Skip to content

docs: reflect current SafeMini runner source #4

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
JustinJLeopard merged 1 commit into from
Aug 10, 2026
Merged

docs: reflect current SafeMini runner source #4

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
15 changes: 12 additions & 3 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,7 +70,7 @@ Both are enforced inside the runner. Either axis can independently fire `BUDGET_
### From git (Phase A — current)

```bash
pip install 'safe-mini @ git+https://github.com/JustinJLeopard/safe-mini.git@v0.1.0'
pip install 'safe-mini @ git+https://github.com/JustinJLeopard/safe-mini.git@17c8514c1bf42d3064748400745099ca1723e782'
```

### From source (development)
Expand All @@ -95,7 +95,15 @@ pip install safe-mini # not yet published

## Status

**Current state:** initial scaffolding (`v0.1.0`, alpha). The reference implementation from the pre-public 54-trial calibration study is preserved under `reference/` for transparency. The production package under `safe_mini/` is currently a typed scaffold with the canonical types + AgentRunner Protocol locked in via tests; the SafeMiniRunner concrete implementation is the next port pass.
**Current source state:** alpha (package metadata `0.1.0`). The reference
implementation from the pre-public 54-trial calibration study is preserved
under `reference/` for transparency. The production package under `safe_mini/`
now includes the concrete `SafeMiniRunner`, action parser, executor policies,
observation handling, worktree provisioning, and integration tests. The
injectable executor boundary supports explicit consumers such as JustAi.

This records source integration only. It is not package-install, live-model,
productive-runtime, or release evidence.

**Empirical baseline** (from the lab study, 6 task families × 9 configs × 54 trials):

Expand All @@ -111,7 +119,8 @@ The lab study artifacts:
- `reference/lab_benchmark_tasks.py` — the 6-task corpus
- `reference/lab_benchmark_safe_mini.py` — the matrix-runner

These will be factored into the production package + the benchmark harness will move to the `local-resident` repo.
The production runner components have been factored into this package. The
benchmark harness remains separate work for `local-resident`.

## Three-repo architecture

Expand Down
Loading