Assistant UI - Maintain backwards compatibility - No configuration changes required	2024-12-10 16:19:17 +03:00
SMKRV	5f0bd861a7	docs(readme): Included note that the integration has been submitted to HACS store and is currently pending review in pull request: [pull request #2896 ](hacs/default#2896 ).	2024-12-10 00:00:18 +03:00
SMKRV	428aee46c8	docs(readme): Included note that the integration has been submitted to HACS store and is currently pending review in pull request: [pull request #2896 ](hacs/default#2896 ).	2024-12-09 23:59:51 +03:00
SMKRV	561bcf0b1d	docs(Code of Conduct): Add Code of Conduct to promote community guidelines - Implement Contributor Covenant Code of Conduct v1.4 - Establish clear expectations for community interactions - Define standards of acceptable and unacceptable behavior - Provide framework for reporting and addressing issues - Emphasize inclusivity and respect for all contributors	2024-12-09 16:52:44 +03:00
SMKRV	2b1e42c665	docs(readme): Included note that the integration has been submitted to HACS store and is currently pending review in pull request: [pull request #2893 ](https://github.com/hacs/default/pull/2893 ).	2024-12-09 15:29:53 +03:00
SMKRV	2d68f29ab5	bump to version 2.0.8	2024-12-09 00:41:28 +03:00
SMKRV	19d4a93bca	bump to version 2.0.8	2024-12-09 00:41:08 +03:00
SMKRV	fb75c5f44e	bump to version 2.0.9	2024-12-09 00:39:28 +03:00
SMKRV	52af987985	bump to version 2.0.9	2024-12-09 00:38:59 +03:00
SMKRV	162a30acdd	bump to version 2.0.8-beta	2024-12-07 00:48:17 +03:00
SMKRV	898a6fc638	bump to version 2.0.8-beta	2024-12-07 00:43:53 +03:00
SMKRV	38e2362be4	bump to version 2.0.8-beta	2024-12-06 16:51:32 +03:00
SMKRV	cea912d0b5	bump to version 2.0.8-beta	2024-12-06 16:51:09 +03:00
SMKRV	5ec00040c2	bump to version 2.0.8-beta	2024-12-06 16:50:26 +03:00
SMKRV	8d28fc4a0d	bump to version 2.0.8-beta	2024-12-06 16:46:11 +03:00
SMKRV	7cc6587724	bump to version 2.0.8-beta	2024-12-06 16:35:26 +03:00
SMKRV	bacf76e0a9	bump to version 2.0.8-beta	2024-12-06 16:33:46 +03:00
SMKRV	f86c7bfd57	refactor(docs): relocate README images from misc/ to assets/	2024-12-06 16:13:27 +03:00
SMKRV	2aaf340575	refactor(docs): relocate README images from misc/ to assets/	2024-12-06 16:11:13 +03:00
SMKRV	bae11ba85c	refactor(docs): relocate README images from misc/ to assets/	2024-12-06 16:10:04 +03:00
SMKRV	9eb7d8912c	fix: sensor history attribute calculation	2024-12-06 12:26:56 +03:00
SMKRV	d29535245f	Release v2.0.7-beta	2024-12-06 12:00:23 +03:00
SMKRV	ca3ae982b0	feat(performance): Optimize system resources and token estimation - Improve JSON history file processing - Add memory and disk space validation - Enhance parallel request handling - Refine token counting heuristics	2024-12-06 03:14:52 +03:00
SMKRV	0c4399b46c	feat(performance): Optimize system resources and token estimation - Improve JSON history file processing - Add memory and disk space validation - Enhance parallel request handling - Refine token counting heuristics	2024-12-06 02:53:41 +03:00
SMKRV	c13ef1921d	feat(performance): Optimize system resources and token estimation - Improve JSON history file processing - Add memory and disk space validation - Enhance parallel request handling - Refine token counting heuristics	2024-12-06 02:51:06 +03:00
SMKRV	0fb9acfa8f	docs:(README)	2024-12-05 02:00:24 +03:00
SMKRV	2ac4389e1a	docs:(README)	2024-12-05 01:55:31 +03:00
SMKRV	de194e425c	docs:(README)	2024-12-05 01:54:09 +03:00
SMKRV	95f3d6506e	docs:(README)	2024-12-05 01:49:26 +03:00
SMKRV	3e877243b9	docs:(README)	2024-12-05 01:46:28 +03:00
SMKRV	fd795c9e90	docs:(readme)	2024-12-05 00:36:08 +03:00
SMKRV	5f5dc041b9	docs: structure	2024-12-04 23:32:05 +03:00
SMKRV	3d3885d43d	Update README.md	2024-12-04 23:28:14 +03:00
smkrvandGitHub	b059744716	Update README.md	2024-12-04 23:23:46 +03:00
SMKRV	f2a41aaa2c	docs: logo	2024-12-04 20:13:08 +03:00
SMKRV	1fcf751d0d	docs: logo	2024-12-04 19:24:30 +03:00
SMKRV	a45c9407fd	docs: logo	2024-12-04 19:19:40 +03:00
SMKRV	21fdf108cf	docs: logo	2024-12-04 19:17:09 +03:00
SMKRV	c7ec2b3ea4	docs: logo	2024-12-04 19:13:57 +03:00
SMKRV	6c4da6cea5	docs: logo	2024-12-04 19:12:44 +03:00
SMKRV	3029c5dd26	docs: logo	2024-12-04 19:12:21 +03:00
SMKRV	3e97028094	docs: logo	2024-12-04 19:11:54 +03:00
SMKRV	1194c87134	docs: logo	2024-12-04 17:51:40 +03:00
SMKRV	e03b5315c2	logo update	2024-12-04 17:51:02 +03:00
SMKRV	fad887492f	docs: logo	2024-12-04 17:48:04 +03:00
SMKRV	f26df29937	docs: logo	2024-12-04 17:47:12 +03:00
SMKRV	69b54a08ba	logo update	2024-12-04 17:42:32 +03:00
SMKRV	7ce77eb18e	docs: logo	2024-12-04 17:36:18 +03:00
SMKRV	1480669dc8	icons update	2024-12-04 17:34:19 +03:00
SMKRV	f397bbffe7	Release 2.0.5-beta	2024-12-03 18:29:24 +03:00
SMKRV	5709bce1ae	docs(license): Switch to CC BY-NC-SA 4.0	2024-11-29 17:13:08 +03:00
SMKRV	d549a36c3a	docs(license): Switch to CC BY-NC-SA 4.0	2024-11-29 17:11:06 +03:00
SMKRV	e9ba480e95	docs: Update to beta	2024-11-29 16:57:32 +03:00
SMKRV	8ac7154399	docs: Update to beta	2024-11-29 16:54:41 +03:00