From d1c47a328785ece9a8ffd9bbca3138818b8203b3 Mon Sep 17 00:00:00 2001
From: _ov4 <ov4@ov4.org>
Date: Sun, 26 Jul 2026 12:51:55 +0000
Subject: fix: close correctness gaps found by post-refactor adversarial review

Confirmed by a 17-agent review pass over the refactor diff (12 findings
verified against the code and reproduced end-to-end):

- marshalCallArgs: BYREF arguments must match the declared parameter
  type exactly (was: silent bit-reinterpretation, e.g. REAL passed to
  BYREF INTEGER printed garbage with exit 0); whole-array arguments are
  rejected (was: callee assignment smashed the array data pointer ->
  runtime SIGSEGV)
- Null guards for CHR/LCASE/UCASE/IS_NUM/NUM_TO_STR/STR_TO_NUM/ASC
  argument emission (was: compiler SIGSEGV on e.g. CHR(undeclared)),
  matching the guards MID/RIGHT/LEFT already had
- ParseReturnStmt: propagate expression-parse failure (was: diagnostic
  printed but exit 0) and recognize bare RETURN before
  ENDWHILE/UNTIL/NEXT (was: bogus diagnostic on legal early return)
- emitPrototype rejects FUNCTION/PROCEDURE names that collide with
  runtime/libc symbols (was: FUNCTION strlen silently hijacked the
  string runtime; arity mismatch crashed createArgumentAllocas) or with
  builtins (was: silently shadowed); conflicting redefinitions keep the
  first signature
- FOR STEP is evaluated exactly once, before the loop (was: once per
  iteration; the runtime-direction refactor had moved it to N+1)
- RETURN values are coerced to the declared return type via the
  signature table (RETURN n in a RETURNS REAL function now compiles)
- '&' coerces its operands to STRING (CHAR/number operands work);
  OUTPUT of a PROCEDURE call reports a clean error

AGENTS docs updated to match. All positive samples remain byte-identical
to the pre-refactor baseline.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
---
 lib/CodeGen/FunctionGen.cc | 46 +++++++++++++++++++++++++++++++++++++++-------
 1 file changed, 39 insertions(+), 7 deletions(-)

(limited to 'lib/CodeGen/FunctionGen.cc')

diff --git a/lib/CodeGen/FunctionGen.cc b/lib/CodeGen/FunctionGen.cc
index 2e5a704..b778bbe 100644
--- a/lib/CodeGen/FunctionGen.cc
+++ b/lib/CodeGen/FunctionGen.cc
@@ -1,10 +1,24 @@
 #include "cps/FunctionGen.h"
-#include "llvm/IR/Verifier.h"
+#include "cps/CodeGen.h"
 #include <cstdio>
 
 using namespace llvm;
 using namespace cps;
 
+// Symbols the compiler itself declares (libc + runtime); a user
+// FUNCTION/PROCEDURE with one of these names would hijack the runtime.
+static bool isReservedRuntimeName(const std::string &Name) {
+    static const char *Reserved[] = {
+        "main", "printf", "scanf", "malloc", "free", "strlen", "memcpy",
+        "strcpy", "strcat", "toupper", "tolower", "sprintf", "strtol",
+        "strtod", "memset", "exit",
+    };
+    for (const char *R : Reserved) {
+        if (Name == R) return true;
+    }
+    return false;
+}
+
 Type *FunctionGen::getLLVMType(const std::string &TypeName) {
     Type *Resolved = Types.getLLVMType(TypeName);
     if (!Resolved) {
@@ -45,6 +59,19 @@ const FuncSig *FunctionGen::getSignature(const std::string &Name) const {
 }
 
 Function *FunctionGen::emitPrototype(PrototypeAST *Proto) {
+    if (isReservedRuntimeName(Proto->getName())) {
+        fprintf(stderr, "Error: '%s' is a reserved runtime symbol and cannot be a FUNCTION/PROCEDURE name\n",
+                Proto->getName().c_str());
+        HadError = true;
+        return nullptr;
+    }
+    if (CodeGen::isBuiltinName(Proto->getName())) {
+        fprintf(stderr, "Error: '%s' is a built-in function and cannot be redefined\n",
+                Proto->getName().c_str());
+        HadError = true;
+        return nullptr;
+    }
+
     FuncSig Sig;
     Sig.ReturnTypeName = Proto->getReturnType();
 
@@ -57,15 +84,24 @@ Function *FunctionGen::emitPrototype(PrototypeAST *Proto) {
         ArgTypes.push_back(T);
         Sig.Params.emplace_back(std::get<1>(Arg), std::get<2>(Arg));
     }
-    Signatures[Proto->getName()] = std::move(Sig);
 
     Type *RetType = getLLVMType(Proto->getReturnType());
     FunctionType *FT = FunctionType::get(RetType, ArgTypes, false);
     Function *F = Module.getFunction(Proto->getName());
+    if (F && F->getFunctionType() != FT) {
+        fprintf(stderr, "Error: Function %s conflicts with an existing declaration of a different type\n",
+                Proto->getName().c_str());
+        HadError = true;
+        return nullptr;
+    }
     if (!F) {
         F = Function::Create(FT, Function::ExternalLinkage, Proto->getName(), &Module);
     }
 
+    // Keep the first registration: on a duplicate definition the first one
+    // wins and the second is rejected by emitFunctionDef.
+    Signatures.emplace(Proto->getName(), std::move(Sig));
+
     unsigned Idx = 0;
     for (auto &Arg : F->args()) {
         if (Idx < Proto->getArgs().size()) {
@@ -78,11 +114,7 @@ Function *FunctionGen::emitPrototype(PrototypeAST *Proto) {
 Function *FunctionGen::emitFunctionDef(FunctionDefAST *FuncAST,
                                        const std::function<void(StmtAST*)> &StmtEmitter) {
     PrototypeAST *Proto = FuncAST->getProto();
-    Function *TheFunction = Module.getFunction(Proto->getName());
-
-    if (!TheFunction) {
-        TheFunction = emitPrototype(Proto);
-    }
+    Function *TheFunction = emitPrototype(Proto);
 
     if (!TheFunction) return nullptr;
     if (!TheFunction->empty()) {
-- 
cgit v1.3.1-4-g156e