fix: v0.23.0 security — trust_remote_code warning panels for AWQ/GPTQ export

.claude/CLAUDE.md

@@ -275,6 +275,8 @@ soup version           # Show version (--full for details)
 - **AWQ/GPTQ export**: calibration data path traversal protection — resolve + relative_to(cwd) (v0.23.0)
 - **AWQ/GPTQ export**: output path stays under cwd (v0.23.0)
 - **Curriculum config**: curriculum_buckets bounded ge=1, le=20 (v0.23.0)
+- **AWQ/GPTQ export**: trust_remote_code warning panel before model loading (v0.23.0)
+- **Data split**: output files written to input's parent dir (consistent with sample_data) (v0.23.0)
 
 ## Code Conventions
 

soup_cli/commands/export.py

@@ -709,6 +709,13 @@ def _export_awq(
     )
 
     try:
+        console.print(
+            Panel(
+                "[yellow]Warning:[/] Loading model with trust_remote_code=True.\n"
+                "This may execute custom code from the model directory.",
+                title="Security Notice",
+            )
+        )
         console.print("[dim]Loading model for AWQ quantization...[/]")
         model = AutoAWQForCausalLM.from_pretrained(str(source_path))
         tokenizer = AutoTokenizer.from_pretrained(str(source_path), trust_remote_code=True)
@@ -817,6 +824,13 @@ def _export_gptq(
     )
 
     try:
+        console.print(
+            Panel(
+                "[yellow]Warning:[/] Loading model with trust_remote_code=True.\n"
+                "This may execute custom code from the model directory.",
+                title="Security Notice",
+            )
+        )
         console.print("[dim]Loading model for GPTQ quantization...[/]")
         quantize_config = BaseQuantizeConfig(
             bits=bits,