Implementing an update mechanism

.env.example

@@ -0,0 +1,5 @@
+# OpenRouter API Configuration
+OPENROUTER_API_KEY=
+
+# OpenRouter Model Configuration
+OPENROUTER_MODEL=

.gitignore

@@ -1,6 +1,9 @@
 # Ignore chat session logs
 chat_sessions/
 .DS_Store
+
+# Ignore user-edited config files
+.env
 
 # Common log files
 *.log

.models

@@ -0,0 +1,71 @@
+#####################################################
+# DO NOT EDIT THIS FILE AS IT WILL BREAKE THE UPDATES
+#####################################################
+
+############### OpenRouter Modes ###############
+# If you want to use a specific model, copy one of the lines below and put it in the OPENROUTER_MODEL= of your .env file.
+# If not set, it will default to "OPENROUTER_MODEL=mistralai/mistral-small-3.2-24b-instruct:free"
+# You can also set it to any model available on OpenRouter: https://openrouter.ai/models
+# Additional free models commonly available on OpenRouter : 
+
+agentica-org/deepcoder-14b-preview:free
+arliai/qwq-32b-arliai-rpr-v1:free
+cognitivecomputations/dolphin-mistral-24b-venice-edition:free
+cognitivecomputations/dolphin3.0-mistral-24b:free
+cognitivecomputations/dolphin3.0-r1-mistral-24b:free
+deepseek/deepseek-chat:free
+deepseek/deepseek-chat-v3-0324:free
+deepseek/deepseek-r1-0528:free
+deepseek/deepseek-r1-0528-qwen3-8b:free
+deepseek/deepseek-r1-distill-llama-70b:free
+deepseek/deepseek-r1-distill-qwen-14b:free
+deepseek/deepseek-r1:free
+deepseek/deepseek-v3-base:free
+featherless/qwerky-72b:free
+google/gemini-2.0-flash-exp:free
+google/gemini-2.5-pro-exp-03-25
+google/gemma-2-9b-it:free
+google/gemma-3-12b-it:free
+google/gemma-3-27b-it:free
+google/gemma-3-4b-it:free
+google/gemma-3n-e2b-it:free
+google/gemma-3n-e4b-it:free
+microsoft/mai-ds-r1:free
+mistralai/devstral-small-2505:free
+mistralai/mistral-7b-instruct:free
+mistralai/mistral-nemo:free
+mistralai/mistral-small-24b-instruct-2501:free
+mistralai/mistral-small-3.1-24b-instruct:free
+mistralai/mistral-small-3.2-24b-instruct:free
+moonshotai/kimi-dev-72b:free
+moonshotai/kimi-vl-a3b-thinking:free
+meta-llama/llama-3.1-405b-instruct:free
+meta-llama/llama-3.2-11b-vision-instruct:free
+meta-llama/llama-3.2-3b-instruct:free
+meta-llama/llama-3.3-70b-instruct:free
+meta-llama/llama-4-maverick:free
+meta-llama/llama-4-scout:free
+nousresearch/deephermes-3-llama-3-8b-preview:free
+nvidia/llama-3.1-nemotron-ultra-253b-v1:free
+nvidia/llama-3.3-nemotron-super-49b-v1:free
+openai/gpt-oss-20b:free
+openrouter/cypher-alpha:free
+qwen/qwen-2.5-72b-instruct:free
+qwen/qwen-2.5-coder-32b-instruct:free
+qwen/qwen3-14b:free
+qwen/qwen3-30b-a3b:free
+qwen/qwen3-32b:free
+qwen/qwen3-4b:free
+qwen/qwen3-8b:free
+qwen/qwen3-235b-a22b:free
+qwen/qwen2.5-vl-32b-instruct:free
+qwen/qwen2.5-vl-72b-instruct:free
+qwen/qwq-32b:free
+rekai/reka-flash-3:free
+sarvamai/sarvam-m:free
+shisa-ai/shisa-v2-llama3.3-70b:free
+tencent/hunyuan-a13b-instruct:free
+thudm/glm-4-32b:free
+thudm/glm-z1-32b:free
+tngtech/deepseek-r1t-chimera:free
+tngtech/deepseek-r1t2-chimera:free

README.md

@@ -6,18 +6,20 @@ Please note that free models on openrouter.ai (those with :free in their slug) a
 
 ## Features
  - 🚀 Minimalist CLI interface — talk to AI directly from your terminal.
- - 🔑 Secure API key & model config — stored in .env file, no need to enter every time.
+ - 🔑 Secure API key & model config — stored in .env file (create it by copiing .env.example), no need to enter every time.
+ - 🔄 Easy update: Run `ai.sh --update` to get the latest version.
+ - 📖 Built-in help: Run `ai.sh --help` for usage instructions.
  - 🤖 Full session memory — ongoing conversations with proper context (stateful chat).
  - 💬 Natural language queries — just type like you're talking to a buddy.
- - 💾 Chat history saved — all conversations stored as timestamped .txt files inside chat_sessions/.
+ - 💾 Chat history saved — all conversations stored as timestamped .txt files inside `chat_sessions/`.
  - 🧠 Dynamic AI name display — bot replies are labeled with the selected model (e.g. Mistral AI:).
  - 👤 Personalized & interactive input — uses your system username in the prompt and supports arrow keys for editing your message like a real terminal app.
  - 🧹 Clean output — only the answer, no JSON noise.
- - 🆓 Uses a free model by default — no paid account required.
- - 🔍 Smart package manager detection — if curl or jq is missing, the script tells you exactly how to install it (e.g. sudo pacman -S jq).
- - 🧪 Works on Linux & macOS — tested on Arch-based, Debian-based and macOS (via brew).
- - ✨ Zero dependencies beyond curl + jq — no Python, no Node.js, no drama.
- - 🐞 Debug mode support — run with DEBUG=true to see full raw API responses on errors in the terminal.
+ - 🆓 Uses a free model by default — no paid account required only your API key.
+ - 🔍 Smart package manager detection — if curl or jq is missing, the script tells you exactly how to install it (e.g. `sudo pacman -S jq)`.
+ - 🧪 Works on Linux & macOS and Windows through WLS — tested on Arch-based, Debian-based and macOS (via brew).
+ - ✨ Zero dependencies beyond `curl` and `jq` — no Python, no Node.js, no drama.
+ - 🐞 Debug mode support — run with `DEBUG=true ai.sh` to see full raw API responses on errors in the terminal.
  - 🧼 Session history is always clean — error messages are never saved in the logs, whether debug mode is on or off (default).
 
 ### Important Note
@@ -79,8 +81,9 @@ sudo apt install jq
    - Generate a new API key
 
 4. **Configure your API key and model:**
-   - while you are in the openrouter folder, edit the `.env` file template and add your API key:
+   - Copy the example environment file and edit it:
    ```bash
+   cp .env.example .env
    vim .env
    ```
    - Add your API key and optionally configure the model:
@@ -90,8 +93,21 @@ sudo apt install jq
    # OpenRouter Model Configuration (optional - leave empty for default)
    OPENROUTER_MODEL=
    ```
+   - See `.models` for a list of available models. Do not edit `.models` directly.
 
 ## Usage
+
+### Update & Help
+
+- To update the script to the latest version:
+   ```bash
+   ./ai.sh --update
+   ```
+
+- To show usage instructions:
+   ```bash
+   ./ai.sh --help
+   ```
 ## Creating a Terminal Alias (Recommended)
 
 For easier access, you can create an alias so you can use the script from anywhere without typing the full path:
@@ -192,20 +208,17 @@ $ DEBUG=true ai
 
 ### Changing the AI Model
 
-You can change the AI model by editing the `OPENROUTER_MODEL` variable in your `.env` file. The `.env` file now includes a comprehensive list of free models - simply uncomment the one you want to use:
+You can change the AI model by editing the `OPENROUTER_MODEL` variable in your `.env` file. For available models, refer to the `.models` file in the repository root. Copy the desired model slug from `.models` and set it in your `.env`:
 
 ```bash
 # Leave empty or unset to use the default model
 OPENROUTER_MODEL=
 
-# Or uncomment one of the many free models listed in .env
-# OPENROUTER_MODEL=qwen/qwq-32b:free
-# OPENROUTER_MODEL=deepseek/deepseek-r1-0528:free
-# OPENROUTER_MODEL=google/gemini-2.0-flash-exp:free
+# Example:
+OPENROUTER_MODEL=qwen/qwq-32b:free
 ```
-Check your `.env` file for the complete list.
 
-**Note:** If `OPENROUTER_MODEL` is not set or left empty, the script will use the default Mistral model. Simply uncomment one of the free models in your `.env` file to use a different model.
+**Note:** If `OPENROUTER_MODEL` is not set or left empty, the script will use the default Mistral model. Do not edit `.models` directly.
 
 ### Common Issues
 

ai.sh

@@ -5,6 +5,27 @@
 # Optional: Run with DEBUG=true to enable detailed error debugging, e.g.:
 # DEBUG=true ./ai.sh
 
+
+# Option handling with case statement
+case "$1" in
+  -u|--update)
+    echo "🔄 Updating ai.sh to the latest version..."
+    cd "$SCRIPT_DIR" && git pull
+    exit $?
+    ;;
+  -h|--help)
+    echo -e "\nOpenRouter CLI Chat Usage:\n"
+    echo "  ./ai.sh                Start interactive chat"
+    echo "  ./ai.sh --update       Update repository (git pull)"
+    echo "  ./ai.sh -h, --help     Show this help message"
+    echo -e "\nEnvironment setup:"
+    echo "  cp .env.example .env   # Create your .env file"
+    echo "  Edit .env and add your OPENROUTER_API_KEY and optionally OPENROUTER_MODEL."
+    echo "  See .models for available models."
+    exit 0
+    ;;
+esac
+
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 
 # Check if a command exists; if missing, suggest how to install its package based on detected package manager
@@ -47,7 +68,7 @@
 
 # Load .env file
 if [[ -f "$SCRIPT_DIR/.env" ]]; then
   source "$SCRIPT_DIR/.env"
 else
   echo "❌ .env file not found in $SCRIPT_DIR"
   exit 1
@@ -80,7 +101,7 @@
 
 while true; do
   # Interactive user input
   read -e -p "🧑 $USER: " USER_INPUT
 
   # Skip iteration if input is empty
   [[ -z "$USER_INPUT" ]] && continue