Skip to content

Commit d7f9b11

Browse files
committed
Verify experiment issues against current main
1 parent a36162c commit d7f9b11

1 file changed

Lines changed: 6 additions & 6 deletions

File tree

‎docs/experiments/review-protocol.md‎

Lines changed: 6 additions & 6 deletions
Original file line numberDiff line numberDiff line change
@@ -10,14 +10,14 @@ All eight issues are in `codeabovelab/guardyx-gstack`. A/B placement within each
1010

1111
| Pair | Real issue A / PR / base..head | Real issue B / PR / base..head | A method | B method |
1212
|---|---|---|---|---|
13-
| 1 — small backend reliability/reporting | [#335](https://github.com/codeabovelab/guardyx-gstack/issues/335) / PR pending / SHA pending | [#172](https://github.com/codeabovelab/guardyx-gstack/issues/172) / PR pending / SHA pending | Raw GitHub diff | codeboost |
14-
| 2 — companion documentation | [#493](https://github.com/codeabovelab/guardyx-gstack/issues/493) / PR pending / SHA pending | [#176](https://github.com/codeabovelab/guardyx-gstack/issues/176) / PR pending / SHA pending | codeboost | Raw GitHub diff |
15-
| 3 — agent-key security | [#506](https://github.com/codeabovelab/guardyx-gstack/issues/506) / PR pending / SHA pending | [#443](https://github.com/codeabovelab/guardyx-gstack/issues/443) / PR pending / SHA pending | Raw GitHub diff | codeboost |
16-
| 4 — compliance export | [#504](https://github.com/codeabovelab/guardyx-gstack/issues/504) / PR pending / SHA pending | [#503](https://github.com/codeabovelab/guardyx-gstack/issues/503) / PR pending / SHA pending | codeboost | Raw GitHub diff |
13+
| 1 — companion documentation | [#493](https://github.com/codeabovelab/guardyx-gstack/issues/493) / PR pending / SHA pending | [#176](https://github.com/codeabovelab/guardyx-gstack/issues/176) / PR pending / SHA pending | Raw GitHub diff | codeboost |
14+
| 2 — agent-key security | [#506](https://github.com/codeabovelab/guardyx-gstack/issues/506) / PR pending / SHA pending | [#443](https://github.com/codeabovelab/guardyx-gstack/issues/443) / PR pending / SHA pending | codeboost | Raw GitHub diff |
15+
| 3 — asynchronous notifications | [#13](https://github.com/codeabovelab/guardyx-gstack/issues/13) / PR pending / SHA pending | [#429](https://github.com/codeabovelab/guardyx-gstack/issues/429) / PR pending / SHA pending | Raw GitHub diff | codeboost |
16+
| 4 — compliance evidence | [#504](https://github.com/codeabovelab/guardyx-gstack/issues/504) / PR pending / SHA pending | [#507](https://github.com/codeabovelab/guardyx-gstack/issues/507) / PR pending / SHA pending | codeboost | Raw GitHub diff |
1717

18-
The pairs are matched before implementation on repository, primary implementation language, scope, and expected review surface. Pair 1 makes small Python backend changes with focused tests; pair 2 changes operational/compliance documentation without runtime behavior; pair 3 changes agent-key lifecycle across the API and UI; pair 4 adds per-invocation compliance evidence across export and PDF surfaces. If implementation discovery makes a pair materially unequal or blocked, stop before the first timed review and record a new frozen protocol revision rather than silently substituting an issue.
18+
The pairs are matched before implementation on repository, primary implementation language, scope, and expected review surface. Pair 1 changes operational/compliance documentation without runtime behavior; pair 2 changes agent-key lifecycle across the API and UI; pair 3 adds medium asynchronous notification delivery across backend jobs and consumer-facing interfaces; pair 4 adds compliance evidence across stored invocation data, exports, mapping data, and PDF surfaces. If implementation discovery makes a pair materially unequal or blocked, stop before the first timed review and record a new frozen protocol revision rather than silently substituting an issue.
1919

20-
Selection history: the first frozen draft paired #554 with #556. Before either implementation began, their required baseline check found that both depend on live 1,400-action/session telemetry unavailable from the operator's environment. They were replaced with #335 and #172, whose evidence can be reproduced locally. The replacement's A/B placement was randomized once; no timed review had started and no planted change existed.
20+
Selection history: the first frozen draft paired #554 with #556. Before either implementation began, their required baseline check found that both depend on live 1,400-action/session telemetry unavailable from the operator's environment. A proposed replacement included #335, but inspect-before-build then proved that `main` already contains its requested in-flight guard even though the issue remains open. A current-tree audit also excluded other stale open issues whose requested work has shipped. The table above contains only work confirmed absent from current `main`; every A/B placement was randomized after that audit. No timed review, experimental implementation, or plant had started before this final selection.
2121

2222
The reviewer must not implement the paired changes or inspect the plants before deciding on the PR. The operator must not expose plant inputs, `sealed.json`, mappings, planted locations, or unblinded implementation notes in the PR, review package, task messages, or protocol updates. An operator prepares plans and commits by hand, records trusted ledger ownership, and supplies both the plan and code to each review method. The earlier one-issue manual assignment is recorded in `manual-assignment.md`; all 12 segments were assigned and in scope, with no unclear case requiring another fixture.
2323

0 commit comments

Comments
 (0)