@@ -10,12 +10,14 @@ All eight issues are in `codeabovelab/guardyx-gstack`. A/B placement within each
 
 | Pair | Real issue A / PR / base..head | Real issue B / PR / base..head | A method | B method |
 |---|---|---|---|---|
-| 1 — MCP discovery | [#556](https://github.com/codeabovelab/guardyx-gstack/issues/556) / PR pending / SHA pending | [#554](https://github.com/codeabovelab/guardyx-gstack/issues/554) / PR pending / SHA pending | Raw GitHub diff | codeboost |
+| 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 |
 | 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 |
 | 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 |
 | 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 |
 
-The pairs are matched before implementation on repository, primary implementation language, subsystem, and expected review surface. Pair 1 changes MCP discovery behavior; 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.
+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.
+
+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.
 
 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.