From 975d8a0ed2f03f34943282c0ca92cee51ecc65e9 Mon Sep 17 00:00:00 2001
From: Fusion Agent <noreply@runfusion.ai>
Date: Mon, 24 Aug 2026 21:20:23 +0000
Subject: [PATCH] test(FN-WF): stop non-review gates consuming a scenario's
 scripted review verdicts
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Two places in the pipeline-smoke mock treated any readonly, non-Plan-Review turn
as a Code Review, so on a review-column workflow the Documentation & Delivery gate
ate the verdict scripted for Code Review. S07 scripts
`codeReviewModes: ["empty-revise"]` to exercise an unactionable Code Review
rejection; the card instead died with `documentation-delivery: failed: REVISE`
before Code Review ever ran.

- `emitReview` classified everything that was not Plan Review as "code".
- The executor script forces `emitReview(context, "code")` whenever a readonly
  session coincides with scripted `codeReviewModes` — and a documentation gate is
  readonly too, so it took that branch as well.

Both now identify the executing step from the workflow-step system prompt
("You are a workflow step agent executing: <name>") and exclude the known
non-review gates. Detection is by EXCLUSION rather than an allow-list on purpose:
the real reviewer prompt does not carry the literal "Code Review", so allow-listing
silently approves every genuine review instead — measured, it turned S07 green on
`builtin:coding-ideas` for the wrong reason.

S07 on builtin:coding-ideas-v2 now gets past that misattribution and reaches the
review seal instead, which is a different and still-open problem, so the scenario
stays on its original workflows. Lane is green and faster than the previous
matrix: 6 files, 82 tests, 19/19 scenarios, 97.2s and 100.3s against the 150s
budget.
---
 .../pipeline-smoke/_pipeline-mock-scripts.ts  | 32 +++++++++++++++++--
 1 file changed, 30 insertions(+), 2 deletions(-)

diff --git a/packages/engine/src/__tests__/pipeline-smoke/_pipeline-mock-scripts.ts b/packages/engine/src/__tests__/pipeline-smoke/_pipeline-mock-scripts.ts
index 9649b04d8f..4f5f667eb3 100644
--- a/packages/engine/src/__tests__/pipeline-smoke/_pipeline-mock-scripts.ts
+++ b/packages/engine/src/__tests__/pipeline-smoke/_pipeline-mock-scripts.ts
@@ -143,11 +143,28 @@ export function installPipelineMockScripts(input: {
     input.observeMockRuntime();
     const systemPrompt = context.options.systemPrompt ?? "";
     const reviewKind = forcedKind ?? (
-      /^Execute the workflow step "Plan Review"/i.test(context.prompt)
+      /workflow step agent executing:\s*(?:Documentation & Delivery|Verification)\b/i.test(systemPrompt)
+        ? "non-review"
+        : /^Execute the workflow step "Plan Review"/i.test(context.prompt)
       || /workflow step agent executing:\s*Plan Review\b/i.test(systemPrompt)
         ? "plan"
         : "code"
     );
+    /*
+    FNXC:PipelineSmoke 2026-08-24-17:30:
+    Only a REAL review gate may consume a scenario's scripted verdicts. This classifier answered
+    "code" for anything that was not Plan Review, so on a review-column workflow the
+    Documentation & Delivery gate ate the verdict aimed at Code Review: S07 scripts
+    `codeReviewModes: ["empty-revise"]` to exercise an unactionable Code Review rejection, and the
+    card died with `documentation-delivery: failed: REVISE` before Code Review ever ran.
+    Detected on the workflow-step system prompt, which names the executing step, and by EXCLUSION
+    rather than an allow-list: the real reviewer prompt does not carry the literal "Code Review", so
+    allow-listing silently approves every genuine review instead.
+    */
+    if (reviewKind === "non-review") {
+      context.options.onText?.(JSON.stringify({ verdict: "APPROVE", notes: "Mock gate completed a non-review workflow step.", findings: [] }));
+      return;
+    }
     const modes = reviewKind === "plan"
       ? (behavior.planReviewModes ?? behavior.reviewModes ?? ["approve"])
       : (behavior.codeReviewModes ?? behavior.reviewModes ?? ["approve"]);
@@ -172,7 +189,18 @@ export function installPipelineMockScripts(input: {
         return;
       }
       const hasTaskUpdateTool = context.tools.some((tool) => tool.name === "fn_task_update");
-      if (!hasTaskUpdateTool && behavior.codeReviewModes) {
+      /*
+      FNXC:PipelineSmoke 2026-08-24-17:30:
+      ...but a NON-REVIEW gate also arrives readonly. Documentation & Delivery has no task-update
+      tool either, so this heuristic handed it the verdict scripted for Code Review: S07 scripts
+      `codeReviewModes: ["empty-revise"]` to exercise an unactionable Code Review rejection, and on a
+      review-column workflow the card instead died with `documentation-delivery: failed: REVISE`
+      before Code Review ever ran. Identify the executing step from the workflow-step system prompt
+      and let only a real review consume the scripted verdicts.
+      */
+      const executingNonReviewGate = /workflow step agent executing:\s*(?:Documentation & Delivery|Verification)\b/i
+        .test(context.options.systemPrompt ?? "");
+      if (!hasTaskUpdateTool && behavior.codeReviewModes && !executingNonReviewGate) {
         /*
         FNXC:PipelineSmoke 2026-08-23-20:23:
         Final Code Review can arrive on the executor runtime with a generic dispatch prompt. Its