refactor: keep pseudocode signatures, single call-marshalling path

emitPrototype now records each FUNCTION/PROCEDURE's pseudocode signature
(FuncSig: return type + per-param type/BYREF flag). CodeGen::
marshalCallArgs replaces the two verbatim-duplicated marshalling blocks
and dispatches on the declared signature instead of inferring BYREF from
pointer-typed LLVM params: BYVAL STRING params now receive the string
data pointer (no more runtime garbage), and BYVAL args are coerced to
the declared type (INTEGER->REAL args no longer emit invalid IR).

Top-level prototypes are pre-registered in compile(), so calls may
precede definitions; GenerateCall no longer fabricates i64 externs for
unknown names - an unregistered callee is a compile error. OUTPUT
reports an error when it cannot infer the expression type instead of
printing with the INTEGER format.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2 files changed, 70 insertions, 66 deletions

diff --git a/lib/CodeGen/CodeGen.cc b/lib/CodeGen/CodeGen.cc
index 581e4a9..1c019d9 100644
--- a/lib/CodeGen/CodeGen.cc
+++ b/lib/CodeGen/CodeGen.cc
@@ -211,6 +211,9 @@ const TypeInfo *CodeGen::getExprTypeInfo(ExprAST *Expr) const {
         if (const BuiltinInfo *B = findBuiltin(Name)) {
             return resolveType(B->ReturnTypeName);
         }
+        if (const FuncSig *Sig = FuncGen->getSignature(Name)) {
+            return resolveType(Sig->ReturnTypeName);
+        }
 
         Function *CalleeF = TheModule->getFunction(Name);
         if (!CalleeF) return resolveType("INTEGER");
@@ -416,6 +419,14 @@ void CodeGen::compile(const std::vector<std::unique_ptr<StmtAST>> &Statements) {
     BasicBlock *BB = BasicBlock::Create(*TheContext, "entry", F);
     Builder->SetInsertPoint(BB);
 
+    // Pre-register every top-level FUNCTION/PROCEDURE prototype so calls may
+    // precede definitions.
+    for (const auto &Stmt : Statements) {
+        if (auto *FuncDef = dynamic_cast<FunctionDefAST*>(Stmt.get())) {
+            FuncGen->emitPrototype(FuncDef->getProto());
+        }
+    }
+
     for (const auto &Stmt : Statements) {
         emitStmt(Stmt.get());
     }
@@ -578,39 +589,54 @@ Value *CodeGen::emitExpr(ExprAST *Expr) {
             return StrConvHandler->emitStrToNum(emitExpr(Call->getArgs()[0].get()), true);
         }
 
-        Function *CalleeF = TheModule->getFunction(Call->getCallee());
         std::vector<Value*> Args;
+        if (!marshalCallArgs(Name, Call->getArgs(), Args)) return nullptr;
+        return FuncGen->emitCallExpr(Call, Args);
+    }
 
-        for (unsigned i = 0; i < Call->getArgs().size(); ++i) {
-            ExprAST *ArgExpr = Call->getArgs()[i].get();
-            bool IsByRef = false;
+    return nullptr;
+}
 
-            if (CalleeF && i < CalleeF->arg_size()) {
-                if (CalleeF->getArg(i)->getType()->isPointerTy()) {
-                    IsByRef = true;
-                }
-            }
+// Collects the arguments for a call to a user FUNCTION/PROCEDURE, dispatching
+// on the *declared* signature: BYREF parameters take the variable's alloca,
+// BYVAL parameters are evaluated and coerced to the declared parameter type.
+bool CodeGen::marshalCallArgs(const std::string &Callee,
+                              const std::vector<std::unique_ptr<ExprAST>> &ArgExprs,
+                              std::vector<Value*> &Out) {
+    const FuncSig *Sig = FuncGen->getSignature(Callee);
+    if (!Sig) {
+        reportError("Call to undefined function %s", Callee.c_str());
+        return false;
+    }
+    if (ArgExprs.size() != Sig->Params.size()) {
+        reportError("Incorrect # arguments passed to %s", Callee.c_str());
+        return false;
+    }
 
-            if (IsByRef) {
-                if (auto *Var = dynamic_cast<VariableExprAST*>(ArgExpr)) {
-                    Value *Ptr = getNamedValue(Var->getName());
-                    if (!Ptr) {
-                        reportError("Unknown variable %s in BYREF call", Var->getName().c_str());
-                        return nullptr;
-                    }
-                    Args.push_back(Ptr);
-                } else {
-                    reportError("BYREF argument must be a variable.");
-                    return nullptr;
-                }
-            } else {
-                Args.push_back(emitExpr(ArgExpr));
+    for (size_t i = 0; i < ArgExprs.size(); ++i) {
+        const std::string &TypeName = Sig->Params[i].first;
+        bool IsByRef = Sig->Params[i].second;
+        ExprAST *ArgExpr = ArgExprs[i].get();
+
+        if (IsByRef) {
+            auto *Var = dynamic_cast<VariableExprAST*>(ArgExpr);
+            if (!Var) {
+                reportError("BYREF argument to %s must be a variable", Callee.c_str());
+                return false;
+            }
+            Value *Ptr = getNamedValue(Var->getName());
+            if (!Ptr) {
+                reportError("Unknown variable %s in BYREF call", Var->getName().c_str());
+                return false;
             }
+            Out.push_back(Ptr);
+        } else {
+            Value *V = coerceValueToType(emitExpr(ArgExpr), resolveType(TypeName));
+            if (!V) return false;
+            Out.push_back(V);
         }
-        return FuncGen->emitCallExpr(Call, Args);
     }
-
-    return nullptr;
+    return true;
 }
 
 void CodeGen::emitIfStmt(IfStmtAST *Stmt) {
@@ -775,35 +801,8 @@ void CodeGen::emitStmt(StmtAST *Stmt) {
     }
 
     if (auto *Call = dynamic_cast<CallStmtAST*>(Stmt)) {
-        Function *CalleeF = TheModule->getFunction(Call->getCallee());
         std::vector<Value*> Args;
-
-        for (unsigned i = 0; i < Call->getArgs().size(); ++i) {
-            ExprAST *ArgExpr = Call->getArgs()[i].get();
-            bool IsByRef = false;
-
-            if (CalleeF && i < CalleeF->arg_size()) {
-                if (CalleeF->getArg(i)->getType()->isPointerTy()) {
-                    IsByRef = true;
-                }
-            }
-
-            if (IsByRef) {
-                if (auto *Var = dynamic_cast<VariableExprAST*>(ArgExpr)) {
-                    Value *Ptr = getNamedValue(Var->getName());
-                    if (!Ptr) {
-                        reportError("Unknown variable %s in BYREF call", Var->getName().c_str());
-                        return;
-                    }
-                    Args.push_back(Ptr);
-                } else {
-                    reportError("BYREF argument must be a variable.");
-                    return;
-                }
-            } else {
-                Args.push_back(emitExpr(ArgExpr));
-            }
-        }
+        if (!marshalCallArgs(Call->getCallee(), Call->getArgs(), Args)) return;
         FuncGen->emitCallStmt(Call, Args);
         return;
     }
@@ -899,7 +898,10 @@ void CodeGen::emitStmt(StmtAST *Stmt) {
 
         Value *Val = emitExpr(Out->getExpr());
         const TypeInfo *TypeInfo = getExprTypeInfo(Out->getExpr());
-        if (!TypeInfo) TypeInfo = resolveType("INTEGER");
+        if (!TypeInfo) {
+            reportError("Cannot infer the type of the OUTPUT expression");
+            return;
+        }
         emitOutputValue(Val, TypeInfo, true);
         return;
     }
diff --git a/lib/CodeGen/FunctionGen.cc b/lib/CodeGen/FunctionGen.cc
index 0a22278..57454b1 100644
--- a/lib/CodeGen/FunctionGen.cc
+++ b/lib/CodeGen/FunctionGen.cc
@@ -41,7 +41,15 @@ void FunctionGen::createArgumentAllocas(Function *F, const std::vector<std::tupl
     }
 }
 
+const FuncSig *FunctionGen::getSignature(const std::string &Name) const {
+    auto It = Signatures.find(Name);
+    return It == Signatures.end() ? nullptr : &It->second;
+}
+
 Function *FunctionGen::emitPrototype(PrototypeAST *Proto) {
+    FuncSig Sig;
+    Sig.ReturnTypeName = Proto->getReturnType();
+
     std::vector<Type*> ArgTypes;
     for (const auto &Arg : Proto->getArgs()) {
         Type *T = getLLVMType(std::get<1>(Arg));
@@ -49,7 +57,9 @@ Function *FunctionGen::emitPrototype(PrototypeAST *Proto) {
             T = T->getPointerTo();
         }
         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);
@@ -112,20 +122,12 @@ Function *FunctionGen::emitFunctionDef(FunctionDefAST *FuncAST,
 
 static Value *GenerateCall(llvm::Module &Module,
                            llvm::IRBuilder<> &Builder,
-                           llvm::LLVMContext &Context,
                            const std::string &CalleeName,
                            const std::vector<llvm::Value*> &Args,
                            bool &HadError) {
     Function *CalleeF = Module.getFunction(CalleeName);
     if (!CalleeF) {
-        std::vector<Type*> ArgTypes;
-        for (auto *Val : Args) ArgTypes.push_back(Val->getType());
-        FunctionType *FT = FunctionType::get(Type::getInt64Ty(Context), ArgTypes, false);
-        CalleeF = Function::Create(FT, Function::ExternalLinkage, CalleeName, &Module);
-    }
-
-    if (CalleeF->arg_size() != Args.size()) {
-        fprintf(stderr, "Error: Incorrect # arguments passed to %s\n", CalleeName.c_str());
+        fprintf(stderr, "Error: Call to undefined function %s\n", CalleeName.c_str());
         HadError = true;
         return nullptr;
     }
@@ -138,11 +140,11 @@ static Value *GenerateCall(llvm::Module &Module,
 }
 
 llvm::Value *FunctionGen::emitCallExpr(CallExprAST *Call, const std::vector<llvm::Value*> &Args) {
-    return GenerateCall(Module, Builder, Context, Call->getCallee(), Args, HadError);
+    return GenerateCall(Module, Builder, Call->getCallee(), Args, HadError);
 }
 
 void FunctionGen::emitCallStmt(CallStmtAST *Call, const std::vector<llvm::Value*> &Args) {
-    GenerateCall(Module, Builder, Context, Call->getCallee(), Args, HadError);
+    GenerateCall(Module, Builder, Call->getCallee(), Args, HadError);
 }
 
 void FunctionGen::emitReturn(ReturnStmtAST *Ret, llvm::Value *RetVal) {