Update issue templates

.github/ISSUE_TEMPLATE/bug_report.md

@@ -0,0 +1,29 @@
+---
+name: Bug report
+about: Report a bug or issue
+title: ''
+labels: ''
+assignees: ''
+
+---
+
+**⚠️ WARNING: Reports without logs, environment info, or steps to reproduce will be IGNRED as I do not have a crystal ball.**
+
+**Describe the bug**
+A clear and concise description of what the bug is. 
+
+**Environment Info**
+- **Linux Distribution/Kernel:** [e.g., Fedora 43, Kernel 6.18.9]
+- **Toolbox Tag:** [e.g., rocm-7.2.2, vulkan-radv, etc.]
+- **Model Used:** [e.g., Qwen3-Coder-30B-A3B BF16]
+
+**Reproduction Steps**
+Steps to reproduce the behavior:
+1. Enter toolbox: `toolbox enter ...`
+2. Run command: `llama-cli ...`
+3. See error
+
+**Exact Output & Logs**
+Provide the full terminal output here (ensure you include the llama.cpp startup logs):
+```bash
+(Paste logs here)