feat: Add ability to edit provider, API key, and endpoint in existing integrations

- Extended OptionsFlowHandler with two-step configuration flow - Step 1: Select provider (OpenAI, Anthropic, DeepSeek, Gemini) - Step 2: Configure API key, endpoint, model, and other settings - Auto-reload integration on options change - When switching providers, show appropriate default endpoint and model - Updated translations for all 8 languages
fix: Fix OptionsFlowHandler for HA 2024.1+ compatibility
2026-07-22 07:03:58 +08:00 · 2025-12-30 17:22:48 +03:00 · 2025-12-30 17:10:06 +03:00 · 2025-12-30 16:56:27 +03:00 · 2025-12-30 16:54:23 +03:00 · 2025-12-30 16:44:01 +03:00
38 changed files with 3689 additions and 1281 deletions
@@ -1,5 +1,6 @@
 name: Validate with hassfest
-
+permissions:
+  contents: read
 on:
  push:
    branches:
@@ -0,0 +1,37 @@
+name: Release
+
+on:
+  release:
+    types: [created]
+
+permissions:
+  contents: write
+
+jobs:
+  build:
+    name: Build and upload release asset
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Check out code
+        uses: actions/checkout@v4
+        with:
+          ref: ${{ github.event.release.tag_name }}
+
+      - name: Create zip archive
+        run: |
+          cd custom_components
+          zip -r ../ha_text_ai.zip ha_text_ai \
+            -x "ha_text_ai/__pycache__/*" \
+            -x "*.pyc" \
+            -x "*.pyo" \
+            -x "*/__pycache__/*" \
+            -x "*.DS_Store"
+
+      - name: Upload release asset
+        uses: softprops/action-gh-release@v2
+        with:
+          tag_name: ${{ github.event.release.tag_name }}
+          files: ha_text_ai.zip
+        env:
+          GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
@@ -1,4 +1,6 @@
 name: Validate
+permissions:
+  contents: read

 on:
  push:
@@ -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.
@@ -2,133 +2,200 @@

 <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-Default-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/main/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 2024.12.0 or later (recommended for best compatibility)
 - 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/Gemini
+- 🔑 **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  
+### 🤖 **Recommended Models**
+
+#### OpenAI Models
+- **GPT-5** - The latest flagship model, best for complex reasoning
+- **GPT-5 mini** - A cost-effective and fast model, suitable for most tasks
+
+#### Anthropic Claude Models  
+- **Claude Opus 4.1** - The most capable model for handling complex tasks
+- **Claude Sonnet 4** - Offers a balance between performance and cost
+- **Claude Haiku 4** - The fastest and most economical option in the series
+
+#### DeepSeek Models
+- **DeepSeek-V3.1** - A general-purpose model for a wide range of tasks
+- **DeepSeek-R1** - A specialized model focused on reasoning and coding
+
+#### Google Gemini Models
+- **Gemini 2.5 Pro & 2.5 Flash** - The newest and most advanced models available
+- **Gemini 2.0 Pro & 2.0 Flash** - Previous generation models that are still powerful and efficient
+
+<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"
-3. Click "..." in top right corner
-4. Select "Custom repositories"
-5. Add repository URL: `https://github.com/smkrv/ha-text-ai`
-6. Choose "Integration" as category
-7. Click "Download"
-8. Restart Home Assistant
+3. Search for "HA Text AI"
+4. Click "Download"
+5. Restart Home Assistant
+
+**Alternative Method (Custom Repository):**
+If the integration is not found in the default repository:
+1. Click "..." in top right corner of HACS
+2. Select "Custom repositories"
+3. Add repository URL: `https://github.com/smkrv/ha-text-ai`
+4. Choose "Integration" as category
+5. Click "Download"

 ### Manual Installation
 1. Download the latest release
@@ -144,7 +211,8 @@ 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)

@@ -152,7 +220,7 @@ To be compatible, a provider should support:
 ha_text_ai:
  api_provider: openai  # Required
  api_key: !secret ai_api_key  # Required
-  model: gpt-4o-mini  # Strongly recommended
+  model: gpt-4o  # Strongly recommended
  temperature: 0.7  # Optional
  max_tokens: 1000  # Optional
  request_interval: 1.0  # Optional
@@ -169,7 +237,7 @@ sensor:
  - platform: ha_text_ai
    name: "My AI Assistant"  # Required, unique identifier
    api_provider: openai  # Optional (inherits from platform)
-    model: "gpt-4o-mini"  # Optional
+    model: "gpt-4o"  # Optional
    temperature: 0.7  # Optional
    max_tokens: 1000  # Optional
 ```
@@ -180,14 +248,16 @@ sensor:

 | Parameter | Type | Required | Default | Description |
 |-----------|------|----------|---------|-------------|
-| `api_provider` | String | ✅ | - | AI service provider (openai, anthropic) |
+| `api_provider` | String | ✅ | - | AI service provider (openai, anthropic, deepseek, gemini) |
 | `api_key` | String | ✅ | - | Authentication key for AI service |
-| `model` | String | ⚠️ | Provider default | Strongly recommended: Specific AI model to use. If not specified, the provider's default model will be used |
-| `temperature` | Float | ❌ | 0.7 | Response creativity level (0.0-2.0) |
+| `model` | String | ⚠️ | gpt-4o-mini | Strongly recommended: Specific AI model to use. Default varies by provider |
+| `temperature` | Float | ❌ | 0.1 | Response creativity level (0.0-2.0) |
 | `max_tokens` | Integer | ❌ | 1000 | Maximum response length |
 | `request_interval` | Float | ❌ | 1.0 | Delay between API requests |
 | `api_endpoint` | URL | ⚠️ | Provider default | Custom API endpoint |
 | `system_prompt` | String | ❌ | - | Default context for AI interactions |
+| `max_history_size` | Integer | ❌ | 50 | Maximum number of conversation entries to store |
+| `context_messages` | Integer | ❌ | 5 | Number of previous messages to include in context (1-20) |

 #### Sensor Configuration

@@ -196,28 +266,58 @@ sensor:
 | `platform` | String | ✅ | - | Must be `ha_text_ai` |
 | `name` | String | ✅ | - | Unique sensor identifier |
 | `api_provider` | String | ❌ | Platform setting | Override global provider |
-| `model` | String | ⚠️ | Platform setting | Recommended: Override global model. If not specified, uses platform or provider default |
-| `temperature` | Float | ❌ | Platform setting | Override global temperature |
-| `max_tokens` | Integer | ❌ | Platform setting | Override global max tokens |
+| `model` | String | ⚠️ | Provider default | Recommended: Override global model (gpt-4o-mini, deepseek-chat, gemini-2.0-flash) |
+| `temperature` | Float | ❌ | 0.1 | Override global temperature |
+| `max_tokens` | Integer | ❌ | 1000 | Override global max tokens |
+
+</details>

 ## 🛠️ Available Services

+### 🔄 Response Variables (New!)
+
+**HA Text AI now supports response variables** - a powerful feature that returns AI responses directly from service calls, eliminating the need for separate text sensors and the 255-character limitation!
+
+#### ✨ Key Benefits:
+- **Unlimited response length** - No more 255-character truncation
+- **Direct data access** - Get responses immediately in automations
+- **Race condition prevention** - Eliminates conflicts in parallel automations
+- **Simplified workflows** - No need to read from sensors
+
 ### ask_question
 ```yaml
 service: ha_text_ai.ask_question
 data:
  question: "What's the optimal temperature for sleeping?"
-  model: "claude-3-sonnet"  # optional
+  model: "claude-3.5-sonnet"  # optional
  temperature: 0.5  # optional
  max_tokens: 500  # optional
  context_messages: 10  #optional, number of previous messages to include in context, default: 5
  system_prompt: "You are a sleep optimization expert"  # optional
+  instance: sensor.ha_text_ai_gpt
+response_variable: ai_response  # NEW! Store response data directly
+```
+
+#### 📊 Response Data Structure:
+```yaml
+# The service returns structured data:
+response_text: "The optimal sleeping temperature is 65-68°F (18-20°C)..."
+tokens_used: 150
+prompt_tokens: 50
+completion_tokens: 100
+model_used: "claude-3.5-sonnet"
+instance: "sensor.ha_text_ai_gpt"
+question: "What's the optimal temperature for sleeping?"
+timestamp: "2025-02-09T16:57:00.000Z"
+success: true
+# error: "Error message" (only present if success: false)
 ```

 ### 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
@@ -229,14 +329,163 @@ data:
 ### clear_history
 ```yaml
 service: ha_text_ai.clear_history
+data:
+  instance: sensor.ha_text_ai_gpt
 ```

 ### get_history
 ```yaml
 service: ha_text_ai.get_history
 data:
-  limit: 5  # optional
-  filter_model: "gpt-4o"  # optional
+  limit: 5  # optional, number of conversations to return (1-100)
+  filter_model: "gpt-4o"  # optional, filter by specific AI model
+  start_date: "2025-02-01"  # optional, filter conversations from this date
+  include_metadata: false  # optional, include tokens, response time, etc.
+  sort_order: "newest"  # optional, sort order: "newest" or "oldest"
+  instance: sensor.ha_text_ai_gpt
+```
+
+## 🚀 Advanced Automation Examples with Response Variables
+
+### Example 1: Smart Home Advice with Direct Response
+```yaml
+automation:
+  - alias: "Get AI Home Advice"
+    trigger:
+      - platform: state
+        entity_id: input_button.ask_ai_advice
+    action:
+      - service: ha_text_ai.ask_question
+        data:
+          question: "What's the best way to optimize energy usage in my home?"
+          instance: sensor.ha_text_ai_gpt
+        response_variable: ai_advice
+      - service: notify.mobile_app
+        data:
+          title: "🏠 Smart Home Tip"
+          message: |
+            {{ ai_advice.response_text }}
+            
+            📊 Tokens used: {{ ai_advice.tokens_used }}
+            🤖 Model: {{ ai_advice.model_used }}
+```
+
+### Example 2: Weather-Based AI Recommendations
+```yaml
+automation:
+  - alias: "Weather-Based AI Suggestions"
+    trigger:
+      - platform: numeric_state
+        entity_id: sensor.outdoor_temperature
+        below: 0
+    action:
+      - service: ha_text_ai.ask_question
+        data:
+          question: |
+            The outdoor temperature is {{ states('sensor.outdoor_temperature') }}°C. 
+            What should I do to prepare my home for freezing weather?
+          system_prompt: "You are a home maintenance expert. Provide practical, actionable advice."
+          instance: sensor.ha_text_ai_gpt
+        response_variable: winter_advice
+      - if:
+          - condition: template
+            value_template: "{{ winter_advice.success }}"
+        then:
+          - service: persistent_notification.create
+            data:
+              title: "❄️ Winter Preparation Advice"
+              message: |
+                {{ winter_advice.response_text }}
+                
+                Generated at: {{ winter_advice.timestamp }}
+        else:
+          - service: persistent_notification.create
+            data:
+              title: "⚠️ AI Service Error"
+              message: "Failed to get winter advice: {{ winter_advice.error }}"
+```
+
+### Example 3: Multi-Step AI Workflow
+```yaml
+automation:
+  - alias: "Multi-Step AI Analysis"
+    trigger:
+      - platform: state
+        entity_id: input_button.analyze_home_status
+    action:
+      # Step 1: Get current status analysis
+      - service: ha_text_ai.ask_question
+        data:
+          question: |
+            Current home status:
+            - Temperature: {{ states('sensor.indoor_temperature') }}°C
+            - Humidity: {{ states('sensor.indoor_humidity') }}%
+            - Energy usage: {{ states('sensor.power_consumption') }}W
+            
+            Analyze this data and provide insights.
+          instance: sensor.ha_text_ai_gpt
+        response_variable: status_analysis
+      
+      # Step 2: Get recommendations based on analysis
+      - service: ha_text_ai.ask_question
+        data:
+          question: |
+            Based on this analysis: "{{ status_analysis.response_text[:500] }}"
+            
+            Provide 3 specific actionable recommendations for improvement.
+          context_messages: 2  # Include previous conversation
+          instance: sensor.ha_text_ai_gpt
+        response_variable: recommendations
+      
+      # Step 3: Send comprehensive report
+      - service: notify.telegram
+        data:
+          title: "🏠 Home Analysis Report"
+          message: |
+            **Analysis:**
+            {{ status_analysis.response_text }}
+            
+            **Recommendations:**
+            {{ recommendations.response_text }}
+            
+            **Report Details:**
+            - Total tokens used: {{ status_analysis.tokens_used + recommendations.tokens_used }}
+            - Analysis model: {{ status_analysis.model_used }}
+            - Generated: {{ recommendations.timestamp }}
+```
+
+### 💡 Migration from Sensors to Response Variables
+
+#### Old Method (Limited):
+```yaml
+# ❌ Old way - limited to 255 characters, race conditions
+automation:
+  - alias: "Old AI Response Method"
+    action:
+      - service: ha_text_ai.ask_question
+        data:
+          question: "Long question here..."
+          instance: sensor.ha_text_ai_gpt
+      - delay: "00:00:05"  # Wait for sensor update
+      - service: notify.mobile
+        data:
+          message: "{{ state_attr('sensor.ha_text_ai_gpt', 'response')[:255] }}..."  # Truncated!
+```
+
+#### New Method (Unlimited):
+```yaml
+# ✅ New way - unlimited length, immediate access, no race conditions
+automation:
+  - alias: "New AI Response Method"
+    action:
+      - service: ha_text_ai.ask_question
+        data:
+          question: "Long question here..."
+          instance: sensor.ha_text_ai_gpt
+        response_variable: ai_response  # Direct access!
+      - service: notify.mobile
+        data:
+          message: "{{ ai_response.response_text }}"  # Full response, no truncation!
 ```

 ### 🏷️ HA Text AI Sensor Naming Convention
@@ -256,7 +505,7 @@ 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 +522,7 @@ 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 +539,16 @@ 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 +604,12 @@ 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
@@ -370,19 +636,27 @@ 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

 **Q: Which AI providers are supported?**
-A: Currently OpenAI (GPT models) and Anthropic (Claude models) are supported, with more providers planned.
+A: OpenAI (GPT models), Anthropic (Claude models), DeepSeek, Google Gemini, and OpenRouter are officially supported, with many other OpenAI-compatible providers working as well.

 **Q: How can I reduce API costs?**
-A: Use GPT-3.5-Turbo or Claude-3-Sonnet for most queries, implement caching, and optimize token usage.
+A: Use gpt-4o-mini or claude-3.5-haiku for most queries, implement caching, and optimize token usage.

 **Q: Are there limitations on the number of requests?**
 A: Depends on your API provider's plan. We recommend monitoring usage and implementing request throttling via `request_interval` configuration.
@@ -393,8 +667,11 @@ A: Yes, you can configure custom endpoints and use any compatible model by speci
 **Q: How do I switch between different AI providers?**
 A: Simply change the model parameter in your configuration or service calls to use the desired provider's model.

-**Q: How can I reduce API costs?**
-A: Use GPT-3.5-Turbo for most queries, implement caching, and optimize token usage.
+**Q: What are the token limits for different models?**
+A: Token limits vary by provider and model. OpenAI's gpt-4o supports up to 128K tokens, Claude 3.5 Sonnet supports up to 200K tokens, while smaller models typically have 8K-32K limits. Check your provider's documentation for specific limits.
+
+**Q: How do I monitor token usage?**
+A: Use the sensor attributes like `Total tokens`, `Prompt tokens`, and `Completion tokens` to track usage. You can also create automations to alert you when usage exceeds certain thresholds.

 **Q: Is my data secure?**
 A: Yes, your data is secure. The system operates entirely on your local machine, keeping your data under your control. API keys are stored securely and all external communications use encrypted connections.
@@ -402,6 +679,15 @@ 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 +714,7 @@ 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

@@ -448,10 +734,12 @@ 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

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

 </div>
+ 
@@ -0,0 +1,148 @@
+# Using response_variable with HA Text AI
+
+After updating the HA Text AI integration, it now supports using the `response_variable` parameter in Home Assistant scripts and automations.
+
+## What Changed
+
+- Added response schema support in the `ha_text_ai.ask_question` service
+- Service is now correctly registered with `supports_response=True` flag
+- You can now use `response_variable` to capture AI response in a variable
+
+## Example Usage in Script
+
+```yaml
+action: ha_text_ai.ask_question
+data:
+  context_messages: 0
+  temperature: 0.7
+  max_tokens: 1000
+  instance: sensor.ha_text_ai_gemini
+  question: "What time is it?"
+response_variable: ai_response
+```
+
+## Example Usage in Automation
+
+```yaml
+alias: "Get AI Response"
+trigger:
+  - platform: state
+    entity_id: input_boolean.ask_ai
+    to: "on"
+action:
+  - action: ha_text_ai.ask_question
+    data:
+      instance: sensor.ha_text_ai_gemini
+      question: "What's the current weather?"
+      temperature: 0.7
+      max_tokens: 500
+    response_variable: weather_response
+  
+  - action: notify.persistent_notification
+    data:
+      title: "AI Response"
+      message: "{{ weather_response.response_text }}"
+```
+
+## Available Fields in response_variable
+
+When you use `response_variable`, you will receive an object with the following fields:
+
+- `response_text` (string) - The AI response text
+- `tokens_used` (integer) - Total number of tokens used
+- `prompt_tokens` (integer) - Number of tokens in the prompt
+- `completion_tokens` (integer) - Number of tokens in the completion
+- `model_used` (string) - The AI model that was used for the response
+- `instance` (string) - The instance name that was used
+- `question` (string) - The original question that was asked
+- `timestamp` (string) - ISO timestamp when the response was generated
+- `success` (boolean) - Whether the request was successful
+- `error` (string) - Error message if the request failed
+
+## Example Using Response Fields
+
+```yaml
+action:
+  - action: ha_text_ai.ask_question
+    data:
+      instance: sensor.ha_text_ai_gemini
+      question: "Tell me a joke"
+    response_variable: joke_response
+  
+  - condition: template
+    value_template: "{{ joke_response.success }}"
+  
+  - action: input_text.set_value
+    target:
+      entity_id: input_text.last_ai_response
+    data:
+      value: "{{ joke_response.response_text }}"
+  
+  - action: input_number.set_value
+    target:
+      entity_id: input_number.tokens_used
+    data:
+      value: "{{ joke_response.tokens_used }}"
+```
+
+## Error Handling
+
+```yaml
+action:
+  - action: ha_text_ai.ask_question
+    data:
+      instance: sensor.ha_text_ai_gemini
+      question: "Test question"
+    response_variable: ai_result
+  
+  - choose:
+      - conditions:
+          - condition: template
+            value_template: "{{ ai_result.success }}"
+        sequence:
+          - action: notify.mobile_app_phone
+            data:
+              title: "AI Response"
+              message: "{{ ai_result.response_text }}"
+      - conditions:
+          - condition: template
+            value_template: "{{ not ai_result.success }}"
+        sequence:
+          - action: notify.mobile_app_phone
+            data:
+              title: "AI Error"
+              message: "Error: {{ ai_result.error }}"
+```
+
+## Migration from Old Approach
+
+**Old method (without response_variable):**
+```yaml
+# Ask question
+- action: ha_text_ai.ask_question
+  data:
+    instance: sensor.ha_text_ai_gemini
+    question: "Hello!"
+
+# Wait and read response from sensor
+- delay: 00:00:05
+- action: notify.mobile_app_phone
+  data:
+    message: "{{ states('sensor.ha_text_ai_gemini') }}"
+```
+
+**New method (with response_variable):**
+```yaml
+# Ask question and get response immediately
+- action: ha_text_ai.ask_question
+  data:
+    instance: sensor.ha_text_ai_gemini
+    question: "Hello!"
+  response_variable: greeting_response
+
+- action: notify.mobile_app_phone
+  data:
+    message: "{{ greeting_response.response_text }}"
+```
+
+The new approach is more reliable as it doesn't require waiting and reading from the sensor.
@@ -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
@@ -34,29 +35,38 @@ from .const import (
    CONF_MAX_TOKENS,
    CONF_API_ENDPOINT,
    CONF_REQUEST_INTERVAL,
+    CONF_API_TIMEOUT,
    CONF_API_PROVIDER,
    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_API_TIMEOUT,
    DEFAULT_CONTEXT_MESSAGES,
-    API_TIMEOUT,
    SERVICE_ASK_QUESTION,
    SERVICE_CLEAR_HISTORY,
    SERVICE_GET_HISTORY,
    SERVICE_SET_SYSTEM_PROMPT,
    DEFAULT_MAX_HISTORY,
    CONF_MAX_HISTORY_SIZE,
+    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,
@@ -66,6 +76,8 @@ SERVICE_SCHEMA_ASK_QUESTION = vol.Schema({
    vol.Optional("temperature"): cv.positive_float,
    vol.Optional("max_tokens"): cv.positive_int,
    vol.Optional("context_messages"): cv.positive_int,
+    vol.Optional("structured_output", default=False): cv.boolean,
+    vol.Optional("json_schema"): cv.string,
 })

 SERVICE_SCHEMA_SET_SYSTEM_PROMPT = vol.Schema({
@@ -77,6 +89,9 @@ SERVICE_SCHEMA_GET_HISTORY = vol.Schema({
    vol.Required("instance"): cv.string,
    vol.Optional("limit"): cv.positive_int,
    vol.Optional("filter_model"): cv.string,
+    vol.Optional("start_date"): cv.string,
+    vol.Optional("include_metadata"): cv.boolean,
+    vol.Optional("sort_order"): vol.In(["newest", "oldest"]),
 })

 def get_coordinator_by_instance(hass: HomeAssistant, instance: str) -> HATextAICoordinator:
@@ -90,35 +105,61 @@ 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."""
+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()
+
+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, {})

-    try:
-        source = os.path.join(os.path.dirname(__file__), 'icons', 'icon.svg')
-        dest_dir = os.path.join(hass.config.path('www'), 'icons')
-        os.makedirs(dest_dir, exist_ok=True)
-        dest = os.path.join(dest_dir, 'icon.png')
-        if not os.path.exists(dest):
-            shutil.copyfile(source, dest)
-    except Exception as ex:
-        _LOGGER.warning("Failed to copy custom icon: %s", str(ex))
-
-    async def async_ask_question(call: ServiceCall) -> None:
-        """Handle ask_question service."""
+    async def async_ask_question(call: ServiceCall) -> dict:
+        """Handle ask_question service with response data."""
        try:
            coordinator = get_coordinator_by_instance(hass, call.data["instance"])
-            await coordinator.async_ask_question(
+            response = await coordinator.async_ask_question(
                question=call.data["question"],
                model=call.data.get("model"),
                temperature=call.data.get("temperature"),
                max_tokens=call.data.get("max_tokens"),
                system_prompt=call.data.get("system_prompt"),
                context_messages=call.data.get("context_messages"),
+                structured_output=call.data.get("structured_output", False),
+                json_schema=call.data.get("json_schema"),
            )
+            
+            # Return structured response data
+            return {
+                "response_text": response.get("content", ""),
+                "tokens_used": response.get("tokens", {}).get("total", 0),
+                "prompt_tokens": response.get("tokens", {}).get("prompt", 0),
+                "completion_tokens": response.get("tokens", {}).get("completion", 0),
+                "model_used": response.get("model", call.data.get("model", coordinator.model)),
+                "instance": call.data["instance"],
+                "question": call.data["question"],
+                "timestamp": response.get("timestamp"),
+                "success": True
+            }
        except Exception as err:
            _LOGGER.error("Error asking question: %s", str(err))
-            raise HomeAssistantError(f"Failed to process question: {str(err)}")
+            # Return error response
+            return {
+                "response_text": "",
+                "tokens_used": 0,
+                "prompt_tokens": 0,
+                "completion_tokens": 0,
+                "model_used": call.data.get("model", ""),
+                "instance": call.data["instance"],
+                "question": call.data["question"],
+                "timestamp": datetime.now().isoformat(),
+                "success": False,
+                "error": str(err)
+            }

    async def async_clear_history(call: ServiceCall) -> None:
        """Handle clear_history service."""
@@ -135,7 +176,10 @@ async def async_setup(hass: HomeAssistant, config: Dict[str, Any]) -> bool:
            coordinator = get_coordinator_by_instance(hass, call.data["instance"])
            return await coordinator.async_get_history(
                limit=call.data.get("limit"),
-                filter_model=call.data.get("filter_model")
+                filter_model=call.data.get("filter_model"),
+                start_date=call.data.get("start_date"),
+                include_metadata=call.data.get("include_metadata", False),
+                sort_order=call.data.get("sort_order", "newest")
            )
        except Exception as err:
            _LOGGER.error("Error getting history: %s", str(err))
@@ -150,11 +194,13 @@ 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,
        async_ask_question,
-        schema=SERVICE_SCHEMA_ASK_QUESTION
+        schema=SERVICE_SCHEMA_ASK_QUESTION,
+        supports_response=True
    )

    hass.services.async_register(
@@ -178,22 +224,79 @@ 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:
+async def async_check_api(session, endpoint: str, headers: dict, provider: str, api_timeout: int = DEFAULT_API_TIMEOUT) -> bool:
    """Check API availability for different providers."""
    try:
-        if provider == API_PROVIDER_ANTHROPIC:
+        if provider == API_PROVIDER_GEMINI:
+            # Gemini API does not support GET /models for validation, just check key presence
+            if headers.get("Authorization", "").replace("Bearer ", ""):
+                return True
+            else:
+                _LOGGER.error("Gemini API key is missing or empty")
+                return False
+        elif provider == API_PROVIDER_ANTHROPIC:
            check_url = f"{endpoint}/v1/models"
+        elif provider == API_PROVIDER_DEEPSEEK:
+            check_url = f"{endpoint}/models"
        else:  # OpenAI
            check_url = f"{endpoint}/models"

-        async with timeout(API_TIMEOUT):
+        async with timeout(api_timeout):
            async with session.get(check_url, headers=headers) as response:
                if response.status in [200, 404]:
                    return True
                elif response.status == 401:
-                    raise ConfigEntryNotReady("Invalid API key")
+                    _LOGGER.error("Invalid API key")
+                    return False
                elif response.status == 429:
                    _LOGGER.warning("Rate limit exceeded during API check")
                    return False
@@ -209,26 +312,42 @@ async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
    _LOGGER.debug(f"Setting up HA Text AI entry: {entry.data}")

    try:
-        if CONF_API_PROVIDER not in entry.data:
+        # Get provider from data or options (options takes precedence)
+        config = {**entry.data, **entry.options}
+        api_provider = config.get(CONF_API_PROVIDER)
+
+        if not api_provider:
            _LOGGER.error("API provider not specified")
            raise ConfigEntryNotReady("API provider is required")

-        # Get configuration
        session = aiohttp_client.async_get_clientsession(hass)
-        api_provider = entry.data.get(CONF_API_PROVIDER)
-        model = entry.data.get(CONF_MODEL, DEFAULT_MODEL)
-        endpoint = entry.data.get(
-            CONF_API_ENDPOINT,
-            DEFAULT_OPENAI_ENDPOINT if api_provider == API_PROVIDER_OPENAI
-            else DEFAULT_ANTHROPIC_ENDPOINT
-        ).rstrip('/')
-        api_key = entry.data[CONF_API_KEY]
+
+        # Get default endpoint based on 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(api_provider, DEFAULT_OPENAI_ENDPOINT)
+
+        # Get default model based on provider
+        default_model = (
+            DEFAULT_DEEPSEEK_MODEL if api_provider == API_PROVIDER_DEEPSEEK else
+            DEFAULT_GEMINI_MODEL if api_provider == API_PROVIDER_GEMINI else
+            DEFAULT_MODEL
+        )
+
+        model = config.get(CONF_MODEL, default_model)
+        endpoint = config.get(CONF_API_ENDPOINT, default_endpoint).rstrip('/')
+        # API key can now be updated via options
+        api_key = config.get(CONF_API_KEY, entry.data.get(CONF_API_KEY))
        instance_name = entry.data.get(CONF_NAME, entry.entry_id)
-        request_interval = entry.data.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)
-        max_tokens = entry.data.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)
-        temperature = entry.data.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)
-        max_history_size = entry.data.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY)
-        context_messages = entry.data.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES)
+        request_interval = config.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)
+        api_timeout = config.get(CONF_API_TIMEOUT, DEFAULT_API_TIMEOUT)
+        max_tokens = config.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)
+        temperature = config.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)
+        max_history_size = config.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY)
+        context_messages = config.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES)
        is_anthropic = api_provider == API_PROVIDER_ANTHROPIC

        headers = {
@@ -242,7 +361,7 @@ async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
        else:
            headers["Authorization"] = f"Bearer {api_key}"

-        if not await async_check_api(session, endpoint, headers, api_provider):
+        if not await async_check_api(session, endpoint, headers, api_provider, api_timeout):
            raise ConfigEntryNotReady("API connection failed")

        _LOGGER.debug("Creating API client for %s with endpoint %s", api_provider, endpoint)
@@ -253,6 +372,7 @@ async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
            headers=headers,
            api_provider=api_provider,
            model=model,
+            api_timeout=api_timeout,
        )

        coordinator = HATextAICoordinator(
@@ -266,6 +386,7 @@ async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
            max_history_size=max_history_size,
            context_messages=context_messages,
            is_anthropic=is_anthropic,
+            api_timeout=api_timeout,
        )

        _LOGGER.debug(f"Created coordinator for {instance_name}")
@@ -279,6 +400,9 @@ async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
        # Set up platforms
        await hass.config_entries.async_forward_entry_setups(entry, PLATFORMS)

+        # Register update listener for options changes
+        entry.async_on_unload(entry.add_update_listener(async_update_options))
+
        _LOGGER.debug(f"Setup completed for {instance_name}")

        return True
@@ -287,6 +411,12 @@ async def async_setup_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
        _LOGGER.exception(f"Error setting up HA Text AI: {err}")
        raise

+async def async_update_options(hass: HomeAssistant, entry: ConfigEntry) -> None:
+    """Handle options update - reload the config entry."""
+    _LOGGER.info("Options updated for %s, reloading integration", entry.title)
+    await hass.config_entries.async_reload(entry.entry_id)
+
+
 async def async_unload_entry(hass: HomeAssistant, entry: ConfigEntry) -> bool:
    """Unload a config entry."""
    try:
@@ -11,13 +11,17 @@ import asyncio
 from typing import Any, Dict, List, Optional
 from aiohttp import ClientSession, ClientTimeout
 from async_timeout import timeout
+from datetime import datetime, timedelta

 from homeassistant.core import HomeAssistant
 from homeassistant.exceptions import HomeAssistantError
 from .const import (
-    API_TIMEOUT,
+    DEFAULT_API_TIMEOUT,
    API_RETRY_COUNT,
    API_PROVIDER_ANTHROPIC,
+    API_PROVIDER_DEEPSEEK,
+    API_PROVIDER_OPENAI,
+    API_PROVIDER_GEMINI,
    MIN_TEMPERATURE,
    MAX_TEMPERATURE,
    MIN_MAX_TOKENS,
@@ -37,6 +41,7 @@ class APIClient:
        headers: Dict[str, str],
        api_provider: str,
        model: str,
+        api_timeout: int = DEFAULT_API_TIMEOUT,
    ) -> None:
        """Initialize API client."""
        self.session = session
@@ -44,21 +49,38 @@ class APIClient:
        self.headers = headers
        self.api_provider = api_provider
        self.model = model
-        self.timeout = ClientTimeout(total=API_TIMEOUT)
+        self.api_timeout = api_timeout
+        self.timeout = ClientTimeout(total=api_timeout)
+        self._closed = False
+
+    async def __aenter__(self):
+        """Async context manager entry."""
+        return self
+
+    async def __aexit__(self, exc_type, exc_val, exc_tb):
+        """Async context manager exit."""
+        await self.shutdown()

    def _validate_parameters(
        self,
        temperature: float,
        max_tokens: int,
    ) -> None:
-        """Validate API parameters."""
+        """Validate API parameters with enhanced type checking."""
+        # Type validation
+        if not isinstance(temperature, (int, float)):
+            raise TypeError(f"Temperature must be a number, got {type(temperature)}")
+        if not isinstance(max_tokens, int):
+            raise TypeError(f"Max tokens must be an integer, got {type(max_tokens)}")
+            
+        # Range validation
        if not MIN_TEMPERATURE <= temperature <= MAX_TEMPERATURE:
            raise ValueError(
-                f"Temperature must be between {MIN_TEMPERATURE} and {MAX_TEMPERATURE}"
+                f"Temperature must be between {MIN_TEMPERATURE} and {MAX_TEMPERATURE}, got {temperature}"
            )
        if not MIN_MAX_TOKENS <= max_tokens <= MAX_MAX_TOKENS:
            raise ValueError(
-                f"Max tokens must be between {MIN_MAX_TOKENS} and {MAX_MAX_TOKENS}"
+                f"Max tokens must be between {MIN_MAX_TOKENS} and {MAX_MAX_TOKENS}, got {max_tokens}"
            )

    async def _make_request(
@@ -67,10 +89,13 @@ class APIClient:
        payload: Dict[str, Any],
    ) -> Dict[str, Any]:
        """Make API request with retry logic."""
-        _LOGGER.debug(f"API Request: URL={url}, Payload={payload}")
+        # Log request without sensitive data
+        safe_payload = {k: v for k, v in payload.items() if k not in ['messages', 'system']}
+        _LOGGER.debug(f"API Request: URL={url}, Safe payload: {safe_payload}")
+        
        for attempt in range(API_RETRY_COUNT):
            try:
-                async with timeout(API_TIMEOUT):
+                async with timeout(self.api_timeout):
                    async with self.session.post(
                        url,
                        json=payload,
@@ -80,16 +105,18 @@ class APIClient:
                        _LOGGER.debug(f"Response status: {response.status}")
                        if response.status != 200:
                            error_data = await response.json()
-                            _LOGGER.error(f"API error: {error_data}")
-                            raise HomeAssistantError(f"API error: {error_data}")
+                            # Log error without sensitive data
+                            safe_error = {k: v for k, v in error_data.items() if k not in ['message', 'details']}
+                            _LOGGER.error(f"API error (status {response.status}): {safe_error}")
+                            raise HomeAssistantError(f"API error: status {response.status}")
                        return await response.json()
            except asyncio.TimeoutError:
-                _LOGGER.warning(f"Timeout on attempt {attempt + 1}")
+                _LOGGER.warning(f"Timeout on attempt {attempt + 1}/{API_RETRY_COUNT}")
                if attempt == API_RETRY_COUNT - 1:
                    raise HomeAssistantError("API request timed out")
                await asyncio.sleep(1 * (attempt + 1))
            except Exception as e:
-                _LOGGER.warning(f"API request failed on attempt {attempt + 1}: {str(e)}")
+                _LOGGER.warning(f"API request failed on attempt {attempt + 1}/{API_RETRY_COUNT}: {type(e).__name__}")
                if attempt == API_RETRY_COUNT - 1:
                    raise
                await asyncio.sleep(1 * (attempt + 1))
@@ -100,6 +127,8 @@ class APIClient:
        messages: List[Dict[str, str]],
        temperature: float,
        max_tokens: int,
+        structured_output: bool = False,
+        json_schema: Optional[str] = None,
    ) -> Dict[str, Any]:
        """Create completion using appropriate API."""
        try:
@@ -107,27 +136,87 @@ class APIClient:

            if self.api_provider == API_PROVIDER_ANTHROPIC:
                return await self._create_anthropic_completion(
-                    model, messages, temperature, max_tokens
+                    model, messages, temperature, max_tokens,
+                    structured_output, json_schema
+                )
+            elif self.api_provider == API_PROVIDER_DEEPSEEK:
+                return await self._create_deepseek_completion(
+                    model, messages, temperature, max_tokens,
+                    structured_output, json_schema
+                )
+            elif self.api_provider == API_PROVIDER_GEMINI:
+                return await self._create_gemini_completion(
+                    model, messages, temperature, max_tokens,
+                    structured_output, json_schema
                )
            else:
                return await self._create_openai_completion(
-                    model, messages, temperature, max_tokens
+                    model, messages, temperature, max_tokens,
+                    structured_output, json_schema
                )
-        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,
+        structured_output: bool = False,
+        json_schema: Optional[str] = None,
+    ) -> 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
+        }
+
+        # Add structured output format if enabled (DeepSeek is OpenAI-compatible)
+        if structured_output and json_schema:
+            try:
+                import json
+                schema = json.loads(json_schema)
+                payload["response_format"] = {
+                    "type": "json_schema",
+                    "json_schema": {
+                        "name": "structured_response",
+                        "strict": True,
+                        "schema": schema
+                    }
+                }
+                _LOGGER.debug("DeepSeek structured output enabled with schema")
+            except json.JSONDecodeError as e:
+                _LOGGER.warning(f"Invalid JSON schema provided: {e}. Falling back to json_object mode.")
+                payload["response_format"] = {"type": "json_object"}
+
+        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,
        messages: List[Dict[str, str]],
        temperature: float,
        max_tokens: int,
+        structured_output: bool = False,
+        json_schema: Optional[str] = None,
    ) -> Dict[str, Any]:
        """Create completion using OpenAI API."""
        url = f"{self.endpoint}/chat/completions"
@@ -138,6 +227,24 @@ class APIClient:
            "max_tokens": max_tokens,
        }

+        # Add structured output format if enabled
+        if structured_output and json_schema:
+            try:
+                import json
+                schema = json.loads(json_schema)
+                payload["response_format"] = {
+                    "type": "json_schema",
+                    "json_schema": {
+                        "name": "structured_response",
+                        "strict": True,
+                        "schema": schema
+                    }
+                }
+                _LOGGER.debug("OpenAI structured output enabled with schema")
+            except json.JSONDecodeError as e:
+                _LOGGER.warning(f"Invalid JSON schema provided: {e}. Falling back to json_object mode.")
+                payload["response_format"] = {"type": "json_object"}
+
        data = await self._make_request(url, payload)
        return {
            "choices": [
@@ -158,6 +265,8 @@ class APIClient:
        messages: List[Dict[str, str]],
        temperature: float,
        max_tokens: int,
+        structured_output: bool = False,
+        json_schema: Optional[str] = None,
    ) -> Dict[str, Any]:
        """Create completion using Anthropic API."""
        url = f"{self.endpoint}/v1/messages"
@@ -173,6 +282,20 @@ class APIClient:
            else:
                filtered_messages.append(msg)

+        # For Anthropic, add structured output instruction to system prompt
+        if structured_output and json_schema:
+            schema_instruction = (
+                f"\n\nIMPORTANT: You MUST respond ONLY with valid JSON that matches "
+                f"this JSON Schema:\n{json_schema}\n"
+                f"Do not include any text before or after the JSON. "
+                f"Do not wrap the JSON in markdown code blocks."
+            )
+            if system_prompt:
+                system_prompt += schema_instruction
+            else:
+                system_prompt = schema_instruction.strip()
+            _LOGGER.debug("Anthropic structured output enabled via system prompt")
+
        payload = {
            "model": model,
            "messages": filtered_messages,
@@ -206,7 +329,164 @@ 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,
+        structured_output: bool = False,
+        json_schema: Optional[str] = None,
+    ) -> Dict[str, Any]:
+        """Create completion using Gemini API with google-genai library.
+
+        Args:
+            model: The model name to use
+            messages: List of message dictionaries with role and content
+            temperature: Sampling temperature between 0.0 and 2.0
+            max_tokens: Maximum number of tokens to generate
+            structured_output: Enable JSON structured output mode
+            json_schema: JSON Schema for structured output validation
+
+        Returns:
+            Dictionary with response content and token usage
+        """
+        try:
+            def import_genai():
+                from google import genai
+                return genai
+
+            genai = await asyncio.to_thread(import_genai)
+
+            # Extract API key from headers (Bearer token)
+            api_key = self.headers.get("Authorization", "").replace("Bearer ", "")
+
+            def create_client():
+                if self.endpoint and self.endpoint != "https://generativelanguage.googleapis.com/v1beta":
+                    return genai.Client(api_key=api_key, transport="rest",
+                                       client_options={"api_endpoint": self.endpoint})
+                else:
+                    return genai.Client(api_key=api_key)
+
+            client = await asyncio.to_thread(create_client)
+
+            # Process messages to extract system instruction and chat history
+            system_instruction = ""
+            contents = []
+
+            for msg in messages:
+                if msg['role'] == 'system':
+                    system_instruction += msg['content'] + "\n"
+                else:
+                    # For chat history, we need to convert to the format Gemini expects
+                    role = "user" if msg['role'] == 'user' else "model"
+                    contents.append({
+                        "role": role,
+                        "parts": [{"text": msg['content']}]
+                    })
+
+            # Parse JSON schema if structured output is enabled
+            parsed_schema = None
+            if structured_output and json_schema:
+                try:
+                    import json
+                    parsed_schema = json.loads(json_schema)
+                    _LOGGER.debug("Gemini structured output enabled with schema")
+                except json.JSONDecodeError as e:
+                    _LOGGER.warning(f"Invalid JSON schema provided: {e}. Structured output disabled.")
+
+            # Create configuration
+            def create_config():
+                from google.genai import types
+                config = types.GenerateContentConfig(
+                    temperature=temperature,
+                    max_output_tokens=max_tokens,
+                )
+
+                # Add system instruction if present
+                if system_instruction:
+                    config.system_instruction = system_instruction.strip()
+
+                # Add structured output configuration for Gemini
+                if structured_output and parsed_schema:
+                    config.response_mime_type = "application/json"
+                    config.response_schema = parsed_schema
+
+                return config
+
+            config = await asyncio.to_thread(create_config)
+
+            def generate_content():
+                # For single message without history, use generate_content
+                if len(contents) <= 1:
+                    # If we have no content yet, create a simple prompt
+                    if not contents:
+                        prompt = "I need your assistance."
+                    else:
+                        prompt = contents[0]["parts"][0]["text"]
+
+                    return client.models.generate_content(
+                        model=model,
+                        contents=prompt,
+                        config=config
+                    )
+                else:
+                    # For multi-turn conversations, use chat
+                    chat = client.chats.create(model=model, config=config)
+
+                    # Send all messages in sequence
+                    for content in contents:
+                        if content["role"] == "user":
+                            response = chat.send_message(content["parts"][0]["text"])
+                            # We don't send assistant messages as they're already part of the history
+
+                    return response
+
+            response = await asyncio.to_thread(generate_content)
+
+            # Extract response text
+            def extract_response():
+                response_text = response.text if hasattr(response, 'text') else ""
+
+                # Try to get token usage if available
+                usage = {}
+                if hasattr(response, 'usage_metadata'):
+                    usage = {
+                        "prompt_tokens": getattr(response.usage_metadata, 'prompt_token_count', 0),
+                        "completion_tokens": getattr(response.usage_metadata, 'candidates_token_count', 0),
+                        "total_tokens": getattr(response.usage_metadata, 'total_token_count', 0)
+                    }
+                else:
+                    # Estimate token count as fallback
+                    usage = {
+                        "prompt_tokens": len(" ".join([m["content"] for m in messages]).split()) // 3,
+                        "completion_tokens": len(response_text.split()) // 3,
+                        "total_tokens": 0  # Will be calculated below
+                    }
+                    usage["total_tokens"] = usage["prompt_tokens"] + usage["completion_tokens"]
+
+                return response_text, usage
+
+            response_text, usage = await asyncio.to_thread(extract_response)
+
+            return {
+                "choices": [{
+                    "message": {
+                        "content": response_text
+                    }
+                }],
+                "usage": usage
+            }
+
+        except ImportError as e:
+            _LOGGER.error(f"Google Gemini library not installed: {str(e)}")
+            raise HomeAssistantError(f"Missing dependency: {str(e)}. Please install google-genai.")
+        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")
-        await self.session.close()
+        self._closed = True
+        # Do NOT close the shared Home Assistant session
@@ -8,6 +8,7 @@ Config flow for HA text AI integration.
 """
 import logging
 from typing import Any, Dict, Optional
+from datetime import datetime, timedelta

 import voluptuous as vol
 from homeassistant import config_entries
@@ -24,23 +25,33 @@ from .const import (
    CONF_MAX_TOKENS,
    CONF_API_ENDPOINT,
    CONF_REQUEST_INTERVAL,
+    CONF_API_TIMEOUT,
    CONF_API_PROVIDER,
    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_API_TIMEOUT,
    DEFAULT_OPENAI_ENDPOINT,
    DEFAULT_ANTHROPIC_ENDPOINT,
+    DEFAULT_DEEPSEEK_ENDPOINT,
+    DEFAULT_GEMINI_ENDPOINT,
    DEFAULT_CONTEXT_MESSAGES,
    MIN_TEMPERATURE,
    MAX_TEMPERATURE,
    MIN_MAX_TOKENS,
    MAX_MAX_TOKENS,
    MIN_REQUEST_INTERVAL,
+    MIN_API_TIMEOUT,
+    MAX_API_TIMEOUT,
    DEFAULT_NAME_PREFIX,
    DEFAULT_MAX_HISTORY,
    CONF_MAX_HISTORY_SIZE,
@@ -90,9 +101,19 @@ 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 +121,7 @@ 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),
@@ -114,6 +135,10 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
                        vol.Coerce(float),
                        vol.Range(min=MIN_REQUEST_INTERVAL)
                    ),
+                    vol.Optional(CONF_API_TIMEOUT, default=DEFAULT_API_TIMEOUT): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=MIN_API_TIMEOUT, max=MAX_API_TIMEOUT)
+                    ),
                    vol.Optional(
                        CONF_CONTEXT_MESSAGES,
                        default=DEFAULT_CONTEXT_MESSAGES
@@ -131,43 +156,185 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
                })
            )

+        # Debug log to identify what's in the input
+        _LOGGER.debug(f"Provider step input data: {user_input}")
+
        input_copy = user_input.copy()

+        # Check if CONF_NAME exists in input_copy and ensure it's not empty
+        if CONF_NAME not in input_copy or not input_copy[CONF_NAME]:
+            _LOGGER.warning(f"Missing name in configuration input: {input_copy}")
+            input_copy[CONF_NAME] = f"gemini_assistant_{datetime.now().strftime('%Y%m%d_%H%M%S')}"
+            _LOGGER.info(f"Auto-generated name: {input_copy[CONF_NAME]}")
+
+        # Ensure API key is present
+        if CONF_API_KEY not in input_copy or not input_copy[CONF_API_KEY]:
+            self._errors["base"] = "invalid_auth"
+            _LOGGER.error("API validation error: 'api_key'")
+            return self.async_show_form(
+                step_id="provider",
+                data_schema=vol.Schema({
+                    vol.Required(CONF_NAME, default=input_copy.get(CONF_NAME, "my_assistant")): str,
+                    vol.Required(CONF_API_KEY): str,
+                    vol.Required(CONF_MODEL, default=input_copy.get(CONF_MODEL, DEFAULT_GEMINI_MODEL if self._provider == API_PROVIDER_GEMINI else DEFAULT_MODEL)): str,
+                    vol.Required(CONF_API_ENDPOINT, default=input_copy.get(CONF_API_ENDPOINT, DEFAULT_GEMINI_ENDPOINT if self._provider == API_PROVIDER_GEMINI else DEFAULT_OPENAI_ENDPOINT)): str,
+                    vol.Optional(CONF_TEMPERATURE, default=input_copy.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)): vol.All(
+                        vol.Coerce(float),
+                        vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
+                    ),
+                    vol.Optional(CONF_MAX_TOKENS, default=input_copy.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
+                    ),
+                    vol.Optional(CONF_REQUEST_INTERVAL, default=input_copy.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)): vol.All(
+                        vol.Coerce(float),
+                        vol.Range(min=MIN_REQUEST_INTERVAL)
+                    ),
+                    vol.Optional(CONF_API_TIMEOUT, default=input_copy.get(CONF_API_TIMEOUT, DEFAULT_API_TIMEOUT)): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=MIN_API_TIMEOUT, max=MAX_API_TIMEOUT)
+                    ),
+                    vol.Optional(
+                        CONF_CONTEXT_MESSAGES,
+                        default=input_copy.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES)
+                    ): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=1, max=20)
+                    ),
+                    vol.Optional(
+                        CONF_MAX_HISTORY_SIZE,
+                        default=input_copy.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY)
+                    ): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=1, max=100)
+                    ),
+                }),
+                errors=self._errors
+            )
+
        try:
+            # Validate and normalize the name
            normalized_name = self._validate_and_normalize_name(input_copy[CONF_NAME])
            input_copy[CONF_NAME] = normalized_name
        except ValueError as e:
            return self.async_show_form(
                step_id="provider",
                data_schema=vol.Schema({
-                    vol.Required(CONF_NAME, default=input_copy[CONF_NAME]): str,
-                    vol.Required(CONF_API_KEY, default=input_copy[CONF_API_KEY]): str,
-                    vol.Required(CONF_MODEL, default=input_copy[CONF_MODEL]): str,
-                    vol.Required(CONF_API_ENDPOINT, default=input_copy[CONF_API_ENDPOINT]): str,
+                    vol.Required(CONF_NAME, default=input_copy.get(CONF_NAME, "my_assistant")): str,
+                    vol.Required(CONF_API_KEY, default=input_copy.get(CONF_API_KEY, "")): str,
+                    vol.Required(CONF_MODEL, default=input_copy.get(CONF_MODEL, DEFAULT_GEMINI_MODEL if self._provider == API_PROVIDER_GEMINI else DEFAULT_MODEL)): str,
+                    vol.Required(CONF_API_ENDPOINT, default=input_copy.get(CONF_API_ENDPOINT, DEFAULT_GEMINI_ENDPOINT if self._provider == API_PROVIDER_GEMINI else DEFAULT_OPENAI_ENDPOINT)): str,
                    vol.Optional(CONF_TEMPERATURE, default=input_copy.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)): vol.All(
                        vol.Coerce(float),
                        vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
                    ),
+                    vol.Optional(CONF_MAX_TOKENS, default=input_copy.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
+                    ),
+                    vol.Optional(CONF_REQUEST_INTERVAL, default=input_copy.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)): vol.All(
+                        vol.Coerce(float),
+                        vol.Range(min=MIN_REQUEST_INTERVAL)
+                    ),
+                    vol.Optional(CONF_API_TIMEOUT, default=input_copy.get(CONF_API_TIMEOUT, DEFAULT_API_TIMEOUT)): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=MIN_API_TIMEOUT, max=MAX_API_TIMEOUT)
+                    ),
+                    vol.Optional(
+                        CONF_CONTEXT_MESSAGES,
+                        default=input_copy.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES)
+                    ): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=1, max=20)
+                    ),
+                    vol.Optional(
+                        CONF_MAX_HISTORY_SIZE,
+                        default=input_copy.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY)
+                    ): vol.All(
+                        vol.Coerce(int),
+                        vol.Range(min=1, max=100)
+                    ),
                }),
                errors={"name": str(e)}
            )

        try:
-            if not await self._async_validate_api(input_copy):
-                return self.async_show_form(
-                    step_id="provider",
-                    data_schema=vol.Schema({
-                    }),
-                    errors=self._errors
-                )
+            # Special handling for Gemini API validation
+            if self._provider == API_PROVIDER_GEMINI:
+                # For Gemini, we just check if API key is present as there's no simple endpoint to validate
+                if not input_copy.get(CONF_API_KEY):
+                    self._errors["base"] = "invalid_auth"
+                    _LOGGER.error("API validation error: 'api_key'")
+                    return self.async_show_form(
+                        step_id="provider",
+                        data_schema=vol.Schema({
+                            vol.Required(CONF_NAME, default=input_copy.get(CONF_NAME, "my_assistant")): str,
+                            vol.Required(CONF_API_KEY): str,
+                            vol.Required(CONF_MODEL, default=input_copy.get(CONF_MODEL, DEFAULT_GEMINI_MODEL)): str,
+                            vol.Required(CONF_API_ENDPOINT, default=input_copy.get(CONF_API_ENDPOINT, DEFAULT_GEMINI_ENDPOINT)): str,
+                            # Other fields remain the same
+                        }),
+                        errors=self._errors
+                    )
+            else:
+                # For other providers, validate API connection
+                if not await self._async_validate_api(input_copy):
+                    return self.async_show_form(
+                        step_id="provider",
+                        data_schema=vol.Schema({
+                            vol.Required(CONF_NAME, default=input_copy.get(CONF_NAME, "my_assistant")): str,
+                            vol.Required(CONF_API_KEY, default=input_copy.get(CONF_API_KEY, "")): str,
+                            vol.Required(CONF_MODEL, default=input_copy.get(CONF_MODEL, DEFAULT_MODEL)): str,
+                            vol.Required(CONF_API_ENDPOINT, default=input_copy.get(CONF_API_ENDPOINT, DEFAULT_OPENAI_ENDPOINT)): str,
+                            vol.Optional(CONF_TEMPERATURE, default=input_copy.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)): vol.All(
+                                vol.Coerce(float),
+                                vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
+                            ),
+                            vol.Optional(CONF_MAX_TOKENS, default=input_copy.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)): vol.All(
+                                vol.Coerce(int),
+                                vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
+                            ),
+                            vol.Optional(CONF_REQUEST_INTERVAL, default=input_copy.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)): vol.All(
+                                vol.Coerce(float),
+                                vol.Range(min=MIN_REQUEST_INTERVAL)
+                            ),
+                            vol.Optional(CONF_API_TIMEOUT, default=input_copy.get(CONF_API_TIMEOUT, DEFAULT_API_TIMEOUT)): vol.All(
+                                vol.Coerce(int),
+                                vol.Range(min=MIN_API_TIMEOUT, max=MAX_API_TIMEOUT)
+                            ),
+                            vol.Optional(
+                                CONF_CONTEXT_MESSAGES,
+                                default=input_copy.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES)
+                            ): vol.All(
+                                vol.Coerce(int),
+                                vol.Range(min=1, max=20)
+                            ),
+                            vol.Optional(
+                                CONF_MAX_HISTORY_SIZE,
+                                default=input_copy.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY)
+                            ): vol.All(
+                                vol.Coerce(int),
+                                vol.Range(min=1, max=100)
+                            ),
+                        }),
+                        errors=self._errors
+                    )
        except Exception as e:
+            # Handle any unexpected exceptions during validation
+            _LOGGER.exception("Unexpected error during API validation")
            return self.async_show_form(
                step_id="provider",
                data_schema=vol.Schema({
+                    vol.Required(CONF_NAME, default=input_copy.get(CONF_NAME, "my_assistant")): str,
+                    vol.Required(CONF_API_KEY, default=input_copy.get(CONF_API_KEY, "")): str,
+                    vol.Required(CONF_MODEL, default=input_copy.get(CONF_MODEL, DEFAULT_GEMINI_MODEL if self._provider == API_PROVIDER_GEMINI else DEFAULT_MODEL)): str,
+                    vol.Required(CONF_API_ENDPOINT, default=input_copy.get(CONF_API_ENDPOINT, DEFAULT_GEMINI_ENDPOINT if self._provider == API_PROVIDER_GEMINI else DEFAULT_OPENAI_ENDPOINT)): str,
+                    # Other fields remain the same
                }),
                errors={"base": str(e)}
            )

+        # All validation passed, create the entry
        return await self._create_entry(input_copy)

    def _validate_and_normalize_name(self, name: str) -> str:
@@ -205,23 +372,34 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
    async def _async_validate_api(self, user_input: Dict[str, Any]) -> bool:
        """Validate API connection."""
        try:
+            if CONF_API_KEY not in user_input:
+                _LOGGER.error("API validation error: 'api_key'")
+                self._errors["base"] = "invalid_auth"
+                return False
+
            session = async_get_clientsession(self.hass)
            headers = self._get_api_headers(user_input)
            endpoint = user_input[CONF_API_ENDPOINT].rstrip('/')

-            check_url = (
-                f"{endpoint}/v1/models" if self._provider == API_PROVIDER_ANTHROPIC
-                else f"{endpoint}/models"
-            )
-
-            async with session.get(check_url, headers=headers) as response:
-                if response.status == 401:
+            if self._provider == API_PROVIDER_GEMINI:
+                if not user_input[CONF_API_KEY]:
                    self._errors["base"] = "invalid_auth"
                    return False
-                elif response.status not in [200, 404]:
-                    self._errors["base"] = "cannot_connect"
-                    return False
                return True
+            else:
+                check_url = (
+                    f"{endpoint}/v1/models" if self._provider == API_PROVIDER_ANTHROPIC
+                    else f"{endpoint}/models"
+                )
+
+                async with session.get(check_url, headers=headers) as response:
+                    if response.status == 401:
+                        self._errors["base"] = "invalid_auth"
+                        return False
+                    elif response.status not in [200, 404]:
+                        self._errors["base"] = "cannot_connect"
+                        return False
+                    return True

        except Exception as err:
            _LOGGER.error("API validation error: %s", str(err))
@@ -230,6 +408,9 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):

    def _get_api_headers(self, user_input: Dict[str, Any]) -> Dict[str, str]:
        """Get API headers based on provider."""
+        if CONF_API_KEY not in user_input:
+            return {"Content-Type": "application/json"}
+
        api_key = user_input[CONF_API_KEY]

        if self._provider == API_PROVIDER_ANTHROPIC:
@@ -238,6 +419,11 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
                "anthropic-version": "2023-06-01",
                "Content-Type": "application/json"
            }
+        elif self._provider == API_PROVIDER_GEMINI:
+            return {
+                "Authorization": f"Bearer {api_key}",
+                "Content-Type": "application/json"
+            }
        return {
            "Authorization": f"Bearer {api_key}",
            "Content-Type": "application/json"
@@ -250,6 +436,12 @@ 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,
@@ -257,10 +449,11 @@ 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),
+            CONF_API_TIMEOUT: user_input.get(CONF_API_TIMEOUT, DEFAULT_API_TIMEOUT),
            CONF_CONTEXT_MESSAGES: user_input.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES),
            CONF_MAX_HISTORY_SIZE: user_input.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY),
        }
@@ -280,70 +473,229 @@ class HATextAIConfigFlow(config_entries.ConfigFlow, domain=DOMAIN):
    @callback
    def async_get_options_flow(config_entry: config_entries.ConfigEntry) -> config_entries.OptionsFlow:
        """Get the options flow for this handler."""
-        return OptionsFlowHandler(config_entry)
+        return OptionsFlowHandler()


 class OptionsFlowHandler(config_entries.OptionsFlow):
    """Handle options flow."""

-    def __init__(self, config_entry: config_entries.ConfigEntry) -> None:
+    def __init__(self) -> None:
        """Initialize options flow."""
-        self.config_entry = config_entry
+        self._errors = {}
+        self._selected_provider = None
+
+    def _get_default_endpoint(self, provider: str) -> str:
+        """Get default endpoint for provider."""
+        return {
+            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(provider, DEFAULT_OPENAI_ENDPOINT)
+
+    def _get_default_model(self, provider: str) -> str:
+        """Get default model for provider."""
+        return (
+            DEFAULT_DEEPSEEK_MODEL if provider == API_PROVIDER_DEEPSEEK else
+            DEFAULT_GEMINI_MODEL if provider == API_PROVIDER_GEMINI else
+            DEFAULT_MODEL
+        )
+
+    def _get_api_headers(self, api_key: str, provider: str) -> Dict[str, str]:
+        """Get API headers based on provider."""
+        if provider == API_PROVIDER_ANTHROPIC:
+            return {
+                "x-api-key": api_key,
+                "anthropic-version": "2023-06-01",
+                "Content-Type": "application/json"
+            }
+        return {
+            "Authorization": f"Bearer {api_key}",
+            "Content-Type": "application/json"
+        }
+
+    async def _async_validate_api(self, provider: str, api_key: str, endpoint: str) -> bool:
+        """Validate API connection."""
+        try:
+            if not api_key:
+                self._errors["base"] = "invalid_auth"
+                return False
+
+            # For Gemini, just check if API key is present
+            if provider == API_PROVIDER_GEMINI:
+                return True
+
+            session = async_get_clientsession(self.hass)
+            headers = self._get_api_headers(api_key, provider)
+            endpoint = endpoint.rstrip('/')
+
+            check_url = (
+                f"{endpoint}/v1/models" if provider == API_PROVIDER_ANTHROPIC
+                else f"{endpoint}/models"
+            )
+
+            async with session.get(check_url, headers=headers) as response:
+                if response.status == 401:
+                    self._errors["base"] = "invalid_auth"
+                    return False
+                elif response.status not in [200, 404]:
+                    self._errors["base"] = "cannot_connect"
+                    return False
+                return True
+
+        except Exception as err:
+            _LOGGER.error("API validation error: %s", str(err))
+            self._errors["base"] = "cannot_connect"
+            return False

    async def async_step_init(self, user_input: Optional[Dict[str, Any]] = None) -> FlowResult:
-        """Manage the options."""
-        if user_input is not None:
-            return self.async_create_entry(title="", data=user_input)
-
+        """Handle provider selection step."""
        current_data = {**self.config_entry.data, **self.config_entry.options}
+        current_provider = current_data.get(CONF_API_PROVIDER, API_PROVIDER_OPENAI)
+
+        if user_input is not None:
+            self._selected_provider = user_input.get(CONF_API_PROVIDER, current_provider)
+            return await self.async_step_settings()

        return self.async_show_form(
            step_id="init",
            data_schema=vol.Schema({
-                vol.Optional(
-                    CONF_MODEL,
-                    default=current_data.get(CONF_MODEL, DEFAULT_MODEL)
-                ): str,
-                vol.Optional(
-                    CONF_TEMPERATURE,
-                    default=current_data.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)
-                ): vol.All(
-                    vol.Coerce(float),
-                    vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
-                ),
-                vol.Optional(
-                    CONF_MAX_TOKENS,
-                    default=current_data.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)
-                ): vol.All(
-                    vol.Coerce(int),
-                    vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
-                ),
-                vol.Optional(
-                    CONF_REQUEST_INTERVAL,
-                    default=current_data.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)
-                ): vol.All(
-                    vol.Coerce(float),
-                    vol.Range(min=MIN_REQUEST_INTERVAL)
-                ),
-                vol.Optional(
-                    CONF_CONTEXT_MESSAGES,
-                    default=current_data.get(
-                        CONF_CONTEXT_MESSAGES,
-                        DEFAULT_CONTEXT_MESSAGES
+                vol.Required(
+                    CONF_API_PROVIDER,
+                    default=current_provider
+                ): selector.SelectSelector(
+                    selector.SelectSelectorConfig(
+                        options=API_PROVIDERS,
+                        translation_key="api_provider"
                    )
-                ): vol.All(
-                    vol.Coerce(int),
-                    vol.Range(min=1, max=20)
                ),
-                vol.Optional(
-                    CONF_MAX_HISTORY_SIZE,
-                    default=current_data.get(
-                        CONF_MAX_HISTORY_SIZE,
-                        DEFAULT_MAX_HISTORY
-                    )
-                ): vol.All(
-                    vol.Coerce(int),
-                    vol.Range(min=1, max=100)
-                ),
-            })
+            }),
+            description_placeholders={
+                "current_provider": current_provider
+            }
        )
+
+    async def async_step_settings(self, user_input: Optional[Dict[str, Any]] = None) -> FlowResult:
+        """Handle settings configuration step."""
+        self._errors = {}
+        current_data = {**self.config_entry.data, **self.config_entry.options}
+        provider = self._selected_provider or current_data.get(CONF_API_PROVIDER, API_PROVIDER_OPENAI)
+
+        # Determine if provider changed to show appropriate defaults
+        provider_changed = provider != current_data.get(CONF_API_PROVIDER)
+
+        # Use new defaults if provider changed, otherwise use current values
+        if provider_changed:
+            default_endpoint = self._get_default_endpoint(provider)
+            default_model = self._get_default_model(provider)
+        else:
+            default_endpoint = current_data.get(CONF_API_ENDPOINT, self._get_default_endpoint(provider))
+            default_model = current_data.get(CONF_MODEL, self._get_default_model(provider))
+
+        if user_input is not None:
+            # Validate API connection
+            api_key = user_input.get(CONF_API_KEY, current_data.get(CONF_API_KEY, ""))
+            endpoint = user_input.get(CONF_API_ENDPOINT, default_endpoint)
+
+            if await self._async_validate_api(provider, api_key, endpoint):
+                # Merge with provider selection
+                final_data = {
+                    CONF_API_PROVIDER: provider,
+                    **user_input
+                }
+                return self.async_create_entry(title="", data=final_data)
+
+            # Show form again with errors
+            return self.async_show_form(
+                step_id="settings",
+                data_schema=self._get_settings_schema(
+                    provider=provider,
+                    current_data=current_data,
+                    user_input=user_input,
+                    default_endpoint=default_endpoint,
+                    default_model=default_model,
+                ),
+                errors=self._errors
+            )
+
+        return self.async_show_form(
+            step_id="settings",
+            data_schema=self._get_settings_schema(
+                provider=provider,
+                current_data=current_data,
+                user_input=None,
+                default_endpoint=default_endpoint,
+                default_model=default_model,
+            ),
+            description_placeholders={
+                "provider": provider
+            }
+        )
+
+    def _get_settings_schema(
+        self,
+        provider: str,
+        current_data: Dict[str, Any],
+        user_input: Optional[Dict[str, Any]],
+        default_endpoint: str,
+        default_model: str,
+    ) -> vol.Schema:
+        """Build settings schema."""
+        data = user_input or current_data
+
+        return vol.Schema({
+            vol.Required(
+                CONF_API_KEY,
+                default=data.get(CONF_API_KEY, "")
+            ): str,
+            vol.Required(
+                CONF_API_ENDPOINT,
+                default=data.get(CONF_API_ENDPOINT, default_endpoint)
+            ): str,
+            vol.Required(
+                CONF_MODEL,
+                default=data.get(CONF_MODEL, default_model)
+            ): str,
+            vol.Optional(
+                CONF_TEMPERATURE,
+                default=data.get(CONF_TEMPERATURE, DEFAULT_TEMPERATURE)
+            ): vol.All(
+                vol.Coerce(float),
+                vol.Range(min=MIN_TEMPERATURE, max=MAX_TEMPERATURE)
+            ),
+            vol.Optional(
+                CONF_MAX_TOKENS,
+                default=data.get(CONF_MAX_TOKENS, DEFAULT_MAX_TOKENS)
+            ): vol.All(
+                vol.Coerce(int),
+                vol.Range(min=MIN_MAX_TOKENS, max=MAX_MAX_TOKENS)
+            ),
+            vol.Optional(
+                CONF_REQUEST_INTERVAL,
+                default=data.get(CONF_REQUEST_INTERVAL, DEFAULT_REQUEST_INTERVAL)
+            ): vol.All(
+                vol.Coerce(float),
+                vol.Range(min=MIN_REQUEST_INTERVAL)
+            ),
+            vol.Optional(
+                CONF_API_TIMEOUT,
+                default=data.get(CONF_API_TIMEOUT, DEFAULT_API_TIMEOUT)
+            ): vol.All(
+                vol.Coerce(int),
+                vol.Range(min=MIN_API_TIMEOUT, max=MAX_API_TIMEOUT)
+            ),
+            vol.Optional(
+                CONF_CONTEXT_MESSAGES,
+                default=data.get(CONF_CONTEXT_MESSAGES, DEFAULT_CONTEXT_MESSAGES)
+            ): vol.All(
+                vol.Coerce(int),
+                vol.Range(min=1, max=20)
+            ),
+            vol.Optional(
+                CONF_MAX_HISTORY_SIZE,
+                default=data.get(CONF_MAX_HISTORY_SIZE, DEFAULT_MAX_HISTORY)
+            ): vol.All(
+                vol.Coerce(int),
+                vol.Range(min=1, max=100)
+            ),
+        })
@@ -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"
@@ -35,32 +61,47 @@ CONF_TEMPERATURE: Final = "temperature"
 CONF_MAX_TOKENS: Final = "max_tokens"
 CONF_API_ENDPOINT: Final = "api_endpoint"
 CONF_REQUEST_INTERVAL: Final = "request_interval"
+CONF_API_TIMEOUT: Final = "api_timeout"
 CONF_INSTANCE: Final = "instance"
 CONF_MAX_HISTORY_SIZE: Final = "max_history_size"  # Correct constant name
 CONF_IS_ANTHROPIC: Final = "is_anthropic"
 CONF_CONTEXT_MESSAGES: Final = "context_messages"
+CONF_STRUCTURED_OUTPUT: Final = "structured_output"
+CONF_JSON_SCHEMA: Final = "json_schema"
+
+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-2.0-flash"
 DEFAULT_TEMPERATURE: Final = 0.1
 DEFAULT_MAX_TOKENS: Final = 1000
 DEFAULT_REQUEST_INTERVAL: Final = 1.0
 DEFAULT_TIMEOUT: Final = 30
+DEFAULT_API_TIMEOUT: Final = 30
 DEFAULT_MAX_HISTORY: Final = 50
 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
+MIN_API_TIMEOUT: Final = 5
+MAX_API_TIMEOUT: Final = 600

 # API constants
-API_TIMEOUT: Final = 30
+API_TIMEOUT: Final = 30  # Legacy constant, use CONF_API_TIMEOUT from config
 API_RETRY_COUNT: Final = 3

 # Service names
@@ -160,7 +201,9 @@ SERVICE_SCHEMA_ASK_QUESTION = vol.Schema({
    vol.Optional("context_messages"): vol.All(
        vol.Coerce(int),
        vol.Range(min=1, max=20)
-    )
+    ),
+    vol.Optional(CONF_STRUCTURED_OUTPUT, default=False): cv.boolean,
+    vol.Optional(CONF_JSON_SCHEMA): cv.string,
 })

 SERVICE_SCHEMA_SET_SYSTEM_PROMPT = vol.Schema({
@@ -197,6 +240,10 @@ CONFIG_SCHEMA = vol.Schema({
            vol.Coerce(float),
            vol.Range(min=MIN_REQUEST_INTERVAL, max=MAX_REQUEST_INTERVAL)
        ),
+        vol.Optional(CONF_API_TIMEOUT, default=DEFAULT_API_TIMEOUT): vol.All(
+            vol.Coerce(int),
+            vol.Range(min=MIN_API_TIMEOUT, max=MAX_API_TIMEOUT)
+        ),
        vol.Optional(CONF_MAX_HISTORY_SIZE, default=DEFAULT_MAX_HISTORY): vol.All(  # Correct usage
            vol.Coerce(int),
            vol.Range(min=1, max=100),
@@ -14,15 +14,17 @@
  "mqtt": [],
  "quality_scale": "silver",
  "requirements": [
-    "openai>=1.12.0",
-    "anthropic>=0.8.0",
+    "aiofiles>=23.0.0",
    "aiohttp>=3.8.0",
+    "anthropic>=0.8.0",
    "async-timeout>=4.0.0",
-    "certifi>=2024.2.2"
+    "certifi>=2024.2.2",
+    "google-genai>=1.16.0",
+    "openai>=1.12.0"
  ],
  "single_config_entry": false,
  "ssdp": [],
  "usb": [],
-  "version": "2.0.4-beta",
+  "version": "2.3.0",
  "zeroconf": []
 }
@@ -9,6 +9,7 @@ Sensor platform for HA Text AI.
 import logging
 import math
 from typing import Any, Dict
+from datetime import datetime, timedelta

 from homeassistant.components.sensor import (
    SensorEntity,
@@ -67,6 +68,8 @@ from .const import (
    ENTITY_ICON_PROCESSING,
    DEFAULT_NAME_PREFIX,
    CONF_MAX_HISTORY_SIZE,
+    MAX_ATTRIBUTE_SIZE,
+    VERSION,
 )

 from .coordinator import HATextAICoordinator
@@ -153,7 +156,7 @@ 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 +181,29 @@ 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 +232,65 @@ 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 +316,12 @@ 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")
@@ -3,6 +3,7 @@ ask_question:
  description: >-
    Send a question to the AI model and receive a detailed response.
    The response will be stored in the conversation history and can be retrieved later.
+    This service now returns response data directly, eliminating the need to read from sensors.
  fields:
    instance:
      name: Instance
@@ -63,16 +64,34 @@ 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

+    structured_output:
+      name: Structured Output
+      description: Enable JSON structured output mode. When enabled, the AI will respond with valid JSON matching the provided schema.
+      required: false
+      default: false
+      selector:
+        boolean: {}
+
+    json_schema:
+      name: JSON Schema
+      description: >-
+        JSON Schema defining the structure of the expected response.
+        Required when structured_output is enabled.
+      required: false
+      selector:
+        text:
+          multiline: true
+
 clear_history:
  name: Clear History
  description: >-
@@ -134,7 +153,7 @@ get_history:
      required: false
      default: false
      selector:
-        boolean:
+        boolean: {}

    sort_order:
      name: Sort Order
@@ -2,71 +2,115 @@
  "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)",
+          "api_timeout": "API-Anfrage Timeout in Sekunden (5-600)",
+          "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)",
+          "api_timeout": "API-Anfrage Timeout in Sekunden (5-600)",
          "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.",
+        "title": "Anbieter auswählen",
+        "description": "Wählen Sie den AI-Anbieter für diese Instanz. Die Integration wird nach dem Speichern der Änderungen neu geladen.",
        "data": {
-          "model": "KI-Modell",
-          "temperature": "Antwortkreativität (0-2)",
-          "max_tokens": "Maximale Antwortlänge (1-4096)",
-          "request_interval": "Mindestzeitraum zwischen Anfragen (0,1-60 Sekunden)",
-          "context_messages": "Anzahl der vorherigen Nachrichten, die im Kontext enthalten sein sollen (1-20)",
-          "max_history_size": "Maximale Größe des Konversationsverlaufs (1-100)"
+          "api_provider": "API-Anbieter"
        }
+      },
+      "settings": {
+        "title": "Verbindungs- und Modelleinstellungen",
+        "description": "Konfigurieren Sie API-Anmeldeinformationen und Modellparameter. Änderungen werden nach dem Neuladen der Integration wirksam.",
+        "data": {
+          "api_key": "API-Schlüssel",
+          "api_endpoint": "API-Endpunkt-URL",
+          "model": "AI-Modell",
+          "temperature": "Kreativität der Antwort (0-2)",
+          "max_tokens": "Maximale Länge der Antwort (1-100000)",
+          "request_interval": "Minimales Anfrageintervall (0,1-60 Sekunden)",
+          "api_timeout": "API-Anfrage Timeout in Sekunden (5-600)",
+          "context_messages": "Anzahl der vorherigen Nachrichten, die im Kontext enthalten sein sollen (1-20)",
+          "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. Dieser Service gibt jetzt Antwortdaten direkt zurück, wodurch separate Textsensoren und die 255-Zeichen-Begrenzung überflüssig werden. Die Antwort wird auch im Gesprächsverlauf gespeichert.",
      "fields": {
        "instance": {
          "name": "Instanz",
@@ -74,43 +118,51 @@
        },
        "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)"
+        },
+        "structured_output": {
+          "name": "Strukturierte Ausgabe",
+          "description": "JSON-Strukturausgabemodus aktivieren. Bei Aktivierung antwortet die KI mit gültigem JSON, das dem angegebenen Schema entspricht."
+        },
+        "json_schema": {
+          "name": "JSON-Schema",
+          "description": "JSON-Schema, das die Struktur der erwarteten Antwort definiert. Erforderlich wenn structured_output aktiviert ist."
        }
      }
    },
    "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 +170,19 @@
        },
        "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 +191,16 @@
      }
    },
    "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 +214,11 @@
          "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 +234,16 @@
            "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 +255,19 @@
            "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 +276,25 @@
            "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 +6,24 @@
        "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)",
+          "api_timeout": "API request timeout in seconds (5-600)",
+          "context_messages": "Number of context messages to retain (1-20)",
+          "max_history_size": "Maximum conversation history size (1-100)"
        }
      },
      "user": {
@@ -17,16 +34,20 @@
          "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)",
+          "api_timeout": "API request timeout in seconds (5-600)",
          "context_messages": "Number of context messages to retain (1-20)",
          "max_history_size": "Maximum conversation history size (1-100)"
        }
      }
    },
    "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",
@@ -45,28 +66,51 @@
      "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": {
    "step": {
      "init": {
-        "title": "Update Instance Settings",
-        "description": "Modify settings for this AI assistant instance.",
+        "title": "Select Provider",
+        "description": "Choose the AI provider for this instance. The integration will reload after saving changes.",
        "data": {
+          "api_provider": "API Provider"
+        }
+      },
+      "settings": {
+        "title": "Connection & Model Settings",
+        "description": "Configure API credentials and model parameters. Changes will take effect after the integration reloads.",
+        "data": {
+          "api_key": "API Key",
+          "api_endpoint": "API Endpoint URL",
          "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)",
+          "api_timeout": "API request timeout in seconds (5-600)",
          "context_messages": "Number of previous messages to include in context (1-20)",
          "max_history_size": "Maximum conversation history size (1-100)"
        }
      }
    }
  },
+  "selector": {
+    "api_provider": {
+      "options": {
+        "openai": "OpenAI (compatible)",
+        "anthropic": "Anthropic (compatible)",
+        "deepseek": "DeepSeek",
+        "gemini": "Google Gemini"
+      }
+    }
+  },
  "services": {
    "ask_question": {
      "name": "Ask Question (HA Text AI)",
-      "description": "Send a question to the AI model and receive a detailed response. The response will be stored in the conversation history and can be retrieved later.",
+      "description": "Send a question to the AI model and receive a detailed response. This service now returns response data directly, eliminating the need for separate text sensors and the 255-character limitation. The response will also be stored in the conversation history.",
      "fields": {
        "instance": {
          "name": "Instance",
@@ -94,7 +138,15 @@
        },
        "max_tokens": {
          "name": "Max Tokens",
-          "description": "Maximum length of the response (1-4096 tokens)"
+          "description": "Maximum length of the response (1-100000 tokens)"
+        },
+        "structured_output": {
+          "name": "Structured Output",
+          "description": "Enable JSON structured output mode. When enabled, the AI will respond with valid JSON matching the provided schema."
+        },
+        "json_schema": {
+          "name": "JSON Schema",
+          "description": "JSON Schema defining the structure of the expected response. Required when structured_output is enabled."
        }
      }
    },
@@ -3,151 +3,203 @@
    "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)",
+          "api_timeout": "Tiempo de espera de solicitud API en segundos (5-600)",
+          "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)",
+          "api_timeout": "Tiempo de espera de solicitud API en segundos (5-600)",
+          "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.",
+        "title": "Seleccionar proveedor",
+        "description": "Elige el proveedor de IA para esta instancia. La integración se recargará después de guardar los cambios.",
        "data": {
+          "api_provider": "Proveedor de API"
+        }
+      },
+      "settings": {
+        "title": "Configuración de conexión y modelo",
+        "description": "Configura las credenciales de API y los parámetros del modelo. Los cambios tendrán efecto después de recargar la integración.",
+        "data": {
+          "api_key": "Clave API",
+          "api_endpoint": "URL del endpoint de API",
          "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)",
+          "api_timeout": "Tiempo de espera de solicitud API en segundos (5-600)",
+          "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)",
-      "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.",
+      "name": "Hacer Pregunta (HA Text AI)",
+      "description": "Envía una pregunta al modelo de IA y recibe una respuesta detallada. Este servicio ahora devuelve datos de respuesta directamente, eliminando la necesidad de sensores de texto separados y la limitación de 255 caracteres. La respuesta también se almacenará en el historial de conversación.",
      "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)"
+        },
+        "structured_output": {
+          "name": "Salida Estructurada",
+          "description": "Habilitar modo de salida JSON estructurada. Cuando está habilitado, la IA responderá con JSON válido que coincida con el esquema proporcionado."
+        },
+        "json_schema": {
+          "name": "Esquema JSON",
+          "description": "Esquema JSON que define la estructura de la respuesta esperada. Requerido cuando structured_output está habilitado."
        }
      }
    },
    "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 +214,7 @@
          "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 +222,94 @@
        },
        "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 +2,114 @@
  "config": {
    "step": {
      "provider": {
-        "title": "AI प्रदाता का चयन करें",
-        "description": "इस उदाहरण के लिए उपयोग करने के लिए AI सेवा प्रदाता चुनें।",
+        "title": "प्रदाता सेटिंग्स",
+        "description": "आपके द्वारा चुने गए एआई प्रदाता के लिए कनेक्शन विवरण प्रदान करें।",
        "data": {
-          "api_provider": "API प्रदाता",
-          "context_messages": "बनाए रखने के लिए संदर्भ संदेशों की संख्या (1-20)"
+          "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)",
+          "api_timeout": "एपीआई अनुरोध टाइमआउट सेकंड में (5-600)",
+          "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)"
+          "api_timeout": "एपीआई अनुरोध टाइमआउट सेकंड में (5-600)",
+          "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।",
+        "title": "प्रदाता चुनें",
+        "description": "इस उदाहरण के लिए एआई प्रदाता चुनें। परिवर्तन सहेजने के बाद एकीकरण पुनः लोड होगा।",
        "data": {
-          "model": "AI मॉडल",
-          "temperature": "प्रतिक्रिया रचनात्मकता (0-2)",
-          "max_tokens": "अधिकतम प्रतिक्रिया लंबाई (1-4096)",
-          "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)"
+          "api_provider": "एपीआई प्रदाता"
        }
+      },
+      "settings": {
+        "title": "कनेक्शन और मॉडल सेटिंग्स",
+        "description": "एपीआई क्रेडेंशियल और मॉडल पैरामीटर कॉन्फ़िगर करें। एकीकरण पुनः लोड होने के बाद परिवर्तन प्रभावी होंगे।",
+        "data": {
+          "api_key": "एपीआई कुंजी",
+          "api_endpoint": "एपीआई एंडपॉइंट यूआरएल",
+          "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)",
+          "api_timeout": "एपीआई अनुरोध टाइमआउट सेकंड में (5-600)",
+          "context_messages": "संदर्भ में शामिल करने के लिए पिछले संदेशों की संख्या (1-20)",
+          "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": "AI मॉडल को प्रश्न भेजें और विस्तृत उत्तर प्राप्त करें। यह सेवा अब प्रत्यक्ष रूप से प्रतिक्रिया डेटा वापस करती है, अलग टेक्स्ट सेंसर की आवश्यकता और 255 वर्ण की सीमा को समाप्त करती है। प्रतिक्रिया को बातचीत के इतिहास में भी संग्रहीत किया जाएगा।",
      "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 +117,81 @@
        },
        "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)"
+        },
+        "structured_output": {
+          "name": "संरचित आउटपुट",
+          "description": "JSON संरचित आउटपुट मोड सक्षम करें। सक्षम होने पर, AI प्रदान किए गए स्कीमा से मेल खाने वाले वैध JSON के साथ प्रतिक्रिया देगा।"
+        },
+        "json_schema": {
+          "name": "JSON स्कीमा",
+          "description": "अपेक्षित प्रतिक्रिया की संरचना को परिभाषित करने वाला JSON स्कीमा। structured_output सक्षम होने पर आवश्यक।"
        }
      }
    },
    "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 +202,14 @@
        "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 +231,46 @@
            "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 +285,13 @@
            "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"
@@ -263,4 +306,4 @@
      }
    }
  }
-}
+}
@@ -2,86 +2,130 @@
  "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)",
+          "api_timeout": "Timeout della richiesta API in secondi (5-600)",
+          "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)",
+          "api_timeout": "Timeout della richiesta API in secondi (5-600)",
+          "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",
-        "description": "Modifica le impostazioni per questa istanza di assistente AI.",
+        "title": "Seleziona fornitore",
+        "description": "Scegli il fornitore AI per questa istanza. L'integrazione verrà ricaricata dopo aver salvato le modifiche.",
        "data": {
+          "api_provider": "Fornitore API"
+        }
+      },
+      "settings": {
+        "title": "Impostazioni di connessione e modello",
+        "description": "Configura le credenziali API e i parametri del modello. Le modifiche avranno effetto dopo il ricaricamento dell'integrazione.",
+        "data": {
+          "api_key": "Chiave API",
+          "api_endpoint": "URL dell'endpoint API",
          "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)",
+          "api_timeout": "Timeout della richiesta API in secondi (5-600)",
          "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. Questo servizio ora restituisce i dati di risposta direttamente, eliminando la necessità di sensori di testo separati e la limitazione di 255 caratteri. La risposta sarà anche memorizzata nella cronologia delle conversazioni.",
      "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 +137,70 @@
          "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)"
+        },
+        "structured_output": {
+          "name": "Output Strutturato",
+          "description": "Abilita la modalità di output JSON strutturato. Quando abilitato, l'IA risponderà con JSON valido corrispondente allo schema fornito."
+        },
+        "json_schema": {
+          "name": "Schema JSON",
+          "description": "Schema JSON che definisce la struttura della risposta attesa. Richiesto quando structured_output è abilitato."
        }
      }
    },
    "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 +211,108 @@
        "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 +2,151 @@
  "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)",
+          "api_timeout": "Таймаут API-запроса в секундах (5-600)",
+          "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)",
+          "api_timeout": "Таймаут API-запроса в секундах (5-600)",
+          "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": "Выбор провайдера",
+        "description": "Выберите провайдера ИИ для этого экземпляра. Интеграция перезагрузится после сохранения изменений.",
        "data": {
+          "api_provider": "Провайдер API"
+        }
+      },
+      "settings": {
+        "title": "Настройки подключения и модели",
+        "description": "Настройте учётные данные API и параметры модели. Изменения вступят в силу после перезагрузки интеграции.",
+        "data": {
+          "api_key": "API-ключ",
+          "api_endpoint": "URL конечной точки API",
          "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)",
+          "api_timeout": "Таймаут API-запроса в секундах (5-600)",
          "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. Сервис теперь возвращает данные ответа напрямую, устраняя необходимость в отдельных текстовых сенсорах и ограничение в 255 символов. Ответ также будет сохранен в истории разговора.",
      "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)"
+        },
+        "structured_output": {
+          "name": "Структурированный вывод",
+          "description": "Включить режим структурированного JSON-вывода. При включении ИИ будет отвечать валидным JSON, соответствующим указанной схеме."
+        },
+        "json_schema": {
+          "name": "JSON Schema",
+          "description": "JSON-схема, определяющая структуру ожидаемого ответа. Обязательна при включении structured_output."
        }
      }
    },
@@ -103,18 +155,18 @@
      "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 +174,33 @@
        },
        "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 +234,10 @@
            "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 +255,7 @@
            "name": "Статус API"
          },
          "tokens_used": {
-            "name": "Использовано токенов всего"
+            "name": "Всего использовано токенов"
          },
          "average_response_time": {
            "name": "Среднее время ответа"
@@ -215,10 +267,10 @@
            "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 +279,7 @@
            "name": "Статус конечной точки"
          },
          "performance_metrics": {
-            "name": "Метрики производительности"
+            "name": "Показатели производительности"
          },
          "history_size": {
            "name": "Размер истории"
@@ -239,16 +291,16 @@
            "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 +2,196 @@
  "config": {
    "step": {
      "provider": {
-        "title": "Изаберите добављача вештачке интелигенције",
-        "description": "Изаберите добављача услуга вештачке интелигенције који ћете користити за ову инстанцу.",
+        "title": "Подешавања провајдера",
+        "description": "Обезбедите детаље о вези за изабраног AI провајдера.",
        "data": {
-          "api_provider": "Добављач API-ја",
-          "context_messages": "Број порука контекста које треба задржати (1-20)"
+          "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)",
+          "api_timeout": "Временско ограничење API захтева у секундама (5-600)",
+          "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)",
+          "api_timeout": "Временско ограничење API захтева у секундама (5-600)",
+          "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.",
+        "title": "Изаберите провајдера",
+        "description": "Изаберите AI провајдера за ову инстанцу. Интеграција ће се поново учитати након чувања измена.",
        "data": {
-          "model": "Модел вештачке интелигенције",
+          "api_provider": "API провајдер"
+        }
+      },
+      "settings": {
+        "title": "Подешавања везе и модела",
+        "description": "Конфигуришите API акредитиве и параметре модела. Промене ће ступити на снагу након поновног учитавања интеграције.",
+        "data": {
+          "api_key": "API кључ",
+          "api_endpoint": "URL API крајње тачке",
+          "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)",
+          "api_timeout": "Временско ограничење API захтева у секундама (5-600)",
          "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 добијте детаљан одговор. Овај сервис сада враћа податке одговора директно, елиминишући потребу за засебним текстуалним сензорима и ограничење од 255 карактера. Одговор ће такође бити сачуван у историји разговора.",
      "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)"
+        },
+        "structured_output": {
+          "name": "Структурисани излаз",
+          "description": "Омогући JSON структурисани излаз. Када је омогућено, AI ће одговарати валидним JSON-ом који одговара датој шеми."
+        },
+        "json_schema": {
+          "name": "JSON шема",
+          "description": "JSON шема која дефинише структуру очекиваног одговора. Обавезна када је structured_output омогућен."
        }
      }
    },
    "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 +204,12 @@
          "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 +225,16 @@
            "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 +243,10 @@
            "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 +258,34 @@
            "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"
@@ -263,4 +306,4 @@
      }
    }
  }
-}
+}
@@ -2,153 +2,196 @@
  "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": "提供者设置",
+        "description": "提供所选AI提供者的连接详细信息。",
        "data": {
-          "api_provider": "API 提供商",
-          "context_messages": "要保留的上下文消息数量 (1-20)"
+          "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）",
+          "api_timeout": "API请求超时时间（5-600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）",
+          "api_timeout": "API请求超时时间（5-600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。",
+        "title": "选择提供者",
+        "description": "选择此实例的AI提供者。保存更改后集成将重新加载。",
        "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)"
+          "api_provider": "API提供者"
        }
+      },
+      "settings": {
+        "title": "连接和模型设置",
+        "description": "配置API凭据和模型参数。更改将在集成重新加载后生效。",
+        "data": {
+          "api_key": "API密钥",
+          "api_endpoint": "API端点URL",
+          "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）",
+          "api_timeout": "API请求超时时间（5-600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模型发送问题并获得详细回答。此服务现在直接返回响应数据，消除了对单独文本传感器的需要和255字符限制。响应也将存储在对话历史中。",
      "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）"
+        },
+        "structured_output": {
+          "name": "结构化输出",
+          "description": "启用JSON结构化输出模式。启用后，AI将以符合提供的模式的有效JSON进行响应。"
+        },
+        "json_schema": {
+          "name": "JSON模式",
+          "description": "定义预期响应结构的JSON模式。启用structured_output时必需。"
        }
      }
    },
    "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 +201,22 @@
      "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 +225,34 @@
            "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 +264,7 @@
            "name": "维护状态"
          },
          "api_version": {
-            "name": "API 版本"
+            "name": "API版本"
          },
          "endpoint_status": {
            "name": "端点状态"
@@ -230,19 +273,19 @@
            "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"
@@ -263,4 +306,4 @@
      }
    }
  }
-}
+}
@@ -1,5 +1,5 @@
 {
-  "name": "HA text AI",
+  "name": "HA Text AI",
  "render_readme": true,
-  "homeassistant": "2024.11.0"
+  "homeassistant": "2024.12.0"
 }
@@ -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	43cbac2d04	feat: Add ability to edit provider, API key, and endpoint in existing integrations - Extended OptionsFlowHandler with two-step configuration flow - Step 1: Select provider (OpenAI, Anthropic, DeepSeek, Gemini) - Step 2: Configure API key, endpoint, model, and other settings - Auto-reload integration on options change - When switching providers, show appropriate default endpoint and model - Updated translations for all 8 languages	2025-12-30 17:22:48 +03:00
SMKRV	986c78dd90	fix: Fix OptionsFlowHandler for HA 2024.1+ compatibility - Remove __init__ method that was passing config_entry as argument - OptionsFlow now automatically receives config_entry from base class - Fixes '500 Internal Server Error' when editing existing integrations	2025-12-30 17:10:06 +03:00
SMKRV	0859c35aec	fix: Change release workflow to trigger on release created event	2025-12-30 16:56:27 +03:00
SMKRV	922fefbd43	chore: Bump version to 2.3.0	2025-12-30 16:54:23 +03:00
SMKRV	a5ac100b06	feat: Add structured output support with JSON schema validation - Introduced `structured_output` and `json_schema` parameters to enhance API responses. - Updated service schemas and API client methods to handle structured output. - Added translations for new parameters in multiple languages. - Updated documentation to reflect changes in service capabilities. Closes #9	2025-12-30 16:44:01 +03:00
smkrvandGitHub	ef579af7c1	Create release.yml	2025-12-30 16:27:46 +03:00
SMKRV	3097106e93	feat: Add configurable API timeout setting - Add CONF_API_TIMEOUT configuration option (5-600 seconds, default 30) - Update config_flow.py with api_timeout field in provider form and options flow - Update api_client.py to use configurable timeout instead of hardcoded value - Update coordinator.py to use api_timeout for async_process_message - Update __init__.py to read and pass api_timeout from config - Merge entry.data with entry.options for proper options flow support - Add translations for api_timeout in all 8 language files (en, ru, de, es, it, hi, sr, zh) - Bump version to 2.2.0 Closes #8	2025-12-22 00:07:17 +03:00
smkrvandGitHub	35073960b8	Delete ha-text-ai.code-workspace	2025-09-03 00:56:56 +03:00
SMKRV	8d0e0b5e44	docs: update README with context_messages parameter - Added context_messages parameter to Platform Configuration table - Fixed duplicate parameter entry in configuration docs - Parameter allows 1-20 previous messages in context (default: 5)	2025-09-02 23:50:20 +03:00
SMKRV	e91c3701c5	Fix: Resolve get_history service parameter handling issue - Fixed async_get_history method to accept limit parameter and other filtering options - Updated service schema to support all parameters from services.yaml - Added support for start_date, include_metadata, and sort_order parameters - Version bump to 2.1.9	2025-09-02 23:27:34 +03:00
smkrv	7f62101b3e	Update HACS minimum HA version to align with README requirement (2024.12.0)	2025-09-02 23:15:01 +03:00
smkrvandGitHub	3729c3736f	Update hassfest.yaml	2025-09-02 09:36:46 +03:00
smkrvandGitHub	f5ce5e459a	Update hassfest.yaml fix: https://github.com/smkrv/ha-text-ai/security/code-scanning/2	2025-09-02 09:24:35 +03:00
smkrv GitHubCopilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>	4064486b1e	Potential fix for code scanning alert no. 1: Workflow does not contain permissions Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>	2025-09-02 09:18:15 +03:00
SMKRV	185778dbd0	docs: Update AI models to latest versions - Update OpenAI models to GPT-5 and GPT-5 mini - Update Anthropic Claude models to 4.1, 4.0 series - Update DeepSeek models to V3.1 and R1 - Update Google Gemini models to 2.5 and 2.0 series - Modernize model descriptions and capabilities	2025-09-02 02:19:37 +03:00
SMKRV	83a255dee0	docs: Update README.md - actualize documentation - Simplify HACS installation instructions - Update recommended models section (remove year from title) - Update Claude model names to current format (claude-3.5-sonnet, claude-3.5-haiku) - Add missing parameters to get_history service documentation - Remove non-configurable history_file_size parameter from table - Add missing context_messages parameter to configuration table - Update all model references in examples to use current naming	2025-09-02 02:11:34 +03:00
SMKRV	6b66dd6a4d	docs: Update README with latest configuration defaults and Gemini models - Update default model from gpt-4o to gpt-4o-mini - Update default temperature from 0.7 to 0.1 - Update default max_history_size from 100 to 50 - Add gemini-2.0-flash as latest recommended Gemini model - Fix logo image link to use main branch instead of specific commit - Update configuration parameters table with current defaults	2025-09-02 02:06:58 +03:00
SMKRV	bd82f23120	docs: Update HACS badge from Custom to Default	2025-09-02 01:56:24 +03:00
SMKRV	eee9754033	fix: Fix JSON syntax errors in translation files - Fixed missing closing brace in es.json selector.api_provider.options - Fixed missing closing brace in de.json selector.api_provider.options - All other translation files (hi.json, it.json, sr.json, zh.json) have correct syntax - Ensures proper JSON validation and prevents parsing errors	2025-09-02 01:26:49 +03:00
SMKRV	517b1f11ae	fix: Remove invalid response schema from services.yaml Home Assistant's hassfest validation does not support 'response' section in services.yaml. The response_variable functionality still works through supports_response=True flag in service registration. Fixes hassfest validation error: extra keys not allowed @ data['ask_question']['response']	2025-09-02 01:22:20 +03:00
SMKRV	ed8f19bfa9	fix: Add support for response_variable in ask_question service - Added response schema definition in services.yaml for ask_question service - Set supports_response=True flag when registering the service - Fixed JSON syntax error in English translation file - Added comprehensive documentation with examples for response_variable usage - Users can now capture AI responses directly in variables without sensor delays Resolves issue where scripts failed with 'Script does not support response_variable' error	2025-09-02 01:19:44 +03:00
SMKRV	7e3daf611b	fix: Remove target requirements from services to fix mandatory device/area/entity selection issue - Removed target blocks from all services in services.yaml - Services now work as global services without requiring device/area/entity selection - Users can call services directly with only required parameters - Fixes issue #2 where services incorrectly required target selection after v2.1.8 update	2025-09-01 23:40:26 +03:00
SMKRV	37919be70f	fix: Resolve hassfest validation errors in services.yaml - Remove invalid response schema from ask_question service - Add required target configuration for all services - Ensure compliance with Home Assistant service schema requirements	2025-09-01 17:20:40 +03:00
SMKRV	e427254584	feat: Implement response variables support and comprehensive production audit (v2.1.8) 🚀 Major Features: - Add response variables support to ask_question service - Eliminate 255-character limitation for AI responses - Enable direct data access in automations without sensors - Prevent race conditions in parallel automations 🔧 Production Code Audit & Fixes: - Enhanced resource management with context managers in api_client.py - Fixed critical race conditions with asyncio.Semaphore implementation - Improved file operations with atomic writes and corruption handling - Enhanced error handling and logging security (removed sensitive data) - Fixed _check_memory_available method placement in coordinator.py 🌐 Translation Updates (8 languages): - Updated all translation files with response variables information - Enhanced service descriptions in: en, ru, de, es, it, hi, sr, zh - Added information about direct response capability - Maintained consistency across all language files 📚 Documentation Enhancements: - Added comprehensive Response Variables section to README - Created advanced automation examples with response_variable usage - Added migration guide from sensors to response variables - Enhanced service documentation with response data structure - Added practical examples for multi-step AI workflows 🔄 Service Improvements: - Enhanced ask_question service to return structured response data - Added comprehensive response schema in services.yaml - Improved error handling with success/failure indicators - Added metadata support (tokens, model, timestamp) �� Version & Manifest: - Bumped version to 2.1.8 - Maintained compatibility with existing integrations - Updated service documentation This release addresses GitHub issue #2 and significantly improves the integration's production readiness while adding powerful new response variable functionality.	2025-09-01 17:14:23 +03:00
SMKRV	76c5629fa0	refactor(google-gemini): rewrite integration using google-genai 1.16.0 Completely rewrote the Google Gemini integration logic based on google-genai 1.16.0 to fix issue #6. Key changes: - Updated to the latest google-genai library - Made API endpoint abstract while retaining option for custom endpoint configuration - Refactored logic and classes exclusively within Google Gemini implementation - All changes are limited to Google Gemini integration refactoring with no impact on other functionality.	2025-05-21 01:27:47 +03:00
SMKRV	7958bd010b	refactor(google-gemini): rewrite integration using google-genai 1.16.0 Completely rewrote the Google Gemini integration logic based on google-genai 1.16.0 to fix issue #6. Key changes: - Updated to the latest google-genai library - Made API endpoint abstract while retaining option for custom endpoint configuration - Refactored logic and classes exclusively within Google Gemini implementation - All changes are limited to Google Gemini integration refactoring with no impact on other functionality.	2025-05-21 01:26:42 +03:00
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