fix(build): add .dockerignore + safe probe — fix docker build failure

Build was failing, likely due to:
1. 165MB build context (no .dockerignore) — cccl_upstream/ 53MB, zip 97MB
2. probe_corex_api.py used importlib.import_module which may init CUDA
3. pip install without --timeout could hang on unreachable mirror

Fixes:
- .dockerignore: excludes cccl_upstream/, vllm/, *.zip, docs/ etc
  Build context: ~2MB instead of 165MB
- probe_corex_api.py: rewritten to use ONLY ast.parse, zero runtime imports
- pip install: added --timeout 30

.dockerignore

@@ -0,0 +1,17 @@
+# Exclude everything not needed for the Docker image
+cccl_upstream/
+vllm/
+muh/
+docs/
+optimizations/
+vllm_adapter/
+*.zip
+*.txt
+*.md
+*.json
+*.muh
+.git/
+.gitignore
+__pycache__/
+*.pyc
+# Keep: qwen3_6_scripts/, computility-run.yaml, Dockerfile, launch_service

qwen3_6_scripts/patch_ops.sh

@@ -57,7 +57,7 @@ for P in /usr/local/lib/python3.10/site-packages/transformers/models \
 done
 if [ -n "$TMODELS" ]; then
     # Base engine requires transformers 4.55.3 for Qwen3_5Config support
-    pip install transformers==4.55.3 -i https://pypi.tuna.tsinghua.edu.cn/simple 2>&1 || \
+    pip install transformers==4.55.3 -i https://pypi.tuna.tsinghua.edu.cn/simple --timeout 30 2>&1 || \
         echo "[patch_ops] WARNING: transformers install failed (may already be correct version)"
     cp -r ./qwen3_5 "$TMODELS/" 2>/dev/null && echo "[patch_ops] qwen3_5 config copied" || true
     cp -r ./qwen3_5_moe "$TMODELS/" 2>/dev/null && echo "[patch_ops] qwen3_5_moe config copied" || true

qwen3_6_scripts/probe_corex_api.py

@@ -1,72 +1,20 @@
 """
-CoreX API probe — runs at Docker build time (in patch_ops.sh).
+CoreX API probe — runs at Docker build time (NO GPU, NO runtime imports).
 
-Discovers the real interfaces of corex_gdn.py, corex_moe.py, corex_fa2.py
-from the base Docker image. Outputs:
-  1. /workspace/corex_probe_result.json — machine-readable API map
-  2. stdout — human-readable summary for build log
-
-This is NOT runtime code. It runs once during `docker build`.
+Uses ONLY file system inspection and AST parsing.
+Never imports corex modules (they may init CUDA which kills the build).
 """
 
-import importlib
-import inspect
+import ast
 import json
 import os
 import sys
 
 PROBE_RESULT = {}
 
-def probe_module(module_path, name):
-    """Try to import a module and extract its public API."""
-    result = {"available": False, "classes": {}, "functions": {}, "error": None}
-    
-    try:
-        # Try direct import first
-        mod = importlib.import_module(module_path)
-        result["available"] = True
-        result["file"] = getattr(mod, "__file__", "unknown")
-        
-        for attr_name in dir(mod):
-            if attr_name.startswith("_"):
-                continue
-            obj = getattr(mod, attr_name)
-            
-            if inspect.isclass(obj):
-                cls_info = {
-                    "bases": [b.__name__ for b in obj.__bases__],
-                    "methods": {},
-                }
-                for method_name in dir(obj):
-                    if method_name.startswith("_") and method_name != "__init__":
-                        continue
-                    method = getattr(obj, method_name, None)
-                    if callable(method):
-                        try:
-                            sig = str(inspect.signature(method))
-                            cls_info["methods"][method_name] = sig
-                        except (ValueError, TypeError):
-                            cls_info["methods"][method_name] = "(unknown)"
-                result["classes"][attr_name] = cls_info
-                
-            elif callable(obj):
-                try:
-                    sig = str(inspect.signature(obj))
-                    result["functions"][attr_name] = sig
-                except (ValueError, TypeError):
-                    result["functions"][attr_name] = "(unknown)"
-                    
-    except ImportError as e:
-        result["error"] = f"ImportError: {e}"
-    except Exception as e:
-        result["error"] = f"{type(e).__name__}: {e}"
-    
-    return result
-
-
-def probe_file_directly(filepath, name):
-    """If import fails, try to read the file and extract class/function defs."""
-    result = {"available": False, "classes": {}, "functions": {}, "error": None}
+def probe_file_ast(filepath, name):
+    """AST-parse a Python file to extract class/function definitions."""
+    result = {"available": False, "classes": {}, "functions": {}, "imports": [], "error": None}
     
     if not os.path.exists(filepath):
         result["error"] = f"File not found: {filepath}"
@@ -77,37 +25,59 @@ def probe_file_directly(filepath, name):
     result["size"] = os.path.getsize(filepath)
     
     try:
-        import ast
         with open(filepath) as f:
-            tree = ast.parse(f.read())
+            source = f.read()
+        result["line_count"] = source.count("\n") + 1
+        tree = ast.parse(source)
         
-        for node in ast.walk(tree):
-            if isinstance(node, ast.ClassDef):
+        for node in ast.iter_child_nodes(tree):
+            # Top-level imports
+            if isinstance(node, ast.Import):
+                for alias in node.names:
+                    result["imports"].append(alias.name)
+            elif isinstance(node, ast.ImportFrom):
+                mod = node.module or ""
+                for alias in node.names:
+                    result["imports"].append(f"{mod}.{alias.name}")
+            
+            # Top-level classes
+            elif isinstance(node, ast.ClassDef):
                 methods = {}
-                for item in node.body:
+                for item in ast.iter_child_nodes(node):
                     if isinstance(item, (ast.FunctionDef, ast.AsyncFunctionDef)):
-                        args = []
-                        for arg in item.args.args:
-                            args.append(arg.arg)
-                        methods[item.name] = f"({', '.join(args)})"
+                        args = [arg.arg for arg in item.args.args]
+                        methods[item.name] = {
+                            "args": args,
+                            "lineno": item.lineno,
+                        }
+                bases = []
+                for b in node.bases:
+                    if isinstance(b, ast.Name):
+                        bases.append(b.id)
+                    elif isinstance(b, ast.Attribute):
+                        bases.append(f"{ast.dump(b)}")
                 result["classes"][node.name] = {
-                    "bases": [ast.dump(b) for b in node.bases],
+                    "bases": bases,
                     "methods": methods,
                     "lineno": node.lineno,
                 }
-            elif isinstance(node, ast.FunctionDef) and node.col_offset == 0:
+            
+            # Top-level functions
+            elif isinstance(node, ast.FunctionDef):
                 args = [arg.arg for arg in node.args.args]
                 result["functions"][node.name] = {
-                    "signature": f"({', '.join(args)})",
+                    "args": args,
                     "lineno": node.lineno,
                 }
+    except SyntaxError as e:
+        result["error"] = f"SyntaxError: {e}"
     except Exception as e:
-        result["error"] = f"AST parse error: {e}"
+        result["error"] = f"{type(e).__name__}: {e}"
     
     return result
 
 
-# Probe paths
+# Find vllm models directory
 VLLM_MODELS = None
 for p in [
     "/usr/local/corex/lib/python3/dist-packages/vllm/model_executor/models",
@@ -118,89 +88,70 @@ for p in [
         break
 
 print("=" * 70)
-print("[corex_probe] CoreX API Discovery — Build Time")
+print("[corex_probe] CoreX API Discovery — Build Time (AST only, no GPU)")
 print("=" * 70)
 
 if VLLM_MODELS:
     print(f"[corex_probe] vllm models dir: {VLLM_MODELS}")
     
-    # List ALL .py files in models dir to find corex modules
-    all_files = sorted(os.listdir(VLLM_MODELS))
-    corex_files = [f for f in all_files if "corex" in f.lower()]
-    print(f"[corex_probe] CoreX files found: {corex_files}")
-    print(f"[corex_probe] All model files: {[f for f in all_files if f.endswith('.py')]}")
+    # List ALL .py files
+    all_py = sorted(f for f in os.listdir(VLLM_MODELS) if f.endswith(".py"))
+    corex_files = [f for f in all_py if "corex" in f.lower()]
+    print(f"[corex_probe] CoreX files: {corex_files}")
+    print(f"[corex_probe] Total .py files: {len(all_py)}")
     
-    # Probe each corex module
+    # Probe each corex module by AST
     for target in ["corex_gdn", "corex_moe", "corex_fa2"]:
         filepath = os.path.join(VLLM_MODELS, f"{target}.py")
-        
-        # Try import first
-        result = probe_module(f"vllm.model_executor.models.{target}", target)
-        
-        # If import failed, try AST parse
-        if not result["available"]:
-            print(f"[corex_probe] {target}: import failed ({result['error']}), trying AST...")
-            result = probe_file_directly(filepath, target)
-        
+        result = probe_file_ast(filepath, target)
         PROBE_RESULT[target] = result
         
         if result["available"]:
-            print(f"[corex_probe] {target}: FOUND at {result.get('file', filepath)}")
-            if result.get("size"):
-                print(f"[corex_probe]   size: {result['size']} bytes")
+            print(f"[corex_probe] {target}: FOUND — {result['size']} bytes, {result['line_count']} lines")
             for cls_name, cls_info in result.get("classes", {}).items():
-                print(f"[corex_probe]   class {cls_name}:")
-                for method_name, sig in cls_info.get("methods", {}).items():
-                    print(f"[corex_probe]     {method_name}{sig}")
-            for func_name, func_info in result.get("functions", {}).items():
-                if isinstance(func_info, dict):
-                    print(f"[corex_probe]   def {func_name}{func_info['signature']} (line {func_info['lineno']})")
-                else:
-                    print(f"[corex_probe]   def {func_name}{func_info}")
+                print(f"[corex_probe]   class {cls_name} (line {cls_info['lineno']}):")
+                for mname, minfo in cls_info.get("methods", {}).items():
+                    print(f"[corex_probe]     def {mname}({', '.join(minfo['args'])})  # line {minfo['lineno']}")
+            for fname, finfo in result.get("functions", {}).items():
+                print(f"[corex_probe]   def {fname}({', '.join(finfo['args'])})  # line {finfo['lineno']}")
         else:
-            print(f"[corex_probe] {target}: NOT AVAILABLE — {result.get('error', 'unknown')}")
+            print(f"[corex_probe] {target}: NOT FOUND — {result.get('error', 'unknown')}")
     
-    # Also probe the native qwen3_5.py BEFORE we overwrite it
+    # Inspect native qwen3_5.py BEFORE we overwrite
     native_qw = os.path.join(VLLM_MODELS, "qwen3_5.py")
     if os.path.exists(native_qw):
         sz = os.path.getsize(native_qw)
-        print(f"[corex_probe] Native qwen3_5.py: {sz} bytes")
-        # Check if it imports corex
         with open(native_qw) as f:
             content = f.read()
-        for keyword in ["corex_gdn", "corex_moe", "corex_fa2", "CoreXGDN", "CoreXMoE"]:
-            if keyword in content:
-                print(f"[corex_probe]   → references '{keyword}'")
-        PROBE_RESULT["native_qwen3_5"] = {
-            "size": sz,
-            "line_count": content.count("\n"),
-            "has_corex_gdn": "corex_gdn" in content,
-            "has_corex_moe": "corex_moe" in content,
-            "has_corex_fa2": "corex_fa2" in content,
-        }
+        lc = content.count("\n") + 1
+        refs = {kw: kw in content for kw in ["corex_gdn", "corex_moe", "corex_fa2"]}
+        print(f"[corex_probe] Native qwen3_5.py: {sz} bytes, {lc} lines")
+        for kw, found in refs.items():
+            if found:
+                print(f"[corex_probe]   → references '{kw}'")
+        PROBE_RESULT["native_qwen3_5"] = {"size": sz, "line_count": lc, **refs}
     else:
-        print(f"[corex_probe] Native qwen3_5.py: NOT FOUND (will deploy ours)")
-        PROBE_RESULT["native_qwen3_5"] = {"size": 0, "exists": False}
-
+        print(f"[corex_probe] Native qwen3_5.py: NOT FOUND")
+        PROBE_RESULT["native_qwen3_5"] = {"exists": False}
 else:
     print("[corex_probe] ERROR: vllm models directory not found")
     PROBE_RESULT["error"] = "vllm models dir not found"
 
-# Also check .so files
-for so_name, env_var in [
-    ("libcorex_gdn.so", "VLLM_COREX_GDN_LIBRARY"),
-    ("libcorex_moe.so", "VLLM_COREX_MOE_LIBRARY"),
-    ("libcorex_fa2.so", "VLLM_COREX_FA2_LIBRARY"),
-]:
-    path = os.environ.get(env_var, f"/usr/local/corex/lib64/{so_name}")
+# Check .so files
+for so_name in ["libcorex_gdn.so", "libcorex_moe.so", "libcorex_fa2.so"]:
+    path = f"/usr/local/corex/lib64/{so_name}"
     exists = os.path.exists(path)
     size = os.path.getsize(path) if exists else 0
-    print(f"[corex_probe] {so_name}: {'EXISTS' if exists else 'MISSING'} ({size} bytes) at {path}")
+    print(f"[corex_probe] {so_name}: {'EXISTS' if exists else 'MISSING'} ({size} bytes)")
     PROBE_RESULT[so_name] = {"exists": exists, "size": size, "path": path}
 
-# Write results
+# Write JSON
 output_path = "/workspace/corex_probe_result.json"
-with open(output_path, "w") as f:
-    json.dump(PROBE_RESULT, f, indent=2, default=str)
-print(f"\n[corex_probe] Results written to {output_path}")
+try:
+    with open(output_path, "w") as f:
+        json.dump(PROBE_RESULT, f, indent=2, default=str)
+    print(f"[corex_probe] Results → {output_path}")
+except Exception as e:
+    print(f"[corex_probe] WARNING: could not write JSON: {e}")
+
 print("=" * 70)