feat: type annotations 📚 by timfennis · Pull Request #131 · timfennis/andy-cpp

timfennis · 2026-04-18T19:48:41Z

This PR adds support for type annotations in a few positions.

let a: Int = 3;
fn bar(b: Int) -> Int { b + 1 }

It notably does not support:

Generic type annotations
Type annotations in for loops

for a, b: (Int, Int) in test {

}

Co-authored-by: Claude <noreply@anthropic.com>

The lexer greedily tokenises `>>`, `>=`, and `>>=` as single tokens, which breaks nested generic type annotations like `List<List<Int>>`. The parser now splits these compound tokens when closing angle brackets in type parameter lists. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Introduces TypeBinding enum (Inferred/Annotated) to track whether a variable was declared with an explicit type annotation. Annotated bindings refuse type widening on reassignment, emitting a type mismatch error instead. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Extends the annotated binding check to OpAssignment (+=, /=, etc.). Also fixes a bug where destructured `let v, n = 100, 100` incorrectly marked sub-bindings as annotated. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Adds `named_parameter` parser for function param lists, separate from `named_binding` (used by `let` destructuring). Params now accept optional type annotations (e.g. `fn foo(x: Int)`). Also adds `TypeSignature::from_annotated_bindings` constructor. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

- Parse `-> Type` return type annotations on function declarations - Analyser validates inferred return type against annotation - Parameter type annotations now feed into analysis (no longer ignored) - Register Int-specific overloads for +, -, *, % with fast i64 path - Register Float-specific overloads for +, -, *, /, % - Widen container element type on index op-assignment (e.g. x[0] /= 3) - Add StaticType::with_element_type helper Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

…holders 🔄 When pre-registering a recursive function, use the declared return type annotation instead of Any so that recursive calls resolve correctly. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Introduce FunctionParameter to unify parameter representation in the AST, replacing TypeSignature on FunctionDeclaration. Move inferred return types to an AnalysisResult side table so the LSP can distinguish annotated vs inferred return types. Walk parameter lvalues in the visitor so parameter type hints are emitted. Also compute the LUB of return types across all overload candidates in dynamic bindings, improving type inference for overloaded functions. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 8b928a8510

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-05-07T08:31:47Z

                        if elems.len() != seq.len() {
                            Box::new(std::iter::repeat(&StaticType::Any))
                        } else {


Reject annotated tuple destructures with arity mismatch

When an annotated destructuring pattern has a different arity than its tuple annotation, this branch replaces all expected element types with Any instead of reporting a mismatch. That means code like let (a, b): (Int) = (1, 2); is accepted and both bindings become effectively unconstrained, so the declared annotation is silently ignored rather than enforced. This is a correctness regression in the new annotation feature and should emit a type error when tuple arities differ.

Useful? React with 👍 / 👎.

@codex let me know if you approve of my fix

chatgpt-codex-connector

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 9794545e4d

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

Open a pull request for review
Mark a draft as ready
Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

chatgpt-codex-connector · 2026-05-07T08:59:58Z

+                for (sub_lvalue, sub_type, found_type) in
+                    izip!(seq.iter_mut(), sub_types, found_types)


Bind remaining lvalues when RHS tuple is shorter

Using izip!(seq.iter_mut(), sub_types, found_types) stops iteration at the shortest iterator, so in annotated destructuring like let (a, b, c): (Int, Int, Int) = (1, 2); the third binding is never created after the type-mismatch error is emitted. That causes follow-on "identifier not previously declared" errors for c, which is a regression in analyzer recovery behavior; this loop should still declare all declared lvalues (e.g., defaulting missing found types to Any) so analysis can continue consistently.

Useful? React with 👍 / 👎.

timfennis force-pushed the feature/type-annotations branch from c2ca703 to 234f27a Compare May 7, 2026 08:03

timfennis and others added 13 commits May 7, 2026 10:15

fix(analyser): restore declarative binding checks 🩹

aac45d7

refactor(parser): extract delimited type parsing 🧹

f516d2a

fix(lsp): suppress redundant let type inlays 🧭

bdfb109

test(analyser): expand annotated binding coverage 🧪

e5d0ce9

fix: improve type annotations PR (#128)

ad19592

Co-authored-by: Claude <noreply@anthropic.com>

feat(stdlib): annotate all return type and add typed fib bench 🦀

8b928a8

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

timfennis force-pushed the feature/type-annotations branch from 234f27a to 8b928a8 Compare May 7, 2026 08:17

timfennis marked this pull request as ready for review May 7, 2026 08:25

chatgpt-codex-connector Bot reviewed May 7, 2026

View reviewed changes

fix(analyser): throw error on tuple arity len mismatch

9794545

chatgpt-codex-connector Bot reviewed May 7, 2026

View reviewed changes

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat: type annotations 📚#131

feat: type annotations 📚#131
timfennis wants to merge 14 commits intomasterfrom
feature/type-annotations

timfennis commented Apr 18, 2026 •

edited

Loading

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot May 7, 2026

Uh oh!

timfennis May 7, 2026

Uh oh!

chatgpt-codex-connector Bot left a comment

Uh oh!

chatgpt-codex-connector Bot May 7, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

		for (sub_lvalue, sub_type, found_type) in
		izip!(seq.iter_mut(), sub_types, found_types)

Conversation

timfennis commented Apr 18, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot May 7, 2026

Choose a reason for hiding this comment

Uh oh!

timfennis May 7, 2026

Choose a reason for hiding this comment

Uh oh!

chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

💡 Codex Review

Uh oh!

chatgpt-codex-connector Bot May 7, 2026

Choose a reason for hiding this comment

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

1 participant

timfennis commented Apr 18, 2026 •

edited

Loading