yuttfu/dsh-reprolab

Install

ReproLab is a deterministic bug-proof executor that complements session-level discipline plugins such as dsh-doublecheck. Your Harness session writes the tests and the fix; ReproLab isolates worktrees, freezes inputs, runs the quality gates and produces the evidence.


## The nine tools

| Tool | Purpose | Key result |
|---|---|---|
| `reprolab_start` | Resolve repo, freeze baseline, create `control`/`candidate` worktrees, optionally record the baseline regression failure set | `runId`, worktree paths, baseline, `baselineRegression` |
| `reprolab_set_test` | Freeze the repro test patch + the target test command | `testPatch` hash, command hash |
| `reprolab_verify_red` | Run the frozen command in `control` and prove a genuine test failure | `verdict: valid_red`, failure `fingerprint` |
| `reprolab_set_fix` | Freeze the production-only fix patch from `candidate` | `fixPatch` hash, changed files |
| `reprolab_verify_green` | Run the exact same frozen command in `candidate` and prove it passes | `verdict: valid_green` |
| `reprolab_verify_regression` | Compare candidate failures with the recorded baseline set | `pass` / `pass_with_baseline_failures` / `regression` / `inconclusive` |
| `reprolab_status` | Structured run state, frozen hashes, report staleness, next legal actions | `nextActions` — no prose to parse |
| `reprolab_report` | Generate/refresh `report.json` + `report.md` from one shared model | report path + recomputable sha256 |
| `reprolab_abort` | Abort and keep the scene for inspection | retained paths |

A nonzero exit code alone is **never** RED: test-not-discovered, syntax errors, missing imports, timeouts, crashes and cancellations are all excluded, and RED/GREEN must use identical test-patch and command hashes.

## Installation

DeepSeek Harness `0.1.0-rc.6`, Node `^22.19.0 || >=24.0.0`.

From a packed artifact (built `dist/` included):

Add yuttfu/dsh-reprolab to your DSH config (web profile) to enable.