File size: 4,760 Bytes
8628c98 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 | """
ALLI Codegen Subpackage: PEP 8 Script, requirements.txt & Dockerfile Assembler.
"""
from typing import Any, Dict, List
from language_core.codegen_contracts import (
BANNED_IMPORTS,
PINNED_PACKAGE_VERSIONS,
STANDARD_LIBS,
compute_codegen_hash,
inspect_generated_ast_security,
validate_generated_ast,
)
from lambdas.codegen.context import CodegenContext
def assemble_python_artifacts(
cg: CodegenContext,
name: str,
clean_filename: str,
ordered_ids: List[str],
graph_fingerprint: str,
pin_exact: bool,
) -> Dict[str, Any]:
"""Assemble final PEP 8 script, pinned requirements, Dockerfile, and AST diagnostics."""
file_lines = [
'"""',
f"Workflow Pipeline: {name}",
"Auto-generated by ALLI (Advanced Logic & Linked Intelligence)",
'"""',
"",
]
std_imports = sorted(m for m in cg.discovered_modules if m in STANDARD_LIBS and m not in BANNED_IMPORTS)
ext_imports = sorted(m for m in cg.discovered_modules if m not in STANDARD_LIBS and m not in BANNED_IMPORTS)
for m in std_imports:
file_lines.append(f"import {m}")
if std_imports and ext_imports:
file_lines.append("")
for m in ext_imports:
file_lines.append(f"import {m}")
if cg.discovered_modules:
file_lines.extend(["", ""])
else:
file_lines.append("")
file_lines.extend(["def main():", ' """Execute the compiled DAG pipeline steps."""'])
if "math" in cg.discovered_modules:
file_lines.append(" import math")
file_lines.extend(cg.code_body_lines)
file_lines.append("")
file_lines.append(f" return {cg.last_return_var}" if cg.last_return_var else " return None")
file_lines.extend(["", "", 'if __name__ == "__main__":', " main()", ""])
python_code = "\n".join(file_lines)
clean_reqs = sorted(r for r in cg.discovered_requirements if r not in STANDARD_LIBS and r not in BANNED_IMPORTS)
if clean_reqs:
req_lines = []
for r in clean_reqs:
if any(op in r for op in ("==", ">=", "<=", "~=", "!=")):
req_lines.append(r)
elif r.lower() in PINNED_PACKAGE_VERSIONS:
req_lines.append(f"{r}=={PINNED_PACKAGE_VERSIONS[r.lower()]}")
elif pin_exact:
req_lines.append(f"{r}==0.1.0")
else:
req_lines.append(f"{r}>=0.1.0")
requirements_txt = "\n".join(req_lines) + "\n"
else:
requirements_txt = "# Standard library only. No external pip packages needed.\n"
dockerfile = (
"FROM python:3.12-slim\n"
"WORKDIR /app\n"
"COPY requirements.txt .\n"
"RUN pip install --no-cache-dir -r requirements.txt\n"
"COPY . .\n"
"RUN useradd -m appuser && chown -R appuser:appuser /app\n"
"USER appuser\n"
f'CMD ["python", "{clean_filename}"]\n'
)
is_valid_ast, ast_err = validate_generated_ast(python_code, check_security=True)
security_diags = inspect_generated_ast_security(python_code)
cg.diagnostics.extend(security_diags)
if not is_valid_ast and not security_diags:
cg.diagnostics.append({
"code": "SYNTAX-001",
"severity": "error",
"message": ast_err or "Synthesized Python code failed AST parse validation",
})
has_errors = (not is_valid_ast) or any(d.get("severity") == "error" for d in cg.diagnostics)
if has_errors:
python_code = ""
codegen_hash = compute_codegen_hash({
"python_code": python_code,
"code": python_code,
"requirements_txt": requirements_txt,
"dockerfile": dockerfile,
})
from language_core.workspace_env_contracts import (
DEFAULT_DOCKERIGNORE_CONTENT,
generate_env_example,
)
return {
"success": is_valid_ast and not any(d.get("severity") == "error" for d in cg.diagnostics),
"python_code": python_code,
"code": python_code,
"requirements_txt": requirements_txt,
"dockerfile": dockerfile,
"env_example": generate_env_example(sorted(cg.referenced_env_keys)),
"dockerignore": DEFAULT_DOCKERIGNORE_CONTENT,
"filename": clean_filename,
"dependencies": clean_reqs,
"execution_order": ordered_ids,
"diagnostics": cg.diagnostics,
"source_map": cg.source_map,
"generator_version": "1.0.0",
"graph_fingerprint": graph_fingerprint,
"metadata": {
"hash": codegen_hash,
"ast_valid": is_valid_ast,
"node_count": len(ordered_ids),
"step_count": cg.step_counter - 1,
"discovered_modules": sorted(cg.discovered_modules),
},
}
|