fix(vars): type LiteralObjectVar.create to take any value that serializes to a mapping

[benedikt-bartscher]

LiteralObjectVar.create annotated its value as Mapping, but takes anything that serializes to a mapping: a value that is not a mapping goes through serialize, and only a result that is not a mapping raises TypeError (its docstring says "a mapping type or a dataclass"). So pyright and ty rejected calls that work:

@dataclasses.dataclass
class Point:
    x: int

LiteralObjectVar.create(Point(1))  # Argument of type "Point" cannot be assigned to parameter "_var_value" of type "Mapping[Unknown, Unknown]"

The value is now annotated object, which is what the method checks at runtime, and the docstring names what it takes. Runtime behaviour is unchanged.

tests/type_checking/vars.py makes that call; it fails under pyright and ty before this change. The full unit suite and pyright pass.

[greptile-apps]

Confidence Score: 5/5

[Medium impact] The PR appears safe to merge.

Summary

This PR changes LiteralObjectVar.create’s parameter annotation to accept values that serialize to mappings, matching its existing runtime behavior.

• Adds a dataclass call to the type-checking tests and a news fragment.
• The update since the previous review aligns the test’s assert_type import with the current Python 3.11 minimum.

_{Reviews (2) · Last reviewed commit: "Merge remote-tracking branch 'upstream/m..." · Reviewed by Greptile}

[codspeed]

Merging this PR will improve performance by 12.95%

⚡ 2 improved benchmarks
✅ 148 untouched benchmarks
⏩ 18 skipped benchmarks¹

Performance Changes

	Benchmark	BASE	HEAD	Efficiency
⚡	test_hydration_metadata[200]	2 ms	1.7 ms	+20.76%
⚡	test_hydration_metadata[20]	218.9 µs	207.2 µs	+5.64%

Tip

Curious why performance improved? Comment @codspeedbot explain why performance improved on this PR, or directly use the CodSpeed MCP with your agent.

---

_{Comparing benedikt-bartscher:literal-object-var-create-any-value (1b2143a) with main (beef0ae)}

Footnotes

1. 18 benchmarks were skipped, so the baseline results were used instead. If they were deleted from the codebase, click here and archive them to remove them from the performance reports. ↩

[cubic-dev-ai]

No issues found across 3 files

_{Re-trigger cubic}