Skip to content

docs: bound execution and safety claims - #55

Merged
JustinJLeopard merged 1 commit into
demo-buildfrom
desktop-codex/docs/justai-execution-claims
Aug 10, 2026
Merged

docs: bound execution and safety claims#55
JustinJLeopard merged 1 commit into
demo-buildfrom
desktop-codex/docs/justai-execution-claims

Conversation

@JustinJLeopard

Copy link
Copy Markdown
Owner

Summary

Align JustAi architecture and demo documentation with the actual explicit SafeMini adapter boundary.

  • retain Bubblewrap as the execution boundary supplied by JustAi
  • describe SafeMini built-ins as host-process policy guards, not a standalone sandbox
  • remove unsupported incident artifact and persisted SafeMini ledger claims
  • scope the lab results as deterministic reference evidence

Validation

  • git diff --check
  • PYTHONPATH=/home/justai/projects/safe-mini-worktrees/justai-executor-factory PYTHONDONTWRITEBYTECODE=1 /usr/bin/python3 -B -m pytest -q -p no:cacheprovider (626 passed, 14 subtests passed)

Non-goals

No runtime routing, dependency installation, service change, release, or product claim beyond source accuracy.

Align JustAi architecture and demo wording with the explicit Bubblewrap adapter and SafeMini's host-process policy guards.

Co-Authored-By: Codex <noreply@openai.com>
Copilot AI lite review requested due to automatic review settings August 10, 2026 13:54
@vercel

vercel Bot commented Aug 10, 2026

Copy link
Copy Markdown

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Actions Updated (UTC)
justai-demo Ready Ready Preview Aug 10, 2026 1:54pm

Request Review

@JustinJLeopard
JustinJLeopard merged commit 558a056 into demo-build Aug 10, 2026
3 checks passed
@JustinJLeopard
JustinJLeopard deleted the desktop-codex/docs/justai-execution-claims branch August 10, 2026 13:55

Copilot AI left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Updates repository documentation to accurately describe JustAi’s explicit SafeMini adapter boundary and to scope SafeMini’s built-in controls as host-process policy guards rather than a standalone sandbox.

Changes:

  • Reframes safe-mini as providing runner contract + policy guards (with in-memory transcripts), while JustAi supplies the Bubblewrap execution boundary.
  • Removes/tones down claims about incident artifacts, persisted ledgers, and over-broad sandbox guarantees.
  • Re-scopes lab results language as deterministic reference evidence rather than generalized isolation/performance claims.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 2 comments.

File Description
README.md Updates the three-repo architecture summary to reflect the explicit Bubblewrap boundary and in-memory transcript scope.
justai-demo-readme/README.md Revises demo-facing positioning to emphasize the bounded adapter and removes stronger sandbox/incident/ledger implications.
docs/ARCHITECTURE.md Aligns architectural description and responsibilities with the explicit adapter boundary and transcript-focused runner results.
Suppressed comments (1)

justai-demo-readme/README.md:69

  • This diagram uses "command-policy guard", but the rest of the docs refer to this control as a "command/path guard". Aligning the label reduces confusion when cross-referencing the architecture document.
                │  • command-policy guard                    │

💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.

**A thin project-orchestration layer with an explicit, bounded local-execution adapter for mini-swe-agent–style coding agents.**

JustAi sits between an engineering goal and the bash actions that fulfill it. It decomposes goals into chunks sized to a budgeted bash-action loop, dispatches each chunk through a sandboxed runner, classifies failures with a structured taxonomy, and learns from every run. The substrate underneath — `safe-mini` — is what makes the loop trustworthy on private repos: scoped worktrees, scrubbed environment, command/path guards, and an incident artifact for every action.
JustAi sits between an engineering goal and the bash actions that fulfill it. It decomposes goals into bounded chunks, applies checkpoints, and records control-plane results. Its explicit SafeMini adapter runs actions through JustAi's Bubblewrap boundary in a copied worktree. SafeMini itself contributes worktree copying, environment scrubbing, command-policy guards, and an in-memory run transcript; those policy controls are not a standalone sandbox.
Comment thread docs/ARCHITECTURE.md
- worktree provisioner
- command/path guard
- incident artifact writer
- in-memory transcript representation
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants