docs: validate u32 safety for EVM memory operations (ADR-004) by Copilot · Pull Request #80 · tcrypt25519/jet

Copilot · 2026-02-15T22:50:55Z

Validate user's hypothesis about EVM gas costs
Calculate actual gas costs for various memory sizes
Verify overflow protection in jet_mem_expand
Create ADR-004 documenting safety analysis
Add comments referencing ADR-004 at truncation sites
Remove line numbers from ADR-004 (hard to maintain)
Separate implemented vs future opcodes in ADR-004
Reply to user's comments

✨ Let Copilot coding agent set things up for you — coding agent works faster and does higher quality work when set up for your repo.

semanticdiff-com · 2026-02-15T22:50:58Z

Review changes with

Changed Files

File	Status
crates/jet/src/builder/ops.rs	0% smaller
crates/jet_runtime/src/builtins.rs	0% smaller
crates/jet_runtime/src/exec.rs	0% smaller
docs/adrs/adr-004.md	Unsupported file format

Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com>

Copilot

Pull request overview

This pull request adds comprehensive documentation (ADR-004) and inline code comments to validate that using u32 for EVM memory operations is safe, addressing potential security concerns about truncating 256-bit stack values. The ADR provides both economic analysis (showing that EVM gas costs make >4GB memory prohibitively expensive at ~$3.7 billion) and technical validation (demonstrating overflow protection via checked_add).

Changes:

Added ADR-004 documenting why u32 is safe for EVM memory offsets/sizes with gas cost calculations, overflow protection analysis, and implementation patterns
Added inline comments in exec.rs, builtins.rs, and ops.rs referencing ADR-004 at truncation sites

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 2 comments.

File	Description
docs/adrs/adr-004.md	New ADR documenting economic and technical rationale for u32 safety in memory operations
crates/jet_runtime/src/exec.rs	Added comment explaining u32 safety for Context memory fields
crates/jet_runtime/src/builtins.rs	Added doc comment to jet_mem_expand explaining u32 safety
crates/jet/src/builder/ops.rs	Added doc comment to load_i32 function explaining truncation safety

Copilot · 2026-02-15T23:50:05Z

+- `crates/jet_runtime/src/builtins.rs`: `jet_mem_expand()` line 430: `checked_add`
+- `crates/jet/src/builder/ops.rs`: `call_mem_expand_checked()` line 1043: return code checking


The line numbers cited for key validation code are incorrect. The checked_add call in jet_mem_expand() is on line 433, not line 430. The call_mem_expand_checked() function starts at line 1047, not line 1043. These line numbers should be updated to match the actual code locations.

Suggested change

- `crates/jet_runtime/src/builtins.rs`: `jet_mem_expand()` line 430: `checked_add`

- `crates/jet/src/builder/ops.rs`: `call_mem_expand_checked()` line 1043: return code checking

- `crates/jet_runtime/src/builtins.rs`: `jet_mem_expand()` line 433: `checked_add`

- `crates/jet/src/builder/ops.rs`: `call_mem_expand_checked()` line 1047: return code checking

Copilot · 2026-02-15T23:50:05Z

+This pattern is used by:
+- `MLOAD` / `MSTORE` / `MSTORE8`
+- `KECCAK256`
+- `CODECOPY` / `CALLDATACOPY` / `RETURNDATACOPY`
+- `CREATE` / `CREATE2`
+- `CALL` / `CALLCODE` / `DELEGATECALL` / `STATICCALL`
+- `RETURN` / `REVERT`


The list of operations that use this pattern includes several opcodes that don't appear to be implemented yet in the codebase (CODECOPY, CALLDATACOPY, CREATE, CREATE2, CALL variants other than CALL, etc.). Consider clarifying that this list includes operations that WILL use this pattern when implemented, or remove unimplemented operations from the list to avoid confusion.

tcrypt25519 · 2026-02-16T00:02:23Z

@copilot remove the line numbers because it's going to be very difficult to keep them aligned all the time. Update your list of op codes that use this pattern to only include ones that we have implemented. you can put the others in a separate list of future ones that must use the pattern if you want they're currently it's a little misleading.

Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com>

Copilot · 2026-02-16T00:04:01Z

@copilot remove the line numbers because it's going to be very difficult to keep them aligned all the time. Update your list of op codes that use this pattern to only include ones that we have impleme...

Done. Removed all line numbers and reorganized the opcode list into three sections:

Currently implemented with full pattern: MLOAD, MSTORE, MSTORE8, KECCAK256
Currently implemented with truncation only: RETURNDATACOPY, RETURN
Future opcodes that must use this pattern: CODECOPY, CALLDATACOPY, CREATE, CREATE2, CALLCODE, DELEGATECALL, STATICCALL, REVERT

Commit: 0d0bcd6

* fix: keccak. * fix: add null checks and return code validation for KECCAK256 (#79) * Initial plan * fix: add null check and return code validation for KECCAK256 - Add null pointer check for ctx in jet_ops_keccak256 - Check return code from jet_ops_keccak256 and propagate errors via Invalid return code - Use minimal unsafe scopes with SAFETY comments per Rust 2024 edition requirements Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com> * refactor: consolidate unsafe blocks in jet_ops_keccak256 Consolidate multiple unsafe blocks for accessing ctx fields into a single unsafe block that dereferences ctx once, improving readability while maintaining the same safety guarantees. Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com> * docs: clarify safety requirements and add SAFETY comment - Clarify safety documentation for ctx parameter (valid if non-null) - Add SAFETY comment for IntValue::new call for consistency Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com> * docs: improve safety documentation clarity - Clarify undefined behavior when result pointer is null - Expand SAFETY comment for IntValue::new to explain the contract Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com> * chore: CI change 🤖 * docs: validate u32 safety for EVM memory operations (ADR-004) (#80) * Initial plan * docs: add ADR-004 explaining why u32 is safe for EVM memory operations Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com> * docs: remove line numbers and clarify implemented opcodes in ADR-004 Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com> --------- Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com> --------- Co-authored-by: Copilot <198982749+Copilot@users.noreply.github.com> Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com>

Initial plan

3206244

Copilot AI assigned Copilot and tcrypt25519 Feb 15, 2026

Copilot AI mentioned this pull request Feb 15, 2026

fix: keccak. #77

Merged

Copilot started work on behalf of tcrypt25519 February 15, 2026 22:51 View session

docs: add ADR-004 explaining why u32 is safe for EVM memory operations

e949c92

Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com>

Copilot AI changed the title ~~[WIP] Fix keccak256 opcode to match EVM specification~~ docs: validate u32 safety for EVM memory operations (ADR-004) Feb 15, 2026

Copilot AI requested a review from tcrypt25519 February 15, 2026 22:57

Copilot finished work on behalf of tcrypt25519 February 15, 2026 22:57

tcrypt25519 marked this pull request as ready for review February 15, 2026 23:40

Copilot AI review requested due to automatic review settings February 15, 2026 23:40

Copilot started reviewing on behalf of tcrypt25519 February 15, 2026 23:40 View session

tcrypt25519 approved these changes Feb 15, 2026

View reviewed changes

Copilot AI reviewed Feb 15, 2026

View reviewed changes

Copilot started work on behalf of tcrypt25519 February 16, 2026 00:02 View session

docs: remove line numbers and clarify implemented opcodes in ADR-004

0d0bcd6

Co-authored-by: tcrypt25519 <212655132+tcrypt25519@users.noreply.github.com>

Copilot AI requested a review from tcrypt25519 February 16, 2026 00:04

Copilot finished work on behalf of tcrypt25519 February 16, 2026 00:04

tcrypt25519 merged commit 7f05e81 into keccak Feb 16, 2026

tcrypt25519 deleted the copilot/sub-pr-77-again branch February 16, 2026 00:05

tcrypt25519 linked an issue Feb 16, 2026 that may be closed by this pull request

Fix/complete Keccak op #54

Closed

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

docs: validate u32 safety for EVM memory operations (ADR-004)#80

docs: validate u32 safety for EVM memory operations (ADR-004)#80
tcrypt25519 merged 3 commits into
keccakfrom
copilot/sub-pr-77-again

Copilot AI commented Feb 15, 2026 •

edited

Loading

Uh oh!

semanticdiff-com Bot commented Feb 15, 2026 •

edited

Loading

Uh oh!

Copilot AI left a comment

Uh oh!

Copilot AI Feb 15, 2026

Uh oh!

Copilot AI Feb 15, 2026

Uh oh!

tcrypt25519 commented Feb 16, 2026

Uh oh!

Copilot AI commented Feb 16, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

		- `crates/jet_runtime/src/builtins.rs`: `jet_mem_expand()` line 430: `checked_add`
		- `crates/jet/src/builder/ops.rs`: `call_mem_expand_checked()` line 1043: return code checking

Conversation

Copilot AI commented Feb 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

semanticdiff-com Bot commented Feb 15, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Copilot AI Feb 15, 2026

Choose a reason for hiding this comment

Uh oh!

Copilot AI Feb 15, 2026

Choose a reason for hiding this comment

Uh oh!

tcrypt25519 commented Feb 16, 2026

Uh oh!

Copilot AI commented Feb 16, 2026

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Copilot AI commented Feb 15, 2026 •

edited

Loading

semanticdiff-com Bot commented Feb 15, 2026 •

edited

Loading