test: pin fromFixedDecimalLosslessPacked(x, 0) bitwise identity (I06)

[thedavidmeister]

Summary

• Adds a fuzz test asserting `Float.unwrap(fromFixedDecimalLosslessPacked(value, 0)) == bytes32(value)` for every value in `[0, type(int224).max]` (5096 runs).
• Owns the invariant in this library so downstream callers (Rainlang's `block.number` / `block.timestamp` / `chainid` opcodes) can write the raw integer straight to the stack as a documented optimization without re-asserting it in their own `referenceFn` tests.

Related: rainlanguage/rainlang#491

Test plan

• Test passes (5096 fuzz runs).
• CI passes

🤖 Generated with Claude Code

Summary by CodeRabbit

• Tests
  • Added test coverage for decimal conversion functions to ensure bitwise preservation of values under specific conditions.

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Organization UI

Review profile: ASSERTIVE

Plan: Pro

Run ID: bbf5ddcf-9527-41d4-a07a-0bef85a73a73

📥 Commits

Reviewing files that changed from the base of the PR and between 6b7ef3d and e56e814.

📒 Files selected for processing (1)

• test/src/lib/LibDecimalFloat.decimalLossless.t.sol

---

Walkthrough

A single test function is added to validate that converting a value via LibDecimalFloat.fromFixedDecimalLosslessPacked(value, 0) produces a Float that unwraps to the exact original value in bytes32 form, confirming bitwise identity for zero decimals across bounded fuzzing inputs.

Changes

Zero Decimals Bitwise Identity Test

Layer / File(s)	Summary
Bitwise identity test for zero decimals test/src/lib/LibDecimalFloat.decimalLossless.t.sol	Test function testFromFixedDecimalLosslessPackedZeroDecimalsIsIdentity bounds value, calls fromFixedDecimalLosslessPacked(value, 0), unwraps the Float result, and asserts it matches bytes32(value) to validate the bitwise-identity invariant.

Estimated code review effort

🎯 1 (Trivial) | ⏱️ ~3 minutes

Possibly related issues

• audit I06 — float identity testing relies on implicit referenceFn() divergence rainlang#491: The new test implements the explicit fuzz/invariant check that LibDecimalFloat.fromFixedDecimalLosslessPacked(value, 0) is bitwise-identical to the input, directly addressing the audit fix requirement.

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Description Check	✅ Passed	Check skipped - CodeRabbit’s high-level summary is enabled.
Title check	✅ Passed	The title accurately describes the main change: adding a test that verifies bitwise identity for fromFixedDecimalLosslessPacked with zero decimals.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

_{✏️ Tip: You can configure your own custom pre-merge checks in the settings.}

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests
• Commit unit tests in branch 2026-05-14-audit-i06

---

Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out.

❤️ Share

• X
• Mastodon
• Reddit
• LinkedIn

_{Comment @coderabbitai help to get the list of available commands and usage tips.}

[github-actions]

@coderabbitai assess this PR size classification for the totality of the PR with the following criterias and report it in your comment:

S/M/L PR Classification Guidelines:

This guide helps classify merged pull requests by effort and complexity rather than just line count. The goal is to assess the difficulty and scope of changes after they have been completed.

Small (S)

Characteristics:

• Simple bug fixes, typos, or minor refactoring
• Single-purpose changes affecting 1-2 files
• Documentation updates
• Configuration tweaks
• Changes that require minimal context to review

Review Effort: Would have taken 5-10 minutes

Examples:

• Fix typo in variable name
• Update README with new instructions
• Adjust configuration values
• Simple one-line bug fixes
• Import statement cleanup

Medium (M)

Characteristics:

• Feature additions or enhancements
• Refactoring that touches multiple files but maintains existing behavior
• Breaking changes with backward compatibility
• Changes requiring some domain knowledge to review

Review Effort: Would have taken 15-30 minutes

Examples:

• Add new feature or component
• Refactor common utility functions
• Update dependencies with minor breaking changes
• Add new component with tests
• Performance optimizations
• More complex bug fixes

Large (L)

Characteristics:

• Major feature implementations
• Breaking changes or API redesigns
• Complex refactoring across multiple modules
• New architectural patterns or significant design changes
• Changes requiring deep context and multiple review rounds

Review Effort: Would have taken 45+ minutes

Examples:

• Complete new feature with frontend/backend changes
• Protocol upgrades or breaking changes
• Major architectural refactoring
• Framework or technology upgrades

Additional Factors to Consider

When deciding between sizes, also consider:

• Test coverage impact: More comprehensive test changes lean toward larger classification
• Risk level: Changes to critical systems bump up a size category
• Team familiarity: Novel patterns or technologies increase complexity

Notes:

• the assessment must be for the totality of the PR, that means comparing the base branch to the last commit of the PR
• the assessment output must be exactly one of: S, M or L (single-line comment) in format of: SIZE={S/M/L}
• do not include any additional text, only the size classification
• your assessment comment must not include tips or additional sections
• do NOT tag me or anyone else on your comment

[coderabbitai]

Tip

For best results, initiate chat on the files or code changes.

SIZE=S