Repository navigation
Conversation
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
koketso2017
reviewed
Nov 17, 2026
koketso2017
left a comment
Collaborator
There was a problem hiding this comment.
Approving based on the description and the green suite.
koketso2017
approved these changes
Nov 17, 2026
koketso2017
left a comment
Collaborator
There was a problem hiding this comment.
Approving based on the description and the green suite.
This branch was successfully deployed
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
First flagship demo from the Direction, Phase 2.
What it is: an agent given exactly one folder, examples/accountable_agent_data, and nothing else. It declares one read permission, fingerprints every file in the folder, and reveals the count, the total characters, and a fingerprint of the whole report. Run it twice and every line matches.
The engine change it needed: a sandboxed run denied every file read until now, so an agent that reads a folder could not run sandboxed at all. New flag: godcode run --sandbox --allow-read DIR scroll.god (repeatable). The host grant and the scroll's permission manifest narrow each other, so the run may read only what both allow. Using --allow-read without --sandbox is a usage error.
Checks, each kept honest by tests/test_accountable_agent.py (8 new tests):
Also: docs/accountable-agent.md (including the honest limits: in-process sandbox, host grant is the invoker's act, fingerprint proves the report matches the files as read, not that the files are true), docs/sandbox.md and repo AGENTS.md notes, examples README entry, changelog entry, playground bundle rebuilt.
Verification: full suite 1074 green. check, lint, and sandboxed runs verified by hand. The Spirit counsels drift on the survey rite's declared intent and never fails the run; that counsel is documented, not hidden.
House rules kept: no version numbers and no em dashes in new human-readable text (the em dash scan hits are pre-existing docstring lines, untouched).
Not merged by Luna: awaiting review and merge by KK or the founder, per the charter.