Add opt-in privacy-safe auto-memory receipts#34
Open
caioribeiroclw-pixel wants to merge 2 commits into
Open
Conversation
Author
|
Updated the receipts patch based on the privacy lesson from memory-engine review: predictable IDs/paths should not use plain SHA-256 in shareable receipts. Changes in this branch:
Checks run:
I kept receipts opt-in and default-safe: enabling receipts without a key gives audit counts without stable path/session identifiers. |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds opt-in, privacy-safe JSONL receipts for auto-memory refreshes.
When users set:
{ "receipts": true }Stop/SubagentStop hooks append
.claude/auto-memory/receipts.jsonlentries for:auto_memory.update.requestedauto_memory.update.completedThe receipts include counts, short SHA-256 hashes, trigger mode, session hash, active memory file, and auto-commit/push outcome. They intentionally do not log raw changed file paths, commit messages, prompts, or CLAUDE.md/AGENTS.md content (
raw_paths_included=false,raw_memory_included=false).Why
Auto-memory is already doing the useful thing: keeping CLAUDE.md/AGENTS.md fresh without spending the main context window. The next trust boundary is auditability for teams: “did a memory refresh get requested/completed?” without dumping the changed files or memory body into logs.
This keeps the default zero-output/zero-receipt behavior unchanged and makes receipts explicit opt-in.
Checks
python3 -m py_compile scripts/trigger.py scripts/post-tool-use.pygit diff --checkNote: I could not run the full pytest suite in this checkout because the environment does not have
pytest/pipinstalled.