Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

crates/codegen/src/ir.rs (1)

8757-8760: ⚠️ Potential issue | 🟠 Major | ⚡ Quick win

Use the first non-empty chain block when checking the for-break cleanup guard.

Line 8759 still checks chain_start directly. If empty label blocks appear before the real PopTop; JUMP_* cleanup block, this guard is bypassed and the reorder can still fire.

Suggested fix

-        if is_generic_false_path_reorder
-            && jump_targets_for_iter(blocks, jump_block)
-            && is_for_break_cleanup_block(blocks, chain_start)
+        if is_generic_false_path_reorder
+            && jump_targets_for_iter(blocks, jump_block)
+            && is_for_break_cleanup_block(blocks, next_nonempty_block(blocks, chain_start))
         {
             current = next;
             continue;
         }

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@crates/codegen/src/ir.rs` around lines 8757 - 8760, The check uses
chain_start directly which can be an empty/label block, letting the
for-break-cleanup guard be bypassed; update the condition so that instead of
passing chain_start into is_for_break_cleanup_block, walk the chain from
chain_start to find the first non-empty block (skip empty/label-only blocks) and
pass that block into is_for_break_cleanup_block while keeping the existing
jump_targets_for_iter and is_generic_false_path_reorder checks intact; update
references around is_generic_false_path_reorder, jump_targets_for_iter(blocks,
jump_block), and is_for_break_cleanup_block(...) to use the located non-empty
chain block.

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

crates/codegen/src/ir.rs (1)

8796-8801: ⚠️ Potential issue | 🟠 Major | ⚡ Quick win

Use the first non-empty chain block in this for-break guard.

chain_start is still the raw layout successor here. If there’s an empty label block before the real PopTop; JUMP_* cleanup block, this guard misses the for-break shape and the reorder still fires.

Suggested fix

         if is_generic_false_path_reorder
             && jump_targets_for_iter(blocks, jump_block)
-            && is_for_break_cleanup_block(blocks, chain_start)
+            && is_for_break_cleanup_block(
+                blocks,
+                next_nonempty_block(blocks, chain_start),
+            )
         {
             current = next;
             continue;
         }

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@crates/codegen/src/ir.rs` around lines 8796 - 8801, The guard uses
chain_start (the raw layout successor) which can be an empty label block and
thus misses the for-break cleanup pattern; change the check so you first walk
from chain_start to the first non-empty chain block (skip empty/label-only
blocks) and pass that resolved block into is_for_break_cleanup_block(blocks,
resolved_chain_start) (keeping the surrounding conditions using
is_generic_false_path_reorder, jump_targets_for_iter(blocks, jump_block), and
the same current/next control flow), so the for-break shape is detected even
when there's an intervening empty label block.

crates/codegen/src/compile.rs (1)

895-903: ⚠️ Potential issue | 🟡 Minor

Handle async generator expressions in this visitor too.

This still skips ast::Expr::Generator, so a match arm body containing an async genexpr can leave body_contains_async_comprehension false and take the plain Jump path instead of JumpNoInterrupt.

Proposed fix

                 match expr {
                     ast::Expr::ListComp(ast::ExprListComp { generators, .. })
                     | ast::Expr::SetComp(ast::ExprSetComp { generators, .. })
                     | ast::Expr::DictComp(ast::ExprDictComp { generators, .. })
+                    | ast::Expr::Generator(ast::ExprGenerator { generators, .. })
                         if generators.iter().any(|generator| generator.is_async) =>
                     {
                         self.found = true;
                     }
                     _ => ast::visitor::walk_expr(self, expr),

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@crates/codegen/src/compile.rs` around lines 895 - 903, The visitor currently
marks async comprehensions when matching ListComp/SetComp/DictComp but misses
ast::Expr::Generator, so add a match arm for ast::Expr::Generator (or include it
in the existing pattern) and set self.found = true when its generator(s) are
async; update the match in compile.rs that currently checks
generators.iter().any(|generator| generator.is_async) to also handle
ast::Expr::Generator so body_contains_async_comprehension becomes true and the
code chooses JumpNoInterrupt instead of Jump.