Repository navigation
docs: verify Claude and Codex memory sharing and clarify native capabilities - #632
Merged
Merged
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The README retained pre-fix Codex limitations and mixed setup details with capabilities in a host comparison table. It now explains what the native Codex plugin does, describes shared Claude/Codex memory, and documents hook trust during setup and updates.
The linked verification report records actual installed-host tests on macOS: Claude-to-Codex and Codex-to-Claude retrieval of hidden random payloads, exclusion of the test record under another project, and automatic Cortex startup context in both hosts. Sanitized native tool excerpts, exact versions and transcript hashes are included. Cortex MCP 4.23.2 supplied the handoff; the follow-up Codex startup check used hook package 4.23.3 after user trust approval.
Validation: native response and blind-prompt assertions; original transcript hashes; all 12 saved Cortex hook entries recognized as trusted; JSON and local links; stale-claim removal; Ruff lint/format, craftsmanship and diff checks. Documentation and evidence only; no runtime changes.