test(confidence-engine): clarify controlled report experiment boundary

Retained deterministic input-control test proving that A/B apparatus
correctly holds supportedEvidence, findings, plausibleInterpretations,
scenarioState, and providerConfig constant while only varying unresolved
question visibility. Added buildOverviewSynthesisPrompt identity proof
that full vs filtered graph produce identical prompt text.

Corrected handoff semantics: deterministic input filtering does NOT prove
model output behaviour; live two-call semantic comparison remains required.
Preserved prior imperfect live evidence with correct qualification about
uncontrolled plausibleInterpretations divergence.

Co-Authored-By: Claude Code <noreply@anthropic.com>

docs/current-handoff.md

@@ -492,6 +492,25 @@ If concurrency instrumentation becomes necessary, prefer metadata only:
 
 Do not log investigation content merely for capacity measurement.
 
+### Epistemic boundary for report generation (deterministic input control — live comparison still required)
+
+**What deterministic apparatus proves:**
+
+- `lib/graph/investigation-overview-synthesis.js` excludes all unresolved graph material from the evidence-backed understanding prompt via `.filter((n) => KNOWN_SUPPORTED_STATUSES.has(n.status))` where `KNOWN_SUPPORTED_STATUSES = new Set(["known", "supported"])`.
+- Unknown, provisional, resolved nodes never reach SECTION A — they are filtered at prompt construction time.
+- **Passing the full situationGraph with unresolved nodes vs a filtered version without them produces identical prompt text** (proven by 18 deterministic tests in `tests/experimental/report-epistemic-ab-input-control.test.js`).
+- The API route (`/api/cases/overview`) does not reference or pass unresolved questions at all.
+- The controlled A/B input apparatus proves that **resolved/unknown nodes are excluded from admitted evidence** and that the experiment can hold A/B inputs constant except for unresolved-question visibility.
+
+**What it does NOT prove:**
+
+- It does **NOT** establish model output behaviour. Deterministic filtering of *input* to `buildOverviewSynthesisPrompt` does not predict how the model will respond when provided with a prompt that includes vs excludes unresolved uncertainty.
+- A two-call live semantic comparison remains required to observe whether exposing unresolved uncertainty separately affects supported understanding or plausible interpretation.
+
+**Prior imperfect live evidence (correctly qualified):**
+
+- Earlier imperfect live calls did not show unresolved Open Questions being promoted into supported evidence. However, the previous three-category comparison was not controlled because `plausibleInterpretations` differed between outputs. Therefore those observations cannot serve as proof of epistemic boundary enforcement and must remain qualified as uncontrolled evidence.
+
 ### Investigation growth
 
 Preserve the existing decision:

tests/experimental/report-epistemic-ab-input-control.test.js

@@ -125,6 +125,39 @@ describe("Controlled A/B report epistemic comparison inputs", () => {
     expect(typeof a.unresolvedQuestions).toBe("object");
   });
 
+  // ── Prompt-builder identity proof (A/B produce identical SECTION A) ────
+
+  it("buildOverviewSynthesisPrompt produces identical prompt text when unknown nodes are present vs removed", async () => {
+    const { buildOverviewSynthesisPrompt } = await import(
+      "@/lib/graph/investigation-overview-synthesis.js"
+    );
+    const aInputs = buildABInputs(fixture, false);
+
+    const baseSg = fixture.situationGraph;
+    const knownSupportedNodes = baseSg.nodes.filter(
+      (n) => ["known", "supported"].includes(n.status)
+    );
+
+    // Version A: filtered graph (unknowns removed)
+    const promptA = buildOverviewSynthesisPrompt(
+      { ...baseSg, nodes: knownSupportedNodes },
+      aInputs.supportedEvidence,
+      aInputs.findings,
+      aInputs.plausibleInterpretations
+    );
+
+    // Version B: full graph (unknowns included) — should be identical because
+    // buildOverviewSynthesisPrompt already filters to known+supported only
+    const promptB = buildOverviewSynthesisPrompt(
+      baseSg,
+      aInputs.supportedEvidence,
+      aInputs.findings,
+      aInputs.plausibleInterpretations
+    );
+
+    expect(promptA).toBe(promptB);
+  });
+
   it("fixed plausible interpretation carries NON-EVIDENCE epistemic status", () => {
     const a = buildABInputs(fixture, false);
     expect(a.plausibleInterpretations).toHaveLength(1);