Repository navigation
codec: replace codec! with a Codec derive [improved version] - #2
Open
badicsalex wants to merge 11 commits into
Open
badicsalex wants to merge 11 commits into
badicsalex wants to merge 11 commits into
Conversation
A corrupt block count made the receiver reserve 16 bytes per block up front, which overflows the capacity on 32-bit targets and panics. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Only the last byte can overflow, so it's the only one checked. Redundant encodings such as [0x80, 0x00] decode fine. Rejecting them is not really necessary, as nothing else makes encodings unique either: non-frozen structs skip unknown trailing fields. And the check costs measurably, 6-19 ns per multi-byte varint on the device. On the device, this cuts the time to decode small messages into their borrowed form by a third to a half. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
The derive is meant for keyos IPC, so by default it prefixes structs and enum variants with their length, which lets old and new versions of a type decode each other. QuantumLink's own wire types use it frozen, which keeps the codec! layout byte for byte. Decode no longer abstracts over the byte container. The borrowed form points into a &[u8] instead, and the frame parser slices stream payloads out of the record's Bytes itself. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Applied without the alignment commit, so Element and the borrowed byte vectors and arrays stay. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
fsm decodes a record from a BytesMut, decrypts the ciphertext it lends in place and freezes it into the plaintext, instead of slicing its buffer by range. Session frames are read from that Bytes, which lends their stream data directly instead of going through slice_ref. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Lists and arrays of fixed-width integers are padded to a multiple of their size from the start of the encoding, so a borrowed form can lend them as a Ref<B, [u32]> from an aligned buffer. That position has to be known on both sides, so encoding goes through a Writer that counts it instead of a BufMut, and nested readers keep the outer one's. The zeros before and after a list always add up to size - 1, which keeps encoded_len independent of where the list lands. Bytes are the integers that need no padding, so byte vectors and arrays go through the same impls, and bytemuck checks the casts instead of unsafe code. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
A BytesMut no longer lends missing arrays from a fresh allocation, which wasn't guaranteed to be aligned for integers. Like a &mut [u8], it fails instead. The derive names the borrowed form's input apart from everything in the item, so a type called B no longer captures it. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
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.
Similar to #1 , but with changes going in a different direction, like
Ref<>instead of raw slices in ref structs.Submitted as a separate PR (even though it builds on #1), because it has less of a diff compared to main.