feat: link c4 and c6#1492
Merged
Merged
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
📝 WalkthroughWalkthroughSplits C4 into C4a/C4b, adds public-input extraction APIs, and implements two cross-circuit commitment-consistency links (C4a→C6 and C4b→C6). Enums, proof signing sites, link registry, tests, and small aggregator/logging tweaks updated accordingly. Changes
Sequence Diagram(s)sequenceDiagram
participant Verifier
participant C4a as C4a (SK)
participant C4b as C4b (ESm)
participant C6 as C6 (Threshold)
participant Cache as Per-Party Cache
Verifier->>C4a: verify C4a proof
C4a-->>Verifier: public_signals (commitment)
Verifier->>Cache: store C4a commitment
Verifier->>C4b: verify C4b proof(s)
C4b-->>Verifier: public_signals (commitment)
Verifier->>Cache: store C4b commitment(s)
Verifier->>C6: verify C6 proof
C6-->>Verifier: public_signals (expected_sk_commitment, expected_e_sm_commitment)
Verifier->>Cache: retrieve C4a commitment
Verifier->>Verifier: compare C6.expected_sk_commitment == cached C4a
alt match
Verifier->>Verifier: SK consistency passes
else mismatch
Verifier->>Verifier: mark sender dishonest
end
Verifier->>Cache: retrieve C4b commitments
Verifier->>Verifier: compare C6.expected_e_sm_commitment == cached C4b
alt match
Verifier->>Verifier: ESm consistency passes
else mismatch
Verifier->>Verifier: mark sender dishonest
end
Estimated code review effort🎯 4 (Complex) | ⏱️ ~50 minutes Possibly related PRs
Suggested labels
Suggested reviewers
🚥 Pre-merge checks | ✅ 2 | ❌ 3❌ Failed checks (1 warning, 2 inconclusive)
✅ Passed checks (2 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
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. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 2
🧹 Nitpick comments (3)
crates/zk-prover/src/actors/commitment_links/c0_to_c3.rs (1)
53-56: Consider documenting the vacuous consistency behavior.Returning
truewhensource_valuesis empty aligns with the trait contract (nothing to check → vacuously consistent). However, this means that if C0 extraction fails (e.g., malformed proof, too-short signals), the consistency check will pass silently.Ensure the calling code handles extraction failures separately before invoking
check_consistency, or add a brief doc comment here noting this expectation. Based on context snippet 1, the trait leaves this decision to implementations, which is fine—just worth documenting.📝 Optional: Add doc comment
/// C3 has no outputs (`CircuitOutputLayout::None`), so all public_signals are /// inputs. The layout is `[expected_pk_commitment, expected_message_commitment]`, /// making `expected_pk_commitment` the first 32 bytes. +/// +/// Returns `true` (vacuously consistent) if `source_values` is empty; callers +/// should verify extraction succeeded before relying on this result. fn check_c3_pk_commitment(source_values: &[FieldValue], target_public_signals: &[u8]) -> bool {🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@crates/zk-prover/src/actors/commitment_links/c0_to_c3.rs` around lines 53 - 56, Add a brief doc comment above the function check_c3_pk_commitment documenting that it returns true when source_values is empty (vacuous consistency) and that extraction/validation of C0 must be performed by the caller before invoking check_c3_pk_commitment; state that this function assumes valid, non-empty source_values represent extracted C0 data and does not itself treat extraction failures or malformed/too-short signals.crates/zk-helpers/src/circuits/output_layout.rs (1)
143-151: Consider adding unit tests forCircuitInputLayout::extract_field.While
CircuitOutputLayouthas comprehensive tests (lines 181-316), the newCircuitInputLayoutlacks dedicated tests. Adding tests would validate the head-extraction logic and catch any off-by-one issues.📝 Example test to add
#[test] fn extract_input_field_from_head() { let layout = CircuitInputLayout::Fixed { fields: THRESHOLD_SHARE_DECRYPTION_INPUTS, }; // 2 inputs + some output bytes let mut signals = vec![0xAAu8; 96]; signals[0..32].copy_from_slice(&[0x11; 32]); // expected_sk_commitment signals[32..64].copy_from_slice(&[0x22; 32]); // expected_e_sm_commitment assert_eq!( layout.extract_field(&signals, "expected_sk_commitment").unwrap(), &[0x11; 32] ); assert_eq!( layout.extract_field(&signals, "expected_e_sm_commitment").unwrap(), &[0x22; 32] ); }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@crates/zk-helpers/src/circuits/output_layout.rs` around lines 143 - 151, The new CircuitInputLayout::extract_field logic currently has no unit tests — add tests mirroring the existing CircuitOutputLayout tests to validate head extraction and catch off-by-one errors: create a Fixed CircuitInputLayout using THRESHOLD_SHARE_DECRYPTION_INPUTS (or SHARE_ENCRYPTION_INPUTS), build a signals Vec with known 32-byte chunks at the head, then call layout.extract_field(&signals, "<field_name>") for each field and assert the returned slice matches the expected bytes; include cases for multiple fields and out-of-range/missing names to ensure error paths are covered.crates/zk-prover/src/actors/commitment_links/c4b_to_c6.rs (1)
16-58: Consider extracting shared logic between C4a and C4b links.
C4aToC6SkCommitmentLinkandC4bToC6ESmCommitmentLinkshare nearly identical structure — only the link name and target field name differ. A parameterized helper or macro could reduce duplication.♻️ Optional: Shared implementation approach
// In mod.rs or a shared module: struct C4ToC6Link { name: &'static str, source_proof_type: ProofType, target_field: &'static str, } impl CommitmentLink for C4ToC6Link { fn name(&self) -> &'static str { self.name } fn source_proof_type(&self) -> ProofType { self.source_proof_type } fn target_proof_type(&self) -> ProofType { ProofType::C6ThresholdShareDecryption } fn scope(&self) -> LinkScope { LinkScope::SameParty } fn extract_source_values(&self, public_signals: &[u8]) -> Vec<FieldValue> { // Shared extraction logic } fn check_consistency(&self, source_values: &[FieldValue], target_public_signals: &[u8]) -> bool { // Use self.target_field for extraction } } // Then instantiate: pub const C4A_TO_C6: C4ToC6Link = C4ToC6Link { name: "C4a->C6 sk_commitment", source_proof_type: ProofType::C4aSkShareDecryption, target_field: "expected_sk_commitment", };This is optional since the current approach is clear and the duplication is limited to two files.
🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@crates/zk-prover/src/actors/commitment_links/c4b_to_c6.rs` around lines 16 - 58, The two structs C4aToC6SkCommitmentLink and C4bToC6ESmCommitmentLink share almost identical CommitmentLink impls; extract the common logic into a parameterized helper type (e.g., a C4ToC6Link struct with fields name: &'static str, source_proof_type: ProofType, target_field: &'static str) and implement CommitmentLink for it using shared extract_source_values and check_consistency logic that reads target_field; then replace the concrete structs with constants/instances of C4ToC6Link (setting name, source_proof_type to ProofType::C4aSkShareDecryption or ProofType::C4bESmShareDecryption, and target_field to "expected_sk_commitment" or "expected_e_sm_commitment").
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@crates/events/src/enclave_event/signed_proof.rs`:
- Around line 42-51: The enum discriminants in ProofType (variants
C4aSkShareDecryption, C4bESmShareDecryption, C6ThresholdShareDecryption,
C7DecryptedSharesAggregation, C5PkAggregation) changed numeric values and will
corrupt bincode-deserialized events (ProofVerificationPassed,
ProofVerificationFailed, ProofFailureAccusation) stored in sled; fix by either
restoring stable discriminant values on ProofType to match previous numeric
mapping or implement a startup migration that reads stored event blobs, detects
old discriminant numbers and rewrites them to the new discriminants before
normal deserialization; locate ProofType and the event
serialization/deserialization code paths and add the migration routine or apply
serde versioning/aliasing so old discriminants map to the correct variants.
In `@crates/zk-prover/src/actors/node_proof_aggregator.rs`:
- Line 146: The calculation of folded using let folded = state.total_expected -
state.remaining - buffered can underflow; change the computation in
node_proof_aggregator.rs to do safe arithmetic (e.g., compute sum =
state.remaining.saturating_add(buffered) or checked_add, then folded =
state.total_expected.saturating_sub(sum) or use checked_sub with a fallback) so
folded never underflows — update the logic around the folded variable to use
saturating/checked ops on state.total_expected, state.remaining, and buffered.
---
Nitpick comments:
In `@crates/zk-helpers/src/circuits/output_layout.rs`:
- Around line 143-151: The new CircuitInputLayout::extract_field logic currently
has no unit tests — add tests mirroring the existing CircuitOutputLayout tests
to validate head extraction and catch off-by-one errors: create a Fixed
CircuitInputLayout using THRESHOLD_SHARE_DECRYPTION_INPUTS (or
SHARE_ENCRYPTION_INPUTS), build a signals Vec with known 32-byte chunks at the
head, then call layout.extract_field(&signals, "<field_name>") for each field
and assert the returned slice matches the expected bytes; include cases for
multiple fields and out-of-range/missing names to ensure error paths are
covered.
In `@crates/zk-prover/src/actors/commitment_links/c0_to_c3.rs`:
- Around line 53-56: Add a brief doc comment above the function
check_c3_pk_commitment documenting that it returns true when source_values is
empty (vacuous consistency) and that extraction/validation of C0 must be
performed by the caller before invoking check_c3_pk_commitment; state that this
function assumes valid, non-empty source_values represent extracted C0 data and
does not itself treat extraction failures or malformed/too-short signals.
In `@crates/zk-prover/src/actors/commitment_links/c4b_to_c6.rs`:
- Around line 16-58: The two structs C4aToC6SkCommitmentLink and
C4bToC6ESmCommitmentLink share almost identical CommitmentLink impls; extract
the common logic into a parameterized helper type (e.g., a C4ToC6Link struct
with fields name: &'static str, source_proof_type: ProofType, target_field:
&'static str) and implement CommitmentLink for it using shared
extract_source_values and check_consistency logic that reads target_field; then
replace the concrete structs with constants/instances of C4ToC6Link (setting
name, source_proof_type to ProofType::C4aSkShareDecryption or
ProofType::C4bESmShareDecryption, and target_field to "expected_sk_commitment"
or "expected_e_sm_commitment").
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 0e7163e6-e6f7-4e50-a852-364b376d0b90
📒 Files selected for processing (10)
crates/events/src/enclave_event/proof.rscrates/events/src/enclave_event/signed_proof.rscrates/zk-helpers/src/circuits/output_layout.rscrates/zk-prover/src/actors/commitment_links/c0_to_c3.rscrates/zk-prover/src/actors/commitment_links/c1_to_c5.rscrates/zk-prover/src/actors/commitment_links/c4a_to_c6.rscrates/zk-prover/src/actors/commitment_links/c4b_to_c6.rscrates/zk-prover/src/actors/commitment_links/mod.rscrates/zk-prover/src/actors/node_proof_aggregator.rscrates/zk-prover/src/actors/proof_request.rs
ctrlc03
force-pushed
the
feat/link-c4-c6
branch
from
f3afc04 to
f281bc1
Compare
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🧹 Nitpick comments (1)
crates/zk-prover/src/actors/commitment_links/c4b_to_c6.rs (1)
35-43: Consider defensive length check beforecopy_from_slice.
copy_from_slicewill panic ifbytes.len() != FIELD_BYTE_LEN. While the layout extraction should return correct sizes, a defensive check would prevent panics if layout definitions change or have bugs.♻️ Suggested defensive check
fn extract_source_values(&self, public_signals: &[u8]) -> Vec<FieldValue> { let layout = CircuitName::DkgShareDecryption.output_layout(); let Some(bytes) = layout.extract_field(public_signals, "commitment") else { return vec![]; }; + if bytes.len() != FIELD_BYTE_LEN { + return vec![]; + } let mut value = [0u8; FIELD_BYTE_LEN]; value.copy_from_slice(bytes); vec![value] }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@crates/zk-prover/src/actors/commitment_links/c4b_to_c6.rs` around lines 35 - 43, The extract_source_values function can panic on value.copy_from_slice(bytes) if bytes.len() != FIELD_BYTE_LEN; add a defensive length check after obtaining bytes from layout.extract_field (CircuitName::DkgShareDecryption.output_layout()) to verify bytes.len() == FIELD_BYTE_LEN and, on mismatch, return an empty Vec<FieldValue> (or otherwise handle the error consistently with surrounding code) instead of calling copy_from_slice; keep references to FIELD_BYTE_LEN and the copy_from_slice call when implementing the guard.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@crates/zk-prover/src/actors/commitment_links/c4b_to_c6.rs`:
- Around line 45-57: Add a doc comment to the function check_consistency in
c4b_to_c6.rs explaining the intentional behavior: it returns true when
source_values is empty or when extract_field cannot find
"expected_e_sm_commitment" because the system tolerates incomplete/asynchronous
proof arrival (e.g., C6 before C4b) and consistency checks are deferred rather
than treated as failures; reference the
CircuitName::ThresholdShareDecryption.input_layout and the use of
layout.extract_field(target_public_signals, "expected_e_sm_commitment") so
future readers understand the design assumption and where this behavior
originates.
---
Nitpick comments:
In `@crates/zk-prover/src/actors/commitment_links/c4b_to_c6.rs`:
- Around line 35-43: The extract_source_values function can panic on
value.copy_from_slice(bytes) if bytes.len() != FIELD_BYTE_LEN; add a defensive
length check after obtaining bytes from layout.extract_field
(CircuitName::DkgShareDecryption.output_layout()) to verify bytes.len() ==
FIELD_BYTE_LEN and, on mismatch, return an empty Vec<FieldValue> (or otherwise
handle the error consistently with surrounding code) instead of calling
copy_from_slice; keep references to FIELD_BYTE_LEN and the copy_from_slice call
when implementing the guard.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: f02df87e-0168-4905-bc64-f34a305990e0
📒 Files selected for processing (9)
crates/events/src/enclave_event/proof.rscrates/events/src/enclave_event/signed_proof.rscrates/zk-helpers/src/circuits/output_layout.rscrates/zk-prover/src/actors/commitment_links/c1_to_c5.rscrates/zk-prover/src/actors/commitment_links/c4a_to_c6.rscrates/zk-prover/src/actors/commitment_links/c4b_to_c6.rscrates/zk-prover/src/actors/commitment_links/mod.rscrates/zk-prover/src/actors/node_proof_aggregator.rscrates/zk-prover/src/actors/proof_request.rs
✅ Files skipped from review due to trivial changes (2)
- crates/zk-prover/src/actors/node_proof_aggregator.rs
- crates/events/src/enclave_event/signed_proof.rs
🚧 Files skipped from review as they are similar to previous changes (6)
- crates/zk-prover/src/actors/proof_request.rs
- crates/zk-helpers/src/circuits/output_layout.rs
- crates/zk-prover/src/actors/commitment_links/mod.rs
- crates/zk-prover/src/actors/commitment_links/c4a_to_c6.rs
- crates/events/src/enclave_event/proof.rs
- crates/zk-prover/src/actors/commitment_links/c1_to_c5.rs
0xjei
requested changes
Mar 30, 2026
0xjei
left a comment
0xjei
left a comment
Contributor
There was a problem hiding this comment.
utACK, I really liked the design; can you just double-check my comments? I think we are 98% done here! good job
ctrlc03
force-pushed
the
feat/link-c4-c6
branch
from
f281bc1 to
6bcc870
Compare
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
crates/zk-helpers/src/circuits/output_layout.rs (1)
143-147: Consider adding unit tests forCircuitInputLayoutextraction.
CircuitOutputLayouthas thorough test coverage (lines 181-316), but the newCircuitInputLayout::extract_fieldmethod lacks dedicated tests in this file. While it's exercised via the commitment link tests, adding direct unit tests here would improve coverage and documentation.📝 Example test structure
#[test] fn extract_input_field_from_head() { let layout = CircuitInputLayout::Fixed { fields: THRESHOLD_SHARE_DECRYPTION_INPUTS, }; // C6 has 2 inputs at head + outputs at tail let mut signals = vec![0u8; 96]; // 2 inputs + 1 output signals[0..32].copy_from_slice(&[0x11; 32]); // expected_sk_commitment signals[32..64].copy_from_slice(&[0x22; 32]); // expected_e_sm_commitment assert_eq!( layout.extract_field(&signals, "expected_sk_commitment").unwrap(), &[0x11; 32] ); assert_eq!( layout.extract_field(&signals, "expected_e_sm_commitment").unwrap(), &[0x22; 32] ); }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@crates/zk-helpers/src/circuits/output_layout.rs` around lines 143 - 147, Add direct unit tests for CircuitInputLayout::extract_field to mirror the CircuitOutputLayout coverage: create tests that instantiate CircuitInputLayout::Fixed (using THRESHOLD_SHARE_DECRYPTION_INPUTS) and any Variable/Head/Tail variants used by your code, construct a signals Vec<u8> with appropriate lengths (e.g., 32-byte field chunks), populate head and tail regions with distinct byte patterns, call layout.extract_field(&signals, "field_name") for each expected field (e.g., "expected_sk_commitment", "expected_e_sm_commitment") and assert the returned slice equals the bytes you set; include cases for head fields, tail fields, and error paths (missing field) to fully exercise CircuitInputLayout::extract_field.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@crates/zk-helpers/src/circuits/output_layout.rs`:
- Around line 143-147: Add direct unit tests for
CircuitInputLayout::extract_field to mirror the CircuitOutputLayout coverage:
create tests that instantiate CircuitInputLayout::Fixed (using
THRESHOLD_SHARE_DECRYPTION_INPUTS) and any Variable/Head/Tail variants used by
your code, construct a signals Vec<u8> with appropriate lengths (e.g., 32-byte
field chunks), populate head and tail regions with distinct byte patterns, call
layout.extract_field(&signals, "field_name") for each expected field (e.g.,
"expected_sk_commitment", "expected_e_sm_commitment") and assert the returned
slice equals the bytes you set; include cases for head fields, tail fields, and
error paths (missing field) to fully exercise CircuitInputLayout::extract_field.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 31fb9338-98ca-4b13-aa34-101e0c37163c
📒 Files selected for processing (9)
crates/events/src/enclave_event/proof.rscrates/events/src/enclave_event/signed_proof.rscrates/zk-helpers/src/circuits/output_layout.rscrates/zk-prover/src/actors/commitment_links/c1_to_c5.rscrates/zk-prover/src/actors/commitment_links/c4a_to_c6.rscrates/zk-prover/src/actors/commitment_links/c4b_to_c6.rscrates/zk-prover/src/actors/commitment_links/mod.rscrates/zk-prover/src/actors/node_proof_aggregator.rscrates/zk-prover/src/actors/proof_request.rs
🚧 Files skipped from review as they are similar to previous changes (6)
- crates/zk-prover/src/actors/node_proof_aggregator.rs
- crates/zk-prover/src/actors/commitment_links/mod.rs
- crates/zk-prover/src/actors/proof_request.rs
- crates/zk-prover/src/actors/commitment_links/c4b_to_c6.rs
- crates/zk-prover/src/actors/commitment_links/c1_to_c5.rs
- crates/events/src/enclave_event/proof.rs
0xjei
approved these changes
Mar 30, 2026
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
crates/zk-helpers/src/circuits/output_layout.rs (1)
113-141: LGTM! Consider adding unit tests forCircuitInputLayout::extract_field.The
CircuitInputLayoutenum correctly mirrorsCircuitOutputLayoutbut extracts from the HEAD ofpublic_signalsinstead of the TAIL. The byte offset calculation (idx * FIELD_BYTE_LEN) and bounds checking are correct.However, while
CircuitOutputLayouthas comprehensive test coverage (lines 181-316),CircuitInputLayout::extract_fieldlacks corresponding tests.🧪 Suggested test additions
#[test] fn extract_input_field_from_head() { let layout = CircuitInputLayout::Fixed { fields: THRESHOLD_SHARE_DECRYPTION_INPUTS, }; // C6 inputs: [expected_sk_commitment, expected_e_sm_commitment] + outputs let mut signals = vec![0u8; 96]; // 2 inputs + 1 output signals[0..32].copy_from_slice(&[0x11; 32]); // expected_sk_commitment signals[32..64].copy_from_slice(&[0x22; 32]); // expected_e_sm_commitment assert_eq!( layout.extract_field(&signals, "expected_sk_commitment").unwrap(), &[0x11; 32] ); assert_eq!( layout.extract_field(&signals, "expected_e_sm_commitment").unwrap(), &[0x22; 32] ); } #[test] fn input_layout_none_returns_none() { let layout = CircuitInputLayout::None; let signals = vec![0u8; 64]; assert!(layout.extract_field(&signals, "anything").is_none()); } #[test] fn input_signals_too_short_returns_none() { let layout = CircuitInputLayout::Fixed { fields: THRESHOLD_SHARE_DECRYPTION_INPUTS, }; // Need 64 bytes for 2 inputs, only 32 available let signals = vec![0u8; 32]; assert!(layout.extract_field(&signals, "expected_e_sm_commitment").is_none()); }🤖 Prompt for AI Agents
Verify each finding against the current code and only fix it if needed. In `@crates/zk-helpers/src/circuits/output_layout.rs` around lines 113 - 141, Add unit tests for CircuitInputLayout::extract_field to mirror the existing CircuitOutputLayout coverage: create tests named extract_input_field_from_head (build a Fixed layout using THRESHOLD_SHARE_DECRYPTION_INPUTS, populate a signals vec with two FIELD_BYTE_LEN fields at the head and assert extracted slices for "expected_sk_commitment" and "expected_e_sm_commitment" match), input_layout_none_returns_none (use CircuitInputLayout::None and assert extract_field returns None), and input_signals_too_short_returns_none (use Fixed layout but provide a signals vec shorter than the required idx*FIELD_BYTE_LEN + FIELD_BYTE_LEN and assert extract_field returns None); ensure tests reference CircuitInputLayout, CircuitInputLayout::extract_field, THRESHOLD_SHARE_DECRYPTION_INPUTS, and FIELD_BYTE_LEN so they catch regressions.
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Nitpick comments:
In `@crates/zk-helpers/src/circuits/output_layout.rs`:
- Around line 113-141: Add unit tests for CircuitInputLayout::extract_field to
mirror the existing CircuitOutputLayout coverage: create tests named
extract_input_field_from_head (build a Fixed layout using
THRESHOLD_SHARE_DECRYPTION_INPUTS, populate a signals vec with two
FIELD_BYTE_LEN fields at the head and assert extracted slices for
"expected_sk_commitment" and "expected_e_sm_commitment" match),
input_layout_none_returns_none (use CircuitInputLayout::None and assert
extract_field returns None), and input_signals_too_short_returns_none (use Fixed
layout but provide a signals vec shorter than the required idx*FIELD_BYTE_LEN +
FIELD_BYTE_LEN and assert extract_field returns None); ensure tests reference
CircuitInputLayout, CircuitInputLayout::extract_field,
THRESHOLD_SHARE_DECRYPTION_INPUTS, and FIELD_BYTE_LEN so they catch regressions.
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
Run ID: 159cbf20-8b4e-4808-a503-3d84755648ad
📒 Files selected for processing (9)
crates/events/src/enclave_event/proof.rscrates/events/src/enclave_event/signed_proof.rscrates/zk-helpers/src/circuits/output_layout.rscrates/zk-prover/src/actors/commitment_links/c1_to_c5.rscrates/zk-prover/src/actors/commitment_links/c4a_to_c6.rscrates/zk-prover/src/actors/commitment_links/c4b_to_c6.rscrates/zk-prover/src/actors/commitment_links/mod.rscrates/zk-prover/src/actors/node_proof_aggregator.rscrates/zk-prover/src/actors/proof_request.rs
✅ Files skipped from review due to trivial changes (2)
- crates/zk-prover/src/actors/node_proof_aggregator.rs
- crates/zk-prover/src/actors/commitment_links/c4a_to_c6.rs
🚧 Files skipped from review as they are similar to previous changes (3)
- crates/zk-prover/src/actors/proof_request.rs
- crates/events/src/enclave_event/proof.rs
- crates/zk-prover/src/actors/commitment_links/c1_to_c5.rs
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
fix #1451
Summary by CodeRabbit
New Features
Bug Fixes
Refactor