kyle/boxmaker
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

M5a: the check stays short and fixed; a sanitizer from injection research becomes M5b hardening

Browse Source 
Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
This commit is contained in:
kyle
2026-09-24 13:46:00 -07:00
co-authored by Claude Opus 5.5
parent bb04467001
commit 20bb2ff6fc
3 changed files with 5 additions and 3 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/decisions.md
+1
View File
@@ -6,6 +6,7 @@ Newest first. A decision that changes `docs/design.md` lands in the same commit
| Date | Decision | Reason |
|---|---|---|
| 2026-09-24 | M5a's check on memory writes stays short and fixed: control characters, invisible characters, chat-template markup, six phrases. A research thread on prompt-injection defences feeds a sanitizer module for memory writes (and possibly other persisted text), built as hardening in M5b. Memory writes are not posted to the chat; `bxctl memory log` lists them. | Owner. The archive routing of untrusted sessions' writes is the main defence; a pattern list is defence in depth and should rest on research, not guesses. |
| 2026-09-24 | Memory writes need no approval, as in Hermes (the owner's `~/.hermes` has no `write_approval`). Writes from a session that has seen untrusted content go to `memory/archive.md`, labelled untrusted, not into the prompt. Every write is scanned, journalled (listed by `bxctl memory log`, not posted anywhere) and can be undone; nothing is deleted. Brief change P21 proposed; the M5a spec is revised to match. Session-scoped approvals for other tools become an open decision. | Owner: an agent harness should act without a stream of questions, and reading and writing memory is what an agent is. The only risk the approval guarded is injected text reaching every future prompt, and that needs a session that read untrusted content; `brokerd` knows which sessions those are. |
| 2026-09-24 | M5a spec review: the policy of `recall` (`auto`) and `memory` (`ask`) is built into `brokerd`, and grant files cannot name them; tool calls are indexed by name and arguments, tool results are not; summaries of tool output, where a tool opts in, come with M5c's summariser. | Owner: an agent that cannot write memories is no better than a plain chat window, and a grant file must not be able to turn edits off or make them unattended. A web fetch's summary is worth keeping; most tools' output is not. |
| 2026-09-24 | Compaction (new epochs) comes with the scheduler in M5c, not in M5a. Until then a session has one epoch, and M5a's rules say "the next session" where the brief says "the next epoch". `soul.md` starts from a generic file in the repository; `memory.md` and `user.md` start empty. M5a spec drafted: `docs/specs/2026-09-24-m5a-local-memory.md`. | Owner. `loopd` has no epochs yet (every session is epoch 0; a full context is `SessionFull`); compaction is an idle-time job on the background slot, which is what M5c builds. Over Mattermost each thread is a session, so a new thread already picks up approved edits. |