docs: bound execution and safety claims - #55
Merged
JustinJLeopard merged 1 commit intoAug 10, 2026
Conversation
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>
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
There was a problem hiding this comment.
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-minias 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. |
| - worktree provisioner | ||
| - command/path guard | ||
| - incident artifact writer | ||
| - in-memory transcript representation |
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
Align JustAi architecture and demo documentation with the actual explicit SafeMini adapter boundary.
Validation
Non-goals
No runtime routing, dependency installation, service change, release, or product claim beyond source accuracy.