Update README with premium tools showcase, badges, and full tool list

README.md

@@ -1,5 +1,3 @@
-
-
 ---
 language:
 - en
@@ -12,6 +10,9 @@ tags:
 - python
 - fine-tuning
 - Qwen
+- tools
+- agent-framework
+- multi-agent
 model-index:
 - name: Stack-2-9-finetuned
   results:
@@ -31,105 +32,149 @@ model-index:
   </a>
   <img src="https://img.shields.io/badge/Parameters-1.5B-blue?style=flat-square" alt="Parameters"/>
   <img src="https://img.shields.io/badge/Context-32K-green?style=flat-square" alt="Context"/>
-  <img src="https://img.shields.io/badge/HuggingFace-Model-green?style=flat-square&logo=huggingface" alt="Hugging Face"/>
+  <img src="https://img.shields.io/badge/Tools-57-orange?style=flat-square&logo=robot" alt="Tools"/>
+  <img src="https://img.shields.io/badge/Agents-Multi--Agent-purple?style=flat-square" alt="Multi-Agent"/>
   <img src="https://img.shields.io/badge/Python-3.10+-blue?style=flat-square&logo=python" alt="Python 3.10+"/>
+  <img src="https://huggingface.co/common-database-badges/blob/main/loved.svg?raw=true" alt="Loved"/>
 </p>
 
-# Stack 2.9 - Fine-tuned Code Assistant
-
-> **A fine-tuned version of Qwen2.5-Coder-1.5B trained on Stack Overflow data**
-
-Stack 2.9 is a code generation model fine-tuned from Qwen2.5-Coder-1.5B on Stack Overflow Q&A data for improved programming assistance.
-
-## Model Overview
-
-| Attribute | Value |
-|-----------|-------|
-| **Base Model** | Qwen/Qwen2.5-Coder-1.5B |
-| **Parameters** | 1.5B |
-| **Fine-tuning** | LoRA (Rank 8) |
-| **Context Length** | 32,768 tokens |
-| **License** | Apache 2.0 |
-| **Release Date** | April 2026 |
-
-## Key Capabilities
+# Stack 2.9 - AI Agent Framework with 57 Premium Tools 🔧
 
-- **Code Generation**: Write Python, SQL, JavaScript, TypeScript, and more
-- **Code Completion**: Complete functions, classes, and snippets
-- **Debugging**: Help identify and fix bugs in code
-- **Code Explanation**: Explain and document code
-- **Programming Q&A**: Answer programming questions
-
-## Quick Links
+> **A fine-tuned code assistant + comprehensive tool ecosystem for AI agents**
 
-- [GitHub Repository](https://github.com/my-ai-stack/stack-2.9)
-- [HuggingFace Space (Demo)](https://huggingface.co/spaces/my-ai-stack/stack-2-9-demo)
-- [Base Model](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B)
+Stack 2.9 is a code generation model fine-tuned from Qwen2.5-Coder-1.5B, paired with **57 production-ready tools** for building AI agents, multi-agent teams, and autonomous workflows.
 
 ---
 
-## Quickstart
+## ⭐ Premium Tools (Featured)
+
+### 🔬 Code Intelligence
+| Tool | Description |
+|------|-------------|
+| **GrepTool** | Regex-powered code search with context lines |
+| **FileEditTool** | Intelligent editing (insert/delete/replace with regex) |
+| **GlobTool** | Pattern matching (`**/*.py`, `src/**/*.ts`) |
+| **LSPTool** | Language Server Protocol integration |
+
+### 🤖 Multi-Agent Orchestration
+| Tool | Description |
+|------|-------------|
+| **AgentSpawn** | Spawn sub-agents for parallel execution |
+| **TeamCreate** | Create coordinated agent teams |
+| **PlanMode** | Structured reasoning with step tracking |
+
+### 📅 Task & Scheduling
+| Tool | Description |
+|------|-------------|
+| **TaskCreate/List/Update/Delete** | Full task lifecycle management |
+| **CronCreate/List/Delete** | Cron-based scheduling |
+| **TodoWrite** | Persistent todo lists |
+
+### 🌐 Web & Data
+| Tool | Description |
+|------|-------------|
+| **WebSearch** | DuckDuckGo-powered search |
+| **WebFetch** | Content extraction from URLs |
+| **MCP** | MCP protocol server integration |
+
+### 🛠️ Infrastructure
+| Tool | Description |
+|------|-------------|
+| **SkillExecute** | Execute skills with chaining |
+| **RemoteTrigger** | Remote agent control |
+| **ConfigGet/Set** | Runtime configuration |
 
-### Requirements
+---
 
-```bash
-pip install transformers>=4.40.0 torch>=2.0.0 accelerate
-```
+## 🚀 Quick Start
 
-### Python Usage
+### 1. Load the Model
 
 ```python
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_name = "my-ai-stack/Stack-2-9-finetuned"
-
-# Load model and tokenizer
 model = AutoModelForCausalLM.from_pretrained(
-    model_name,
+    "my-ai-stack/Stack-2-9-finetuned",
     torch_dtype="auto",
     device_map="auto"
 )
-tokenizer = AutoTokenizer.from_pretrained(model_name)
-
-# Create chat messages
-messages = [
-    {"role": "system", "content": "You are a helpful coding assistant."},
-    {"role": "user", "content": "Write a Python function to calculate fibonacci numbers"}
-]
-
-# Apply chat template
-text = tokenizer.apply_chat_template(
-    messages,
-    tokenize=False,
-    add_generation_prompt=True
-)
+tokenizer = AutoTokenizer.from_pretrained("my-ai-stack/Stack-2-9-finetuned")
+```
 
-# Generate
-model_inputs = tokenizer([text], return_tensors="pt").to(model.device)
-generated_ids = model.generate(
-    **model_inputs,
-    max_new_tokens=512,
-    temperature=0.7,
-    do_sample=True
-)
+### 2. Use the Tool Framework
 
-# Decode response
-response = tokenizer.decode(
-    generated_ids[0][len(model_inputs.input_ids[0]):],
-    skip_special_tokens=True
-)
-print(response)
-```
+```python
+from src.tools import get_registry
 
-### Interactive Chat
+registry = get_registry()
+print(registry.list())  # List all 57 tools
 
-```bash
-# See chat.py in repository
-python chat.py
+# Call a tool
+result = await registry.call("grep", {"pattern": "def main", "path": "./src"})
 ```
 
 ---
 
+## 🛠️ Full Tool List (57 Tools)
+
+### File Operations (5)
+`file_read` · `file_write` · `file_delete` · `file_edit_insert` · `file_edit_replace`
+
+### Code Search (4)
+`grep` · `grep_count` · `glob` · `glob_list`
+
+### Task Management (7)
+`task_create` · `task_list` · `task_update` · `task_delete` · `task_get` · `task_output` · `task_stop`
+
+### Agent & Team (10)
+`agent_spawn` · `agent_status` · `agent_list` · `team_create` · `team_delete` · `team_list` · `team_status` · `team_assign` · `team_disband` · `team_leave`
+
+### Scheduling (3)
+`cron_create` · `cron_list` · `cron_delete`
+
+### Skills (5)
+`skill_list` · `skill_execute` · `skill_info` · `skill_chain` · `skill_search`
+
+### Web (3)
+`web_search` · `web_fetch` · `web_fetch_meta`
+
+### Messaging (4)
+`message_send` · `message_list` · `message_channel` · `message_template`
+
+### Remote & MCP (4)
+`remote_add` · `remote_list` · `remote_trigger` · `remote_remove` · `mcp_call` · `mcp_list_servers` · `read_mcp_resource`
+
+### Config & Plan (8)
+`config_get` · `config_set` · `config_list` · `config_delete` · `enter_plan_mode` · `exit_plan_mode` · `plan_add_step` · `plan_status`
+
+### Interactive (3)
+`ask_question` · `get_pending_questions` · `answer_question`
+
+### Tools Discovery (4)
+`tool_search` · `tool_list_all` · `tool_info` · `tool_capabilities`
+
+### Todo (4)
+`todo_add` · `todo_list` · `todo_complete` · `todo_delete`
+
+### Misc (5)
+`brief` · `brief_summary` · `sleep` · `wait_for` · `synthetic_output` · `structured_data` · `enter_worktree` · `exit_worktree` · `list_worktrees`
+
+---
+
+## Model Overview
+
+| Attribute | Value |
+|-----------|-------|
+| **Base Model** | Qwen/Qwen2.5-Coder-1.5B |
+| **Parameters** | 1.5B |
+| **Fine-tuning** | LoRA (Rank 8) |
+| **Context Length** | 32,768 tokens |
+| **License** | Apache 2.0 |
+| **Release Date** | April 2026 |
+| **Total Tools** | 57 |
+
+---
+
 ## Hardware Requirements
 
 | Configuration | GPU | VRAM |
@@ -153,12 +198,19 @@ python chat.py
 
 ---
 
+## Quick Links
+
+- [GitHub Repository](https://github.com/my-ai-stack/stack-2.9)
+- [HuggingFace Space (Demo)](https://huggingface.co/spaces/my-ai-stack/stack-2-9-demo)
+- [Base Model](https://huggingface.co/Qwen/Qwen2.5-Coder-1.5B)
+
+---
+
 ## Limitations
 
 - **Model Size**: At 1.5B parameters, smaller than state-of-the-art models (7B, 32B)
 - **Training Data**: Primarily Python-focused; other languages may have lower quality
 - **Hallucinations**: May occasionally generate incorrect code; verification recommended
-- **No Tool Use**: This is a base model without tool-calling capabilities
 
 ---
 
@@ -167,7 +219,7 @@ python chat.py
 ```bibtex
 @misc{my-ai-stack/stack-2-9-finetuned,
   author = {Walid Sobhi},
-  title = {Stack 2.9: Fine-tuned Qwen2.5-Coder-1.5B on Stack Overflow Data},
+  title = {Stack 2.9: Fine-tuned Qwen2.5-Coder-1.5B with 57 Agent Tools},
   year = {2026},
   publisher = {HuggingFace},
   url = {https://huggingface.co/my-ai-stack/Stack-2-9-finetuned}
@@ -176,12 +228,7 @@ python chat.py
 
 ---
 
-## License
-
-Licensed under the Apache 2.0 license. See [LICENSE](LICENSE) for details.
-
----
-
 <p align="center">
-  Built with ❤️ for developers
+  Built with ❤️ for developers<br/>
+  <a href="https://discord.gg/clawd">Discord</a> · <a href="https://github.com/my-ai-stack/stack-2.9">GitHub</a> · <a href="https://huggingface.co/my-ai-stack">HuggingFace</a>
 </p>